Electric drives, which are a main component in industrial applications, control electric motors and record vital information about their respective industrial processes. The development of electric drives as Fog nodes within a fog computing platform (FCP) leads to new abilities such as programmability, analytics, and connectivity, increasing their value. In this study, the FORA FCP reference architecture is used to implement electric drives as Fog nodes, which is called "fogification". The fogified drive architecture and its components are designed using Architecture Analysis and Design Language (AADL). The design process was driven by the high-level requirements that the authors elicited. Both the fogified drive architecture and the current drive architecture are used to implement a self baggage drop system in which electric drives are the key components. The fog-based design was then evaluated using several key performance indicators (KPIs), which reveal its advantages over the current drive architecture. The evaluation results show that safety-related isolation is enabled with only 9% overhead on the total Fog node utilization, control applications are virtualized with zero input-output jitter, the hardware cost is reduced by 44%, and machine learning at the edge is performed without interrupting the main drive functionalities and with an average 85% accuracy. The conclusion is that the fog-based design can successfully implement the required electric drive functionalities and can also enable innovative uses needed for realizing the vision of Industry 4.0.
Electric drives are used to control electric motors, which are pervasive in industrial applications. In this paper we propose enhancing the electric drives to fulfil the role of fog nodes within a Fog Computing Platform (FCP). Fog Computing is envisioned as a realization of future distributed architectures in Industry 4.0. We identify the system-level requirements of such an FCP, including requirements that are extracted from the current architecture of drives, which we consider as a baseline. These requirements are then used to design a system-level architecture, which we model using the Architecture Analysis & Design Language (AADL). We identify the “technology bricks” (components such as hardware, software, middleware, services, methods and tools) needed to implement the FCP. The proposed fog-based architecture is then used to implement a Conveyor Belt industrial use case. We evaluate the resulting use case on several aspects, demonstrating the usefulness of the proposed fogbased approach. By developing the electric drives as fog nodes, new offerings like programmability, analytics and connectivity to customer Clouds are expected to increase the added value. Increased flexibility allows drives to assume a larger role in industrial and domestic control systems, instrumenting thus also legacy systems by using drives as the data source.
Safety-critical systems in industrial automation, avionics, or automotive domains demand correct, timely and predictable performance under all(including faulty) operating conditions. Fault-tolerance plays an important role in ensuring seamless system function even in the presence of failures. Typically such systems run hard real-time applications, and hence timing violations can result in hazards.
Fog computing is an adaptive paradigm which distributes computation and communication along the cloud-IoT continuum to reduce communication latencies, making it more conducive to execute real-time applications. This requires enhancements to the network connecting various sub-systems to support timely delivery of safety-critical messages. Traditionally safety-critical systems are designed offline and are not re-configured during runtime. The inherent adaptive properties of fog computing systems make it susceptible to timeliness violations and can be a hindrance to safety guarantees. At the same time, adaptivity in terms of migrating computation and communication to different devices in the fog-cloud continuum can be used to make the system more fault-tolerant by suitable design approaches.
In this work we provide design approaches geared towards achieving safety and predictability of critical applications that run on adaptive fog computing platforms. To this end, we start by performing a survey of safety considerations in a fog computing system and identifying key safety challenges. We then propose a design approach to improve predictability in an autonomous mobile robot use-case in a factory setting designed using the fog computing paradigm. We narrow our attention on time-sensitive networking (TSN) and propose a temporal redundancy-based fault tolerance approach for time-sensitive messages. Furthermore, we study the 802.1CB TSN protocol and suggest improvements to reduce network congestion owing to replicated frames.
As a future work, we intend to also include the wireless aspects in the evaluation of timeliness guarantees for safety-critical applications. The emphasis will be on run-time failure scenarios and self-healing mechanisms based on online decisions taken in concert with offline guarantees.
Tight end-to-end worst-case delay bounds for periodic traffic streams are essential for time sensitive networks. In this paper, we provide an algorithm to compute a tight (and accurate) end-to-end worst-case bound by considering distinct topological patterns and the manner in which streams enter and leave switches. This refined analysis uses non-preemptive, strict-priority arbitration mechanism commonly deployed in Ethernet switches. Compared to the state-of-the-art that considers all higher and equal priority interference as contributing to the worst-case bound, we present an analytical approach for computing a tighter worst-case delay bound and prove through discrete event simulations that only a certain number of equal-priority interference streams can actually affect the worst-case case. Our results enable efficient resource allocation and have implications for online re-configuration mechanisms for time-sensitive factory communication systems.
Time Sensitive Networking (TSN) is a set of standards aimed at providing real-time guarantees over existing Ethernet standards. Worst-case traversal time (WCTT) analyses of network traffic are traditionally used in schedulability and routing analyses to determine feasible routes for traffic streams. However, worst-case conditions happen quite rarely from a probabilistic perspective. The typical or average-case traversal times are easier to compute and can be used as an effective design tool for routing and scheduling. In this paper, we present "MaLoC"or Maximally Loaded Common links for routing and scheduling of rate-constrained (RC) traffic in time-sensitive networks (TSN). The proposed framework employs a fully decentralized approach to route and schedule generation with only switch-local information. We further provide a preliminary evaluation of the proposed approach using a simple network topology.
