Electricity price forecasting on the day-ahead market using machine learning

The price of electricity on the European market is very volatile. This is due both to its mode of production by different sources, each with its own constraints (volume of production, dependence on the weather, or production inertia), and by the difficulty of its storage. Being able to predict the p...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Applied energy Jg. 313; S. 118752
Hauptverfasser: Tschora, Léonard, Pierre, Erwan, Plantevit, Marc, Robardet, Céline
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.05.2022
Elsevier
Schlagworte:
Artificial Intelligence
Computational Engineering, Finance, and Science
Computer Science
Data Structures and Algorithms
Economics and Finance
electricity
electricity costs
Electricity price forecasting
energy
Explainable AI (XAI)
Forecast evaluation
Humanities and Social Sciences
Machine Learning
markets
Open-access benchmark
prediction
prices
weather
Electricity price forecasting
Forecast evaluation
Open-access benchmark
Explainable AI (XAI)
Machine learning
ISSN:0306-2619, 1872-9118
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The price of electricity on the European market is very volatile. This is due both to its mode of production by different sources, each with its own constraints (volume of production, dependence on the weather, or production inertia), and by the difficulty of its storage. Being able to predict the prices of the next day is an important issue, to allow the development of intelligent uses of electricity. In this article, we investigate the capabilities of different machine learning techniques to accurately predict electricity prices. Specifically, we extend current state-of-the-art approaches by considering previously unused predictive features such as price histories of neighboring countries. We show that these features significantly improve the quality of forecasts, even in the current period when sudden changes are occurring. We also develop an analysis of the contribution of the different features in model prediction using Shap values, in order to shed light on how models make their prediction and to build user confidence in models. •Evaluation of several machine learning models for electricity price forecasting.•Methodology is rigorously detailed, the source and the data are made available.•New Machine Learning models are provided and achieved cutting edge results.•Performances of the models are increased by adding new features to the datasets.•XAI techniques are used to explain which features impact most the predictions.•Modeling multiple countries at once improves results.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0306-2619
1872-9118
DOI:10.1016/j.apenergy.2022.118752