Short-term hourly load forecasting using PSO-based AR model

Abstract

Load forecasting is essential for effective and stable power system planning and operation. Decision making related to power system operation is influenced by future's electric load patterns. In this paper, particle swarm optimization (PSO) based autoregressive (AR) model is presented for short-term hourly load forecasting. First of all, among several potential input candidates, relevant inputs that have high correlation with prediction model's output are selected. According to the number of selected inputs, the order of AR model is fixed. Finally, AR model's parameters are optimized using PSO that is a global optimization algorithm. To verify the performance, the proposed method is applied to two kinds of real world hourly load dataset in South Korea. The proposed method shows good prediction accuracy.