Short term load forecasting using data mining technique

Accurate load and price forecasting are become very essential in power system planning. This will increase the efficiency of electricity generation and distribution while maintaining sufficient security of operation. This paper proposes method for Short Term Load Forecasting using data mining technique. The data provided by utility of Malaysia were analyzed to see its behavior or load pattern in a day during weekday and weekend in Peninsular Malaysia. By considering day-type in a week, five model of SARIMA (Time Series approach) have been created using Minitab. The forecasting is held based on the similar repeating trend of patterns from historical load data. The half hourly load data for six weeks had been plotted according to day-type to forecast the load demand for a day ahead. The MAPEs (Mean Absolute Percentage Error) obtained were ranging from 1.07% to 3.26%. Hence this modeling had improved the accuracy of forecasting rather than using only one model for all day in a week.