الفهرس | Only 14 pages are availabe for public view |
Abstract The ever-growing demand for high data rate and more user capacity increases the need to use the available spectrum more efficiently. The increasing demand for wireless connectivity with higher data-rate and lower latency has fueled the explorations of millimeter-wave (mm-Wave) spectrum and massive MIMO communications in the past decade. Both technologies are recognized as the key enablers of 5G and beyond systems. Hybrid beamforming (HBF) is one of the most promising energy and cost-effective methods to realize mm-Wave massive MIMO communications with lower complexity and cost. With the motivation of giving more insights and in-deep technical recommendations to B5G systems designers regarding HBF, in this thesis a HBF taxonomy is presented in terms of channel state information (CSI) availability, frequency bandwidth, architecture complexity, analog beamformer components, number of users, connectivity to RF chains, and the digital beamforming (DBF) and analog beamforming (ABF) design. Furthermore, a comprehensive survey on the state-of-the-art use-cases for each classification is provided followed by identification of the future challenges and open research issues. In addition, a deep learning network is proposed for the design of the precoder and combiner in hybrid architectures. The proposed network employs a parametric rectified linear unit (PReLU) activation function which improves model accuracy with almost no complexity cost compared to other functions. The proposed network accepts practical channel estimation input and can be trained to enhance spectral efficiency considering the hardware limitation of the hybrid design. Simulation shows that the proposed network achieves small performance improvement when compared to the same network with the ReLU activation function. |