TY - JOUR
T1 - Forecasting day-ahead electricity prices in Europe
T2 - The importance of considering market integration
AU - Lago Garcia, Jesus
AU - De Ridder, Fjo
AU - Vrancx, Peter
AU - De Schutter, Bart
N1 - Accepted Author Manuscript
PY - 2018
Y1 - 2018
N2 - 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.
AB - 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.
KW - Bayesian optimization
KW - Deep neural networks
KW - Electricity market integration
KW - Electricity price forecasting
KW - Functional ANOVA
UR - http://www.scopus.com/inward/record.url?scp=85036461446&partnerID=8YFLogxK
U2 - 10.1016/j.apenergy.2017.11.098
DO - 10.1016/j.apenergy.2017.11.098
M3 - Article
SN - 0306-2619
VL - 211
SP - 890
EP - 903
JO - Applied Energy
JF - Applied Energy
ER -