Conformal Prediction for Electricity Price Forecasting in the Day-Ahead and Real-Time Balancing Market

TL;DR

This paper tackles the challenge of reliable probabilistic electricity price forecasting in Day-Ahead and Balancing Markets under renewable-driven volatility. It leverages Conformal Prediction (CP) techniques, notably Ensemble Batch Prediction Intervals (EnbPI) and Sequential Predictive Conformal Inference (SPCI), and introduces a robust QR-CP ensemble (Q-Ens) that fuses quantile regression with CP-based methods. Through extensive case studies in the Irish DAM and BM, the work demonstrates that CP approaches improve PI validity and trading outcomes, while the QR-CP ensemble achieves favorable tradeoffs between interval sharpness and coverage, translating into higher simulated profitability for Battery Energy Storage System (BESS) trading. The findings highlight the practical value of CP in risk management and market participation, while also noting data, computation, and robustness considerations for real-world deployment.

Abstract

The integration of renewable energy into electricity markets poses significant challenges to price stability and increases the complexity of market operations. Accurate and reliable electricity price forecasting is crucial for effective market participation, where price dynamics can be significantly more challenging to predict. Probabilistic forecasting, through prediction intervals, efficiently quantifies the inherent uncertainties in electricity prices, supporting better decision-making for market participants. This study explores the enhancement of probabilistic price prediction using Conformal Prediction (CP) techniques, specifically Ensemble Batch Prediction Intervals and Sequential Predictive Conformal Inference. These methods provide precise and reliable prediction intervals, outperforming traditional models in validity metrics. We propose an ensemble approach that combines the efficiency of quantile regression models with the robust coverage properties of time series adapted CP techniques. This ensemble delivers both narrow prediction intervals and high coverage, leading to more reliable and accurate forecasts. We further evaluate the practical implications of CP techniques through a simulated trading algorithm applied to a battery storage system. The ensemble approach demonstrates improved financial returns in energy trading in both the Day-Ahead and Balancing Markets, highlighting its practical benefits for market participants.

Figures (8)

• Figure 1: Quantile forecast of electricity prices
• Figure 2: Construction of the Ensemble, Q-Ens.
• Figure 3: Interval Width for each model in the DAM
• Figure 4: DAM Coverage for 0.1-0.9 quantile pair
• Figure 5: DAM Coverage for 0.3-0.7 quantile pair