Premium
Order@Cloud: An agnostic meta‐heuristic for VM provisioning, adaptation, and organisation
Author(s) -
Geronimo Guilherme,
Uriarte Rafael,
Westphall Carlos
Publication year - 2019
Publication title -
international journal of network management
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.373
H-Index - 28
eISSN - 1099-1190
pISSN - 1055-7148
DOI - 10.1002/nem.2085
Subject(s) - computer science , cloud computing , provisioning , virtual machine , flexibility (engineering) , distributed computing , adaptation (eye) , set (abstract data type) , heuristic , domain (mathematical analysis) , order (exchange) , artificial intelligence , computer network , operating system , optics , economics , programming language , mathematical analysis , statistics , physics , mathematics , finance
Summary We propose a flexible meta‐heuristic framework for virtual machine (VM) organisation, provisioning, and adaptation in the cloud domain, based on migration costs and environment constraints. Order@Cloud improves VM placements according to multiple objectives represented by rules, qualifiers, and improvement cost, which can be easily modified and extended. Order@Cloud theoretically guarantees the adoption of a better set of placements, after considering their costs and benefits, by prioritising the worst VM placements. While existing solutions address only specific objectives, our framework is objective‐agnostic and extensible, which enables the adoption and implementation of new policies and priorities. We conduct experiments using a real cloud environment data and discuss the framework's performance, flexibility, and optimality and provide insights on the challenges and benefits of deploying this framework.