Day-Ahead Electricity Price Forecasting Using Merit-Order Curves Time Series

TL;DR

This paper presents a simple, efficient framework for predicting day-ahead electricity supply and demand curves, leading to more accurate price forecasts than traditional price-based models, especially during volatile periods.

Contribution

The paper introduces a novel curve-based forecasting method that outperforms existing models in accuracy for day-ahead electricity prices using merit-order curves.

Findings

Curve-based model improves forecast accuracy by ~5%.

Significant accuracy gains during mid-day hours.

Method is computationally efficient and robust.

Abstract

We introduce a general, simple, and computationally efficient framework for predicting day-ahead supply and demand merit-order curves, from which both point and probabilistic electricity price forecasts can be derived. We conduct a rigorous empirical comparison of price forecasting performance between the proposed curve-based model, i.e., derived from predicted merit-order curves, and state-of-the-art price-based models that directly forecast the clearing price, using data from the Italian day-ahead market over the 2023-2024 period. Our results show that the proposed curve-based approach significantly improves both point and probabilistic price forecasting accuracy relative to price-based approaches, with average gains of approximately 5%, and improvements of up to 10% during mid-day hours, when prices occasionally drop due to high renewable generation and low demand.