XWind: A Cross-site Router for Large Language Model Inference Serving at Renewable Energy Farms
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917523331481600 |
|---|---|
| author | Reddy, Tella Rajashekhar Deshmukh, Atharva Yu, Liangcheng Zhang, Chaojie Shepperd, Mike Gandhi, Rohan Parayil, Anjaly Iyengar, Srinivasan Manchepalli, Ajay Bhattacherjee, Debopam |
| author_facet | Reddy, Tella Rajashekhar Deshmukh, Atharva Yu, Liangcheng Zhang, Chaojie Shepperd, Mike Gandhi, Rohan Parayil, Anjaly Iyengar, Srinivasan Manchepalli, Ajay Bhattacherjee, Debopam |
| contents | AI power demand is growing at an unprecedented rate while power grids are often ailing and struggle to keep up. Grid expansion comes with high capital expenditure and long-distance transmission losses, yet there is abundant renewable energy at the source, just not matched to demand.
This paper proposes a complementary AI infrastructure deployment model, AI Greenferencing, that brings modular AI compute to renewable energy sources, focusing on wind, allowing AI footprint expansion, generating local behind-the-meter demand for renewable sites, and helping ease the growing strain on power utilities. Our feasibility analysis shows that 890+ GW of wind capacity lies within 50 ms network round trip time of Azure data centers, and that site-wise right-sizing combined with spatial complementarity of wind energy keeps aggregate fleet utilization on par with traditional deployments.
To serve inference requests under variable wind power, we build XWind, a lightweight, reactive, and workload-agnostic AI inference router that uses only real-time signals: inference latency, KV-cache utilization, and queue depth, to dynamically configure sites and distribute requests. Evaluated on a real 64-GPU A100 testbed emulating three wind-powered sites with Azure production traces, XWind reduces P99 end-to-end latency by up to 52% over the strongest contender (also our idea) and by up to 98% over baselines such as power-capping and GPU idling, with consistent gains across workload types, load levels, and GPU generations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_23348 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | XWind: A Cross-site Router for Large Language Model Inference Serving at Renewable Energy Farms Reddy, Tella Rajashekhar Deshmukh, Atharva Yu, Liangcheng Zhang, Chaojie Shepperd, Mike Gandhi, Rohan Parayil, Anjaly Iyengar, Srinivasan Manchepalli, Ajay Bhattacherjee, Debopam Distributed, Parallel, and Cluster Computing Artificial Intelligence Networking and Internet Architecture AI power demand is growing at an unprecedented rate while power grids are often ailing and struggle to keep up. Grid expansion comes with high capital expenditure and long-distance transmission losses, yet there is abundant renewable energy at the source, just not matched to demand. This paper proposes a complementary AI infrastructure deployment model, AI Greenferencing, that brings modular AI compute to renewable energy sources, focusing on wind, allowing AI footprint expansion, generating local behind-the-meter demand for renewable sites, and helping ease the growing strain on power utilities. Our feasibility analysis shows that 890+ GW of wind capacity lies within 50 ms network round trip time of Azure data centers, and that site-wise right-sizing combined with spatial complementarity of wind energy keeps aggregate fleet utilization on par with traditional deployments. To serve inference requests under variable wind power, we build XWind, a lightweight, reactive, and workload-agnostic AI inference router that uses only real-time signals: inference latency, KV-cache utilization, and queue depth, to dynamically configure sites and distribute requests. Evaluated on a real 64-GPU A100 testbed emulating three wind-powered sites with Azure production traces, XWind reduces P99 end-to-end latency by up to 52% over the strongest contender (also our idea) and by up to 98% over baselines such as power-capping and GPU idling, with consistent gains across workload types, load levels, and GPU generations. |
| title | XWind: A Cross-site Router for Large Language Model Inference Serving at Renewable Energy Farms |
| topic | Distributed, Parallel, and Cluster Computing Artificial Intelligence Networking and Internet Architecture |
| url | https://arxiv.org/abs/2605.23348 |