Improving Performance for Decentralized Execution of Composite Web Services

Decentralized orchestration of composite web services offers performance improvements in terms of increased throughput and lower response time. However, most relevant research literature in decentralizing service composition omit the step of selecting component services, the locations of which have major impact on the amount of dataflow messages and the volume of network traffic during decentralized execution. In order to reduce the network traffic generated by data flow messages thus to improve the performance of the decentralized orchestration, this paper presents an approach to component service selection using data dependency graphs. The performance evaluation concludes that a substantial decrease in network traffic by use of our service selection approach results in a reduction of approximately 30% in execution time on average.