Deep neural network channel estimation method and system based on data driving

Abstract

A network model is iteratively trained based on a data driving mode, a data driving type channel estimation communication system suitable for the deep neural network is designed, data driving adopts various data, the number of times of perceptron training is increased, the channel environment is simulated, real channel distribution is constantly fitted, and the accuracy of channel estimation is improved. The extreme value is continuously optimized through a forward and reverse algorithm, the channel state information can be obtained through data training, and the communication quality is improved.

Description

technical field [0001] The invention relates to the field of communication technology, in particular to a data-driven deep neural network channel estimation method and system. Background technique [0002] Wireless communication technology is accompanied by the development of communication and signal fields and the continuous improvement of communication systems. We can achieve low-latency mutual communication through the propagation of radio signals at any time, but traditional communication technologies still have serious inter-symbol interference and spectrum interference. Influences such as low utilization rate and multipath effect all include the design of multiple system underlying reasons and the corresponding selection of frequency, bandwidth resource allocation and channel model technology. In the 21st century, with the introduction of discrete Fourier transform and inverse discrete Fourier transform into Orthogonal Frequency Division Multiplexing (OFDM) and Multipl...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the serious shortage of channel estimation algorithm performance, system accuracy and spectrum utilization, the present invention proposes a data-driven deep neural network channel estimation method and system

Images