Driven by the new generation of information technology, modern manufacturing is shifting from traditional rigid production to flexible, customized models. This transformation imposes higher demands on systems' dynamic adaptability and real-time responsiveness. The emergence of Edge Computing (EC) and the Age of Information (AoI) offers promising solutions to these challenges. Significant progress has been made in areas such as edge resource allocation and information update strategies, contributing to enhanced system responsiveness. However, most existing studies assume task independence, which limits their applicability in complex scenarios (such as high-end manufacturing), where task dependency is dynamic and ubiquitous. In addition, ensuring end-to-end integration of sensing, transmission, computation, and control (STCC) remains a major challenge. To address this gap, this study proposes a collaborative framework focusing on sensing, transmission, computation, and control (STCC), centering around task chains. For the first time, it introduces and defines the Dependency-Aware Age of Information (DAoI) metric to quantify inter-task dependencies and the effects of delay propagation, thereby enabling a more accurate assessment of data timeliness. Additionally, an optimal controller using the Linear Quadratic Regulator (LQR) is designed. Our model optimizes control performance and energy consumption through a Markov Decision Process (MDP). The proposed Dependency-Aware Heterogeneous Task and Resource Co-scheduling (MAPPO-DHTCO) algorithm efficiently manages task dependencies and resource allocation. Experimental results show that this method has significantly improved performance compared to the benchmark method.

Meeting the deterministic demands of industrial tasks can be quite challenging due to the diversity of devices and the unclear relationship between tasks and platforms in industrial edge computing scenarios. To tackle this issue, this study introduces an entropy-weighted scheduling method grounded in resource quantification. First, we scrutinized the affinity challenge when tasks operate across different platforms and broadened the scope of scheduling evaluation criteria within existing real-time systems. This expansion was accomplished by examining the alignment between various task attributes and platform characteristics through resource quantification. Subsequently, we employed the entropy weight method to handle the information entropy of all scheduling evaluation criteria and calculated the weighted sums to allocate the optimal scheduling device for each task. Ultimately, the entropy-weighted scheduling algorithm, which relies on resource quantification, was formulated to assess the algorithm’s scheduling performance under various parameter configurations. The experimental analysis indicated that the scheduling method based on resource quantification could effectively optimize the resource demand relationship between tasks and platforms, and the scheduling success rate of the proposed algorithm was 5.1%, 7.7%, and 34.5% higher than those of multitarget tracking sensor scheduling algorithm, D-Quantify, and RRA algorithms, respectively.

Computationally intensive control tasks, especially the control of image-based mobile controllers, usually require more computational capacity and network transmission resources than traditional control tasks due to the assembly of camera-based visual perception sensors. As a result, the collaborative design of network, computation, and control is of great importance to improve the efficiency of resource usage while ensuring control performance, thus achieving overall system optimality. In this article, we proposed a synergistic algorithm for network and computational resource scheduling through deep deterministic policy gradient and control based on self-triggered model predictive control, which provides optimal resource scheduling instructions after observing the system state in real time, and uses these resources to complete control tasks in the controller with a self-triggering mechanism to achieve the goal of ensuring control performance and reducing energy consumption. Finally, we designed numerical simulation experiments to verify the effectiveness of the algorithm proposed in this article.

In this paper, we consider the trade-off problem of control performance and computing resource utilization in edge controller in the context of smart manufacturing. In the Internet factory, an edge device needs to complete multiple computing tasks including control tasks under the condition of limited computing resources. Therefore, we propose a Time Division Multiplexing based self-triggered model predictive control algorithm and a computing resource allocation algorithm based on reinforcement learning to solve the optimal control input and optimal computing resource allocation scheme at the same time. Through the information interaction between the controller and the computing resource management unit, the proposed algorithm can calculate the future optimal control strategy and resource allocation scheme according to the real-time state of physical system and computing resource utilization requirement. Through simulation analysis, we get the trade-off relationship between control performance and computing resource allocation, and verify the effect of the method in the real-time operation of the system.

Deterministic response is the core foundation for the safe operation of industrial production systems. However, with the increasing demand for intelligence, flexibility, and agility, ensuring the deterministic response of computing and control tasks while meeting new demands has become the primary issue that manufacturers urgently need to address. In response to this issue, this article focuses on AI-driven cyber–physical production systems (AI-CPPSs) and conducts research on the adaptive interaction mechanism of network, computing, and manufacturing resources with guaranteed performance. The efficient adaptive configuration of network, computing, and manufacturing resources is used to meet the response requirements of dynamic tasks. To achieve on-demand configuration of multidimensional resources for tasks, we first propose an AI-CPPS-oriented modeling method named the hourglass method, which redefines task models and multidimensional resources with resources as the core. Furthermore, through the proposed method of computing power quantification and a heterogeneous frame structure, we achieve the unified arrangement of network, computing, and manufacturing resources in the time dimension. Finally, to ensure the security and reliability of resource interaction, a multidimensional resource interaction mechanism is proposed for network computing control, namely, the quicksand mechanism. The experimental results indicate that the proposed quicksand mechanism can optimize resource utilization based on ensuring a deterministic task response.

