Channel Estimation Method for 3d MIMO-OFDM System Based on Convolutional Neural Network

Abstract

The invention discloses a channel estimation method for a 3D MIMO-OFDM system based on a convolutional neural network, which includes calculating an LS estimated value by using a pilot value received in a 3D MIMO-OFDM system, and performing preprocessing on the LS estimated value to obtain Graphic representation of the real part and graphical representation of the imaginary part; the graphical representation of the real part and the graphical representation of the imaginary part are used as the input of the trained real part CECNN model and the imaginary part CECNN model respectively, and a complete channel graphical representation is output respectively ; Respectively normalize the reverse operation of the two complete channel image representations to obtain real part data and imaginary part data; and splicing the real part data and imaginary part data to obtain the complete channel response value of the 3D MIMO‑OFDM system.

Description

technical field [0001] The invention belongs to the technical field of information and communication engineering, and relates to a channel estimation method for a 3D MIMO-OFDM system based on a convolutional neural network. Background technique [0002] Channel estimation is the process of estimating model parameters of an assumed channel model from received data, and the accuracy of channel estimation will directly affect the performance of the entire system. The existing 3D MIMO-OFDM system expands the vertical dimension of the channel on the original MIMO-OFDM system, making the wireless channel more complicated than other situations. If the existing conventional LS algorithm is used (the LS algorithm obtains the channel Response H at the pilot frequency, and interpolating H to obtain a complete channel response value) to perform channel estimation on it, there are defects such as poor estimation accuracy and large occupation of pilot frequency resources. Contents of th...

AI Technical Summary

Problems solved by technology

The existing 3D MIMO-OFDM system expands the vertical dimension of the channel on the original MIMO-OFDM system, making the wireless channel more complicated than other situations. If the existing conventional LS algorithm is used (the LS algorithm obtains the channel The response H at the pilot frequency, and the complete channel response value can be obtained by interpolating H) to perform channel estimation on it, there are defects such as poor estimation accuracy and large occupation of pilot frequency resources.

Images