Workflow-based resource allocation to optimize overall performance of composite services
Future Generation Computer Systems
| Hi-index | 0.00 |
The emerging paradigm of distributed Web services has promised seamless business integration across the Internet that shares not only computing power but also applications. One major challenge is resource allocation to each end user in an economically efficient and low latency manner. A common solution is proportional sharing where each user gets his resource in proportion to the predetermined weight. However, this does not allow users to differentiate the value of their services and to dynamically adjust the weights. A resource reservation mechanism may improve the information and service sharing but usually introduces a high latency. In this paper, we propose a progressive auction based market mechanism for resource allocation that allows user differentiation of the service value and ensures the resource acquisition latency to be limited only to the communication delay in Service-Oriented Architecture (SOA) systems. We present a service sharing prototype for selecting services for further business process composition or solution creation and show experimental results on the formation of reliable user ranking in resource sharing through the progressive auction.