Workload Classification & Software Energy Measurement for Efficient Scheduling on Private Cloud Platforms

TL;DR

This paper investigates how different workloads affect server energy consumption in private clouds and introduces CloudMonitor, a software tool that predicts power usage with high accuracy based on resource monitoring.

Contribution

It provides the first detailed analysis of workload-resource-power relationships and develops a scalable, software-based power prediction model for private cloud data centers.

Findings

Workloads dominating specific resources significantly impact energy consumption.

CloudMonitor achieves over 95% accuracy in power prediction after training.

Resource-based workload characterization can improve energy-efficient scheduling.

Abstract

At present there are a number of barriers to creating an energy efficient workload scheduler for a Private Cloud based data center. Firstly, the relationship between different workloads and power consumption must be investigated. Secondly, current hardware-based solutions to providing energy usage statistics are unsuitable in warehouse scale data centers where low cost and scalability are desirable properties. In this paper we discuss the effect of different workloads on server power consumption in a Private Cloud platform. We display a noticeable difference in energy consumption when servers are given tasks that dominate various resources (CPU, Memory, Hard Disk and Network). We then use this insight to develop CloudMonitor, a software utility that is capable of >95% accurate power predictions from monitoring resource consumption of workloads, after a "training phase" in which a dynamic power model is developed.