Electricity prices forecasting using multilayered perceptron network with Levenberg-Marquardt

In competitive electricity markets in most country, pnce forecasting is becoming increasingly relevant to power producers and consumers. Price forecasts provide crucial infonnation for power producers and consumers to develop bidding strategies in order to maximize benefit. In this paper, a Multi-layer Perceptron (MLP) based neural network model to forecast price profile in electricity market has been presented. Publicly available data acquired from the Australia electricity market were used for training and testing the Artificial Neural Network (ANN). The results obtained through the simulation show that the proposed algorithm is efficient, accurate and can be used to forecast electricity prices.