A channel construction method for a passive optical network communication system

Abstract

The application discloses a channel construction method for a passive optical network communication system and belongs to the optical fiber communication field. The method is as follows: based on the M-QAM signal sequence after synchronization processing, the current M-QAM signal is regarded as real data. The condition vector and the real data are combined to construct a training data set, and a TFPNet network model for channel construction of the passive optical network system is constructed. The TFPNet network model is trained with the combination of the real data and the condition vector as an input feature sequence, fully processes signal features, and can combine and utilize the previous signal data information in the training data to perform sequence feature fusion on the signal data sequence when processing the signal data at the current moment, so that the nonlinear interference relationship between the current signal and the previous signal is better represented. The application has lower calculation complexity, can efficiently recover the data symbols transmitted in a wavelength division multiplexing system, and compensates for linear damage and nonlinear damage in the passive optical network optical communication system.

Description

Technical Field

[0001] The invention relates to a channel construction method for a passive optical network communication system, and belongs to the field of optical fiber communication. Background Art

[0002] With the rise of big data, cloud computing, and the metaverse, the demand for capacity and bandwidth in fiber-optic communications is rapidly increasing. Key physical properties of light waves, such as amplitude, phase, polarization, and frequency, have been fully developed and applied. Passive optical networks (PONs) are a highly efficient fiber-optic communication technology that significantly increases the transmission capacity of fiber links by supporting multiple transmission modes through schemes such as multimode fiber (MMF) or few-mode fiber (FMF). However, in practical communication channels, the increase in multiplexing modes and transmission distances, coupled with the inherent nonlinear effects of optoelectronic devices in the system, inevitably leads to severe nonlinear impairments. In PON fiber-optic communication systems, multiple optoelectronic devices are required to modulate signals. These devices exhibit inherent nonlinear effects that can severely damage signals. Currently, accurate modeling of the impact of these device nonlinearities on signals is limited, making it difficult to determine a precise theoretical model. Furthermore, the interplay of nonlinear effects from multiple devices further complicates the nonlinear model. Currently, there is no accurate theoretical model to describe the PON system channel. Therefore, deep learning has become a powerful tool for modeling unknown channels. In this work, we propose a novel data-driven approach to estimate the accurate distribution of channel transfer functions using a time-frequency joint prediction network (TFPNet). This approach lays the foundation for building digital networks for passive optical network systems.

[0003] Currently, most deep learning-based channel construction methods model channels based on existing theoretical models. These channels have a clear theoretical basis and can be effectively modeled by neural networks. However, to date, no modeling method has been developed specifically for dealing with channels in actual passive optical network systems that lack a clear theoretical model. In passive optical network transmission, the nonlinear effects of various devices make the nonlinear model of the signal extremely complex. Traditional channel estimation methods based on generative adversarial neural networks (GANs) are unable to accurately estimate the channels of passive optical network systems because the discriminator loss function has difficulty converging accurately, leading to problems such as system instability and mode collapse. Summary of the Invention

[0004] In order to address the challenge of the lack of an accurate channel model for signals in optical fiber transmission in passive optical network communication systems, the present invention aims to provide a channel construction method for passive optical network communication systems. A conditional vector is generated based on the transmitted M-QAM signal sequence, and real data is generated based on the received M-QAM signal sequence to construct a training data set. A joint prediction method in the time domain and frequency domain is adopted to construct the channel of the passive optical network communication system. The gradient back propagation algorithm and the Adam parameter optimization algorithm are used to update the TFPNet network model parameters, fully characterizing the optical fiber nonlinear effects on the signal during the transmission process of the passive optical network system, thereby improving the accuracy and stability of the communication system channel construction.

[0005] The purpose of the present invention is achieved through the following technical solutions:

[0006] The present invention discloses a channel construction method for a passive optical network communication system. At the transmitting end of the passive optical network communication system, a transmitted data sequence is mapped into constellation symbols. Through upsampling and matched filtering, the current M-QAM signal and its preceding and following n M-QAM signals are combined into a conditional vector. At the receiving end of the passive optical network communication system, an M-QAM signal sequence is received after being transmitted through a hollow-core optical fiber. The received M-QAM signal needs to be synchronized. Based on the synchronized M-QAM signal sequence, the current M-QAM signal is regarded as real data. The conditional vector and real data are combined to construct a training data set, and a TFPNet network model for channel construction in the passive optical network system is constructed. The TFPNet network model is trained using the combination of real data and the conditional vector as an input feature sequence. The TFPNet network model is trained using the training data set. The feature sequence of the newly generated M-QAM signal is input into the trained TFPNet network model. The TFPNet network model outputs a predicted signal for each M-QAM signal. After clock recovery of the predicted signal and the signal transmitted by the corresponding passive optical network system channel, each symbol is compared one by one, and the normalized mean square error of all signals is calculated to obtain the channel construction accuracy of the TFPNet network model. Based on the channel construction results, the complex nonlinear effects in the passive optical network communication system are characterized to improve the accuracy of channel construction. The TFPNet network model adopts a time domain and frequency domain joint prediction method to construct different time domain and frequency domain joint prediction networks according to the characteristics of different damages to predict nonlinear damage, and uses the gradient back propagation algorithm and the Adam parameter optimization algorithm to update the TFPNet network model parameters, reduce nonlinear damage, improve the stability of channel construction, and achieve high-precision channel construction in the passive optical network communication system.

