Learning automata-based adaptive web services composition

Guoqiang Li*, Dandan Song, Lejian Liao, Fuzhen Sun, Jianguang Du

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Citations (Scopus)

Abstract

Service-oriented computing is a widely adopted paradigm in real applications. Considering the continuous evolution of services, adaptive service composition has always been a major concern. It is a big challenge to adjust the composition to be optimal in real-time. In this paper, a learning automata-based approach is proposed to attack this problem. It consists of two important components: random environment and a learning automaton. The former can be mapped to the service's execution environment. The latter is responsible for the adaptation achievement using reward and penalty functions, while we take the service composition structures into account to compute the usefulness value of all services. At last, simulation study has shown that our approach is efficient to find the optimal (sub-optimal) composition.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS
EditorsM. Surendra Prasad Babu, Li Wenzheng, Eric Tsui
PublisherIEEE Computer Society
Pages792-795
Number of pages4
ISBN (Electronic)9781479932788
DOIs
Publication statusPublished - 21 Oct 2014
Externally publishedYes
Event2014 5th IEEE International Conference on Software Engineering and Service Science, ICSESS 2014 - Beijing, China
Duration: 27 Jun 201429 Jun 2014

Publication series

NameProceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS
ISSN (Print)2327-0586
ISSN (Electronic)2327-0594

Conference

Conference2014 5th IEEE International Conference on Software Engineering and Service Science, ICSESS 2014
Country/TerritoryChina
CityBeijing
Period27/06/1429/06/14

Keywords

  • learning automata
  • self-adaptive web service composition
  • web service

Fingerprint

Dive into the research topics of 'Learning automata-based adaptive web services composition'. Together they form a unique fingerprint.

Cite this