Deep Learning-Based Visibility Region Classification for Extra-Large Aperture Arrays

Spatial non wide-sense stationarities cause partial visibility regions (VRs), and it is a unique propagation characteristic of emerging extra-large aperture arrays (ELAAs). Thus, classification of VRs is a necessity for accurate estimation of channels and efficient design of VR-aware precoders for ELAAs. In this paper, a deep learning framework is proposed to classify VRs in ELAAs. Our objective is to boost the accuracy of classifying VRs based on the uplink pilots received at the ELAAs. Consequently, we focus on guaranteeing user-fairness in the presence of wholly/partial VRs and improving the achievable rates by adopting VR-aware channel estimation and precoding. We propose a hybrid deep learning architecture comprising one dimensional convolutional neural networks and long-short term memory to classify VRs of each user at the ELAA. To achieve a higher accuracy, we generate a diverse dataset through Monte-Carlo simulations that captures numerous combinations of VRs at the ELAA. A transmit power allocation algorithm is also proposed to achieve a common downlink rate for all users irrespective of the different VRs, and its computational complexity is discussed. A set of numerical results is presented to evaluate the performance of our proposed framework. It is efficient and accurate in classifying VRs. Thus, it can be used to enhance the estimation accuracy of ELAA channels with VRs and thereby to design VR-aware precoders to boost spectral/energy efficiency of the next-generation wireless systems.