[0007] The present invention discloses a channel construction method for a passive optical network communication system, comprising the following steps:

[0008] Step 1: At the transmitting end of the coherent optical fiber communication system, the transmitted binary data sequence is mapped to an M-QAM constellation symbol. The M-QAM modulation format signal constellation diagram has M standard constellation points. Therefore, the M-QAM signal is divided into M different categories, and each standard constellation point corresponds to a category, numbered from 1 to M as the category label. At the receiving end of the coherent optical fiber communication system, the M-QAM signal sequence after optical fiber transmission is received. For each M-QAM signal, the current M-QAM signal is combined with the real and imaginary data of the n previous and next M-QAM signals to form the conditional vector of the M-QAM signal.

[0009] At the transmitting end of the passive optical network system, the transmitted binary data sequence undergoes M-QAM symbol mapping, followed by upsampling and pulse shaping. The current M-QAM signal is combined with the n preceding and succeeding M-QAM signals to construct a conditional vector for characterizing intersymbol interference (ISI). The electrical signal is modulated onto an optical carrier using a Mach-Zehnder modulator. The center frequencies of the optical carrier are set to 191.6, 191.7, 191.8, 191.9, 192.0, 192.1, 192.2, 192.3, 192.4, 192.5, 192.6, 192.7, 192.8, 192.9, 193.0, and 193.1 THz, respectively. An erbium-doped fiber amplifier amplifies the signal. These 16 signals are modulated into one optical signal using a wavelength division multiplexer (WDM) and transmitted over a hollow-core fiber. At the receiving end of the passive optical network system, a wavelength selective switch is used to demultiplex the received signal to obtain an M-QAM signal sequence after transmission through a specified band. Clock recovery and synchronization processing are performed on the M-QAM signal. Based on the synchronized M-QAM signal sequence, the current M-QAM signal is used as the real data of the M-QAM signal sequence, and a training data set is constructed based on the conditional vector and the real data.

[0010] At the transmitting end of the passive optical network system, the transmitted binary data sequence is subjected to M-QAM symbol mapping processing, and then the M-QAM symbol sequence is upsampled and pulse-shaped. According to the inter-symbol interference caused by dispersion, the current M-QAM signal is combined with the n previous and next M-QAM signals to construct a conditional vector [x t-n ,…,x t ,…,x t+n ], i=1,2,…,N, where x t Indicates the sample currently being sent, [x t-n ,…,x t-1 ] indicates the sample that has been sent before the current sample, [x t+1 ,…,xt+n ] represents the sample to be transmitted, and n represents the number of preceding and following symbols, which is related to the strength of inter-symbol crosstalk. The M-QAM signal sequence is modulated onto the optical carrier by a Mach-Zehnder modulator, and the signal is amplified by an erbium-doped fiber amplifier. At the receiving end of the passive optical network system, the M-QAM signal sequence after hollow-core fiber transmission is received, and the M-QAM signal is clock recovered and synchronized to obtain a linearly equalized PAM-8 signal sequence s = [s1, s2, ..., s N ],i=1,2,…,N, where vector s i =[s 1 ,s 2 ,…,s 6 ] represents the i-th M-QAM signal in the M-QAM signal sequence. For the PAM-8 signal sequence s i (i=1,2,…,N), for each M-QAM signal s i , will s i As the real data y of the M-QAM signal (i) =[s i ], i = 1, 2, ..., N, N represents the size of the training data set, construct the real data feature sequence corresponding to each M-QAM signal, and construct the training data set {x (i) ,y (i)}.

[0011] Step 2: Construct a TFPNet network model for passive optical network system channel construction. The TFPNet network model is a time-frequency joint prediction network, which consists of three sub-networks, namely a time domain prediction network, a high-frequency prediction network and a nonlinear prediction network. The output signals of the three sub-networks are added to obtain the output signal y of the time-frequency joint prediction network. The data in the conditional vector feature sequence of the M-QAM signal is fully serialized and fused through the fully connected layer in the TFPNet network model. When processing the M-QAM signal data at the current moment, the preceding M-QAM signal data information and the subsequent M-QAM signal data information in the conditional vector are combined and utilized, that is, the sequence M-QAM signal data in the conditional vector is serialized and fused to better characterize the nonlinear interference relationship between the current M-QAM signal and the preceding M-QAM signal and the subsequent M-QAM signal, thereby improving the nonlinear construction capability of the TFPNet network model for the M-QAM signal and outputting a signal sequence that characterizes the real channel effect. Through the training method of the time-frequency joint prediction, a TFPNet network model for characterizing the real passive optical network system channel is obtained.

