Performance Analysis of Cooperative and Non-Cooperative Relaying over VLC Channels.

The line-of-sight (LoS) channel is one of the requirements for efficient data transmission in visible-light communications (VLC), but this cannot always be guaranteed in indoor applications for a variety of reasons, such as moving objects and the layout of rooms. The relay-assisted VLC system is one of the techniques that can be used to address this issue and ensures seamless connectivity. This paper investigates the performance of half-duplex (HD) conventional DF relay system and cooperative systems (i.e., selective DF (SDF) and incremental DF (IDF)) over VLC channels in terms of outage probability and energy consumption. Analytical expressions for both outage probability and the minimum energy-per-bit performance of the aforementioned relaying systems are derived. Furthermore, Monte Carlo simulations are provided throughout the paper to validate the derived expressions. The results show that exploiting SDF and IDF relaying schemes can achieve approximately 25% and 15% outage probability enhancement compared to single-hop and DF protocols, respectively. The results also demonstrate that the performance of the single-hop VLC system deteriorates when the end-to-end distances become larger. For example, when the vertical distance is 3.5m, the single-hop approach consumes 20%, 40% and 45% more energy in comparison to the DF, SDF, and IDF approaches, respectively.

Deep Learning-Based Secure MIMO Communications with Imperfect CSI for Heterogeneous Networks.

Perfect channel state information (CSI) is required in most of the classical physical-layer security techniques, while it is difficult to obtain the ideal CSI due to the time-varying wireless fading channel. Although imperfect CSI has a great impact on the security of MIMO communications, deep learning is becoming a promising solution to handle the negative effect of imperfect CSI. In this work, we propose two types of deep learning-based secure MIMO detectors for heterogeneous networks, where the macro base station (BS) chooses the null-space eigenvectors to prevent information leakage to the femto BS. Thus, the bit error rate of the associated user is adopted as the metric to evaluate the system performance. With the help of deep convolutional neural networks (CNNs), the macro BS obtains the refined version from the imperfect CSI. Simulation results are provided to validate the proposed algorithms. The impacts of system parameters, such as the correlation factor of imperfect CSI, the normalized doppler frequency, the number of antennas is investigated in different setup scenarios. The results show that considerable performance gains can be obtained from the deep learning-based detectors compared with the classical maximum likelihood algorithm.