arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.01459cs.DCcs.AIcs.LG
收藏

面向地理分布式数据中心AI推理工作负载的博弈论深度强化学习方法以最小化碳排放与能源成本

Game-Theoretic Deep Reinforcement Learning to Minimize Carbon Emissions and Energy Costs for AI Inference Workloads in Geo-Distributed Data Centers

Hewlett Packard Labs(慧与实验室);Colorado State University(科罗拉多州立大学)

Ninad Hogade, Sudeep Pasricha

AI总结:

本文提出博弈论深度强化学习(GT-DRL)方法,通过将非合作博弈论融入DRL框架,优化地理分布式数据中心AI推理工作负载分配,在保证计算性能的同时有效降低碳排放和云运营成本。

摘要:

由于人工智能(AI)工作负载的增加,数据中心正在消耗越来越多的能源,这对环境产生了负面影响,并提高了运营成本。在保持数据中心性能的同时降低运营开支和碳排放是一个具有挑战性的问题。本工作引入了一种结合博弈论(Game Theory, GT)与深度强化学习(Deep Reinforcement Learning, DRL)的独特方法,用于优化地理分布式数据中心中AI推理工作负载的分配,以减少碳排放和云运营(能源+数据传输)成本。所提出的技术将非合作博弈论的原理集成到DRL框架中,使数据中心能够在考虑硬件资源异构性、电力价格的动态特性、数据中心间的数据传输成本以及碳足迹的同时,做出关于工作负载分配的智能决策。我们进行了大量实验,将我们的博弈论DRL(GT-DRL)方法与当前基于DRL的方法及其他优化技术进行了比较。结果表明,我们的策略在减少碳排放和最小化云运营成本方面优于最先进的方法,同时不影响计算性能。这项工作对于在跨不同地理位置处理AI推理工作负载的数据中心实现可持续性和成本效益具有重要意义。

英文摘要:

Data centers are increasingly using more energy due to the rise in Artificial Intelligence (AI) workloads, which negatively impacts the environment and raises operational costs. Reducing operating expenses and carbon emissions while maintaining performance in data centers is a challenging problem. This work introduces a unique approach combining Game Theory (GT) and Deep Reinforcement Learning (DRL) for optimizing the distribution of AI inference workloads in geo-distributed data centers to reduce carbon emissions and cloud operating (energy + data transfer) costs. The proposed technique integrates the principles of non-cooperative Game Theory into a DRL framework, enabling data centers to make intelligent decisions regarding workload allocation while considering the heterogeneity of hardware resources, the dynamic nature of electricity prices, inter-data center data transfer costs, and carbon footprints. We conducted extensive experiments comparing our game-theoretic DRL (GT-DRL) approach with current DRL-based and other optimization techniques. The results demonstrate that our strategy outperforms the state-of-the-art in reducing carbon emissions and minimizing cloud operating costs without compromising computational performance. This work has significant implications for achieving sustainability and cost-efficiency in data centers handling AI inference workloads across diverse geographic locations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