I=
Pakistan Research Repository Home
 

Title of Thesis

Application of Artificial Neural Networks to Short Term Load Forecasting

Author(s)

SYED RIAZ UL HASSNAIN

Institute/University/Department Details
Department of Electrical and Electronics Engineering / University of Engineering and Technology, Peshawar
Session
2009
Subject
Electrical Engineering
Number of Pages
363
Keywords (Extracted from title, table of contents and abstract of thesis)
Application, Artificial, Neural, Networks, Short Term, Load Forecasting, Intelligence, techniques, advantageous, statistical, models

Abstract
In modern complex and highly interconnected power systems, load forecasting is the first and most critical step in operational planning. The ability to predict load from few hours ahead to several days in the future can help utility operators to efficiently schedule and utilize power generation. The main focus of this research is to have an accurate and robust solution to the Short-term Load Forecasting (STLF) problem using Artificial Intelligence based techniques.
Amongst several techniques reported in the literature, Artificial Neural Network (ANN) has been proposed as one of the promising solution for STLF. The ANN is more advantageous than statistical models, because it is able to model a multivariate problem without making complex dependency assumptions among input variables. By learning from training data, the ANN extracts the implicit nonlinear relationship among input variables. However, ANN-based STLF models use Backward Propagation (BP) algorithm for training, which does not ensure convergence and hangs in local minima more often. BP requires much longer time for training, which makes it difficult for realtime application. To overcome this problem, we use Particle Swarm Optimization (PSO) algorithm to evolve directly ANN by considering it as an optimization problem. With PSO responsible for training, we can modify ANN in any way to suit the problem or class of problems. Secondly, load series is complex and exhibit several level of seasonality due to which sometimes ANN is unable to capture the trend. To overcome this shortcoming, we have used modularized approach.
We used smaller ANN models of STLF based on hourly load data and train them through the use of PSO algorithm. A variety of Swarm based ANN hourly load models have been trained and tested over real time data spread over a period of 10 years. Keeping in view the various seasonal effects and cyclical behavior, we divided the load data in different scenarios and results were analyzed and compared. The forecast results in majority of the cases are fairly accurate and prove the promise of proposed methodology. This approach gives better-trained models capable of performing well over time varying window and results in fairly accurate forecasts.

Download Full Thesis
41,302 KB
S. No. Chapter Title of the Chapters Page Size (KB)
1 0 CONTENTS

 

iv
406 KB
2

1

INTRODUCTION

1.1 General

1.2 Problem Statement
1.3 Objectives And Scope
1.4 Original Contributions
1.5 Organization Of Thesis

1
147 KB
3 2 LITERATURE REVIEW

2.1 Hybrid Approach

2.2 Overview Of The Hybrid Based Approaches To STLF
2.3 Conclusions

5
133 KB
4 3 ARTIFICIAL NEURAL NETWORKS

3.1 Introduction

3.2 Biological Neuron
3.3 Back Error Propagation
3.4 Caveats

10
153 KB
5 4 SHORT-TERM LOAD FORECASTING

4.1 Introduction

4.2 Short Term Load Forecasting
4.3 Methods Of Forecasting Loads

21
139 KB
6 5 SHORT TERM LOAD FORECASTING USING PARTICLE SWARM OPTIMIZATION (PSO) BASED ANN APPROACH

5.1 Introduction

5.2 Ant Colony Optimization
5.3 Particle Swarm Optimization
5.4 Introduction To Modularized Approach
5.5 Significance Of Ann Approach
5.6 Particle Swarm Based Optimization (Pso) Based Ann Model
5.7 Pso-Ann Training Approach
5.8 Pre-Processing Of Given Data
5.9 Selection Of Inputs

26
208 KB
7 6 EXPERIMENTAL RESULTS

6.1 Data Set

6.2 Input And Output For The Ann Model
6.3 Performance Of Standard Bp Based Ann And Si Modified Ann
6.4 Comparison Of Results With Conventional Techniques

40
381 KB
8 7 DISCUSSION ON RESULTS

7.1 Results Overview

7.2 Ann Forecast Model For Summers With Daily Temperature
7.3 Comments On Switched Training And Testing
7.4 Comparison Of Old Load Data And New Load Data

67
206 KB
9 8 CONCLUSIONS AND FUTURE PROSPECTS

8.1 Conclusions
8.2 Future Work

73
145 KB
10 9 REFERENCES & APPENDICES


 

75
1,037 KB