Estimating real-time service process response time using server utilizations

In this paper, we study the algorithms to estimate the response times of service executions during real-time service composition. By using reservation schedules to derive server utilization, we can compute a more realistic response time for each service than its static execution time. Reservation schedules are kept in a system data structure called hierarchical TBTree (hTBTree). Using these response time estimates, integer programming or graph search algorithms can be used to compose a service process which is more likely to meet its end-to-end deadline. We conduct performance study to compare compositions with and without using server utilizations.