Capstone Project – I: Review – 1 on
Smart Greenhouse Monitoring System
Presented by the Batch No. : A5
Name Roll Number (TL)
M Santhosh BU21CSEN0100822
T Venkata Shiva BU21CSEN0100841
A Guru Rahul Reddy BU21CSEN0100948
J Pavan Kumar BU21CSEN0101703
Under the Guidance of
K.K. Baseer
Designation
Department of Computer Science and Engineering
GITAM School of Technology, GITAM (Deemed to be University),
Bengaluru, Karnataka, INDIA.
CONTENTS
1. Abstract
2. Introduction
3. Literature Survey
4. Conclusion
5. References
2
Abstract
The Smart Greenhouse Monitoring System is a technologically
advanced platform designed to enhance agricultural efficiency
through precise environmental control and automation. Utilizing a
comprehensive array of sensors, it monitors conditions such as
temperature, humidity, CO2 levels, and soil moisture. Data collected
is processed and relayed in real-time to a cloud-based server, enabling
remote management via user-friendly mobile and web applications.
This system ensures optimal plant growth by automating irrigation,
lighting, and ventilation based on real-time data, thereby reducing the
need for manual intervention and improving resource use efficiency.
It also includes security features for data protection and user access
control, making it a robust solution for modern agricultural needs.
The Smart Greenhouse Monitoring System represents a significant
step forward in the integration of IoT and cloud computing in
agriculture, promoting sustainability and higher productivity in
greenhouse operations.
Introduction
The Smart Greenhouse Monitoring System is a cutting-edge solution
designed to address the challenges of traditional greenhouse management by
leveraging IoT, cloud computing, and automation. Greenhouses are
essential for providing controlled environments for plant growth, but
manual monitoring of temperature, humidity, and other factors can be labor-
intensive and inefficient. This system overcomes these limitations by
continuously monitoring key environmental parameters using advanced
sensors, including temperature, humidity, soil moisture, and CO2 sensors.
The data collected is processed by a microcontroller and sent to a cloud
platform, enabling real-time monitoring and decision-making.
Introduction..contd
The system’s cloud-based architecture allows users to remotely monitor
greenhouse conditions via web and mobile applications. These
interfaces provide real-time data, send alerts for anomalies, and enable
control of settings like irrigation and ventilation. This remote access
ensures optimal growing conditions while reducing manual
intervention.
By automating key processes, the Smart Greenhouse Monitoring
System improves resource efficiency and sustainability. It minimizes
water and energy use, while ensuring plants thrive under ideal
conditions. This makes it a valuable tool for enhancing productivity and
promoting sustainable farming practices.
Literature Survey
Table 1: Literature Survey
Techniques/Algorithms
S . No Paper Details Summary Research Gap
Used
Conventional greenhouses face
sustainability challenges due to
high energy consumption and
reliance on non-renewable
A Systematic Review of resources, necessitating the Modular Design Techniques,
Optimal and Practical
Methods in Design,
adoption of smart technologies IoT-Based Automation Algorithms, High Initial Costs,
Renewable Energy Integration Methods, Complexity in Integration,
Construction, Control, and renewable energy solutions
Energy Management Optimization Maintenance and Reliability,
1 Energy Management and for efficient and environmentally
Techniques, Scalability Challenges,
Operation of
friendly operation . The existing Predictive Analytics and Data Processing Data Management,
Smart
Methods, Limited Accessibility
Greenhouses(Volume 12 approach integrates advanced
Sustainable Construction Practices
2024) design, construction, control
systems, and renewable energy
technologies to optimize energy
management and sustainability
in smart greenhouses.
The problem highlighted in the paper is the
inadequacy of current GHG emissions 1. High-Resolution Electricity Modeling
assessment methods based on historical 2. Temporal GHG Emissions Analysis
Assessment of Spatial and high computational demand, challenges in obtaining
data or estimated generation, which fail to [Link] Emissions Assessment
Temporal Modeling on accurate spatial and temporal data, complexity in
accurately reflect future power systems' 4. Inclusion of Start-Up Emissions
2 Greenhouse Gas modeling start-up emissions, and difficulties in
emissions due to spatial-temporal and 5. Comparison of Total Emissions and
Emissions From accounting for rapid system changes and
techno-economic variations. This gap Emission Intensity
Electricity Generation geographical variations.
hinders effective environmental policy 6. Optimization for Renewable Integration
making and emissions reduction strategies and Energy Storage
in the electricity sector.
Table 2: Literature Survey
Paper Techniques/
[Link] Summary Research Gap
Details Algorithms Used
the challenge of addressing climate
1. Advanced Data Management
change by reducing greenhouse gas
Techniques
(GHG) emissions across various
2. Application of AI and Machine
sectors using effective Computer
Greenhouse Gas Learning [Link] Integration
Science Architecture (CSA) principles
Emission Reduction 3. IoT Integration for Monitoring and [Link] Costs
. Computer Science Architecture
3 Architecture Control [Link] Privacy and Security: .
(CSA) is utilized, encompassing data,
in Computer Science: 4. Smart Grid Technologies 4. Scalability Issues
application, technology, and business
A Systematic Review 5. Blockchain for Transparent 5. Technological Dependence
architecture, to address climate change
Reporting
by incorporating advanced
6. Multi-Agent Systems for
technologies like AI, IoT, and smart
Optimization
grids to mitigate GHG emissions.
