Dynamic Stochastic Models for Workflow Response Optimization

  • Authors:
  • Radu Sion;Junichi Tatemura

  • Affiliations:
  • Stony Brook University;NEC Research Labs

  • Venue:
  • ICWS '05 Proceedings of the IEEE International Conference on Web Services
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we propose a solution for optimizing (web service)business workflow response times through dynamic resource allocation.On-the-fly monitoring is combined with a novel workflow modelingalgorithm that discovers critical execution paths and builds "dynamic" stochastic models in the associated "critical graph." One novelcontribution of this work is the ability to naturally handle parallelworkflow execution paths. This is essential in applications whereworkflows include multiple concurrent service calls/paths that need to be "joined" at a later point in time. We discuss theautomatic deployment of on-the-fly monitoring mechanisms withinthe resource management mechanisms. We implement, deployand experiment with a proof of concept within a generalized web services business process (BPEL4WS/SOAP) framework. In the experimental setup we explore and show the naturaladaptation to changing workflow conditions and appropriateautomatic re-allocation of resources to reduce execution times.