In industrial wireless networks with resource-constrained and densely deployed devices, link scheduling is a challenging task. Traditional optimization methods have high computational complexity and low scalability. Graph learning offers a promising approach, yet it also comes with limitations of capturing multivariate relationships from interference, leading to ineffective link scheduling. In this article, hypergraphs are additionally introduced to model cumulative interference from concurrent transmissions. Considering the constructed comprehensive interference model, we propose a Lightweight link scheduling algorithm based on hybrid binary Graph and HyperGraph representation learning (L-GHG) in an unsupervised manner. Thereinto, the L-GHG algorithm extracts and fuses features from various interference relationships for link scheduling decisions. A graph partitioning based on channel state information is proposed to reduce redundant search space arising from cumulative interference. Simulations demonstrate that our proposed algorithm outperforms benchmark schemes regarding generalizability and scalability. We also validate the availability of the proposed algorithm in practical experiments.

In Time Division Multiple Access (TDMA)-based industrial wireless networks, the dynamic nature of the network environment and the diversity of communication services require more intelligent and efficient slot scheduling methodologies. Current research on multi-Quality of Service (QoS) scheduling has yet to adequately adapt to heterogeneous dynamic scenarios, which are characterized by varying periods, deadlines, and transmission units, resulting in limited scalability and inefficient resource utilization. To tackle these issues, this study introduces a Deep Q-Network algorithm enhanced with a Reward Backtracking mechanism (RB-DQN), designed to optimize slot scheduling in industrial wireless networks with mixed and heterogeneous QoS demands. This method comprehensively considers the influence of heterogeneous transmission units, deadlines, and packet generation times on resource allocation, and devises a joint metric to guarantee QoS for diverse data types. Furthermore, RB-DQN integrates delayed feedback to mitigate slot overlapping conflicts arising from disparate transmission unit sizes, thereby enhancing resource utilization efficiency. Extensive simulation results indicate that, in comparison to existing scheduling strategies, the proposed algorithm significantly reduces the delay and jitter for delay-sensitive data, while maintaining the continuity and stability of video data streams.

Channel-state information (CSI)-based physical-layer authentication (PLA) has gained significant attention. However, in industrial mobile scenarios, the time-varying channels and changing device locations limit the reliability of CSI-based PLA algorithms. Furthermore, the performance of existing PLA algorithms degrades sharply at uncalibrated locations. To improve the reliability and robustness of authentication, we propose a new spatiotemporal gradient-based-PLA (STG-PLA) algorithm enhanced by CSI-to-image transformation. We first extract correlation and scattering features to depict the multidimensional channel properties, including selectivity and dispersion. We then convert several individual CSI sequences to a CSI-image. Therefore, the spatiotemporal correlation gradient of the CSI-sequences is reflected in one CSI-image. Both simulations and experiments show that STG-PLA reduces the authentication error rate from$>10{\%}$(in existing studies) to$< 1{\%}$, which signifies considerable progress toward the practical applicability. Furthermore, with no model retraining, STG-PLA exhibits the robust performance when the device moves to uncalibrated locations.

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.