Channel estimation method for multi-antenna system based on deep learning

Abstract

The invention discloses a multi-antenna system channel estimation method based on deep learning, which is suitable for estimating uplink multipath channels. The invention is realized based on a conditional generation confrontation network. The condition generation confrontation network includes two parts: a generator and a discriminator based on a deep learning network. The method includes two parts: offline training and online testing: offline training first generates training samples based on real channel measurements, and then uses the generator to obtain the estimated channel corresponding to the training samples; secondly, the discriminator obtains the discriminant output, and calculates the loss function to update the discriminator and The network parameters of the generator; after the loop iteration is completed, the trained generator neural network is stored in the base station; in the online test phase, the quantized pilot signal and the original pilot signal are input into the trained generator, and the user to all The estimated channel of the antenna. Compared with the prior art, the estimated normalized mean square error can be effectively reduced.

Description

technical field [0001] The invention belongs to the field of channel estimation in wireless communication, and in particular relates to a channel estimation method for a multi-antenna system based on deep learning. Background technique [0002] Massive multi-antenna (Multiple-Input-Multiple-Output, MIMO) technology is a key technology in 5G and future communications. In a massive MIMO system, the number of antennas at the base station is large, and each antenna is equipped with a high-resolution analog-to-digital converter (ADC), which will greatly increase the energy consumption and hardware cost at the base station. If a low-precision ADC is used for each antenna, the system performance will be degraded due to the quantization distortion introduced by the low-resolution ADC. Only a few antennas are equipped with high-resolution ADCs, and the hybrid ADC structure in which the remaining antennas are equipped with low-resolution ADCs can achieve a good compromise between per...

AI Technical Summary

Problems solved by technology

However, the existing deep learning channel estimation methods generally do not study the loss function, or use the more common L 1 or L 2 loss function

This type of loss function is not designed for the channel estimation problem in massive MIMO, it will limit the performance to a large extent and lead to poor channel estimation results, there is still a lot of room for improvement

Images