[0012] The TFPNet network model and loss function for passive optical network system channel construction are constructed. The TFPNet network model is a time-frequency joint prediction network composed of three sub-networks: a time-domain prediction network, a high-frequency prediction network, and a nonlinear prediction network. The training data set is constructed by the conditional vector of the M-QAM signal and the real data, and the training set and the noise vector with Gaussian distribution are simultaneously input into the time-domain prediction network and the high-frequency prediction network for prediction. The original signal x is input into the time-domain prediction network and then passes through the fully connected layer to obtain the output signal y1, as shown in formula (1).

[0013] y1=w*x+b (1)

[0014] Where W and b represent the weight and bias in the fully connected layer, respectively. In the fully connected layer, the linear features of the original signal are captured and fitted to predict the linear impairment of the original signal. The original signal x is input into the frequency domain prediction network and then passes through the time-frequency converter to convert the time domain signal x into the frequency domain signal X[k]. This process is shown in Equation (2).

[0015]

[0016] Where x[n] represents the nth symbol, and then the frequency domain signal X[k] is input into the fully connected layer and activated by the activation function ReLu to obtain the frequency domain output signal Y[k], as shown in formula (3),

[0017] Y[k]=ReLu(w*X[k]+b) (3)

[0018] Where W and b represent the weight and bias in the fully connected layer, respectively. The output signal y2 is obtained by inverse Fourier transform through the frequency-time converter. In the fully connected layer, the high-frequency features of the original signal are captured and fitted to predict the nonlinear damage to the original signal x caused by high-frequency fading caused by nonlinear devices. The original input signal x is subtracted from y1 and y2 to obtain x3 containing only nonlinear damage, and x3 is input into the nonlinear prediction network. After x3 is input into the time domain prediction network, it passes through the fully connected layer to obtain the output signal y3, as shown in formula (4).

[0019] y3=w*x3+b (4)

[0020] In the fully connected layer, the nonlinear characteristics of x3 are captured and fitted to predict the nonlinear damage caused to the original signal by the passive optical network system; the output signals of the three sub-networks are added to obtain the output signal y of the time-frequency joint prediction network. The data in the conditional vector feature sequence of the M-QAM signal is fully serialized and fused through the fully connected layer in the TFPNet network model. When processing the M-QAM signal data at the current moment, the preceding M-QAM signal data information and the subsequent M-QAM signal data information in the conditional vector are combined and utilized, that is, the sequence M-QAM signal data in the conditional vector is serialized and fused to better characterize the nonlinear interference relationship between the current M-QAM signal and the preceding M-QAM signal and the subsequent M-QAM signal, thereby improving the nonlinear construction capability of the TFPNet network model for the M-QAM signal and outputting a signal sequence that represents the real channel effect. Through the training method of the time-frequency joint prediction, a TFPNet network model for characterizing the channel of the real passive optical network system is obtained.

[0021] Step 3: For the TFPNet network model constructed in step 2 for passive optical network system channel construction, configure the parameters required for model training, set the learning rate, batch size, weight initialization method, optimization method, and number of iterations; use the training data set constructed in step 1 to train the TFPNet network model for passive optical network system channel construction, and fully characterize the real passive optical network channel response through the trained TFPNet network model.

[0022] For the TFPNet network model constructed in step 2 for passive optical network system channel construction, configure the parameters required for model training, set the learning rate, batch size, weight initialization method, optimization method, and number of iterations.

[0023] Using the training dataset {x (i) ,y (i)}, train the TFPNet network model constructed in step 2, use the gradient back propagation algorithm and Adam parameter optimization algorithm to determine the optimal model parameters, and obtain the trained TFPNet network model. The conditional vector x of the current M-QAM signal is constructed through the trained TFPNet network model (i) The corresponding real data y (i) The TFPNet network model is used to fully characterize the influence of the M-QAM signal on the hollow-core optical fiber transmission process caused by the optical fiber nonlinear effect.

[0024] Step 4: Input the feature sequence of the newly generated M-QAM signal into the trained TFPNet network model, output the predicted signal of each M-QAM signal, calculate the normalized mean square error between the output predicted signal result and the signal transmitted by the corresponding passive optical network system channel, and obtain the channel construction result of the TFPNet network model, characterizing the complex nonlinear effects of the passive optical network communication system. According to the channel construction result, the nonlinear damage is reduced, the stability of the channel construction is improved, and high-precision channel construction can be achieved in the passive optical network communication system.

