CASCADED ARTIFICIAL NEURAL NETWORKS FOR SHORT-TERM LOAD FORECASTING

An application of artificial neural networks (ANNs) to short-term load forecasting is presented in this paper. An algorithm using cascaded l earning algorithm together with the historical load and weather data i s proposed to forecast half-hourly load for the next 24 hours. This ca scaded neural network algorithm (CANNs) includes peak, minimum, and da ily energy prediction as additional input data for the final forecast stage. These additional input data are predicted using the first (ANNs ) model. The networks are trained and tested on the electric power sys tem of Kuwait. The absolute average forecasting error is reduced from 3.367% to 2.707% by applying CANNs as compared to the conventional ANN s. Simulation results indicate that the developed forecasting approach is effective and point to the potential of the methodology for econom ic applications.