Forecasting electricity prices with machine learning: Predictor sensitivity

TL;DR

This paper compares various machine learning models for electricity price forecasting, analyzing the impact of different predictors, and demonstrates that incorporating external variables significantly improves forecast accuracy.

Contribution

It introduces a comprehensive sensitivity analysis of predictor variables in machine learning models for electricity price prediction, highlighting their individual contributions.

Findings

External predictors reduce RMSE by up to 21.96%.

Machine learning models outperform traditional methods in accuracy.

Sensitivity analysis clarifies predictor importance.

Abstract

Purpose: Trading on electricity markets occurs such that the price settlement takes place before delivery, often day-ahead. In practice, these prices are highly volatile as they largely depend upon a range of variables such as electricity demand and the feed-in from renewable energy sources. Hence, accurate forecasts are demanded. Approach: This paper aims at comparing different predictors stemming from supply-side (solar and wind power generation), demand-side, fuel-related and economic influences. For this reason, we implement a broad range of non-linear models from machine learning and draw upon the information-fusion-based sensitivity analysis. Findings: We disentangle the respective relevance of each predictor. We show that external predictors altogether decrease root mean squared errors by up to 21.96%. A Diebold-Mariano test statistically proves that the forecasting accuracy of the proposed machine learning models is superior. Originality: The benefit of adding further predictors has only recently received traction; however, little is known about how the individual variables contribute to improving forecasts in machine learning.