Load forecasting for power system planning using a genetic-fuzzy-neural networks approach

Prediction of future load demand is important for secure operation of power systems and their economical utilization. A number of algorithms have been suggested for solving this problem. In this paper, a genetic-fuzzy-neural networks approach for mid-term load forecasting is proposed. In this paper the relationship between humidity, temperature and load is identified with a case study for a particular region in Oman. The output load obtained is corrected using a correction factor from neural networks model, which depends on previous set of loads. Data for monthly peak load of four years has been used for training the model, which then forecasts the load of the fifth year. The model has been validated using actual data from an electricity company.