Search papers, labs, and topics across Lattice.
This study evaluates short-term net load forecasting for 200 real-world low-voltage feeders using advanced time series foundation models, specifically Chronos-Bolt, Chronos-2, and TabPFN-TS, against six baseline models. The findings reveal that Chronos-2 significantly outperforms the others, particularly in peak load prediction, while also adapting to increased uncertainty when weather data is omitted. A novel application-oriented metric is introduced to assess the trade-off between cost reduction and risk of failure in grid asset planning and operation, highlighting the practical implications of the forecasting capabilities.
Chronos-2 not only excels in peak load forecasting but also adapts to uncertainty without relying heavily on weather data, reshaping expectations for low-voltage load predictions.
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.