The challenge is efficiently managing
agricultural production in greenhouses
amidst climate change impacts, insect [Link] Robotics
Smart Farming Robot
infestations, and the need for [Link] Sensor Networks 1. Limited Data Coverage
for Detecting
advanced technology [Link] [Link] Learning Algorithm 2. High Initial Costs
Environmental
4 solution employs an autonomous [Link] Clustering for Crop 3. Complexity of System Integration
Conditions in a
robot equipped with a wireless sensor [Link] Analysis 4. Maintenance and Reliability
Greenhouse(volume 09
network and an unsupervised learning [Link] Interface for Route Planning 5. Data Privacy and Security
2024)
algorithm to analyze greenhouse and Data Observation
conditions and optimize crop
management.
Table 3: Literature Survey
S.N Paper Techniques/
Summary Research Gap
o Details Algorithms Used
The problem is the inadequacy of
current GHG emissions assessment 1. Detailed Electricity Modeling
Assessment of Spatial methods based on historical data or 2. Hourly Resolution Emission
and Temporal Modeling energy models, which fail to accurately Quantification
[Link] Data Limitations
on reflect future power systems' emissions [Link] and Temporal Variation
[Link] Inaccuracies
Greenhouse Gas due to spatial-temporal and techno- Analysis
5 [Link]-Temporal Variation [Link]
Emissions From economic variations . The solution [Link] of Start-Up and Shutdown
Techno-Economic Characteristics
Electricity employs a comprehensive methodology Emissions
5. Marginal Impact Assessments
Generation(Volume 14 based on a detailed electricity model [Link] GHG Emissions Analysis
2023) that quantifies GHG emissions with 6. Time-Varying and Marginal
high spatial-temporal and techno- Assessment Techniques
economic resolution.
The problem is the need for improved
water monitoring systems to address the
complex interactions of anthropogenic
Surface Water
activities, climate change, [Link] of Water Monitoring
Monitoring Systems—
sedimentation, and wastewater inputs, Approaches
The [Link] Research on Optimization
with limited research on optimizing [Link] Techniques Optimization
Importance of [Link] Integration of Sampling
these systems through combined [Link] Modeling (Water Quality
Integrating Information Techniques
6 sampling techniques and predictive and Quantity Models)
Sources [Link] in Sensor Implementation
models . The solution uses a proposed [Link] Fusion and Verification
for Sustainable [Link] Model-Based Approaches
framework that integrates various water [Link] of Semi-Mechanistic Models
Watershed [Link] of Comprehensive Frameworks
monitoring approaches, sampling [Link] of Data Science and
Management(Volume
techniques, and predictive models, Artificial Intelligence
11 2023)
combining water quality and quantity
models for a comprehensive
environmental assessment.
Table 4: Literature Survey
S. Paper Techniques/
Summary Research Gap
No Details Algorithms Used
The problem is the need for advanced,
non-invasive methods to continuously
monitor plant health, insect infestation,
and pollinator behavior to optimize
Towards Continuous [Link] (THz) Imaging and
crop yield and resource use while
Real-Time Plant and Sensing
understanding insect-plant interactions [Link] Real-Time Monitoring
Insect Monitoring by [Link]-Time Data Collection
and environmental stressors. The [Link] Techniques
Miniaturized [Link]-Invasive Monitoring
7 solution employs miniaturized terahertz [Link] Detailed Insights
THz [Link] Measurement of Water
(THz) systems for continuous 24/7 [Link] Coverage of Environmental Stressors
Systems(VOLUME 3, Uptake and Insect Behavior
real-time monitoring of plants and [Link] Resource Consumption
NO. 3, JULY 2023 [Link] of Crop Yield and
insects, providing dynamic and non-
913) Resource Use
invasive insights into plant health,
insect infestation, and pollinator
behavior.
Conclusion
In conclusion, the Smart Greenhouse Monitoring System exemplifies
a transformative approach to modern agriculture, merging cutting-
edge technology with sustainability principles. By leveraging real-
time data and automation, the system not only enhances operational
efficiency but also ensures optimal plant growth while conserving
resources. Its integration of IoT and cloud computing, coupled with
robust security features, positions it as a pivotal tool for advancing
greenhouse management and addressing contemporary agricultural
challenges.
References
Journals
[1] J. Hwang and H. Yoe , ‘‘Study on the context-aware middleware for ubiquitous
greenhouses using wireless sensor networks,’’ Sensors, vol. 11, no. 5, pp. 4539–
4561, Apr. 2011
[2] I. Khan, M. W. Jack, and J. Stephenson, ‘‘Analysis of greenhouse
gas emissions in electricity systems using time-varying carbon intensity,’’ J. Cleaner
Prod., vol. 184, pp. 1091–1101, May 2018, doi:
10.1016/[Link].2018.02.309.
[3] M. H. Ko, B. Ryuh , K. C. Kim, A. Suprem, and N. P. Mahalik,
‘‘Autonomous greenhouse mobile robot driving strategies from system
integration perspective: Review and application,’’ IEEE/ASME Trans.
Mechatronics, vol. 20, no. 4, pp. 1705–1716, Aug. 2015.
[4] D. Xue and W. Huang, ‘‘Smart agriculture wireless sensor routing protocol
and node location algorithm based on Internet of Things technology ,’’ IEEE
Sensors J., vol. 21, no. 22, pp. 24967–24973, Nov. 2021.
