FM-CAC: Carbon-Aware Control for Battery-Buffered Edge AI via Time-Series Foundation Models
For edge AI deployments, this work addresses the unmanaged carbon emissions problem with a proactive control framework that achieves substantial emission reductions without sacrificing QoS.
FM-CAC reduces carbon emissions by up to 65.6% in battery-buffered edge AI systems while maintaining near-maximum inference accuracy by jointly optimizing software pipeline variants, hardware operating points, and battery actions using time-series foundation models for carbon forecasting.
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.