Digital Twins (DT) have evolved from static digital mirrors into executable cyber-physical counterparts that predict, optimize, and control complex systems. However, the practical deployment of DT in Internet of Things (IoT) environments suffers from limited data fidelity, model brittleness, and resource constraints across the edge–cloud continuum. Generative DT (GDT) is DT augmented with Generative AI (GenAI). They enable the synthesis of high-fidelity data, bridge model-driven and data-driven paradigms, and provide adaptive decision support under uncertainty. This paper systematically reviews the research progress on GDT in the Manufacturing Internet of Things (MIoT), covering system architectures, key enabling technologies, and representative application scenarios. It also summarizes the main limitations of existing studies and outlines future research directions.

Tightly interdependent cyber and service networks in the Manufacturing Internet of Things (MIoT) drive cascading failures to propagate in intertwined horizontal (intra-layer) and vertical (cross-layer) directions, greatly complicating post-cascading-failure recovery decisions. To address limitations of existing approaches that neglect cross-layer dependencies and struggle to simultaneously handle heterogeneous load patterns and multiple failure states, this paper proposes a coordinated recovery framework for cyber-service-coupled MIoT, termed the coupled reinforcement learning (Coupled-RL) mechanism. Specifically, the Coupled-RL-based recovery method equips two layer-specific recovery agents for the cyber and service networks and a lightweight coordinator that orchestrates cross-layer decision-making. This coordinator is designed to avoid infeasible and globally suboptimal plans: its Feasibility Module (FM) shares the set of repaired nodes between layers and filters out actions that violate cross-layer prerequisites, while its Prediction Module (PM) exchanges per-state maximal target Q-values across layers—these values are used to construct a coupled return and inject cross-layer foresight into the Bellman update process of the agents. A weighted coupled return function and an alternating decision procedure further enable decentralized policy coordination. Extensive experiments demonstrate that the proposed recovery method effectively addresses the two-layer network coordination problem in MIoT during cascading failure recovery. Additionally, a comparative analysis between the proposed algorithm and existing ones is conducted to verify its superiority.

With the rapid development of Industry 5.0, the Industrial Internet of Things (IIoT) plays an increasingly important role as a key information infrastructure supporting data collection, transmission, and decision-making. Federated Learning-enabled IIoT (FL-enabled IIoT) systems deploy artificial intelligence (AI) models at the network edge and utilize model aggregation mechanisms to facilitate efficient data processing and intelligent decision-making. However, anomalies occurring in local nodes can propagate through the aggregation process, leading to model contamination and performance degradation, thereby compromising overall system reliability. To address this issue, this paper proposes a reliability model for FL-enabled IIoT systems. In this model, we systematically describe the entire process of model performance degradation caused by node failures and its impact on system task reliability. This includes the effects of multiple functional failures induced by node faults (i.e., data loss, communication interruption, and computational resource degradation) on model performance, as well as the failure propagation process caused by model contamination and data quality deterioration. Additionally, to evaluate the impact of model performance variations on practical production tasks, a task-oriented reliability metric is proposed. Simulation and experimental results demonstrate that the proposed modeling approach effectively characterizes the model performance degradation process and task reliability under node failure conditions.

Intelligent manufacturing systems progressively advance toward highly collaborative and distributed decision making. Federated learning (FL)-enabled intelligent manufacturing systems facilitate efficient data processing and intelligent decision making by deploying artificial intelligence models at the edge and integrating model aggregation mechanisms. However, anomalies occurring in the local devices on which the local models depend can propagate through the aggregation process, leading to model contamination and performance degradation, thereby compromising the task reliability of the entire system. To address this issue, this article proposes a reliability modeling approach for FL-enabled intelligent manufacturing systems (FL-IMSs). In the proposed model, we characterize the performance degradation process of the local model caused by terminal device failures and its impact on task reliability. This process includes the effect of data quality degradation triggered by device failures on model performance, as well as failure propagation caused by intermodel dependencies. Furthermore, to assess the impact of model performance variations on practical production tasks, a task-oriented reliability metric is introduced. Simulation and experimental results demonstrate that the proposed modeling approach effectively captures local model performance degradation and task reliability in FL-IMSs under terminal device failure conditions.

