QoS-aware and multi-granularity service composition

  • Authors:

  • Zaiwen Feng;Rong Peng;Raymond K. Wong;Keqing He;Jian Wang;Songlin Hu;Bing Li

  • Affiliations:

  • State Key Lab of Software Engineering, Wuhan University, Wuhan, China and School of Computer, Wuhan University, Wuhan, China;State Key Lab of Software Engineering, Wuhan University, Wuhan, China and School of Computer, Wuhan University, Wuhan, China;School of Computer Science & Engineering, University of New South Wales, Sydney, Australia;State Key Lab of Software Engineering, Wuhan University, Wuhan, China and School of Computer, Wuhan University, Wuhan, China;State Key Lab of Software Engineering, Wuhan University, Wuhan, China and School of Computer, Wuhan University, Wuhan, China;Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China;State Key Lab of Software Engineering, Wuhan University, Wuhan, China and School of Computer, Wuhan University, Wuhan, China

  • Venue:
  • Information Systems Frontiers
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

Composition of Web services can be very complex, and usually involves multiple atomic services and varieties of message exchange patterns. Worst still, with the increasing amount of available services with varying granularity and quality, selecting the best combination of services becomes very challenging. This paper addresses the issues on multi-granularity service composition with awareness of the service quality. In particular, we consider how a new service composition plan is produced, while preserving its original observable behaviors of a service that are shown to the service user, by substituting the service with another service or a set of services of finer or coarser grain. The new plan aims to have services of better quality (if the corresponding underlying services are available). To achieve this, we firstly define a behavioral signature model to capture observable behaviors of services. We then present that two service composition plans are choreography equivalent if they comply with the same behavioral signature model. We then propose a behavioral extracting algorithm to obtain the behavioral signature model from a service composition plan. We also present a method to determine choreography equivalence. Finally we briefly describe our prototype implementation that captures all these proposed algorithms.