SLA-Aware and Energy-Efficient VM Consolidation in Cloud Data Centers Using Host States Naive Bayesian Prediction Model

Virtual Machine (VM) consolidation provides a promising approach to save energy and improve resource utilization in data centers. However, aggressive consolidation of VMs may lead to the Service Level Agreements(SLA) violation which is essential for data centers and their users. Therefore, reduction...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Ubiquitous Computing & Communications, Big Data & Cloud Computing, Social Computing & Networking, Sustainable Computing & Communications (ISPA/IUCC/BDCloud/SocialCom/SustainCom) pp. 80 - 87
Main Authors Li, Lianpeng, Dong, Jian, Zuo, Decheng, Liu, JIaxi
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2018
Subjects
Bayes methods
Cloud computing
cloud data centers
Data centers
Energy consumption
energy-efficient
Heuristic algorithms
Naive Bayesian classifier
Predictive models
Resource management
SLA-aware
VM consolidation
Online AccessGet full text

Cover

More Information
Summary:Virtual Machine (VM) consolidation provides a promising approach to save energy and improve resource utilization in data centers. However, aggressive consolidation of VMs may lead to the Service Level Agreements(SLA) violation which is essential for data centers and their users. Therefore, reduction of the SLA violation level and power costs are considered as two objectives in this paper. We present a host states prediction mode based on Naive Bayesian classifier for SLA-aware and energy-efficient consolidation of VMs in cloud data centers. Different from other future resource utilization prediction methods, our proposed method predict the future host states instead. We validate our approach with the CloudSim toolkit using real world PlanetLab workload and random workload. The experimental results show that our proposed method can significantly reduce SLA violation rates while keeping energy cost efficient.
DOI:10.1109/BDCloud.2018.00025