Day-ahead electricity price forecasting using WT, CLSSVM and EGARCH model

Accurate price forecasting becomes more and more important for all market participants in competitive electricity markets, which can maximize producers’ profits and consumers’ utilities, respectively. In this paper, a new hybrid forecast technique based on wavelet transform (WT), chaotic least squares support vector machine (CLSSVM) and exponential generalized autoregressive conditional heteroskedastic (EGARCH) model is proposed for day-ahead electricity price forecasting. The superiority of this proposed method is examined by using the data acquired from the locational marginal price (LMP) of PJM market and market clearing price (MCP) of Spanish market. Empirical results show that this proposed method performs better than some of the other price forecast techniques.

► Advanced computational methods to solve day-ahead electricity price forecasting.
► Hybrid model has become a common practice to improve the prediction accuracy.
► Validation and verification of numerical results through experiments connects computation models to the real word.