arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.07810eess.SYcs.SY
收藏

具有分布式优化的温度感知LLM推理调度在大规模地理分布边缘数据中心中的应用

Temperature-Aware Scheduling of LLM Inference in Large-Scale Geo-Distributed Edge Data Centers with Distributed Optimization

Chongqing University(重庆大学);Flinders University(弗林德斯大学);Loughborough University(拉夫堡大学);Shanghai Jiao Tong University(上海交通大学);University of South Australia(南澳大学);Murdoch University(默多克大学)

Arash Khalatbarisoltani, Amin Mahmoudi, Jie Han, Muhammad Saeed, Wenxue Liu, Jinwen Li, Solmaz Kahourzade, Amirmehdi Yazdani, Xiaosong Hu

AI总结:

本研究提出一种温度感知方法,通过分布式优化共同优化LLM的能耗、碳排放、首次令牌时间和水资源消耗,以提升地理分布边缘数据中心的可持续性。

摘要:

大型语言模型(LLM)对数据中心环境的影响正成为一个重要问题。尽管许多努力集中在减少LLM的训练开销上,但推理阶段的碳排放和水资源消耗往往超过训练成本。数据中心的冷却系统在此背景下至关重要,但通常使用一个与位置无关的效率项来建模。然而,其能效高度受环境温度影响,不同地理区域的温度差异可能显著。利用这种温度多样性可以帮助降低总冷却能耗并提高边缘数据中心的性能。为了解决与LLM相关的关键可持续性问题,本研究提出了一种温度感知方法,旨在共同优化LLM的能耗、碳排放、首次令牌时间以及水资源消耗。该方法采用基于交替方向乘子法的分布式优化算法,旨在增强澳大利亚地理分布边缘数据中心中LLM托管的可持续性。我们的方法展示了冷却能耗的减少,并提高了地理分布云环境的整体成本效率。

英文摘要:

The environmental impact of Large Language Models (LLMs) on data centers hosting these models is becoming a significant concern. While many efforts have focused on reducing the substantial training overhead of LLMs, carbon and water consumption during the inference phase can often surpass the costs associated with their training. The cooling systems of data centers are crucial in this context, but they are frequently modeled with a location-independent efficiency term. However, their energy efficiency is highly influenced by ambient temperature, which can vary significantly across different geographical locations. Leveraging this temperature diversity can help reduce total cooling energy costs and improve the performance of edge data centers. To address these critical sustainability issues related to LLMs, this study proposes a temperature-aware approach that co-optimizes LLM energy costs, carbon emissions, time-to-first token, and water consumption. The approach employs a distributed optimization algorithm based on an alternating direction method of multipliers, aimed at enhancing the sustainability of LLM hosting across geo-distributed edge data centers in Australia. Our method demonstrates reductions in cooling energy consumption and improves overall cost efficiency for geo-distributed cloud environments.

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。

↑