NEURAL-NETWORK-BASED SHORT-TERM LOAD FORECASTING USING WEATHER COMPENSATION

This paper presents a novel technique for electric load forecasting ba sed on neural weather compensation. Our proposed method is a nonlinear generalization of Box and Jenkins approach for nonstationary time-ser ies prediction. A weather compensation neural network is implemented f or one-day ahead electric load forecasting. Our weather compensation n eural network can accurately predict the change of actual electric loa d consumption from the previous day. The results, based on Hong Kong I sland historical load demand, indicate that this methodology is capabl e of providing a more accurate load forecast with a 0.9% reduction in forecast error.