A hybrid wavelet-ELM based short term price forecasting for electricity markets

Accurate electricity price forecasting is a formidable challenge for market participants and managers owing to high volatility of the electricity prices. Price forecasting is also the most important management goal for market participants since it forms the basis of maximizing profits. This study investigates the performance of a novel neural network technique called Extreme Learning Machine (ELM) in the price forecasting problem. Keeping in view the risk associated with electricity markets with highly volatile prices, relying on a single technique is not so profitable. Therefore ELM has been coupled with the Wavelet technique to develop a hybrid model termed as WELM (wavelet based ELM) to improve the forecasting accuracy as well as reliability. In this way, the unique features of each tool are combined to capture different patterns in the data. The robustness of the model is further enhanced using the ensembling technique. Performances of the proposed models are evaluated by using data from Ontario, PJM, New York and Italian Electricity markets. The experimental results demonstrate that the proposed method is one of the most suitable price forecasting techniques. (C) 2013 Elsevier Ltd. All rights reserved.