Industrial Internet Of Things Systems Research Articles

Joint Device Selection and Bandwidth Allocation for Cost-Efficient Federated Learning in Industrial Internet of Things

Along with the deployment of Industrial Internet of Things (IIoT), massive amounts of industrial data have been generated at the network edge, driving the evolution of edge machine learning (ML). But during the ML model training, it may bring privacy leakage by traditional central methods. To address this issue, federated learning (FL) has been proposed as a distributed learning framework for training a global model without uploading raw data to protect data privacy. Since the communication and computing resources are usually limited in IIoT networks, how to reasonably select device and allocate bandwidth is crucial for the FL model training. Therefore, this paper proposes a joint edge device selection and bandwidth allocation scheme for FL to minimize the time-averaged cost under the given long-term energy budget and delay constraints in IIoT system. To tackle with this long-term optimization problem, we construct a virtual energy deficit queue and leverage the Lyapunov optimization theory to transform it into a list of round-wise drift-plus-cost minimization problems firstly. Then, we design an iterative algorithm to allocate reasonable bandwidth and select appropriate devices to achieve cost minimization while satisfying the energy consumption constraints. Besides, we develop an optimality analysis of the average cost and energy violation for our proposed scheme. Extensive experiments verify that our proposed scheme can achieve superior performance in cost efficiency over other schemes while guaranteeing FL training performance.

Robust Monitor for Industrial IoT Condition Prediction

The robustness of Machine learning (ML) models has gained much attention along with their wide application on various safety required Industrial Internet of Things (IIoT) paradigms. Researchers found that some specific attacks added on sensor measurements can maliciously disturb IIoT monitors that are designed using ML architectures. Traditional detection methods could judge whether the measurements are attacked to prevent the failure of monitors. Unfortunately, recent works argue that commonly used detection methods could be circumvented through adaptive attacks that could acquire the mechanism of detectors; they could not truly enhance the robustness of ML models. Instead, general robust mechanisms should be performed to authentically enhance the robustness of models against any potential attacks with specific restrictions. On the basis of the above argument, we design a robust condition monitor for predicting the fault condition of IIoT systems using the adversarial training technique called robust temporal convolutional network (RTCN). The model is designed to be formally robust to attacks with restricted magnitude. The temporal convolutional network (TCN) is employed to design the base structure of the monitor. TCN can capture temporal information from sensors to enhance the feature extraction performance of models. We also present a novel False data injection (FDI) attack generating method that utilizes the conception of adversarial perturbations to disturb well-trained monitors. Experimental results verify the efficiency of feature extraction performance of our model from IIoT systems. Furthermore, adversarial training mechanism through a min-max manner could effectively improve the reliability of ML-based IIoT monitors against strong FDI attacks.

Enabling blockchain-assisted certificateless public integrity checking for industrial cloud storage systems

Due to the sharp increase in industrial data, cloud computing has been integrated into intelligent Industrial Internet of Things systems to store and process massive data. Since core data are key factors in the industrial production process, any intercepted or altered data may cause severe consequences, and the integrity and confidentiality of outsourced industrial data have become extremely concerning security issues. In this paper, we focus on devising an enhanced blockchain-assisted certificateless public integrity checking (BA-CPIC) mechanism for industrial cloud storage systems. BA-CPIC contributes to checking outsourced industrial encrypted data, and exploits the smart contract in the Ethereum blockchain to provide assistance to users for checking malicious behaviors of auditors (e.g., colluding with industrial cloud servers or lazing checking). Besides, BA-CPIC preserves the identity privacy of users enjoying outsourced storage and blockchain-assisted integrity checking services. By contrast, some misbehaved users in industrial cloud storage systems could also be traced and revoked in due course. BA-CPIC avoids both inherent drawbacks of key escrow and complex certificate management, it is provided corresponding security analysis under the certificateless security model. The performance evaluation demonstrates the feasibility of BA-CPIC in the deployment of industrial cloud storage systems.

