Predicting long-term electricity prices using modified support vector regression method

• Published in: Electrical engineering Vol. 106; no. 4; pp. 4103 - 4114
• Main Authors: Abroun, Mehdi, Jahangiri, Alireza, Shamim, Ahmad Ghaderi, Heidari, Hanif
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 2024; Springer Nature B.V
• Subjects: Artificial neural networks; Deregulation; Economic forecasting; Economics and Management; Effectiveness; Electrical Engineering; Electrical Machines and Networks; Electricity pricing; Energy costs; Energy Policy; Energy technology; Engineering; Original Paper; Power Electronics; Prices; Regression models; Support vector machines; Weather; Weather forecasting; Support vector regression; Monthly electricity price; Forecasting; Grey Verhulst method; Time series
• ISSN: 0948-7921; 1432-0487
• DOI: 10.1007/s00202-023-02174-x

The energy market operates in a highly deregulated and competitive environment, where electricity price plays a crucial role. Forecasting electricity prices presents a significant challenge due to the influence of complex factors such as weather patterns, fuel costs, and the advancement of renewable energy technologies. This study focuses on monthly electricity prices in four neighboring European countries: Bulgaria, Greece, Hungary, and Romania, which share similar weather conditions and economic characteristics. The research investigates the efficacy of four forecasting methods: Grey Verhulst Model (GVM), Nonlinear Regression, Feedforward Neural Network, and Support Vector Regression (SVR). These methods are applied to both short-term (1 month-ahead) and long-term (up to 7 months) electricity price forecasting in the aforementioned countries. The findings reveal that GVM proves suitable for short-term predictions. However, when it comes to long-term forecasting, SVR accurately captures the trends and turning points in electricity prices, albeit with unsatisfactory error rates. To address this issue, a modified version of SVR, referred to as Modified SVR (MSVR), is proposed to mitigate the errors. The results demonstrate that MSVR is an effective approach for long-term electricity price prediction.