Optical performance monitoring method, device, equipment, vehicle, medium and program product

Abstract

The invention discloses an optical performance monitoring method, device and equipment, a vehicle, a medium and a program product, and belongs to the technical field of optical fiber communication. The method comprises: acquiring a target signal of an optical network; the target signal comprises a signal of the optical network in at least part of monitoring duration of a monitoring period; and determining the signal quality of the optical network in the monitoring period of the target signal according to the error vector amplitude of the target signal. According to the embodiment of the invention, the signal of the optical network in at least part of the monitoring duration of the monitoring period is acquired, the part of signal represents a part of signal of the monitoring period instead of the signal of the whole monitoring period, and the signal quality of the monitoring period is determined through the error vector amplitude of the part of signal. The signal quality of the monitoring period is estimated through the short signal sequence, a large number of data points of the signals of the whole monitoring period do not need to be calculated, the optical performance monitoring efficiency is improved, and therefore the optical performance monitoring method and device can better adapt to the rapidly-changing network environment.

Description

Technical Field

[0001] This application belongs to the field of optical fiber communication technology, and in particular relates to an optical performance monitoring method, device, equipment, vehicle, medium and program product. Background Technology

[0002] To meet ever-increasing bandwidth demands, optical networks have evolved into highly flexible and configurable elastic optical networks to cope with different application and traffic requirements. Optical performance monitoring (OPM) is a key component in maintaining the efficient operation and troubleshooting of optical networks.

[0003] The most intuitive metric for evaluating signal quality is the Bit Error Rate (BER). A lower BER generally indicates better signal quality, thus aiding in BER estimation. Related technologies typically use the Optical Signal-to-Noise Ratio (OSNR) to help estimate the BER. However, OSNR calculation requires the entire signal acquisition process to be completed, and the calculation itself is time-consuming. In today's rapidly changing network environment, the response speed of this method may not meet monitoring needs. Summary of the Invention

[0004] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes a method, apparatus, equipment, vehicle, medium, and program product for optical performance monitoring, so as to improve the efficiency of optical performance monitoring.

[0005] In a first aspect, this application provides a method for monitoring optical performance, including:

[0006] Acquire the target signal of the optical network; the target signal includes the signal of the optical network during at least a portion of the monitoring duration of the monitoring period;

[0007] The signal quality of the optical network within the monitoring period of the target signal is determined based on the error vector magnitude of the target signal.

[0008] According to the optical performance monitoring method of this application, a target signal of an optical network is acquired; the target signal includes the signal of the optical network within at least a portion of the monitoring duration of a monitoring period; and the signal quality of the optical network within the monitoring period containing the target signal is determined based on the error vector magnitude of the target signal. This embodiment of the application acquires the signal of the optical network within at least a portion of the monitoring duration of a monitoring period, where this portion of the signal represents a part of the monitoring period, rather than the entire monitoring period, and determines the signal quality of the monitoring period based on the error vector magnitude of this portion of the signal. This achieves the estimation of signal quality for the monitoring period using a shorter signal sequence, eliminating the need to calculate a large number of data points for the entire monitoring period, thus improving the efficiency of optical performance monitoring and better adapting to rapidly changing network environments.

[0009] According to one embodiment of this application, the error vector amplitude is determined by the error vector amplitude estimation model after the amplitude distribution of the target signal is input into the error vector amplitude estimation model;

[0010] The amplitude distribution of the target signal is used to represent the frequency of the target signal's amplitude in each amplitude range.

[0011] In this embodiment, by inputting the amplitude distribution of the target signal into a preset error vector amplitude estimation model, the model can quickly estimate the error vector amplitude based on the frequency of the target signal amplitude in each amplitude range, thereby further improving the calculation speed and accuracy.

[0012] According to one embodiment of this application, the amplitude distribution of the target signal is obtained by performing digital signal processing on the target signal and then calculating the amplitude.

[0013] In this embodiment, digital signal processing of the target signal is performed using digital signal processing technology, which not only improves the integrity and accuracy of the signal, but also enhances the signal's anti-interference ability, making the amplitude distribution of the acquired target signal more accurate.

[0014] According to one embodiment of this application, the error vector magnitude estimation model is obtained by training a pre-built neural network model using a pre-built sample set;

[0015] The sample set uses the amplitude distribution of signal sequences in the optical network as training samples, and the label of the training samples is the error vector amplitude of the signal sequences.

[0016] In this embodiment, by employing machine learning techniques, the amplitude distribution of signal sequences in the optical network is used as training samples and input into the neural network model. Since the transmission quality of different signals and the impairment of the communication system can be reflected in the amplitude distribution, the neural network model can better learn the relationship between signal features and error vector amplitude, resulting in a model that can estimate the error vector amplitude of new signal sequences. The generalization ability of the model enables the estimation process to adapt to different signal conditions and network environments, improving the robustness and accuracy of the estimated error vector amplitude.

[0017] According to one embodiment of this application, the signal sequence includes multiple signals of preset length obtained by splitting the sample signal of the optical network, and / or the signal sequence includes sample signals of preset length sampled by the optical network.

[0018] In this embodiment, by splitting the sample signal in the optical network into multiple signal sequences of preset length, or by directly sampling the sample signal of preset length, the processing speed and accuracy can be effectively improved in application scenarios that require real-time monitoring and analysis of signals.

[0019] According to one embodiment of this application, the sample signal is obtained by digital signal processing of a signal received by a receiver in an optical network.

[0020] According to one embodiment of this application, the digital signal processing includes at least one of dispersion compensation, clock recovery, and equalization.

