energies

Article
Predicting and Forecasting of Vehicle Charging Station Using
ECNN with DHFO Algorithm
Rosebell Paul * and Mercy Paul Selvan

Department of Computer Science and Engineering, School of Computing, Sathyabhama Institute of Science and
Technology, Chennai 600119, India; [Link]@[Link]
* Correspondence: rosebellabin@[Link]

Abstract: The forecast of the optimal placement of a charging station (CS) according to the real-time
consumption of electric vehicles is a subject of urgency in this new era. The demand of a charging
station in an area based on the trend of consumption can be predicted by means of interpolation
and the extrapolation of historical data using a linear function of prediction model. The prediction
of the charging station system was performed with distance relevancy methods. An adaptive
optimal learning model was proposed to enhance the prediction performance for charging station
management and to represent the pattern of vehicles’ travelling directions. The proposed model
uses Distributional Homogeneity Feature Optimization (DHFO) using artificial intelligence (AI)
to categorize and forecast the charging station from the database. The prediction performance
of this model is improved more than the conventional classification model by filtering the apt
features from all the electric vehicular and charging station attributes in the database. The Enhanced
Cladistic Neural Network (ECNN) is used to improve the pattern learning model and increase
learning accuracy. By comparing statistical parameters with other state-of-the-art methodologies, the
suggested model’s overall findings were verified.

Keywords: vehicle charging station prediction; forecasting data; Distributional Homogeneity Feature
Optimization (DHFO); Enhanced Cladistic Neural Network (ECNN)

Citation: Paul, R.; Selvan, M.P.

Predicting and Forecasting of Vehicle
Charging Station Using ECNN with
1. Introduction
DHFO Algorithm. Energies 2024, 17,
4308. [Link]
Faster electric vehicle (EV) adoption all over the world aims to achieve the decarbona-
en17174308 tion of the entire planet, thereby making Earth a safer and more sustainable place to live.
Various research has been conducted all over the world to examine the biggest challenges
Academic Editors: Marianna Jacyna,
faced by the automobile industry during this transition phase. The range anxiety is the
Emilian Szczepański and
greatest hindrance for all EV users. The uncertainty of running out of battery power during
Mariusz Izdebski
journeys is the predominant barrier for this quantum change. A myriad of conditional
Received: 31 July 2024 factors were reviewed depending on environmental, economic, social, and technical aspects
Revised: 21 August 2024 to resolve this situation. The installation of power supplies at apt locations will reduce the
Accepted: 26 August 2024 fear of EV users of running out of power. This paved the way for studies and experiments
Published: 28 August 2024 to be carried out on the prediction of EV users’ behavior and the optimal placement of
charging stations.
Numerous systems are available to forecast the way an electric vehicle will approach
a charging station by monitoring the State of the Charge (SOC) of the vehicle [1]. The
Copyright: © 2024 by the authors.
SOC of the vehicle depends on several environmental and vehicle parameters. It gives an
Licensee MDPI, Basel, Switzerland.
indication of the maximum range that can be covered by a vehicle and helps it to recognize
This article is an open access article
when it is in urgent need of charge. Machine learning algorithms can carry out the forecast
distributed under the terms and
process to identify available charging stations using vehicle historical data. The charging
conditions of the Creative Commons
stations may not be the most optimal ones as there can be multiple issues while tracking
Attribution (CC BY) license (https://
[Link]/licenses/by/
the vehicle’s range, traffic conditions, and maximum charging capacity of the charging
4.0/).
station, as discussed in [2]. This causes the charging station prediction and other vehicle

Energies 2024, 17, 4308. [Link] [Link]

Energies 2024, 17, 4308 2 of 25

routing processes to be misclassified. To get around that, the charging station prediction
was followed by a historical data reference for relevancy. Apart from that, the lack of
sufficient numbers of charging stations is a primary concern hindering the growth of EV
adoption. This has triggered the necessity of installing new charging stations. Hence, the
identification of the most suitable location for the same is a challenging task.
The Multi-Objective Optimal Placement model is ideally based on the above percep-
tions to develop an optimal charging station prediction for EV users. The Multi-Objective
Optimal Placement model mainly concentrates on three stages—vehicle allocation, vehicle
count selection, and end-user vehicle node placement. In this, the vehicle allocation defines
the cluster-based coverage area computation of EVs that is in the proximity of the CS.
Based on the vehicle distance to the CS and the power requirement, the parameters are
validated and assigned to the best CS. The vehicle count selection takes into consideration
the traffic conditions that are to be matched against the maximum charging capacity of the
CS. This will select the number of vehicles that can be mapped with the available CS by
comparing the available power of the CS along with the requirement of the EV to charge.
The end-user vehicle node-based optimal placement refers to the parameters of the electric
vehicle that will meet the criteria such as State of the Charge (SOC), based on the power
demand, distance to travel, availability of terminals, and capacity of CS. Based on these
three stages of the optimization model, the vehicle can identify the best place to charge the
vehicle with minimum service time.
The proposed system takes into consideration the three stages of the Multi-Objective
Optimal Placement model in its design to predict the most optimal charging station from
the available ones for an electric vehicle, and forecasts the most suitable location to install
a new charging station, taking only the most necessary vehicle parameter values into
account. The study in [2] revealed that historical data for an area also play a prominent
role in developing an advanced model of feature prediction, and these are adopted in the
proposed classification system. To improve the prediction model, an optimization method
was used to forecast the data pattern feature analysis [3] from the vehicle data samples and
the weight input properties, which led to the selection of the best attributes. To improve
the classification performance and increase prediction accuracy, an adequate amount of
data samples were taken during the training process for forecasting the power demand as
studied in [4].
As in a linear function, a straight line was drawn to predict values outside the dataset—in
the proposed system, the route path of the EV from an origin to destination is the standard
baseline taken. The prediction of the available charging station system was then performed
with the distance relevancy methods across this line. The power demand of the charging
station in an area based on the power consumption rate and the vehicle density can be
predicted by means of interpolation and the extrapolation of the historical data using the
linear function of prediction model. An adaptive optimal learning model was proposed to
enhance the performance of prediction of the most apt charging station from the available
ones, and the pattern of vehicle movement in the travelling direction was the primary
source of data pattern, along with charging station parameters and power demand. This
pattern of EV movement and its intersection across the baseline O-D Trip formed the core
computation of the prediction. The proposed model used Distributional Homogeneity
Feature Optimization (DHFO) and artificial intelligence (AI) to obtain the optimal feature
selection for this prediction. The prediction performance of this model was improved more
than the conventional classification model by filtering the apt features from all the electric
vehicular and charging station attributes in the database. The Enhanced Cladistic Neural
Network (ECNN) was then used to improve the pattern learning model and increase
learning accuracy to forecast the co-ordinate positions for the installation of a charging
station. The pattern analysis for forecasting the co-ordinates of the new charging station
mainly concentrated on the power demand of the existing charging stations, along with
their availability. By comparing these statistical parameters with other state-of-the-art
methodologies, the suggested model’s overall findings have been verified.
Energies 2024, 17, 4308 3 of 25

The following are the main highlights of the proposed framework:

• Distributional Homogeneity Feature Optimization (DHFO) technique, which is a novel
optimal feature selection system for vehicle parameters required for the prediction of
an apt location for a charging station for an EV, was developed;
• The classification performance was enhanced by organizing the best feature properties
that were pertinent to the data;
• The weight and vehicle type of feature attributes were used to anticipate and predict
the range of charging station site forecast based on the state of power demand;
• An Enhanced Cladistic Neural Network (ECNN) classifier was implemented for the
classification approach;
• The performance of the proposed classification model was validated based on the
statistical parameters, and the comparison was conducted with existing approaches.
The overall organization of the paper is as follows. Section 2 examines the various op-
timization techniques for the Optimal Placement Model to determine the optimal charging
station direction selection. The working model of the suggested ECNN with the DHFO
optimization algorithm for the optimal charging station direction selection is described in
Section 3. Section 4 provides an explanation of the simulation graph charts and validation
of the outcomes of the suggested model, along with the comparison results. Section 5
concludes with a discussion of the paper’s work and potential improvements.

2. Related Works
This section provides a comprehensive overview of the current techniques for forecast-
ing data and predicting charging stations for electric vehicles The challenges and limitations
inferred from these studies, which paved the way to scope out further research, have been
summarized in Figure 1. Most of the recent techniques mainly give emphasis to socioeco-
nomic and environmental factors, but vehicle density and state of charge play dominant
roles and need to be considered. A study of the influence of the social, economic, and envi-
ronmental factors on the identification of the charging station location was made in [4–7].
The work [4] proposed a suitable ranking system based on the above influencing factors
but lacks the detailing on the technical aspects such as the electric demand and state of
charge of the vehicles travelling a particular path that may affect the forecasting of optimal
charging station placement. The Charging Station Allocation Data were approximated
using the time series and data samples from the Charging Station Time Chart in [8]. In
doing so, the production analysis in the basin-scale vehicle level allocation model makes
use of the OSM data samples. This also refers to the variation in charging power and the
availability forecast based on dataset history. In [9], a gravity-dependent Huff model was
described, taking into consideration Sioux-Fall network for illustration. The study’s main
focus is from the perspective of a private investor of in a charging station and leverages an
optimal pricing strategy. A dynamic pricing strategy based on the Markov decision process
and multi-agent neural network was proposed in [10]. The study suggested that charging
during off-peak times could be more cost effective. In [11], graph-based computations were
used for the maximum comfort and ease of EV users. The schedule time of route flow was
predicted in this work using data modeling from short-term availability forecasts. This was
operated based on historical data samples for station power and demand characteristics, as
well as availability.
 Energies
Energies 2024,2024, 17, x FOR PEER REVIEW
17, 4308 4 of 26
4 of 25

[Link]
Figure Summaryof
of recent
recent approaches
approaches forforEVEVcharging
chargingstation prediction
station with
prediction details
with of dataset,
details of dataset,
algorithms, and limitations (Refs. [2–4,8–25]).
algorithms, and limitations (Refs. [2–4,8–25]).

