Enhancing Fault Detection in Time Sensitive Networks using Machine Learning

With the development of industrial Internet of Things, many new industrial networks are emerging. Among these networks, the standard of Wireless Networks for Industrial Automation-Process Automation (WIA-PA) is one typical specification for industrial wireless networking, while Time-Sensitive Network (TSN) is another typical specification for industrial wired networking. A factory network often consists of multiple kinds of networks, including wireless media and wired media. Therefore, effective protocol conversion among different industrial networks becomes more and more significant. To address this issue, this paper presents a conversion scheme between WIA-PA and TSN based on data flow mapping. The proposed scheme is composed of a set of conversion methods, including priority conversion method, flow identification conversion method, address conversion method, cross-network clock synchronization method, and bandwidth reservation method. The conversion mechanism is designed in detail and implemented on experimental platform. Test results show that the mutual conversion of data streams of the two networks is achieved effectively by the proposed scheme, while the key network characteristics such as the data stream priorities are maintained.

With the interconnection of distributed devices from different industrial automation networks, heterogeneous traffics with different Quality of Service (QoS) requirements increase dramatically. Shapers in Time-Sensitive Networking (TSN) enable the coexistence of different industrial traffics within a single network infrastructure. In this paper, with full consideration of the time-criticality of different industrial traffics and shaping mechanisms, we propose a network calculus-based modeling scheme for the widely-used Credit Based Shaper (CBS) and Time Aware Shaper (TAS). Then, we analyze the QoS of industrial traffics with different real-time characteristics by CBS and TAS, respectively. To evaluate the accuracy of network calculus-based modeling scheme, we compare our theoretical analysis with simulations, wherein a compactness function is defined to describe QoS compactness. Simulation results verify the effectiveness of proposed modeling scheme, by which we further validate both CBS and TAS can satisfy the QoS of traffics for different industrial automation scenarios.

5th-Generation (5G) and Time-Sensitive Networking (TSN) are regarded as competitive new technologies for future industrial networks; 5G-TSN collaboration transmission has drawn more attention because it can provide a guarantee of low-latency, ultra-reliable and deterministic transmission for time-critical automation applications. However, the methodologies of resource scheduling mechanisms in 5G and Time-Sensitive Networking (TSN) are quite different, which may lead to an inefficient Quality of Service (QoS) guarantee for deterministic transmission across 5G and TSN. Therefore, an efficient 5G-TSN joint scheduling algorithm based on Deep Deterministic Policy Gradient (DDPG) is proposed and analyzed in this article. The proposed algorithm takes both 5G radio channel information and the Gate Control List (GCL) state in the TSN domain into consideration, aiming to provide a latency guarantee for time-triggered applications across 5G and TSN as well as a throughput guarantee for video applications in 5G systems. The simulation results compare the latency and throughput performance of the proposed joint scheduling algorithm with several traditional 5G scheduling algorithms; meanwhile, several GCL setting methods are given to verify the impacts on latency and throughput performance within the proposed algorithm. The simulation results demonstrate that the proposed DDPG-based joint scheduling algorithm can significantly enhance the multi-application-carrying capability of 5G-TSN collaboration architecture.

The paper considers the problem of modeling time-critical networks in order to study the effectiveness of various real-time traffic management methods. Relevance. Real-time network modeling is an active area of research in computer science and information technology. Research in this area is aimed at developing methods and algorithms for efficient real-time data transmission. The work is devoted to modeling time-sensitive networks using various real-time traffic management methods. Goal. The purpose of the work was to analyze existing real-time network standards, develop a simulation model of a real-time network, and investigate the effectiveness of various real-time traffic management methods. Research methods. The research methods are based on modern theories of mathematical modeling, simulation modeling, and telecommunications standards, namely Time-Sensitive Networking (TSN). The results. The standards of real-time networks were thoroughly investigated. Detailed attention was paid to TSN (Time Sensitive Network) technology, the problem of achieving synchronization in such networks and various methods of traffic generation were investigated; the obtained analytical results were checked for compliance with the TSN network specification. OMNeT++ software was used for modeling real-time networks. End-to-end delay graphs were constructed for each traffic generation method under different to conditions of real-time networks. Conclusions. The paper considered TSN standard networks for reliable real-time communication and increase versatility in industrial networks. The problem of achieving synchronization of devices in the TSN network was investigated, various methods of traffic planning were considered, the importance of using end-to-end switching technology was established, a simulation model of the TSN network was developed.

