面向电网的 AI 数据中心概率负荷预测基准
Grid-Oriented Probabilistic Load Forecasting for AI Data Centers
拿 448 张 GPU 的真实功耗数据做负荷预测基准，LightGBM 校准后覆盖率从 63.4% 提到 87.3%，备用成本省近 10%，做电力调度或数据中心运维的可以看看。
一篇 arXiv 论文基于 448-GPU AI 集群的实测功耗构建了开放的电网侧负荷预测基准。评估分四个阶段：概率预测、在线不确定性校准、时序场景生成和全网备用容量测算。在集群利用率变化后，quantile LightGBM 在名义 90% 区间上仅达到 63.4% 覆盖率，经在线工况条件校准后提升到 87.3%。基于历史预测误差重建时间依赖关系后，斜坡统计偏差下降，三项预测任务的备用成本降低 7.4-10.6%。
Grid-Oriented Probabilistic Load Forecasting for AI Data Centers
Probabilistic load forecasts for AI data centers need to represent both uncertainty under changing workloads and temporal dependence to support grid operations. This paper develops an open, grid-oriented benchmark using measured GPU power from a 448-GPU AI cluster. Forecasts are evaluated through four stages: probabilistic prediction, online uncertainty calibration, temporal scenario generation, and horizon-wide reserve sizing. Following a change in cluster utilization, a quantile LightGBM forecast achieves only 63.4% coverage for a nominal 90% interval, while online regime-conditioned calibration increases coverage to 87.3%. Even with well-calibrated marginal forecasts, independent sampling produces unrealistic ramp distributions and excessive reserve procurement. Reconstructing temporal dependence from historical forecast errors reduces the discrepancy in ramp statistics and lowers realized reserve cost by 7.4-10.6% across three forecasting tasks. These findings show that marginal forecast quality alone is insufficient for operational decisions and motivate joint evaluation of calibration, temporal structure, and decision outcomes.