Home // CLOUD COMPUTING 2015, The Sixth International Conference on Cloud Computing, GRIDs, and Virtualization // View article

Autonomic Management for Energy Efficient Data Centers

Authors:
Forough Norouzi
Michael Bauer

Keywords: autonomic computing; energy aware data center; self-management system; policy-based management

Abstract:
The complexity of today’s data centers has led researchers to investigate ways in using autonomic methods for data center management. In this work, we consider using autonomic management techniques that can help reduce data center energy consumption. In particular, we consider policy-based, multi-level autonomic management for energy aware data centers. We advocate for a hierarchical model of managers with loosely coupled communication between them. We describe our manager topology, communications and manager operations. We implement our approach for high performance computing centers that may have one or more large high performance computing systems. A data center simulator has been implemented that calculates data center energy consumption. We evaluate different management policies and our approach using this simulator. Preliminary experiments show promising results in terms of minimizing energy consumption and overhead on service level expectations in high performance computing systems.

Pages: 138 to 146

Copyright: Copyright (c) IARIA, 2015

Publication date: March 22, 2015

Published in: conference

ISSN: 2308-4294

ISBN: 978-1-61208-388-9

Location: Nice, France

Dates: from March 22, 2015 to March 27, 2015