Deep Reinforcement Learning for Stochastic Computation Offloading in Digital Twin Networks

The dependability of the Industrial Internet of Things (IIoT) system can directly affect the production efficiency of the whole system. In this paper, we design a novel production-centric IIoT system with a digital twin network. The operation process of the IIoT system is proposed to calculate a suitable control command and to make an optimal production scheme and AGV dispatch of the whole factory. Moreover, resilience is used to introduce the system dependability of the IIoT network. The simulation results show that the proposed production-centric IIoT system with a digital twin network can achieve improved dependability for the IIoT system compared with the traditional scheme.

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].

Massive MIMO systems have received a great deal of attention as a means to improve both spectral efficiency (SE) and energy efficiency (EE) of wireless networks. While applying Massive MIMO to cellular networks has drawn significant attention, much less attention has been given to applying Massive MIMO to industrial Internet of things (IIoT) networks. The devices for IIoT networks have been continually growing, and to simultaneously support a large number of IIoT devices, orthogonal uplink reference signals (RSs) can be heavily reused, which severely compromises the quality of the channel estimation for all devices. This RS reuse Massive MIMO system can be successfully applied to IIoT networks to support a vast number of devices. In this paper, we provide the special characteristics of Massive MIMO applied to massive IIoT networks with respect to the operation, performance, and challenges. We present the technical overview of RS reuse Massive MIMO to realize low power, low latency, and low cost IIoT network, and then provide the performance using numerical results to verify the effectiveness of the system. Following this, we elaborate on the challenges associated with implementing these systems in reality, and offer insights into related issues that arise.

As a typical application of the Internet of Things (IoT), the Industrial IoT (IIoT) connects all the related IoT sensing and actuating devices ubiquitously so that the monitoring and control of numerous industrial systems can be realized. Deep learning, as one viable way to carry out big-data-driven modeling and analysis, could be integrated in IIoT systems to aid the automation and intelligence of IIoT systems. As deep learning requires large computation power, it is commonly deployed in cloud servers. Thus, the data collected by IoT devices must be transmitted to the cloud for training process, contributing to network congestion and affecting the IoT network performance as well as the supported applications. To address this issue, in this article, we leverage the fog/edge computing paradigm and propose an edge computing-based deep learning model, which utilizes edge computing to migrate the deep learning process from cloud servers to edge nodes, reducing data transmission demands in the IIoT network and mitigating network congestion. Since edge nodes have limited computation ability compared to servers, we design a mechanism to optimize the deep learning model so that its requirements for computational power can be reduced. To evaluate our proposed solution, we design a testbed implemented in the Google cloud and deploy the proposed convolutional neural network (CNN) model, utilizing a real-world IIoT data set to evaluate our approach. 1 Our experimental results confirm the effectiveness of our approach, which cannot only reduce the network traffic overhead for IIoT but also maintain the classification accuracy in comparison with several baseline schemes. 1 Certain commercial equipment, instruments, or materials are identified in this article in order to specify the experimental procedure adequately. Such identification is not intended to imply recommendation or endorsement by the National Institute of Standards and Technology, nor is it intended to imply that the materials or equipment identified are necessarily the best available for the purpose.

Blockchain-based technologies have been created across a range of businesses for improving data security and integrity. A network chain is the most remarkable blockchain applications as part of the Industrial Internet of Things (IIoT). Sensor data in real time aids industrial equipment and infrastructures in making decisions and taking specified actions. Without sufficient security, an IIoT system can cause operational disruption and financial loss and lead to malicious activities and system manipulation. Detecting anomalies in IIoT networks is critical for network security. In this paper we discuss the Proof of Authority consensus algorithm. The Proof of Authority (PoA) depends on the reputation of trusted parties in blockchain network. The PoA consensus mechanism is based on the values of identities on a network, and validators stake their own identities and reputation. So, the validating nodes that are randomly picked as trustworthy safeguard the Proof of Authority Blockchain network. In Proof of Authority model, transactions are reviewed by already approved network users, and it operates with a fixed number of block validators. Since the identities of the nodes are trusted and known, the process can be used in applications like supply chains and trade networks.

