Enhancing Fault Detection in Time Sensitive Networks using Machine Learning

Abstract

Time sensitive networking (TSN) is gaining attention in industrial automation networks since it brings essential real-time capabilities to the Ethernet layer. Safety-critical realtime applications based on TSN require both timeliness as well as fault-tolerance guarantees. The TSN standard 802.1CB introduces seamless redundancy mechanisms for time-sensitive data whereby each data frame is sequenced and duplicated across a redundant link to prevent single points of failure (most commonly, link failures). However, a major shortcoming of 802.1CB is the lack of fault detection mechanisms which can result in unnecessary replications even under good link conditions -clearly inefficient in terms of bandwidth use. This paper proposes a machine learning-based intelligent configuration synthesis mechanism that enhances bandwidth utilization by replicating frames only when a link has a higher propensity for failure.

A Classification of the Enabling Techniques for Low Latency and Reliable Communications in 5G and Beyond: AI-Enabled Edge Caching

“…The standards define how frames belonging to a particular traffic class or having a particular priority are handled by TSN-enabled bridges. Based on the discussions in [16], [ [16], [31]- [33], [44], [51], [92]- [97].…”

“…On the other hand, the challenges of the TSN and DetNet standards were considered in [10], [16], [94], [96], [97], together with the potential solutions. Here, we highlight some of the challenges.…”

“…The frame replication technique may result in inefficient bandwidth utilization. Therefore, the work in [16], [97] presented the techniques to alleviate the limitations. In the case of frame replication and elimination mechanisms, [16] presented that the packet replication can be controlled based on traffic class and the path information acquired through the TSN stream identification.…”

“…In [97], a machine learning-based intelligent configuration synthesis mechanism was proposed to enable fault detection techniques in order to detect when and where a fault occurs. Subsequently, the intelligent configuration synthesis mechanism replicates the frames only when a link has a higher propensity for failure.…”

“…On the other hand, in traffic flows with deterministic behavior and bounded ULL, the TSN and DetNet standards present effective mechanisms. However, the TSN and DetNet incur several challenges as highlighted in [10], [16], [94], [96], [97]. For example, the latency of low priority traffic is based on the preemption occurrences which depends on the high priority traffic intensity.…”