Forecasting day-ahead electricity prices in Europe: The importance of considering market integration. (1st February 2018)

• Record Type: Journal Article
• Authors: Lago, Jesus; De Ridder, Fjo; Vrancx, Peter; De Schutter, Bart
• Is Part Of: Applied energy. Volume 211(2018)
• Page Start: 890
• Page End: 903
• Publication Date: 2018-02-01
• Subjects: Electricity price forecasting -- Electricity market integration -- Deep neural networks -- Functional ANOVA -- Bayesian optimization; Power (Mechanics) -- Periodicals; Energy conservation -- Periodicals; Energy conversion -- Periodicals; 621.042
• DOI: 10.1016/j.apenergy.2017.11.098
• Languages: English
• ISSNs: 0306-2619

Abstract

Highlights: Models to include market integration in electricity price forecasting are proposed. The forecasters lead to accuracy improvements that are statistically significant. Deep neural networks are used as based models of the larger modeling framework. A forecasters that predicts prices in various markets leads to the best results. A novel feature selection algorithm based on functional ANOVA is proposed. Abstract: Motivated by the increasing integration among electricity markets, in this paper we propose two different methods to incorporate market integration in electricity price forecasting and to improve the predictive performance. First, we propose a deep neural network that considers features from connected markets to improve the predictive accuracy in a local market. To measure the importance of these features, we propose a novel feature selection algorithm that, by using Bayesian optimization and functional analysis of variance, evaluates the effect of the features on the algorithm performance. In addition, using market integration, we propose a second model that, by simultaneously predicting prices from two markets, improves the forecasting accuracy even further. As a case study, we consider the electricity market in Belgium and the improvements in forecasting accuracy when using various French electricity features. We show that the two proposed models lead to improvements that are statistically significant. Particularly, due to market integration, the predictive accuracy is improved from 15.7% to 12.5% sMAPE (symmetric mean absolute percentage error). In addition, we show that the proposed feature selection algorithm is able to perform a correct assessment, i.e. to discard the irrelevant features.