[0025] The conditional vector feature sequence x of the newly generated M-QAM signal * Input into the trained TFPNet network model and output the predicted data Y′ of the M-QAM signal.

[0026] The normalized mean square error NMSE is calculated between the output prediction signal result Y′ and the signal Y transmitted by the corresponding passive optical network system channel.

[0027]

[0028] Where S is the total number of predicted symbols, Y′ is the predicted data, and Y is the true data.

[0029] TFPNet achieves high-accuracy channel construction, fully characterizes the fiber nonlinear effects on signals during transmission in passive optical network systems, reduces nonlinear damage based on the channel construction results, improves the stability of channel construction, and can achieve high-precision channel construction in passive optical network communication systems.

[0030] In order to accurately simulate the complex characteristics of channel impairments in communications, it is preferred to map the transmitted data sequence into 64-QAM constellation symbols.

[0031] Beneficial effects:

[0032] 1. The present invention discloses a channel construction method for a passive optical network communication system. It adopts a time-frequency joint prediction method to construct different networks based on the characteristics of different impairments to predict the impairments. It uses the gradient backpropagation algorithm and the Adam parameter optimization algorithm to update the TFPNet network model parameters. Compared with the CGAN channel construction method, it fully characterizes the optical fiber nonlinear effects on the signal during the transmission process of the passive optical network system, and improves the accuracy and stability of the communication system channel construction.

[0033] 2. The present invention discloses a channel construction method for a passive optical network communication system, which uses a time-frequency joint prediction network TFPNet as a bridging layer in the autoencoder to provide accurate gradient information for end-to-end optimization based on the autoencoder, thereby achieving more accurate end-to-end optimization of the passive optical network system.

[0034] 3. The present invention discloses a channel construction method for a passive optical network communication system. According to the inter-symbol crosstalk caused by dispersion and a spatial light modulator (SLM), a current M-QAM signal is combined with the n M-QAM signals before and after it to construct a conditional vector for characterizing the inter-symbol crosstalk; an M-QAM signal sequence after hollow-core optical fiber transmission is received, the M-QAM signal is clock recovered and synchronized, and based on the synchronized M-QAM signal sequence, the current M-QAM signal is used as the real data of the M-QAM signal; a training data set is constructed based on the conditional vector and the real data, and a TFPNet network model is constructed using the data set data-driven method. Compared with previous data-driven modeling strategies, a time-frequency joint prediction network is proposed to achieve higher-accuracy channel construction and reduce the complexity of training the TFPNet network model in response to the nonlinearity unique to passive optical network systems.

[0035] 4. The present invention discloses a channel construction method for a passive optical network communication system, which implements the channel construction of the passive optical network system based on the TFPNet network and uses a GPU to train the TFPNet network, thereby increasing the channel construction speed of the passive optical network system and improving the efficiency of data generation.

[0036] 5. The present invention discloses a channel construction method for a passive optical network communication system. By learning and processing the transmitted and received M-QAM signal data, the trained TFPNet network model constructs a nonlinear relationship between the characteristic sequence of the current M-QAM signal and its corresponding received data. The nonlinear relationship can fully characterize the influence of the M-QAM signal caused by the nonlinear effect of the optical fiber during the optical fiber transmission process; accurate signal generation is achieved according to the nonlinear relationship, and the signal recovery is achieved based on the trained TFPNet network model without relying on the precise parameter information of the optical fiber transmission link. This improves the generalization of the present invention and can be universally applied to the channel construction of all optical fiber communication links. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 The present invention discloses a flow chart of a channel construction method for a passive optical network communication system.

[0038] Figure 2 This is the network architecture diagram of TFPNet;

[0039] Figure 3 This is the structural diagram of the TFPNet conditional vector;

[0040] Figure 4 Waveform comparison chart of TFPNet generated data and real channel output data;

[0041] Figure 5 Comparison of the normalized mean square error of TFPNet and GAN generated data at different received optical powers at a transmission frequency of 191.6 THz.

[0042] Figure 6 For a transmission frequency of 192.6 THz, a comparison chart of the normalized mean square error of TFPNet and GAN generated data at different received optical powers. DETAILED DESCRIPTION

[0043] The present invention will be described in detail below with reference to the accompanying drawings and embodiments. The technical problems solved by the technical solution of the present invention and the beneficial effects thereof are also described. It should be noted that the described embodiments are only intended to facilitate understanding of the present invention and do not serve to limit the present invention in any way.

