The Evolution of Probabilistic Price Forecasting Techniques: A Review of the Day-Ahead, Intra-Day, and Balancing Markets

TL;DR

The paper tackles the challenge of quantifying uncertainty in electricity price forecasts amid rising renewable penetration by reviewing probabilistic forecasting methods across Day-Ahead, Intraday, and Balancing Markets. It traces the evolution from Bayesian and distribution-based approaches to quantile regression and, more recently, conformal prediction (CP) techniques, highlighting validity-focused developments such as EnbPI and SPCI. Key contributions include a cross-market synthesis of methods, discussion of evaluation metrics and practical deployment considerations, and identification of gaps in IDM and BM where adaptive CP methods could yield the most impact. The work underlines the need for standardized benchmarks, dynamic, low-latency CP extensions, and robust economic evaluations to bridge methodological advances with real-time grid operation and trading needs in modern, renewable-dominated power systems.

Abstract

Electricity price forecasting has become a critical tool for decision-making in energy markets, particularly as the increasing penetration of renewable energy introduces greater volatility and uncertainty. Historically, research in this field has been dominated by point forecasting methods, which provide single-value predictions but fail to quantify uncertainty. However, as power markets evolve due to renewable integration, smart grids, and regulatory changes, the need for probabilistic forecasting has become more pronounced, offering a more comprehensive approach to risk assessment and market participation. This paper presents a review of probabilistic forecasting methods, tracing their evolution from Bayesian and distribution based approaches, through quantile regression techniques, to recent developments in conformal prediction. Particular emphasis is placed on advancements in probabilistic forecasting, including validity-focused methods which address key limitations in uncertainty estimation. Additionally, this review extends beyond the Day-Ahead Market to include the Intra-Day and Balancing Markets, where forecasting challenges are intensified by higher temporal granularity and real-time operational constraints. We examine state of the art methodologies, key evaluation metrics, and ongoing challenges, such as forecast validity, model selection, and the absence of standardised benchmarks, providing researchers and practitioners with a comprehensive and timely resource for navigating the complexities of modern electricity markets.

Figures (6)

• Figure 1: Contrasting granularity of markets
• Figure 2: Quantile forecast of electricity prices
• Figure 3: Parametric probabilistic forecasting methods: Bayesian, Distribution-Based, and Monte Carlo.
• Figure 4: Non-parametric probabilistic forecasting methods: Bootstrap and Historical Simulation.
• Figure 5: Regression-based approaches: Quantile Regression (QR) and Quantile Regression Averaging (QRA).