Influence of artificial neural network structure on quality of short-term electric energy consumption forecast

Authors:
Publisher website
Google Scholar
Abstract
The influence of an artificial neural network structure on the quality of short-term electric energy consumption forecasts is described. The problem of short-term electric energy consumption forecasting is very important in the daily activity of electricity distribution companies and other industrial enterprises. Accurate electric energy consumption forecast enables optimisation of the costs of electric energy purchase and planning of technological processes. There are many different forecasting methods on the market. The most accurate methods are those based on an artificial neural network technique. An attempt to investigate the influence of a one-directional ANN structure (number of hidden layers and number of neurons in layers) on the short-term forecast quality is presented. The quality of an ANN learning process is also investigated. Negative phenomena observed during the learning process, especially the phenomena of an artificial neural network overlearning, are shown. Computational experiments have been executed on the test problems. Proper data from electricity distribution companies have been taken into account. Results obtained show that the ANN structure has an essential influence on the quality of electric energy consumption forecasts.

This publication has 2 references indexed in Scilit: