• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2015, Vol. 37 ›› Issue (11): 1989-1996.

• 论文 • Previous Articles     Next Articles

A marine monitoring big data placement strategy in cloud
computing environment based on data dependency  

HUANG Dongmei1,SUI Hongyun1,HE Qi1,ZHAO Danfeng1,DU Yanling1,SU Cheng2   

  1. (1.College of Information,Shanghai Ocean University,Shanghai 201306;
    2.East China Sea Branch of S.O.A,Shanghai 201306,China)
  • Received:2015-07-13 Revised:2015-09-20 Online:2015-11-25 Published:2015-11-25

Abstract:

Marine monitoring data is big and has strong data dependency. How to design a fast placement strategy and control the marine data efficiently becomes more and more important for the management and the application of big marine monitoring data. In cloud computing environments, according to the characteristics of big marine monitoring data we propose a placement strategy based on data dependency. Under the condition of guaranteeing the load balancing of data centers, the dependencies among monitoring tasks, monitoring points and monitoring data are considered comprehensively. The dependency of monitoring points, the dependency of monitoring data and the overall dependency of monitoring data are established.According to the three kinds of dependencies, the marine data placement is done so as to make the big marine monitoring data in the same data center with higher dependency.Experimental results show that our strategy reduces the response time of ocean monitoring data access and provides an effective placement strategy for ocean monitoring data.

Key words: big marine monitoring data;cloud computing environment;data placement;dependency