Saved in:
Bibliographic Details
Main Authors: Wang, Ziying, Zhang, Ying, Wang, Lei, Lin, Yuzhang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.27207
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914518264709120
author Wang, Ziying
Zhang, Ying
Wang, Lei
Lin, Yuzhang
author_facet Wang, Ziying
Zhang, Ying
Wang, Lei
Lin, Yuzhang
contents Short-term load forecasting for AI data centers presents new challenges because it is computing-driven, with heterogeneous job arrivals, sizes, and durations exhibiting bursty, non-stationary dynamics. Compared with traditional load types, data center loads are less researched and can pose greater threats to the efficiency and stability of power grids. To close the gap, this paper proposes a regime-adaptive ensemble learning forecasting algorithm to predict computing-driven dynamic workloads in AI data centers. A weight-learned neural network within an ensemble learning framework is developed to exploit the complementary strengths of two machine learning (ML) submodels across varying operating regimes. Furthermore, a novel feature engineering strategy is developed to incrementally learn from a non-stationary data stream. Thus, the ensemble weights are dynamically optimized to facilitate adaptive calibration of inter-submodel contributions. Comparative case studies on the MIT Supercloud dataset demonstrate that the proposed method significantly enhances load forecasting accuracy and adaptivity across various regimes, and the selected combination of ML models for ensemble learning outperforms other possible combinations. To the best of our knowledge, our method is the first to reduce minute-class forecasting errors for AI data center loads to below 1%, highlighting its potential for grid-interactive coordination and demand response.
format Preprint
id arxiv_https___arxiv_org_abs_2604_27207
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Regime-Adaptive Weighted Ensemble Learning for Computing-Driven Dynamic Load Forecasting in AI Data Centers
Wang, Ziying
Zhang, Ying
Wang, Lei
Lin, Yuzhang
Systems and Control
Short-term load forecasting for AI data centers presents new challenges because it is computing-driven, with heterogeneous job arrivals, sizes, and durations exhibiting bursty, non-stationary dynamics. Compared with traditional load types, data center loads are less researched and can pose greater threats to the efficiency and stability of power grids. To close the gap, this paper proposes a regime-adaptive ensemble learning forecasting algorithm to predict computing-driven dynamic workloads in AI data centers. A weight-learned neural network within an ensemble learning framework is developed to exploit the complementary strengths of two machine learning (ML) submodels across varying operating regimes. Furthermore, a novel feature engineering strategy is developed to incrementally learn from a non-stationary data stream. Thus, the ensemble weights are dynamically optimized to facilitate adaptive calibration of inter-submodel contributions. Comparative case studies on the MIT Supercloud dataset demonstrate that the proposed method significantly enhances load forecasting accuracy and adaptivity across various regimes, and the selected combination of ML models for ensemble learning outperforms other possible combinations. To the best of our knowledge, our method is the first to reduce minute-class forecasting errors for AI data center loads to below 1%, highlighting its potential for grid-interactive coordination and demand response.
title Regime-Adaptive Weighted Ensemble Learning for Computing-Driven Dynamic Load Forecasting in AI Data Centers
topic Systems and Control
url https://arxiv.org/abs/2604.27207