TRAP@NCI

Q-Aware: A new approach towards the task scheduling process using nature-inspired meta-heuristic algorithms

Nemani, Midhun Kumar (2017) Q-Aware: A new approach towards the task scheduling process using nature-inspired meta-heuristic algorithms. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (1MB) | Preview

Abstract

Cloud Computing is the modern invocation being recited by the IT industry, and has set an example for accessing as well as configuring large-scale distributed computing applications across the clusters in datacenters. Today, it is in control of the greater percentage of computing quite recently, subsequently physical assets are being over-stacked. In-order to manage and assign tasks for the physical or virtual resources, techniques of clustering, scheduling and load balancing are being used. The current techniques are profoundly complex for non-pre-emptive tasks, which has remained as an irrecoverable restraint on the part of scheduling mechanism. In recent times, researches have implemented nature-inspired algorithms into the field of computing to solve the problems associated to complexity and to provide optimal solutions. In this paper, our focus lies in computing the makeSpan and costs incurred for resource management in the task scheduling process with a new methodology. We are proposing a heuristic approach namely Q-aware algorithm which takes the decisions based on analytical scheming. It works by forming a cluster of VMs using K means algorithm based on the memory, CPU, and band-width. This proposed technique uses a pool of nature-inspired algorithms namely SA,GA,IWO,PSO,ABC for the scheduling of tasks. This experiment is performed using cloudsim as simulator in-order to create a datacenter environment and schedule the tasks onto the virtual resources. The results show that the proposed system successfully performs the hyper-analytical scheming and measures the makespan, and calculates the resource utilization during the process.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

T Technology > T Technology (General) > Information Technology > Cloud computing
Divisions: School of Computing > Master of Science in Cloud Computing
Depositing User: CAOIMHE NI MHAICIN
Date Deposited: 21 Nov 2017 15:15
Last Modified: 21 Nov 2017 15:15
URI: http://trap.ncirl.ie/id/eprint/2878

Actions (login required)

View Item View Item