CN113114422A

CN113114422A - Deep learning detection-super-Nyquist rate atmospheric optical transmission method

Info

Publication number: CN113114422A
Application number: CN202110392584.1A
Authority: CN
Inventors: 曹明华; 吴照恒; 王惠琴; 张伟; 王博; 周洪涛; 王效兵; 邱艳; 王莹
Original assignee: Lanzhou University of Technology
Current assignee: Lanzhou University of Technology
Priority date: 2021-04-13
Filing date: 2021-04-13
Publication date: 2021-07-13

Abstract

A deep learning detection-super-Nyquist rate atmospheric optical transmission method combines a detection algorithm based on a deep learning technology with a super-Nyquist rate technology, further improves the error code performance of an atmospheric optical communication system at a high transmission rate, and belongs to the technical field of wireless optical communication. Thereby realizing a transmission rate greater than the nyquist rate; and the receiving end recovers the signal by adopting a matched filter, super-Nyquist sampling and deep learning detection. Compared with the traditional wireless optical communication system, the introduction of the super-Nyquist technology effectively improves the system transmission rate, the introduction of the deep learning detection algorithm reduces the system operation amount, and the design of the novel atmospheric optical communication system has reference value.

Description

Deep learning detection-super-Nyquist rate atmospheric optical transmission method

Technical Field

The invention relates to a deep learning detection-super-Nyquist rate atmospheric optical transmission method, which combines a deep learning detection algorithm with a super-Nyquist (FTN) technology, further improves the error code performance of an atmospheric optical communication system at a high transmission rate and belongs to the technical field of wireless optical communication.

Background

The demand for network capacity, rate and delay with wireless communication networks is increasing. The atmospheric laser communication has the advantages of unlimited frequency spectrum, flexible link and the like as one of the alternative technologies of the next generation communication. However, atmospheric laser communication systems are susceptible to weather, aerosols, and turbulence, resulting in the transmission performance of the system being affected. In order to solve the problem, researchers have proposed methods such as a high-order modulation technology, a wavelength division multiplexing technology, a super-nyquist rate transmission technology and the like to compensate for the defects of the link. The FTN technique is a novel non-orthogonal transmission technique, and can effectively increase the transmission rate of the system. Meanwhile, the system performance can be improved by combining the technology with high-order modulation, wavelength division multiplexing and the like.

Research on the FTN technology in the fields of microwave communication and optical fiber communication has achieved abundant results. In the field of free space optical communication, technicians introduce the FTN technology into an indoor visible light communication system to realize the transmission rate of 1.47Gb/s under the transmission distance of 1.5 m. Numerous studies show that the FTN technology is expanded from the wireless and optical fiber fields to the atmospheric optical communication system, and the application scenes and the prospects of the FTN technology are richer and wider. However, there are complex uncertainties in the outdoor air channel, which results in poor performance of the communication system. Therefore, the FTN atmospheric optical communication system under the turbulent flow channel becomes a problem which needs to be researched urgently. On the other hand, the deep learning technology is recently widely applied to communication, and the neural network has the advantages of flexibility, changeability, strong anti-interference capability and the like. Therefore, the FTN technology is combined with Deep Learning (DL) to construct a DL-FTN atmospheric optical transmission decoding method, and the error code performance of the DL-FTN atmospheric optical transmission decoding method in a weak turbulence (Gamma-Gamma) channel is analyzed.

Disclosure of Invention

The invention aims to provide a deep learning detection-super Nyquist rate atmospheric optical transmission method, which improves the transmission rate of an atmospheric optical communication system by introducing an FTN technology and deep learning.

