A Deep Learning-Based Optimization Method for Millimeter-Wave Mimo Hybrid Beamforming

Abstract

The present invention discloses a millimeter-wave MIMO hybrid beamforming optimization method based on deep learning, specifically comprising: the deep learning-based millimeter-wave MIMO hybrid beamforming optimization method of the present invention can form traditional millimeter-wave large-scale MIMO hybrid beamforming The constraints in the optimization problem are mapped to the neural network, and the multi-user hybrid beamforming system is completely transformed into an equivalent neural network. This enables the transformation of the complex non-convex optimization problem in hybrid beamforming into an end-to-end unsupervised optimization similar to autoencoders, where multiple beamforming matrices can be jointly optimized.

Description

technical field [0001] The present invention relates to the field of wireless communication, in particular to a millimeter-wave MIMO hybrid beamforming optimization method based on deep learning Background technique [0002] Hybrid beamforming is a promising technique for millimeter-wave multiple-input multiple-output (MIMO) systems to support ultra-high transmission capacity with low complexity. However, the design of digital and analog beamformers is a non-convex optimization challenge, especially in multi-user situations. The optimization problem of hybrid beamforming involves the optimization of four beamforming, and the gradual optimization of four matrices using a hierarchical structure cannot ensure a global optimal solution; the beamforming matrix obtained by the traditional scheme is used as the label to train the neural network proposed by the researchers. method, whose performance is limited by traditional schemes, which do not take full advantage of the powerful...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to overcome the above-mentioned deficiencies in the prior art, and to provide an optimization method for millimeter-wave MIMO hybrid beamforming based on deep learning. The present invention uses a neural network to construct a hybrid beamforming system, and the hybrid beam The matrix F of the baseband beamformer in the shaping system bb , the matrix F of the RF beamformer rf , the matrix W of the RF combiner rf and baseband combiner matrix W bb Equivalently converted into a cascaded neural network comprising four neural networks; in the present invention, the radio frequency combined neural network is split into k sub-radio frequency combined neural networks; the baseband combined neural network is split into k sub-baseband combined neural networks; the sub-radio frequency combined neural network It is connected with the sub-baseband combined with the neural network one by one to simulate the multi-user scenario in a single cell; and the user priority coefficient is added to change the user optimization priority; the entire beamforming system is mapped to a neural network, so that the mixed beamforming The complex non-convex optimization problem is transformed into an end-to-end unsupervised optimization technique similar to autoencoders to solve the joint optimization of beamforming matrices in hybrid beamforming techniques

Images