Short-term load forecasting under EU-AI Act Requirements in Safety-Critical Environments: Results from a 41-day live challenge on the aggregated German transmission-grid load

2026-08-05

AI Summary

This study addresses the European Union AI Act’s compliance requirements for critical infrastructure—specifically, determinism, reproducibility, and auditability—by designing and evaluating a short-term electricity load forecasting system with embedded regulatory compliance. Built upon the open-source framework spotforecast2-safe, the system integrates anomaly detection with gap-aware preprocessing, calendar and weather covariates, recursive multi-step forecasting, and hyperparameter optimization to accurately predict 24-hour-ahead transmission-level load across Germany over a 41-day evaluation period. Results demonstrate that the proposed lightweight, transparent, and localized model (e.g., macl2l) achieves predictive performance on par with billion-parameter foundation models such as Chronos-2, significantly outperforms the ENTSO-E official benchmark, and offers superior energy efficiency and auditability—thereby achieving, for the first time, a synergistic alignment between high-accuracy forecasting and compliance with the EU AI Act.

Abstract

Short-term load forecasting (STLF) play a vital role in the electric power industry. It serves infrastructure that European and German law designate as critical. Determinism, reproducibility, and auditability are engineering requirements rather than optional extras. STLF is no longer purely an accuracy problem. It is also a software-engineering and compliance problem. This paper describes results from a 41-day live challenge that evaluated a complete STLF pipeline for the aggregated German transmission-grid load. The pipeline is based on the open-source Python library spotforecast2-safe, which implements the EU-AI Act Requirements in Safety-Critical Environments by design. The pipeline predicts the 24 hourly load values of a target day from European Network of Transmission System Operators for Electricity (ENTSO-E) data. It includes anomaly detection and gap-aware data preparation, calendar and weather covariates, a recursive multi-step forecasting algorithm, and hyperparameter tuning. Forecast accuracy is measured against the official ENTSO-E day-ahead forecast. The EU-AI act compliant spotforecast2-safe pipeline beats the ENTSO-E baseline. In-context models show competitive performance. Transparent, low-cost, and auditable local models (referred to as macl2l in this paper) are competitive with more than 100-million-parameter large, energy-intensive pre-trained foundation models such as chronos-2. The challenge infrastructure, the complete submission history of all teams, and the frozen final leaderboard are publicly available.

Problem

• short-term load forecasting
• EU-AI Act
• safety-critical environments
• compliance
• auditability

Innovation

• EU-AI Act compliance
• short-term load forecasting
• safety-critical systems
• auditable AI
• lightweight forecasting models