After geohazards occur, conducting rapid and sustainable secondary geohazard monitoring plays a crucial role in reducing secondary geohazard risks. However, geohazard situations vary across different areas and dynamically change with the development of geohazards. Therefore, ensuring timely data collection and the ability to dynamically adjust to changes in geohazards poses significant challenges in geohazard monitoring scenarios. This article proposes a low-latency data collection scheme considering data importance levels (LLDCL), which prioritizes data collection from high-importance sensor nodes (SNs) while still collecting data from lower importance SNs. Given the potential for sudden events in geohazard monitoring scenarios that may require adjustments to the emergency levels of monitoring points, this article introduces a deep reinforcement learning (DRL) algorithm for unmanned aerial vehicles (UAVs) path planning based on weighted age of information (DRL-WAoI). This algorithm enables UAVs to respond quickly to dynamic environments by adjusting their flight paths in real time. Furthermore, considering the limited battery capacity of UAVs, this article establishes a token-based energy trading model between UAVs and the base station (BS) to facilitate UAV recharging. Simulation experiments show that the LLDCL scheme can effectively adapt to the dynamically changing conditions of geohazard monitoring scenarios, providing a viable solution for UAV data collection and transmission.

With the advancement of digitalization and intelligentization in manufacturing systems, digital twin-driven cyber-physical manufacturing systems (DT-driven CPMSs) have emerged as a key technology for enabling smart manufacturing. Existing studies have primarily focused on the applications of DT technology, but have not fully addressed the reliability challenges arising from equipment degradation and sudden failures during system operation. To address this challenge, we propose an interdependent network model for DT-driven CPMSs that integrates real-time sensing and control feedback dependencies across the cyber layer, physical layer, and virtual decision space. The model emphasizes the characterization of data dependencies between devices under sensing-control dependencies, including production data support and collaborative production dependencies. Based on the proposed system model, we further develop a system reliability model. By incorporating the routing-driven characteristics of data in the cyber layer and the material supply-demand relationships among equipment in the physical layer, the proposed reliability model enables the joint modeling of long-term equipment degradation and sudden failure propagation under sensing-control dependencies within the system. Experimental results demonstrate that the proposed model can effectively capture system reliability behavior under these challenging operational conditions. Further analysis reveals that although the cyber layer constitutes a key bottleneck for system reliability, the physical layer is more effective in regulating it. Specifically, the average gain in system reliability achieved through redundancy enhancement in the physical layer reaches 0.82, which is significantly higher than the 0.39 gain achieved in the cyber layer.

Cascading failures are a critical factor affecting the reliability of industrial Internet of things (IIoT) systems. Establishing a realistic cascading failure model is of significant importance for researching and improving the reliability of IIoT. However, existing research on cascading failure modeling for IIoT lacks in-depth exploration of the actual characteristics of industrial scenarios, making it difficult to accurately characterize the cascading failure process in IIoT. In this work, based on the cyber–service coupling characteristic of IIoT systems, we establish a realistic interdependent network model, taking into full consideration the sensing-control data flow, the service community structure, and the diverse coupling patterns. On this basis, a cascading failure model for IIoT is developed, considering the routing-driven characteristic of the cyber network and the production–supply relationships among various manufacturing units in the service network. Extensive experiments are conducted to verify the rationality of the proposed model, and some meaningful findings are also obtained.