Intelligent and Low Overhead Network Synchronization for Large-Scale Industrial IoT Systems in the 6G Era

Holistic temporal coherence among distributed industrial infrastructures enabled by accurate network synchronization is essential for achieving tight orchestration of large-scale industrial Internet of Things (IIoT) systems. However, the low efficiency and situation agnosticism of conventional synchronization techniques using an inflexible "observing-andcalibrating" approach for clock offset correction are inevitably hindering the performance of many IIoT applications with increasing scale and heterogeneity. In this article, we provide an in-depth analysis of the challenges associated with conventional synchronization schemes over large-scale IIoT systems and then present three promising research directions for achieving intelligent and low overhead IIoT synchronization. Particularly, we first propose a new modelbased network synchronization scheme that can proactively enable low overhead clock calibration by leveraging the inherent characteristics of heterogeneous clocks to avoid frequent timestamp exchange. We then design an intelligent device clustering mechanism with a specifically designed synchronization strategy for each group of IIoT devices by jointly exploiting their distinctive synchronization requirements and multi-dimensional device attributes. To leverage the unique characteristics of each oscillator, we analyze historical timestamps to reject unreliable timestamps and identify unreliable devices. Finally, we envision an edge-cloud collaborative network synchronization paradigm to implement the proposed schemes and demonstrate their efficacy in large-scale IIoT systems.

Deep AI-Powered Cyber Threat Analysis in IIoT

Distributed Industrial Internet of Things (IIoT) has entirely revolutionized the industrial sector that varies from autonomous industrial processes to automation of processes without human intervention. However, threat hunting and intelligence is the most complex task in distributed IIoT. Besides, there exist no standard architectures for hunting micro services orchestration in distributed IIoT systems. The authors propose an efficient and self-learning autonomous multi-vector threat intelligence and detection mechanism to proactively defend IIoT systems/networks. Our proposed novel Cuda-empowered Convolutional LSTM2D (ConvLSTM2D) mechanism is highly scalable with self-optimizing capabilities to proficiently tackle diverse dynamic variants of emerging IIoT sophisticated threats and attacks. For a comprehensive evaluation, the authors employed a current state-of-the-art dataset with 21 million instances comprised of varying attack patterns and prevalent threat vectors. Moreover, the proposed technique is compared with our constructed contemporary Deep Learning (DL)-driven architectures and benchmark algorithms. The proposed mechanism outperforms in terms of detection accuracy with a trivial trade-off in speed efficiency.

Data Acquisition for Estimating Energy-Efficient Solar-Powered Sensor Node Performance for Usage in Industrial IoT

In the era of rapid technological growth, we are facing increased energy consumption. The question of using renewable energy sources is also essential for the sustainability of wireless sensor networks and the Industrial Internet of Things, especially in scenarios where there is a need to deploy an extensive number of sensor nodes and smart devices in industrial environments. Because of that, this paper targets the problem of monitoring the operations of solar-powered wireless sensor nodes applicable for a variety of Industrial IoT environments, considering their required locations in outdoor scenarios and the efficient solar power harvesting effects. This paper proposes a distributed wireless sensor network system architecture based on open-source hardware and open-source software technologies to achieve that. The proposed architecture is designed for acquiring solar radiation data and other ambient parameters (solar panel and ambient temperature, light intensity, etc.). These data are collected primarily to define estimation techniques using nonlinear regression for predicting solar panel voltage outputs that can be used to achieve energy-efficient operations of solar-powered sensor nodes in outdoor Industrial IoT systems. Additionally, data can be used to analyze and monitor the influence of multiple ambient data on the efficiency of solar panels and, thus, powering sensor nodes. The architecture proposal considers the variety of required data and the transmission and storage of harvested data for further processing. The proposed architecture is implemented in the small-scale variants for evaluation and testing. The platform is further evaluated with the prototype sensor node for collecting solar panel voltage generation data with open-source hardware and low-cost components for designing such data acquisition nodes. The sensor node is evaluated in different scenarios with solar and artificial light conditions for the feasibility of the proposed architecture and justification of its usage. As a result of this research, the platform and the method for implementing estimation techniques for sensor nodes in various sensor and IoT networks, which helps to achieve edge intelligence, is established.