The Industrial Internet of things (IIoT), the implementation of IoT in the industrial sector, requires a deterministic, real-time, and low-latency communication response for its time-critical applications. A delayed response in such applications could be life-threatening or result in significant losses for manufacturing plants. Although several measures in the likes of predictive maintenance are being put in place to prevent errors and guarantee high network availability, unforeseen failures of physical components are almost inevitable. Our research contribution is to design an efficient communication prototype, entirely based on internet protocol (IP) that combines state-of-the-art communication computing technologies principles to deliver a more stable industrial communication network. We use time-sensitive networking (TSN) and edge computing to increase the determinism of IIoT networks, and we reduce latency with zero-loss redundancy protocols that ensure the sustainability of IIoT networks with smooth recovery in case of unplanned outages. Combining these technologies altogether brings more effectiveness to communication networks than implementing standalone systems. Our study results develop two experimental IP-based industrial network communication prototypes in an intra-domain transmission scenario: the first one is based on the parallel zero-loss redundancy protocol (PRP) and the second one using the high-availability seamless zero-loss redundancy protocol (HSR). We also highlight the benefits of utilizing our communication prototypes to build robust industrial IP communication networks with high network availability and low latency as opposed to conventional communication networks running on seldom redundancy protocols such as Media Redundancy Protocol (MRP) or Rapid Spanning Tree Protocol (RSTP) with single-point of failure and delayed recovery time. While our two network communication prototypes—HSR and PRP—offer zero-loss recovery time in case of a single network failure, our PRP communication prototype goes a step further by providing an effective redundancy scheme against multiple link failures.

As new networking paradigms emerge for different networking applications, e.g., cyber-physical systems, and different services are handled under a converged data link technology, e.g., Ethernet, certain applications with mission critical traffic cannot coexist on the same physical networking infrastructure using traditional Ethernet packet-switched networking protocols. The IEEE 802.1Q Time Sensitive Networking (TSN) Task Group is developing protocol standards to provide deterministic properties, i.e., eliminates non-deterministic delays, on Ethernet based packet-switched networks. In particular, the IEEE 802.1Qcc, centralized management and control, and the IEEE 802.1Qbv, Time-Aware Shaper (TAS), can be used to manage and control Scheduled Traffic (ST) streams with periodic properties along with Best-Effort (BE) traffic on the same network infrastructure. We investigate the effects of using the IEEE 802.1Qcc management protocol to accurately and precisely configure TAS enabled switches (with transmission windows governed by Gate Control Lists (GCLs) with Gate Control Entries (GCEs)) ensuring ultra-low bounded latency, zero packet loss, and minimal jitter for ST TSN traffic. We examine both a centralized network/distributed user model (hybrid model) and a fully-distributed (decentralized) 802.1Qcc model on a typical industrial control network with the goal of maximizing the number of ST streams.