Basedon
Based onthe
theavailable
available data
data and
anddemand
demandforecast,
forecast, Ref. [12]
Ref. developed
[12] developed a station avail-
a station avail-
ability retrieval model. This analyzed various classification models to compare
ability retrieval model. This analyzed various classification models to compare the efficacy the efficacy
ofofclassification
classification based
based ononstatistical variables
statistical andand
variables to estimate station
to estimate availability
station from sat-
availability from
ellite data. The behavior pa ern of EV users for charging was thoroughly analyzed in
satellite data. The behavior pattern of EV users for charging was thoroughly analyzed
[13,26–28]. The cost of land invested in by the operators was also taken into consideration
in [13,26–28]. The cost of land invested in by the operators was also taken into consideration
for predicting the best charging station location. These are all forecasted based on the
for predicting the best charging station location. These are all forecasted based on the power
power consumption and availability factors for the various station availability circum-
consumption and availability factors for the various station availability circumstances, but
stances, but lack vehicle parameters and SoC detailing. In a similar vein, Ref. [14] put forth
lack vehicle parameters and SoC detailing. In a similar vein, Ref. [14] put forth a prediction
a prediction model for the SOC level in the charging station that considered the uncon-
model
trolledforpower
the SOC
losslevel in the
and the charging
unequal station that
distribution considered
of the availablethe uncontrolled
content power loss
load. According
and the unequal distribution of the available content load. According
to this prediction, after the flooding effect, the status of the station will increase the rangeto this prediction,
after the flooding
of SOC > 6.5 to aeffect,
maximum the status of 7.
value of theThe
station will increase
construction of the the rangestation
charging of SOCat>the 6.5 to
a proper
maximum station is improved by this estimation. With this improvement in mind, Ref. [15] is
value of 7. The construction of the charging station at the proper station
suggestedby
improved a power logging prediction
this estimation. With thismodel for the charging
improvement in mind, station fieldsuggested
Ref. [15] to supply route
a power
flow-level data. This helps to grow the charging station in the field more by estimating theThis
logging prediction model for the charging station field to supply route flow-level data.
amount
helps of power
to grow supply and
the charging other associated
station in the fieldfeatures
more by based on the power
estimating level. A of
the amount CNNpower
feature-based path planner for EV was studied in [29]. Based on the traffic flow the waitingpath
supply and other associated features based on the power level. A CNN feature-based
time tofor
planner become
EV wascharged
studiedwasinpredicted.
[29]. BasedThis
oncan
thebe usedflow
traffic in further studiestime
the waiting to track the
to become
most suitable
charged CS when the
was predicted. SOC
This canofbe
a vehicle
used ingets below
further the minimum
studies to trackthreshold.
the most suitable CS
when the SOC of a vehicle gets below the minimum threshold.
Several additional techniques have improved the construction range and the other
decision plan based on the forecasting data and the station parameter prediction process.
Based on this, Ref. [30] suggested using an optimization model to estimate the quality of
Energies 2024, 17, 4308 5 of 25

charging stations as a decision support for corridors. This validates the power availability
for the public in highways as special segment of highways are corridors dedicated to EV
charging. It classified the CS in corridors as better locations than other CSs. The vehicle
level quality was determined by the fuzzy interference system, which also segments each
division independently. But this study is suitable only for high density traffic areas. Ref. [17]
presented the estimation of geographical variance in the field of land used for charging
station installation. During power fills, this forecasts the SOC level of the car. To forecast
what kind of car-level charging station can develop there, this also assesses the redox
condition of the station. Ref. [18] converted double-layer vehicle levels to ratoon charging
station fields to lessen carbon emissions and enhance ecosystem benefits. This will result in
a higher annual yield, lower demand, and lower car battery charging costs because of the
ratoon vehicle-level (RV) technology. The analytical report of CS construction was used to
analyze this together with various data points in the entire article.
Numerous techniques are aimed at estimating the necessity of CSs taking into consid-
eration the OD (Origin Destination) trip and SOC level of the vehicles [17]. Considering
this, Ref. [19] suggested a model to allocate optimal CSs for the bus network in Toronto.
Depending on the vehicle-level SOC cycle and bus trip route, the fastest charging time with
minimum cost was assured. An additional state-of-prediction for determining the allocation
of discharge according to station characteristics, vehicle range estimation, and battery SOC
conditions was the focus of [20,31]. To make the best choice from the available charging
stations, the range of an electric vehicle is forecasted based on a fuzzy classifier. This study
provided a report of the maximum distance an EV can travel to reach the most suitable
charging station. An intelligent route flow system to increase the CSs based on weight and
station availability-level projected from the user preference features was proposed by the
author in [32]. Based on the remote sensing data, Ref. [21] suggested a city-level prediction
for the deployment of charging stations with a minimum budget. The study gave priority
to socioeconomic factors such as customer satisfaction, as well as population density. Using
the combination of deep learning with phenological properties, this was estimated and
forecasted [33]. An optimal placement of charging station in distribution networks was
suggested in [22]. To safeguard the charging station CS, the author of [34] provided research
based on several charging station discharge categorization models. The suggested model
was a data-based station range prediction based on the station’s availability, the cost value
of the station’s power demand, and other pertinent aspects and parameters. A business
approach to a charging station was proposed in [23]. This study led to the motivation of
finding the most optimal placement of charging station, but the technical aspects of the
prediction algorithm for the same was not elaborated. Although the battery swapping
method as in [35,36] is a great trend these days, taking into consideration the time, it may
not be practical in all adverse scenarios. A time series-based approach was discussed in [37]
regarding charging demand, but the optimal placement of CS is not suggested in that study.
All the studies discussed so far may mainly be categorized into the following domains
based on the decision parameters affecting EVs and their charging stations: power distribu-
tion, socioeconomic–environmental factors, EV vehicle, CS parameters, and geographical–
topological factors. Most of the studies summarized in the existing literature are based on a
plethora of features which are specific to regions. The datasets used by most of the studies
are real-time or recorded transportation data focused on a particular town or country, taking
into consideration the attribute features of that region. A thorough study was conducted
based on the literature summarized above to identify the constraints in each of the specified
domains as listed in Figure 1. The traffic and vehicle parameters play a prominent role
as influencing factors in all situations. Based on these features, a new optimal prediction
system was proposed in our study. The most significant features and their relationship to
computing the demand of CSs are discussed in detail in the next section. The proposed
framework enhances the accuracy of predicting the best CS from existing ones, as well as
forecasting the optimal location for installing a CS, taking into consideration the electric
Energies 2024, 17, 4308 6 of 25

vehicle parameter features obtained from the dynamic tracking of vehicle movements, as
well as its State of Charge.
The CS characteristics such as power demand, charging piles, as well as frequency of
vehicle occurrences and the distance to reach the CS, are also considered. The forecasting
model of the CS represents the best location to place a new CS based on the parameters
of power demand, frequency of vehicle occurrences, availability of existing CS, and the
peak time of vehicle visits. This will predict the best location for placement of CS according
to the suggested co-ordinate positions. For this purpose, cutting-edge techniques like the
Enhanced Cladistic Neural Network (ECNN) and the Ensemble Modulation Pattern (EMP)
system are recommended.

3. Proposed Methodology
This section explains the proposed procedure of the optimal charging station prediction
and forecasting model. When an EV travels from an origin to its destination, its initial co-
ordinate positions are initialised based on the OSM data samples. As its journey continues,
the state of charge (SOC) of the vehicle decreases and the distance that it can travel depends
on vehicle parameters such as its battery make—lithium or hybrid—as well as battery
power capacity, driving speed, and the traffic density. The existing charging stations near to
the EV current position are made available to the EV. The cluster similarity measures form
a cluster of CS where EV can place a charging request when the EV battery has a minimum
SOC. Vehicles may prefer level1, level2, or DC fast charging, depending on its capability
and charger compatibility. Each charging station has its own charging capacity which is
divided into the available charging piles. Hence, the demand of a charging station depends
on the availability of the number of charging piles, as well as its maximum charging
capacity. That is, if a charging station has a maximum of 100 kW and two charging piles,
then the charging capacity of that charging station is restricted to a maximum of 50 kW per
pile. Hence the vehicle approaching the charging station must ensure this power demand
of the CS by checking if the charging piles are available and other EVs are not plugged in at
the station.
The demand of CS is computed based on the generated dataset which takes into
consideration the number of charging piles, vehicle density, cost, and charging capacity of
the charging station.
The power demand ‘PD ’ in a charging station can be calculated by referring to the
below equation.
PD = (VC × β × R) − C
where, VC —Vehicle Count (number of vehicles that are connected in the piles in individual CS).
β—Power constant for charging a vehicle.
R—Random value to represent the power consumption of each EV vehicle that are
connected to the piles of a CS. Each vehicle will consume different amounts of power
based on the battery state and the range of battery, therefore, a random value will refer to
the different amount of power consumption for connected EVs, along with the charging
constant ‘β’.
C—Total capacity of CS that is the ability to supply power to the connected EVs in
the piles.
This demand value, if negative, indicates that some piles are empty and vehicles can
be connected to the CS. On the other hand, if the demand value is positive, it indicates that
the charging stations are fully occupied, and then, based on the historical data and pattern
of the feature attributes taken into account in the study, a new charging station location is
recommended within the coverage area of that EV. Thus, the forecasting of the CS is based
on the vehicle demand and the CS availability, as well as recognizing the area where the
vehicle cannot reach the CS with its minimum SOC of battery level.
This prediction is computed using the ECNN algorithm which performs a pattern
analysis while tracking the dynamic movement of the EV to available CS with respect to
time and the SOC parameters. SOC parameters mainly refer to the percentage of SOC
 CS is based on the vehicle demand and the CS availability, as well as recognizing the area
where the vehicle cannot reach the CS with its minimum SOC of ba ery level.
This prediction is computed using the ECNN algorithm which performs a pa ern
Energies 2024, 17, 4308
analysis while tracking the dynamic movement of the EV to available CS with respect to
7 of 25
time and the SOC parameters. SOC parameters mainly refer to the percentage of SOC
ba ery level and the distance that can be covered by that EV to a CS. This distance varies
from time to time as it depends on the vehicle parameters such as the ba ery make and
battery level and the distance that can be covered by that EV to a CS. This distance varies
capacity,
from time driving
to timespeed, and traffic.
as it depends Hence
on the the parameters
vehicle proposed system
such aspredicts the make
the battery optimal andCS
for
capacity, driving speed, and traffic. Hence the proposed system predicts the optimal CS aforCS
an EV, and if the CS is already occupied it forecasts an optimal location to install
inanthe
EV,future.
and if the CS is already occupied it forecasts an optimal location to install a CS in
Figure 2 displays the main architecture diagram for the proposed charging station
the future.
prediction
Figuremodel. The methodology
2 displays is divided
the main architecture into three
diagram main
for the stages which
proposed are station
charging labelled
inprediction
the Figure 2.
model. The methodology is divided into three main stages which are labelled in
the Figure 2.

