Enabling Sustainable Clouds

Abstract

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-eciency and purchasing carbon osets. These approaches have limits: many cloud data centers already operate near peak eciency, and carbon osets cannot scale to near zero carbon where there is little carbon left to oset. 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 rst" approach to cloud design that elevates carbon-eciency to a rst-class metric. To do so, we argue that cloud platforms should virtualize the energy system by exposing visibility into, and software-dened control of, it to applications, enabling them to dene their own abstractions for managing energy and carbon emissions based on their own requirements. CCS CONCEPTS• Computer systems organization ! Cloud computing; Special purpose systems.

Carbon-Efficient Neural Architecture Search

“…As observed in [2], grid carbon emissions vary geographically and temporally based on the mix of active generators. Consequently, different carbon emissions arise even when consuming the same electricity at different locations or times.…”

“…While recent works have significantly improved the search efficiency of NAS [19,22,23,29,31], e.g., reducing the GPU-hours to tens of hours without sacrificing the architecture quality, there still lacks conscious efforts in reducing carbon emissions. As noted in a recent vision paper by Bashir et al [2], energy efficiency can help reduce carbon emissions but is not equivalent to carbon efficiency.…”

Software‐in‐the‐loop simulation for developing and testing carbon‐aware applications

“…Such virtual energy systems would allow applications to define their own abstractions for managing energy and carbon emissions based on their own requirements. 8 However, research and development on novel interfaces and abstraction layers, as well as carbon-aware applications themselves, remain complex due to the scarcity of available testing environments. For example, Souza et al 9 implemented a hardware testbed to demonstrate the feasibility of their proposed ecovisor which extends to a couple of microservers, each consuming up to 10 W under full CPU and GPU load.…”

“…However, renewable energy sources such as solar and wind are highly variable by nature, which requires computing infrastructure to adaptively adjust its resource usage to the availability of clean energy. While this new paradigm, often called carbon‐aware computing , 5‐7 is a promising idea in theory, today's energy systems are not designed to expose their underlying complexities to consumers: The unreliability of on‐site renewable energy or the state of energy storage is hidden behind the simple abstraction of an unlimited and reliable power supply 8 . This means that carbon‐aware applications which by design require signals from the energy system, can usually not access this information.…”

“…For example, by determining when virtual batteries should be charged using grid energy, or by setting power caps on servers and containers by limiting their resource usage. Such virtual energy systems would allow applications to define their own abstractions for managing energy and carbon emissions based on their own requirements 8 …”