# Towards Carbon-Neutral Edge Computing: Greening Edge AI by Harnessing Spot and Future Carbon Markets

arXiv: https://arxiv.org/abs/2304.11374 · HTML: https://mlsanity.com/paper/2304.11374/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 45 references that are in the map.
- First posted on arXiv 22 Apr 2023.

## Builds on (most cited first, 9 of 9)

- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing](https://mlsanity.com/paper/1910.05316/) (2019)
- [Artificial Intelligence-Enabled Intelligent 6G Networks](https://mlsanity.com/paper/1912.05744/) (2019)
- [An Energy and Carbon Footprint Analysis of Distributed and Federated Learning](https://mlsanity.com/paper/2206.10380/) (2022)
- [Accuracy-Guaranteed Collaborative DNN Inference in Industrial IoT via Deep Reinforcement Learning](https://mlsanity.com/paper/2301.00130/) (2022)
- [Carbon-Neutralized Task Scheduling for Green Computing Networks](https://mlsanity.com/paper/2209.02198/) (2022)
- [Less Carbon Footprint in Edge Computing by Joint Task Offloading and Energy Sharing](https://mlsanity.com/paper/2211.05529/) (2022)
- [Exploiting the Solar Energy Surplus for Edge Computing](https://mlsanity.com/paper/2006.05703/) (2020)

## Built on by (most cited first, 4 of 4)

- [Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models](https://mlsanity.com/paper/2503.06027/) (2025)
- [Green Edge AI: A Contemporary Survey](https://mlsanity.com/paper/2312.00333/) (2023)
- [Generative AI for Low-Carbon Artificial Intelligence of Things with Large Language Models](https://mlsanity.com/paper/2404.18077/) (2024)
- [Carbon-aware decentralized dynamic task offloading in MIMO-MEC networks via multi-agent reinforcement learning](https://mlsanity.com/paper/2602.18797/) (2026)

## Abstract (arXiv)

Provisioning dynamic machine learning (ML) inference as a service for artificial intelligence (AI) applications of edge devices faces many challenges, including the trade-off among accuracy loss, carbon emission, and unknown future costs. Besides, many governments are launching carbon emission rights (CER) for operators to reduce carbon emissions further to reverse climate change. Facing these challenges, to achieve carbon-aware ML task offloading under limited carbon emission rights thus to achieve green edge AI, we establish a joint ML task offloading and CER purchasing problem, intending to minimize the accuracy loss under the long-term time-averaged cost budget of purchasing the required CER. However, considering the uncertainty of the resource prices, the CER purchasing prices, the carbon intensity of sites, and ML tasks' arrivals, it is hard to decide the optimal policy online over a long-running period time. To overcome this difficulty, we leverage the two-timescale Lyapunov optimization technique, of which the T-slot drift-plus-penalty methodology inspires us to propose an online algorithm that purchases CER in multiple timescales (on-preserved in carbon future market and on-demanded in the carbon spot market) and makes decisions about where to offload ML tasks. Considering the NP-hardness of the T-slot problems, we further propose the resource-restricted randomized dependent rounding algorithm to help to gain the near-optimal solution with no help of any future information. Our theoretical analysis and extensive simulation results driven by the real carbon intensity trace show the superior performance of the proposed algorithms.