Saved in:
Bibliographic Details
Main Authors: Yang, Kang, Hanafy, Walid A., Shenoy, Prashant, Srivastava, Mani
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