The emergence of the Internet of Things (IoT) has revolutionized various domains by enabling seamless connectivity and real-time data exchange between connected IoT devices. However, in sparse deployment scenarios where sensor nodes are sparsely distributed, ensuring low data delivery latency becomes a significant challenge. Our research aims to address this issue by utilizing unmanned aerial vehicles (UAVs) to support IoT networks. In the existing UAV-aided IoT systems, all UAVs are required to return to the base station to deliver data, which results in significant data delivery latency. To overcome this limitation, we propose a collaborative data acquisition model that uses air-to-air data relay between UAVs. By leveraging the mobility and agility of UAVs, the proposed system facilitates efficient data relay between sensor nodes and the base station. To further optimize the performance of the system, we present a time-balancing scheduling data acquisition (TSDA) scheme. This scheme combines a centripetal-based relay pairing method for UAVs to achieve seamless data relay and a joint scheduling scheme to minimize the hovering time during data delivery. Through extensive simulations, we demonstrate that the proposed TSDA scheme can achieve lower data delivery latency in sparse deployment scenarios compared to existing data acquisition schemes. In addition, the joint scheduling scheme can significantly reduce the hovering time of UAVs so that the collaborative relaying advantage can be better exploited.

In practical cyber-manufacturing systems (CMS), the node component is the forwarder of information and the provider of services. This dual role makes the whole system have the typical physical-services interaction characteristic, making CMS more vulnerable to cascading failures than general manufacturing systems. In this work, in order to reasonably characterize the cascading process of CMS, we first develop an interdependent network model for CMS from a physical-service networking perspective. On this basis, a realistic cascading failure model for CMS is designed with full consideration of the routing-oriented load distribution characteristics of the physical network and selective load distribution characteristics of the service network. Through extensive experiments, the soundness of the proposed model has been verified and some meaningful findings have been obtained: (1) attacks on the physical network are more likely to trigger cascading failures and may cause more damage; (2) interdependency failures are the main cause of performance degradation in the service network during cascading failures; and (3) isolation failures are the main cause of performance degradation in the physical network during cascading failures. The obtained results can certainly help users to design a more reliable CMS against cascading failures.

Current research on cascading failures of wireless sensor networks (WSNs) mainly focuses on single-sink networks and rarely involves multisink networks. To this end, this article proposes a realistic cascading model for multisink WSNs based on a new load metric “multioriented link betweenness.” On this basis, a memetic algorithm MA-MSP is proposed to help WSNs resist cascading failures via multisink placement optimization, in which the local search operator is designed based on a new network balancing metric “multioriented network entropy.” Extensive simulations have shown that the proposed cascading model can properly characterize the cascading process of multisink WSNs. Link capacity is a key factor in determining network robustness. MA-MSP can obtain a more robust placement scheme with less time compared to existing algorithms. The network communication efficiency is positively related to network robustness, and the average shortest path length is negatively related to network robustness.

Existing routing protocols for multi-sink wireless sensor networks (WSNs) attempt to optimize energy efficiency and routing survivability from the perspective of the network itself, without considering the impact of external environment, making them unable to respond to environmental changes in a timely manner. Therefore, the routing survivability of these routing protocols in harsh environments is questionable. To solve this problem, we design a sustainable multipath routing protocol SMRP, in which the routing decisions are made according to a mixed potential field in terms of depth, residual energy and environment. The basic idea of SMRP is to instruct messages to select paths with a tradeoff among delivery latency, energy balance and routing survivability. As the environmental field is constructed and updated using the sensing capability of WSN itself, the constructed multipath can be secured by avoiding passing through the dangerous areas. We explore the impact of the number of sink nodes and the number of paths on routing performance, and compare SMRP with commonly used routing protocols (i.e., EDGR and IPF). Through extensive experiments, SMRP has proved to have better performance in terms of packet delivery ratio and network lifetime under harsh environments.

Existing routing protocols of wireless sensor networks (WSNs) attempted to optimize the energy efficiency and the routing reliability from the perspective of the network itself and failed to take into consideration the environmental impact from outside, causing them cannot make prompt reaction to the dynamic changes of the environments (e.g., wildfire). Thus, in these routing protocols the routing survivability under harsh environments is questionable. To tackle this issue, in this paper by referencing the concept of potential field, we design an environment-cognitive multipath routing protocol (ECMRP) in order to provide sustainable message forwarding service under harsh environments. In ECMRP, routing decisions are made according to a mixed potential field in terms of depth, residual energy and environment. The basic idea of this approach is to instruct data packets to select routes with the tradeoff among latency, energy conservation and routing survivability. As the environmental field is constructed and updated using the sensing capability of WSN itself, constructed routes can avoid crossing through the danger zones to keep the paths safe. The experimental results show that ECMRP can obtain significant improvements in packet delivery ratio and network lifetime under harsh conditions.

