Accurate channel state information (CSI) prediction is essential for 6G massive multiple-input multiple-output (m-MIMO) IoT systems. Deep learning models, such as Transformers, exhibit quadratic computational complexity, resulting in significant efficiency bottlenecks when processing high-dimensional, long sequences channel data in high-mobility scenarios. The Mamba architecture, distinguished by its unique selective state-space model (SSM), presents a promising solution which combines linear computational complexity with robust capabilities for modeling long-range dependencies. Building on this foundation, we propose ChannelMamba, an end-to-end model specifically designed for channel prediction. First, the model employs a dual-domain input module that captures comprehensive channel features by concurrently processing frequency-domain CSI and delay-domain channel impulse response (CIR) data. Sub-sequently, we develop a cross-path parameter-sharing strategy for the Mamba modules to efficiently capture temporal channel dynamics while enhancing model generalization. Furthermore, to address the multi-dimensional dependencies and global context inherent in channel data, we design a bidirectional Mamba module for cross-feature modeling, enhanced with a lightweight attention mechanism. Finally, extensive experimental evaluations across various standard scenarios demonstrate the significant advantages of ChannelMamba over baseline methods in terms of prediction accuracy, robustness, generalization and computational efficiency, achieving new state-of-the-art performance in channel prediction tasks.

Highly flexible Automated Guided Vehicles (AGVs) are interconnected via Industrial Wireless Control Networks (IWCNs) in Multi-access Edge Computing (MEC)-assisted smart factories. The MEC alleviates the lack of computational resources in AGV systems through task offloading. However, IWCNs with limited communication resources struggle to support the highly concurrent offloading of AGVs. In the distributed AGV systems with multi-MEC servers, AGV mobility leads to uneven distribution across MEC server areas, potentially resulting in severe competition for communication resources. Therefore, in this paper, we design a Transferable joint Task Offloading and Multi-Channel Access (T2OMCA) algorithm based on multi-agent deep reinforcement learning. Specifically, AGV observations are modelled as graphs, in which edge relationships are learned through Transformer. This enables AGVs to utilize domain information to collaborate and alleviate concurrent offloading. Moreover, the T2OMCA algorithm converts network input into fixed embeddings to accommodate varying numbers of AGVs. Finally, to encourage exploration in the high-dimensional action space, the T2OMCA algorithm introduces a noisy network and a prioritized experience replay mechanism. Extensive simulations show that the T2OMCA algorithm outperforms existing algorithms in terms of average completion rate, processing delay, and access conflict rate under time-varying AGV topologies.

Time-Critical Wireless Network (TCWN) is a promising communication technology that can satisfy the low latency, high reliability, and deterministic requirements of mission-critical applications. Multiple TCWNs required by various applications inevitably coexist with each other. Most existing works aim to achieve acceptable latency or consider the simplest topology (i.e., line topology). As latency requirements become more stringent, exploring the minimum data collection latency becomes an interesting problem. In this paper, the coexisting system consists of multiple tree-topology-based TCWNs. We first establish a conversion framework to convert an arbitrary tree topology into multiple analogous line topologies to reduce the analysis complexity. We then propose a Time-Critical wireless network Scheduling (TCS) algorithm to minimize the data collection latency of coexisting TCWNs. The TCS algorithm consists of two phases. In the internetwork scheduling phase, we strictly derive a general expression to characterize the practical network requirements. In the intranetwork scheduling phase, we design two levels of priority assignment algorithms to accurately characterize the critical states and resource requirements of different nodes. We conduct extensive simulations to verify the effectiveness of the TCS algorithm. The evaluation results show that the TCS algorithm can achieve minimum data collection latency in more than 99.956% cases, and the maximum difference compared to the optimal value is one time slot.

