High frequency short-term demand forecasting model for distribution power grid based on ARIMA

Short-term load forecasting is an important issue for power system planning, operation and control. Operating decisions such as dispatch scheduling of generating capacity, reliability analysis, and generation planning can be benefit on accurate load forecasts. So, many research efforts have been expended to increase the accuracy, especially for short-term prediction such as hourly prediction for the next month. In this paper, a high frequency forecast model based on ARIMA was proposed to estimate the relationships between user's demand and various variables. This method is used to forecast hourly and quarter-hourly electricity demand for next few days ahead. The performance of this methodology is validated with real data from the Guangdong Power Grid Corporation (GPGC), which is the largest province grid corporation in China.