Abstract
Distributed e-business application platforms such as the web services framework will require sophisticated workload management infrastructures for the routing of client requests to the most appropriate services. This paper introduces a novel and dynamic predictive framework that uses both analytical performance modelling and historical data to extrapolate a request's predicted performance under varying workloads and conditions on different systems. Such a framework can facilitate a routing algorithm in meeting quality of service-based metric requirements. An e-business benchmark is used as a demonstrator to provide an insight into the techniques used in predicting request response times.