Availability management framework reduces outages in safety critical IoT systems
An Availability Management Framework for Microservice-Based Safety-Critical CIoT Systems: Architecture and End-to-End Evaluation
Networking and Internet Architecture
Summary
Safety-critical IoT systems often experience long outages when their parts fail, because current fixes happen only after problems start. The authors propose a new method that uses machine learning to detect problems early and switch to a backup system before failure occurs. They tested this approach on a remote-controlled driving system and found it greatly reduced outage times compared to standard recovery methods. This means safer and more reliable systems for applications where delays can be dangerous.
What this means in practice
- •For industrial iot engineers: Improve real-time availability in safety-critical IoT deployments by using predictive anomaly detection and rapid switchover to backup services.
- •For cloud platform operators: Integrate machine learning based anomaly detection with orchestration platforms to reduce downtime caused by container restarts under resource pressure.
Authors
Hassaan Siddiqui, Ferhat Khendek
Abstract
Safety-critical Cellular Internet of Things (CIoT) systems increasingly rely on microservice architectures orchestrated across heterogeneous edge and cloud platforms. Although this paradigm improves modularity and scalability, the fault-tolerance mechanisms of contemporary orchestration platforms remain predominantly reactive, i.e., failed components are restarted or rescheduled only after an outage has already occurred. Such recovery can produce multi-second End to End Service Outage Time (E2E SOT), which can grow further under container restart backoff. This paper proposes an Availability Management Framework (AMF), a generic monitor-predict-recover loop that complements reactive recovery with machine learning-based anomaly detection and make-before-break switchover to a standby replica. Candidate ML models are evaluated offline under three protocols, including a change of operating regime, in order to select a model for live deployment. AMF is instantiated and evaluated on a three-tier tele-operated driving (ToD) testbed under a staged resource-exhaustion scenario. Relative to Kubernetes-only recovery, AMF completes switchover during the anomaly window, reduces E2E SOT, and avoids the tens-of-seconds outages associated with repeated in-place restarts under backoff. On this non-real-time testbed, residual E2E SOT lies inside healthy-path jitter and is therefore limited by path timing rather than by lateness of the recovery decision. The paper whows that coupling a validated ML based anomaly detector with proactive switchover can remove restart- and backoff-dominated outage from a critical path.