Journal
KNOWLEDGE-BASED SYSTEMS
Volume 140, Issue -, Pages 64-81Publisher
ELSEVIER
DOI: 10.1016/j.knosys.2017.10.027
Keywords
Web service composition; QoS; Credibility evaluation; Multi-objective optimization
Categories
Funding
- NSFC [61672152, 61232007, 61532013]
- Collaborative Innovation Center of Novel Software Technology and Industrialization
- Collaborative Innovation Center of Wireless Communications Technology
Ask authors/readers for more resources
QoS-aware Web service composition is regarded as one of the fundamental issues in service computing. Given the open and dynamic internet environment, which lacks a central control of individual service providers, we propose in this paper a novel method that seamlessly considers Quality of Service (QoS) and credibility of service providers to achieve optimal service compositions. Instead of using creditability as one of the QoS attributes, we treat it as the overall capability of a service provider to deliver its promised QoS. We aggregate both user experience (i.e., user trust) and track record (i.e., service reputation) of a provider for accurate creditability evaluation. To facilitate user decision making when multiple (and sometimes conflicting) QoS attributes are involved, we develop an automatic weight calculation approach based on rough set theory and a fuzzy analytic hierarchy process, which assigns higher weights to the more discriminative attributes. Finally, to achieve an optimal service composition, a two phase optimization process is employed, where local optimization chooses services based on creditable QoS assessment and global optimization tackles a multi-objective problem using an effective cuckoo search algorithm. Extensive experimental results show that the proposed QoS-aware service composition approach achieves desirable QoS with credibility guarantees. The performance of our proposed approach also significantly outperforms other competitive methods. (C) 2017 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available