Tactile Internet of Things (IoT) requires ultra-responsive and ultra-reliable connections for massive IoT devices. As a promising enabler of Tactile IoT, grant-free non-orthogonal multiple access (NOMA) exploits the joint benefit of grant-free access and non-orthogonal transmissions to achieve low latency massive access. However, it suffers from the reduced reliability caused by random interference. Hence, we formulate a variational optimization problem to improve the reliability of grant-free NOMA. Due to the intractability of this problem, we resort to deep learning by parameterizing the intractable variational function with a specially designed deep neural network, which incorporates random user activation and symbol spreading. The network is trained according to a novel multi-loss function where a confidence penalty based on the user activation probability is considered. The spreading signatures are automatically generated while training, which matches the highly automatic applications in Tactile IoT. The significant reliability gain of our scheme is validated by simulations.

Reconfigurable intelligent surface (RIS) has emerged as a competitive solution to the blocking problem in millimeter wave (mmWave) communications. However, due to the passive nature of the RIS, obtaining channel state information (CSI) for RIS-assisted mmWave communication systems is rather difficult. Considering that the currently available RIS hardware cannot arbitrarily switch between the active (reflection with configurable phase response) and deactivate (absorption) modes, we suggest a new beam training method for RIS-assisted mmWave communication systems in this study. First, a predefined hierarchical codebook is created using the pattern synthesis method. Then, we provide a novel hierarchical beam training method using two multi-mainlobe codewords in each layer of the hierarchical codebook for beam sweeping. Combining the results of the beam identification in all the layers will yield the ultimate ideal beam direction. Theoretical analyses demonstrate that the suggested approach can effectively reduce training overhead while ensuring successful beam alignment. Simulation results show that the practical codebook can be created successfully, and the suggested method can achieve accurate beam alignment with reduced training overhead.

The Cellular Vehicle-to-Everything (C-V2X) networks can support direct vehicle-to-vehicle V2V communications via sidelink/PC5 interface without cellular infrastructure support. The sensing-based Semi-Persistent Scheduling (SPS) scheme is to allow vehicles to autonomously reserve and select radio resources. However, the common sensing nature of distributed SPS algorithm gives rise to that C-V2X distributed communications can be challenged by the resource selection collisions, especially in aperiodic traffic, which resulting in low reliability. In this paper, we propose a short term sensing based resource selection (STS-RS) scheme to reduce packet collisions due to resource contention, where a short term sensing duration is configured at the beginning of the resource unit right before resource selection, and whether the packet is ultimately transmitted on the selected resource depends on the sensing result. Furthermore, analysis models of the performance for the proposed STS-RS scheme and SPS scheme defined in C-V2X mode 4 are investigated. Finally, simulations and numerical results show that the STS-RS scheme significantly reduces the packet collisions and increase the C-V2X direct communication performance compared to SPS scheme.

Artificial intelligence (AI) has become a promising solution for meeting the stringent performance requirements on wireless physical layer in sixth-generation (6G) communication systems, due to its strong ability to learn complex model, achieve end-to-end optimization and adapt to dynamic environments. This article provides a comprehensive review with respect to artificial intelligence for wireless physical-layer technologies (AI4PHY). Specifically, we first analyze the characteristics of the classic AI techniques and their potential applications for physical-layer technologies. Then we study the AI-enhanced designs from the point of view of the basic physical-layer modules, including coding, modulation, multiple access, multiple-input-multiple-output (MIMO), channel estimation, as well as relay transmission. The standardization progress of AI4PHY in 3GPP is also discussed. Based on the current AI4PHY researches, we propose some potential future research directions to inspire and encourage the further exploration.

Deep learning has shown promise in enhancing channel state information (CSI) feedback. However, many studies indicate that better feedback performance often accompanies higher computational complexity. Pursuing better performance-complexity tradeoffs is crucial to facilitate practical deployment, especially on computation-limited devices, which may have to use lightweight autoencoder with unfavorable performance. To achieve this goal, this paper introduces knowledge distillation (KD) to achieve better tradeoffs, where knowledge from a complicated teacher autoencoder is transferred to a lightweight student autoencoder for performance improvement. Specifically, two methods are proposed for implementation. Firstly, an autoencoder KD-based method is introduced by training a student autoencoder to mimic the reconstructed CSI of a pretrained teacher autoencoder. Secondly, an encoder KD-based method is proposed to reduce training overhead by performing KD only on the student encoder. Additionally, a variant of encoder KD is introduced to protect user equipment and base station vendor intellectual property. Numerical simulations demonstrate that the proposed methods can significantly improve the student autoencoder’s performance, while reducing the number of floating point operations and inference time to 3.05%–5.28% and 13.80%–14.76% of the teacher network, respectively. Furthermore, the variant encoder KD method effectively enhances the student autoencoder’s generalization capability across different scenarios, environments, and bandwidths.