[0021] In this embodiment, digital signal processing (DPS) is applied to the initial signal, including steps such as dispersion compensation, clock recovery, and equalization, which improves signal quality. Dispersion compensation corrects pulse broadening caused by medium dispersion during transmission, improving signal clarity. Clock recovery recovers the transmitting clock from the received signal, improving signal synchronization. Equalization adjusts the amplitude and phase of the signal to compensate for non-ideal characteristics during transmission. This DPS application not only improves signal integrity and accuracy but also enhances its anti-interference capabilities.

[0022] According to one embodiment of this application, the length of the target signal is the same as the length of the signal sequence.

[0023] In this embodiment, the length of the target signal is consistent with the length of the signal sequence of the sample used in the training model, which ensures consistency between the training data and the actual monitored signal, thereby improving the estimation accuracy of the model.

[0024] According to one embodiment of this application, the error vector magnitude estimation model is constructed based on a feedforward neural network or a convolutional neural network.

[0025] In this embodiment, a feedforward neural network or a convolutional neural network is used as the basis for constructing the error vector magnitude estimation model. Feedforward neural networks, with their simple hierarchical structure and ease of implementation, can quickly learn and identify signal features while consuming relatively little energy. Convolutional neural networks, on the other hand, can capture local features and automatically learn the local dependencies of signals, making them very suitable for processing signal data with spatial or temporal correlations, and offering high accuracy.

[0026] According to one embodiment of this application, the target signal includes a signal with one or more modulation formats.

[0027] In this embodiment, by receiving a target signal containing multiple different modulation formats, it is possible to more flexibly adapt to different transmission requirements and network conditions, thereby improving the adaptability of optical performance monitoring.

[0028] According to one embodiment of this application, the target signal includes a signal of a preset length extracted from the signal of the optical network within the at least part of the monitoring duration, and / or, the target signal includes a signal of a preset length detected by the optical network within the at least part of the monitoring duration.

[0029] In this embodiment, by acquiring signals within at least a portion of the monitoring duration within the monitoring period and extracting a preset length of signal from this portion of the monitoring duration as the target signal, or by directly acquiring a preset length of signal within at least a portion of the monitoring duration as the target signal, unnecessary data processing can be reduced. This enables the estimation of signal quality for the monitoring period using a shorter signal sequence, eliminating the need to calculate a large number of data points for the entire signal, and further improving the efficiency of optical performance monitoring.

[0030] Secondly, this application provides an electronic device, comprising:

[0031] A transceiver module is used to acquire target signals from an optical network; the target signals include signals from the optical network during at least a portion of the monitoring duration of the monitoring period.

[0032] The processing module is used to determine the signal quality of the optical network within the monitoring period of the target signal based on the error vector magnitude of the target signal.

[0033] The electronic device according to this application acquires a target signal of an optical network; the target signal includes the signal of the optical network within at least a portion of the monitoring duration of a monitoring period; and determines the signal quality of the optical network within the monitoring period containing the target signal based on the error vector magnitude of the target signal. This embodiment of the application acquires the signal of the optical network within at least a portion of the monitoring duration of a monitoring period, where this portion of the signal represents a part of the monitoring period, rather than the entire monitoring period, and determines the signal quality of the monitoring period based on the error vector magnitude of this portion of the signal. This achieves the estimation of signal quality for a monitoring period using a shorter signal sequence, eliminating the need to calculate a large number of data points for the entire monitoring period, thus improving the efficiency of optical performance monitoring and better adapting to rapidly changing network environments.

[0034] Thirdly, this application provides an electronic device including a processor connected to a memory storing a computer program executable on the processor, wherein the processor executes the computer program to implement the optical performance monitoring method as described in the first aspect above.

[0035] Fourthly, this application provides an electronic device with light receiving function, the electronic device including the electronic device described in the second or third aspect above.

[0036] Fifthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the optical performance monitoring method as described in the first aspect above.

[0037] In a sixth aspect, this application provides a chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the optical performance monitoring method as described in the first aspect above.

[0038] In a seventh aspect, this application provides a computer program product, including a computer program that, when executed by a processor, implements the optical performance monitoring method as described in the first aspect above.

[0039] Eighthly, this application provides a vehicle that includes the electronic device described in the second or third aspect above, or the vehicle includes an electronic device with light receiving function as described in the fourth aspect above.

[0040] The above-described one or more technical solutions in the embodiments of this application have at least one of the following technical effects:

[0041] According to the optical performance monitoring method of this application, a target signal of an optical network is acquired; the target signal includes the signal of the optical network within at least a portion of the monitoring duration of a monitoring period; and the signal quality of the optical network within the monitoring period containing the target signal is determined based on the error vector magnitude of the target signal. This embodiment of the application acquires the signal of the optical network within at least a portion of the monitoring duration of a monitoring period, where this portion of the signal represents a part of the monitoring period, rather than the entire monitoring period, and determines the signal quality of the monitoring period based on the error vector magnitude of this portion of the signal. This achieves the estimation of signal quality for the monitoring period using a shorter signal sequence, eliminating the need to calculate a large number of data points for the entire monitoring period, thus improving the efficiency of optical performance monitoring and better adapting to rapidly changing network environments.

[0042] Furthermore, in some embodiments, by inputting the amplitude distribution of the target signal into a preset error vector amplitude estimation model, the model can quickly estimate the error vector amplitude based on the frequency of the target signal amplitude in each amplitude range, thereby further improving the calculation speed and accuracy.

[0043] Furthermore, in some embodiments, digital signal processing is performed on the target signal using digital signal processing technology, which not only improves the integrity and accuracy of the signal, but also enhances the signal's anti-interference ability, making the amplitude distribution of the acquired target signal more accurate.