For time-sensitive networks, as in the context of IEEE TSN and IETF Detnet, cyclic dependencies are associated with certain fundamental properties such as improving availability and decreasing reconfiguration effort. Nevertheless, the existence of cyclic dependencies can cause very large latency bounds or even global instability, thus making the proof of the timing predictability of such networks a much more challenging issue. Cyclic dependencies can be removed by reshaping flows inside the network, by means of regulators. We consider FIFO-per-class networks with two types of regulators: perflow regulators and interleaved regulators (the latter reshape entire flow aggregates). Such regulators come with a hardware cost that is less for an interleaved regulator than for a perflow regulator; both can affect the latency bounds in different ways. We analyze the benefits of both types of regulators in partial and full deployments in terms of latency. First, we propose Low-Cost Acyclic Network (LCAN), a new algorithm for finding the optimum number of regulators for breaking all cyclic dependencies. Then, we provide another algorithm, Fixed- Point Total Flow Analysis (FP-TFA), for computing end-to-end delay bounds for general topologies, i.e., with and without cyclic dependencies. An extensive analysis of these proposed algorithms was conducted on generic grid topologies. For these test networks, we find that FP-TFA computes small latency bounds; but, at a medium to high utilization, the benefit of regulators becomes apparent. At high utilization or for high line transmission-rates, a small number of per-flow regulators has an effect on the latency bound larger than a small number of interleaved regulators. Moreover, interleaved regulators need to be placed everywhere in the network to provide noticeable improvements. We validate the applicability of our approaches on a realistic industrial timesensitive network.

A tactical network mainly consists of software-defined radios (SDRs) integrated with programmable and reconfigurable features that provide the addition and customization of different waveforms for different scenarios, e.g., situational awareness, video, or voice transmission. The network, which is mission-critical, congested, and delay-sensitive, operates in infrastructure-less terrains with self-forming and self-healing capabilities. It demands reliability and the need to survive by seamlessly maintaining continuous network connectivity during mobility and link failures. SDR platforms transfer large amounts of data that must be processed with low latency transmissions. The state-of-the-art solutions lack the capability to provide high data throughput and incorporate overhead in route discovery and resource distribution that is not appropriate for resource-constrained mission-critical networks. A cross-layer design exploits existing resources to react to environment changes efficiently, enable reliability, and escalate network throughput. A solution that integrates SDR benefits and cross-layer optimization can perform all the mentioned operations efficiently. In tactical networks, SDR’s maximum usable bandwidth can be utilized by exploiting radios’ autonomous behavior. This paper presents a novel virtual sub-nets based cross-layer medium access control (VSCL-MAC) protocol for self-forming multihop tactical radio networks. It is a MAC-centric design with cross-layer optimization that enables dynamic routing and autonomous time-slot scheduling in a multichannel network environment among SDRs. The cross-layer coupling uses link-layer information from the hybrid of time division multiple access and frequency division multiple access (TDMA/FDMA) MAC to proactively enable distributed intelligent routing at the network layer. The virtual sub-nets based distributed algorithm exploits spectrum resources and provides call setup with persistently available k-hop route information and simultaneous collision-free transmission of voice and data. The experimental results over extensive simulations show significant performance improvements in terms of minimum control overhead, processing time in relay nodes, a substantial increase in network throughput, and lower data latency (up to 76.98%) compared to conventional time-slotted MAC protocols. The design is useful for mission-critical, time-sensitive networks and exploits multihop simultaneous communication in a distributed manner.

As Industry 5.0 progresses, the demand for zero-touch configuration in industrial automation and smart manufacturing is increasing. This paper proposes a dynamic configuration management framework for Time-Sensitive Networking (TSN), aiming to address the challenges of flexibility and adaptability in dynamic network environments. A zero-touch configuration model is presented for TSN by incorporating a Delay-Aware Shortest Path Search (DASPS) algorithm to improve scheduling success rates. Simulation results demonstrate the ability of the framework to reconfigure networks within 2.67 milliseconds. The DASPS algorithm achieves a scheduling success rate of 70.22% for 1000 TSN flows, in contrast to only 22.23% achieved by the Shortest Path Search (SPS) algorithm. The proposed model effectively adapts to dynamic network changes, guaranteeing real-time data transmission. To further evaluate system adaptability, path entropy is introduced as a metric to quantitatively assess the balance of scheduling outcomes under topological changes. In the event of link failures, path entropy experiences a sharp decline but rapidly recovers after reconfiguration, demonstrating the system’s strong self-healing capability.

