Load Balancing Improvement Through Flexible Assignment of Jobs in the Grids

Author:

Maru Jalay Saurin1,Jani Raxit1,Parmar Nishith1

Affiliation:

1. Gandhinagar Institute of Technology, India

Abstract

Grid computing has emerged as a striking computing concept due to the availability of high-speed wide area networks and low-cost computational capital. This represents a novel load balancing algorithm for grid systems by allowing for node allure. The set of partners and neighbours are created for each node using the prestige of the job. For each job, in the gird, the given algorithm uses the popularity of other nodes in the grid to form k number of partners and p number of neighbours. The methods for constructing neighbours and partners are existing. A new job arriving to a node is immediately dispersed to the originating node or to its partner nodes. The load adjustment is approved incessantly, and reciprocal information administration is used to minimize the communication overhead in the elaborated load balancing algorithm. The given algorithm is self-motivated, sender-initiated, and decentralized.

Publisher

IGI Global

Reference13 articles.

1. Ashok, A. S., & D., P. (2012). Grid Computing: various job scheduling strategies, emerging trends in computer science and information technology. In Proceedings of the International Conference on Emerging Trends in Computer Science and Information Technology. ETCSIT.

2. Benmohammed-Mahieddine, K. (n.d.). An Evaluation of Load Balancing Algorithms for Distributed Systems. Academic Press.

3. An Adaptive Scoring Job Scheduling algorithm for grid computing.;R.-S.Chang;Information Sciences,2012

4. El-Zogdhy, S., Kameda, H., & Li, J. (2006). Numerical studies on a paradox for noncooperative static load balancing in distributed computer systems. Computers and Operations Research, 345-355.

5. Diffusive load balancing schemes on heterogeneous networks

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3