Peak-aware short-term load forecasting across distribution grid aggregation levels
Peak-Aware Short-Term Load Forecasting Across Distribution Grid Aggregation Levels
For those working on grid management or energy forecasting, this paper provides a detailed comparison of models for peak-aware short-term load forecasting, which is crucial for congestion management and asset protection.
This paper studies short-term load forecasting for distribution system operators, focusing on high-demand periods.
It compares models like LightGBM, XGBoost, Chronos Bolt, and Chronos-2 across three aggregation levels (area codes, substations, and low-voltage feeders).
Chronos-2 achieves the best performance in high-demand periods, reducing mean HD-NMAE by 20-51% compared to gradient boosted models.
The study uses datasets from the UK and Switzerland and highlights the importance of peak-aware evaluation.
Peak-Aware Short-Term Load Forecasting Across Distribution Grid Aggregation Levels
For distribution system operators, short-term load forecasting (STLF) supports congestion management, voltage control, and asset protection. Most existing approaches focus on overall accuracy across all time steps and neglect performance during high-demand (HD) periods, where larger forecast errors can increase the risk of congestion and voltage violations. In this paper, we study peak-aware STLF across three operator-relevant distribution grid aggregation levels, area codes (AC), secondary substations (SUB), and low-voltage (LV) feeders, using open datasets from the United Kingdom and Switzerland. We compare statistical baselines, machine learning models (LightGBM and XGBoost), and recent time-series foundation models (Chronos Bolt and Chronos-2) under a peak-aware evaluation framework that reports both overall and HD forecasting performance using NMAE and MAPE. The results show that Chronos-2 achieves the best HD performance across all aggregation levels, with HD-NMAE and HD-MAPE of 0.039 and 4.53% at AC, 0.080 and 9.45% at SUB, and 0.138 and 16.14% at LV, while Chronos-Bolt consistently ranks second best. Compared with the gradient boosted ML models, Chronos-2 reduces mean HD-NMAE by about 20-51% across levels while remaining best or near-best on the overall metrics. A quantile analysis of the probabilistic Chronos outputs further identifies aggregation-specific operating points, and runtime measurements indicate that foundation model inference is fast enough for practical deployment. Overall, the findings highlight peak-aware evaluation and aggregation specific quantile selection as a practical pathway toward more operationally relevant STLF in distribution networks.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Chronos-2, load forecasting, power grid, Chronos.
Source attribution: curated from arXiv cs.LG (@Souhardya Chattopadhyay, Julian Oelhaf, Antonia Schoening, Jessica Deuschel, Bitan Bhattacharyya, Christian Bergler, Andreas Maier, Siming Bayer).