Architectureshowcasing
[Link]
Figure showcasing the
the three
three main
main phases
phasesofofthe
thesystem:
system:initialization,
initialization,DHFO,
DHFO,and
and
ECNN algorithm.
ECNN algorithm.

The first stage is the architecture initialization where the source and destination of the
The first stage is the architecture initialization where the source and destination of
path to be travelled by the user are initialized, along with all the necessary vehicle parameters.
the path to be travelled by the user are initialized, along with all the necessary vehicle
The second stage comprises the DHFO algorithm which mainly concentrates on the
parameters.
optimal feature selection based on the demand computation and vehicle parameters. It
The second
recognizes stage comprises
the geographical the DHFOofalgorithm
co-ordinates the CS that which mainly can
the vehicle concentrates
reach with onits
the
optimal
minimum feature
SOC of selection basedThe
battery level. on cluster
the demand computation
similarity measures formand vehicle
a clusterparameters.
of CS where It
recognizes the geographical co-ordinates of the CS that
EV can place a charging request when the EV battery has minimal SOC. the vehicle can reach with its min-
imumIn SOC of ba ery level. The cluster similarity measures form
the third stage, the Enhanced Cladistic Neural Network (ECNN) technique a cluster of CS where EV
op-
can place a charging request when the EV ba ery has minimal SOC.
timizes the clustering and feature selection, and makes the final prediction. The ECNN
In the third
algorithm stage, the
preprocesses theEnhanced Cladistic
testing weight data Neural
using the Network
concept(ECNN) techniqueThe
of normalization. opti-
mizes the clustering
preprocessed and feature
data blocks selection,
are then split intoand makes
groups the final
to extract prediction.
data [Link] ECNN
Every blockal-
gorithm
group ispreprocesses
then subjected the
to testing weightModulation
the Ensemble data using Pattern
the concept
(EMP).of This
normalization. The pre-
efficiently extracts
processed data blocks are then split into groups to extract data pa erns. Every block group
geometrical characteristics to raise the general level of classification accuracy. Finally, the
isclassifier
then subjected to the
is utilized Ensemble
to classify Modulation
whether Pa ern
the location ID (EMP). Thiswith
is satisfied efficiently extracts
the relevance geo-
ratio
metrical characteristics
or not. The to raise
relevance ratio the general
defines the ratiolevel of classification
between the number accuracy.
of known Finally, the the
values and clas-
sifier is utilized
predicted valuestoofclassify
the datawhether
samples. the location ID is satisfied with the relevance ratio or
Thus, the entire forecasting of the CS is based on the power demand and availability
of the CS, and the recognition of the area where the vehicle cannot reach the CS with its
minimum SOC of battery level. The cluster similarity measures form a cluster of CS where
EV can place a charging request when the EV battery has minimal SOC. This will predict
 EV can place a charging request when the EV ba ery has minimal SOC. This will pr
the best location for the placement of a CS by suggesting geographical co-ordinate
tions extracted using a map matched tool. Figure 3 is the flowchart of the proposed
tem.
Energies 2024, 17, 4308 8 of 25
The proposed algorithms are explained in depth in the ensuing subsections.
Section 3.1: Distributional Homogeneity Feature Optimization (DHFO);
Section
the best 3.2:
location forEnhanced Cladistic
the placement Neural
of a CS by Network
suggesting (ECNN)
geographical Algorithm.
co-ordinate positions
extracted using a map matched tool. Figure 3 is the flowchart of the proposed system.

Figure 3. Flowchart of the proposed system.

Figure 3. Flowchart of the proposed system.
The proposed algorithms are explained in depth in the ensuing subsections.
3.1. Distributional Homogeneity
Section 3.1: Distributional Feature Optimization
Homogeneity (DHFO)(DHFO);
Feature Optimization
The Distributional Homogeneity Feature Optimization is a multi-objective optim
Section 3.2: Enhanced Cladistic Neural Network (ECNN) Algorithm.

tion
3.1. Distributionalwhich
algorithm uses Feature
Homogeneity the various parameters
Optimization (DHFO) in different objective conditions
nalizeThethe most suitable
Distributional combination
Homogeneity FeatureofOptimization
parametersis that will enhance
a multi-objective the classific
optimiza-
accuracy. Here,
tion algorithm the optimization
which uses the various algorithm
parameters is in
used to reduce
different the conditions
objective size of feature
to data
(before training) of a classifier to enhance the prediction performance. For that, the
finalize the most suitable combination of parameters that will enhance the classification
of the DHFO
accuracy. Here, optimization
the optimizationalgorithm
algorithm isisused
the to full datathe
reduce ofsize
theoftraining feature set. A
feature database
(before training) of a classifier to enhance the prediction performance. For that, the input of
scribed in the algorithm below, the input is the geographical co-ordinates of the ve
the DHFO optimization algorithm is the full data of the training feature set. As described in
obtained from
the algorithm the the
below, OSM Data
input Samples
is the andco-ordinates
geographical Demand Cost of the(𝑀 )] obtained
vehicle (the entire
fromchargin
tion parameters
the OSM as inand
Data Samples Figure
Demand 4) ofCost
randomly generated
(M N ID ) (the CS. From
entire charging these
station inputs, the ou
parameters
of
asthe DHFO
in Figure 4) algorithm
of randomlyisgenerated
the optimal selected
CS. From thesefeature
inputs, atheributes
output among
of the DHFOthe overall
base. Based on the selected indexes of the training database, the selectedona ribute
algorithm is the optimal selected feature attributes among the overall database. Based
the selected indexes of the training database, the selected attributes are passed as the input
passed as the input for the classifier in both the training and testing processes.
for the classifier in both the training and testing processes.
In Algorithm 1, the multi-objective DHFO method’s precise steps and equation model
are made available. To construct the root direction, the input was selected as the co-ordinate
position of the available charging stations, and the starting direction was formed based on
 Energies 2024, 17, 4308 9 of 25

the vehicle’s geographic latitude–longitude co-ordinates setting of 0.5 if the link difference
obtained from the datapoints was less than the defined range as in algorithm below. The
coverage area for the randomly allocated CS location in terms of latitude and longitude was
24, 17, x FOR PEER REVIEW ±0.5 from the route path co-ordinate position of EV movement. The number 12 ofof26divisions
to allocate the random CS was specified as 10 numbers which split the CS location into
different positions. These randomly allocated CS contained the additional parameters along
with the latitude and longitude, such as total capacity (kW), number of charging piles, cost
was chosen. The(Pstraining
per kWh),model of the
vehicle ECNN
count was
already used to classify
connected to the CSthe classes
piles, of live demand
and power mov- in the
ing vehicle parameters.
CS (kW).

Figure 4. Initialized table

Figure of demand
4. Initialized data.
table of demand data.

3.2.3. Train Test Split

Each charging station contained an individual range of all these listed parameters.
The final These
phaseformed the training database for the classifier to define the available CS with/without
in preprocessing is to split the dataset into train and test sets. The
power demand.
process of spli ing the dataset is a typical phase in learning algorithms to address over-
The initial value of SOC was set at 20%. The distance covered by the car in terms of
fi ing and for evaluating the performance
SOC was defined as EV-km-perofSOC
the Unit,
trained model
being properly
1.5. The criticalon unseen
value data.
of SOC was 5. This
In the proposed work, the dataset was split in the ratio of 70:30, where 70% was used
was followed by the feature pattern analysis method to extract the most suitable for features
training and remaining 30%ofwas
for prediction aptretained
CS using for
the model testing.
population strength of the vehicle which was generated
in this study along with the power capacity of the vehicle that was connected to the electric
3.2.4. Classification Model
vehicle Description
model.
In this process,The
thesize
ECNNof the
is dataset for theclassifier
a multi-level N numberused
of attributes in this caseof
for the prediction is the
the best
RN database
model. The total dataset size is expressed in terms of M. The key relevancy prediction be-
location for a charging station based on the feature a ributes that are collected from the
tween feature characteristics is represented by the matrix Ki and Kj . Next, wdx , wdy , and wdxy
parameters of the CS and EV. The classification result from the ECNN is the prediction of
are the particle parameters of Ki and K j . As indicated by the following equations, the binary
the nearest CS representation
location in theofroute
these path based on the parameters
calculated asofMSOC, Km can travel
particles is similarly xy , Nxy and Nyx .
by vehicle, Cost of CS, and Demand in (KW). If there was no CS predicted
The demand cost matrix represents the Euclidean distance between in the coverage
each demand
area of the current
valuemoving
arrangedvehicle, then of
in the form this recommended
a square matrix. Inthe location
this, of CS
Equations (1)based
and (2)onrepresent
the demand levelthe and the distance
availability matrixtoand
thethe
CSresponsibility
in the coverage area.
matrix, The labels for
respectively, thatthe
are con-of ‘i’ and
index
sidered for the‘j’.
classification are: matrix is evaluated with the demand cost and with the responsibility
This availability
(a) CS stationmatrix to refresh the matrix based on the update of vehicle availability.
available with sufficient power to charge the EV—Class 1;
(b) CS station available with power demand  (KW)—Class 2;
0.5, i f ( M N ID (i, j) <= 0.5)
(c) CS station not available—Class 3; Aij = 0, Otherwise
(1)
(i) Recommend new CS station;
(ii) Recommend the longitude andMlatitude of Anew CS
I f station.