A blockchain-based security and trust mechanism for AI-enabled IIoT systems

The complexity and heterogeneity of artificial intelligence (AI) enabled industrial Internet of things (IIoT) lead to lacks of mutual trust between devices and directly affects the data security for the network. Therefore, it is necessary to provide trust mechanisms in AI-enabled IIoT. However, the existing trust mechanisms are not suitable in distributed networks. Thus, this paper presents a blockchain-based cloud-edge-end framework and designs a trust mechanism based on blockchain consensus. It utilizes the BLS-based proof of replication (PoRep) as consensus mechanisms and realizes device mutual trust. The device data is stored in servers to generate proofs and reach consensuses after broadcasting to other nodes. This ensures the data security of networks and provides mutual trust mechanisms between various devices. Moreover, the secret sharing based verifiable delay functions (VDF) is utilized to prevent the servers from calculating data replicas dynamically in PoRep and improve the efficiency of reaching consensus among nodes.

Threat modeling in smart firefighting systems: Aligning MITRE ATT&CK matrix and NIST security controls

Industrial automation technologies are envisioned as multi-device systems that are constantly interacting with one another and with enterprise systems. In these industrial systems, the industrial internet of things (IIoT) significantly improves system efficiency, scalability, ease of control, and monitoring. These benefits have been achieved at the cost of greater security risks, thus making the system vulnerable to cyberattacks. Historically, industrial networks and systems lacked security features like authentication and encryption due to intended isolation over the Internet. Lately, remote access to these IIoT systems has made an attempt of holistic security alarmingly critical. In this research paper, a threat modeling framework for smart cyber–physical system (CPS) is proposed to get insight of the potential security risks. To carry out this research, the smart firefighting use case based on the MITRE ATT&CK matrix was investigated. The matrix analysis provided structure for attacks detection and mitigation, while system requirement collection (SRC) was applied to gather generic assets’ information related to hardware, software and network. With the help of SRC and MITRE ATT&CK, a threat list for the smart firefighting system was generated. Conclusively, the generated threat list was mapped on the national institute of standards and technology (NIST) security and privacy controls. The results show that these mapped controls can be well-utilized for protection and mitigation of threats in smart firefighting system. In future, critical cyber–physical systems can be modeled upon use case specific threats and can be secured by utilizing the presented framework.

Synchronization Under Hardware Impairments in Over-6-GHz Wireless Industrial IoT Systems

Mobile devices perform cell search for initial access in cellular-based industrial Internet of Things (IoT) systems. Existing fifth-generation (5G) New Radio (NR) cell-search scheme provides timing synchronization and cell identification. Usage scenarios emerging with the growth of the IoT market require unprecedented precision, reliability, and scalability in the future network, and a shift toward high frequency bands can be one of the key enablers to achieve these stringent requirements. However, in high frequency bands, hardware impairments including carrier frequency offset and phase noise are exacerbated, and a sharp beam causes the problem of cell identity (ID) ambiguity that can reach further than a reduced cell coverage. In this paper, a cell-search scheme is proposed for time-critical industrial IoT over mobile networks operating in high frequency bands. To achieve high timing accuracy under the increased hardware impairments, primary synchronization signals are designed based on the distributed concatenations of a Zadoff-Chu sequence and its modification. Next, a secondary synchronization signal is designed based on the distributed concatenation of a Kasami sequence and its modification, which provides larger set of cell IDs and is robust to the impairments. Compared to 5G NR under the increased hardware impairments, our analysis and evaluation show that the proposed cell-search scheme has advantages such as 25 % lower timing detection complexity, 150 % larger set of cell IDs, up to 15 dB and 6 dB signal-to-noise ratio gain in terms of timing and cell ID detection performance, respectively, and 60 % shorter cell-search time, thereby realizing 80 % lower battery consumption.

