首页    期刊浏览 2024年11月27日 星期三
登录注册

文章基本信息

  • 标题:DECENTRALIZED LOAD BALANCING IN HETEROGENEOUS DISTRIBUTED SYSTEMS USING TRAINING BASED APPROACH
  • 本地全文:下载
  • 作者:MOHD HAROON ; MOHD HUSAIN
  • 期刊名称:International Journal of Computer Science and Engineering
  • 印刷版ISSN:2278-9960
  • 电子版ISSN:2278-9979
  • 出版年度:2016
  • 卷号:5
  • 期号:1
  • 页码:6
  • 语种:English
  • 出版社:IASET Journals
  • 摘要:Load balancing and job scheduling both are the most important attributes in parallel system and distributed system, once the new jobs are generated, then the scheduler decide whether the generated job is executed, load balancing is one of the important activities, by load balancing technique, load of the entire computing system is balanced, resulting that improving of system throughput, and response time, resource utilization is also improved by the load balancing approach. A new model is proposed, in this model a new load distribution approach has been defined, and during compile time further reallocation of the load is also defined in this model, by the help of this approach, a processor network has been created, in this network, data movement, data reallocation, process or thread creation is also understandable. The proposed algorithm is adaptable and scalable, this algorithm is applied in adhoc network, the generated work is randomly distributed among all processors, and if any computing node is out of order then the load reallocation method can justify the further allocation of the load.
国家哲学社会科学文献中心版权所有