A Classification Framework of Service Composition Issues in BIRIS Scenario

Service composition (SC) is currently one of the most popular research topics in service computing domain. Given a specific functional and non-functional requirements on a specific service, a composition algorithm selects a set of service components from an existing repository and composes them together as a total solution to fulfill the requirement. There have been fruitful achievements, e.g., template-based composition, planning-based composition, automated/semi-automated/manual composition, etc. However, along with BIRIS becomes a dominate form of modern service systems, a series of new appearing features bring great challenges to traditional SC researches, e.g., (1) from one single requirement to temporally sequential requirements, (2) the available services from abundant to limited, (3) from orchestration-oriented composition solution to choreography-oriented ones, (4) from specified requirements to ambiguous and personalized ones, (5) from the objective of maximizing customer satisfaction to ensuring the benefits of customers and providers together, etc. This paper analyzes these challenges elaborately and presents a classification framework which includes 4 dimensions and 13 sub-dimensions. Several typical SC issues in BIRIS scenario are identified under the framework.