Cyber security and beyond: Detecting malware and concept drift in AI-based sensor data streams using statistical techniques

In the Industrial Internet of Things (IIoT), mobile devices can be used to remotely monitor and control industrial processes, equipment, and machinery. They can also be used to optimize production and maintenance processes, improve safety, and increase efficiency in industries such as manufacturing, energy, and transportation. The adoption of IIoT has the potential to increase production and efficiency, but it also raises new cybersecurity concerns since interconnected industrial systems are more susceptible to malware intrusions. Malware attacks on IIoT systems can have grave consequences, including production delays, data loss, and physical asset damage. To aid this we propose to use statistical drift detection methods to perceive any change in data patterns and train the machine learning classifiers to counter newly developed malware samples then and there. Our results with an accuracy of 95.2% and F1-score of 94% indicate that our approach is highly successful and easy to adopt.

Virtual Commissioning of Distributed Systems in the Industrial Internet of Things

With the convergence of information technology (IT) and operational technology (OT) in Industry 4.0, edge computing is increasingly relevant in the context of the Industrial Internet of Things (IIoT). While the use of simulation is already the state of the art in almost every engineering discipline, e.g., dynamic systems, plant engineering, and logistics, it is less common for edge computing. This work discusses different use cases concerning edge computing in IIoT that can profit from the use of OT simulation methods. In addition to enabling machine learning, the focus of this work is on the virtual commissioning of data stream processing systems. To evaluate the proposed approach, an exemplary application of the middleware layer, i.e., a multi-agent reinforcement learning system for intelligent edge resource allocation, is combined with a physical simulation model of an industrial plant. It confirms the feasibility of the proposed use of simulation for virtual commissioning of an industrial edge computing system using Hardware-in-the-Loop. In summary, edge computing in IIoT is highlighted as a new application area for existing simulation methods from the OT perspective. The benefits in IIoT are exemplified by various use cases for the logic or middleware layer using physical simulation of the target environment. The relevance for real-life IIoT systems is confirmed by an experimental evaluation, and limitations are pointed out.

An artificial intelligence lightweight blockchain security model for security and privacy in IIoT systems

The Industrial Internet of Things (IIoT) promises to deliver innovative business models across multiple domains by providing ubiquitous connectivity, intelligent data, predictive analytics, and decision-making systems for improved market performance. However, traditional IIoT architectures are highly susceptible to many security vulnerabilities and network intrusions, which bring challenges such as lack of privacy, integrity, trust, and centralization. This research aims to implement an Artificial Intelligence-based Lightweight Blockchain Security Model (AILBSM) to ensure privacy and security of IIoT systems. This novel model is meant to address issues that can occur with security and privacy when dealing with Cloud-based IIoT systems that handle data in the Cloud or on the Edge of Networks (on-device). The novel contribution of this paper is that it combines the advantages of both lightweight blockchain and Convivial Optimized Sprinter Neural Network (COSNN) based AI mechanisms with simplified and improved security operations. Here, the significant impact of attacks is reduced by transforming features into encoded data using an Authentic Intrinsic Analysis (AIA) model. Extensive experiments are conducted to validate this system using various attack datasets. In addition, the results of privacy protection and AI mechanisms are evaluated separately and compared using various indicators. By using the proposed AILBSM framework, the execution time is minimized to 0.6 seconds, the overall classification accuracy is improved to 99.8%, and detection performance is increased to 99.7%. Due to the inclusion of auto-encoder based transformation and blockchain authentication, the anomaly detection performance of the proposed model is highly improved, when compared to other techniques.

Blockchain-Based Resource Trading in Multi-UAV-Assisted Industrial IoT Networks: A Multi-Agent DRL Approach

