An ANN decision support for optimal judgment of Egyptian power system load forecasting

Total system load forecast reflects current and future trends and is carried out for power system networks. To fully integrate the advantages of several forecasting models and improve the accuracy of load forecast results, the application of these methods for power system load forecasting is introduced in this paper. In this study, the prediction of peak electric loads in Egypt up to year 2020 is discussed using artificial neural networks (ANN). Backpropagation and a recurrent neural network were designed and tested for this purpose. This study is concerned with a complex process that involves decision-making situations. In order to decide which of the proposed projects should be retained in the final project, numerous conflicting criteria must be considered. This study focuses on Egyptian data that seem to influence long-term electric load demands. The actual yearly data, are used. As a result, the demands from 2004 to 2020 are predicted. Based on the forecast results, some suggestions for the Egyptian network are presented.