Artificial neural network based hourly load forecasting for decentralized load management

Abstract

Decentralised load management is an essential part of the power system operation. Forecasting load demand at the substation level is generally more difficult and less accurate compared to forecasting total system load demand. In this paper, multi-layered feedforward (MLFF) neural network is used to predict the bus-load demand at the substation level. The MLFF network is trained using the backpropagation (BP) algorithm with an adaptive learning technique. The algorithm is tested for two systems having different load patterns.