6G Internet of Things (IoT) is envisioned to provide large-scale network connections and high data transmission rates to satisfy the diverse needs of IoT nodes. The wireless powered communication network (WPCN) is the essential part of the future 6G IoT, which can provide nodes with reliable and efficient data and energy transmission. In complex environments, wireless power transmissions are inefficient due to transmission distance and obstacles. To address these concerns, we propose a novel quality of experience (QoE)-driven framework for aerial intelligent reflective surface (IRS)-assisted WPCN, which exploits the maneuverability of unmanned aerial vehicle (UAV) to improve the network performance. In the framework, we construct a nonlinear satisfaction function to quantify the QoE and design an adaptive reflective units configuration scheme based on the QoE to reduce resource consumption (e.g., energy) while satisfying the QoE requirements. The optimization problem of maximizing average throughput is formulated by jointly optimizing the aerial IRS flight trajectory, node association variable, time slot allocation ratio, and IRS phase. The existence of coupling between optimization variables and the nonconvexity lead to the difficulty of solving the optimization problem directly. To effectively solve the above optimization problem, the block coordinate descent (BCD) algorithm is utilized to decompose the optimization problem into four subproblems to be solved separately. Simulation results demonstrate that the proposed scheme can significantly enhance the throughput compared with other schemes.

Federated learning (FL) is a distributed learning framework that allows clients to build models without disclosing local data. However, in resource-constrained scenarios, it is costly to participate in FL for all clients. Hence, selection strategy should be designed to select the most appropriate client groups. Current selection strategies are mainly cost and accuracy oriented, ignoring the autonomy of clients, which leads to the inability of clients to make autonomous decisions when participating in model training and updating. To realize autonomous selection of clients, we design a novel model accuracy-aware bidirectional client selection (MABCS) algorithm. The MABCS algorithm implements selection from both server and client dimensions. Specifically, the server evaluates the contributions of clients and design an accuracy-aware dynamic incentive mechanism. The client measures participation autonomy based on the reward and cost to decide whether or not to participate in FL. Thus, the client selection problem is modeled as a joint nonconvex optimization problem that maximizes the system revenue by optimizing the selection strategy and resource allocation strategy. The block coordinate descent algorithm is utilized to decouple the selection strategy and resource allocation strategy, and a linear approximation is employed to transform the selection strategy problem into a convex problem. An alternating optimization algorithm is used for the subproblems after the decomposition to obtain a near-optimal solution. Simulation results indicate that the MABCS algorithm exhibits superior convergence performance compared with other benchmark schemes.

Localization is a key technology to ensure the effective operation of wireless sensor networks in different environments. Due to the prevalence of cyber-attacks in real-world application scenarios, ensuring the accuracy of localization under denial-of-service (DoS) attacks is a growing concern. Existing research focuses on distributed localization ofstatic sensor networksunder DoS attacks. This article aims to extend the study of distributed localization inmobile sensor networkssubject to DoS attacks. Under DoS attacks, communication between sensor nodes can become intermittent, resulting in the time-varying characteristic for communication networks among all sensor nodes, which poses a challenge for successful localization. To overcome this challenge, this article proposes a distributed iterative localization algorithm using relative barycentric coordinates and distance measurements. Based on a hybrid approach composed of graph composition and sub-stochastic matrix, a comprehensive analysis of the convergence, rate and complexity of the localization algorithm is presented. At last, the theoretical results are verified by experimental examples.

The Industrial Internet of Things (IIoTs) plays an important role in various industrial applications, which require multiple time-critical networks to be deployed in the same region. The limited communication resources inevitably incur network coexistence problems. For scenarios where coexisting networks cannot coordinate effectively, the centralized or partial-information-based decentralized resource allocation methods cannot be implemented. To address this concern, we propose a Cooperation-Free Reinforcement Learning (CF-RL) algorithm for the fully distributed resource allocation problem in coexisting IIoT systems. Each network adopts the proposed algorithm to minimize collisions through a trial-and-error approach without any information interaction. To resist the influence of environmental dynamics, each coexisting network learns the state transition probability of the resource block instead of the resource block's position. Moreover, to potentially ensure the overall system performance, each network additionally considers the period offset in the initialization phase and action selection phase, so that the coexisting networks have different preferences for different state transitions. We conduct extensive simulations to verify the convergence performance. Evaluation results show that the CF-RL algorithm almost achieves (more than 99.88%) the effect of centralized resource allocation and has obvious superiorities over other cooperation-free algorithms in terms of the convergence rate, the number of collisions, and the resource utilization ratio.