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.
The Fog computing paradigm employing multiple technologies is expected to play a key role in a multitude of industrial applications by fulfilling futuristic requirements such as flexible and enhanced computing, storage, and networking capability closer to the field devices. While performance aspects of the Fog paradigm has been the central focus of researchers, safety aspects have not received enough attention so far. In this paper, we identify various safety challenges related to the Fog paradigm and provide specific safety design aspects as a step towards enhancing safety in industrial automation scenarios. We contextualize these ideas by invoking a distributed mobile robots use-case that can benefit from the use of the Fog paradigm.
Current industrial automation applications particularly within the smart manufacturing domain require mobility, flexibility of deployment, and scalability. In addition to these, it is important to mitigate the risk of safety hazards. In this paper we discuss a flexible, granular, and software-based system design that aims to improve both security and safety of an autonomous mobile robot (AMR) based industrial automation systems. The decentralised control architecture ensures that safety-critical functions are distributed throughout the network. To this end, we first define system-level safety requirements and identify procedures required to satisfy safety-critical functions such as emergency-stop (E-Stop). We then explain the benefits provided by the proposed system architecture vis-a-vis its resilience towards potential safety hazards.
Time sensitive networking (TSN) is gaining attention in industrial automation networks since it brings essential real-time capabilities at the data link layer. Though it can provide deterministic latency under error free conditions, TSN still largely depends on space redundancy for improved reliability. In many scenarios, time redundancy could be an adequate as well as cost efficient alternative. Time redundancy in turn will have implications due to the need for over-provisions needed for timeliness guarantees. In this paper, we discuss how to embed fault-tolerance capability into TSN schedules and describe our approach using a simple example.
Due to the fast growing of data consumed in mobile devices through cellular networks, solutions that provide higher data rates are an important target for the mobile networking community. One such solution is the aggregation of mobile technologies (most commonly LTE) with wireless LAN solutions (most commonly Wi-Fi). Seeing its potential impact, 3GPP has devised the LTE/Wi-Fi Aggregation (LWA) specification, which defines a tight coupling between eNBs and Wi-Fi Access Points (APs). In this paper, we implement and evaluate an LWA solution, and compare its performance to the one for full offloading (only Wi-Fi) and no offloading (only LTE) through physical experimentation. The developed prototype LWA solution is based on open source and commodity hardware, which promises a low-cost and easily implementable LWA solution. Aggregation and offloading process are managed by the eNB, therefore, the core network remains intact without any modification. Physical experiments are done to detail the network performances for all these three policies for TCP and UDP traffic and both for uplink and downlink connections. In TCP transmissions with LWA policy, the different delays between Wi-Fi and LTE links causes the performance degradation because of the out-of-order arrivals of the segments. For this, we evaluate a solution where an artificial delay is added to reduce the number of out-of-order packets.
In recent years, the Internet of Things (IoT) has gained a lot of attention due to connecting various sensor devices with the cloud, in order to enable smart applications such as: smart traffic management, smart houses, and smart grids, among others. Due to the growing popularity of the IoT, the number of Internet-connected devices has increased significantly. As a result, these devices generate a huge amount of network traffic which may lead to bottlenecks, and eventually increase the communication latency with the cloud. To cope with such issues, a new computing paradigm has emerged, namely: fog computing. Fog computing enables computing that spans from the cloud to the edge of the network in order to distribute the computations of the IoT data, and to reduce the communication latency. However, fog computing is still in its infancy, and there are still related open problems. In this paper, we focus on the node discovery problem, i.e., how to add new compute nodes to a fog computing system. Moreover, we discuss how addressing this problem can have a positive impact on various aspects of fog computing, such as fault tolerance, resource heterogeneity, proximity awareness, and scalability. Finally, based on the experimental results that we produce by simulating various distributed compute nodes, we show how addressing the node discovery problem can improve the fault tolerance of a fog computing system. © Vasileios Karagiannis, Nitin Desai, Stefan Schulte, and Sasikumar Punnekkat; licensed under Creative Commons License CC-BY 2nd Workshop on Fog Computing and the IoT (Fog-IoT 2020).
Low latency and on demand resource availability enable fog computing to host industrial applications in a cloud like manner. One industrial domain which stands to benefit from the advantages of fog computing is robotics. However, the challenges in developing and implementing a fog-based robotic system are manifold. To illustrate this, in this paper we discuss a system involving robots and robot cells at a factory level, and then highlight the main building blocks necessary for achieving such functionality in a fog-based system. Further, we elaborate on the challenges in implementing such an architecture, with emphasis on resource virtualization, memory interference management, real-time communication and the system scalability, dependability and safety. We then discuss the challenges from a system perspective where all these aspects are interrelated.