WaterWise: Co-optimizing Carbon- and Water-Footprint Toward Environmentally Sustainable Cloud Computing
🤖 AI Summary
Cloud data centers face the challenge of jointly optimizing carbon emissions and water consumption, which are inherently difficult to reconcile. This paper is the first to systematically reveal a significant negative trade-off between these two sustainability metrics. We propose WaterWise, a parallel job scheduling framework for carbon–water co-optimization in geo-distributed environments. WaterWise integrates spatiotemporal-aware mixed-integer linear programming (MILP) modeling with an online heuristic algorithm to enable real-time, dual-objective optimization. Evaluated on real-world workload traces and multi-region electricity/water grid datasets, WaterWise reduces aggregate carbon and water footprints by 37% compared to single-objective baselines and expands the Pareto frontier by 2.1×. To our knowledge, this work presents the first deployable, dual-footprint co-optimization scheduling solution for sustainable cloud computing.
Application Category
📝 Abstract
The carbon and water footprint of large-scale computing systems poses serious environmental sustainability risks. In this study, we discover that, unfortunately, carbon and water sustainability are at odds with each other - and, optimizing one alone hurts the other. Toward that goal, we introduce, WaterWise, a novel job scheduler for parallel workloads that intelligently co-optimizes carbon and water footprint to improve the sustainability of geographically distributed data centers.
Problem
Research questions and friction points this paper is trying to address.
Carbon Emission Reduction
Water Conservation
Sustainable Cloud Computing
Innovation
Methods, ideas, or system contributions that make the work stand out.
WaterWise
Sustainable Computing
Eco-friendly Resource Management
🔎 Similar Papers
No similar papers found.