The popularization of unmanned aerial vehicles (UAVs) has boosted various civil applications such as traffic monitoring, in which the effective coordination of the UAV swarm plays a significant role in expanding the monitoring range and enhancing the execution efficiency. However, due to the isolated local environments as well as the heterogeneous execution capabilities, it is challenging to achieve highly consistent actions. In this article, we incorporate the federated learning framework with the imitation learning technique to coordinate the UAVs' maneuvers by interactively imitating the leader UAV's operations. During the interagent global model download phase, we utilize the generative adversarial imitation learning (GAIL) model to accurately follow the leader UAV's operations by removing the biased estimates of imitation parameters. While in the intraagent local model training phase, we utilize the self-imitation learning (SIL) model to correct delicate imitation errors by virtue of the follower UAVs' own historical valuable experiences. In order to achieve more efficient distributed parameter interactions, we regularize the federated gradient updates and eventually yield coordinated swarm policies. We evaluate the proposed algorithm in the UAV-based traffic monitoring scenario. Evaluation results demonstrate the superiorities on training and execution efficiencies.

Conventional wireless automated guided vehicle (AGV) systems based on WiFi or ZigBee suffer random network performance and fail to guarantee the ordered and reliable transmission in AGV applications. In this article, we study the transmission scheduling with order constraints in WIA-FA-based AGV systems. We first present the transmission process of data packets in the WIA-FA-based AGV system, and design a novel superframe structure to support the ordered data exchange in the AGV system. Then, we design three heuristic rules for timeslot allocation to regulate the device transmissions subject to order constraints. Finally, inspired by the designed rules, we propose a dynamic expected packet loss rate-based timeslot allocation (DELTA) algorithm and prove its time complexity rigorously. The simulation results show that the proposed DELTA algorithm outperforms the existing works in terms of transmission reliability for different channel conditions and network scales.

WIA-FA and IEEE 802.11 are two most widely adopted industrial wireless standards in discrete manufacturing. However, comprehensive performance comparisons between WIA-FA and IEEE 802.11 are still missing and industrial applications urgently need experimental methods to guide the selection of appropriate wireless technologies. To this end, this article performs extensive experiments between WIA-FA and IEEE 802.11 in two practical industrial scenarios, with one ordered scenario defining the transmission order of devices and the other order-free scenario imposing no order constraints to the transmission order of devices. Network performance indices of the WIA-FA and IEEE 802.11 networks, including reliability, delay, jitter, and disorder rate, are compared for different network sizes and data generation periods. Experimental results show that the WIA-FA protocol provides stable network performance, while the network performance of the IEEE 802.11 protocol is random and uncontrollable. Additionally, we perform preliminary comparisons of WIA-FA with IEEE 802.11ax and 5G New Radio.

Concordant operations among automatic industrial devices (i.e., agents) play a significant role in achieving efficient smart manufacturing. Existing multiagent cooperation methods focus on centralized training with decentralized execution, which is unsuitable for the edge-based distributed industrial scenarios. To harmonize distributed devices' actions and enhance the production efficiency, in this article, we propose an Interactive-Imitation-based Distributed Coordination (IIDC) algorithm. Specifically, we leverage the generative adversarial imitation learning (GAIL) model to direct one agent's actions by following external professional demonstrations. We also adopt the self-imitation learning (SIL) model to direct one agent's potential actions by following its own previous good experiences. As the imperfect demonstrations in the GAIL-based interagent imitation process may degrade the imitation accuracy, we present a confidence-based matching method to reduce the gap between the professional and imitative behaviors. Furthermore, during the SIL-based intra-agent imitation process, the rewardless explorations also lead to nonoptimal imitation policy. We then present a Stein variational policy gradient based self-imitation method to learn an expected optimal policy. We validate the IIDC algorithm's effectiveness via the sequential assembly task. Evaluation results demonstrate that the IIDC algorithm can enhance the production efficiency evidently.

