Affiliations: [a] Department of Mathematics and Computer Science, Faculty of Science, Menoufia University, Egypt. E-mail: elzoghdy@yahoo.com | [b] Department of Information Technology, College of Computer and Information Technology, Taif University, Saudi Arabia. E-mail: alzoghdy@tu.edu.sa | [c] Department of Software Engineering, College of Computer and Information Sciences, King Saud University, Saudi Arabia. E-mail: ghoneim@ksu.edu.sa
Correspondence:
[*]
Corresponding author: S.F. El-Zoghdy, Department of Mathematics and Computer Science, Faculty of Science, Menoufia University, Egypt. E-mails: elzoghdy@yahoo.com, alzoghdy@tu.edu.sa.
Abstract: This paper proposes a new selection-based model for filtering nodes in heterogeneous distributed computing systems based on quality of services criteria and load balancing polices. The proposed model is composed of two levels; base and load balancing. The base level has three components: user set, enterprise service bus header and computing nodes set, communicating through net centric enterprise service bus. The load balancing level in turn is composed of two phases. The first phase selects the candidate computing nodes that satisfy the requirements of the submitted tasks. The second phase applies any of the imported load balancing policies for nominating a computing node from the list of candidate computing nodes to process submitted tasks. Moreover, a quality of service load balancing policy is proposed. This policy combines three key performance indicators in a single weighted normalized factor. The performance of the proposed model is evaluated and compared using suggested load balancing policy and other five similar load balancing policies through simulation. The results reveal that, the performance of proposed model using suggested load balancing policy outperforms that of the other studied policies in terms of average task response time, average computing node utilization, and load balancing level.
