CarbonScaler: Leveraging Cloud Workload Elasticity for Optimizing Carbon-Efficiency

Abstract

Cloud platforms are increasing their emphasis on sustainability and reducing their operational carbon footprint. A common approach for reducing carbon emissions is to exploit the temporal flexibility inherent to many cloud workloads by executing them in periods with the greenest energy and suspending them at other times. Since such suspend-resume approaches can incur long delays in job completion times, we present a new approach that exploits the elasticity of batch workloads in the cloud to optimize their carbon emissions. Our approach is based on the notion of "carbon scaling," similar to cloud autoscaling, where a job dynamically varies its server allocation based on fluctuations in the carbon cost of the grid's energy. We develop a greedy algorithm for minimizing a job's carbon emissions via carbon scaling that is based on the well-known problem of marginal resource allocation. We implement a CarbonScaler prototype in Kubernetes using its autoscaling capabilities and an analytic tool to guide the carbon-efficient deployment of batch applications in the cloud. We then evaluate CarbonScaler using real-world machine learning training and MPI jobs on a commercial cloud platform and show that it can yield i) 51% carbon savings over carbon-agnostic execution; ii) 37% over a state-of-the-art suspend-resume policy; and iii) 8% over the best static scaling policy.

References in corpus (3)

• Let's Wait Awhile: How Temporal Workload Shifting Can Reduce Carbon Emissions in the Cloud
• On the Limitations of Carbon-Aware Temporal and Spatial Workload Shifting in the Cloud
• On the Promise and Pitfalls of Optimizing Embodied Carbon

Cited by in corpus (7)

• On the Limitations of Carbon-Aware Temporal and Spatial Workload Shifting in the Cloud
• The Sunk Carbon Fallacy: Rethinking Carbon Footprint Metrics for Effective Carbon-Aware Scheduling
• LACS: Learning-Augmented Algorithms for Carbon-Aware Resource Scaling with Uncertain Demand
• The Green Mirage: Impact of Location- and Market-based Carbon Intensity Estimation on Carbon Optimization Efficacy
• The Cloud Next Door: Investigating the Environmental and Socioeconomic Strain of Datacenters on Local Communities
• EnsembleCI: Ensemble Learning for Carbon Intensity Forecasting
• EcoKube: Simulating Carbon-Aware Scheduling Policies in Heterogeneous Edge-Cloud Environments