Use of Artificial Neural Networks for Short Term Load Forecasting

Abstract

In order to schedule an effective service and economical capital extension of an electric power distribution system, the system administrator must be able to predict the need for power delivery. Short Term Load Forecasting (STLF) is one of the critical topics of power systems and precise load forecasting is crucial for controlling supply and demand of electricity. This paper provides an overview of innovative methods based on Artificial Neural Networks (ANNs), as well as their current use in the field of STLF. A short review of researchers' work in Multilayer Perceptron (MLP) for STLF is presented. An improved confrontation based on Radial Basis Function Networks (RBFNs) and their advantages are examined. Different optimization techniques, such as clustering, can be used whether to reduce errors and its variations or to speed up computational time, hence resulting in an even more improved model. © 2021 ACM.