Understanding electricity prices beyond the merit order principle using explainable AI

TL;DR

This paper introduces an explainable AI model for German day-ahead electricity prices that surpasses traditional merit order models by analyzing external factors and their interactions.

Contribution

The study presents a novel explainable machine learning approach that outperforms existing models and provides detailed insights into feature importance and interactions affecting electricity prices.

Findings

Load, wind, and solar generation are key price determinants.

Wind power influences prices more strongly than solar power.

Fuel prices have complex, nontrivial effects and interactions.

Abstract

Electricity prices in liberalized markets are determined by the supply and demand for electric power, which are in turn driven by various external influences that vary strongly in time. In perfect competition, the merit order principle describes that dispatchable power plants enter the market in the order of their marginal costs to meet the residual load, i.e. the difference of load and renewable generation. Many market models implement this principle to predict electricity prices but typically require certain assumptions and simplifications. In this article, we present an explainable machine learning model for the prices on the German day-ahead market, which substantially outperforms a benchmark model based on the merit order principle. Our model is designed for the ex-post analysis of prices and thus builds on various external features. Using Shapley Additive exPlanation (SHAP) values, we can disentangle the role of the different features and quantify their importance from empiric data. Load, wind and solar generation are most important, as expected, but wind power appears to affect prices stronger than solar power does. Fuel prices also rank highly and show nontrivial dependencies, including strong interactions with other features revealed by a SHAP interaction analysis. Large generation ramps are correlated with high prices, again with strong feature interactions, due to the limited flexibility of nuclear and lignite plants. Our results further contribute to model development by providing quantitative insights directly from data.