Many-Objective Virtual Machine Placement

The process of selecting which virtual machines (VMs) should be executed at each physical machine (PM) of a virtualized infrastructure is commonly known as Virtual Machine Placement (VMP). This work presents a general many-objective optimization framework that is able to consider as many objective f...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of grid computing Jg. 15; H. 2; S. 161 - 176
Hauptverfasser: López-Pires, Fabio, Barán, Benjamín
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Dordrecht Springer Netherlands 01.06.2017
Springer Nature B.V
Schlagworte:
Algorithms
Communications traffic
Computer Science
Management of Computing and Information Systems
Multiple objective analysis
Optimization
Placement
Power consumption
Processor Architectures
Quality of service architectures
User Interfaces and Human Computer Interaction
Virtual environments
Memetic algorithm
Cloud computing
Many-objective optimization
Virtual machine placement
Interactive algorithm
Resource allocation
ISSN:1570-7873, 1572-9184
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The process of selecting which virtual machines (VMs) should be executed at each physical machine (PM) of a virtualized infrastructure is commonly known as Virtual Machine Placement (VMP). This work presents a general many-objective optimization framework that is able to consider as many objective functions as needed when solving a VMP problem in a pure multi-objective context. As an example of utilization of the proposed framework, a formulation of a many-objective VMP problem (MaVMP) is proposed, considering the simultaneous optimization of the following five objective functions: (1) power consumption, (2) network traffic, (3) economical revenue, (4) quality of service and (5) network load balancing. To solve the formulated MaVMP problem, an interactive memetic algorithm is proposed. Experimental results prove the correctness of the proposed algorithm, its effectiveness converging to a manageable number of solutions and its capabilities to solve problem instances with large numbers of PMs and VMs.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1570-7873
1572-9184
DOI:10.1007/s10723-017-9399-x