A NEURAL-NET APPROACH TO ECONOMIC-POWER DISPATCH

An improved method for achieving the economic power dispatch using an artificial neural network (ANN) is proposed in the present paper. The ANN is constructed according to the back propagation learning rule which is an iterative gradient algorithm designed to adjust the interconnection weights among processing elements. The developed ANN was used to plan the optimal dispatch of each generating unit by training data. The data are derived by using the Lagrange multipliers method to analyze economic dispatch problems of the Taiwan power system (TPS). To demonstrate the effectiveness of the proposed approach, the economic dispatch of 21 thermal units in Taiwan was performed. Numerical results show that the system production cost was minimal and the time taken for processing the economic dispatch problems was reduced. Hence, the ANN will be a valuable tool to assist system dispatchers in handling the on-line economic dispatch of TPS.