Short term load forecasting for Iran National Power System and its regions using multi layer perceptron and fuzzy inference systems

Many researchers have investigated short term load forecasting (STLF) in recent decades because of its importance in power system operation. In this paper a multi layers perceptron (MLP) neural network (NN) is designed for load forecasting in normal weather condition and ordinary days. The architecture of the proposed network is a three-layer feedforward neural network whose parameters are tuned by Levenberg-Marquardt backpropagation (LMBP) augmented by an early stopping (ES) method tried out for increasing the speed of convergence. For abrupt weather changes and special holidays, we have added a fuzzy inference systems (FIS) to modify the forecasted load appropriately. We show that this method satisfy the Iran electricity market rule. Simulation examples for Iran National Power System (INPS) and any of its regions, Bakhtar Region Electric Co. (BREC) demonstrate capabilities of proposed method for load forecasting.