Time Series Foundation Models for Energy Load Forecasting on Consumer Hardware: A Multi-Dimensional Zero-Shot Benchmark
This work addresses the reliability of TSFMs for mission-critical energy load forecasting, providing practical benchmarks for grid operations, but it is incremental as it focuses on evaluating existing models rather than introducing new methods.
The paper evaluated four Time Series Foundation Models (TSFMs) for zero-shot electricity demand forecasting on consumer hardware, finding that top models achieved a MASE of 0.31 at long context lengths, a 47% reduction over a baseline, and varied in calibration and robustness under distribution shifts.
Time Series Foundation Models (TSFMs) have introduced zero-shot prediction capabilities that bypass the need for task-specific training. Whether these capabilities translate to mission-critical applications such as electricity demand forecasting--where accuracy, calibration, and robustness directly affect grid operations--remains an open question. We present a multi-dimensional benchmark evaluating four TSFMs (Chronos-Bolt, Chronos-2, Moirai-2, and TinyTimeMixer) alongside Prophet as an industry-standard baseline and two statistical references (SARIMA and Seasonal Naive), using ERCOT hourly load data from 2020 to 2024. All experiments run on consumer-grade hardware (AMD Ryzen 7, 16GB RAM, no GPU). The evaluation spans four axes: (1) context length sensitivity from 24 to 2048 hours, (2) probabilistic forecast calibration, (3) robustness under distribution shifts including COVID-19 lockdowns and Winter Storm Uri, and (4) prescriptive analytics for operational decision support. The top-performing foundation models achieve MASE values near 0.31 at long context lengths (C = 2048h, day-ahead horizon), a 47% reduction over the Seasonal Naive baseline. The inclusion of Prophet exposes a structural advantage of pre-trained models: Prophet fails when the fitting window is shorter than its seasonality period (MASE > 74 at 24-hour context), while TSFMs maintain stable accuracy even with minimal context because they recognise temporal patterns learned during pre-training rather than estimating them from scratch. Calibration varies substantially across models--Chronos-2 produces well-calibrated prediction intervals (95% empirical coverage at 90% nominal level) while both Moirai-2 and Prophet exhibit overconfidence (~70% coverage). We provide practical model selection guidelines and release the complete benchmark framework for reproducibility.