A Reinforcement Learning Based Framework for Holistic Energy Optimization of Sustainable Cloud Data Centers
IEEE Transactions on Services Computing · 2025-01 · 18 (1) · 15-28
DOI: 10.1109/tsc.2024.3495495 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Services Computing, 2025-01. Verfasst von Daming Zhao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Major Project of Inner Mongolia Natural Science Foundation, Research and Application of Key Technology of Big Data for Discipline Inspection and Supervision.
Abstract (Originalsprache)
The widespread adoption of cloud data centers has led to a rise in energy consumption, with the associated carbon emissions posing a further threat to the environment. Cloud providers are increasingly moving towards sustainable data centers powered by renewable energy sources (RES). The existing approaches fail to efficiently coordinate IT and cooling resources in such data centers due to the intermittent nature of RES and the complexity of state and action spaces among different devices, resulting in poor holistic energy efficiency. In this paper, a reinforcement learning (RL) based framework is proposed to optimize the holistic energy consumption of sustainable cloud data centers. First, a joint prediction method MTL-LSTM is developed to accurately evaluate both energy consumption and thermal status of each physical machine (PM) under different optimization scenarios to improve the state space information of the RL algorithm. Then, this framework designs a novel energy-aware approach named BayesDDQN, which leverages Bayesian optimization to synchronize the adjustments of VM migration and cooling parameter within the hybrid action space of the Double Deep Q-Network (DDQN) for achieving the holistic energy optimization. Moverover, the pre-cooling technology is integrated to further alleviate hotspot by making full use of RES. Experimental results demonstrate that the proposed RL-based framework achieves an average reduction of 2.83% in holistic energy consumption and 4.74% in brown energy, which also reduces cooling energy consumption by 13.48% with minimal occurrences of hotspots. Furthermore, the proposed MTL-LSTM method reduces the root mean square error (RMSE) of energy consumption and inlet temperature predictions by nearly half compared to LSTM and XGBoost.
Förderung
- National Natural Science Foundation of China
- Major Project of Inner Mongolia Natural Science Foundation
- Research and Application of Key Technology of Big Data for Discipline Inspection and Supervision
- Science and Technology Plan Special Project of Hohhot
Zitieren
APA
Zhao, D., Zhou, J., Zhai, J., & Li, K. (2025). A Reinforcement Learning Based Framework for Holistic Energy Optimization of Sustainable Cloud Data Centers. IEEE Transactions on Services Computing, 18(1), 15-28. https://doi.org/10.1109/tsc.2024.3495495
Vancouver
Zhao D, Zhou J, Zhai J, Li K. A Reinforcement Learning Based Framework for Holistic Energy Optimization of Sustainable Cloud Data Centers. IEEE Transactions on Services Computing. 2025;18(1):15-28. doi:10.1109/tsc.2024.3495495
BibTeX
@article{Zhao2025,
author = {Zhao, Daming and Zhou, Jiantao and Zhai, Jidong and Li, Keqin},
title = {A Reinforcement Learning Based Framework for Holistic Energy Optimization of Sustainable Cloud Data Centers},
journal = {IEEE Transactions on Services Computing},
year = {2025},
volume = {18},
number = {1},
pages = {15--28},
doi = {10.1109/tsc.2024.3495495}
}
EUVIMED