Blockchain and federated learning-based intrusion detection approaches for edge-enabled industrial IoT networks: a survey

This chapter aims to explore the managerial aspects of implementing artificial intelligence (AI) governance and digital twins (DTs) within the context of Industrial Internet of Things (IIoT). It focuses on establishing ethical and secure cybersecurity frameworks to enhance operational efficiency and protect critical infrastructure. The focus is on conducting systematic literature review. It begins with an overview of AI governance principles and the role of DTs in IIoT. The research then delves into the challenges and best practices for integrating these technologies, emphasising the importance of ethical considerations and robust cybersecurity measures. The study reveals that effective AI governance and the use of DTs can significantly improve the security and operational performance of IIoT systems. However, the integration of these technologies requires careful planning and adherence to ethical standards. For managers in the industrial sector, this chapter provides actionable insights into developing and implementing ethical and secure AI governance frameworks. It highlights the importance of fostering a culture of cybersecurity awareness and ethical responsibility, which are essential for safeguarding DTs and IIoT systems against cyber threats. This chapter contributes to the emerging discourse on AI governance and DTs by offering a managerial perspective on the ethical and secure deployment of these technologies in IIoT. It fills a gap in existing literature by providing a comprehensive analysis of the interplay between AI, DTs, and cybersecurity, and offering practical recommendations for industry leaders.

Through interconnecting machines, sensors, and devices, the Industrial Internet of Things (IIoT) has revolutionized industrial processes by allowing real-time data analysis and decision-making. The implementation of cloud, edge, and fog computing models has followed IIoT development, bringing unique security and privacy challenges in their wake. In this all-encompassing report, the potential risks, complications, and apprehensions of these models are analyzed with respect to IIoT integration. Examining cloud, edge, and fog computing models distinguishes and assesses their benefits when applied to IIoT. The paper analyzes the strengths offered by each model and addresses the risks associated with security and privacy, such as data infringement, malware, and denial-ofservice attacks. IIoT systems, in particular, pose significant challenges in providing protection. Cloud, edge, and fog computing models provide ample benefits but IIoT systems utilizing these models must have strong security and privacy policies in place. This paper highlights specific technical and organizational strategies to tackle potential challenges and risks. By effectively implementing these strategies, organizations can tap into the advantages of these models while ensuring the safety of their IIoT systems. Informed decisions can be made, and IIoT deployments can be safeguarded with the aid of the valuable resource given in this paper, which offers comprehensive analysis and recommendations. For those in the field of IIoT security, including practitioners and researchers, this paper is of great value.

The rapid expansion of Industrial Internet of Things (IIoT) systems has heightened concerns over data privacy, security, and trust in highly interconnected industrial environments. This paper proposes BLOX-Trust ((Blockchain-Optimized Zero-Trust), a novel blockchain-enhanced zero-trust framework that integrates decentralized identity management, smart contracts, and adaptive access control to ensure robust privacy and security in IIoT networks. By leveraging permissioned blockchain for immutable audit trails and incorporating zero-trust principles for continuous verification of devices and users, BLOX-Trust enables fine-grained, dynamic policy enforcement while mitigating risks such as unauthorized access, data tampering, and advanced cyberattacks. Edge computing is integrated to reduce latency and optimize real-time operations, while AI-driven anomaly detection supports proactive threat identification. Experimental evaluations in simulated IIoT environments demonstrate BLOX-Trust’s effectiveness, achieving secure, low-latency transactions with scalable performance. The results highlight its potential to enhance resilience, transparency, and operational efficiency in modern industrial ecosystems.

Industry 4.0 is the next revolution in manufacturing technology that is going to change the production and distribution of goods and services within the following decade. Powered by different enabling technologies that are also being developed simultaneously, it has the potential to create radical changes in our societies such as by giving rise to highly‐integrated smart cities. The Industrial Internet of Things (IIoT) is one of the main areas of development for Industry 4.0. These IIoT devices are used in mission‐critical sectors such as the manufacturing industry, power generation, and healthcare management. However, smart factories and cities can only function when threats to cyber security, data privacy, and information integrity are properly managed. In this regard, securing IIoT devices and their networks is vital to preserving data and privacy. The use of artificial intelligence is an enabler for more secure IIoT systems. In this study, we propose high‐performing deep learning models for the classification of botnet attacks that commonly affect IIoT devices and networks. Evaluation of results shows that deep learning models such as the artificial neural network (ANN), the long short‐term memory (LSTM), and the gated recurrent unit (GRU) can successfully be used for classifications of IIoT malware attacks with an accuracy of up to 99%.

Industrial Internet of Things (IIoT) finds use in several industrial applications like robots, medical devices, and software-defined manufacturing processes. Apart from the promising benefits of the IIoT networks, several challenging issues need to be resolved, such as network connectivity, security, privacy, heterogeneity, scheduling, and energy efficiency. Due to the large-scale deployment and heterogeneity of the nodes in IIoT networks, some energy-limited nodes have existed in the IIoT networks, resulting in reduced network lifetime. At the same time, security and privacy are also considered as the major issues that exist in the design of IIoT, which can be addressed using secure routing techniques. In this view, this study develops a trust-aware multiobjective metaheuristic optimization-based secure clustering with route planning (TAMOMO-SCRP) technique for cluster-based IIoT environment. The presented TAMOMO-SCRP technique mainly focuses on the design of bald eagle search (BES) algorithm for clustering and routing processes. The proposed TAMOMO-SCRP model derives a fitness function for accomplishing maximum energy efficiency and security. For an effective clustering process, the TAMOMO-SCRP model designs an objective function involving four parameters such as trust level (TL), communication cost (CC), residual energy (RE), and node degree (ND). Besides, the route selection process is based on the fitness function with two variables, namely, queue length and link quality. For assessing the enhanced performance of the TAMOMO-SCRP model, a wide range of experiments were carried out to get the outcomes of network life time(NLT) as 39451,half network die (HND) as 25950 and Stability period (SP) 8000 time calculated no. of alive nodes. The achieved outcomes make sure the better performance of the TAMOMO-SCRP technique against the other recent approaches.

