Navigating the Safety-Fidelity Trade-off: Massive-Variate Time Series Forecasting for Power Systems via Probabilistic Scenarios
This work provides a large-scale benchmark and a new model for probabilistic time series forecasting in power systems, addressing the lack of constraint-aware evaluation at scale.
The authors introduce PowerPhase, a probabilistic forecasting benchmark for power systems with up to 36,964 channels, and propose PowerForge, a scenario-based forecaster that achieves the best average rank across all grids, outperforming eight baselines.
Probabilistic forecasting models are increasingly deployed on multivariate systems with distinct channel physics and operational constraints, but existing benchmarks evaluate neither property at scale. Public canonical multivariate benchmarks cap out at 2,000 channels, while power-system benchmarks either lack temporal structure or probabilistic evaluation. We introduce PowerPhase, a probabilistic forecasting benchmark built on six transmission grids ranging from 2,000 to 36,964 jointly forecasted channels, more than an order of magnitude beyond popular canonical multivariate benchmarks. Each target trajectory is the output of an AC power-flow solve, and PowerPhase ships with constraint-aware metrics, including Safety_mBrier, NECV, and CVaR-alpha, that complement CRPS and Distortion. Across eight baselines and three seeds, distributional accuracy and constraint satisfaction rank models differently, a trade-off we term safety-fidelity. We further propose PowerForge, a scenario-based quantile forecaster with type-specific decoding heads and a causal bridge between variable groups, which achieves the best average rank on every grid.