[0044] Example 1:

[0045] In passive optical network transmission systems, the complex nonlinearities of the components within them lead to complex nonlinear impairments in the optical fiber. Therefore, traditional GAN ​​methods struggle to achieve accurate convergence during channel construction. In contrast, TFPNet employs a dual residual structure and updates model parameters through forward propagation, significantly improving the accuracy and stability of channel construction. Furthermore, TFPNet utilizes a joint time-frequency prediction network to handle the complex nonlinear effects of passive optical network systems.

[0046] This embodiment discloses a channel construction method based on a joint time-frequency prediction network, applicable to passive optical network transmission systems. Different networks are constructed based on the characteristics of different impairments to predict them. A dual residual structure is used to update the TFPNet network model parameters through forward propagation, fully characterizing the fiber nonlinear effects on signals during passive optical network transmission.

[0047] like Figure 1 As shown, the channel construction method of a passive optical network communication system disclosed in this embodiment is specifically implemented as follows:

[0048] Step 1: At the transmitting end of the passive optical network system, the transmitted binary data sequence is mapped to 64-QAM symbols. The 64-QAM symbol sequence is then upsampled and pulse-shaped. Based on the inter-symbol interference caused by dispersion, the current 64-QAM signal is combined with the five preceding and succeeding 64-QAM signals to construct a conditional vector representing the inter-symbol interference. The electrical signal is modulated onto an optical carrier using a Mach-Zehnder modulator and amplified using an erbium-doped fiber amplifier. At the receiving end of the passive optical network system, the 64-QAM signal sequence is received after transmission through hollow-core fiber. The 64-QAM signal is clock-recovered and synchronized. Based on the synchronized 64-QAM signal sequence, the current 64-QAM signal is used as the actual data for the 64-QAM signal. A training dataset is constructed based on the conditional vector and the actual data.

[0049] At the transmitting end of the passive optical network system, the transmitted binary data sequence is processed by PAM-8 symbol mapping, and then the 64-QAM symbol sequence is upsampled and pulse-shaped. According to the dispersion and inter-symbol interference caused by the spatial light modulator, the current 64-QAM signal is combined with the five previous and next 64-QAM signals to construct the conditional vector x used to characterize the inter-symbol interference. (i) =[x t-5 ,…,x t ,…,x t+5 ],i=1,2,…,128000, where x t Indicates the sample currently being sent, [x t-5 ,…,x t-1 ] indicates the sample that has been sent before the current sample, [x t+1 ,…,x t+5 ] represents the sample to be transmitted, and the conditional vector structure is as follows Figure 2 As shown. The 64-QAM signal sequence is modulated onto an optical carrier by a Mach-Zehnder modulator, and the signal is amplified by an erbium-doped fiber amplifier. The signal is coupled from the optical fiber into space through a polarization controller, a collimator, and linear polarization. At the receiving end of the passive optical network system, the 64-QAM signal sequence after transmission through the hollow-core fiber is received, and the 64-QAM signal is clock recovered and synchronized to obtain a synchronized 64-QAM signal sequence s = [s1, s2, ..., s] with a sequence length of 128,000. N ],i=1,2,…,N,where s i =[s 1 ,s 2 ,…,s 6 ] vector represents the i-th 64-QAM signal in the 64-QAM signal sequence. i(i=1,2,…,N), for each 64-QAM signal s i , which is used as the real data y of the 64-QAM signal (i) =[s i ], i=1,2,…,N, construct the real data feature sequence corresponding to each 64-QAM signal, and construct the training data set {x (i) ,y (i)}, where the first 80% of the training set is used as the training set and the last 20% is used as the test set.

[0050] Step 2: Construct a TFPNet network model and loss function for passive optical network system channel construction. The TFPNet network model is a joint time-frequency prediction network composed of three sub-networks: a time-domain prediction network, a high-frequency prediction network, and a nonlinear prediction network. The training dataset constructed from the conditional vector of the 64-QAM signal and real data, along with a Gaussian noise vector, is fed into the time-domain prediction network and the high-frequency prediction network, respectively, for prediction. The original signal x is input into the time domain prediction network and then passes through the fully connected layer to obtain the output signal y1. In the fully connected layer, the linear features of the original signal are captured and fitted to predict the linear impairment of the original signal. The original signal x is input into the frequency domain prediction network and then passes through the time-frequency converter to convert the time domain signal x into a frequency domain signal fx. The frequency domain signal fx is then input into the fully connected layer and activated by the activation function ReLu to obtain the frequency domain output signal fy2. Finally, the frequency-time converter obtains the output signal y2. In this fully connected layer, the high-frequency features of the original signal are captured and fitted to predict the nonlinear impairment caused by high-frequency fading caused by nonlinear devices. The original input signal x is subtracted from y1 and y2 to obtain x3 containing only nonlinear impairments. This is then input into the nonlinear prediction network. After x3 is input into the time domain prediction network and passes through the fully connected layer, the output signal y3 is obtained. In the fully connected layer, the nonlinear characteristics of x3 are captured and fitted to predict the nonlinear impairment caused by the passive optical network to the original signal. Finally, the output signals of the three sub-networks are added together to obtain the output signal y of the joint time-frequency prediction network. The fully connected layer in the TFPNet network model performs a full feature serialization fusion process on the data in the conditional vector feature sequence of the 64-QAM signal. When processing the 64-QAM signal data at the current moment, it can combine and utilize the pre-sequence 64-QAM signal data information and the post-sequence 64-QAM signal data information in the conditional vector, that is, the sequence 64-QAM signal data in the conditional vector is subjected to serialization feature fusion, which better characterizes the nonlinear interference relationship between the current 64-QAM signal and the pre-sequence 64-QAM signal and the post-sequence 64-QAM signal, improves the nonlinear construction capability of the TFPNet network model for the 64-QAM signal, and outputs a signal sequence that represents the real channel effect. Through the training method of the time-frequency joint prediction, a TFPNet network model that can represent the channel of the real passive optical network system is obtained.

