A virtual machine placement algorithm for balanced resource utilization in cloud data centers
Authors:
- Nguyen Trung HieuNHNguyen Trung Hieu
- Mario Di FrancescoMFMario Di Francesco
- Antti Yla-JaaskiAYAntti Yla-Jaaski
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21596182,p. 474-481
Abstract
Virtual machine (VM) placement is the process of selecting the most suitable server in large cloud data centers to deploy newly-created VMs. Several approaches have been proposed to find a solution to this problem. However, most of the existing solutions only consider a limited number of resource types, thus resulting in unbalanced load or in the unnecessary activation of physical servers. In this article, we propose an algorithm, called Max-BRU, that maximizes the resource utilization and balances the usage of resources across multiple dimensions. Our algorithm is based on multiple resource-constraint metrics that help to find the most suitable server for deploying VMs in large cloud data centers. The proposed Max-BRU algorithm is evaluated by simulations based on synthetic datasets. Experimental results show two major improvements over the existing approaches for VM placement. First, Max-BRU increases the resource utilization by minimizing the amount of physical servers used. Second, Max-BRU effectively balances the utilization of multiple types of resources.Keywords
This publication has 15 references indexed in Scilit:
- A family of heuristics for agent-based elastic Cloud bag-of-tasks concurrent schedulingFuture Generation Computer Systems, 2013
- Energy-aware scheduling for infrastructure clouds2012
- A Profit-Aware Virtual Machine Deployment Optimization Framework for Cloud Platform Providers2012
- Network aware resource allocation in distributed clouds2012
- A dynamic and integrated load-balancing scheduling algorithm for Cloud datacenters2011
- On Theory of VM Placement: Anomalies in Existing Methodologies and Their Mitigation Using a Novel Vector Based Approach2011
- Open Source Cloud Computing Platforms2010
- Real-time scheduling of divisible loads in cluster computing environmentsJournal of Parallel and Distributed Computing, 2010
- Market-Based Load Balancing for Distributed Heterogeneous Multi-Resource Servers2009
- Server-storage virtualization: Integration and load balancing in data centers2008