N ID (i, j ) − ij Aij <= M N ID (i, j)
Rij = (2)
Otherwise
These classes are defined by the training set0for the classifier extracted from the pa-
rameters of the CS and EV. These parameters are arranged in the form of feature a ributes
to construct the training model for the classifier. This training model will be a one-time
process while installing the system on the manufacturing side. While driving the EV, the
parameters from the live running vehicle will be arranged as the testing feature vector. At
this testing stage, the parameters from each time point are used as the input to the classi-
fier for testing. The classifier predicts the class according to the best match with the train-
Energies 2024, 17, 4308 10 of 25

Algorithm 1: DHFO Algorithm

Input: Input Data [co-ordinates and demand Cost (M N ID )]
Output: Predicted CS and demand, Aij , Rij , Cid
Step 1: Construct availability matrix and demand cost matrix
Let Si and S j be size of matrix (M N ID ) and set K = 2; where, N ID—Node ID
For i = 1 to Si
For j = 1 to S j
Compute the initial position of CS data, Aij by

0.5 i f ( M N ID (i, j) <= 0.5)
Aij =
0 Otherwise
End for j;
End for i;
Step 2: Construct and update responsibility matrix and availability matrix;
For Xk = 1 to k
For i = 1 to Si
For j = 1 to S j
Compute the relevant vector, Rij by
(  
M N ID (i, j) − Aij I f Aij <= M N ID (i, j)
Rij =
0 Otherwise
End for j
End for i
For i = 1 to Si
For j = 1 to S j
Let temp_Rij = 0;
For m = 1 to Si
temp_Rij = temp_Rij + Rim
End for m; (  
temp_Rij + Rij i f temp R ij ≤ 0
temp_Rij =
Rij Otherwise
(  If = j), then
(i!
0 I f temp R ij < 0
Aij =
temp_Rij Otherwise
Else (  
temp_Rij I f temp_Rij > 0
Aij =
0 Otherwise
End if
End for S j
End for Si
End for Xk
Step 3: Compute exponential matrix and the average of relevant vector based on the estimated list
index and ( then update
 in the
 list by
1 i f Aij + Rij > 0
Expmij =
0 Otherwise
size( Idx )
avgidx = 1x ∑ x=1 ls Ri( Idx x )
Update avglist ←avgidx ;
For y = 1 to S j
Compute the related average of overall vector avg R by
Sj
∑ Rij
avg R = j=S1j
Computeq the distance list between the average list and the related parameter by
disls = avg2List − ( avg R 2 )
Update Cid ←min(disls )
End for y;
Energies 2024, 17, 4308 11 of 25

1
Next, the ratio of and difv is used to compute the distance distxy . As a
log(Dervxy )
result, the sum of Tdist and distxy is updated in the Tdist .
q
disls = avg2List − ( avg R 2 ) (3)

1 size( Idxls )
x ∑ x =1
avgidx = Ri( Idx x ) (4)

The values of Tdist are then used to update the value of Odist , and lastly, the updated
Odist
M is used to estimate MNID (i, j).
The charging station architecture optimized the station’s orientation and set it up for
quicker data transfer based on the evaluation of these criteria. The output of DHFO was
the optimal feature database (training database), and the selected attributes of the overall
training database were used as the input for the ECNN classifier.

3.2. Enhanced Cladistic Neural Network (ECNN) Algorithm

The optimal feature database (training database), which is the output of the above-
described DHFO, was the extracted attributes of the overall training database that was used
as the input for the ECNN classifier. It was computed like the evolutionary relationship
concept in the construction of a cladogram. Cladograms are often used to create a linear
representation of hypotheses. They describe the evolutionary relationships between varied
features, showing how they are organized depending on co-operative characteristics. The
ECNN-based classification algorithm is used to predict the CS position based on the EV and
CS features that are optimized from the DHFO algorithm. This will estimate the parameters
of the vehicle, and allow the CS module to train itself on a suitable combination of indexes.
From that, if a vehicle requests any CS prediction, this will find the best co-ordinate position
of CS that is related to the satisfactory level of the vehicle for it to charge its battery. This
classification model can also forecast and recommend the location to install a CS later,
based on the demand estimation and the history of trained data from the available features.
This will update the training database for improving the performance in accuracy and
sensitivity levels. The ECNN algorithm takes into consideration the vehicle capacity that
can be integrated into the architecture depending on the minimal link coverage distance
that is the time it takes to reach the available CS, which may vary from time to time. This
algorithm’s primary contribution is its ability to forecast the optimal CS, based on the
parameters influencing this link coverage. The link coverage varies from time to time as
it depends on the vehicle parameters such as its model, the battery make and capacity,
driving speed, and traffic.
The model training begins with data preprocessing. The main phases of preprocessing
undergone in the proposed framework are (i) data normalization, (ii) feature optimization
using DHFO, and (iii) train test split.

3.2.1. Data Normalization

The normalization process aims to scale the numerical values in a dataset to a common
range without affecting the range of values. The normalization process applied in the
proposed model is min–max normalization applied as in equation,

X − Xmin
X′ =
Xmax − Xmin

3.2.2. Feature Optimization

Feature optimization is the process to minimize the number of features to decrease
the complexity of computation, as well as to improve the efficiency of the training model.
The feature optimization technique used in the proposed model is DHFO which has been
described in Section 3.1. Every optimization iteration received the instance’s data matrix as
input. Here it is used to reduce the size of the dataset before training the classifier to enhance
Energies 2024, 17, 4308 12 of 25

the prediction performance. As mentioned in Algorithm 1, the input is Co-ordinates and

Demand Cost (MNID) (the full table parameters are in Figure 4) of randomly generated
CS. Thus, the training feature set of the classifier model comprises the collected OSM data
co-ordinate positions, the selected attributes from the parameters of CS and EV such as SOC,
Km can travel by vehicle, Cost of CS, and Demand in (KW) from the randomly generated CS.
The optimal feature database obtained from DHFO and the selected attributes are passed as
the input to the ECNN classifier in both the training and testing processes. The data matrix
was updated every time the ideal charging station direction was chosen. The training
model of the ECNN was used to classify the classes of live moving vehicle parameters.

3.2.3. Train Test Split

The final phase in preprocessing is to split the dataset into train and test sets. The
process of splitting the dataset is a typical phase in learning algorithms to address overfitting
and for evaluating the performance of the trained model properly on unseen data. In the
proposed work, the dataset was split in the ratio of 70:30, where 70% was used for training
and remaining 30% was retained for model testing.

3.2.4. Classification Model Description

In this process, the ECNN is a multi-level classifier used for the prediction of the best
location for a charging station based on the feature attributes that are collected from the
parameters of the CS and EV. The classification result from the ECNN is the prediction of
the nearest CS location in the route path based on the parameters of SOC, Km can travel
by vehicle, Cost of CS, and Demand in (KW). If there was no CS predicted in the coverage
area of the current moving vehicle, then this recommended the location of CS based on the
demand level and the distance to the CS in the coverage area. The labels that are considered
for the classification are:
(a) CS station available with sufficient power to charge the EV—Class 1;
(b) CS station available with power demand (KW)—Class 2;
(c) CS station not available—Class 3;
(i) Recommend new CS station;
(ii) Recommend the longitude and latitude of new CS station.
These classes are defined by the training set for the classifier extracted from the
parameters of the CS and EV. These parameters are arranged in the form of feature attributes
to construct the training model for the classifier. This training model will be a one-time
process while installing the system on the manufacturing side. While driving the EV, the
parameters from the live running vehicle will be arranged as the testing feature vector. At
this testing stage, the parameters from each time point are used as the input to the classifier
for testing. The classifier predicts the class according to the best match with the training
database (feature set) and gives out the class label as 1, 2, or 3. If it predicted class 3, then
the classifier will again validate the parameters to recommend the best location for a new
CS, and this produces the longitude and latitude for the new CS.
The ECNN model’s algorithm steps are given in Algorithm 2:

Algorithm 2: ECNN Algorithm

Input: Input vehicle pattern set TD (s)
Output: Classified result V (k)
The initial pattern for the prediction is arranged as,
TD (s) = { TD1 (s), TD2 (s), . . . , TDm (s)}
In the input layer of the neural network, the data sequence can be formed as the matrix in the
equation below.
 
TD1 (s)
 TD2 (s) 
XD (s) =  ...


TDm (s)
Energies 2024, 17, 4308 13 of 25

Algorithm 2: Cont.
∗ (s) .


From the matrix arrangement, the block correlation feature can be estimated by F XD (s).XD
This can be represented as
∗ (s ) = X ∗ .e T − Tm


F XD (s).XD D
Where, ‘T’ and ‘Tm ’ represent the attribute values from matrix XD (s).
Estimate the
√ kernel
 model
 √ ofclassifier
q
1 2q 2q
Km = 2q −1 l kq l r ∀ q = 1, 2, . . . , N //’r’ represents the range of feature
distance, ‘l’ represents the length of the feature vector.
Estimate the relevancy using the kernel function with feature points.
tn = F T ωn
Where, ‘ωn ’ weight value of attributes.
un = F T ωn
Extract the training features and form the network by
Tr = {t1 , t2 , . . . , tn }
Xb = Xb + ∑iN=1 ti (d) pi
Estimate the matching score for the correlated blocks by

T
 T 
T̂s = Xbd − Xb PT

Where, the relevance factor Xbd ∈ R(T −Tp ) M can be written as

T
R(T −Tp ) M = T̂s Q T + tt a
Where, ‘P’ and ‘Q T ’—predicted component.
The predicted label can be represented by
d
V (k) = R j −ijRi
Where, dij —distance matrix for ‘i’ and ‘j’ of the relevance matrix ‘R.

