基于Hadoop的可信Web服务多维QoS权重最优选择模型  

Multidimensional QoS Weight Model for Trusted Web Service Optimal Selection Based on Hadoop

作　　者：何小霞[1] 谭良[1,2] 

机构地区：[1]四川师范大学计算机科学学院,成都610068 [2]中国科学院计算技术研究所,北京100190

出　　处：《计算机科学》2015年第4期51-55,67,共6页Computer Science

基　　金：国家自然科学基金(61373162);四川省科技支撑项目(2014GZ007)资助

摘　　要：随着Web服务应用的快速增长,用户如何在众多功能相似的Web服务中更加准确地选择出满足自己非功能性需求的Web服务是一个急需解决的问题。针对此问题,设计了一种基于Hadoop的可信Web服务多维QoS权重最优选择模型——HL模型。在HL模型中,以Hadoop和HBase平台为基本框架,首先,使用主客观赋权模式为多维QoS属性赋权值,提高QoS属性权重的客观性和准确性;其次,加入信誉度参数来提高Web服务QoS属性的可信性,并采用QoS-Tree来存储QoS属性值和权重值。实验表明该模型不仅提高了QoS属性的可信性,使用一种客观的手法给出了合理的Web服务推荐顺序来满足用户的QoS需求偏好,而且还提高了Web服务在Hadoop中的查找准确性。With the rapid growth of the Web service application,major problem is how to select Web service more accurately to meet the users＇ non-function requirements from many functions similar of the Web services.To solve this problem,we designed a multidimensional QoS weight model for the trusted Web service optimal selection based on Hadoop,called HL pattern.In the pattern,we took the Hadoop and HBase platform as the basic framework.Firstly,using subjective-objective empowerment mode to multi-dimension QoS attribute weighting improves the objectivity and accuracy of the QoS attribute weights.Then,credibility parameters are added to improve the credibility of the Web service QoS attributes,and QoS-tree is used to store the QoS attribute values.Experimental results show that this model not only improves the credibility of the QoS attributes,gives the rational Web service recommended sequence,with an objective means to meet the demand of the user＇s QoS preference,but also improves the Web Service search accuracy in the Hadoop.

关 键 词：WEB服务 HADOOP QoS-Tree QoS权重 主客观赋权 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]