FM-CAC: Carbon-Aware Control for Battery-Buffered Edge AI via Time-Series Foundation Models

arXiv:2604.16448v1 Announce Type: cross Abstract: 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.

Related

• A KL Lens on Quantization: Fast, Forward-Only Sensitivity for Mixed-Precision SSM-Transformer Models
• MSTN: A Lightweight and Fast Model for General TimeSeries Analysis
• Logo-LLM: Local and Global Modeling with Large Language Models for Time Series Forecasting
• BioTrain: Sub-MB, Sub-50mW On-Device Fine-Tuning for Edge-AI on Biosignals
• AIPC: Agent-Based Automation for AI Model Deployment with Qualcomm AI Runtime

Source: arXiv cs.LG | 2026-04-21