Take a break: cloud scheduling optimized for real-time electricity pricing

TL;DR

This paper introduces a grid-aware cloud scheduling algorithm that predicts electricity price peaks to reduce energy consumption and costs, promoting environmentally sustainable cloud computing.

Contribution

It presents a novel scheduling method that leverages real-time electricity prices to optimize cloud resource usage, including a practical implementation and evaluation.

Findings

Significant energy savings achieved in experiments.

Cost reductions for cloud providers and users.

Feasibility of green instances for sustainable cloud services.

Abstract

Cloud computing revolutionised the industry with its elastic, on-demand approach to computational resources, but has lead to a tremendous impact on the environment. Data centers constitute 1.1-1.5% of total electricity usage in the world. Taking a more informed view of the electrical grid by analysing real-time electricity prices, we set the foundations of a grid-conscious cloud. We propose a scheduling algorithm that predicts electricity price peaks and throttles energy consumption by pausing virtual machines. We evaluate the approach on the OpenStack cloud manager through an empirical approach and show reductions in energy consumption and costs. Finally, we define green instances in which cloud providers can offer such services to their customers under better pricing options.