An Artificial Neural Networks Forecasting for Malaysia’s Load

Abstract

In this paper, two artificial neural networks models, namely the multilayer feedforward neural
network and the recurrent neural network are applied for Malaysia's load forecasting. A half hourly
load data is divided equally into three distinct sets for training, validation and testing.
Backpropagation is selected as the learning algorithm whereas the transfer function for both hidden
layer and output layer is sigmoid the function. The forecasting performances were compared between
these two models. The results show that, the sum squared error (SSE) of multilayer feedforward
neural network were the lowest hence the multilayer feedforward neural network is a better model for
a half hourly Malaysia's load.