In this paper, we study a multiple-input-multiple-output (MIMO) non-orthogonal multiple access (NOMA) downlink system, where a base station employs beamforming to transmit multiple data streams simultaneously to a central user and a cell-edge user. Over each beam, the orthogonal frequency division multiplexing (OFDM) modulated signals intended for both users are superimposed and then transmitted. Because of beamforming and OFDM modulation, the central user may have weaker beams compared with the cell-edge user. This causes the unsuccessful successive interference cancellation (SIC). To solve this problem, we derive the necessary and sufficient conditions to ensure the successful SIC for arbitrary beamforming matrices. Based on these conditions, we design a specialized beamforming structure where signals over weak beams can be orthogonally separated from those over strong ones. We propose that joint encoding and decoding are applied to signals over weak beams and similarly to those over strong ones. To optimize the beamforming matrices, we propose a constrained convex concave procedure based algorithm and a matrix fractional programming based algorithm. It is verified through simulation results that the proposed scheme performs better than the conventional OFDM-NOMA scheme.

This paper investigates deploying semantic edge inference systems for performing a common image clarification task. In particular, each system consists of multiple Internet of Things (IoT) devices that first locally encode the sensing data into semantic features and then transmit them to an edge server for subsequent data fusion and task inference. The inference accuracy is determined by efficient training of the feature encoder/decoder using labeled data samples. Due to the difference in sensing data and communication channel distributions, deploying the system in a new environment may induce high costs in annotating data labels and re-training the encoder/decoder models. To achieve cost-effective transferable system deployment, we propose an efficient Domain Adaptation method for Semantic Edge INference systems (DASEIN) that can maintain high inference accuracy in a new environment without the need for labeled samples. Specifically, DASEIN exploits the task-relevant data correlation between different deployment scenarios by leveraging the techniques of unsupervised domain adaptation and knowledge distillation. It devises an efficient two-step adaptation procedure that sequentially aligns the data distributions and adapts to the channel variations. Numerical results show that, under a substantial change in sensing data distributions, the proposed DASEIN outperforms the best-performing benchmark method by 7.09% and 21.33% in inference accuracy when the new environment has similar or 25 dB lower channel signal to noise power ratios (SNRs), respectively. This verifies the effectiveness of the proposed method in adapting both data and channel distributions in practical transfer deployment applications.

In this paper, we propose a novel semantic digital analog converter (sDAC) for the compatibility between semantic and digital communications. Most of the current semantic communication systems rely primarily on analog modulation, limiting their integration with digital communication systems, which are more common in practice. In fact, traditional quantization methods are unsuitable for semantic communication because they do not account for semantic information within symbols. These factors block the wide application of the semantic communication. To address these challenges, sDAC is proposed. It is a simple yet efficient and generative module used to realize digital and analog bi-directional conversion. The entire process is independent of any specific semantic model, modulation methods, or channel conditions. In the experiment section, the performance of sDAC is tested across different semantic models, semantic tasks, modulation methods, channel conditions and quantization orders. Test results show that the proposed sDAC has great generative properties and channel robustness.

To combine the orthogonal frequency division multiplexing (OFDM) modulation with non-orthogonal multiple access (NOMA) technique, it is required to ensure the successful successive interference cancellation procedure. Because of the fast Fourier transform (FFT) and inverse FFT employed at the OFDM transceivers, the central user may have weak subcarriers and the cell-edge user may have strong subcarriers. In this paper, we propose that for the central or cell-edge user, signals over the weak (strong) subcarriers are jointly encoded and decoded. Our objective is to maximize the weighted sum average achievable rates at both the central and cell-edge users through power allocation optimization. To solve the optimization problem, we propose a constrained convex-concave procedure (CCCP) based locally optimal solution, a Lagrangian dual transformation based locally optimal solution, and a prime decomposition based near-optimal solution. The prime decomposition based algorithm, which solves the problem based on water-filling, has extremely low computational complexity. It is shown through simulation results that the proposed scheme outperforms the conventional OFDM-NOMA scheme. Furthermore, it is found that the results obtained by the CCCP based solution, Lagrangian dual transformation based solution, and prime decomposition based solution match one another.

Reinforcement learning has been widely used to train a sequential power control policy from simulation environment in Internet of Vehicles. However, disturbance is usually inevitably introduced when the agent getting into the practical environment from the simulation environment, which leads to a critical challenge when multiple links share a common spectrum. This paper is dedicated to addressing this issue in a two-pronged way. On one hand, we set the aim of policy learning as minimizing the network transmission outage probability from a risk-sensitive perspective. On the other hand, we propose a meta soft actor-critic based power control scheme, where the key hyperparameter is auto-adjusted to adapt to environment variations and L2 regulation is taken in the loss function of critic network to avoid overfitting to the simulation environment. Simulation results show that, the proposed algorithm achieves a higher successful transmission probability under the same conditions and is more robust under disturbed environment, than the baseline schemes.

Recently, Green Radio, which aims to reduce energy consumption of information and communication technologies (ICTs), has been concerned by telecommunication operators and researchers and can be applied to emergency scenarios. However, the communication system in emergency situation is pursuing not only energy reduction, but the large number of serviced users. In this paper, in order to provide telecommunication services for a great number of clients with low energy consumption in emergency scenarios, a capacity-and-energy efficient radio resource allocation mechanism is proposed, which is modeled as a Sigmoid-based optimization problem. Our simulation results demonstrate that compared with the conventional resource allocation algorithms, the proposed one achieves the largest capacity-and-energy efficiency, i.e., the largest number of serviced users per power unit.