[0044] Furthermore, in some embodiments, machine learning techniques are employed to input the amplitude distribution of signal sequences in the optical network as training samples into the neural network model. Since the transmission quality of different signals and the impairment of the communication system can be reflected in the amplitude distribution, the neural network model can better learn the relationship between signal features and error vector amplitude, resulting in a model capable of estimating the error vector amplitude of new signal sequences. The model's generalization ability enables the estimation process to adapt to different signal conditions and network environments, improving the robustness and accuracy of the estimated error vector amplitude.

[0045] Furthermore, in some embodiments, by splitting the sample signal in the optical network into multiple signal sequences of preset length, or by directly sampling a sample signal of preset length, the processing speed and accuracy can be effectively improved in application scenarios that require real-time monitoring and analysis of signals.

[0046] Furthermore, in some embodiments, digital signal processing (DPS) techniques are used to process the initial signal, including steps such as dispersion compensation, clock recovery, and equalization. This improves signal quality. Dispersion compensation corrects pulse broadening caused by medium dispersion during transmission, improving signal clarity. Clock recovery recovers the transmitting clock from the received signal, improving signal synchronization. Equalization adjusts the amplitude and phase of the signal to compensate for non-ideal characteristics during transmission. DPS processing of the initial signal not only improves signal integrity and accuracy but also enhances its anti-interference capabilities.

[0047] Furthermore, in some embodiments, the length of the target signal is consistent with the length of the signal sequence of the samples used in training the model, thereby improving the consistency between the training data and the actual monitored signal and thus improving the estimation accuracy of the model.

[0048] Furthermore, in some embodiments, feedforward neural networks or convolutional neural networks are used as the basis for constructing the error vector magnitude estimation model. Feedforward neural networks, with their simple hierarchical structure and ease of implementation, can quickly learn and identify signal features while consuming less energy. Convolutional neural networks, on the other hand, can capture local features and automatically learn the local dependencies of signals, making them very suitable for processing signal data with spatial or temporal correlations, and offering high accuracy.

[0049] Furthermore, in some embodiments, by receiving a target signal containing multiple different modulation formats, it is possible to more flexibly adapt to different transmission requirements and network conditions, thereby improving the adaptability of optical performance monitoring.

[0050] Furthermore, in some embodiments, by acquiring signals within at least a portion of the monitoring duration within the monitoring period and extracting a signal of a preset length from this portion of the monitoring duration as the target signal, or by directly acquiring a signal of a preset length within at least a portion of the monitoring duration as the target signal, unnecessary data processing can be reduced. This enables the estimation of signal quality for the monitoring period using a shorter signal sequence, eliminating the need to calculate a large number of data points for the entire signal, and further improving the efficiency of optical performance monitoring.

[0051] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0052] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a schematic flowchart of the optical performance monitoring method provided in the embodiments of this application;

[0054] Figure 2 This is a schematic diagram illustrating the principle of neural network model training provided in the embodiments of this application;

[0055] Figure 3 This is a schematic diagram of GPU power consumption for optical performance monitoring using different neural networks, provided in an embodiment of this application.

[0056] Figure 4 This is a performance diagram of different error vector magnitude estimation models provided in the embodiments of this application;

[0057] Figure 5 This is a schematic diagram of the signal transmission process provided in an embodiment of this application;

[0058] Figure 6 These are amplitude histograms of signals with different modulation formats at different transmission distances, as provided in the embodiments of this application.

[0059] Figure 7 The EVM is the estimated result of a QPSK modulation format signal provided in the embodiments of this application when the transmission distance and OSNR change;

[0060] Figure 8 The EVM is the estimated result of a 16QAM modulation format signal provided in the embodiments of this application when the transmission distance and OSNR change;

[0061] Figure 9 The EVM is the estimated result of a 64QAM modulation format signal provided in the embodiments of this application when the transmission distance and OSNR change;

[0062] Figure 10 This is a schematic diagram illustrating optical performance monitoring during a monitoring period, provided in an embodiment of this application.

[0063] Figure 11 This is a schematic diagram of signal processing during the optical performance monitoring process provided in the embodiments of this application;

[0064] Figure 12 This is one of the structural schematic diagrams of the electronic device provided in the embodiments of this application;

[0065] Figure 13 This is the second schematic diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0066] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0067] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0068] With the continuous growth of bandwidth demands, optical networks are evolving into highly flexible and configurable elastic optical networks to adapt to different application scenarios and traffic requirements. Such networks can dynamically allocate resources to optimize network performance and meet user needs. Optical performance monitoring is a crucial link in maintaining efficient network operation and troubleshooting, accurately and in real-time monitoring the quality of optical signals, which helps to identify and resolve problems promptly. The most intuitive metric for evaluating signal quality is the bit error rate (BER); a lower BER indicates better signal quality. Existing optical performance monitoring technologies typically use the optical signal-to-noise ratio (OSNR) to assist in estimating the BER. OSNR measures the ratio of signal power to noise power; generally, a higher OSNR is considered to indicate better signal quality and a lower BER. However, in related technologies, OSNR is usually estimated by monitoring the OSNR, but OSNR calculation requires the entire signal acquisition process and is time-consuming. In today's rapidly changing network environment, the response speed of this method may not meet the monitoring needs.

[0069] To address at least one of the aforementioned technical problems, this application proposes a method, apparatus, device, vehicle, medium, and program product for monitoring optical performance. The following, in conjunction with the accompanying drawings, provides a detailed description of the optical performance monitoring method, apparatus, device, vehicle, medium, and program product provided by the embodiments of this application through specific examples and application scenarios.

[0070] Among them, the optical performance monitoring method can be applied to the terminal, and can be executed by the hardware or software in the terminal.

[0071] Optionally, the terminal may include, but is not limited to, portable communication devices such as mobile phones or tablets with touch-sensitive surfaces (e.g., touchscreen displays and / or touchpads). It should also be understood that in some embodiments, the terminal may not be a portable communication device, but rather a desktop computer with touch-sensitive surfaces (e.g., touchscreen displays and / or touchpads). In some embodiments, the terminal may also be an optical receiver with a processor, a fiber optic switch, etc.

[0072] However, it should be understood that a terminal may include one or more other physical user interface devices such as a physical keyboard, mouse, and joystick.

[0073] The optical performance monitoring method provided in this application embodiment can be executed by an electronic device or a functional module or entity in an electronic device that can implement the optical performance monitoring method. The electronic device mentioned in this application embodiment may include, but is not limited to, a server, an ECU (Electronic Control Unit), an MCU (Microcontroller Unit), or other controllers. The optical performance monitoring method provided in this application embodiment will be described below using an electronic device as the execution subject as an example.

[0074] like Figure 1 As shown, the optical performance monitoring method includes steps 110 and 120.

[0075] Step 110: Acquire the target signal of the optical network; the target signal includes the signal of the optical network during at least a portion of the monitoring duration of the monitoring cycle.

[0076] In optical networks, a signal refers to an information carrier transmitted through optical fiber, typically a light wave generated by a laser or other light source. These light waves can encode information such as voice, video, and data, and are transmitted to the receiving end via optical fiber.

[0077] A signal can be a sequence of symbols, represented in complex number form. The representation varies depending on the modulation format. The modulation format, in a digital communication system, refers to the method used to convert digital signals (such as binary data) into a signal format suitable for transmission over a medium (such as optical fiber or radio waves). Common modulation formats include Quadrature Phase Shift Keying (QPSK) and Multiple Quadrature Amplitude Modulation (MQAM). MQAM can be 16QAM, 64QAM, etc. In signals modulated by different formats, each symbol represents different bits of information. For example, in 16QAM, each symbol represents 4 bits of information, combining changes in signal phase and amplitude; in 64QAM, each symbol represents 6 bits of information, combining more phase and amplitude changes; and in QPSK, each symbol represents 2 bits, using two quadrature phases to transmit data. For example, for a bit string [1,0,1,1,0,1], after modulation, the bits can be mapped to symbols. For example, in 16QAM modulation, 4 bits can be mapped to one symbol. The complex form of the signal is represented as: signal S = [3+3j, 1-1j, -1+3j, ...], where j is the imaginary unit.

[0078] It should be noted that signals with different modulation formats can be represented by different constellation diagrams. Constellation diagrams are typically represented on a two-dimensional plane, with the horizontal axis representing the I (in-phase) component and the vertical axis representing the Q (quadrature) component. A constellation diagram includes multiple constellation points. Specifically, a QPSK constellation diagram contains 4 constellation points, while a 16QAM constellation diagram contains 16. The position of the constellation points is determined by the amplitude and phase of the signal. In QPSK, the constellation points are located at the intersection of the I and Q axes, while in MQAM, the constellation points are distributed across different amplitudes and phases. For a given signal, a constellation diagram can be used to represent that signal segment. For example, the symbols of the signal can be mapped onto constellation points; the same symbol can be mapped to the same constellation point, and different symbols can be mapped to different constellation points.

[0079] In this embodiment of the application, the target signal of the optical network can be acquired by a receiver in the optical network. For example, the receiver can be a digital coherent receiver, which can detect optical signals in the optical network and convert these optical signals into electrical signals for output.

[0080] The monitoring period is the time range within which the performance of an optical network is monitored. The monitoring period can be fixed, such as every 10 minutes or 15 minutes, or it can be dynamic, adjusted according to the needs and conditions of the network.

[0081] In this embodiment of the application, within the monitoring period, signals within at least a portion of the monitoring duration of the monitoring period can be acquired as target signals.

[0082] Step 120: Determine the signal quality of the optical network within the monitoring period of the target signal based on the error vector amplitude of the target signal.

[0083] Error Vector Magnitude (EVM) is a metric for measuring the quality of a modulated signal, describing the degree of deviation between the modulated signal and the ideal signal.

[0084] In this embodiment, the modulation format of the target signal is first determined. Then, an ideal signal is generated according to the modulation format. The magnitude of the error vector between the target signal and the ideal signal is then calculated to obtain the error vector magnitude of the target signal. For example, if the modulation format is 16QAM, a corresponding ideal signal for 16QAM is generated; if the modulation format is 64QAM, a corresponding ideal signal for 64QAM is generated. Then, the error vector between each symbol in the target signal and each symbol in the ideal signal is calculated to obtain the error vector magnitude. The calculated error vector magnitude can be converted to a percentage or decibel (dB) form as needed.

[0085] In this embodiment, since the target signal is a signal within at least a portion of the monitoring duration within the monitoring period, when the error vector amplitude of the target signal is small, it can be predicted that the error vector amplitude of the signal within the monitoring period is also small. In this case, the signal quality within the monitoring period is high. Conversely, when the error vector amplitude of the target signal is large, it can be predicted that the error vector amplitude of the signal within the monitoring period is also large. In this case, the signal quality within the monitoring period is low.

[0086] Of course, in order to improve the accuracy of determining the signal quality within the monitoring period, in addition to determining the error vector amplitude of the target signal, the signal quality within the monitoring period can also be comprehensively determined by combining indicators such as the optical signal-to-noise ratio and bit error rate of the target signal.

[0087] According to the optical performance monitoring method of this application, a target signal of the optical network is acquired; the target signal includes the signal of the optical network within at least a portion of the monitoring duration of the monitoring period; and the signal quality of the optical network within the monitoring period containing the target signal is determined based on the error vector amplitude of the target signal. This embodiment of the application acquires the signal of the optical network within at least a portion of the monitoring duration of the monitoring period, where this portion of the signal represents a part of the monitoring period, rather than the entire monitoring period, and determines the signal quality of the monitoring period based on the error vector amplitude of this portion of the signal. This achieves the estimation of the signal quality of the monitoring period using a shorter signal sequence, eliminating the need to calculate a large number of data points for the entire monitoring period, thus improving the efficiency of optical performance monitoring and better adapting to rapidly changing network environments.

[0088] In some embodiments, the error vector magnitude is determined by the error vector magnitude estimation model after the amplitude distribution of the target signal is input into the error vector magnitude estimation model;

[0089] The amplitude distribution of the target signal is used to represent the frequency of the target signal's amplitude in each amplitude range.

[0090] In some embodiments, amplitude distribution represents the frequency of different amplitudes occurring in various amplitude intervals. Amplitude distribution can be represented by vectors, amplitude histograms (AH), tables, sequences, etc. Taking amplitude distribution represented by amplitude histograms as an example, each bar in the amplitude histogram represents an amplitude interval, and the height of the bar represents the frequency of amplitude values ​​occurring within that interval.

[0091] In amplitude distribution, the number and range of amplitude intervals can be preset or determined based on the amplitude range of the target signal. For example, the number of amplitude intervals can be predefined, such as 8, 16, 32, or 64. Then, combined with the maximum and minimum amplitudes of the target signal, the range of the amplitude intervals is determined based on the number of intervals. For example, if the amplitude range of the target signal is 1-200 and the number of amplitude intervals is 8, then the amplitude range of 0-200 can be divided into 8 equal parts, with each interval consisting of 25 amplitude units.

[0092] In this embodiment, the amplitude of the signal can be calculated based on its complex form, thereby performing amplitude transformation on the target signal to obtain its amplitude distribution. Specifically, the amplitude can be obtained by taking the modulus of the complex sign of the signal according to the following formula:

[0093] |M i |=|a+bj|

[0094] Among them, M iLet represent the target signal, 'a' represent the real part of the signal, which is related to the signal amplitude, 'b' represent the imaginary part of the signal, which is related to the signal phase, and 'j' be the imaginary unit.

[0095] In this embodiment, the amplitude distribution of the target signal can be input into a preset error vector amplitude estimation model to obtain the error vector amplitude output by the error vector amplitude estimation model. The error vector amplitude estimation model is a model trained using a machine learning algorithm. This model can analyze the amplitude distribution and thus output an estimated value of the error vector amplitude.

[0096] In this embodiment, by inputting the amplitude distribution of the target signal into a preset error vector amplitude estimation model, the model can quickly estimate the error vector amplitude based on the frequency of the target signal amplitude in each amplitude range, thereby further improving the calculation speed and accuracy.

[0097] The amplitude distribution of the target signal is obtained by performing amplitude calculation after digital signal processing of the target signal.

[0098] In this embodiment, the target signal may be affected by various factors during transmission, such as dispersion, clock skew, and channel distortion. To restore the original characteristics of the signal and improve its quality, digital signal processing is required, including dispersion compensation, clock recovery, and equalization. The amplitude distribution of the digitally processed target signal is then calculated.

[0099] In this embodiment, digital signal processing of the target signal is performed using digital signal processing technology, which not only improves the integrity and accuracy of the signal, but also enhances the signal's anti-interference ability, making the amplitude distribution of the acquired target signal more accurate.

[0100] In some embodiments, the error vector magnitude estimation model is obtained by training a pre-built neural network model using a pre-built sample set;

[0101] The sample set uses the amplitude distribution of signal sequences in the optical network as training samples, and the label of the training samples is the error vector amplitude of the signal sequence.

[0102] In this embodiment, a sample set can be constructed using signal sequences in an optical network, with the amplitude distribution of the signal sequences serving as training samples and the error vector amplitude of the signal sequences serving as the labels of the training samples.

[0103] Specifically, for a signal sequence in an optical network, its amplitude can be obtained by taking its modulus. These amplitude values ​​are then grouped according to amplitude intervals, for example, into 64 intervals. The frequency of these amplitude values ​​within these intervals is determined, thus obtaining the amplitude distribution of the signal sequence. This amplitude distribution can be represented by a vector x of size 64×1. i express.

[0104] In this embodiment, the amplitude distribution of a signal sequence can be used as a sample, and the label of this sample is the true error vector amplitude of the signal sequence. A sample set is constructed by acquiring the amplitude distribution of multiple signal sequences. This sample set is then divided into a training set, a validation set, and a test set according to a preset ratio to train the neural network model. Taking an amplitude histogram to represent the amplitude distribution as an example, the training principle is as follows: Figure 2 As shown.

[0105] Specifically, first, the parameters in the neural network model, such as weights and biases, can be initialized. Then, the training set is input into the neural network model, and forward propagation calculations are performed. i The output value is obtained through calculation by the neural network model. Specifically, each neuron in the m hidden layers of the neural network model receives the output value from the previous m-1 layers and generates another output value, which is then passed to the next layer.

[0106] a m =f m (W m ·a m-1 +b m )

[0107] Among them, a m W represents the output value of layer m. m b represents the weight from layer m-1 to layer m. m This represents the deviation from layer m-1 to layer m. m () denotes the activation function of m layers. Then, the loss function is calculated, which is the difference between the estimated EVM and the true EVM. For example, the mean squared logarithmic error (MSLE) can be used as the loss function to capture small estimation errors.

[0108]

[0109] EVMt i This refers to the actual EVM, EVMe. i This represents the estimated EVM.

[0110] Of course, loss functions can also be calculated in other ways, such as minimum mean squared error (MMSE) and mean absolute error (MAE).

[0111] Next, backpropagation is performed based on the calculated loss function value to calculate the gradient of each neuron and update the weights, biases, and other parameters of the neural network model to reduce the value of the loss function. Forward and backpropagation are repeated, continuously updating the weights, biases, and other parameters of the neural network model, until the number of iterations reaches a preset value or the gradient no longer decreases. At this point, training stops, and the error vector magnitude estimation model is obtained.

[0112] In this embodiment, by employing machine learning techniques, the amplitude distribution of signal sequences in the optical network is used as training samples and input into the neural network model. Since the transmission quality of different signals and the impairment of the communication system can be reflected in the amplitude distribution, the neural network model can better learn the relationship between signal features and error vector amplitude, resulting in a model that can estimate the error vector amplitude of new signal sequences. The generalization ability of the model enables the estimation process to adapt to different signal conditions and network environments, improving the robustness and accuracy of the estimated error vector amplitude.

[0113] In some embodiments, the signal sequence includes multiple signals of a preset length obtained by splitting the sample signal of the optical network, and / or the signal sequence includes sample signals of a preset length sampled by the optical network.

[0114] In this embodiment, different signals in the optical network can be acquired as sample signals, and the sample signals can be split. For example, for sample signal S1(k), the signal can be split to obtain multiple signal sequences M1, M2, ..., M of preset length. k The preset length can be a predetermined length or a length determined based on the modulation format of the sample signal. For example, the length of the signal sequence can be N symbols / cluster, where the cluster is equal to the modulation order. The modulation order is equal to the number of constellation points in the constellation diagram. The modulation order describes the number or complexity of the modulated signal states and is usually related to the representational power of the modulation format. It defines the number of bits that each modulation symbol can carry. For example, the modulation order of QPSK is 4, 16QAM is 16, and 64QAM is 64.

[0115] In this embodiment, a sample signal of a preset length can also be directly obtained as a signal sequence.

[0116] In this embodiment, by splitting the sample signal in the optical network into multiple signal sequences of preset length, or by directly sampling the sample signal of preset length, the processing speed and accuracy can be effectively improved in application scenarios that require real-time monitoring and analysis of signals.

[0117] In some embodiments, a neural network model can be constructed based on a feedforward neural network or a convolutional neural network, or based on a variation of a convolutional neural network or other neural networks.

[0118] like Figure 3 As shown, Figure 3 The image shows GPU (Graphics Processing Unit) power consumption records for monitoring optical performance using error vector magnitude estimation models obtained by constructing neural network models using Feedforward Neural Networks (FFNN) and Convolutional Neural Networks (CNN). It can be observed that the FFNN approach not only has a shorter runtime but also reduces average GPU power consumption by half. Compared to the CNN approach, the low-complexity FFNN estimation saves 95% of energy.

[0119] Figure 4 The performance comparison of error vector magnitude estimation models obtained through different training schemes is shown, where the Mean Absolute Error (MAE) is defined as:

[0120]

[0121] Among them, EVMt i This refers to the actual EVM, EVMe. i Let represent the estimated EVM, and k represent the estimated quantity.

[0122] pass Figure 4It can be seen that with 8 bins (i.e., 8 amplitude intervals in the amplitude histogram (AH)), a MAE value below 0.5% can be achieved when the signal sequence length N symbols / N = 100 in the cluster. However, the estimation accuracy is lower for lower N values. After carrier phase recovery (CPR) of the signal, using the signal's constellation diagram (IQ) as input, the CNN-based error vector amplitude estimation model provides the most accurate EVM estimation. Before CPR, the MAE value of the EVM estimation using the error vector amplitude estimation model is also low. Specifically, when the signal sequence length N symbols / N = 100 in the cluster, using an 8-bin amplitude histogram as model input, the accuracy of EVM estimation using the FFNN and CNN schemes is similar.

[0123] In this embodiment, a feedforward neural network or a convolutional neural network is used as the basis for constructing the error vector magnitude estimation model. Feedforward neural networks, with their simple hierarchical structure and ease of implementation, can quickly learn and identify signal features while consuming relatively little energy. Convolutional neural networks, on the other hand, can capture local features and automatically learn the local dependencies of signals, making them very suitable for processing signal data with spatial or temporal correlations, and offering high accuracy.

[0124] In some embodiments, the sample signal is obtained by digitally processing the signal received by the receiver in the optical network.

[0125] In some embodiments, digital signal processing includes at least one of dispersion compensation, clock recovery, and equalization.

[0126] In this embodiment, the signal received by the receiver may be affected by various factors during transmission, such as dispersion, clock skew, and channel distortion. Digital signal processing is required to restore the original characteristics of the signal and improve its quality.

[0127] In this embodiment, since the training process does not depend on real-time signal processing, the signal received by the receiver can be processed offline to obtain the processed sample signal.

[0128] In this embodiment, digital signal processing (DPS) is applied to the initial signal, including steps such as dispersion compensation, clock recovery, and equalization, which improves signal quality. Dispersion compensation corrects pulse broadening caused by medium dispersion during transmission, improving signal clarity. Clock recovery recovers the transmitting clock from the received signal, improving signal synchronization. Equalization adjusts the amplitude and phase of the signal to compensate for non-ideal characteristics during transmission. This DPS application not only improves signal integrity and accuracy but also enhances its anti-interference capabilities.

[0129] In some embodiments, the length of the target signal is the same as the length of the signal sequence.

[0130] In this embodiment, the length of the target signal is consistent with the length of the signal sequence of the sample used in the training model, which ensures consistency between the training data and the actual monitored signal, thereby improving the estimation accuracy of the model.

[0131] In some embodiments, the target signal includes a signal in one or more modulation formats.

[0132] In this embodiment, the target signal may include signals with one or more modulation formats, and the sample signals used to train the model may also be signals with one or more different modulation formats. An example illustrating the source of the sample signal in this embodiment is as follows: Figure 5 As shown, in the signal generation process at the transmitting end, a pseudo-random binary sequence (PRBS) is first generated, which is then mapped to the corresponding modulation format using Gray coding. Next, a Nyquist pulse shaper with a roll-off factor of 0.15 is used to filter complex symbols, generating 28Gbaud and 32Gbaud signals. The generated signals are then resampled to 50GSa / s to meet the rate requirements of subsequent processing stages.

[0133] The resampled signal is loaded by two synchronous arbitrary waveform generators (AWGs), such as the Tektronix AWG70001A with a sampling rate of 50 GSa / s. The in-phase (I) and quadrature (Q) electrical signals at the AWG output are amplified by a pair of linear amplifiers, such as the SHF827. These amplified in-phase and quadrature electrical signals are then modulated onto a continuous wave (CW) optical carrier emitted by an external cavity laser (wavelength 1550.2 nm, output power 10 dBm) through an IQ modulator with a bandwidth of 3 dB, thus obtaining the modulated optical signal.

[0134] To compensate for signal loss caused by the IQ modulator during modulation, an erbium-doped fiber amplifier (EDFA) was used to compensate for the modulation loss of the IQ modulator. Finally, the modulated optical signal was received by a coherent receiver. This receiver included a balanced coherent receiver front-end, a 200kHz local oscillator (LO) laser, and a real-time digital storage oscilloscope (DSO), model Keysight DSOX93304Q, with a sampling rate of 80 GSa / s and a bandwidth of 33 GHz, used for real-time acquisition and analysis of the received signal.

[0135] The above method can be used to acquire signals with different modulation formats, and then these signals can be processed offline by DSP to obtain sample signals.

[0136] Since the effective transmission distance of signals with different modulation formats varies—for example, the effective transmission distance of QPSK is 2000km—the signal accuracy deteriorates beyond this distance. In this embodiment, signals can be acquired within the effective transmission distance of the modulation format; for example, signals can be acquired at intervals within the effective distance, thereby diversifying the sample signals and improving the model's generalization ability. The amplitude histograms of signals with different modulation formats at different transmission distances are shown below. Figure 6 As shown.

[0137] Figure 7-9 The paper compares the estimation results and actual values ​​of the error vector amplitude estimation model based on FFNN for three modulation formats under varying transmission distances and OSNRs. The measured OSNR values ​​are also displayed on the x-axis of the graph. When the signal sequence length is 100 symbols / cluster, the amplitude histogram of 64 bins achieves a normalized MAE of less than 6.7% (QPSK), 2.4% (16QAM), and 2.1% (64QAM). Therefore, when training the neural network model, using a signal sequence of length 100 symbols / cluster and dividing the amplitude histogram into 64 amplitude intervals results in higher accuracy of the estimated EVM value.

[0138] In this embodiment, the receiver receives signals containing multiple different modulation formats, which significantly improves the diversity and representativeness of the sample signals. This enables the trained error vector amplitude estimation model to learn the signal changes brought about by different modulation formats, thereby improving the model's generalization ability and accuracy.

[0139] In this embodiment, by receiving a target signal containing multiple different modulation formats, it is possible to more flexibly adapt to different transmission requirements and network conditions, thereby improving the adaptability of optical performance monitoring.

[0140] In some embodiments, the target signal includes a signal of a predetermined length extracted from the signal of the optical network within at least a portion of the monitoring duration, and / or the target signal includes a signal of a predetermined length detected by the optical network within at least a portion of the monitoring duration.

[0141] In this embodiment, such as Figure 10 As shown, during the monitoring of optical performance, multiple monitoring cycles can be set, such as every 10 minutes, 15 minutes, etc., or the cycle can be dynamic and adjusted according to network needs and conditions. Within a monitoring cycle, one or more shorter time periods can be selected as observation phases. The duration of the observation phase should be shorter than the duration of the monitoring cycle; that is, the observation phase is a portion of the detection time within the monitoring cycle. This allows for the selection of time periods with different network loads or conditions for analysis. Figure 10 As shown, the initial stage of a monitoring cycle can be used as the observation stage, and observations can be performed every preset duration, which is the monitoring cycle.

[0142] In this embodiment, a signal of a preset length can be extracted from the signal during the observation phase as the target signal, or the signal of a preset length during the observation phase can be directly obtained as the target signal.

[0143] During the observation phase, such as Figure 11 As shown, a coherent receiver can be used to capture signals from an optical network. The captured signals can be processed offline using DSP, such as dispersion compensation, clock recovery, and equalization, to obtain the target signal. Then, the amplitude distribution of the target signal is input into the error vector amplitude estimation model to obtain the EVM value output by the model.

