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

• URL: http://arxiv.org/abs/2604.16448v1
• Date: Tue, 07 Apr 2026 17:23:06 GMT
• Title: FM-CAC: Carbon-Aware Control for Battery-Buffered Edge AI via Time-Series Foundation Models
• Abstract summary: Edge AI deployments scale to billions of devices running always-on, real-time compound AI pipelines.<n>This paper proposes FM-CAC, a proactive carbon-aware control framework that leverages a battery as an active temporal buffer.<n>Results show that FM-CAC reduces carbon emissions by up to 65.6% while maintaining near-maximum inference accuracy.
• Score: 4.9890124441309185
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 papers

• Emission-Aware Reinforcement Learning for Sustainable Electric Vehicle Charging and Carbon Dioxide Reduction Under Varying Renewable Penetration [1.4498318750453458]
  Electric Vehicle (EV) adoption challenges power distribution networks through peak load spikes, voltage instability, and transformer overloads from uncoordinated charging.<n>Existing approaches rarely treat real-time carbon intensity or fluctuating renewable energy (RE) availability as primary scheduling objectives.<n>This paper proposes an emission-aware RL strategy based on the Soft Actor Critic (SAC) algorithm, with a multi-objective reward that penalises carbon emissions, curtailed on-site renewables, and unmet user demand.
  arXiv  Detail & Related papers  (2026-05-23T12:19:45Z)
• Towards eco friendly cybersecurity: machine learning based anomaly detection with carbon and energy metrics [0.17476892297485447]
  This study introduces an eco aware anomaly detection framework that unifies machine learning based network monitoring with real time carbon and energy tracking.<n>We benchmark Logistic Regression, Random Forest, Support Vector Machine, Isolation Forest, and XGBoost models across energy, carbon, and performance dimensions.<n>Results reveal that optimized Random Forest and lightweight Logistic Regression models achieve the highest eco efficiency, reducing energy consumption by more than forty percent compared to XGBoost.
  arXiv  Detail & Related papers  (2025-12-31T14:36:57Z)
• Diffusion-Modeled Reinforcement Learning for Carbon and Risk-Aware Microgrid Optimization [48.70916202664808]
  DiffCarl is a diffusion-modeled carbon- and risk-aware reinforcement learning algorithm for intelligent operation of multi-microgrid systems.<n>It outperforms classic algorithms and state-of-the-art DRL solutions, with 2.3-30.1% lower operational cost.<n>It also achieves 28.7% lower carbon emissions than those of its carbon-unaware variant and reduces performance variability.
  arXiv  Detail & Related papers  (2025-07-22T03:27:07Z)
• CarbonCall: Sustainability-Aware Function Calling for Large Language Models on Edge Devices [0.44784055850794474]
  Large Language Models (LLMs) enable real-time function calling in edge AI systems but introduce significant computational overhead, leading to high power consumption and carbon emissions.<n>We introduce CarbonCall, a sustainability-aware function-calling framework that integrates dynamic tool selection, carbon-aware execution, and quantized adaptation.<n>Experiments on an NVIDIA Jetson AGX Orin show that CarbonCall reduces carbon emissions by up to 52%, power consumption by 30%, and execution time by 30%, while maintaining high efficiency.
  arXiv  Detail & Related papers  (2025-04-29T01:37:08Z)
• Towards net-zero manufacturing: carbon-aware scheduling for GHG emissions reduction [0.0]
  Scope 2 emissions are the indirect emissions related to the production and consumption of grid electricity.<n>This study introduces a carbon-aware permutation flow-shop scheduling model designed to reduce scope 2 emissions.
  arXiv  Detail & Related papers  (2025-03-03T09:06:54Z)
• Carbon Market Simulation with Adaptive Mechanism Design [55.25103894620696]
  A carbon market is a market-based tool that incentivizes economic agents to align individual profits with the global utility. We propose an adaptive mechanism design framework, simulating the market using hierarchical, model-free multi-agent reinforcement learning (MARL) Numerical results show MARL enables government agents to balance productivity, equality, and carbon emissions.
  arXiv  Detail & Related papers  (2024-06-12T05:08:51Z)
• Generative AI for Low-Carbon Artificial Intelligence of Things with Large Language Models [67.0243099823109]
  Generative AI (GAI) holds immense potential to reduce carbon emissions of Artificial Intelligence of Things (AIoT) In this article, we explore the potential of GAI for carbon emissions reduction and propose a novel GAI-enabled solution for low-carbon AIoT. We propose a Large Language Model (LLM)-enabled carbon emission optimization framework, in which we design pluggable LLM and Retrieval Augmented Generation (RAG) modules.
  arXiv  Detail & Related papers  (2024-04-28T05:46:28Z)
• Carbon Footprint Reduction for Sustainable Data Centers in Real-Time [2.794742330785396]
  We propose a Data Center Carbon Footprint Reduction (DC-CFR) multi-agent Reinforcement Learning (MARL) framework to optimize data centers for the objectives of carbon footprint reduction, energy consumption, and energy cost.<n>The results show that the DC-CFR MARL agents effectively resolved the complex interdependencies in optimizing cooling, load shifting, and energy storage in real-time for various locations under real-world dynamic weather and grid carbon intensity conditions.
  arXiv  Detail & Related papers  (2024-03-21T02:59:56Z)
• Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model [72.65502770895417]
  We quantify the carbon footprint of BLOOM, a 176-billion parameter language model, across its life cycle. We estimate that BLOOM's final training emitted approximately 24.7 tonnes ofcarboneqif we consider only the dynamic power consumption. We conclude with a discussion regarding the difficulty of precisely estimating the carbon footprint of machine learning models.
  arXiv  Detail & Related papers  (2022-11-03T17:13:48Z)
• Measuring the Carbon Intensity of AI in Cloud Instances [91.28501520271972]
  We provide a framework for measuring software carbon intensity, and propose to measure operational carbon emissions. We evaluate a suite of approaches for reducing emissions on the Microsoft Azure cloud compute platform.
  arXiv  Detail & Related papers  (2022-06-10T17:04:04Z)
• Optimizing carbon tax for decentralized electricity markets using an agent-based model [69.3939291118954]
  Averting the effects of anthropogenic climate change requires a transition from fossil fuels to low-carbon technology. Carbon taxes have been shown to be an efficient way to aid in this transition. We use the NSGA-II genetic algorithm to minimize average electricity price and relative carbon intensity of the electricity mix.
  arXiv  Detail & Related papers  (2020-05-28T06:54:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.