With the Industrial Internet of Things (IIoT), mobile devices (MDs) and their demands for low-latency data communication are increasing. Due to the limited resources of MDs, such as energy, computation, storage, and bandwidth, IIoT systems cannot meet MDs’ quality of service (QoS) and security requirements. Recently, UAVs have been deployed as aerial base stations in the IIoT network to provide connectivity and share resources with MDs. We consider a resource trading environment where multiple resource providers compete to sell their resources to MDs and maximize their profit by continually adjusting their pricing strategies. Multiple MDs, on the other hand, interact with the environment to make purchasing decisions based on the prices set by resource providers to reduce costs and improve QoS. We propose a novel intelligent resource trading framework that integrates multi-agent deep reinforcement Learning (MADRL), blockchain, and game theory to manage dynamic resource trading environments. A consortium blockchain with a smart contract is deployed to ensure the security and privacy of the resource transactions. We formulated the optimization problem using a Stackelberg game. However, the formulated optimization problem in the multi-agent IIoT environment is complex and dynamic, making it difficult to solve directly. Thus, we transform it into a stochastic game to solve the dynamics of the optimization problem. We propose a dynamic pricing algorithm that combines the Stackelberg game with the MADRL algorithm to solve the formulated stochastic game. The simulation results show that our proposed scheme outperforms others to improve resource trading in UAV-assisted IIoT networks.

A Delay-Sensitive Multibase-Station Multichannel Access System for Smart Factory

The intelligence of industrial production depends on real-time and reliable transmission and timely feedback of information in the Industrial Internet of Things (IIoT) systems. However, the scarcity of spectrum resources, a harsh industrial electromagnetic environment, and a need for real-time processing of massive traffic have posed severe challenges to the real-time and reliable access of the MAC layer. Aiming to solve the real-time transmission problem in the IIoT system, a delay-sensitive multibase-station multichannel access scheme is proposed. First, a multibase-station multichannel access model for real-time transmission is developed. The way to match sensing nodes with base stations and channels is formulated as a delay-sensitive multibase-station multichannel access (DMMA) problem. Moreover, it is theoretically proved that the DMMA problem is NP-Hard. Finally, a delay-sensitive greedy schedule (DG-Schedule) scheme based on the minimum deadline priority is proposed to obtain a feasible solution to the DMMA problem. According to experiments on the TI CC2530, DG-Schedule can reduce packet loss by 11% and average latency by 88% compared to CSMA/CA. Therefore, the DG-Schedule scheme is more suitable for IIoT scenarios.

Privacy-Preserving Authentication Scheme With Revocability for Multi-WSN in Industrial IoT

Wireless sensor network (WSN), as one of the core technology in the Industrial Internet of Things (IIoT) system, plays a critical role in collecting data for the monitoring areas. Security and privacy are essential to ensure the trustworthy completeness of data access and transmission for the WSN-based IIoT system. Recently, a series of excellent privacy-preserving authentication schemes for the WSN-based IIoT system have been proposed. There is, however, strong demand for further improvements in multiple registrations, user revocation, and forward secrecy. Targeted by these security issues, we propose an efficient privacy-preserving authentication scheme with revocability for multi-WSNs in the IIoT environment. In the proposed scheme, the user can access multiple different WSNs with the same identity and password through a single registration. Our scheme is provable secure under the random oracle model, and security analysis via practical circumstances shows that it is able to provide a variety of security requirements, such as user revocation, forward secrecy, etc. In addition, the comparison with related schemes indicates that the proposed one has fewer sensor nodes-based computations and overall communication overheads. It is, therefore, more suitable for the resource-constrained IIoT environment than existing approaches.

FGC: GCN-Based Federated Learning Approach for Trust Industrial Service Recommendation

With the development of the Industrial Internet of Things system, the huge amount of devices, services, and continuous data, making it difficult to discover a trusted service in complex scenarios. To better leverage knowledge and historical behavior, recommendation systems are applied. However, the model accuracy closely depends on training data size; there is a great risk of data leaking by collecting from multiple departments. To solve these problems, we propose a graph-convolutional-neural-network-based federated approach, which accurately recommends proper service for participating clients without gathering the raw data. Specifically, each client trains locally and uploads the weights of their model to the server for aggregation. Besides, the potential overlapping services of different clients are leveraged to guide the embedding aggregation and sharing, which, in turn, optimize the local training results. Their sensitive scenarios' embedding is kept locally. Owing to the model aggregation, it also resists the poisoning attack to some degree. In addition, the comprehensive experiments on classic public recommendation datasets evaluate the feasibility, effectiveness, trustworthiness, and potential influences.