In industrial wireless sensor networks (IWSNs), monitoring data generated by field devices are supposed to be delivered to the gateway with low latency and high reliability. However, most of industrial wireless standards are based on IEEE 802.15.4 and offer limited data rates, which prevents their adoption in critical scenarios. Based on IEEE 802.11, WIA-FA is proposed to address higher communication requirements in factory automation. In this paper, we first analyze the drawbacks of the default NACK-based retransmission scheme of WIA-FA, and then propose an automatic on-demand retransmission (AODR) scheme. Finally, we give a detailed reliability analysis of the proposed AODR scheme. Simulation results show that the proposed AODR scheme outperforms existing works in terms of reliability for different scenarios.

The limited spectrum resources inevitably incur the spectrum sharing among coexisting industrial wireless networks (IWNs), and multiple coexistence IWNs form a heterogeneous environment. An effective resource allocation thus plays a crucial role in coordinating the efficient operations of multiple IWNs. Existing works only study the constrained coexistence problem among specified types of networks with a limited number of nodes over one single channel. In this paper, we investigate a general coexistence problem over multiple channels among arbitrary types of networks with line topologies, and the number of nodes in each network is also arbitrary. We rigorously analyze theoretical scheduling latency of this general coexistence problem, then we propose an algorithm to attain the optimal result. The presented Coexisting Line topology Networks Resource Allocation (CLNRA) algorithm consists of two phases. In the inter-network resource allocation phase, non-overlapped channels are allocated to each network according to the corresponding transmission priority. While in the intra-network resource allocation phase, we filter out the nodes that may generate continuous empty buffers so as to enhance the resource utilization ratio. We also verify the effectiveness of the CLNRA algorithm through extensive simulations. Evaluation results show that the CLNRA algorithm can attain the theoretical optimal result in 99:3% cases, and it has obvious superiorities on resource utilization ratio and scheduling latency.

In industrial wireless sensor networks (IWSNs), monitoring data generated by field devices should be delivered to the gateway prior to deadlines. Traditional field devices with one radio interface can only work in the half-duplex mode, which may cause severe degradation of the network real- timeliness. Considering the scenarios where each field device is with multiple radio interfaces, we study the joint scheduling of slots, channels and radio interfaces in IWSNs with mesh topologies. Specifically, a new method to calculate the total and remaining resource blocks of each transmission is first given. Then, a two-level priority assignment rule is designed by jointly considering remaining resource blocks and deadlines. Finally, a remaining resource blocks based least laxity first (RRBs-LLF) algorithm based on the above rule is proposed. Simulation results show that the proposed RRBs-LLF algorithm outperforms existing works in terms of schedulable ratio.

Intelligent factory automation systems strongly rely on industrial wireless control networks which have to ensure timely and reliable data exchange among their components. This paper presents a comprehensive survey on recently approved International Electrotechnical Commission standard Wireless networks for Industrial Automation-Factory Automation (WIA-FA). This paper first introduces the system architecture of WIA-FA including network device, network topology, and system management, and then illustrates WIA-FA protocol stack and key technologies. Furthermore, two WIA-FA testbeds are described to demonstrate the high performance of WIA-FA. After that, three examples of practical applications are provided in this paper. One application deploys a WIA-FA network to monitor and control industrial robots in a digital workshop. The second application adopts the deployment of WIA-FA as a real-time wireless network that connects automated guided vehicles (AGVs) in a logistic sorting system. The last application coordinates multiple cooperative AGVs via the WIA-FA network to carry large and complex components. Finally, the open issues and future directions for WIA-FA networks are presented.