Fault-tolerant deployment of embedded software for cost-sensitive real-time feedback-control applications

Abstract

Abstract

Synthesis of fault-tolerant embedded systems with checkpointing and replication

“…Very few researchers [14,19,20] consider the optimization of implementations to reduce the overheads due to fault-tolerance and, even if optimization is considered, it is very limited and does not include the concurrent usage of several fault-tolerance techniques. Moreover, the application of faulttolerance techniques is considered in isolation, and thus is not considered in relation to other levels of the design process, including mapping, scheduling and bus access optimization.…”

“…A simple heuristic for combining several static schedules in order to mask fault-patterns through replication is proposed in [5], without considering the timing constraints of the application. This approach is used as the basis for cost and fault-tolerance trade-offs within the Metropolis environment [20]. Graph transformations are used in [3] in order to introduce replication mechanisms into an application.…”

Synthesis of Fault-Tolerant Embedded Systems

“…For example, Pinello et al [25] propose a heuristic for combining several static schedules in order to mask fault patterns. Multiple failures are addressed with active replication in [11] in order to guarantee a required level of fault tolerance and satisfy time constraints.…”

Synthesis of Fault-Tolerant Schedules with Transparency/Performance Trade-offs for Distributed Embedded Systems

“…A simple heuristic for combining several static schedules in order to mask fault-patterns through replication is proposed in [4], without, however, considering any timing constraints. This approach is used as the basis for cost and fault-tolerance trade-offs within the Metropolis environment [15].…”