[0051] Step 3: For the TFPNet network model constructed in step 2 for passive optical network system channel construction, configure the parameters required for model training, set the learning rate, batch size, weight initialization method, optimization method, and number of iterations; use the training data set constructed in step 1 to train the TFPNet network model for passive optical network system channel construction, and construct the nonlinear relationship between the current 64-QAM signal feature sequence and its corresponding real channel signal through the trained TFPNet network model, fully characterizing the network model of the real passive optical network channel response.

[0052] For the TFPNet network model constructed in step 2, the proposed TFPNet network model was trained and evaluated in Pytorch 1.6.0, with the learning rate set to 0.0005, the batch size set to 500, the pooling kernels k of the three blocks set to 6, 3, and 1 respectively, random weight initialization method used, gradient backpropagation algorithm and Adam optimization algorithm used, and the maximum number of training steps set to 500.

[0053] Using the training dataset {x (i) ,y (i)}, i = 1, 2, ..., 128000, the TFPNet network model constructed in step 2 is trained, and the gradient back propagation algorithm and the Adam parameter optimization algorithm are used to determine the optimal model parameters to obtain a trained TFPNet network model. The conditional vector x of the current 64-QAM signal is constructed using the trained TFPNet network model. (i) The corresponding real data y (i) The TFPNet network model can fully characterize the influence of the 64-QAM signal on the optical fiber transmission process caused by the optical fiber nonlinear effect.

[0054] Step 4: Input the newly generated 64-QAM signal from the transmitter as a conditional vector into the trained TFPNet network model, and output the predicted signal Y′ corresponding to each 64-QAM signal; compare the output predicted signal result with the corresponding actual channel data. Figure 3 The waveforms of the channel output data and the data generated using TFPNet are shown for 20 GBaud, 64-QAM transmission over 5 km of hollow-core fiber at 0 dBm received optical power. Overall, the waveforms show that the actual channel output waveform and the TFPNet-generated waveform have consistent power levels. Zooming in on a portion of the waveform reveals a significant overlap between the TFPNet-generated and actual channel waveforms. This high consistency in the signal waveforms demonstrates that TFPNet effectively characterizes the characteristics of the signal passing through the passive optical network channel.

[0055] In order to quantitatively express the gap between the modeling effect based on GAN and TFPNet and the output based on the real passive optical network channel, the normalized mean square error method is used, as shown in the following formula

[0056]

[0057] Where S is the data length, Y is the data after clock synchronization and correlation at the receiving end of the passive optical network system, and Y′ is the data generated by the TFPNet.

[0058] like Figure 4 and Figure 5 As shown in the figure, using the TFPNet-based passive optical network channel construction method, 20GBaud, 64-QAM achieves a normalized mean square error of 1.2×10 -2 Compared with the GAN-based channel construction method, the modeling accuracy is improved by up to 34.5%, effectively characterizing the complex channel effects of the communication system, reducing the impact of complex nonlinearities caused by multi-components on channel construction, and improving the construction accuracy of the communication system channel.

