A hybrid intelligent algorithm for short-term energy price forecasting in the Ontario market

Price forecasting is a crucial information for market participants in an electricity market. However, the electricity price is a complex signal due to its nonlinearity, stochasticity, and time dependent behavior. This paper presents a novel hybrid intelligent algorithm that uses the combination of a data filtering technique based on the wavelet transform (WT), an optimization technique based on firefly (FF) algorithm, and a soft computing model based on fuzzy ARTMAP (FA) network. The innovative contribution of this paper is an application of the FF algorithm to optimize FA network that utilizes the historical ill-behaved energy price time-series through the WT. Good forecast performance and adaptability of the proposed hybrid WT+FF+FA m o d e l to changes in the data is illustrated using the Ontario market power system data. The test results demonstrates that the proposed hybrid technique is able to improve the day-ahead price forecasting performance significantly when compared with other conventional soft computing models available in literature.