PriceFM: Foundation Model for Probabilistic Electricity Price Forecasting
By: Runyao Yu , Chenhui Gu , Jochen Stiasny and more
Potential Business Impact:
Predicts European electricity prices better.
Electricity price forecasting in Europe presents unique challenges due to the continent's increasingly integrated and physically interconnected power market. While recent advances in deep learning and foundation models have led to substantial improvements in general time series forecasting, most existing approaches fail to capture the complex spatial interdependencies and uncertainty inherent in electricity markets. In this paper, we address these limitations by introducing a comprehensive and up-to-date dataset across 24 European countries (38 regions), spanning from 2022-01-01 to 2025-01-01. Building on this groundwork, we propose PriceFM, a spatiotemporal foundation model that integrates graph-based inductive biases to capture spatial interdependencies across interconnected electricity markets. The model is designed for multi-region, multi-timestep, and multi-quantile probabilistic electricity price forecasting. Extensive experiments and ablation studies confirm the model's effectiveness, consistently outperforming competitive baselines and highlighting the importance of spatial context in electricity markets. The dataset and code can be found at https://github.com/runyao-yu/PriceFM.
Similar Papers
WindFM: An Open-Source Foundation Model for Zero-Shot Wind Power Forecasting
Machine Learning (CS)
Predicts wind power accurately for any location.
Benchmarking Pre-Trained Time Series Models for Electricity Price Forecasting
Machine Learning (CS)
Predicts electricity prices better for trading.
Benchmarking Pre-Trained Time Series Models for Electricity Price Forecasting
Machine Learning (CS)
Helps predict electricity prices better for trading.