How to shorten time delay and enhance delivery ratio is still an open problem in the study of opportunistic networks. Most proposals are trying to deal with this issue by introducing infrastructures. Although related research has been proven to be useful in improving the routing performance of the network, there is still room for further improvement. In this article, inspired by the powerful message synchronization capability of wireless sensor networks (WSNs), we propose a new opportunistic network framework called WON that introduces WSNs into opportunistic network. With the support of WSNs, fast message delivery and high success ratio can be achieved. We specifically present the layered architecture of WON and compare WON to existing architectures in opportunistic networking. The simulation results concerning delivery delay and success ratio are highly encouraging. Finally, open issues are outlined.

Research relating to the invulnerability of Wireless Sensor Networks (WSNs) has made gratifying progress. However, most of them concentrate on the statistic features of networks, and ignore the cascading failure of network caused by dynamic load changes. In this study, considering the realistic characteristics of WSNs, random network, scale-free network, WS small-network and NW small-network models have been built and the invulnerability performance and cascading process of these network models under random attack are researched respectively. The study presents that the increase of the coefficient of tolerance-T is beneficial to improving the invulnerability of all networks, especially NW small-world network model. By evaluating the distribution of causes (i.e., Traffic overload, invalid connectivity) to node failures, it was found that invalid connectivity is major reason for failure nodes. Besides that, scale-free network shows more steady performance than other networks in terms of error-tolerance.

Network invulnerability is an important property of networks that operate under very likely physical attacks and failures due to operating environmental conditions. A notable example of such networks is wireless fire alarming networks (WFANs) that are strongly related to the safety of the public and to the efficiency of rescuing. WFANs based on wireless sensor networks (WSN) are gaining momentum as they considered a viable and effective solution. However, the current research on invulnerability in the WSN domain mainly focuses on the optimization of the sensor node layout in the initialized network and on routing protocols, whereas the importance of optimization of the deployed network is less explored. In this paper, we show that the invulnerability of WSNs can be improved by introducing two new elements: super wires and super nodes. Moreover, on the basis of the definition of a novel centrality measurement, we propose two layout schemes based on super wires and super nodes for enhancing network invulnerability. The simulation analysis indicates that the proposed schemes are able to enhance the invulnerability of the network with low network construction costs.

Opportunistic network as a representative network evolved from social networks and ad hoc networks, has been on cutting edges in recent years. Due to its inherent characteristics serving for intermittent networking setting specifically, the opportunistic network has been also widely applied in the domain of Internet of Things (IoT). Many researchers have focused on the realistic mobility model and cost-effective routing scheme. Community as one of the most inherent attributes of the opportunistic network has been proved to be much helpful in simulating mobility traces of human society and selecting suitable message forwarders. This paper proposes a community-structured mobility model with consideration of geographical location preference and time-variance in human behavior patterns. Based on this model, a novel routing algorithm is presented by jointly considering utilities generated by social degree and relation. The results show that our routing scheme is able to improve success rate while control the routing cost and transmission delay into a reasonable range.

Body Sensor Networks (BSNs) are conveying notable attention due to their capabilities in supporting humans in their daily life. In particular, real-time and noninvasive monitoring of assisted livings is having great potential in many application domains, such as health care, sport/fitness, e-entertainment, social interaction and e-factory. And the basic as well as crucial feature characterizing such systems is the ability of detecting human actions and behaviors. In this paper, a novel approach for human posture recognition is proposed. Our BSN system relies on an information fusion method based on the D-S Evidence Theory, which is applied on the accelerometer data coming from multiple wearable sensors. Experimental results demonstrate that the developed prototype system is able to achieve a recognition accuracy between 98.5% and 100% for basic postures (standing, sitting, lying, squatting).