Home | Computer Systems Science & Engineering | Engineering Intelligent Systems | Books
 
     
   
Introduction
Contents
Ordering
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   

Neural Networks Applications in Power Systems

Introduction

The continuing increase in the size and complexity of power systems has led to the need for sophisticated computer based tools for solving the difficult problems that arise in the planning, operation, diagnosis and design of these systems. We have seen the introduction of mathematical programming, control theory, simulation tools and expert systems in recent times. These tools have been quite successful in the different classes of problems they have been used for. Their use, however, presupposes that one is either able to:

(a) build a mathematical model for the problem, or
(b) find an expert who is capable of solving the problem and extract the knowledge of the expert and represent it in today's technology.

There is still a class of problems which does not satisfy the above two criteria. These problems are either characterised by

(a) large amounts of data that are used in forecasting or diagnosis, or
(b) by large dimensionality requiring large solution times.

This has led to the exploration of the use of neural networks for the solution of these power system problems. The recent interest has seen the growth of symposia which include neural networks as an integral part of power system solution techniques.
The motivation for this book arises from the need to

(1) provide material in a form that is understandable and useful to power system engineers or graduate student programs, and
(2) to make clear a statement of the present state of the art to assist researchers in the area.

The first chapter of this book provides a tutorial on neural network techniques which is couched in the language of power systems. The second chapter provides a survey of the state of the art with regard to applications of neural networks to power system problems. Chapters 3 to 10 provide a number of case studies of the application of neural networks to power system problems. These have been selected to demonstrate the different classes of problems within the power system area that can be usefully tackled using the technology. It also illustrates the different types of neural networks that can be utilized for power system problems.

Tharam Dillon
Dagmar Niebur


Contents

1 Tutorial on Artificial Neural Networks for Power Systems
Tharam Dillon and Dagmar Niebur

2 Artificial Neural Networks for Power Systems: State of the Art
Dagmar Niebur

3 Component Fault Diagnosis
Yoshio Izui

4 System Fault Diagnosis using Device-specific Artificial Neural Networks
Edmund Handschin, Dietmar Kuhlmann and Wolfgang Hoffmann

5 Techniques for Security Assessment
M A El-Sharkawi and S Weerasooriya

6 Static Security Assessment
Dagmar Niebur and Alain J Germond

7 Neural Networks for Assessing the Transient Stability of Electric Power Systems
Dejan J Sobajic, Yoh-Han Pao and Miodrag Djukanovic

8 Application to Unit Commitment
H Sasaki

9 Application of Revised Boltzmann Machines to Topological Observability Analysis
Hiroyuki Mori

10 An Application on Load Modelling for Dynamic Calculation
T T Nguyen

11 Short Term Load Forecasting using Neural Networks
Tharam Dillon and Sabrina Sestito

Ordering

Copies may be ordered direct from the publishers priced 48.00 plus 7.00 postage and packing (US$74 plus $12 postage and packing).
Send a purchase orders, check or Mastercard/Visa/AMEX card details to:

CRL Publishing Ltd, PO Box 31, Market Harborough, Leics LE16 7BP, UK.
Fax: +44 (0)1858 431649, email: admin@crlpublishing.co.uk

The book is also available through bookshops via teleordering and other such systems.
Quote ISBN no. 0 9527874 0 7

Edited by T S Dillon and D Niebur

 

9 Priory Business Park, Wistow Road, Kibworth Beauchamp, Leicester, LE8 0RX | Tel: +44 116 279 2299 | Fax: +44 116 279 2277
E-mail: admin@crlpublishing.co.uk