Performance improvement of distributed system through load balancing and task scheduling using fuzzy logic
by Abhijit A. Rajguru; Sulabha S. Apte
International Journal of Engineering Systems Modelling and Simulation (IJESMS), Vol. 11, No. 1, 2019

Abstract: Task scheduling and load balancing in distributed network are the most challenging research area in computer science. In distributed systems, scheduling mechanism has more issues as there is no centralised authority to allocate the workload among multiple processors. Further, handling both load balancing and scheduling at hand is a daunting task. In this paper, we propose a fuzzy-based load balancing and task scheduling technique to optimise the performance of distributed system. Initially, clusters are formed and node with larger buffer availability and high CPU speed is elected as cluster head. Tasks are prioritised into flexible and non-flexible using task prioritising strategy. Non-flexible tasks are prioritised over flexible tasks. For non-flexible tasks, essential information of nodes such as CPU speed, work load and distance from cluster head are made pass through the fuzzy system. Node state is obtained as output. Based on states of node, non-flexible tasks are allocated. Our technique dynamically handles scheduling and load balancing at hand. We use simulation results to prove efficiency of our technique.

Online publication date: Tue, 09-Apr-2019

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Engineering Systems Modelling and Simulation (IJESMS):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com