Green-LLM: Optimal Workload Allocation for Environmentally-Aware Distributed Inference
For LLM service providers, this work offers a method to reduce operational costs and environmental impacts through optimal workload distribution.
This paper proposes an optimization model for allocating LLM inference workloads across heterogeneous edge data centers to minimize energy consumption, carbon emissions, and water usage while improving user experience, with numerical results validating the approach.
This letter investigates the optimal allocation of large language model (LLM) inference workloads across heterogeneous edge data centers (DCs) over time. Each DC features on-site renewable generation and faces dynamic electricity prices and spatiotemporal variability in renewable availability. The central question is: how can inference workloads be optimally distributed to the DCs to minimize energy consumption, carbon emissions, and water usage while enhancing user experience? This letter proposes a novel optimization model for LLM service providers to reduce operational costs and environmental impacts. Numerical results validate the efficacy of the proposed approach.