[0059] The above specific description further illustrates the purpose, technical solutions and beneficial effects of the invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and does not limit the scope of protection of the present invention. Any modifications, replacements, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A channel construction method for a passive optical network communication system, characterized in that: The following steps are included: Step 1: At the transmitting end of the coherent optical fiber communication system, the transmitted binary data sequence is mapped to an M-QAM constellation symbol. The M-QAM modulation format signal constellation diagram has M standard constellation points. Therefore, the M-QAM signal is divided into M different categories. Each standard constellation point corresponds to a category and is numbered from 1 to M as a category label. At the receiving end of the coherent optical fiber communication system, an M-QAM signal sequence after optical fiber transmission is received. For each M-QAM signal, the real data and imaginary data of the current M-QAM signal are combined with the real data and imaginary data of the n M-QAM signals before and after it as a conditional vector of the M-QAM signal; Step 2: Construct a TFPNet network model for passive optical network system channel construction; the TFPNet network model is a time-frequency joint prediction network, which consists of three sub-networks, namely a time domain prediction network, a high-frequency prediction network and a nonlinear prediction network; the output signals of the three sub-networks are added to obtain the output signal y of the time-frequency joint prediction network; the data in the conditional vector feature sequence of the M-QAM signal is fully serialized and fused through the fully connected layer in the TFPNet network model, and when processing the current moment M-QAM signal data, the preceding M-QAM signal data information and the subsequent M-QAM signal data information in the conditional vector are combined and utilized, that is, the sequence M-QAM signal data in the conditional vector is serialized and fused to better characterize the nonlinear interference relationship between the current M-QAM signal and the preceding M-QAM signal and the subsequent M-QAM signal, thereby improving the nonlinear construction capability of the TFPNet network model for the M-QAM signal and outputting a signal sequence representing the real channel effect; through the training method of the time-frequency joint prediction, a TFPNet network model for characterizing the real passive optical network system channel is obtained; Step 3: For the TFPNet network model constructed in step 2 for passive optical network system channel construction, configure the parameters required for model training, set the learning rate, batch size, weight initialization method, optimization method, and number of iterations; use the training data set constructed in step 1 to train the TFPNet network model for passive optical network system channel construction, and use the trained TFPNet network model to fully characterize the real passive optical network channel response; Step 4: Input the feature sequence of the newly generated M-QAM signal into the trained TFPNet network model, output the predicted signal of each M-QAM signal, calculate the normalized mean square error between the output predicted signal result and the signal transmitted by the corresponding passive optical network system channel, and obtain the channel construction result of the TFPNet network model, characterizing the complex nonlinear effects of the passive optical network communication system. According to the channel construction result, the nonlinear damage is reduced, the stability of the channel construction is improved, and high-precision channel construction can be achieved in the passive optical network communication system.

2. The channel construction method for a passive optical network communication system according to claim 1, wherein: The implementation method of step one is: At the transmitting end of the passive optical network system, the transmitted binary data sequence is mapped to M-QAM symbols, upsampled and pulse-shaped, and the current M-QAM signal is combined with the n previous and next M-QAM signals to construct a conditional vector for characterizing intersymbol interference. The electrical signal is modulated onto an optical carrier via a Mach-Zehnder modulator, with the center frequencies of the optical carrier set to 191.6, 191.7, 191.8, 191.9, 192.0, 192.1, 192.2, 192.3, 192.4, 192.5, 192.6, 192.7, and 192.8, respectively. 8, 192.9, 193.0, and 193.1 THz, using an erbium-doped fiber amplifier to amplify the signals; modulating these 16 signals into one optical signal through a wavelength division multiplexer and transmitting it through a hollow-core optical fiber; at the receiving end of the passive optical network system, using a wavelength selective switch to demultiplex the received signals to obtain an M-QAM signal sequence after transmission through a specified wavelength band, performing clock recovery and synchronization processing on the M-QAM signal, and based on the synchronized M-QAM signal sequence, using the current M-QAM signal as the real data of the M-QAM signal sequence, constructing a training data set based on the conditional vector and the real data; At the transmitting end of the passive optical network system, the transmitted binary data sequence is subjected to M-QAM symbol mapping processing, and then the M-QAM symbol sequence is upsampled and pulse-shaped. According to the inter-symbol interference caused by dispersion, the current M-QAM signal is combined with the n previous and next M-QAM signals to construct a conditional vector [x t-n ,…,x t ,…,x t+n ], i=1,2,…,N, where x t Indicates the sample currently being sent, [x t-n ,…,x t-1 ] indicates the sample that has been sent before the current sample, [x t+1 ,…,x t+n ] represents the sample to be transmitted, n represents the number of preceding and following symbols, which is related to the intensity of inter-symbol crosstalk; the M-QAM signal sequence is modulated onto the optical carrier by a Mach-Zehnder modulator, and the signal is amplified by an erbium-doped fiber amplifier; At the receiving end of the passive optical network system, the M-QAM signal sequence after hollow-core optical fiber transmission is received, and the clock recovery and synchronization processing of the M-QAM signal are performed to obtain a PAM-8 signal sequence s = [s1, s2, ..., s N ],i=1,2,…,N, where vector s i =[s 1 ,s 2 ,…,s 6 ] represents the i-th M-QAM signal in the M-QAM signal sequence; for the PAM-8 signal sequence s i (i=1,2,…,N), for each M-QAM signal s i , will s i As the real data y of the M-QAM signal (i) =[s i ], i = 1, 2, ..., N, N represents the size of the training data set, construct the real data feature sequence corresponding to each M-QAM signal, and construct the training data set {x (i) ,y (i) }.

