Transformer Implementation for Short Term Electricity Load Forecasting, Case Study: Bali, Indonesia

Abstract

Short term load forecasting is a crucial process in ensuring optimal and reliable operation of electric power system which is critical in sustaining highly technological economies. Various approaches and methods have been implemented in forecasting electricity load of a system including statistical methods such as auto regression and machine learning methods such as support vector machine and also deep learning methodology as recurrent neural network methodology which gain popularity in electricity load forecasting nowadays. In this paper, Transformer as a deep learning methodology is used to forecast hourly electricity load in Bali Area. Three lookback days scenario and ten days of forecast period are used to evaluate the performance of the Transformer models. This study suggest that although higher lookback days will give more complicated model due to increasing number of parameters involved, the best overall prediction performance are given by transformer model with 1 day of lookback period. The three model in this study also tend to have low prediction performance in predicting electricity load for weekend or holiday period. Future study using multivariate transformer model is suggested to improve the prediction performance of the transformer model in predicting electricity load in Bali area.