Energy-aware Load Balancing Policies for the Cloud Ecosystem

TL;DR

This paper proposes energy-aware load balancing policies for large-scale data centers, focusing on minimizing energy consumption by optimal workload distribution and server sleep states, while maintaining quality of service.

Contribution

It introduces a reformulated load balancing model that optimizes energy use by distributing workloads to minimal active servers at optimal energy levels, considering VM migration costs.

Findings

Energy savings through workload consolidation

Model effectiveness in reducing active servers

Impact of VM migration costs on energy efficiency

Abstract

The energy consumption of computer and communication systems does not scale linearly with the workload. A system uses a significant amount of energy even when idle or lightly loaded. A widely reported solution to resource management in large data centers is to concentrate the load on a subset of servers and, whenever possible, switch the rest of the servers to one of the possible sleep states. We propose a reformulation of the traditional concept of load balancing aiming to optimize the energy consumption of a large-scale system: {\it distribute the workload evenly to the smallest set of servers operating at an optimal energy level, while observing QoS constraints, such as the response time.} Our model applies to clustered systems; the model also requires that the demand for system resources to increase at a bounded rate in each reallocation interval. In this paper we report the VM migration costs for application scaling.