Securing Industrial Internet of Things (Industrial IoT)- A Reviewof Challenges and Solutions

Industrial IoT (Industrial IoT) is a new promising technology which can be used to increase the amount of productions with high qualities. Industrial IoT technologies guarantee full control to the processes remotely through the internet which can reduce the number of workers in the field. As a result, this can reduce the percentage of worker injuries and accidents in addition to the total costs. The Industrial IoT systems are attractive targets to attackers. For this reason, these systems require high levels of security since such levels have direct effects on physical devices which may be dangerous on human life and safety. To guarantee high level of security, a combination between Information Technologies (IT) and Operation Technologies (OT) with new innovative methods should take place. In this paper, many new technologies and security methods are reviewed with their possible attacks in order to provide Industrial IoT infrastructure designers with the required information to take them into consideration. Also, differences and convergences between both classical Information Technology (IT) and operational Technology (OT) and their relations to the Industrial IoT systems are investigated with the possible attacks on each layer of the IT and the OT.

Synchronization of Shop-Floor Logistics and Manufacturing Under IIoT and Digital Twin-Enabled Graduation Intelligent Manufacturing System.

Logistics interfaces with manufacturing throughout the entire production process need synchronous operations. For achieving integrated organization and operations between manufacturing and logistics, this article introduces the concept of shop-floor logistics and manufacturing synchronization with four principles, including: 1) synchronization-oriented manufacturing system; 2) synchronized information sharing; 3) synchronized decision making; and 4) synchronized operations. The marriage of the principles rendered the development of an overall framework of the Industrial Internet of Things (IIoT) and digital twin-enabled graduation intelligent manufacturing system (GiMS). A mixed-integer programming-based synchronization mechanism is proposed under GiMS. To meet the requirement of fast decision making in real-life shop-floor logistics and manufacturing synchronization problems, an equivalent constraint programming model is developed and tested. The observation and analysis of the case company show the advantage of the proposed concept and approach with the best performance regarding key performance indicators. The concept of synchronization provides an insight for understanding the interaction of logistics and manufacturing at the operational level. This article potentially enables manufacturers to reevaluate and develop their manufacturing planning and control strategies in the IIoT and digital twin-based manufacturing environment.

Efficient Batch Authentication Scheme Based on Edge Computing in IIoT

In the industrial Internet of Things (IIoT) environment (e.g., a smart factory), smart devices with limited computing power can bring large amounts of privacy-sensitive data into insecure networks when they interact. If a network attacker intercepts and tampers with this data, it may cause chaos in production and even paralyze the entire IIoT system. Therefore, to ensure the regular operation of intelligent production, data receivers must authenticate the data before using them. However, existing message authentication schemes in the IIoT environment authenticate each message individually, which creates many redundant operations. Hence, to ensure data security among smart devices and reduce the computational overhead of data processing, we propose a batch authentication scheme based on edge computing in IIoT. Specifically, we design a lightweight batch authentication algorithm and use edge servers to assist smart devices in authenticating data, thus reducing the computational burden on smart devices and improving the efficiency of message authentication. The security analysis shows that the proposed scheme is secure in the random oracle model and meets the series of security requirements of the IIoT. In addition, we illustrate the efficiency of the scheme through experiments.

Capacity Analysis of Power Beacon-Assisted Industrial IoT System with UAV Data Collector

The performance analysis of an energy constrained Internet of Things (IoT) system with unmanned aerial vehicle (UAV) is provided in this paper. In the considered system, a power beacon is used for the energy supply of a sensor node that has no other power sources, while the UAV is used for the collection of sensor data. The outage and capacity performances are analyzed under the assumption of a Nakagami-m fading environment, for the case when the power and information transfer are performed based on the time-switching protocol and the UAV is randomly positioned at a certain height. Based on the provided analysis we derive the exact closed-form expressions for the outage probability, the outage capacity and the ergodic capacity of the power beacon assisted IoT system. The analytical results are confirmed using an independent simulation method. The performed analysis demonstrates the impact of various system and channel parameters on system performances.