PACO-VMP: Parallel Ant Colony Optimization for Virtual Machine Placement

Joshua Peake, Martyn Amos, Nicholas Costen, Giovanni Masala, Huw Lloyd*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

48 Citations (Scopus)
36 Downloads (Pure)

Abstract

The Virtual Machine Placement (VMP) problem is a challenging optimization task that involves the assignment of virtual machines to physical machines in a cloud computing environment. The placement of virtual machines can significantly affect the use of resources in a cluster, with a subsequent impact on operational costs and the environment. In this paper, we present an improved algorithm for VMP, based on Parallel Ant Colony Optimization (PACO), which makes effective use of parallelization techniques and modern processor technologies. We achieve solution qualities that are comparable with or superior to those obtained by other nature-inspired methods, with our parallel implementation obtaining a speed-up of up to 2002x over recent serial algorithms in the literature. This allows us to rapidly find high-quality solutions that are close to the theoretical minimum number of Virtual Machines.
Original languageEnglish
Pages (from-to)174-186
Number of pages13
JournalFuture Generation Computer Systems
Volume129
Early online date14 Dec 2021
DOIs
Publication statusPublished - 1 Apr 2022

Keywords

  • Virtual Machine Placement
  • Ant Colony Optimization
  • Swarm Intelligence
  • Parallel MAX-MIN Ant System
  • Parallel Ant Colony Optimization
  • Swarm intelligence

Fingerprint

Dive into the research topics of 'PACO-VMP: Parallel Ant Colony Optimization for Virtual Machine Placement'. Together they form a unique fingerprint.

Cite this