Knowledge inference using knowledge graphs is one of the recent research trends for fault diagnosis. As complex Industrial Internet of Things (IIoT) systems evolve to incorporate distributed subsystems, each subsystem may have local measurements interpreted by a local Knowledge Base (KB). In this work, we propose a distributed fault diagnosis framework with distributed path-based reasoning. In contrast to centralized reasoning that requires merging of the distributed KBs, the proposed framework employs a centralized coordinator to transfer the model among decentralized agents and allows an agent to handover training paths for others to continue training by filling in missing links using their local KBs. Our work is the very first distributed knowledge inference framework to reason among distributed fault diagnosis systems to tackle the KB isolation, scalability and flexibility issues of centralized fault diagnosis systems. To validate our framework with IIoT datasets, we build a fault knowledge graph from the Tennessee Eastman (TE) process simulations. Evaluations show that our framework outperforms the non-cooperative distributed reasoning method in terms of prediction accuracy. With the TE process dataset, the mean reciprocal rank is improved from 0.1612 to 0.19 with transferred models, and further to 0.206 with hand-over queries between agents.

Industrial Internet of Things (IIoT) systems play a pivotal role in enabling real-time monitoring and analysis of equipment to prevent breakdowns and optimize performance. Predictive maintenance stands as a critical component of IIoT systems, allowing industries to anticipate equipment failures, minimize downtime, and enhance overall equipment effectiveness. This paper investigates the potential of Long Range (LoRa) technology in predictive maintenance applications within IIoT systems. Specifically, the study delves into the utilization of LoRa technology to bolster predictive maintenance capabilities, with a focus on a live prediction analysis demonstration conducted on an industrial robotic arm. The research presents a detailed test bed setup for conducting predictive maintenance, which involves capturing data from the robot, transmitting it to a LoRaWAN gateway, enabling prediction of normal or abnormal behavior in the robotic arm. This study provides insights into the efficacy of LoRa technology in enhancing predictive maintenance capabilities within IIoT systems.

Global CO2 emissions reduction requires industries to manage and understand their CO2 emission levels in real-time. This paper examines the Industrial Internet of Things (IIoT) for real-time monitoring, measurement, and visualization of reducing CO2 emissions in industrial and environmental domains. Methodology: The methodology consists of a literature review based on peer-reviewed publications and use cases to explore the current state and practical implications. Furthermore, a technical analysis of IIoT systems, CO2 sensors, and data processing techniques is also identified. Results: IIoT systems can support CO2 emission monitoring and accuracy optimization in industrial domains by combining CO2 sensors, wireless communication, and data fusion techniques. In addition, machine learning and artificial intelligence can be used to reduce anomalies in CO2 sensor readings and predictive maintenance of systems. Challenges: Challenges include interoperability, data security and system scalability. To resolve these issues standardized communication protocols, data security methods and implementation barriers should be improved. Future Directions: To enhance data processing and security features, future work should focus on integrating edge computing, artificial intelligence, machine learning, and blockchain techniques. In addition, data visualizations and cost-effective solutions should also be in focus, to provide more adoptable IIoT systems in industrial domains. Conclusion: As IIoT systems and CO2 sensor technologies evolve, IIoT systems can contribute significantly to increasing global air quality and CO2 emission control in industry, agricultural, and urban areas.

Industrial Internet of Things (IIoT) is a fusion of industrial automation systems and IoT systems. It features comprehensive sensing, interconnected transmission, intelligent processing, self-organization and self-maintenance. Its applications span intelligent transportation, smart factories, and intelligence. Many areas such as power grid and intelligent environment detection. With the widespread application of IIoT technology, the cyber security threats to industrial IoT systems are increasing day by day, and information security issues have become a major challenge in the development process. In order to protect the industrial IoT system from network attacks, this paper aims to study the industrial IoT information security protection technology, and the typical architecture of industrial Internet of things system, and analyzes the network security threats faced by industrial Internet of things system according to the different levels of the architecture, and designs the security protection strategies applied to different levels of structures based on the specific means of network attack.