# Sustainable Carbon-Aware and Water-Efficient LLM Scheduling in Geo-Distributed Cloud Datacenters

arXiv: https://arxiv.org/abs/2505.23554 · HTML: https://mlsanity.com/paper/2505.23554/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 29 May 2025.

## Builds on (most cited first, 12 of 12)

- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems](https://mlsanity.com/paper/2401.17644/) (2024)
- [SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient](https://mlsanity.com/paper/2301.11913/) (2023)
- [The Unseen AI Disruptions for Power Grids: LLM-Induced Transients](https://mlsanity.com/paper/2409.11416/) (2024)
- [Towards a Systematic Survey for Carbon Neutral Data Centers](https://mlsanity.com/paper/2110.09284/) (2021)
- [Energy and Network Aware Workload Management for Geographically Distributed Data Centers](https://mlsanity.com/paper/2106.00066/) (2021)
- [SHIELD: Sustainable Hybrid Evolutionary Learning Framework for Carbon, Wastewater, and Energy-Aware Data Center Management](https://mlsanity.com/paper/2308.13086/) (2023)
- [GreenCourier: Carbon-Aware Scheduling for Serverless Functions](https://mlsanity.com/paper/2310.20375/) (2023)
- [MOSAIC: A Multi-Objective Optimization Framework for Sustainable Datacenter Management](https://mlsanity.com/paper/2311.08583/) (2023)
- [Game-Theoretic Deep Reinforcement Learning to Minimize Carbon Emissions and Energy Costs for AI Inference Workloads in Geo-Distributed Data Centers](https://mlsanity.com/paper/2404.01459/) (2024)
- [CASA: A Framework for SLO and Carbon-Aware Autoscaling and Scheduling in Serverless Cloud Computing](https://mlsanity.com/paper/2409.00550/) (2024)
- [A Framework for SLO, Carbon, and Wastewater-Aware Sustainable FaaS Cloud Platform Management](https://mlsanity.com/paper/2410.11875/) (2024)

## Built on by (most cited first, 4 of 4)

- [Agentic Services Computing](https://mlsanity.com/paper/2509.24380/) (2025)
- [MARLIN: Multi-Agent Game-Theoretic Reinforcement Learning for Sustainable LLM Inference in Cloud Datacenters](https://mlsanity.com/paper/2605.13496/) (2026)
- [AI Inference as Relocatable Electricity Demand: A Latency-Constrained Energy-Geography Framework](https://mlsanity.com/paper/2604.27855/) (2026)
- [Dissecting the Carbon-SLO Tension in Geo-Distributed LLM Serving](https://mlsanity.com/paper/2610.14571/) (2026)

## Abstract (arXiv)

In recent years, Large Language Models (LLM) such as ChatGPT, CoPilot, and Gemini have been widely adopted in different areas. As the use of LLMs continues to grow, many efforts have focused on reducing the massive training overheads of these models. But it is the environmental impact of handling user requests to LLMs that is increasingly becoming a concern. Recent studies estimate that the costs of operating LLMs in their inference phase can exceed training costs by 25x per year. As LLMs are queried incessantly, the cumulative carbon footprint for the operational phase has been shown to far exceed the footprint during the training phase. Further, estimates indicate that 500 ml of fresh water is expended for every 20-50 requests to LLMs during inference. To address these important sustainability issues with LLMs, we propose a novel framework called SLIT to co-optimize LLM quality of service (time-to-first token), carbon emissions, water usage, and energy costs. The framework utilizes a machine learning (ML) based metaheuristic to enhance the sustainability of LLM hosting across geo-distributed cloud datacenters. Such a framework will become increasingly vital as LLMs proliferate.