Deriving Monitoring Bounds for Distributed Real-Time Systems

Runtime controllers can be used in distributed embedded systems to throttle or stop software components and thus to limit the timing effects that applications have on each other through scheduling dependencies. Such runtime controllers require bounds on the worst-case admissible resource utilization per task to estimate and to control the worst-case interference between applications. Multi-dimensional sensitivity analysis can be used to derive efficient local controller bounds from global system constraints. In this paper we present a novel distributed algorithm to determine a multi-dimensional sensitivity bound on activation jitter which serves that purpose. Distribution makes it suitable for in-field application in modular designs, a main requirement in many industrial applications. Its properties are formally derived. Extensive experiments evaluate the solution quality and computation time.