Reliable Grid Forecasting: State Space Models for Safety-Critical Energy Systems
This work addresses the safety-critical issue of grid forecasting for energy operators, focusing on operational risk rather than just statistical accuracy, though it is incremental in applying existing models to a new evaluation framework.
The paper tackles the problem of grid load forecasting for safety-critical energy systems by introducing a grid-specific evaluation framework that measures operational risk, and demonstrates that the S-Mamba model achieves a lower reserve margin (14.12%) compared to iTransformer (16.66%) under tail-risk conditions.
Accurate grid load forecasting is safety-critical: under-predictions risk supply shortfalls, while symmetric error metrics mask this operational asymmetry. We introduce a grid-specific evaluation framework--Asymmetric MAPE, Under-Prediction Rate, and Reserve Margin--that directly measures operational risk rather than statistical accuracy alone. Using this framework, we conduct a systematic evaluation of Mamba-based State Space Models for California grid forecasting on a weather-aligned CAISO TAC-area dataset spanning Nov 2023--Nov 2025 (84,498 hourly records across 5 transmission areas). Our analysis reveals that standard accuracy metrics are poor proxies for operational safety: models with identical MAPE can require vastly different reserve margins. We demonstrate that forecast errors are weakly but significantly associated with temperature (r = 0.16, p < 10^{-16}), motivating weather-aware modeling rather than loss function modification alone. The S-Mamba model achieves the lowest Reserve_{99.5}% margin (14.12%) compared to 16.66% for iTransformer, demonstrating superior forecast reliability under a 99.5th-percentile tail-risk reserve proxy.