Industrial Internet of Things (IIoT) networks will provide Ultra-Reliable Low-Latency Communication (URLLC) to support critical processes underlying the production chains. However, standard protocols for allocating wireless resources may not optimize the latency-reliability trade-off, especially for uplink communication. For example, centralized grant-based scheduling can ensure almost zero collisions, but introduces delays in the way resources are requested by the User Equipments (UEs) and granted by the gNB. In turn, distributed scheduling (e.g., based on random access), in which UEs autonomously choose the resources for transmission, may lead to potentially many collisions especially when the traffic increases. In this work we propose DIStributed combinatorial NEural linear Thompson Sampling (DISNETS), a novel scheduling framework that combines the best of the two worlds. By leveraging a feedback signal from the gNB and reinforcement learning, the UEs are trained to autonomously optimize their uplink transmissions by selecting the available resources to minimize the number of collisions, without additional message exchange to/from the gNB. DISNETS is a distributed, multi-agent adaptation of the Neural Linear Thompson Sampling (NLTS) algorithm, which has been further extended to admit multiple parallel actions. We demonstrate the superior performance of DISNETS in addressing URLLC in IIoT scenarios compared to other baselines.

INTRODUCTION:5th generation cellular mobile communications (5G) is one of the main requirements for the digital future. The new standard will offer high bandwidths (10GB/s), low latency (<1ms), and a high quality of service. It is not yet known whether 5G performance is sufficient for demanding eHealth applications (e.g., telemedicine).MATERIAL AND METHODS:We evaluated 5G performance in two different medical applications (person/asset track & tracing and video data transmission for telesurgery) to appraise the impact of this new technology. In addition, a Delphi study was conducted evaluating the expectations and acceptance of 5G in the medical field in general.RESULTS:Delphi study revealed that 5G has great potential for the future information transfer in the healthcare domain, and an increase of research activities for 5G applications in hospitals is needed. Clinical evaluation proved technical feasibility and accuracy of the 5G track & trace prototype solution. For the telepresence use case, the video stream data rate varied between 900KB-1MB/s (7.2-8 Mb/s). The data rate of the robotic control command varied between 2.4-7.2KB/s (19.2-57.6Kb/s). Delay time (latency) ranged between 2-60ms depending on the transmitted data packet length. Seventy-five percent of data packets were processed after 30ms.CONCLUSION:5G data transmission volume, rate, and latency met the requirements for real-time track & trace and telemedicine applications. Especially for the latter, 5G data transmission offers a high potential and further research should be carried out.