Probabilistic multivariate electricity price forecasting using implicit generative ensemble post-processing

TL;DR

This paper introduces a novel likelihood-free ensemble post-processing method for multivariate probabilistic electricity price forecasting, capturing dependencies and outperforming benchmarks on German market data.

Contribution

It proposes an implicit generative ensemble framework that improves joint distribution estimation for electricity prices, enhancing uncertainty quantification.

Findings

Outperforms established model combination benchmarks

Successfully captures dependency structures in multivariate forecasts

Demonstrated on German day-ahead market data

Abstract

The reliable estimation of forecast uncertainties is crucial for risk-sensitive optimal decision making. In this paper, we propose implicit generative ensemble post-processing, a novel framework for multivariate probabilistic electricity price forecasting. We use a likelihood-free implicit generative model based on an ensemble of point forecasting models to generate multivariate electricity price scenarios with a coherent dependency structure as a representation of the joint predictive distribution. Our ensemble post-processing method outperforms well-established model combination benchmarks. This is demonstrated on a data set from the German day-ahead market. As our method works on top of an ensemble of domain-specific expert models, it can readily be deployed to other forecasting tasks.