4. Results and Discussion

The outcomes of the suggested model for classifying charging stations according to
availability and weight characteristics were verified and contrasted with the approaches
already in use. The first Section 4.1 was a briefing on the experimental setup and the dataset.
The tracking of the map-matched data samples with the output of the experiment was
discussed in Section 4.2. The performance indicators used for the study were discussed
in the second Section 4.3, followed by the quantitative evaluation based on the metrices
used to calculate the performance of the suggested classification model in Section 4.4. The
computational complexity of the system was analyzed in the following subsection E. An
investigation based on the road map matched with the OSM samples and experimental
results obtained was elaborated, followed by the performance comparison with other
existing approaches in the last Section 4.5.

4.1. Experimental Setup

Python 3.19 was used for the experimental study and testing. To perform the weight
flow analysis, the position and co-ordinate data were chosen based on the coverage area of
the electric vehicle.
The data samples for the experimental setup were generated from the OpenStreetMap
(OSM). OSM is a map embed API that provides map-matched data for the Origin Destina-
tion (O-D) Road Trip as planned for the EV user ([Link]
5/21.494/66.665, accessed on 26 January 2024). The geographic data are collected from
the traffic co-ordinate positions in the OSM database. Similarly, an archival database of
several map-harmonized tours are taken into consideration. According to the direction
on the map, the CS co-ordinate positions and the specification of CS are simulated and
verified. This includes weight data from the vehicle database, with some data created as
placeholders for missing values to forecast and predict the data. In this work, there were
five different road trip datasets generated for the locations from Bangalore to Mysore(D1),
Bangalore to Pune(D2), Bangalore to Tumkur(D3), Bangalore to Cochin(D4), and Bangalore
to Hyderabad(D5) in random directions on the map. These trips interconnecting different
 The data samples for the experimental setup were generated from the Open-
StreetMap (OSM). OSM is a map embed API that provides map-matched data for the
Origin Destination (O-D) Road Trip as planned for the EV user (h ps://[Link]-
[Link]/#map=5/21.494/66.665, accessed on 26 January 2024). The geographic data
are collected from the traffic co-ordinate positions in the OSM database. Similarly, an ar-
chival database of several map-harmonized tours are taken into consideration. According
Energies 2024, 17, 4308 to the direction on the map, the CS co-ordinate positions and the specification of CS are 14 of 25
simulated and verified. This includes weight data from the vehicle database, with some
data created as placeholders for missing values to forecast and predict the data. In this
work, there were five different road trip datasets generated for the locations from Banga-
lore to Mysore(D1),
Sates in Southern India were Bangalore to Pune(D2),
of variable Bangalore
length, to Tumkur(D3),
as shown in FigureBangalore to Co- 5b shows the
5a. Figure
chin(D4), and Bangalore to Hyderabad(D5) in random directions on the map. These trips
map direction D1, fromdifferent
interconnecting the source of Bangalore
Sates in Southern India weretoof the destination
variable of in
length, as shown Mysore.
Fig- Each part
ure 5a.
of this trip was Figure 5bfragmented
further shows the map into
direction D1, from
several the source
road of Bangalore
segments. to the desti-
Random position changes
nation of Mysore. Each part of this trip was further fragmented into several road seg-
and the creation of a situation where data are missing are then generated and simulated in
ments. Random position changes and the creation of a situation where data are missing
various modules.
are then The Open-Source
generated and simulatedRouting Machine
in various modules. The (OSRM)
Open-Source routing service provided the
Routing Machine
(OSRM) routing
available charging service
stations onprovided the available
the routes chosencharging stations
for the on the routes chosen for
study.
the study.

Energies 2024, 17, x FOR PEER REVIEW 15 of 26

(a)

(b)
Figure 5. Data Samples taken for the experimental study. (a) Five road trips D1 to D5 chosen for
Figure 5. Data
study Samples taken offor
(b) path of direction the
route experimental
Bangalore study.
to Mysore from (a) Five road trips D1
OSM data. to D5 chosen for
study (b) path of direction of route Bangalore to Mysore from OSM data.
Figure 4 shows the initialized demand parameters of CS at each co-ordinate position
which comprises co-ordinate positions of the CS in terms of latitude and longitude, the
Figuremaximum
4 shows thepower
output initialized
that a CSdemand
provides in parameters of CS
kW, number of piles at each
available co-ordinate
in the CS, position
cost per kWh
which comprises (varying frompositions
co-ordinate 5 to 10), andof
number
the CSof vehicles
in termsalready
of ge ing charged.
latitude and longitude, the
maximum These
outputparameter values are used to compute the power demand of CS. The CS with and
power that a CS provides in kW, number of piles available in the CS, cost
without demand are further examined using the DHFO and ECNN algorithm to predict
per kWh (varying fromcharging
the most optimal 5 to 10),
stationand number
for the EV [Link] vehicles already getting charged. These
parameter values are used to compute the power demand of CS. The CS with and without
4.2. Track Analysis with Map
demand are further examined using the DHFO and ECNN algorithm to predict the most
The map-matched route trips taken from the OpenStreetMap Database were utilized
optimal charging
to performstation for study.
the proposed the EVThe users.
data of available charging stations on the trips taken
were extracted using the Open-Source Routing Machine (OSRM). All the available charg-
ing stations near to the EV were grouped together based on clustering. The demand value
of each CS was computed as described in the DHFO algorithm, taking into consideration
the vehicle SOC and traffic density. The demand value in the positive range indicates that
a greater number of vehicles can be charged there. The negative value of demand suggests
unavailability of suitable charging stations, and hence there is an urge to place one there.
Figure 6 shows the simulation update of vehicle movement in all the O-D road trip
datasets that were generated for the locations from Bangalore to Mysore (D1), Bangalore
to Pune (D2), Bangalore to Tumkur (D3), Bangalore to Cochin (D4), and Bangalore to Hy-
derabad (D5) in random directions on the map. The dynamic prediction of optimal CS
placement is represented by the legend marks. In this, the black color represents the vehi-
Energies 2024, 17, 4308 15 of 25

4.2. Track Analysis with Map

The map-matched route trips taken from the OpenStreetMap Database were utilized
to perform the proposed study. The data of available charging stations on the trips taken
were extracted using the Open-Source Routing Machine (OSRM). All the available charging
stations near to the EV were grouped together based on clustering. The demand value of
each CS was computed as described in the DHFO algorithm, taking into consideration the
vehicle SOC and traffic density. The demand value in the positive range indicates that a
greater number of vehicles can be charged there. The negative value of demand suggests
unavailability of suitable charging stations, and hence there is an urge to place one there.
Figure 6 shows the simulation update of vehicle movement in all the O-D road trip
datasets that were generated for the locations from Bangalore to Mysore (D1), Bangalore
to Pune (D2), Bangalore to Tumkur (D3), Bangalore to Cochin (D4), and Bangalore to
Hyderabad (D5) in random directions on the map. The dynamic prediction of optimal CS
placement is represented by the legend marks. In this, the black color represents the vehicle
and the orange color represents the movement tracking of the EV. The green dots represent
the co-ordinate positions of all the charging stations adjacent to the route of the electric
Energies 2024, 17, x FOR
vehicle, PEER REVIEW
traced using the clustering algorithm. The red dot in the figure indicates the co- 16 of 26
ordinate positions of the CS which are of high demand in the path for the specified source
to destination. The purple dot indicates the co-ordinate positions of the CS based on the
optimization algorithm. on theItoptimization
represents algorithm. It represents
the forecasted the forecastedlocation
and recommended and recommended
to place thelocation to
CS. It was obtainedplace basedtheon
[Link]
It was obtained
demand based onwith
estimation the demand
vehicleestimation
distance. with
The vehicle distance. The
prediction
was done dynamically, prediction
basedwas on done dynamically, based
the classification on thetaking
algorithm classification algorithm taking
into consideration the into con-
sideration the selected feature parameters from the DHFO algorithm and computing the
selected feature parameters from the DHFO algorithm and computing the demand MNID
demand MNID (i, j), as described in Algorithms 1 and 2 above. As the EV travels towards
(i, j), as described to in charging
Algorithms 1 and 2 above. As the EV travels towards to charging
station, the SOC reduces. A minimum threshold of 5% was set for the SOC to
station, the SOC reduces. A minimum
ensure that the EV would threshold of 5%
be charged wasitset
before was for the SOC
totally to ensure
drained. The EV,that
on reaching
the EV would be charged beforethreshold
this minimum it was totally drained.
of SOC, The EV,
will identify on reaching
the predicted thisbecome
CS and minimumcharged. Ac-
threshold of SOC, will cordingly, thethe
identify SOC will be updated
predicted CS and and the vehicle
become travels
charged. towards itsthe
Accordingly, destination.
SOC Each
will be updated and ofthe
the vehicle
data samples of the
travels O-D trip
towards itstaken (D1–D7 described
destination. Each of thein the
datafollowing
samplessection)
of were
the O-D trip takenfurther(D1–D7 divided into more
described than
in the 50 datapoints,
following overall.
section) Thus,
were we considered
further dividedapproximately
into
more than 50 datapoints,350 datapoints.
[Link] ensuing
Thus, subsections approximately
we considered address the performance [Link]
350 datapoints.
ensuing subsections address the performance outcomes.

(a)

Figure 6. Cont.
 Energies 2024, 17, x FOR PEER REVIEW 17 of 2
Energies 2024, 17, 4308 16 of 25

(b)

(c)

Figure 6. Cont.
 Energies 2024, 17, x FOR PEER REVIEW 18 of 26
Energies 2024, 17, 4308 17 of 25

(d)

(e)
Figure 6. Simulation of the paths taken for the testing of the prediction. (a) Simulation of vehicle
Figure 6. Simulation of the paths taken for the testing of the prediction. (a) Simulation of vehicle
tracking and CS prediction for the direction path from Bangalore to Mysore; (b) simulation of vehi-
tracking and CS prediction for theand
cle tracking direction path from
CS prediction Bangalore
for direction pathtofrom
Mysore;
Pune (b) simulation
to Bangalore; (c) of vehicle of vehicle
simulation
tracking and CS prediction for direction path from Pune to Bangalore; (c) simulation of vehicle
tracking and CS prediction for the direction path from Tumkur to Bangalore; (d) simulation of vehicle
tracking and CS prediction for direction path from Hyderabad to Bangalore; (e) simulation of vehicle
tracking and CS prediction for the direction path from Bangalore to Ernakulam.

