earticle

논문검색

A Load Balancing Algorithm based on the Variation Trend of Entropy in Homogeneous Cluster

초록

영어

In order to solve the problems of ill-balanced task allocation, long response time, low throughput rate and poor performance, which appeared in cluster system, this paper proposes a new load balancing algorithm of homogeneous cluster based on the variation trend of entropy. In this paper, we introduces the thermodynamic concept of entropy into load balancing algorithm and gives a new algorithm, so that we can calculate the entropy of the system to ensure that each scheduling and migration toward the entropy increasing tendency. The result of simulating experiments shows that this algorithm has more obvious advantages compared with traditional algorithms, such as achieving the load balancing status as soon as possible, shorting the task execution time, increasing system performance and so on.

목차

Abstract
 1. Introduction
 2. Basic Concept
  2.1. Concept of Entropy
  2.2. Concept of Load Balancing
 3. Model of the Algorithm
 4. Implementation of the Algorithm
  4.1. Collection and Processing of Load Information
  4.2. Selection of the Scheduling Policy
  4.3. Choice of the Migration Strategy
  4.4. Implementation of the Migration
  4.5. Description of the Algorithm
 5. Experiments and Results
 6. Conclusion
 References

저자정보

  • Kehe Wu Beijing Engineering Research Center of Electric Information Technology, North China Electric Power University, NO.2 Beinong Road, Changping District, Beijing 102206, China
  • Long Chen Department of Control and Computer Engineering School, North China Electric Power University, NO.2 Beinong Road, Changping District, Beijing 102206, China
  • Shichao Ye Department of Control and Computer Engineering School, North China Electric Power University, NO.2 Beinong Road, Changping District, Beijing 102206, China
  • Yi Li Department of Control and Computer Engineering School, North China Electric Power University, NO.2 Beinong Road, Changping District, Beijing 102206, China

참고문헌

자료제공 : 네이버학술정보

    함께 이용한 논문

      ※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.

      0개의 논문이 장바구니에 담겼습니다.