Enforcing timeliness and safety in mission-critical systems

Abstract

Advances in sensor, microprocessor and communication technologies have been fostering new applications of cyber-physical systems, often involving complex interactions between distributed autonomous components and the operation in harsh or uncertain contexts. This has led to new concerns regarding performance, safety and security, while ensuring timeliness requirements are met. To conciliate uncertainty with the required predictability, hybrid system architectures have been proposed, which separate the system in two parts: one that behaves in a best-effort way, depending on the context, and another that behaves as predictably as needed, providing critical services for a safe and secure operation. In this paper we address the problem of verifying the correct provisioning of critical functions at runtime in such hybrid architectures. We consider, in particular, the KARYON hybrid architecture and its Safety Kernel. We also consider a hardware-based non-intrusive runtime verification approach, describing how it is applied to verify Safety Kernel software functions. Finally, we experimentally evaluate the performance of two distinct Safety Kernel implementations and discuss the feasibility issues to incorporate non-intrusive runtime verification.