Forecasting spot electricity prices: Deep learning approaches and empirical comparison of traditional algorithms. (1st July 2018)

• Record Type: Journal Article
• Authors: Lago, Jesus; De Ridder, Fjo; De Schutter, Bart
• Is Part Of: Applied energy. Volume 221(2018)
• Page Start: 386
• Page End: 405
• Publication Date: 2018-07-01
• Subjects: Electricity price forecasting -- Deep learning -- Benchmark study; Power (Mechanics) -- Periodicals; Energy conservation -- Periodicals; Energy conversion -- Periodicals; 621.042
• DOI: 10.1016/j.apenergy.2018.02.069
• Languages: English
• ISSNs: 0306-2619

Abstract

Highlights: A novel deep learning framework to forecast electricity prices is proposed. The framework leads to accuracy improvements that are statistically significant. The largest benchmark to date in electricity price forecasting is presented. 27 state-of-the-art methods for predicting electricity prices are compared. Machine learning models are shown to, in general, outperform statistical methods. Abstract: In this paper, a novel modeling framework for forecasting electricity prices is proposed. While many predictive models have been already proposed to perform this task, the area of deep learning algorithms remains yet unexplored. To fill this scientific gap, we propose four different deep learning models for predicting electricity prices and we show how they lead to improvements in predictive accuracy. In addition, we also consider that, despite the large number of proposed methods for predicting electricity prices, an extensive benchmark is still missing. To tackle that, we compare and analyze the accuracy of 27 common approaches for electricity price forecasting. Based on the benchmark results, we show how the proposed deep learning models outperform the state-of-the-art methods and obtain results that are statistically significant. Finally, using the same results, we also show that: (i) machine learning methods yield, in general, a better accuracy than statistical models; (ii) moving average terms do not improve the predictive accuracy; (iii) hybrid models do not outperform their simpler counterparts.