Resource utilization prediction with multipath traffic routing for congestion-aware VM migration in cloud computing

R Gowri Prakash,S Duraisamy2,R Shankar

doi:10.17485/ijst/v14i7.1901

Abstract

Background: The Load Balancing (LB) schemes in cloud computing consider both current and future utilization of resources to decide the most suitable Virtual Machines (VMs) to be migrated to the most appropriate Physical Machines (PMs). But, the possibility of network congestion occurrence was high when increasing the bandwidth use between VMs within the cloud data centers. Also, a less-than-optimal migration of VMs can lead to high network traffic since it causes inter-VM traffic for traversing the bottleneck network routes. Objective: To enhance the efficiency of LB and reduce the possibility of congestion occurrence during VM migration in cloud data centers. Methods: Osmotic Hybrid artificial Bee and Ant Colony with Future Utilization Prediction with Multipath Traffic Routing (OH-BAC-FUP-MTR) mechanism are presented in this article to achieve the above objective. Initially, the OH-BAC-FUP mechanism is performed to decide the most suitable VMs to be migrated to the most suitable PMs. During VM migration, if any congestion exists due to high bandwidth use or traffic flows, then the MTR algorithm is applied to partition the flows and route them through multiple link-disjoint routes. Based on this, the congestion is avoided while ensuring the bandwidth and security grade demands. Also, the highest traffic on the path is applied as a congestion factor. Moreover, the current and future network states are taken into account for MTR to select the most optimal route from multiple routes with no consideration of the past use of the paths. Findings: The simulation outcomes demonstrate the OH-BAC-FUP-MTR mechanism consumes 8.74% of overall energy, 6.8% of Service Level Agreement violation Time per Active Host (SLATAH), 27.63% of Performance Degradation due to Migration (PDM), 22.98% of SLA Violation (SLAV), 27.27% of VM migrations and 30.77% of hosts shutdown compared to the OH-BAC-FUP using Linear Regression (LR) and Optimal Piecewise LR (OPLR). Keywords: Cloud computing; load balancing; VM migration; OH-BAC-FUP; multipath traffic routing

Highlights

The cloud computing paradigm possesses numerous problems as its usage is increasing exponentially
The analysis is carried out based on energy consumption, the number of Virtual Machines (VMs) migrations and the number of Service Level Agreement (SLA) Violation (SLAV), SLATAH, Performance Degradation due to Migration (PDM) and the number of host’s shutdowns
This study presents an OH-BAC-FUP-MTR mechanism for enhancing the performance of Load Balancing (LB) and reducing the chance of congestion occurrence in the cloud data centers

Summary

Introduction

The cloud computing paradigm possesses numerous problems as its usage is increasing exponentially. The Load Balancing (LB) schemes in cloud computing consider both current and future utilization of resources to decide the most suitable Virtual Machines (VMs) to be migrated to the most appropriate Physical Machines (PMs). The possibility of network congestion occurrence was high when increasing the bandwidth use between VMs within the cloud data centers. Objective: To enhance the efficiency of LB and reduce the possibility of congestion occurrence during VM migration in cloud data centers. The OH-BAC-FUP mechanism is performed to decide the most suitable VMs to be migrated to the most suitable PMs. During VM migration, if any congestion exists due to high bandwidth use or traffic flows, the MTR algorithm is applied to partition the flows and route them through multiple link-disjoint routes.

Objectives

Methods

Results

Conclusion