Probabilistic Low-Voltage Peak Load Forecasting with Time Series Foundation Models Evaluated on Application-Oriented Metrics

2026-07-02

AI Summary

This study addresses key challenges in low-voltage load forecasting, including excessive manual intervention, inadequate uncertainty quantification, inaccurate peak load prediction, and evaluation metrics misaligned with practical grid requirements. Leveraging foundation time series models—Chronos-Bolt, Chronos-2, and TabPFN-TS—the authors conduct short-term probabilistic net load forecasting across 200 real-world low-voltage feeders. They propose novel application-oriented evaluation metrics tailored to utility asset planning and operational cost–risk trade-offs, and further assess model adaptability under missing weather covariates. Experimental results demonstrate that Chronos-2 significantly outperforms six baseline methods, particularly excelling in peak load prediction and the proposed application-driven metrics.

Abstract

Low-voltage load forecasting is an important component in current and future energy systems with a high degree of electrification and decentralized generation. However, current forecasting methods require significant manual effort, often lack uncertainty estimation and proper peak prediction, and they are often not adequately evaluated in terms of grid requirements. In the present study, we provide an extensive evaluation of short-term net load forecasts of 200 real-world low-voltage feeders with a focus on the rapidly evolving time series foundation models. Our study compares Chronos-Bolt, Chronos-2 and TabPFN-TS to six baseline models and demonstrates superior performance, in particular for Chronos-2. An ablation study, in which weather covariates are omitted, shows that time series foundation models adapt to increased uncertainty, despite the importance of weather information. A novel application-oriented metric links the model's forecasting capabilities in peak prediction to the trade-off in grid asset planning and operation between cost reduction and minimizing the risk of failure.

Problem

• low-voltage load forecasting
• peak load prediction
• uncertainty estimation
• application-oriented metrics
• grid requirements

Innovation

• time series foundation models
• probabilistic forecasting
• peak load prediction
• application-oriented metrics
• low-voltage distribution networks