Efficient Algorithm for Jitter Minimization in Time-Triggered Periodic Mixed-Criticality Message Scheduling Problem

Abstract

The current research in real-time scheduling focuses mostly on the certification of functionalities with respect to safety requirements under conservative assumptions or to achieve efficient resource utilization but with optimistic assumptions. With growing system complexity, the safety certification is becoming hard, especially in event-triggered environments. In time-triggered environments, the network nodes are synchronized by clocks and follow a static schedule hence they are easily certifiable. However, the time-triggered paradigm has two disadvantages. The first one is its general non-flexibility (e.g. message retransmission, efficient resource usage) and the second one is the need for an efficient scheduling algorithm producing the schedule. In this paper, we propose a solution to both of these issues. To address the first disadvantage, we propose a method for non-preemptive message retransmission in time-triggered environments while preserving the efficient use of resources. Based on the message criticality we allow a certain number of retransmissions. The observed prolongation of the processing time of a highly critical message is compensated by skipping transmission of less critical messages. Static schedules then contain all alternatives caused by the retransmissions that can occur during a run time execution. Schedules conform with certification requirements imposed on the highly critical messages while preserving the efficient use of resources. To address the second disadvantage, we propose a novel heuristic scheduling algorithm with an unscheduling step for solving large instances of periodic message scheduling problem. The message periodicity is assumed to be a power of two and the objective is to minimize the maximal jitter. The efficiency of the approach is demonstrated on problem instances with up to 2000 messages.