Enabling Sustainable Clouds: The Case for Virtualizing the Energy System
Not on the map. Why?
Abstract (arXiv)
Cloud platforms' growing energy demand and carbon emissions are raising concern about their environmental sustainability. The current approach to enabling sustainable clouds focuses on improving energy-efficiency and purchasing carbon offsets. These approaches have limits: many cloud data centers already operate near peak efficiency, and carbon offsets cannot scale to near zero carbon where there is little carbon left to offset. Instead, enabling sustainable clouds will require applications to adapt to when and where unreliable low-carbon energy is available. Applications cannot do this today because their energy use and carbon emissions are not visible to them, as the energy system provides the rigid abstraction of a continuous, reliable energy supply. This vision paper instead advocates for a ``carbon first'' approach to cloud design that elevates carbon-efficiency to a first-class metric. To do so, we argue that cloud platforms should virtualize the energy system by exposing visibility into, and software-defined control of, it to applications, enabling them to define their own abstractions for managing energy and carbon emissions based on their own requirements.
Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Jun 2021.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2023: 5; 2024: 4; 2025: 2; 2026: 1.
12 papers.
- 2023Making AI Less "Thirsty": Uncovering and Addressing the Secret Water Footprint of AI Modelscited by 44
- 2023Towards Environmentally Equitable AI via Geographical Load Balancingcited by 10
- 2023Online Conversion with Switching Costs: Robust and Learning-Augmented Algorithmscited by 10
- 2023CAFE: Carbon-Aware Federated Learning in Geographically Distributed Data Centerscited by 6
- 2024CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Frameworkcited by 5
- 2024Chasing Convex Functions with Long-term Constraintscited by 4
- 2023Carbon-Efficient Neural Architecture Searchcited by 2
- 2025Green Federated Learning via Carbon-Aware Client and Time Slot Schedulingcited by 2
- 2025SPIRIT: Short-term Prediction of solar IRradIance for zero-shot Transfer learning using Foundation Modelscited by 1
- 2026From Barrier to Bridge: The Case for AI Data Center/Power Grid Co-Designcited by 1
- 2024Learning-Augmented Competitive Algorithms for Spatiotemporal Online Allocation with Deadline Constraintscited by 0
- 2024Towards Environmentally Equitable AIcited by 0
- 2026From Barrier to Bridge: The Case for AI Data Center/Power Grid Co-Design4 May 2026
- 2025Green Federated Learning via Carbon-Aware Client and Time Slot Scheduling10 Sep 2025
- 2025SPIRIT: Short-term Prediction of solar IRradIance for zero-shot Transfer learning using Foundation Models14 Feb 2025
- 2024Towards Environmentally Equitable AI21 Dec 2024
- 2024Learning-Augmented Competitive Algorithms for Spatiotemporal Online Allocation with Deadline Constraints14 Aug 2024
- 2024CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Framework3 Jun 2024
- 2024Chasing Convex Functions with Long-term Constraints21 Feb 2024
- 2023CAFE: Carbon-Aware Federated Learning in Geographically Distributed Data Centers6 Nov 2023
- 2023Online Conversion with Switching Costs: Robust and Learning-Augmented Algorithms31 Oct 2023
- 2023Carbon-Efficient Neural Architecture Search9 Jul 2023
- 2023Towards Environmentally Equitable AI via Geographical Load Balancing20 Jun 2023
- 2023Making AI Less "Thirsty": Uncovering and Addressing the Secret Water Footprint of AI Models6 Apr 2023