Empirical evaluation of Time Series Foundation Models for Day-ahead and Imbalance Electricity Price Forecasting in Belgium

2026-05-16

AI Summary

This study evaluates the zero-shot capabilities of time series foundation models for day-ahead and imbalance electricity price forecasting in Belgium, with a focus on their performance under highly volatile market conditions. It presents the first empirical assessment of models such as Chronos-2 (in ARX mode), Chronos-Bolt, and TimesFM 2.5 in a real-world electricity market setting, benchmarking them against conventional machine learning approaches. The results show that Chronos-2 achieves a 5% lower mean absolute error (MAE) than the best ensemble model for day-ahead price prediction, yet consistently exhibits approximately 10% higher MAE for imbalance price forecasting—except for the two-hour-ahead horizon. These findings illuminate both the strengths and limitations of foundation models across normal and extreme market regimes, offering a new paradigm for electricity price forecasting.

Abstract

Recent advances in Time Series Foundation Models (TSFMs) promise zero-shot forecasting capabilities with minimal task-specific training. While these models have shown strong performance across generic benchmarks, their applicability in volatile, complex electricity markets remains underexplored. Addressing this gap, this study provides a systematic empirical evaluation of several TSFMs, specifically Chronos-2 and Chronos-Bolt (developed by Amazon), and TimesFM 2.5 (provided by Google), for forecasting Belgian day-ahead and imbalance electricity prices. For both considered markets, Chronos-2 in ARX mode produces the most accurate forecasts. Compared with the best ensemble prediction from other machine learning methods, Chronos-2's Mean Absolute Error (MAE) is 5% lower for the day-ahead market. In contrast, the model yields 10% higher MAE predicting imbalance prices across all forecast horizons, except for the two-hour-ahead horizon. Moreover, we find that TSFMs exhibit genuine zero-shot forecasting skills but still struggle under extreme market conditions.

Problem

• Time Series Foundation Models
• Electricity Price Forecasting
• Day-ahead Market
• Imbalance Market
• Zero-shot Forecasting

Innovation

• Time Series Foundation Models
• zero-shot forecasting
• electricity price forecasting
• Chronos-2
• imbalance market