Complex neural network channel prediction method

Abstract

The invention discloses a complex neural network channel prediction method, and mainly aims to solve the problem of channel fading caused by channel time variation in an MIMO (Multiple Input Multiple Output) system. According to the technical scheme, the complex neural network communication prediction method comprises the following steps: 1, measuring a channel by a base station to obtain a channel coefficient training sequence containing an estimation error; 2, acquiring a corresponding training sample and desired output according to the obtained channel coefficient sequence; 3, inputting a training sample to perform complex wavelet neural network training in order to obtain a final network weight; and 4, performing channel coefficient prediction through a trained complex wavelet neural network by the base station. The method is simple, convenient and feasible, has a good effect, and is suitable for lowering the influence of the channel time variation on an MIMO system channel.

Description

technical field [0001] The invention belongs to the technical field of communication, and relates to a channel prediction method, which can be used in a MIMO mobile communication system with time-varying channels. Background technique [0002] In wireless communication, reflection, diffraction and scattering are ubiquitous in various environments, and multipath propagation is inevitable; the relative movement of the transmitter and receiver inevitably produces Doppler spread, which makes the wireless channel appear frequency selectivity and time-varying properties. Fading due to frequency selectivity and time variation are considered as two different distortions. The former depends on the multipath spread and is generally characterized by the coherence bandwidth; the latter depends on the time variation of the channel and is generally characterized by the coherence time. In order to reduce the bit error rate of the system, the estimated channel information is usually used ...

AI Technical Summary

Problems solved by technology

At present, the neuron function usually chooses the nonlinear sigmoid function, but this function cannot effectively extract local channel information from the channel sequence because it cannot analyze and process the non-stationary signal with multiple resolutions.

[0008] In addition, most of the above-mentioned existing channel prediction technologies rely on the ideal channel response for prediction, but in the actual system, due to the influence of factors such as noise, the obtained channel response contains estimation errors

Channel estimation errors will pose great challenges to traditional channel prediction algorithms

Images