3. The channel construction method for a passive optical network communication system according to claim 2, wherein: The implementation method of step 2 is: Construct a TFPNet network model and loss function for passive optical network system channel construction. The TFPNet network model is a time-frequency joint prediction network composed of three sub-networks: a time-domain prediction network, a high-frequency prediction network, and a nonlinear prediction network. The training data set is constructed by the conditional vector of the M-QAM signal and the real data, and the training data set and the noise vector with Gaussian distribution are simultaneously input into the time domain prediction network and the high frequency prediction network for prediction; The original signal x is input into the time domain prediction network and then passes through the fully connected layer to obtain the output signal y1, as shown in formula (1). y1=w*x+b (1) Where W and b represent the weight and bias in the fully connected layer, respectively. In the fully connected layer, the linear features of the original signal are captured and fitted to predict the linear impairment of the original signal. The original signal x is input into the frequency domain prediction network and then passes through the time-frequency converter to convert the time domain signal x into the frequency domain signal X[k]. This process is shown in Equation (2). Where x[n] represents the nth symbol, and then the frequency domain signal X[k] is input into the fully connected layer and activated by the activation function ReLu to obtain the frequency domain output signal Y[k], as shown in formula (3), Y[k]=ReLu(w*X[k]+b) (3) Where W and b represent the weight and bias in the fully connected layer, respectively. The output signal y2 is obtained by inverse Fourier transform through the frequency-time converter. In the fully connected layer, the high-frequency features of the original signal are captured and fitted to predict the nonlinear damage to the original signal x caused by high-frequency fading caused by nonlinear devices. The original input signal x is subtracted from y1 and y2 to obtain x3 containing only nonlinear damage, and x3 is input into the nonlinear prediction network. After x3 is input into the time domain prediction network, it passes through the fully connected layer to obtain the output signal y3, as shown in formula (4). y3=w*x3+b (4) In the fully connected layer, the nonlinear characteristics of x3 are captured and fitted to predict the nonlinear damage caused to the original signal by the passive optical network system; the output signals of the three sub-networks are added to obtain the output signal y of the time-frequency joint prediction network; the data in the conditional vector feature sequence of the M-QAM signal is fully feature-serialized and fused through the fully connected layer in the TFPNet network model. When processing the M-QAM signal data at the current moment, the preceding M-QAM signal data information and the subsequent M-QAM signal data information in the conditional vector are combined and utilized, that is, the sequence M-QAM signal data in the conditional vector is subjected to serialized feature fusion to better characterize the nonlinear interference relationship between the current M-QAM signal and the preceding M-QAM signal and the subsequent M-QAM signal, thereby improving the nonlinear construction capability of the TFPNet network model for the M-QAM signal and outputting a signal sequence representing the real channel effect; through the training method of the time-frequency joint prediction, a TFPNet network model for characterizing the real passive optical network system channel is obtained.

4. A channel construction method for a passive optical network communication system according to claim 3, characterized in that: The implementation method of step three is: For the TFPNet network model constructed in step 2 for passive optical network system channel construction, configure the parameters required for model training, set the learning rate, batch size, weight initialization method, optimization method, and number of iterations; Using the training dataset {x (i) ,y (i) }, train the TFPNet network model constructed in step 2, use the gradient back propagation algorithm and the Adam parameter optimization algorithm to determine the optimal model parameters, and obtain a trained TFPNet network model; construct the conditional vector x of the current M-QAM signal through the trained TFPNet network model (i) The corresponding real data y (i) The TFPNet network model is used to fully characterize the influence of the M-QAM signal on the hollow-core optical fiber transmission process caused by the optical fiber nonlinear effect.

5. The channel construction method for a passive optical network communication system according to claim 4, wherein: The conditional vector feature sequence x of the newly generated M-QAM signal * Input into the trained TFPNet network model and output the predicted data Y′ of the M-QAM signal; Calculate the normalized mean square error NMSE between the output prediction signal result Y′ and the signal Y transmitted by the corresponding passive optical network system channel; Where S is the total number of predicted symbols, Y′ is the predicted data, and Y is the true data; The TFPNet model achieves high-accuracy channel construction, fully characterizes the fiber nonlinear effects on signals during transmission in passive optical network systems, reduces nonlinear damage based on the channel construction results, improves the stability of channel construction, and can achieve high-precision channel construction in passive optical network communication systems.

6. A channel construction method for a passive optical network communication system according to claim 1, 2, 3, 4 or 5, characterized in that: The transmitted data sequence is mapped into 64-QAM constellation symbols.

Images