Mid Term Load Forecasting of the Country Using Statistical Methodology: Case study in Thailand

The paper describes the statistical methodology of multiple linear regression (MLR) and autoregressive integrated moving average (ARIMA) methods for mid term load forecasting of the country. The mid term load forecast has many applications such as maintenance scheduling, fuel reserve planning and unit commitment. However, the monthly peak load is a nonlinear, and non-stationary signal. Therefore, this paper proposed a statistical methodology to solve this problem which using multiple linear regression, and autoregressive integrated moving average, based on historical series of electric peak load, weather, and new economic variables such as consumer price index, and industrial index. This paper focuses on the forecasting of monthly peak load for 12 months ahead. This study focused on the mid term load forecasting of peak load demand for Thailand. Finally, we compared between MLR and ARIMA method that the results obtained the autoregressive integrated moving average method proves to be the best accuracy more than the multiple linear regression method.