计算机科学与探索 ›› 2014, Vol. 8 ›› Issue (10): 1177-1186.DOI: 10.3778/j.issn.1673-9418.1402027

• 学术研究 • 上一篇    下一篇

云存储智能多数据副本放置机制

张  榜+,王兴伟,黄  敏   

  1. 东北大学 信息科学与工程学院,沈阳 110819
  • 出版日期:2014-10-01 发布日期:2014-09-29

Intelligent Multiple Data Replica Placement Scheme for Cloud Storage

ZHANG Bang+, WANG Xingwei, HUANG Min   

  1. College of Information Science and Engineering, Northeastern University, Shenyang 110819, China
  • Online:2014-10-01 Published:2014-09-29

摘要: 数据副本管理机制是云存储系统的重要组成部分。为了提高云存储系统的可伸缩性、可靠性,同时改善用户访问时间,通常采用多数据副本机制,并且需要解决数据副本放置问题。为此,提出了一种用于云存储系统的智能多数据副本放置机制。该机制基于p-中心模型,以最小化访问代价为优化目标,基于遗传算法(genetic algorithm,GA)确定优化的数据副本放置方案,基于生物地理学优化(biogeography-based optimization,BBO)算法确定用户访问请求对数据副本的优化分配。基于CloudSim进行了仿真实现和性能评价,结果表明,云存储智能多数据副本放置机制是可行和有效的。

关键词: 云存储, 多数据副本, 副本放置, 遗传算法(GA), 生物地理学优化(BBO)

Abstract: The data replica management scheme is a critical component of cloud storage system. In order to improve its scalability and reliability at the same time shorten user access time, the multiple data replica scheme should be adopted and the proper placement for each replica should be determined. Thus, this paper proposes an intelligent multiple data replica placement scheme for cloud storage. This scheme is based on p-center model with minimizing user access cost as its optimization objective. It uses genetic algorithm (GA) to find the optimal data replica placement solution and uses biogeography-based optimization (BBO) algorithm to optimally assign user access request to the specific data replica. The proposed scheme has been implemented based on CloudSim and performance evaluation has been done. The simulation results show that it is both feasible and effective.

Key words: cloud storage, multiple data replica, replica placement, genetic algorithm (GA), biogeography-based optimization (BBO)