Design of artificial neural networks for short-term load forecasting. Part 1: Self-organising feature maps for day type identification

Abstract
A new approach using artificial neural networks (ANNs) is proposed for short-term load forecasting. To forecast the hourly loads of a day, the hourly load pattern and the peak and valley loads of the day must be determined. In paper I a neural network based on self-organising feature maps to identify those days with similar hourly load patterns is developed. These days with similar load patterns are said to be of the same day type. The load pattern of the day under study is obtained by averaging the load patterns of several days in the past which are of the same day type as the given day. In Part II of the paper a feedforward multilayer neural network is designed to predict daily peak load and valley load. Once the peak load and valley load and the hourly load pattern are available, the desired hourly loads can be readily computed. The effectiveness of the proposed neural network is demonstrated by the short-term load forecasting of the Taiwan Power Company.

This publication has 2 references indexed in Scilit: