English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Electricity prices in liberalized markets are determined by the supply anddemand for electric power, which are in turn driven by various externalinfluences that vary strongly in time. In perfect competition, the merit orderprinciple describes that dispatchable power plants enter the market in theorder of their marginal costs to meet the residual load, i.e. the difference ofload and renewable generation. Many market models implement this principle topredict electricity prices but typically require certain assumptions andsimplifications. In this article, we present an explainable machine learningmodel for the prices on the German day-ahead market, which substantiallyoutperforms a benchmark model based on the merit order principle. Our model isdesigned for the ex-post analysis of prices and thus builds on various externalfeatures. Using Shapley Additive exPlanation (SHAP) values, we can disentanglethe role of the different features and quantify their importance from empiricdata. Load, wind and solar generation are most important, as expected, but windpower appears to affect prices stronger than solar power does. Fuel prices alsorank highly and show nontrivial dependencies, including strong interactionswith other features revealed by a SHAP interaction analysis. Large generationramps are correlated with high prices, again with strong feature interactions,due to the limited flexibility of nuclear and lignite plants. Our resultsfurther contribute to model development by providing quantitative insightsdirectly from data.

Understanding electricity prices beyond the merit order principle using explainable AI