Graceful Degradation with Condition- and Inference-aware for Mixed-Criticality Scheduling in Autonomous Systems

---

Authors:

Jie Zou, Xiaotian Dai and John McDermid

Keywords:

Abstract:

"In an autonomous system, understanding functional causality is important when designing a shared resource scheduling strategy; without this, the system would be unlikely to achieve the holistic functional quality of service (QoS) and may not meet safety goals. This work proposes a novel graceful degradation strategy in a mixed-criticality context. Instead of discarding computational load at the application level, a qualitative and quantitative definition of importance order is used to assist in realising finer-grained task-level degradation and rescue more LO-criticality tasks. The causality analysis-based degradation bridges the gap where functional dependencies are not considered in scheduling design and thus leads to the system can continue to run with relatively higher QoS during the degradation process."