Artificial neural network based peak load forecasting using Levenberg–Marquardt and quasi-Newton methods

Abstract

Daily electrical peak-load forecasting has been done using the feedforward neural network based on the Levenberg-Marquardt back-propagation algorithm, Broyden-Fletcher-Goldfarb-Shanno back-propagation algorithm and one-step secant backpropagation algorithm by incorporating the effect of eleven weather parameters, the type of day and the previous day peak load information. To avoid the trapping of the network into a state of local minima, the optimisation of user-defined parameters viz. learning rate and error goal has been performed. Training data set has been selected using a growing window concept and is reduced as per the nature of the day and the season for which the forecast is made. For redundancy removal in the input variables, reduction of the number of input variables has been done by the principal component analysis method of factor extraction. The resultant data set is used for the training of a three-layered neural network. To increase the learning speed, the weights and biases are initialised according to the Nguyen and Widrow method. To avoid over-fitting, an early stopping of training is done at the minimum validation error.