A Markov-Based Prediction Model for Host Load Detection in Live VM Migration

Host load detection algorithm determines if a given host is overload or underloaded then the decision can be made to migrate VMs to achieve host/server consolidation and load balancing in cloud data centers while satisfying the QoS constraints. Presently, host load detection is a challenging problem...

Full description

Saved in:
Bibliographic Details
Published in2017 IEEE 5th International Conference on Future Internet of Things and Cloud (FiCloud) pp. 32 - 38
Main Authors Melhem, Suhib Bani, Agarwal, Anjali, Goel, Nishith, Zaman, Marzia
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.08.2017
Subjects
Data center
Detection algorithms
Heuristic algorithms
Host underload/overload detection
Live Migration
Load modeling
Markov processes
Prediction algorithms
Predictive models
Virtual machine consolidation
Online AccessGet full text

Cover

More Information
Summary:Host load detection algorithm determines if a given host is overload or underloaded then the decision can be made to migrate VMs to achieve host/server consolidation and load balancing in cloud data centers while satisfying the QoS constraints. Presently, host load detection is a challenging problem in the cloud data center management specially with high dynamic environment for the host load. In this paper, we propose a novel Markov-based prediction algorithm to forecast the future load state of the host. The experimental results demonstrate that the proposed algorithm has better performance than the other competitive algorithms. The results for different types of PlanetLab real and random workloads show significant reduction of the SLA violation and the number of VM migrations.
DOI:10.1109/FiCloud.2017.37