Long-term electric load forecast in Kuwaiti and Egyptian power systems

This paper presents an efficient methodology for forecasting annual peak demands in electrical power systems. The proposed approach is developed as an accurate alternative forecasting method to other existing methods. The method is based on cuckoo search algorithm. It is used to minimize the error associated with the estimated model parameters in order for the forecasted demands to follow the real load data. Real data from Kuwaiti and Egyptian networks are used to perform this study. Three long-term forecasting models have been used in this research work to measure the robustness of the developed estimation tool. Durbin-Watson statistical test is conducted to validate selected models’ adequacy, and model transformation is applied as a remedial measure to ill-conditioned time series data when needed. Forecasting outcomes are reported and compared to those obtained using other forecasting techniques. The performance of the proposed method is examined and evaluated. Results reveal that cuckoo search algorithm has is a promising potential as a viable tool for parameter estimation.