Day-ahead Price Forecasting in Victoria Electricity Market Using Particle Swarm Optimization Based Neural Network Model

In this paper, a particle swarm optimization (PSO) based neural network (NN) model to forecast price profile in real-time Victoria Electricity Market (VEM) has been presented. The PSO algorithm offers the capability of converging towards the global minimum point of a complex error surface. In order to take advantage of the homogeneity of the time series forty-eight separate feed-forward neural networks have been used for modeling 48 half-hourly trading intervals of the day. Forecasting performance of the proposed model has been compared with (i) heuristic technique, (ii) least square estimation (LSE) based model and already published works. Forecasting results show that PSO based NN model is more accurate than the other models and can be practically used by the participants to bid effectively as it predicts price before closing of window for submission of bids.