4.3. Performance Indicators

By calculating the statistical probability between the number of misclassified results
and the properly classified data samples, one can determine the parameters utilized in the
performance metric-based analytical procedure. The confusion matrix layout is used to
Energies 2024, 17, 4308 18 of 25

generate all of these, which are then assessed by comparing the categorized results to the
dataset’s ground truth. The true positives and false positives of the predictions made are
used to compute the precision, recall, accuracy, and F1 score. Each of these measures is
significant, according to the varying situations, to get a broader understanding of the errors
and performance of the model. The accuracy is the baseline measure used in the classifier
model to get an indication of how efficient the system is. It is computed as in Equation (5).

Total correct labels

Accuracy, Acc = (5)
Total No. of Samples

To ensure that the system performs well, even when the datasets are not properly
balanced, we utilized the precision value as it gives the ratio of true positives across all the
positive values. It is beneficial in scenarios when the estimate of false positives is high. The
mathematical equation of precision is mentioned in Equation (6) stated below.

TP
Precision, P = (1 − FPR) = (6)
TP + FP
Recall is taken into consideration when the estimate of false negatives is high and the
equation to compute it is specified in Equation (7) stated below.

Recall, R = (1 − FNR) (7)

The F1 score is also considered to find an equilibrium between the precision and recall.
The F1 score is a single metric that is computed as the harmonic mean of precision and
recall, as in Equation (8).
2PR
F1 Score, F_S = (8)
P+R
Area under Receiver Operating Characteristic (ROC) curve is another important metric
used to evaluate the performance of the model. The ROC curve is plotted as the curve
between recall or sensitivity defined in Equation (9) and the false positive rate (FPR) which
is (1 − specificity which is mentioned in Equation (10)) or the proportion of incorrect
classification made by the model, as in Equation (11).

True Positive(TP)
Sensitivity, TPR = (9)
Total No. of Positive samples

True Negative(TN)
Specificity, TNR = (10)
Total No. of Negative samples
False Positive(FN)
1 − Specificity = FPR = (11)
True Negative(TN) + False Positive(FP)

4.4. Quantitative Evaluation Based on Performance Measures

The complete outline of the performance of the system was obtained using the above-
defined performance metrices. The five defined road O-D trips in Figure 5, as mentioned
in the experimental setup, were taken into consideration. The performance measures of
precision, recall, F1 score, and accuracy were computed across each of these segments.
The plot showing the tradeoff in these performance measures is visually represented
in Figure 7. It was observed that the model obtained a higher recall and accuracy measure
across all five defined road trips. The higher recall shows that the system was successful in
predicting the maximum number of optimal CSs available for the EV user for a particular
road trip. The higher accuracy value across all the road segments ensured that the system’s
overall performance was high. Hence it can be inferred that the model will ensure that the
EV user will be intimated with all possible optimal CS on the path it is travelling on. The
ROC curve outlining the performance of the proposed model on the different datasets is
 The plot showing the tradeoff in these performance measures is visually represented
in Figure
in Figure 7. 7. It
It was
was observed
observed thatthat the
the model
model obtained
obtained aa higher
higher recall
recall andand accuracy
accuracy measure
measure
across all five defined road trips. The higher recall shows that the
across all five defined road trips. The higher recall shows that the system was successful system was successful
in predicting
in predicting the the maximum
maximum number number of of optimal
optimal CSsCSs available
available for
for the
the EV
EV user
user for
for aa partic-
partic-
ular road trip. The higher accuracy value across all the road segments
ular road trip. The higher accuracy value across all the road segments ensured that the ensured that the
Energies 2024, 17, 4308 system’s overall performance was high. Hence it can be inferred that the model
system’s overall performance was high. Hence it can be inferred that the model will ensure19 of 25 will ensure
that the
that the EV
EV user
user will
will bebe intimated
intimated with
with allall possible
possible optimal
optimal CS CS onon the
the path
path itit is
is travelling
travelling
on. The ROC curve outlining the performance of the proposed model
on. The ROC curve outlining the performance of the proposed model on the different da- on the different da-
tasets
tasets
plotted is plo
is in ed
ploFigure in Figure
ed in 8.
Figure 8. The
8. The
The plot plot
is,plot is, again,
is, again,
again, an indication
an indication
an indication that
thatuse
that the the
theof use
use of optimal
of optimal
optimal feature
feature
feature selection
selection
selection
and demand and computation
and demand computation
demand computation of the
of
of the proposed the proposed
proposed systemin
system
system results results
results in elevated
in
elevated elevated resultsin the
results
results (>0.9)
(>0.9) in
(>0.9)
proposedin the
the proposed application.
proposed
application. application. The area
The
The area under area under
theunder
curvesthethe curves is
is curves
labelled is in
labelled
labelled in the
in
the graph. the graph.
graph.

Figure 7.
Figure
Figure 7. Plot
[Link] representing
Plotrepresenting
representingthe
the quantitative
the evaluation
quantitative
quantitative based
evaluation
evaluation on performance
based
based on performance measures.
on performance measures.
measures.

Figure 8.
Figure
Figure 8. ROC
[Link] curve
ROCcurve ofofthe
curveof the proposed
proposed
the model
model
proposed onon
on
model thethe
the different
different datasets
datasets
different D1 to
D1
datasets to
D1D5.
D5.
to D5.

4.5. Computational
4.5.
4.5. Computational Complexity
ComputationalComplexity
Complexity
The
The proposed
Theproposed
proposed study mainly
study
study mainly
mainly comprises
comprises
comprises two main
two main algorithms—DHFO
two algorithms—DHFO
main algorithms—DHFO and ECNN.
and ECNN. and The
TheECNN.
computational complexity
computational
The complexity of
computational of the
the system
complexity system depends
of the depends on
system on the
the working
depends working of
on the of the
the feature
workingfeature optimiza-
of optimiza- op-
the feature
tion and
tion and neural
timization neural network
and network algorithms,
neural algorithms, as
network as discussed
discussed in
algorithms, as in [38].
[38]. The
discussedThe DHFO
DHFO algorithm
in [38].algorithm takes
The DHFO takesalgorithm
into
into
consideration
consideration
takes the input
the input co-ordinates
into consideration co-ordinates
the input of of the EV
the EV user,
co-ordinatesuser,of asthe
as well
wellEV as user,
as the charging
the charging station.
as wellstation.
as the TheThe
charging
availability
availability
station. and
Theand the demand
the demand
availability and matrix
matrix are updated
are
the demand updated
matrixforare
for each
each of the
of the nodes
updated nodes taken
taken
for each into
ofinto consid-taken
the consid-
nodes
eration.
eration.
into The construction
The construction
consideration. of the
of the relevancy
relevancy
The construction matrix
matrix
of the is nested
is
relevancynested for loop,
for
matrix loop, whichfor
which
is nested is iterated
is iterated to
to
loop, which is
the maximum
the maximum
iterated of
to theof N, where
N,
maximumwhere of
N is
N is the
N, the totalN
total
where number
number of nodes.
of
is the total nodes. It is
It
number is of
followed
followed
[Link] by the
the
It is updatingby the
updating
followed
part of
part of the
updating thepart
above-constructed
above-constructed matrix based
matrix
of the above-constructed based on the
on
matrix the relevant
relevant
based vector
vector
on the as well
as
relevant well as the
as
vector theasvehicle
vehicle
well as the
vehicle node co-ordinate positions. This modification again includes an iteration within the
above-nested for loop, thereby the final computational complexity is O(n3 ).
The complexity of the algorithm depends on the training and testing phases. Dur-
ing the training phase, the complexity of the one-time step of the forward pass of each
layer involves matrix manipulations resulting in a complexity of O (ni × ni+1 ), where i
refers to the layers. The updating of the weights in the backward pass also results in O
(ni × ni+1 ) computational time. The estimation of the matching score for the correlated
blocks is O (n2 R), where R represents the total attributes. Hence, total computational
complexity of the ECNN algorithm,
taking into consideration k epochs and T time steps, is
O(k.T∑ni=−11 (ni ∗ ni+1 )) + O n2 .R . For the testing phase, the computational complexity is
much less linear in nature as it is directly proportional to the input size only.
 Energies 2024, 17, 4308 20 of 25

4.6. Comparison with Existing Approaches

Several studies have been made to resolve the range anxiety problem of EV users.
The optimal prediction of charging station is the primary concern of all these studies. The
study in [8] examined deep learning methods for optimal prediction. In the experimental
study, the OSM road network from Denmark was used, along with weather and digital
Energies 2024, 17, x FOR PEER REVIEWelevation information, to make the predictions. The speed profile was investigated 22 of 26
based
on different trip segments. The statistics of the investigated models were tabulated and,
being a regression model, the Root Mean Square Error (RMSE) and Mean Absolute Error
(MSE) were
In this tabulated.
process, The results
the ECNN showed
classifier that the
worked system
as the performed
multi-level exceptionally
classifier to predictwell
the
with a RMSE of approximately 0.8 for all kinds of speed profile when compared
best location based on the feature a ributes that were collected from the parameters of the to other
deep learning models.
CS and EV. While driving the EV, the parameters from the live running vehicle were ar-
In our study we proposed an enhanced cladistic neural network classifier algorithm
ranged as the testing feature vector. At this testing stage, the parameters from each time
with Distributed Homogenous Feature optimization, thereby chalking out the most signifi-
point were used as the input to the classifier for testing. The classifier predicted the class
cant features for prediction of the CSS. Hence, for analysis, we used the translation function
according to the the
and converted bestabove
matchregression
with the training database
results setting into(feature set)threshold
a suitable and gavebased
out the
on class
the
label as 1:CS station available with sufficient power to charge the EV
domain area where we could conclude that most of the DNN-based models showed an (green-colored dots),
CSoutstanding
station available with power
performance. demand
Using the (KW)—Class
threshold 2 (red-colored
of 2.0, the classification dots), or no
performance CS—
metrics
Class 3 (purple-colored dots as in Figures 9 and 10). If it predicted class
computed for each regression method indicated that most methods performed similarly, 3, then the classi-
fier would,
with again, validate
high precision above the
0.9,parameters
recall aboveto0.8,recommend
and F1-scores the above
best location for a new CS
0.85, approximately.
that gives9 depicts
Figure out the the
longitude and Denmark
route from latitude forto the new [Link] the prediction of optimal CS
Hannover
using the proposed system, which is labelled D6.

