Short Term Load Forecasting Using an Artificial Neural Network Trained by Artificial Immune System Learning Algorithm

Load forecasting is very essential to the operation of electric utility. It is a pre-requisite to economic dispatch of electrical power and enhances the efficiency besides ensuring reliable operation of a power system. Electrical energy demand is highly dependent on various independent variables such as the weather, temperature, holidays, and days in a week. The accuracy of the forecast is important to ensure consistent electrical power supply to customer without compromising the economic aspect of the power system operation. In this paper, an Artificial Neural Network (ANN) trained by the Artificial Immune System (AIS) learning algorithm is proposed for short term load forecasting model. Two sets of electrical energy demand data were used to test the capability of the proposed algorithm. Based on the results obtained, it shows that the proposed AIS learning algorithm is capable to provide a comparable forecast to that of Artificial Neural Network with Back Propagation (BP) as the learning algorithm. Hence, this indicates that Artificial Immune System could be implemented as an alternative learning algorithm for an Artificial Neural Network.