Recent Advances in Probabilistic Electricity Price Forecasting: A Review of Methods and Evaluation Metrics

Abstract

Electricity price forecasting has traditionally relied on point predictions, which provide a single expected value for each future delivery period. However, the high volatility, spikes, heavy tails, negative prices and regime changes observed in modern electricity markets make point forecasts insufficient for many trading, bidding, storage, scheduling and risk-management decisions. This review focuses on probabilistic electricity price forecasting (PEPF), which represents uncertainty through quantiles, prediction intervals, predictive densities and multivariate scenarios. It systematizes recent developments in post-processing methods, Quantile Regression Averaging, conformal prediction, Bayesian and heteroscedastic models, distributional neural networks, copula-based approaches, normalizing flows, generative models and scenario generation. Particular attention is paid to probabilistic forecast evaluation, including proper scoring rules, calibration diagnostics and statistical testing. The review highlights the transition from marginal uncertainty quantification toward coherent multivariate and decision-oriented forecasting, and identifies open challenges related to calibration, dependence modeling, benchmark design, economic value assessment and reproducibility.