Hybrid wavelet model for electricity pool-price forecasting in a deregulated electricity market

• Main Authors: Benaouda D., Murtagh F.
• Other Authors: 15844746300
• Format: Conference paper
• Published: 2023
• Subjects: Autoregression; Multi-layer perceptron; Resolution scale; Time-series; Wavelet transform; Energy policy; Marketing; Multilayer neural networks; Regression analysis; Time series analysis; Wavelet transforms; Electricity markets; Hybrid wavelet models; Resolution scales; Electric load forecasting

Electricity supply industry is in the process of deregulation in many countries including Australia. The purpose of deregulation is to give consumers free choices of their electricity supply. Thus, accurate electricity pool price forecasting can provide a set of vital predicted information that helps generation, transmission and retailer participating companies to bid strategically into a deregulated electricity market in order to maximize their profits. In this article, we propose a wavelet multiscale decomposition based autoregressive approach for the prediction of one-hour ahead and one-day ahead pool price based on historical electricity pool price and predicted electricity load data. This approach is based on a multiple resolution decomposition of the signal using the non-decimated or redundant Haar � trous wavelet transform whose advantage is taking into account the asymmetric nature of the time-varying data. There is an additional computational advantage in that there is no need to re-compute the wavelet transform (wavelet coefficients) of the full signal if the electricity pool price data (time series) is regularly updated. We assess results produced by this multiscale autoregressive (MAR) method, in both linear and non-linear variants, with single resolution autoregressive (AR), and multilayer perceptron (MLP) model. Experimental results are based on the New South Wales (Australia) electricity load and pool price data that is provided by the National Electricity Market Management Company (NEMMCO). � 2006 IEEE.