The Effect of the Network in Cutting Carbon for Geo-shifted Workloads

2025-04-18

AI Summary

This study addresses the long-overlooked carbon cost of wide-area network (WAN) data transfer for geographically migratable cloud workloads, which has constrained effective carbon reduction. We propose the first high-fidelity carbon cost modeling method that jointly incorporates fine-grained physical network topology and regionally dynamic grid carbon intensity, enabling integrated quantification of WAN transmission and computation emissions. Building upon this, we design a geo-temporal joint optimization scheduling framework that jointly determines *when* and *where* to migrate workloads. Empirical evaluation shows that our approach achieves 2.3× greater carbon reduction compared to time-only migration baselines, while reducing WAN carbon cost estimation error to ±8.7%. To our knowledge, this is the first work to empirically demonstrate that integrating spatial workload migration with precise network-aware carbon modeling significantly unlocks the carbon neutrality potential of cloud computing.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Search and Optimization: Combinatorial Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Sustainability and climate impact of web technologies

Abstract

Organizations are increasingly offloading their workloads to cloud platforms. For workloads with relaxed deadlines, this presents an opportunity to reduce the total carbon footprint of these computations by moving workloads to datacenters with access to low-carbon power. Recently published results have shown that the carbon footprint of the wide-area network (WAN) can be a significant share of the total carbon output of executing the workload itself, and so careful selection of the time and place where these computations are offloaded is critical. In this paper, we propose an approach to geographic workload migration that uses high-fidelity maps of physical Internet infrastructure to better estimate the carbon costs of WAN transfers. Our findings show that space-shifting workloads can achieve much higher carbon savings than time-shifting alone, if accurate estimates of WAN carbon costs are taken into account.

Problem

• Reducing carbon footprint in geo-shifted cloud workloads
• Estimating WAN transfer carbon costs accurately
• Optimizing workload migration for carbon savings

Innovation

• Uses high-fidelity Internet infrastructure maps
• Estimates WAN transfer carbon costs accurately
• Prioritizes space-shifting over time-shifting