File(s) under permanent embargo
QoS-aware service composition for cloud manufacturing based on the optimal construction of synergistic elementary service groups
Cloud manufacturing (CMfg) has drawn extensive attentions from industrial community and academia. Quality of service (QoS)-aware service composition is critical to the on-demand use of distributed manufacturing resources and capabilities in CMfg systems. However, most previous work plainly composed composite services by the approach of one-to-one mapping-based service composition (OOM-SC), which leads to drawbacks to both the overall QoS of composite services and the success rate of service composition. To circumvent this, an approach of synergistic elementary service group-based service composition (SESG-SC) is proposed in this paper. It releases the assumption of one-to-one mapping between elementary services and subtasks, allowing a free combination of multiple functionally equivalent elementary services into a synergistic elementary service group (SESG) to perform each subtask collectively, thereby bettering the overall QoS and achieving more acceptable success rate. To introduce an optimal construction of SESGs into the optimization model of QoS-aware service composition, three kinds of redundant structures within SESGs are discussed and the corresponding QoS evaluation formulas are also proposed. To deal with the increasing computing complexity of the optimization model, an algorithm named matrix-coded genetic algorithm with collaboratively evolutional populations (MCGA-CEP) is designed in the current study. The experimental results indicate that the proposed SESG-SC approach significantly outperforms the previous approaches, and the proposed MCGA-CEP is sound on performance-wise.
History
Journal
International journal of advanced manufacturing technologyVolume
88Issue
9-12Pagination
2757 - 2771Publisher
SpringerLocation
London, Eng.Publisher DOI
ISSN
0268-3768eISSN
1433-3015Language
engPublication classification
C Journal article; C1.1 Refereed article in a scholarly journalCopyright notice
2016, Springer-Verlag LondonUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC