A carrier phase recovery method and system based on convolutional recurrent neural network

Abstract

The present invention relates to the field of optical fiber communication technology, and in particular discloses a carrier phase recovery method and system based on a convolutional recurrent neural network. The present invention first uses a convolutional layer to perform Gaussian blur on the received signal to reduce the influence of amplified spontaneous radiation. Then, a recursive relationship between symbols is constructed with the help of a recurrent neural network, thereby effectively removing the interference of additive Gaussian white noise under low signal-to-noise ratio conditions and improving the performance of the blind phase search algorithm in a probabilistic shaping system. The present invention adopts a convolutional recurrent neural network in combination with a blind phase search algorithm to achieve effective compensation of phase noise in a probabilistic shaping system, solve the problem that the performance of the traditional blind phase search algorithm is limited at low signal-to-noise ratios in the probabilistic shaping system, further explore the advantages of probabilistic shaping in optical communications, effectively improve the mutual information performance of the transmission system, and has important application prospects in the field of carrier phase recovery involving optical communications.

Description

Technical Field

[0001] The present invention relates to the field of optical fiber communication technology, and in particular to a carrier phase recovery method and system based on convolutional recurrent neural network. Background Art

[0002] In the field of optical communications, greater bandwidth, longer transmission distances, and higher receiving sensitivity are currently pursued goals. The development of coherent optical communication technology and constellation shaping technology has greatly improved the capacity of fiber-optic communication systems. Coherent optical communication systems can be used in communications with signals of various modulation formats while meeting the above goals. To meet the ever-increasing bandwidth demand, probabilistic shaping systems are often used to improve spectrum utilization. Probabilistic shaping technology increases the system's achievable information rate and reduces the signal-to-noise ratio required for transmission by adjusting the probability distribution of signal constellation points. However, when signals propagate through probabilistic shaping systems, the uniform distribution of transmitted signals is disrupted, resulting in performance degradation of most existing digital signal processing algorithms.

[0003] Blind phase search is an algorithm that divides the phase interval into equally spaced intervals to generate a series of test phases, thereby compensating for carrier phase noise. This algorithm, which requires no pilot overhead, is highly effective in compensating for phase noise impairments in high-order quadrature amplitude modulation. It is widely used in coherent optical communication systems and often serves as the limiting reference value for most carrier phase recovery algorithms.

[0004] However, after using probability shaping to adjust the probability distribution of signal constellation points, the probability of high-amplitude symbols in the transmitted signal is reduced, resulting in severe impairment of the mutual information performance of the blind phase search algorithm. Furthermore, in low signal-to-noise ratio (SNR) scenarios, to mitigate the effects of additive white Gaussian noise (AWGN), blind phase search algorithms often need to increase the length of the averaging filter to improve system performance, which increases the algorithm's complexity. The challenge now is to reduce the impact of AWGN without increasing the filter length, amplify the gain of high-amplitude symbols, and enhance the algorithm's robustness and ability to quickly track phase noise.

[0005] Existing fiber-optic communication technologies have the following technical problems: (1) When the signal propagates in the probability shaping system, the uniform distribution characteristic of the transmission signal is broken, resulting in the performance degradation of most existing digital signal processing algorithms; (2) After the probability distribution of the signal constellation points is adjusted by probability shaping, the probability of high-amplitude symbols appearing in the transmission signal is reduced, resulting in serious mutual information performance damage in the blind phase search algorithm; (3) In the case of low signal-to-noise ratio, in order to alleviate the influence of additive white Gaussian noise, the blind phase search algorithm improves the system performance by increasing the length of the averaging filter, which increases the complexity of the algorithm. Summary of the Invention

[0006] To solve the above technical problems, the present invention provides a carrier phase recovery method and system based on convolutional recurrent neural network, which improves the existing technology, reduces the influence of additive white Gaussian noise, amplifies the gain of high-amplitude symbols, and enhances the robustness of the algorithm and its ability to quickly track phase noise.

[0007] To achieve the above object, the technical solution adopted by the present invention is: first, a carrier phase recovery method based on a convolutional recurrent neural network is provided, comprising the following steps:

[0008] S1 will input the signal Normalize and batch to obtain batch signals;

[0009] S2 selects the test phase and performs the test on the batch signals according to the test phase. Rotate, judge the signal after each rotation with the standard constellation point, calculate the difference between the rotated signal and the judgment signal The square of the Euclidean distance;

[0010] S3 uses the square of the Euclidean distance as the input of the convolutional recurrent neural network and constructs a recursive relationship of the sum of the squares of the Euclidean distance;

[0011] S4 takes the test phase corresponding to the minimum value of the sum of squares of the Euclidean distances as a carrier phase estimate; and performs carrier phase recovery on the batched signals according to the obtained carrier phase estimate;

[0012] S5 repeats steps S2-S4 until the input signal until the recovery is complete.

[0013] Preferably, the input signal in S1 is:

[0014] ,

[0015] in, is the input signal, For an ideal noise-free signal, is the additive white Gaussian noise in the optical fiber link, is the phase noise.

[0016] Preferably, the test phase S2 The selection process is as follows:

[0017] Phase Angle Divide the phases into B equal parts and obtain B test phases as follows:

[0018] ,

[0019] Where B is the test angle, which means the phase angle The number of equal-interval divisions.

[0020] Preferably, the Euclidean distance square calculation process in S2 is:

[0021]

[0022] in, It is the symbol after the judgment.

[0023] Preferably, the recursive relationship construction process of the sum of squared distances in S3 is as follows:

[0024] Construct the convolution kernel M according to the amplitude of the received signal:

[0025]

[0026] in, represents the amplitude of the nth symbol, and L represents the length of the convolution kernel;

[0027] Perform a convolution operation on the square of the Euclidean distance:

[0028] ,

[0029] in, Represents convolution calculation, M is the convolution kernel, which is related to the amplitude characteristics of the constellation points;

[0030] Calculate the current symbol before and after The sum of squares of the Euclidean distances of the symbols, that is, the sum of squares of the current Euclidean distances, is obtained:

[0031] ,

[0032] in, is the number of filter taps;

[0033] The sum of the current Euclidean distance squares Send it into the recurrent neural network to construct the sum of squared Euclidean distances with the previous batch The recursive relationship between:

[0034] ,

[0035] in, For the forgetting factor.

[0036] Preferably, the input signal S1 The forming method comprises the following steps:

[0037] S1.1 sends the binary sequence into the constant component distribution matcher for probability shaping to generate a bit sequence that conforms to the Maxwell-Boltzmann distribution;

[0038] S1.2 maps the bit sequence to generate corresponding 64QAM symbols;

[0039] S1.3 modulates the signal onto an optical carrier wave using an IQ modulator and then transmits it into a standard single-mode optical fiber link for transmission. At the receiving end, the local oscillator laser uses the same parameters as the transmitting end laser, and the optical signal is filtered by an optical bandpass filter.

[0040] S1.4 Coherent receiver receives optical signal and converts it into electrical signal as input signal .

[0041] Preferably, the convolutional recurrent neural network described in S3 includes an input layer, a hidden layer and an output layer, and the layers are connected in a fully connected manner; the hidden layer is divided into a CNN layer and a RNN layer, the CNN layer includes a convolutional layer and a fully connected layer, and the RNN layer is a long short-term memory network structure (LSTM), including layer units.

[0042] Preferably, the convolutional recurrent neural network uses a rectified linear unit as an activation function, a mean square error function as a loss function, and is trained using a back propagation algorithm.

[0043] The present invention also provides a carrier phase recovery system based on a convolutional recurrent neural network, comprising:

[0044] Signal input module:

[0045] For input signal Normalize and batch to obtain batch signals;

[0046] Euclidean distance square calculation module:

[0047] Used to select the test phase and batch the signals according to the test phase Rotate, judge the signal after each rotation with the standard constellation point, calculate the difference between the rotated signal and the judgment signal The square of the Euclidean distance;

[0048] Recursive relation building blocks:

[0049] Used to take the square of Euclidean distance as the input of convolutional recurrent neural network and construct the recursive relationship of the sum of squared Euclidean distance;

[0050] Carrier phase recovery module:

[0051] It is used to take the test phase corresponding to the minimum value of the sum of squares of the Euclidean distances as the carrier phase estimation value; and perform carrier phase recovery on the batch signals according to the obtained carrier phase estimation value.

[0052] The above technical solution has the following advantages or beneficial effects:

[0053] This paper constructs a convolutional recurrent neural network, introduces Gaussian blurring through the convolutional layer to reduce the impact of amplified spontaneous emission noise, and then uses the recursive relationship constructed by the recurrent neural network to reduce the impact of additive white Gaussian noise at low signal-to-noise ratios. This solves the problem of carrier phase recovery algorithm performance degradation caused by unequal signal transmission probabilities in probabilistically shaped coherent optical communication systems. This improves the accuracy of phase noise estimation, enhances channel mutual information, reduces algorithm complexity, and ultimately improves the performance of the probabilistic shaping system.

[0054] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar components or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed herein and should not be construed as limiting the scope of the invention.

[0056] Figure 1 A flow chart of a carrier phase recovery method based on a convolutional recurrent neural network provided by the present invention;

[0057] Figure 2 Schematic diagram of the structure of the convolutional recurrent neural network model in the present invention;

[0058] Figure 3 A flowchart of a preferred embodiment of a carrier phase recovery method based on a convolutional recurrent neural network provided by the present invention;

[0059] Figure 4 A structural diagram of a carrier phase recovery system based on a convolutional recurrent neural network provided by the present invention; DETAILED DESCRIPTION

[0060] Hereinafter, only certain exemplary embodiments are briefly described. As will be appreciated by those skilled in the art, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and description are to be considered as illustrative in nature and not restrictive.

[0061] The present invention first provides a carrier phase recovery method based on convolutional recurrent neural network, the process is as follows Figure 1 As shown, the following steps are included:

[0062] S1 will input the signal Normalize and batch to obtain batch signals;

[0063] S2 selects the test phase and performs the test on the batch signals according to the test phase. Rotate, judge the signal after each rotation with the standard constellation point, calculate the difference between the rotated signal and the judgment signal The square of the Euclidean distance;

[0064] S3 uses the square of the Euclidean distance as the input of the convolutional recurrent neural network and constructs a recursive relationship of the sum of the squares of the Euclidean distance;

[0065] S4 takes the test phase corresponding to the minimum value of the sum of squares of the Euclidean distances as a carrier phase estimate; and performs carrier phase recovery on the batched signals according to the obtained carrier phase estimate;

[0066] S5 repeats steps S2-S4 until the input signal until the recovery is complete.

[0067] Figure 3 The present invention provides a flow chart of the steps of a preferred embodiment of a carrier phase recovery method based on a convolutional recurrent neural network. Figure 3 As shown, according to an embodiment of a carrier phase recovery method based on a convolutional recurrent neural network of the present invention, the specific implementation steps are as follows:

[0068] S1.1 sends a 65536-bit binary sequence into a constant component distribution matcher for probability shaping to generate a bit sequence that conforms to the Maxwell-Boltzmann distribution.

[0069] S1.2 maps the bit sequence to generate the corresponding 64QAM symbol. The wavelength of the transmitting laser is set to 1550nm and the linewidth is set to 100kHz.

[0070] S1.3 modulates the signal onto an optical carrier using an IQ modulator and then transmits it through a standard single-mode optical fiber link with a transmission distance of 160 km. At the receiving end, the local oscillator laser uses the same parameters as the transmitting laser, and the optical signal is filtered by an optical bandpass filter with a bandwidth set to 60 GHz.

[0071] The S1.4 coherent receiver receives an optical signal and uses the electrical signal obtained after photoelectric conversion as the input signal. The input signal is digitally processed and divided into batches of 32 symbols. The digital signal processing includes resampling, normalization, orthogonalization, dispersion compensation, polarization mode dispersion compensation, and frequency offset estimation.

[0072] S2 selects 16 test phases and tests the batch signals according to the test phases. Rotate, judge the signal after each rotation with the standard constellation point, calculate the difference between the rotated signal and the judgment signal The square of the Euclidean distance;

[0073] The test phase The selection process is as follows:

[0074] Phase Angle Divide the phases into 16 equal parts to obtain 16 test phases as follows:

[0075] .

[0076] The Euclidean distance square calculation process is:

[0077] .

[0078] S3 uses the square of the Euclidean distance as the input of the convolutional recurrent neural network and constructs a recursive relationship of the sum of the squares of the Euclidean distances, which is equivalent to using an infinitely long filter with an exponentially decaying coefficient to reduce the impact of additive Gaussian white noise.

[0079] The recursive relationship construction process of the Euclidean distance sum squared is as follows:

[0080] Construct the convolution kernel M according to the amplitude of the received signal:

[0081]

[0082] in, represents the amplitude of the nth symbol, and L represents the length of the convolution kernel;

[0083] First, the Euclidean distance squared is used in the convolution layer and the convolution kernel Perform convolution and assign different weight coefficients to the square of the Euclidean distance of different symbols:

[0084] ,

[0085] in, Represents convolution calculation, M is the convolution kernel, which is related to the amplitude characteristics of the constellation points;

[0086] Calculate the sum of the squares of the Euclidean distances of the 16 symbols before and after the current symbol, that is, the sum of the squares of the current Euclidean distances, and get:

[0087] ;

[0088] The sum of the current Euclidean distance squares Send it into the recurrent neural network to construct the sum of squared Euclidean distances with the previous batch The recursive relationship between:

[0089] ,

[0090] in, For the forgetting factor.

[0091] The structure of the convolutional recurrent neural network model is as follows Figure 2 As shown in the figure, the model consists of an input layer, hidden layers, and an output layer. Layers are connected using a fully connected architecture. The hidden layers are divided into CNN layers and RNN layers. The CNN layers include convolutional layers and fully connected layers, while the RNN layers use a long short-term memory (LSTM) network structure with layer units. A rectified linear unit (RLU) is used as the activation function, and a mean squared error (MSE) function is used as the loss function. Training is performed using a backpropagation algorithm to reduce the loss function until the optimal neural network is obtained. After training, the performance of the neural network model is verified using test data.

[0092] S4 takes the test phase corresponding to the minimum value of the sum of squares of the Euclidean distances as the carrier phase estimation value; and performs carrier phase recovery on the input signal according to the obtained carrier phase estimation value;

[0093] S5 repeats steps S2-S4 to recover the carrier phase of the signal in batches until all signals are recovered.

[0094] The present invention also provides a carrier phase recovery system based on convolutional recurrent neural network, the structure of which is as follows: Figure 4 Shown, including:

[0095] Signal input module:

[0096] For input signal Normalize and batch to obtain batch signals;

[0097] Euclidean distance square calculation module:

[0098] Used to select the test phase and batch the signals according to the test phase Rotate, judge the signal after each rotation with the standard constellation point, calculate the difference between the rotated signal and the judgment signal The square of the Euclidean distance;

[0099] Recursive relation building blocks:

[0100] Used to take the square of Euclidean distance as the input of convolutional recurrent neural network and construct the recursive relationship of the sum of squared Euclidean distance;

[0101] Carrier phase recovery module:

[0102] It is used to take the test phase corresponding to the minimum value of the sum of squares of the Euclidean distances as the carrier phase estimation value; and perform carrier phase recovery on the batch signals according to the obtained carrier phase estimation value.

[0103] The above technical solution has the following advantages or beneficial effects: The present invention uses a convolutional recurrent neural network to perform Gaussian blurring on the received signal, reducing the impact of amplified spontaneous emission on phase noise compensation. Furthermore, by constructing a recursive relationship between symbols through the recurrent neural network, the problem of excessively long filters required to remove additive white Gaussian noise in traditional blind phase search algorithms is resolved, further improving the feasibility and robustness of the algorithm.

[0104] In the description of this specification, reference to the terms "one embodiment," "a preferred embodiment," "example," "specific example," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. In addition, those skilled in the art may combine and integrate different embodiments or examples described in this specification, as well as features of different embodiments or examples, unless otherwise inconsistent.

[0105] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0106] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0107] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0108] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be accomplished by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps in the method embodiments. The device embodiments correspond to the method embodiments, so the description of the device embodiments is relatively brief, and the relevant description can refer to the description of the method embodiments.

[0109] Furthermore, the functional units in the various embodiments of the present invention may be integrated into a single processing module, each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or software functional modules. If the integrated modules are implemented as software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium. The storage medium may be a read-only memory, a magnetic disk, or an optical disk, etc.

[0110] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various modifications and substitutions within the technical scope disclosed in the present invention, and such modifications and substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A carrier phase recovery method based on convolutional recurrent neural network, characterized in that: The steps include: S1 will input the signal Normalize and batch to obtain batch signals; S2 selects the test phase and performs the test on the batch signals according to the test phase. Rotate, judge the signal after each rotation with the standard constellation point, calculate the difference between the rotated signal and the judgment signal The square of the Euclidean distance; S3 takes the square of Euclidean distance as the input of convolutional recurrent neural network and constructs the recursive relationship of the sum of squared Euclidean distance; The recursive relationship construction process of the distance square sum is as follows: Construct the convolution kernel M according to the amplitude of the received signal: ， in, represents the amplitude of the nth symbol, and L represents the length of the convolution kernel; Perform a convolution operation on the square of the Euclidean distance: ， in, Represents convolution calculation, M is the convolution kernel, which is related to the amplitude characteristics of the constellation points; Calculate the current symbol before and after The sum of squares of the Euclidean distances of the symbols, that is, the sum of squares of the current Euclidean distances, is obtained: ， in, is the number of filter taps; The sum of the current Euclidean distance squares Send it into the recurrent neural network to construct the sum of squares of the Euclidean distance between it and the previous batch The recursive relationship between: ， in, For the forgetting factor, S4 takes the test phase corresponding to the minimum value of the sum of squares of the Euclidean distances as a carrier phase estimation value; and performs carrier phase recovery on the batched signals according to the obtained carrier phase estimation value; S5 repeats steps S2-S4 until the input signal until the recovery is complete.

2. The carrier phase recovery method based on convolutional recurrent neural network according to claim 1, wherein: The input signal of S1 is: ， in, is the input signal, For an ideal noise-free signal, is the additive white Gaussian noise in the optical fiber link, is the phase noise.

3. A carrier phase recovery method based on convolutional recurrent neural network as claimed in claim 1, wherein the test phase The selection process is as follows: Phase Angle Divide the phases into B equal parts and obtain B test phases as follows: ， Where B is the test angle, which means the phase angle The number of equal-interval divisions.

4. The carrier phase recovery method based on convolutional recurrent neural network according to claim 1, wherein: The calculation process of the Euclidean distance squared in S2 is: ， in, It is the symbol after the judgment.

5. The carrier phase recovery method based on convolutional recurrent neural network according to claim 1, wherein: S1 Input signal The forming method comprises the following steps: S1.1 sends the binary sequence into the constant component distribution matcher for probability shaping to generate a bit sequence that conforms to the Maxwell-Boltzmann distribution; S1.2 maps the bit sequence to generate corresponding 64QAM symbols; S1.3 modulates the signal onto an optical carrier wave using an IQ modulator and then transmits it into a standard single-mode optical fiber link for transmission. At the receiving end, the local oscillator laser uses the same parameters as the transmitting end laser, and the optical signal is filtered by an optical bandpass filter. S1.4 Coherent receiver receives optical signal and converts it into electrical signal as input signal .

6. The carrier phase recovery method based on convolutional recurrent neural network according to claim 1, wherein: The convolutional recurrent neural network uses a rectified linear unit as an activation function, adopts a mean square error function as a loss function, and adopts a back propagation algorithm for training.

7. A carrier phase recovery system based on convolutional recurrent neural network, characterized by: include: Signal input module: For input signal Normalize and batch; Euclidean distance square calculation module: The received signal is tested according to the phase Rotate, judge the signal after each rotation with the standard constellation point, calculate the difference between the rotated signal and the judgment signal The square of the Euclidean distance; Recursive relation building blocks: The square of the Euclidean distance is used as the input of the convolutional recurrent neural network to construct a recursive relationship of the sum of the square of the Euclidean distance; Carrier phase recovery module: The test phase corresponding to the minimum value of the sum of squared Euclidean distances is taken as a carrier phase estimation value; and the carrier phase of the input signal is recovered according to the obtained carrier phase estimation value.

Images