CarbonEdge: Leveraging Mesoscale Spatial Carbon-Intensity Variations for Low Carbon Edge Computing

TL;DR

This paper addresses the rising carbon footprint of latency-sensitive edge computing by uncovering mesoscale variations in grid carbon intensity and exploiting them with CarbonEdge, a carbon-aware placement framework for edge data centers. It introduces a mesoscale-aware optimization that jointly considers carbon intensity, hardware energy efficiency, and latency constraints, implemented atop Sinfonia and validated with real traces and large-scale simulations. The results show substantial emissions reductions—up to 78.7% regionally and 49.5% US / 67.8% Europe CDN-scale—while keeping latency increases modest (often under 11 ms). The work demonstrates the practical potential of fine-grained carbon data for edge decarbonization and provides a prototype open-source platform, though it notes limitations like data availability, lack of automatic redeployment, and exclusion of embodied emissions.

Abstract

The proliferation of latency-critical and compute-intensive edge applications is driving increases in computing demand and carbon emissions at the edge. To better understand carbon emissions at the edge, we analyze granular carbon intensity traces at intermediate "mesoscales," such as within a single US state or among neighboring countries in Europe, and observe significant variations in carbon intensity at these spatial scales. Importantly, our analysis shows that carbon intensity variations, which are known to occur at large continental scales (e.g., cloud regions), also occur at much finer spatial scales, making it feasible to exploit geographic workload shifting in the edge computing context. Motivated by these findings, we propose \proposedsystem, a carbon-aware framework for edge computing that optimizes the placement of edge workloads across mesoscale edge data centers to reduce carbon emissions while meeting latency SLOs. We implement CarbonEdge and evaluate it on a real edge computing testbed and through large-scale simulations for multiple edge workloads and settings. Our experimental results on a real testbed demonstrate that CarbonEdge can reduce emissions by up to 78.7\% for a regional edge deployment in central Europe. Moreover, our CDN-scale experiments show potential savings of 49.5\% and 67.8\% in the US and Europe, respectively, while limiting the one-way latency increase to less than 5.5 ms.

Figures (17)

• Figure 1: Energy mix and carbon intensity of four regions.
• Figure 2: Carbon intensity snapshots of four mesoscale regions, highlighting variations across zones.
• Figure 3: Yearly carbon intensity of two mesoscale regions.
• Figure 4: Spatial-temporal variations in carbon intensity over two days and 12 months in 2023 in the West US.
• Figure 5: Carbon savings with search radii of 200 km, 500 km, and 1000 km. (d) One-way latency across pairwise distances.