Figure
[Link]
Roadtrip
tripfrom
fromDenmark
Denmarkto
toHannover
Hannover with
with the prediction of
the prediction ofoptimal
optimalCS.
CS.

Figure 10 represents the geographical picture of the route trip from the road network
in Wuhan which is a case study in [39]. The route chosen was from Wuhan to Wanggang,
and labelled D7. In the study in [39], different baseline standards were chosen to analyze
the influence of urban area in the prediction. The RMSE and MAE for the different baselines
were tabulated. These hypothetical regression results, when converted using the trade-
off threshold 2.0, clearly revealed that the effectiveness was high, with an accuracy and
precision of approximately 0.9, and a precision and F1 score of almost over 0.85.
The performance measures obtained for these two road trips, D6 and D7, using our
system, were also of a high standard in terms of accuracy, precision, and recall. In Table 1,
the results are evaluated from the tracking of vehicle movement with respect to time
response based on the SOC parameters. This result is simulated for routes D6 and D7. With
our proposed approach, the optimal charging stations predicted are highlighted as purple
dots in Figures 9 and 10.

Figure 10. Road trip from Wuhan to Wanggang with the prediction of optimal CS.
Energies 2024, 17, 4308
Figure 9. Road trip from Denmark to Hannover with the prediction of optimal CS. 21 of 25

Figure
Figure10.10.
Road trip
Road from
trip Wuhan
from to Wanggang
Wuhan withwith
to Wanggang the prediction of optimal
the prediction CS. CS.
of optimal

InThe
thisproposed
work, the technique could
data pa erns classify
were the results
efficiently in using
extracted a generalized
DHFO, andapproach
the mov-by effec-
ing vehicle was accurately detected by using the ECNN technique. From these CS location
tively extracting the data patterns of the input image and taking into consideration the
predictions and the tracking performance evaluation, the parameters representing the
most optimized parameters from the OSM sample data. The approaches which have been
performance
taken for the of analysis
the proposed model
in the were
current satisfactory
study when compared
also include additionalwith other state-
parameters from the
of-art methods. The precision, recall, and accuracy defined the sensitivity of the proposed
urban region, as well as environmental factors such as weather perspective. This proposed
study is not specific, and is independent of whether the samples were taken from urban
or rural areas, as well of other environmental factors, but still provides a promising and
satisfactory prediction of suitable CS.
In this process, the ECNN classifier worked as the multi-level classifier to predict the
best location based on the feature attributes that were collected from the parameters of
the CS and EV. While driving the EV, the parameters from the live running vehicle were
arranged as the testing feature vector. At this testing stage, the parameters from each time
point were used as the input to the classifier for testing. The classifier predicted the class
according to the best match with the training database (feature set) and gave out the class
label as 1:CS station available with sufficient power to charge the EV (green-colored dots),
CS station available with power demand (KW)—Class 2 (red-colored dots), or no CS—Class
3 (purple-colored dots as in Figures 9 and 10). If it predicted class 3, then the classifier
would, again, validate the parameters to recommend the best location for a new CS that
gives out the longitude and latitude for the new CS.
In this work, the data patterns were efficiently extracted using DHFO, and the moving
vehicle was accurately detected by using the ECNN technique. From these CS location
predictions and the tracking performance evaluation, the parameters representing the
performance of the proposed model were satisfactory when compared with other state-of-
art methods. The precision, recall, and accuracy defined the sensitivity of the proposed
algorithm in the prediction of CS and the forecasting of the CS location to recommend the
position where we can optimally place the CS in the path of direction.
Table 1 and Figure 11 show the accuracy and tracking performance rates of the existing
approaches: Data-Driven Context Aware Learning DDCAL [39], Probabilistic Deep learning
for EV [8], Machine learning Analysis (MLA) based on Linear Regression and Support
Vector Machine [2], Fuzzy-based multi-criteria decision-making NWHFMCGDM [40], and
Proposed Techniques. All these existing approaches have been studied using the data
samples D6 and D7. These results are evaluated based on the successful classification
with less time difference. To track the evaluation, the performance measures’ accuracy and
tracking performance rates of these approaches were calculated. From the evaluation, it was
found that the proposed system provides an efficient result, when compared to the other
techniques, and it is stable across all the data routes. To compare the efficiency of feature
extraction and classification performance across the systems, the tracking performance
 PDLEV [8] 0.90 94.45
D6 MLA [2] 0.90 90.01
NWHFMGDM [41] 0.89 99.00
Proposed 0.91 99.89
Energies 2024, 17, 4308 22 of 25
DDCAL [39] 0.89 89
PDLEV [8] 0.88 93.29
D7 MLA [2] 0.89 91.2
rate was used. The tracking performance depends on the computational time taken with
NWHFMGDM [41] 0.88 99.1
respect to the data used, as well as the hyperparameters which are model-specific tunable
Proposed
settings. In this work, the data patterns0.91 99.95using DHFO, and the
were efficiently extracted
moving vehicle could be accurately detected by using the ECNN technique.

Figure 11. Comparison plot of tracking performance.

From the CS location predictions and the tracking performance evaluation, the pa-
rameters representing the performance of the proposed model were better than the other
state-of-art methods.

Table 1. Comparative analysis with respect to D6 and D7.

Data Sample Taken Methods Accuracy Tracking Performance %

DDCAL [39] 0.90 80
PDLEV [8] 0.90 94.45
D6 MLA [2] 0.90 90.01
NWHFMGDM [41] 0.89 99.00
Proposed 0.91 99.89
DDCAL [39] 0.89 89
PDLEV [8] 0.88 93.29

D7 MLA [2] 0.89 91.2

NWHFMGDM [41] 0.88 99.1
Proposed 0.91 99.95

5. Conclusions
An innovative charging station prediction model was put forth in this era of the
Internet of vehicles [42], utilizing an Enhanced Cladistic Neural Network (ECNN) for
charging station prediction and an adaptive Distributional Homogeneity Feature Optimiza-
tion (DHFO) method for optimal feature selection based on pattern analysis. The results
were evaluated from the tracking of vehicle movement, in which the EV could reach the
CS with an optimal time difference, and it ensured a high score in all standard metrics
across all the OSM data samples used, showing the stability of the system’s performance.
From the evaluation, it was found that the proposed system provided a satisfactory result,
when compared to the other existing techniques, by taking into consideration only the most
significant features obtained on the pattern of vehicle for prediction of the most optimal
existing CS, as well forecasting the geographical co-ordinates apt for the installation of the
CS. The additional socioeconomic and geographical factors, as described in other existing
Energies 2024, 17, 4308 23 of 25

approaches, influenced the system, but their impact was considerably small on vehicle and
CS parameters.

Limitations and Future Prospects

The study mainly concentrated on the charging station prediction, as well as forecast-
ing of location to install a new CS, assuming the higher adoption rate of EV. The study
was predominantly based on dynamic vehicle tracking and was not validated for the stan-
dard EV datasets, as most of the available datasets are region-specific and may drastically
change with time, depending on the adoption rate of EV in those regions. Although the
geographical co-ordinates of a future CS have been forecasted, the power distribution
and government policies, as well as guidelines, must also be studied prior to the final
installation of the charging stations. Based on feature optimization model advancement,
this kind of pattern-based prediction model may be tested and implemented in the future
for large data in car patterns. Further studies could also be conducted, based on a time
series plot with different vehicle models.

Author Contributions: Conceptualization, R.P.; Methodology, R.P.; Validation, M.P.S.; Writing—

original draft, R.P.; Writing—review & editing, R.P. and M.P.S.; Supervision, M.P.S. All authors have
read and agreed to the published version of the manuscript.
Funding: This research received no external funding.
Data Availability Statement: The original contributions presented in the study are included in the
article, further inquiries can be directed to the corresponding author.
Conflicts of Interest: The authors declare that they have no conflicts of interest.

