User Requirements Based Service Identification for Big Data

Abstract

Service identification meets with new challenges with overwhelming rise of categories and numbers of services in big data scenarios. Most of the current service identification approaches have paid little attention to the granularity of indicator for service identification, neither do they provide with any trustworthy monitoring mechanism during the process of service identification. To address the problems above, we propose a user requirements based service identification approach for big data (URBSI-BD). In the proposed URBSI-BD, we firstly cluster massive services with BIRCH clustering algorithm to obtain a number of service sets. We then employ PSO algorithm with MapReduce mechanism to achieve a fine-grained evaluation of indicator for service identification. Based on the integration, candidate services which can better meet with user requirements will be selected. Finally, we use Beth trust model on the quality of experience of users and set up a monitoring mechanism to better obtain required services. Simulation results and analysis demonstrate that the proposed approach has better performance in service identification compared with other current approaches in big data scenarios.