The invention relates to a deep learning detection-super-Nyquist rate atmospheric optical transmission method, which is characterized in that firstly, a super-Nyquist technology is introduced to ensure that the symbol transmission rate is greater than the Nyquist rate, secondly, a deep learning detection algorithm is introduced to decode a Quadrature Phase Shift Keying (QPSK) signal or a Quadrature Amplitude Modulation (QAM) signal, and the calculated amount is reduced by 75 percent under the condition of keeping the performance consistent with the maximum likelihood decoding error code performance. The deep learning detection method specifically comprises the following steps:

step 1: at a transmitting end, firstly, the binary information sequence is modulated and mapped into a QPSK signal or a QAM signal, and then the QPSK signal or the QAM signal is formed into a super-Nyquist signal through a super-Nyquist shaping filter.

Step 2: modulating the super-Nyquist signal obtained in the step 1 onto a laser carrier and transmitting the laser carrier by an optical antenna.

And step 3: the laser reaches an optical receiving antenna after passing through a weak turbulence atmospheric channel which follows Gamma-Gamma distribution, a photodiode on the receiving antenna converts an optical signal into an electric signal, the electric signal passes through a matched filter, and sampling is carried out at the time interval of T to obtain a corresponding code element waveform. Where τ is the acceleration factor (0< τ <1) and T is the symbol period.

And 4, step 4: constructing a neural network by adopting a torch library, constructing a multilayer neural network in a serial form, and taking the output of the previous single-layer network as the input of the next single-layer neural network; the neural network adopts a structure of increasing first and then decreasing, and the system comprises 7 layers of neural networks in total, wherein the number of neurons of an input layer 1 layer, a hidden layer 5 layer and an output layer is respectively M, 100, 150, 200, 100, 50 and N (M and N are window numbers of the input network and the output network), a Loss function is a cross entropy function (Cross entropy Loss), an Optimizer is a Stochastic Gradient Optimizer (SGD) (Stochastic Gradient Optimizer)/standard Gradient Descent method (GD), and the learning rate is 0.001, 0.0001 and 0.00001.

And 5: and (3) decoding the code element waveform received in the step (3) by using the neural network trained in the step (4), wherein the decoding process comprises the following steps of firstly, transmitting the signal received in the step (3) into an input layer of the neural network, and then, processing the signal by a hidden layer to an output layer. And the output layer has four types of output corresponding to four phases of QPSK/QAM, thereby recovering the original information.

The invention has the advantages that: in the atmospheric optical communication, the FTN technology is combined with deep learning, and the signal is packed more tightly, so that the Nyquist rate limit is exceeded, the transmission rate of the atmospheric optical communication system is effectively improved, and the error code performance is improved. The proposed deep learning detection method reduces the amount of computation of the system without losing signal performance. An effective measure is provided for solving the transmission requirements of high capacity, high speed and high quality in atmospheric optical communication.

Drawings

Fig. 1 is a block diagram of a DL-Detection-FTN atmospheric optical communication system, fig. 2 is a comparison (QPSK modulation) of DL-Detection-FTN and MLSE-FTN error performance, and fig. 3 is a comparison (QAM modulation) of DL-Detection-FTN and MLSE-FTN error performance.

Detailed Description

The invention provides a deep learning detection-atmospheric optical transmission method with super-Nyquist rate. The method introduces FTN technology in atmospheric optical communication and combines with deep learning, thereby breaking through the limitation of Nyquist criterion and further improving the transmission rate and error code performance of the system. The present invention will be described in detail below with reference to the following embodiments in conjunction with the accompanying drawings

The invention is achieved by the following technical measures:

1. basic assumptions

The invention adopts deep learning pre-equalization, the channel state follows Gamma-Gamma distribution, and only additive white Gaussian noise is considered on the assumption that background light is filtered by a filter. This assumption is typical of such systems and is not a particular requirement of the present invention.

2. Detailed description of the invention

According to the system diagram in fig. 1, at the transmitting end, a binary information sequence is first passed through an FTN shaping filter to form an FTN signal.

