Modelling Scenarios for Carbon-aware Geographic Load Shifting of Compute Workloads

2025-09-08

AI Summary

The rapid global expansion of data centers exacerbates carbon emissions, prompting interest in carbon-aware geographic load shifting—i.e., scheduling computation to regions with low-carbon electricity grids—as a mitigation strategy. Method: We conduct an analytical modeling and multi-scenario assessment under idealized assumptions—ignoring grid capacity constraints, demand volatility, and curtailment—to quantify the theoretical global emission reduction ceiling of this approach. Contribution/Results: Even under optimal conditions, geographic load shifting achieves only ~5% reduction in data center operational emissions—insufficient to offset emissions growth from industry expansion. This work provides the first systematic characterization of the inherent limitations of geographic load migration for carbon mitigation, challenging its prevailing status as a primary green computing lever. Our findings critically inform policy and infrastructure planning, urging a strategic recalibration toward more impactful decarbonization pathways for computing infrastructure.

Technology Category

• Machine Learning: Efficient ML / Green AI
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Combinatorial Optimization

Application Category

• Responsible Web: Sustainability and climate impact of web technologies
• 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

Abstract

We present an analytical model to evaluate the reductions in emissions resulting from geographic load shifting. This model is optimistic as it ignores issues of grid capacity, demand and curtailment. In other words, real-world reductions will be smaller than the estimates. However, even with these assumptions, the presented scenarios show that the realistic reductions from carbon-aware geographic load shifting are small, of the order of 5%. This is not enough to compensate the growth in emissions from global data centre expansion.

Problem

• Evaluating emission reductions from geographic load shifting
• Ignoring grid capacity and demand constraints in modeling
• Assessing insufficient reductions to offset data center growth

Innovation

• Analytical model for emission reduction evaluation
• Geographic load shifting of compute workloads
• Optimistic assumptions ignoring grid constraints