Incremental, Distributed, and Concurrent Scheduling in Systems-of-Systems with Real-Time Requirements

Systems-of-Systems (SoS) are large-scale networked embedded systems that are characterized by operational and managerial independence of constituent systems, geographical distribution, emergent behavior and evolutionary development processes. This paper introduces a conceptual model and a scheduling algorithm for supporting real-time requirements in SoS. Real-time support is essential in many safety-relevant application areas such medical, military and industrial SoS. The search for a feasible schedule is computed incrementally upon the introduction of new applications in the SoS. The distributed computation of the schedule using the different constituent systems considers the lack of global knowledge and control in the SoS, while also reducing the overall scheduling time. Concurrent scheduling activities are supported to deal with the uncoordinated and possibly simultaneous introduction of multiple applications. The paper introduces a high-level scheduling algorithm for the SoS as well as a low-level scheduling problem for individual constituent systems. The incremental scheduling problem for the constituent systems is formulated using IBM CPLEX. An experimental evaluation with automatically generated examples demonstrates the feasibility of the proposed solution.