ServiceFlow: QoS-based hybrid service-oriented grid workflow system

  • Authors:
  • Haijun Cao;Hai Jin;Xiaoxin Wu;Song Wu

  • Affiliations:
  • Services Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China 430074;Services Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China 430074;Communication Technology Lab, Intel China Research Center, Beijing, China 100080;Services Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China 430074

  • Venue:
  • The Journal of Supercomputing
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Based on OGSA, grid workflow may construct new value-added services by composing existing elementary services with sophisticated workflow logic. Due to the highly heterogeneous and dynamic features of grid, Quality of Service (QoS) becomes essential and poses great challenges to grid workflow. This paper presents a QoS-based hybrid service-oriented grid workflow system called ServiceFlow, which enables the construction of QoS-aware workflow at both abstract and concrete service levels. To gather and delegate multiple concrete physical services providing equivalent functionality but diverse QoS capabilities, virtual service is proposed to participate in service composition. In addition, two phases of service selection, namely pre-matching phase and QoS-based service selection phase, are designed for dynamic service bindings at runtime. Performance evaluation results indicate that ServiceFlow can improve different QoS metrics to fulfill the user's requirements.