Short-term price forecasting using new wavelet-neural network with data pre filtering in ISO New England market

Abstract

Effective load and price forecasting in presence of the noisy data collection process and complicated load features is important in deregulated power system. This paper presents a method of wavelet neural networks with data pre-filtering for short term price forecasting. The key idea is to use a spike filtering technique to detect spikes in load data and correct them. Wavelet decomposition is then used to decompose the filtered loads into multiple components at different frequencies, separate neural networks are applied to capture the features of individual components, and results of neural networks are then combined to form the final forecasts. To perform moving forecasts, six dedicated wavelet neural networks are used based on test results. Numerical testing demonstrates the effects of data pre-filtering and the accuracy of wavelet neural networks based on a data set from ISO New England.