Wherein, E is symbol pulse energy, tau is a time acceleration factor ((0< tau <1), r (T) is a pulse waveform, and T is a code element period;

wherein, P_OCIs the average emitted optical power, ω_ocIs the optical frequency, phi_ocIs the initial phase.

S_OP(t) the signal after passing through the atmospheric channel may be represented as;

S_R(t)＝h·S_DL-OP(t)+N(t) (4)

receiving signal S_R(t) matched filtered, ADC sampled, signal representable as;

and directly decoding the sampled signals by using the trained neural network.

3 bit error performance

In order to further illustrate the correctness of the invention and the influence of the atmospheric turbulence on the system error rate, on the basis of the theoretical analysis, a Monte Carlo method is adopted to analyze the DL-FTN scheme in a Gamma-Gamma turbulence channelError performance of. The simulation conditions were as follows: the system error limit is set to 3.8 x 10^-3The photoelectric conversion coefficient is 0.5, the lambda is 1550nm,

is 7 x 10^-15m^-23And L is 500 m. The number of the neural network layers is 7, wherein the input layer is 1, the hidden layer is 4 and the output layer is provided. The numbers are M, 100, 150, 200, 100, 50, N (M and N are the number of windows of the input and output network), respectively.

Fig. 2 and 3 show the relationship between the system error performance and the monte carlo simulation result. It can be seen that: the error code performance after DL detection is compared with the maximum likelihood detection performance, and it can be seen from the figure that the deep learning detection method reduces 75% of the operation amount compared with the maximum likelihood without sacrificing the error code performance.

Through the above description of the embodiments, those skilled in the art may implement the method according to the embodiment of the present invention through software or hardware, which is part of the contribution of the present invention to the prior art.

Claims

1. A deep learning detection-super Nyquist rate atmospheric optical transmission method is characterized in that a super Nyquist technique is introduced so that a symbol transmission rate is greater than a Nyquist rate; by introducing a deep learning detection algorithm to decode QPSK/QAM, the calculated amount is reduced by 75% under the condition of keeping the performance consistent with the maximum likelihood decoding error code performance; the deep learning detection method specifically comprises the following steps:

step 1: at a transmitting end, firstly, a binary information sequence is modulated and mapped into a Quadrature Phase Shift Keying (QPSK) signal or a Quadrature Amplitude Modulation (QAM) signal, and then the super-Nyquist shaping filter forms a super-Nyquist signal:

step 2: modulating the super-Nyquist signal obtained in the step 1 onto a laser carrier and sending out the super-Nyquist signal by an optical antenna:

and step 3: laser light reaches an optical receiving antenna after passing through a weak turbulence atmospheric channel which follows Gamma-Gamma distribution, a photodiode on the receiving antenna converts an optical signal into an electric signal, the electric signal passes through a matched filter, and sampling is carried out at a time interval of tau T to obtain a corresponding code element waveform, wherein tau is an acceleration factor (0< tau <1), and T is a code element period:

and 4, step 4: constructing a neural network by adopting a torch library, constructing a multilayer neural network in a serial form, and taking the output of the previous single-layer network as the input of the next single-layer neural network; the neural network adopts an ascending-first and descending-second structure, and the system comprises 7 layers of neural networks, wherein the number of neurons of an input layer 1 layer, a hidden layer 5 layer and an output layer is respectively M, 100, 150, 200, 100, 50 and N (M and N are window numbers of the input network and the output network), a Loss function is a cross entropy function (Cross entropy Loss), an optimizer is a random gradient optimizer (SGD)/standard gradient descent method (GD), and the learning rate is 0.001, 0.0001, 0.00001:

and 5: decoding the code element waveform received in the step 3 by using the neural network trained in the step 4, wherein the decoding process comprises the following steps of firstly, transmitting the signal received in the step 3 into an input layer of the neural network, and then transmitting the signal to an output layer after the signal is processed by a hidden layer; and the output layer has four types of output corresponding to four phases of QPSK/QAM, thereby recovering the original information.