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

TL;DR

This paper proposes an online, multi-timescale approach for green edge AI that optimally manages ML task offloading and carbon emission rights purchasing under market uncertainties, aiming to minimize accuracy loss and carbon costs.

Contribution

It introduces a novel joint ML offloading and CER purchasing framework with an online algorithm based on Lyapunov optimization, addressing market uncertainties and NP-hardness with a randomized rounding method.

Findings

The proposed algorithms outperform baseline methods in simulations.

The approach effectively balances accuracy loss and carbon costs.

The method adapts well to real-world carbon intensity fluctuations.

Abstract

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.