发表机构
Purdue University（普渡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对LLM服务多维度环境影响，提出PRISM统一框架，区分配置与部署影响，识别条件并平衡四维度，区域路由实验中中位最坏遗憾降低50.2%。
AI 中文摘要
大语言模型（LLM）服务在能源消耗、碳排放、水资源消耗和生物多样性损失方面对环境产生影响。然而，这些维度在很大程度上是孤立评估的，导致不清楚它们何时以及如何导致不同的优化决策。我们提出了PRISM，一个统一框架，用于在能源、碳、水和生物多样性影响方面表征和优化LLM服务。我们的分析揭示了一个根本性区别：计算配置决定能源消耗，而LLM服务的部署地点和时间决定其碳、水和生物多样性影响。在固定的部署选择和仅运营核算下，所有维度保持相同的基于能源的配置排名。部署排名在不同维度间可能不同，而当体现影响超过生命周期交叉边界时，它们可以打破配置不变性。PRISM识别这些条件，量化跨维度遗憾，并平衡四个维度。在区域路由实验中，PRISM相对于最强基线将中位最坏情况遗憾降低了50.2%。
英文摘要
Large language model (LLM) serving has environmental impacts across energy consumption, carbon emission, water consumption, and biodiversity loss. Yet these dimensions are largely evaluated in isolation, leaving it unclear when and how they lead to different optimization decisions. We present PRISM, a unified framework for characterizing and optimizing LLM serving across energy, carbon, water, and biodiversity impacts. Our analysis reveals a fundamental distinction: computing configurations determine energy consumption, whereas where and when LLM serving is deployed determine its carbon, water, and biodiversity impacts. Under a fixed deployment choice and operational-only accounting, all dimensions preserve the same energy-based configuration ranking. Deployment rankings can diverge across dimensions, while embodied impacts can break configuration invariance when they exceed a lifecycle crossover boundary. PRISM identifies these conditions, quantifies cross-dimensional regrets, and balances the four dimensions. In regional-routing experiments, PRISM reduces median worst-case regret by 50.2% relative to the strongest baseline.
Comments41 pages, 30 figures, 13 tables