Industrial Internet, motivated by the deep integration of new-generation information and communication technology (ICT) and advanced manufacturing technology, will open up the production chain, value chain, and industry chain by establishing complete interconnections between humans, machines, and things. This will also help establish novel manufacturing and service modes, where personalized and customized production for differentiated services is a typical paradigm of future intelligent manufacturing. Thus, there is an urgent requirement to break through the existing chimney-like service mode provided by the hierarchical heterogeneous network architecture and establish a transparent channel for manufacturing and services using a flat network architecture. Starting from the basic concepts of process manufacturing and discrete manufacturing, we first analyze the basic requirements of typical manufacturing tasks. Then, with an overview on the developing process of industrial Internet, we systematically compare the current networking technologies and further analyze the problems of the present industrial Internet. On this basis, we propose to establish a novel “thin waist” that integrates sensing, communication, computing, and control for the future industrial Internet. Furthermore, we perform a deep analysis and engage in a discussion on the key challenges and future research issues regarding the multi-dimensional collaborative sensing of task–resource, the end-to-end deterministic communication of heterogeneous networks, and virtual computing and operation control of industrial Internet.

Task offloading and resource allocation are fundamental and crucial for the edge computing-enhanced industrial Internet of things, where the security and credibility among massive heterogeneous devices are being challenged. This paper first proposes a novel blockchain consensus scheme named replicated and Byzantine fault tolerant, which can enhance the trust among nodes with the low communication cost. Then, with the objective of minimizing the task completion time, which includes credible verification, task offloading and transaction record, a joint task offloading and resource allocation problem with respect to blockchain verification ratio, offloading decision, communication and computing resources is formulated. Due to its non-convexity and the decentralized characteristic of blockchain, a multi-agent deep reinforcement learning algorithm with deterministic policy gradient is proposed to appropriate the optimal solution. Experiment results confirm the effectiveness of the proposed scheme in guaranteeing the timeliness and security.

The cyber–physical production system (CPPS) has practical requirements, such as distributed, reconfigurable, and high-performance, which bring a new challenge to performance guarantee of remote manufacturing with time delay under shared resources. Time delay has a great influence on system performance, and the mainstream methods mainly reduce its influence by optimizing control. However, due to the uncertainty of time delays, the existing methods have great limitations, and the configuration complexity is high. To address this issue, we take teleoperation as the control model, then we introduce 5G slicing and edge computing technologies to turn this control problem into a control–communication–computing co-design problem. An industrial teleoperation testbed is implemented to help clarify this problem and explore the key points in solving it. Then, a novel co-design teleoperation platform (CdTP) is designed that can quantitatively describe the relationship between the time delay and system configuration. Based on CdTP, system performance assurance does not have to be achieved by blindly increasing the total amount of resources, but can be achieved by improving the utilization of shared control–communication–computing resources. In addition, CdTP can dynamic configure resources based on changing requirements, which make it combines flexibility, real time, and reliability. Finally, we propose a resource allocation method to minimize the maximum job delay. The evaluation and experimental results indicate that our platform can achieve an all-in-one configuration, and validation of the proposed method is conducted to provide deterministic delay guarantees.

Summary At present, blockchain is not only applied in the financial field, but also extended to the medical, insurance, internet of things, and many other fields. Its independence leads to more and more significant problems of network isolation. To address the problem of the cooperative operation between different blockchains, this article proposes virtual chain, a storage model supporting cross‐blockchain transaction. It not only ensures that cross‐chain transactions are tamper‐proof and traceable but also realizes completely decentralized storage. First, to tackle the multidimensional heterogeneous problem existing in cross‐chain trading, a data structure based on prefix tree is proposed to manage cross‐chain trading data on top of source chain and target chain. Second, a signature verification mechanism based on elliptic curve is proposed to meet the operational atomicity requirements of both parties of cross‐chain transaction. Third, the data fusion technology is used to expand the block capacity indirectly to achieve the high throughput of cross‐chain transactions. Finally, by using the credibility‐based access control and block chain technology to ensure the security of the data storage model, and conduct security analysis from three aspects of tamper‐proof, data protection and anti‐conspiracy node attack. The experiment shows that the proposed cross‐chain transaction storage model can realize the efficient storage of the heterogeneous data, and satisfy the high requirement of the cross‐chain transaction. Moreover, the virtual chain storage model establishes a safe and reliable working environment.