Time-sensitive networking (TSN) strives to provide an ultralow-latency real-time deterministic network for time-critical traffic using the time-aware shaper (TAS) mechanism. For this purpose, methods for routing and scheduling the time-critical flows must be specified. However, this is an NP-hard problem. Although several prior studies have suggested constraint programming (CP)-based approaches, these methods fail to provide a reasonable runtime due to the complexity of the problem. Motivated by this, we propose a TAS co-optimization (TACO) framework that solves the TAS scheduling and routing problem in TSN with a reasonable runtime. As an alternative to CP-based approaches, TACO considers a metaheuristic approach to co-optimize routing, scheduling order, and transmission timing. However, joint optimization through a metaheuristic algorithm is challenging due to the heterogeneous search spaces of the subproblems. Therefore, TACO carefully integrates the search spaces into a single domain and optimizes routing and TAS scheduling jointly with its heuristic algorithm. We evaluate TACO in various industrial networking scenarios to demonstrate that TACO achieves up to an 88% increase in the scheduling success rate with a good convergence rate and an overall low latency/jitter compared to other approaches.

Integrating Time-Sensitive Networking (TSN) in industrial wireless networks ensures reliability in data transmission. Automated powerline inspection using Unmanned Aerial Vehicles (UAVs) is an industrial application that requires time-constrained secure data exchanges with its ground station. However it is currently facing several critical challenges include handling massive data generated from onboard sensor, the limited computational capabilities, and ensuring secure communication over open wireless channels. Aiming to emphasize human-centric automation for enhanced operational safety and in alignment with the principles of Industry 5.0, this paper introduces a time-sensitive communication and detection framework for UAVIndustrial applications, named Latent-Coded UAV-IoT Transmission Segmentation YOLOv9 (LCUT-Sv9). It employs a modified lightweight Tiny-YOLOv9 model for powerline detection and utilizes autoencoder-based Latent-Coded UAV-IoT Transmission (LCUT) with the Message Queuing Telemetry Transport (MQTT) protocol for time-sensitive communication. The LCUT-Sv9 framework was evaluated using the widely adopted Transmission Towers / Power Lines Aerial-image (TTPLA) dataset, and demonstrated a significant detection accuracy improvement of 24.15 % over state-of-the-art (SOTA) techniques. LCUT also ensures minimal data transmission, reducing encoded data by approximately 50 %, making it compatible with the strict requirements of TSN-enabled industrial wireless networks.

The Open Platform Communication Unified Architecture (OPC UA) is a platform-independent service-oriented architecture, it has been widely used in industrial field network communication for its open, cross-platform, security, and extensible information model characteristics. The OPC UA supports clients/server (C/S) and publisher/subscriber (Pub/Sub) communication modes, using the Pub/Sub mode with the Time-Sensitive Networking (TSN) technology can greatly improve the real-time capability of the OPC UA. In factory field automation communication systems, various OPC UA servers are embedded in controllers, sensors, and actuators to enable the reliable exchange of information among each system with different data streams (i.e., real-time and non-real-time). It is hard to configure and manage such a large number of heterogeneous OPC UA servers. In this work, we propose an OPC UA multi-server aggregation and management architecture for industrial field networks, which supports the automatic discovery and aggregate of OPC UA servers, and a centralized configuration management method for OPC UA communication data streams is also supported. A laboratory-level OPC UA multi-server aggregation management platform is implemented to validate the proposed architecture. The test results demonstrate that the platform can support centralized management and configuration of multiple OPC UA servers and their corresponding data streams through a uniform OPC UA interface.

