0% found this document useful (0 votes)
104 views

Kecerdasan Buatan: Artificial Intelligence

1. The document discusses an artificial intelligence course outline that includes introduction to AI, genetic algorithms, neural networks, particle swarm optimization, and AI project applications. 2. Assessment includes 40% assignments, 30% midterm exam, 30% final exam, and up to 10% additional points for participation in online discussions. 3. The course will use MATLAB/Python simulations and cover problem formulation, solutions, and evaluation metrics for AI techniques applied to power system challenges.

Uploaded by

Wahyu HP
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
104 views

Kecerdasan Buatan: Artificial Intelligence

1. The document discusses an artificial intelligence course outline that includes introduction to AI, genetic algorithms, neural networks, particle swarm optimization, and AI project applications. 2. Assessment includes 40% assignments, 30% midterm exam, 30% final exam, and up to 10% additional points for participation in online discussions. 3. The course will use MATLAB/Python simulations and cover problem formulation, solutions, and evaluation metrics for AI techniques applied to power system challenges.

Uploaded by

Wahyu HP
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 30

TE201428

KECERDASAN BUATAN
ARTIFICIAL INTELLIGENCE
Happy Aprillia, S.ST., M.T., M.Eng. Ph.D.
NIPH. 100115031
KONTRAK MATA KULIAH

Komponen Penilaian:
1. Tugas - 40% (4 Tugas)
2. UTS - 30%
3. UAS - 30%
4. Keaktifan dalam Menuangkan Pertanyaan dan Diskusi dalam Forum +10%

Software Simulasi
1. Matlab / Python
SEMESTER OVERVIEW

1. Introduction artificial intelligence


2. Genetic Algorithm
3. Neural Network
4. Particle Swarm Optimization
5. AI Project Applications
INTRODUCTION TO ARTIFICIAL INTELLIGENCE
TE201428 – Kecerdasan Buatan

Problem
formulation

Solutions
TE201428 – Kecerdasan Buatan Problems in Power Systems

Power systems consists of:


• Conventional generating
units (PG)
• Renewable energy
plants (PRE)
• Transmissions (PTr)
• Loads (PL)

Ideal: PG = PL
Trans. Losses: PG = PL + PTr
Addition of RE: PG + PRE = PL + PTr
TE201428 – Kecerdasan Buatan Problems in Power Systems

PG > P L
TE201428 – Kecerdasan Buatan Problems in Power Systems

PG > PL
?
PG1 + PG2 = PL  minimum cost operation
OpCostG1 + OpCostG2  operation hours of each G (hG),
fuel price of each G (fG)
(fG1 *PG1*hG1 ) + (fG2 *PG2*hG2 ) = min (Operation Cost)
𝑛𝑜_𝑔
σ𝑛=1 (fGn * PGn ∗ hGn ) = min (Operation Cost)
TE201428 – Kecerdasan Buatan Problems in Power Systems

PG > PL
?
PG1 + PG2
constraint

= PL  minimum cost operation


Problem
formulation OpCostG1 + OpCostG2  operation hours of each G (hG),
fuel price of each G (fG)
(fG1 *PG1*hG1 ) + (fG2 *PG2*hG2 ) = min (Operation Cost)
𝑛𝑜_𝑔
σ𝑛=1 (fGn * PGn ∗ hGn ) = min (Operation Cost)
Known Unknown Objective
Parameters and variables Solutions Function
TE201428 – Kecerdasan Buatan Problems in Power Systems

P G < PL
TE201428 – Kecerdasan Buatan Problems in Power Systems

P G < PL
PG = PL1+ … + PLN 
? Unknown
solution

maximize power distribution from demand combination

 find minimum cost of load shedding


Objective
PL1 PL2 PL3 PL4 PL5 Function

Min(CostLS)?
=
PG ?
constraint
TE201428 – Kecerdasan Buatan Problems in Power Systems

PG + PRE ≠ PL + PTr
TE201428 – Kecerdasan Buatan Problems in Power Systems

PG + PRE ≠ PL + PTr ?
• Renewable energy has uncertain behavior due to weather
• Forecasting technique is important

Pforecasting = Pactual_RE
𝑃෡ = P
1 𝑡=𝑁 P − 𝑃෠
Mean absolute error percentage (MAPE) = σ𝑡=1 𝑥100%
𝑁 P
Find minimum MAPE  is our objective function
TE201428 – Kecerdasan Buatan Problems in Power Systems

Find minimum MAPE  is our objective function


Model parameters
adjustment
Forecasting input Forecasting
results
- Historical data Forecasting
𝑃෠
- weather model Objective
Function
Evaluation
Actual data

1 𝑡=𝑁 P − 𝑃෠
Mean absolute error percentage (MAPE) = σ𝑡=1 𝑥100%
𝑁 P
TE201428 – Kecerdasan Buatan Definisi
TE201428 – Kecerdasan Buatan Definisi

KECERDASAN BUATAN?
Kemampuan sebuah sistem untuk menafsirkan data dengan
benar, mempelajari data tersebut dan menggunakan data
pembelajaran tersebut untuk mencapai tujuan dan tugas
tertentu melalui adaptasi yang fleksibel [1]

[1] Andreas Kaplan; Michael Haenlein (2019) Siri, Siri in my Hand, who's the Fairest in the Land? On the Interpretations, Illustrations and Implications of Artificial Intelligence, Business Horizons, 62(1), 15-25
TE201428 – Kecerdasan Buatan Komponen untuk Membangun Kecerdasan Buatan

