Particle Swarm Optimization based Local Linear Wavelet Neural Network for forecasting electricity prices

This paper proposes a Local Linear Wavelet Neural Network (LLWNN) - a combination of Artificial Neural Network and Local Linear Wavelet Technique-to predict electricity prices for one hour to twenty four hours in advance. The prices of Ontario electricity market are taken as experimental data. Multilayer Perceptron (MLP) model has also been discussed for comparison purpose. Backpropagation learning algorithm is used to train both the models. Further to get more accuracy, both the models have been integrated with Particle Swarm Optimization (PSO). The Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) are used to find out the forecasting performance of the proposed model.