# CarbonEdge: Carbon-Aware Deep Learning Inference Framework for Sustainable Edge Computing

arXiv: https://arxiv.org/abs/2603.27420 · HTML: https://mlsanity.com/paper/2603.27420/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 28 Mar 2026.

## Builds on (most cited first, 19 of 19)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink](https://mlsanity.com/paper/2204.05149/) (2022)
- [Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing](https://mlsanity.com/paper/1910.05316/) (2019)
- [MobileNetV4 -- Universal Models for the Mobile Ecosystem](https://mlsanity.com/paper/2404.10518/) (2024)
- [CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devices](https://mlsanity.com/paper/2012.03257/) (2020)
- [Counting Carbon: A Survey of Factors Influencing the Emissions of Machine Learning](https://mlsanity.com/paper/2302.08476/) (2023)
- [Lightweight Deep Learning for Resource-Constrained Environments: A Survey](https://mlsanity.com/paper/2404.07236/) (2024)
- [EcoServe: Designing Carbon-Aware AI Inference Systems](https://mlsanity.com/paper/2502.05043/) (2025)
- [Clover: Toward Sustainable AI with Carbon-Aware Machine Learning Inference Service](https://mlsanity.com/paper/2304.09781/) (2023)
- [GreenScale: Carbon-Aware Systems for Edge Computing](https://mlsanity.com/paper/2304.00404/) (2023)
- [AMP4EC: Adaptive Model Partitioning Framework for Efficient Deep Learning Inference in Edge Computing Environments](https://mlsanity.com/paper/2504.00407/) (2025)
- [HiDP: Hierarchical DNN Partitioning for Distributed Inference on Heterogeneous Edge Platforms](https://mlsanity.com/paper/2411.16086/) (2024)
- [Sustainable Edge Computing: Challenges and Future Directions](https://mlsanity.com/paper/2304.04450/) (2023)
- [Toward Sustainability-Aware LLM Inference on Edge Clusters](https://mlsanity.com/paper/2512.04088/) (2025)
- [Carbon-Aware Computing for Data Centers with Probabilistic Performance Guarantees](https://mlsanity.com/paper/2410.21510/) (2024)
- [A Survey on Task Scheduling in Carbon-Aware Container Orchestration](https://mlsanity.com/paper/2508.05949/) (2025)

## Built on by (most cited first, 1 of 1)

- [Winning by Peeking: Unenforced Budgets and Test-Set Selection Inflate Short-Budget AutoML Comparisons](https://mlsanity.com/paper/2608.07303/) (2026)

## Abstract (arXiv)

Deep learning applications at the network edge lead to a significant growth in AI-related carbon emissions, presenting a critical sustainability challenge. The existing edge computing frameworks optimize for latency and throughput, but they largely ignore the environmental impact of inference workloads. This paper introduces CarbonEdge, a carbon-aware deep learning inference framework that extends adaptive model partitioning with carbon footprint estimation and green scheduling apabilities. We propose a carbon-aware scheduling algorithm that extends traditional weighted scoring with a carbon efficiency metric, supporting a tunable performance--carbon trade-off (demonstrated via weight sweep). Experimental evaluations on Docker-simulated heterogeneous edge environments show that CarbonEdge-Green mode achieves a 22.9% reduction in carbon emissions compared to monolithic execution. The framework achieves 1.3x improvement in carbon efficiency (245.8 vs 189.5 inferences per gram CO2) with negligible scheduling overhead (0.03ms per task). These results highlight the framework's potential for sustainable edge AI deployment, providing researchers and practitioners a tool to quantify and minimize the environmental footprint of distributed deep learning inference.