Authors
- Haoyu Jiang Zhejiang University
- Boan Qu Zhejiang University
- Junjie Zhu Zhejiang University
- Fanjie Zeng Zhejiang University
- Xiaojie Lin Zhejiang University
- Wei Zhong Zhejiang University
DOI:
https://doi.org/10.1609/aaai.v40i1.37011Abstract
The explosive growth of artificial intelligence is exponentially escalating computational demand, inflating data center energy use and carbon emissions, and spurring rapid deployment of green data centers to relieve resource and environmental stress. Achieving sub-minute orchestration of renewables, storage, and loads, while minimizing PUE and lifecycle carbon intensity, hinges on accurate load forecasting. However, existing methods struggle to address small-sample scenarios caused by cold start, load distortion, multi-source data fragmentation, and distribution shifts in green data centers. We introduce HyperLoad, a cross-modality framework that exploits pre-trained large language models (LLMs) to overcome data scarcity. In the Cross-Modality Knowledge Alignment phase, textual priors and time-series attributes are mapped to a common latent space, maximizing the utility of prior knowledge. In the Multi-Scale Feature Modeling phase, domain-aligned priors are injected through adaptive prefix-tuning, enabling rapid scenario adaptation, while an Enhanced Global Interaction Attention mechanism captures cross-device temporal dependencies. The public GreenData dataset is released for benchmarking. Under both data-sufficient and data scarce regimes, HyperLoad consistently surpasses state-of-the-art (SOTA) baselines, demonstrating its practicality for sustainable green data center management.
How to Cite
Jiang, H., Qu, B., Zhu, J., Zeng, F., Lin, X., & Zhong, W. (2026). HyperLoad: A Cross-Modality Enhanced Large Language Model-Based Framework for Green Data Center Cooling Load Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 40(1), 480–488. https://doi.org/10.1609/aaai.v40i1.37011
Issue
Section
AAAI Technical Track on Application Domains I