Data model dual-drive joint MIMO channel estimation and signal detection method

Abstract

The invention discloses a data model dual-drive joint MIMO channel estimation and signal detection method. Channel estimation and signal detection are carried out through a channel estimator and a signal detector. The signal detector takes the channel estimation result and the received data signal as the input of each layer of network, and the tth layer of network is combined with the output of the (t-1) th layer of network to calculate an error variance vector; the tth layer of network calculates and obtain external information according to the input parameters to be trained, the error variance estimation vector and the linear estimator, obtains a signal estimation value by adopting an unscattered estimation function according to the external information, and outputs and transmits the signal estimation value to the next layer of network; and the estimated value of the final sending symbol is output by the Tth layer of network. Meanwhile, the signal detector feeds back the estimated sending symbol to the channel estimator, so that the channel estimation result is further improved. According to the invention, the network performance can be greatly improved, dynamic updating and network self-adaption are realized, the performance of the receiver can be improved, and remarkable performance gain is obtained on the basis of a traditional iterative receiver.

Description

technical field [0001] The invention relates to a joint MIMO channel estimation and signal detection method with dual data model drivers, belonging to the technical field of wireless communication. Background technique [0002] The MIMO system has become the mainstream technology of a large number of wireless communication standards because it can improve the spectrum efficiency and link reliability of the network. MIMO receiver is an important link in MIMO system design. Among them, iterative receivers based on approximate message passing and expectation propagation algorithms have received continuous attention. The receiver continuously approximates the minimum mean square error estimation in an iterative manner, decouples the detection problem of the MIMO system into a multi-channel parallel AWGN channel detection problem, and uses the non-dispersion estimation function to calculate the signal estimation value according to the external information. In the MIMO system ob...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art, provide a joint MIMO channel estimation and signal detection method driven by data models, and solve the problem of how to combine wireless transmission with deep learning to improve network self-adaptation

Images