The Industrial Internet of Things (IIoT) plays an important role in digital transformation of traditional industries toward Industry 4.0. By connecting sensors, instruments, and other industry devices to the Internet, IIoT facilitates the data collection, data analysis, and automated control, thereby improving the productivity and efficiency of the business as well as the resulting economic benefits. Due to the complex IIoT infrastructure, anomaly detection becomes an important tool to ensure the success of IIoT. Due to the nature of IIoT, graph-level anomaly detection has been a promising means to detect and predict anomalies in many different domains, such as transportation, energy, and factory, as well as for dynamically evolving networks. This article provides a useful investigation on graph neural networks (GNNs) for anomaly detection in IIoT-enabled smart transportation, smart energy, and smart factory. In addition to the GNN-empowered anomaly detection solutions on point, contextual, and collective types of anomalies, useful data sets, challenges, and open issues for each type of anomalies in the three identified industry sectors (i.e., smart transportation, smart energy, and smart factory) are also provided and discussed, which will be useful for future research in this area. To demonstrate the use of GNN in concrete scenarios, we show three case studies in smart transportation, smart energy, and smart factory, respectively.

Network slicing has been widely agreed as a promising technique to accommodate diverse services for the Industrial Internet of Things (IIoT). Smart transportation, smart energy, and smart factory/manufacturing are the three key services to form the backbone of IIoT. Network slicing management is of paramount importance in the face of IIoT services with diversified requirements. It is important to have a comprehensive survey on intelligent network slicing management to provide guidance for future research in this field. In this paper, we provide a thorough investigation and analysis of network slicing management in its general use cases as well as specific IIoT services including smart transportation, smart energy and smart factory, and highlight the advantages and drawbacks across many existing works/surveys and this current survey in terms of a set of important criteria. In addition, we present an architecture for intelligent network slicing management for IIoT focusing on the above three IIoT services. For each service, we provide a detailed analysis of the application requirements and network slicing architecture, as well as the associated enabling technologies. Further, we present a deep understanding of network slicing orchestration and management for each service, in terms of orchestration architecture, AI-assisted management and operation, edge computing empowered network slicing, reliability, and security. For the presented architecture for intelligent network slicing management and its application in each IIoT service, we identify the corresponding key challenges and open issues that can guide future research. To facilitate the understanding of the implementation, we provide a case study of the intelligent network slicing management for integrated smart transportation, smart energy, and smart factory. Some lessons learnt include: 1) For smart transportation, it is necessary to explicitly identify service function chains (SFCs) for specific applications along with the orchestration of underlying VNFs/PNFs for supporting such SFCs; 2) For smart energy, it is crucial to guarantee both ultra-low latency and extremely high reliability; 3) For smart factory, resource management across heterogeneous network domains is of paramount importance. We hope that this survey is useful for both researchers and engineers on the innovation and deployment of intelligent network slicing management for IIoT.

Critical infrastructure systems are vital to underpin the functioning of a society and economy. Due to ever-increasing number of Internet-connected Internet-of-Things (IoTs) / Industrial IoT (IIoT), and high volume of data generated and collected, security and scalability are becoming burning concerns for critical infrastructures in industry 4.0. The blockchain technology is essentially a distributed and secure ledger that records all the transactions into a hierarchically expanding chain of blocks. Edge computing brings the cloud capabilities closer to the computation tasks. The convergence of blockchain and edge computing paradigms can overcome the existing security and scalability issues. In this paper, we first introduce the IoT/IIoT critical infrastructure in industry 4.0, and then we briefly present the blockchain and edge computing paradigms. After that, we show how the convergence of these two paradigms can enable secure and scalable critical infrastructures. Then, we provide a survey on state-of-the-art for security and privacy, and scalability of IoT/IIoT critical infrastructures. A list of potential research challenges and open issues in this area is also provided, which can be used as useful resources to guide future research.

Virtual network embedding arranges virtual network services onto substrate network components. The performance of embedding algorithms determines the effectiveness and efficiency of a virtualized network, making it a critical part of the network virtualization technology. To achieve better performance, the algorithm needs to automatically detect the network status which is complicated and changes in a time-varying manner, and to dynamically provide solutions that can best fit the current network status. However, most existing algorithms fail to provide automatic embedding solutions in an acceptable running time. In this paper, we combine deep reinforcement learning with a novel neural network structure based on graph convolutional networks, and propose a new and efficient algorithm for automatic virtual network embedding. In addition, a parallel reinforcement learning framework is used in training along with a newly-designed multi-objective reward function, which has proven beneficial to the proposed algorithm for automatic embedding of virtual networks. Extensive simulation results under different scenarios show that our algorithm achieves best performance on most metrics compared with the existing stateof- the-art solutions, with upto 39.6% and 70.6% improvement on acceptance ratio and average revenue, respectively. Moreover, the results also demonstrate that the proposed solution possesses good robustness.

The Internet-of-Things (IoT) has been deeply penetrated into a wide range of important and critical sectors, including smart city, water, transportation, manufacturing and smart factory. Massive data are being acquired from a fast growing number of IoT devices. Efficient data processing is a necessity to meet diversified and stringent requirements of many emerging IoT applications. Due to the constrained computation and storage resources, IoT devices have resorted to the powerful cloud computing to process their data. However, centralised and remote cloud computing may introduce unacceptable communication delay since its physical location is far away from IoT devices. Edge cloud has been introduced to overcome this issue by moving the cloud in closer proximity to IoT devices. The orchestration and cooperation between the cloud and the edge provides a crucial computing architecture for IoT applications. Artificial intelligence (AI) is a powerful tool to enable the intelligent orchestration in this architecture. This paper first introduces such a kind of computing architecture from the perspective of IoT applications. It then investigates the state-of-the-art proposals on AI-powered cloud-edge orchestration for the IoT. Finally, a list of potential research challenges and open issues is provided and discussed, which can provide useful resources for carrying out future research in this area.

Network slicing has emerged as a promising networking paradigm to provide resources tailored for Industry 4.0 and diverse services in 5G networks. However, the increased network complexity poses a huge challenge in network management due to virtualized infrastructure and stringent quality-of-service requirements. Digital twin (DT) technology paves a way for achieving cost-efficient and performance-optimal management, through creating a virtual representation of slicing-enabled networks digitally to simulate its behaviors and predict the time-varying performance. In this article, a scalable DT of network slicing is developed, aiming to capture the intertwined relationships among slices and monitor the end-to-end (E2E) metrics of slices under diverse network environments. The proposed DT exploits the novel graph neural network model that can learn insights directly from slicing-enabled networks represented by non-Euclidean graph structures. Experimental results show that the DT can accurately mirror the network behaviour and predict E2E latency under various topologies and unseen environments.