Quantum Particle Swarm Optimization Technique for Load Balancing in Cloud Computing

Cloud Computing systems are widely applied in many fields such as communication data management, web application, network monitoring, financial management and so on. The distributed Cloud Computing technology has been produced as the development of the computer network and distributed computing tech...

Full description

Saved in:

Bibliographic Details
Main Author:	Elrasheed Ismail, Sultan
Format:	Thesis
Published:	2013
Subjects:	QA76 Computer software
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-ump-ir.7286
record_format	uketd_dc
spelling	my-ump-ir.72862021-08-18T06:22:21Z Quantum Particle Swarm Optimization Technique for Load Balancing in Cloud Computing 2013-08 Elrasheed Ismail, Sultan QA76 Computer software Cloud Computing systems are widely applied in many fields such as communication data management, web application, network monitoring, financial management and so on. The distributed Cloud Computing technology has been produced as the development of the computer network and distributed computing technology. Researches on data Cloud Computing become the necessary trend in the distributed Cloud Computing system domain since the sources and application of the data are distributed and the scale of the applications enlarges quickly. Load management is the focus of research in both of the area in distributed Cloud Computing systems and centralized Cloud Computing systems. Although researches on the load management in the cloud systems is similar to that of traditional parallel and distributed systems in many aspects, essential differences exist between them. The choice of a scheduling strategy has significant impact on the runtime Central Processing Unit, memory consumption as well as the storage systems. Load balancing optimization techniques such as Ant Colony Optimization (ACO), First Come First Served (FCFS), Round Robin (RR) and Particle Swarm Optimization (PSO) are popular techniques being used for scheduling and load balancing. However, these techniques have its weaknesses in terms of minimizing makespan, computation cost and communication cost. In this study, load balancing technique in Cloud Computing called Quantum Particle Swarm Optimization (QPSO) technique proposed by considering only minimization of makespan, computation cost and communication cost. Performance of the QPSO technique based on many heuristic algorithms it is comprised the following steps. Firstly, tasks are assigned averagely to the machines according to a special initialization policy. Then the optimal criterion for exchanging tasks between two machines is proposed and exploited to speed up the improving process towards load balance. Secondly, this thesis proposes job-combination based static algorithm for load balancing where all jobs should organized into the standard job combinations, each task of which consists of one to four jobs. Then they are assigned to the machines according to the assignment algorithm for job combinations, which is a special integer partition algorithm. Finally, the result of experiment shows that QPSO can achieve at least three times cost saving as compared with ACO, FCFS, RR and PSO. 2013-08 Thesis http://umpir.ump.edu.my/id/eprint/7286/ phd doctoral Universiti Malaysia Pahang Faculty of Computer Systems & Software Engineering
institution	Universiti Malaysia Pahang Al-Sultan Abdullah
collection	UMPSA Institutional Repository
topic	QA76 Computer software
spellingShingle	QA76 Computer software Elrasheed Ismail, Sultan Quantum Particle Swarm Optimization Technique for Load Balancing in Cloud Computing
description	Cloud Computing systems are widely applied in many fields such as communication data management, web application, network monitoring, financial management and so on. The distributed Cloud Computing technology has been produced as the development of the computer network and distributed computing technology. Researches on data Cloud Computing become the necessary trend in the distributed Cloud Computing system domain since the sources and application of the data are distributed and the scale of the applications enlarges quickly. Load management is the focus of research in both of the area in distributed Cloud Computing systems and centralized Cloud Computing systems. Although researches on the load management in the cloud systems is similar to that of traditional parallel and distributed systems in many aspects, essential differences exist between them. The choice of a scheduling strategy has significant impact on the runtime Central Processing Unit, memory consumption as well as the storage systems. Load balancing optimization techniques such as Ant Colony Optimization (ACO), First Come First Served (FCFS), Round Robin (RR) and Particle Swarm Optimization (PSO) are popular techniques being used for scheduling and load balancing. However, these techniques have its weaknesses in terms of minimizing makespan, computation cost and communication cost. In this study, load balancing technique in Cloud Computing called Quantum Particle Swarm Optimization (QPSO) technique proposed by considering only minimization of makespan, computation cost and communication cost. Performance of the QPSO technique based on many heuristic algorithms it is comprised the following steps. Firstly, tasks are assigned averagely to the machines according to a special initialization policy. Then the optimal criterion for exchanging tasks between two machines is proposed and exploited to speed up the improving process towards load balance. Secondly, this thesis proposes job-combination based static algorithm for load balancing where all jobs should organized into the standard job combinations, each task of which consists of one to four jobs. Then they are assigned to the machines according to the assignment algorithm for job combinations, which is a special integer partition algorithm. Finally, the result of experiment shows that QPSO can achieve at least three times cost saving as compared with ACO, FCFS, RR and PSO.
format	Thesis
qualification_name	Doctor of Philosophy (PhD.)
qualification_level	Doctorate
author	Elrasheed Ismail, Sultan
author_facet	Elrasheed Ismail, Sultan
author_sort	Elrasheed Ismail, Sultan
title	Quantum Particle Swarm Optimization Technique for Load Balancing in Cloud Computing
title_short	Quantum Particle Swarm Optimization Technique for Load Balancing in Cloud Computing
title_full	Quantum Particle Swarm Optimization Technique for Load Balancing in Cloud Computing
title_fullStr	Quantum Particle Swarm Optimization Technique for Load Balancing in Cloud Computing
title_full_unstemmed	Quantum Particle Swarm Optimization Technique for Load Balancing in Cloud Computing
title_sort	quantum particle swarm optimization technique for load balancing in cloud computing
granting_institution	Universiti Malaysia Pahang
granting_department	Faculty of Computer Systems & Software Engineering
publishDate	2013
_version_	1783731924820295680

Quantum Particle Swarm Optimization Technique for Load Balancing in Cloud Computing

Similar Items