IEEJ Transactions on Power and Energy
Online ISSN : 1348-8147
Print ISSN : 0385-4213
ISSN-L : 0385-4213
Development of Peak Load Forecasting System using Neural Networks and Fuzzy Theory
Yoshiteru UekiTetsuro MatsuiHiroshi EndoTatsuyosi KatoRyosaku Araya
Author information

1995 Volume 115 Issue 9 Pages 1038-1045


This paper presents a peak load forecasting system using multi layer neural networks and fuzzy theory. Electric load forecasting in power systems is very important task for it's reliability and economic operation. Especially daily peak load forecasting is one of the basic operation of generation scheduling for the following day. Therefore, many statistical methods have been developed and used for such forecasting. Although, it has been difficult to construct a proper functional model, or needed huge effort.
The system we developed is applied by neural network and fuzzy theory to forecast for daily, weekly and monthly peak load . The system consists of an engineering workstation(EWS) and a personal computer(PC). EWS is for learning and data-bases, PC for man-machine interface such as forecasting operation.
The system has used under actual task since june '93. The result evaluated by absolute mean error is 1.63% for 10 months. From the results shown here, the system applied by neural network and fuzzy theory has high validity.

Information related to the author
© The Institute of Electrical Engineers of Japan
Previous article Next article