Nomenclature

CS Charging Station
EV Electric Vehicle
AI Artificial Intelligence
DHFO Distributional Homogeneity Feature Optimization
ECNN Enhanced Cladistic Neural Networks
SoC State of Charge of Electric Vehicle
OSM OpenStreetMap
CNN Convolution Neural Network
O-D Origin Destination
EMP Ensemble Modulation Pattern
OSRM Open-Source Routing Machine
P Precision
R Recall
FPR False Positive Rate
FNR False Negative Rate
ROC Receiver Operating Characteristic
Acc Accuracy Measure
RMSE Root Mean Square Error
MAE Mean Absolute Error
DNN Deep Neural Network

References
1. Sasank, T.V.; Akash, K.B.; Siddharth, I.S.; Susila, M. State of Charge Estimation and Analysis For an Electric Vehicle. In
Proceedings of the 2023 International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and
Computational Intelligence (RAEEUCCI), Chennai, India, 19–21 April 2023; pp. 1–6. [CrossRef]
2. Alanazi, F.; Alshammari, T.O.; Azam, A. Optimal Charging Station Placement and Scheduling for Electric Vehicles in Smart Cities.
Sustainability 2023, 15, 16030. [CrossRef]
3. Kim, D.; Kwon, D.; Han, J.; Lee, S.M.; Elkosantini, S.; Suh, W. Data-Driven Model for Identifying Factors Influencing Electric
Vehicle Charging Demand: A Comparative Analysis of Early- and Maturity-Phases of Electric Vehicle Programs in Korea. Appl.
Sci. 2023, 13, 3760. [CrossRef]
Energies 2024, 17, 4308 24 of 25

4. Liu, A.; Zhao, Y.; Meng, X.; Zhang, Y. A three-phase fuzzy multi-criteria decision model for charging station location of the
sharing electric vehicle. Int. J. Prod. Econ. 2020, 225, 107572. [CrossRef]
5. Shahriar, S.; Al-Ali, A.R.; Osman, A.H.; Dhou, S.; Nijim, M. Prediction of EV Charging Behavior Using Machine Learning. IEEE
Access 2021, 9, 111576–111586. [CrossRef]
6. Çelik, S.; Ok, Ş. Electric vehicle charging stations: Model, algorithm, simulation, location, and capacity planning. Heliyon 2024,
10, e29153. [CrossRef]
7. Hecht, C.; Figgener, J.; Sauer, D.U. Predicting Electric Vehicle Charging Station Availability Using Ensemble Machine Learning.
Energies 2021, 14, 7834. [CrossRef]
8. Petkevicius, L.; Saltenis, S.; Civilis, A.; Torp, K. Probabilistic Deep Learning for Electric-Vehicle Energy-Use Prediction. In
Proceedings of the 17th International Symposium on Spatial and Temporal Databases (SSTD ‘21), Virtual, 23–25 August 2021;
Association for Computing Machinery: New York, NY, USA, 2021; pp. 85–95. [CrossRef]
9. Zhao, Y.; Guo, Y.; Guo, Q.; Zhang, H.; Sun, H. Deployment of the electric vehicle charging station considering existing competitors.
IEEE Trans. Smart Grid 2020, 11, 4236–4248. [CrossRef]
10. Aljafari, B.; Jeyaraj, P.R.; Kathiresan, A.C.; Thanikanti, S.B. Electric vehicle optimum charging-discharging scheduling with
dynamic pricing employing multi agent deep neural network. Comput. Electr. Eng. 2023, 105, 108555. [CrossRef]
11. Mao, D.; Tan, J.; Wang, J. Location planning of PEV fast charging station: An integrated approach under traffic and power grid
requirements. IEEE Trans. Intell. Transp. Syst. 2020, 22, 483–492. [CrossRef]
12. Li, N.; Jiang, Y.; Zhang, Z.-H. A two-stage ambiguous stochastic program for electric vehicle charging station location problem
with valet charging service. Transp. Res. Part B Methodol. 2021, 153, 149–171. [CrossRef]
13. Cao, W.; Wan, Y.; Wang, L.; Wu, Y. Location and capacity determination of charging station based on electric vehicle charging
behavior analysis. IEEJ Trans. Electr. Electron. Eng. 2021, 16, 827–834. [CrossRef]
14. Li, J.; Liu, Z.; Wang, X. Public charging station location determination for electric ride-hailing vehicles based on an improved
genetic algorithm. Sustain. Cities Soc. 2021, 74, 103181. [CrossRef]
15. Ahmad, F.; Khalid, M.; Panigrahi, B.K. An enhanced approach to optimally place the solar powered electric vehicle charging
station in distribution network. J. Energy Storage 2021, 42, 103090. [CrossRef]
16. Wang, H.; Meng, Q.; Wang, J.; Zhao, D. An electric-vehicle corridor model in a dense city with applications to charging location
and traffic management. Transp. Res. Part B Methodol. 2021, 149, 79–99. [CrossRef]
17. Lee, J.-B. Review on Environmentally-Friendly Vehicle Charging Station Location and Size Problems. KSCE J. Civ. Eng. 2022, 26,
3741–3751. [CrossRef]
18. Yu, Z.; Wu, Z.; Li, Q.; Bai, Q. A map matching-based method for electric vehicle charging station placement at directional road
segment level. Sustain. Cities Soc. 2022, 84, 103987. [CrossRef]
19. Othman, A.M.; Gabbar, H.A.; Pino, F.; Repetto, M. Optimal electrical fast charging stations by enhanced descent gradient and
Voronoi diagram. Comput. Electr. Eng. 2020, 83, 106574. [CrossRef]
20. Çeven, S.; Albayrak, A.; Bayır, R. Real-time range estimation in electric vehicles using fuzzy logic classifier. Comput. Electr. Eng.
2020, 83, 106577. [CrossRef]
21. Sun, C.; Li, T.; Tang, X. A Data-Driven Approach for Optimizing Early-Stage Electric Vehicle Charging Station Placement. IEEE
Trans. Ind. Inform. 2023. [CrossRef]
22. Nurmuhammed, M.; Akdağ, O.; Karadağ, T. A novel modified Archimedes optimization algorithm for optimal placement of
electric vehicle charging stations in distribution networks. Alex. Eng. J. 2023, 84, 81–92. [CrossRef]
23. Sabyasachi, S.; Singh, A.R.; Godse, R.; Jaiswal, S.; Bajaj, M.; Srivastava, I.; Blazek, V.; Prokop, L.; Misak, S. Reimagining E-mobility:
A holistic business model for the electric vehicle charging ecosystem. Alex. Eng. J. 2024, 93, 236–258. [CrossRef]
24. Zhou, J.; Wu, Y.; Wu, C.; He, F.; Zhang, B.; Liu, F. A geographical information system based multi-criteria decision-making
approach for location analysis and evaluation of urban photovoltaic charging station: A case study in Beijing. Energy Convers.
Manag. 2020, 205, 112340. [CrossRef]
25. Chumbi, W.E.; Martínez-Minga, R.; Zambrano-Asanza, S.; Leite, J.B.; Franco, J.F. Suitable Site Selection of Public Charging
Stations: A Fuzzy TOPSIS MCDA Framework on Capacity Substation Assessment. Energies 2024, 17, 3452. [CrossRef]
26. Zhao, T.; Li, N.; Kong, N.; Xie, X. Optimal Location of Electrical Vehicle Charging Stations With Both Self-and Valet-Charging
Service. IEEE Trans. Autom. Sci. Eng. 2023. [CrossRef]
27. Shen, X.; Lv, J.; Du, S.; Deng, Y.; Liu, M.; Zhou, Y. Integrated optimization of electric vehicles charging location and allocation for
valet charging service. Flex. Serv. Manuf. J. 2023, 1–27. [CrossRef]
28. Almaghrebi, A.; Aljuheshi, F.; Rafaie, M.; James, K.; Alahmad, M. Data-Driven Charging Demand Prediction at Public Charging
Stations Using Supervised Machine Learning Regression Methods. Energies 2020, 13, 4231. [CrossRef]
29. Fang, X.; Xie, Y.; Wang, B.; Xu, R.; Mei, F.; Zheng, J. Research on electric vehicle charging load prediction method based on spectral
clustering and deep learning network. Front. Energy Res. 2024, 12, 1294453. [CrossRef]
30. Erdoğan, S.; Çapar, I.; Çapar, I.; Nejad, M.M. Establishing a statewide electric vehicle charging station network in Maryland: A
corridor-based station location problem. Socio-Econ. Plan. Sci. 2022, 79, 101127. [CrossRef]
31. Kim, S.; Jeong, Y.; Nam, J.-W. Solving Optimal Electric Vehicle Charger Deployment Problem. Appl. Sci. 2024, 14, 5092. [CrossRef]
32. Zhang, B.; Zhao, M.; Hu, X. Location planning of electric vehicle charging station with users’ preferences and waiting time:
Multi-objective bi-level programming model and HNSGA-II algorithm. Int. J. Prod. Res. 2023, 61, 1394–1423. [CrossRef]
Energies 2024, 17, 4308 25 of 25

33. Zheng, J.; Zhu, J.; Xi, H. Short-term energy consumption prediction of electric vehicle charging station using attentional feature
engineering and multi-sequence stacked Gated Recurrent Unit. Comput. Electr. Eng. 2023, 108, 108694. [CrossRef]
34. Suhail, M.; Akhtar, I.; Kirmani, S. Objective functions and infrastructure for optimal placement of electrical vehicle charging
station: A comprehensive survey. IETE J. Res. 2023, 69, 5250–5260. [CrossRef]
35. Hemmati, R. (Ed.) Chapter 3—Integration of electric vehicles and charging stations. In Energy Management in Homes and Residential
Microgrids; Elsevier: Amsterdam, The Netherlands, 2024; pp. 79–140, ISBN 9780443237287. [CrossRef]
36. Vani, B.V.; Kishan, D.; Ahmad, W.; Reddy, B.N.K. An efficient battery swapping and charging mechanism for electric vehicles
using bat algorithm. Comput. Electr. Eng. 2024, 118, 109357. [CrossRef]
37. Kim, Y.; Kim, S. Forecasting Charging Demand of Electric Vehicles Using Time-Series Models. Energies 2021, 14, 1487. [CrossRef]
38. Shah, B.; Bhavsar, H. Time Complexity in Deep Learning Models. Procedia Comput. Sci. 2022, 215, 202–210. [CrossRef]
39. Yang, Y.; Zhang, Y.; Meng, X. A Data-Driven Approach for Optimizing the EV Charging Stations Network. IEEE Access 2020, 8,
118572–118592. [CrossRef]
40. Loni, A.; Asadi, S. Data-driven equitable placement for electric vehicle charging stations: Case study San Francisco. Energy 2023,
282, 128796. [CrossRef]
41. Zhang, P.; Zhang, Z.; Gong, D.; Cui, X. A novel normal wiggly hesitant fuzzy multi-criteria group decision making method and
its application to electric vehicle charging station location. Expert Syst. Appl. 2023, 223, 119876. [CrossRef]
42. Philip, A.O.; U, S.M.; Paul, R.; Saravanaguru, R. Towards intelligent trust-based incident and evidence management models for
Internet of Vehicles: A survey. Comput. Electr. Eng. 2024, 117, 109284. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.