More data and information is being captured from systems, machines, and devices and made available to industrial information technology (IT) systems. The information is processed on-the-fly, enabling IT-based management systems to generate updated information for real-time control of the manufacturing processes. This data capturing and collection for IT systems is often referred to as the Internet of Things (IoT). When adopted to the industrial requirements, such as robustness, reliability, timeliness, and security, it is often termed as the industrial IoT (IIoT) [A1]. IIoT has attracted the attention of both the industry and academia since it is expected to enhance day-to-day activities, create new business models, products, and services, and as a broad source of research topics and ideas. Meanwhile, it is envisioned that the fifth-generation (5G) networks will be a cornerstone in future wireless industrial connectivity, and currently, there are multitude of ongoing research efforts in their design and optimization. Future industries willembrace use cases with numerous wireless-connected sensors and devices, and judging by the demand, massive machine-type communication and ultra-reliable low-latency communication (URLLC) in the literature and standardization activities, have been identified as two of the three main communication scenarios for 5G. These scenarios demand intelligent, scalable, and robust radio access techniques, network architectures, and deployment options to meet industrial demands [A2]. Therefore, more in-depth research is needed for IIoT and sensor networks in 5G-and-beyond wireless communication systems to address various challenges, including the following. 1)Transmit power control policy should be judiciously designed to improve both the spectrum efficiency and energy efficiency effectively; higher transmit powers can improve reliability but increase the interference and battery consumption. 2)Low-latency communication and computing is one of the significant challenges in 5G-and-beyond IIoT; uploading the device data to the cloud computing centers has high latency and resources waste issues in sensor networks. 3)Addressing privacy and security problems [A3] in the 5G-IIoT is fundamental to the further development and spread of 5G-IIoT. 4)Reliability and latency requirements of URLLC services, requiring less than 1-ms user plane latency and higher than 99.999% reliability, are demanding to meet, especially in time-varying industrial wireless channels. 5)Radio resource allocation, sharing, and isolation with performance guarantees under dynamic traffic conditions are critical issues for emerging IIoT applications requiring real-time support of massive connected devices. 6)5G-and-beyond IIoT networks must satisfy industrial-grade coverage, capacity, time-sensitive networking, and over-the-air time synchronization requirements [A4].

As the promising deterministic networking technology of Industrial Internet of Things (IIoT), Time-Sensitive Networking (TSN) has been widely investigated in recent years. Most existing research focuses on offline scheduling and routing for TSN, which is time-consuming and thus unsuitable for dynamic stream demands. To tackle this problem, an online scalable scheduling and routing (OSSR) scheme is proposed for TSN in this paper. A novel slot occupancy representation (SOR) model is established based on divisibility theory to transform the clique-based to a three-level tree-based mode in complex IIoT scenarios. This transformation reduces the computational complexity of maximum slot occupancy judgment from exponential to linear complexity. Based on the above SOR model, a load balance metric for stream scheduling is constructed to guide the optimal routing. Assessed by this metric, an online decoupled routing and scheduling algorithm is proposed to minimize the maximum slot occupancy of all links while guaranteeing high scalability. Evaluation results show that the proposed OSSR scheme outperforms the existing approaches with better adaption to dynamics and lower slot occupancy of links.

As an emerging communication technology, time-sensitive networking (TSN) promises the real time and deterministic interaction of massive data in Industrial Internet of Things. However, it is challenging to schedule the time-sensitive flows timely and superiorly through the mechanism analysis for current TSN scheduling models, especially in complex industrial scenarios. In this article, we propose an analysis approach of flow sequences based on divisibility theory to characterize the flow conflicts and dependencies, which derives the scheduling flexibility based on flow position diversity (PD) and the equivalent flow judgment conditions for slot occupancy. Integrating the abovementioned derivation, a parallel computing framework with the generalized slot length is established to lower the scheduling complexity. Within each computing unit, an incremental scheduling algorithm with the flow judgment conditions and PD-based search boundary is proposed. It reduces the scheduling complexity further while maintaining load balance for the mixed transmission of periodic and aperiodic flows. To achieve the optimality of runtime and load balance, two PD-based flow sorting strategies are designed, respectively. The evaluation results show that compared with the existing works, the runtime efficiency of scheduling at scale is increased by at least 1500 times in complex traffic scenarios while the load balance on the network links is also improved.