1. Perumusan Masalah
• Penentuan input dan output
• Variabel terikat dan variabel bebas
2. Data
3. Penentuan Fungsi Tujuan (Objective Function)
4. Pemilihan model AI yang sesuai dengan perumusan masalah
5. Evaluasi
• Ketepatan solusi
• Waktu Komputasi
TE201428 – Kecerdasan Buatan

MENGAPA KECERDASAN BUATAN DIBUTUHKAN


DALAM SISTEM TENAGA LISTRIK?
Analisa sistem tenaga menggunakan teknik konvensional:
Practical Application Of AI
1. Analisa memerlukan Systems In Transmission
perhitungan kompleks Line
2. Menyita waktu untuk
memperhatikan
perhitungan
3. Keakuratan dalam
menganalisa data
sistem secara cepat
dan efisien
TE201428 – Kecerdasan Buatan Teknik dalam Kecerdasan Buatan

Dictatorship If A=> B, C==B Expert system

A put in black box get C,


B put in black box get D, Artificial neural networks
What is the black box?

What if A is 0.7 B and A is


0.3 C? What is the result? Fuzzy logic system

How to get minimum result in the


objective function when we have A, B, Heuristic method
and C between a specific range, what is Swarm algorithm
the solutions in the fast way?
TE201428 – Kecerdasan Buatan Expert System
• Menggunakan pengetahuan yang dimiliki
manusia untuk kondisi tertentu dan
diimplementasikan dalam bentuk bahasa
mesin
• Biasanya menggunakan mekanisme dan
informasi tertentu untuk menyelesaikan
masalah yang tidak bisa diselesaikan
manusia.
• Pemrograman yang teruji dan memiliki
kompetensi di daerah tertentu
• Disebut juga sebagai knowledge based system
atau rule based system
• Contoh:
• Pendiagnosaan kegagalan proteksi relay,
• Monitoring untuk membandingkan system
vulnerability,
• diagnosa kegagalan system dari hasil analisa,
• Menganalisa situasi hasil deskripsi data
sensor
TE201428 – Kecerdasan Buatan Artificial Neural Network
TE201428 – Kecerdasan Buatan Artificial Neural Network

Neuron
TE201428 – Kecerdasan Buatan Artificial Neural Network
• Sistem yang terinspirasi dari struktur biologi yang terdiri dari sebuah set antara input
dan output dari jaring saraf tiruan dimana, setiap neuron menghasilkan satu output
sebagai fungsi dari beberapa input
• Jaring saraf tiruan biasa digunakan untuk mengenali pola (pattern recognition) dan
pengelompokan pola (pattern classification)
• Ada beberapa arsitektur ANN berdasarkan jumlah layer dan topologi dari hubungan
antara pola, feedforward, back propagation atau recurrent, yaitu:
• Multi layer perceptron
• Radial Basis Function
• Back Propagation Neural Network
• Recurrent Neural Neural Network
• Aplikasi: Peramalan daya
TE201428 – Kecerdasan Buatan Fuzzy Logic System

- Sistem logical untuk standarisasi dan formalisasi untuk memetakan suatu ruang input
ke dalam ruang output.
- Memasukkan input fuzzy.
- Mengaplikasikan operator fuzy.
- Mengaplikasikan metode implikasi.
- Komposisi semua output.
- Defuzifikasi.
- Aplikasi:
- State estimation, peramalan beban
dan energi, pengevaluasian
keamanan system, perencanaan
dan pengoperasian daya reaktif
TE201428 – Kecerdasan Buatan Genetic Algorithm (GA)
• Genetic Algorithm adalah metode
pencarian heuristik yang terinspirasi oleh
teori evolusi alam Charles Darwin.
• Algoritma ini mencerminkan proses seleksi
alam di mana individu-individu yang paling
cocok dipilih untuk reproduksi guna
menghasilkan keturunan dari generasi
berikutnya.
TE201428 – Kecerdasan Buatan Swarm Algorithm

• Diinspirasi oleh sistem mahluk hidup yang memliki interaksi lokal antar
individu di dalam kelompok mereka dan interaksi dengan
lingkungannya.
• Contoh:
• Particle Swarm Optimization
• Whale Optimization Algorithm
• Bat algorithm
• Ant colony algorithm
• Chicken swarm optimization
• Bee colony algorithm
• Fireflies algoritm
• Grey-wolf algorithm
• Aplikasi: untuk optimizasi dan analisa data.
TE201428 – Kecerdasan Buatan Swarm Algorithm
Search space
Of solutions

Convergence Curve
TE201428 – Kecerdasan Buatan Swarm Algorithm

Population for X2 = 1:10


Population for X1 = 1:10
Will we get the solutions?
TE201428 – Kecerdasan Buatan Aplikasi AI di STL

• Operation of power system


• unit commitment, hydrothermal coordination, economic dispatch, congestion
management, maintenance scheduling, state estimation, load and power flow.
• Planning of power system like generation expansion planning, power system
reliability, transmission expansion planning, reactive power planning.
• Control of power system like voltage control, stability control, power flow control, load
frequency control.
• Control of power plants like fuel cell power plant control, thermal power plant control.
• Control of network like location, sizing and control of FACTS devices.
• Electricity markets like strategies for bidding, analysis of electricity markets.
• Automation of power system like restoration, management, fault diagnosis, network
security.

AI model design is important to get the correct solutions in time


TE201428 – Kecerdasan Buatan

KESIMPULAN

You might also like