Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.16448 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914485142290432 |
|---|---|
| author | Yang, Kang Hanafy, Walid A. Shenoy, Prashant Srivastava, Mani |
| author_facet | Yang, Kang Hanafy, Walid A. Shenoy, Prashant Srivastava, Mani |
| contents | As edge AI deployments scale to billions of devices running always-on, real-time compound AI pipelines, they represent a massive and largely unmanaged source of energy consumption and carbon emissions. To reduce carbon emissions while maximizing Quality-of-Service (QoS), this paper proposes FM-CAC, a proactive carbon-aware control framework that leverages a battery as an active temporal buffer. By decoupling energy acquisition from energy consumption, FM-CAC can maximize the use of low-carbon energy, substantially reducing carbon emissions. At each control step, FM-CAC jointly optimizes the software pipeline variant, the hardware operating point, and the battery charging and discharging actions. To support this decision process, FM-CAC leverages edge-friendly Time-Series Foundation Models (TSFMs) for zero-shot carbon forecasting and integrates these forecasts into a dynamic programming solver with deferred cost attribution to prevent myopic battery depletion. Results show that FM-CAC reduces carbon emissions by up to 65.6% while maintaining near-maximum inference accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_16448 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FM-CAC: Carbon-Aware Control for Battery-Buffered Edge AI via Time-Series Foundation Models Yang, Kang Hanafy, Walid A. Shenoy, Prashant Srivastava, Mani Systems and Control Machine Learning As edge AI deployments scale to billions of devices running always-on, real-time compound AI pipelines, they represent a massive and largely unmanaged source of energy consumption and carbon emissions. To reduce carbon emissions while maximizing Quality-of-Service (QoS), this paper proposes FM-CAC, a proactive carbon-aware control framework that leverages a battery as an active temporal buffer. By decoupling energy acquisition from energy consumption, FM-CAC can maximize the use of low-carbon energy, substantially reducing carbon emissions. At each control step, FM-CAC jointly optimizes the software pipeline variant, the hardware operating point, and the battery charging and discharging actions. To support this decision process, FM-CAC leverages edge-friendly Time-Series Foundation Models (TSFMs) for zero-shot carbon forecasting and integrates these forecasts into a dynamic programming solver with deferred cost attribution to prevent myopic battery depletion. Results show that FM-CAC reduces carbon emissions by up to 65.6% while maintaining near-maximum inference accuracy. |
| title | FM-CAC: Carbon-Aware Control for Battery-Buffered Edge AI via Time-Series Foundation Models |
| topic | Systems and Control Machine Learning |
| url | https://arxiv.org/abs/2604.16448 |