Compared to industrial wired networks, 5G can improve device mobility and reduce the cost of networking. However, the real-time performance and reliability of 5G new radio (NR) still need to be improved to satisfy industrial applications’ requirements. In factories, the main factor that affects the performance of 5G NR is the unstable signal quality caused by high temperatures and metal. Although assigning dedicated resources to all transmissions and retransmissions is an effective method to improve the performance of 5G NR, the unstable signal quality causes the resources required for retransmissions to be uncertain. To address the problem, we introduce the mixed-criticality task model to 5G NR. When high-criticality packets cannot be transmitted, they are allowed to preempt the resources shared with low-criticality packets. The mixed-criticality scheduling problem of 5G NR is NP-hard. We formulate it as an optimization modulo theories (OMT) specification and propose a scheduling algorithm based on bin packing methods to make 5G NR satisfy industrial applications’ requirements. Finally, we conduct extensive evaluations based on an industrial 5G testbed and random test cases. The evaluation results indicate that our algorithm makes communication reliability greater than 99.9% on unlicensed spectrum, and for most test cases, our algorithm is close to optimal solutions.

The IEC standard WIA-PA is a communication protocol for industrial wireless sensor networks. Its special features, including a hierarchical topology, hybrid centralized-distributed management and packet aggregation make it suitable for large-scale industrial wireless sensor networks. Industrial systems place large real-time requirements on wireless sensor networks. However, the WIA-PA standard does not specify the transmission methods, which are vital to the real-time performance of wireless networks, and little work has been done to address this problem. In this article, we propose a real-time aggregation scheduling method for WIA-PA networks. First, to satisfy the real-time constraints on dataflows, we propose a method that combines the real-time theory with the classical bin-packing method to aggregate original packets into the minimum number of aggregated packets. The simulation results indicate that our method outperforms the traditional bin-packing method, aggregating up to 35% fewer packets, and improves the real-time performance by up to 10%. Second, to make it possible to solve the scheduling problem of WIA-PA networks using the classical scheduling algorithms, we transform the ragged time slots of WIA-PA networks to a universal model. In the simulation, a large number of WIA-PA networks are randomly generated to evaluate the performances of several real-time scheduling algorithms. By comparing the results, we obtain that the earliest deadline first real-time scheduling algorithm is the preferred method for WIA-PA networks.

With the development of wireless transmission technology, the coexistence of a variety of network protocols is inevitable in industrial control networks for a certain period of time. Due to the lack of a necessary coordination mechanism between different network protocols, this may impact the transmission performance of the backhaul network connecting several subnetworks with different protocols when there are traffic bursts in certain subnets. This paper solves the problem from the perspective of dynamic routing that is based on power control. When a subnet gateway node cannot meet the bandwidth demands of the traffic burst, the interference-reducing dynamic power control method (IR-DPC) is proposed to resolve the impact on backhaul networks. It via the nodes can be connected to the gateway (1) directly, (2) by increasing the power of the gateway and (3) by adjusting the antenna direction and power respectively to conduct power control and routing recovery. Then, the method was analyzed through theoretical analysis and simulation. The results show that the routing recovery time is within 10 ms and the traffic burst bandwidth demand that is satisfied is more than twice that of traditional methods within a given range.

Wireless sensor networks (WSNs) have been widely used in industrial systems that demand a high degree of reliability and real-time performance in communications. However, because of limited network resources and delays caused by transmission conflicts and channel contention, many industrial applications cannot meet these demands. To resolve these issues, we introduce Narrow Band Internet of Things (NB-IoT) technology into industrial networks to reduce transmission delays. Two challenges are addressed in this work: (1) the primary goal is to guarantee the schedulability of the system, so the controller must determine when NB-IoT nodes transmit to base stations; and (2) because communication through the base station is a paid service, the controller must minimize the use of NB-IoT slots. We resolve these issues via a scheduling analysis and transmission mode selection. In addition, we propose a Path Selection Algorithm (PSA) to improve the schedulability of the industrial system. Experiments indicate the effectiveness and efficacy of our approach.

A smart factory generates vast amounts of data that require transmission via large-scale wireless networks. Thus, the reliability and real-time performance of large-scale wireless networks are essential for industrial production. A distributed data transmission scheme is suitable for large-scale networks, but is incapable of optimizing performance. By contrast, a centralized scheme relies on knowledge of global information and is hindered by scalability issues. To overcome these limitations, a hybrid scheme is needed. We propose a hierarchical data transmission framework that integrates the advantages of these schemes and makes a tradeoff among real-time performance, reliability, and scalability. The top level performs coarse-grained management to improve scalability and reliability by coordinating communication resources among subnetworks. The bottom level performs fine-grained management in each subnetwork, for which we propose an intrasubnetwork centralized scheduling algorithm to schedule periodic and aperiodic flows. We conduct both extensive simulations and realistic testbed experiments. The results indicate that our method has better schedulability and reduces packet loss by up to $22\%$ relative to existing methods.

Industrial systems demand high degree of reliability and real-time requirements in communications. To meet the stringent real-time performance requirements of control systems, there is a critical need for estimation system schedulability before system running. Concerning this issue, in this paper, we propose a supply/demand bound function analysis approach based on earliest deadline first scheduling to estimate system schedulability when we know network routing and the information of flows. By estimating system upper-bound demand, we can determine the schedulability of industrial wireless networks. Experiments indicate the effectiveness and efficacy of our approach.