On the analysis of semi-hard real-time control systems

Abstract

In this paper we investigate systems which combine the timing requirements of real-time processing with the complexity of knowledge processing. In such real-time environments it cannot be guaranteed that all processes meet their deadlines but it is possible to isolate a subset of critical processes which must meet their deadlines. We call such systems semi-hard real-time control systems. The behavior of critical processes in terms of resource utilization is known in advance but there are non-critical processes whose behavior is subject to change. Though priority scheduling is used, the execution times of critical processes has to be determined by a non-deterministic analysis which takes into account contention for system resources with non-critical processes. A subset of system resources do not allow preemption, for example a process running into a critical section must complete its function. The structure and the performance of a class of such systems, namely the data acquisition and analysis systems are analyzed in case of procedure oriented as well as in the case of message oriented design. A methodology for system modeling and the approximations needed are discussed. Even in the simple case of a system with only one critical process the analysis is non-trivial; due to priority scheduling the system model is non-separable hence does not have a product form solution.