[0144] Of course, carrier phase recovery can also be performed on the target signal before inputting the amplitude distribution of the target signal into the error vector amplitude estimation model, so as to improve the integrity of the target signal and make the output EVM value more accurate.

[0145] In this embodiment, the bit error rate of the target signal can also be calculated, and the signal quality within the monitoring period can be comprehensively determined by combining the bit error rate and the EVM value.

[0146] In this embodiment, by acquiring signals within at least a portion of the monitoring duration within the monitoring period and extracting a preset length of signal from this portion of the monitoring duration as the target signal, or by directly acquiring a preset length of signal within at least a portion of the monitoring duration as the target signal, unnecessary data processing can be reduced. This enables the estimation of signal quality for the monitoring period using a shorter signal sequence, eliminating the need to calculate a large number of data points for the entire signal, and further improving the efficiency of optical performance monitoring.

[0147] The optical performance monitoring method provided in this application can be executed by an electronic device. This application uses an electronic device executing the optical performance monitoring method as an example to illustrate the electronic device provided in this application.

[0148] This application also provides an electronic device.

[0149] like Figure 12 As shown, the electronic device includes:

[0150] The transceiver module 1210 is used to acquire the target signal of the optical network; the target signal includes the signal of the optical network during at least a portion of the monitoring duration of the monitoring period;

[0151] The processing module 1220 is used to determine the signal quality of the optical network within the monitoring period of the target signal based on the error vector amplitude of the target signal.

[0152] The electronic device according to this application acquires a target signal of an optical network; the target signal includes the signal of the optical network within at least a portion of the monitoring duration of a monitoring period; and determines the signal quality of the optical network within the monitoring period containing the target signal based on the error vector amplitude of the target signal. This embodiment of the application acquires the signal of the optical network within at least a portion of the monitoring duration of a monitoring period, where this portion of the signal represents a part of the monitoring period, rather than the entire monitoring period, and determines the signal quality of the monitoring period based on the error vector amplitude of this portion of the signal. This achieves the estimation of signal quality for the monitoring period using a shorter signal sequence, eliminating the need to calculate a large number of data points for the entire monitoring period, thus improving the efficiency of optical performance monitoring and better adapting to rapidly changing network environments.

[0153] The electronic device in this application embodiment can be a terminal or other devices besides a terminal. For example, the electronic device can be an in-vehicle electronic device, a mobile internet device (MID), a robot, an ultra-mobile personal computer (UMPC), an ECU (Electronic Control Unit), an MCU (Microcontroller Unit), or other controllers, and can also be a server, network attached storage (NAS), a personal computer (PC), a television set (TV), an ATM, or a self-service machine, etc. This application embodiment does not specifically limit the scope.

[0154] The electronic device in this application embodiment can be a device with an operating system. This operating system can be a Microsoft (Windows) operating system, an Android operating system, an iOS operating system, or other possible operating systems; this application embodiment does not specifically limit the specific operating system.

[0155] In some embodiments, such as Figure 13 As shown, this application embodiment also provides an electronic device 1300, including a processor 1301, the processor 1301 being connected to a memory 1302, the memory 1302 storing a computer program that can run on the processor 1301. When the program is executed by the processor 1301, it implements the various processes of the above-described optical performance monitoring method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0156] It should be noted that the electronic devices in the embodiments of this application include the aforementioned mobile electronic devices and non-mobile electronic devices.

[0157] This application also provides an electronic device with optical receiving function, which includes the aforementioned electronic device. For example, the electronic device may be an optical receiver, a fiber optic switch, etc.

[0158] This application also provides a vehicle that includes the above-mentioned electronic device, or the vehicle includes the above-mentioned electronic device with light receiving function.

[0159] This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described optical performance monitoring method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0160] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0161] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described optical performance monitoring method.

[0162] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0163] This application also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above-described optical performance monitoring method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0164] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0165] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0166] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0167] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

[0168] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0169] Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.

Claims

1. A method of monitoring optical performance, characterized by, The method comprises: obtaining a target signal of an optical network; the target signal comprises signals of the optical network in at least part of a monitoring duration of a monitoring period; determining signal quality of the optical network in the monitoring period in which the target signal is located according to an error vector magnitude of the target signal.

2. The method of claim 1, wherein, The error vector magnitude is determined by an error vector magnitude estimation model after inputting an amplitude distribution of the target signal into the error vector magnitude estimation model; The amplitude distribution of the target signal is used to represent frequencies of amplitudes of the target signal in respective amplitude intervals.

3. The method of claim 2, wherein, The amplitude distribution of the target signal is obtained after performing digital signal processing on the target signal and then performing amplitude calculation.

4. The method according to claim 2 or 3, characterized in that, The error vector magnitude estimation model is obtained by training a pre-established neural network model using a pre-constructed sample set; The sample set takes an amplitude distribution of a signal sequence in an optical network as a training sample, and a label of the training sample is an error vector magnitude of the signal sequence.

5. The method of claim 4, wherein, The signal sequence comprises a plurality of signals of a preset length obtained by splitting a sample signal of the optical network, and / or the signal sequence comprises a sample signal of a preset length sampled from the optical network.

6. The method of claim 5, wherein, The sample signal is obtained by performing digital signal processing on a signal received by a receiver in the optical network.

7. The method according to claim 3 or 6, characterized in that, The digital signal processing comprises at least one of dispersion compensation, clock recovery, and equalization.

8. The method of claim 4, wherein, The length of the target signal is the same as the length of the signal sequence.

9. The method of claim 2 or 3, wherein, The error vector magnitude estimation model is constructed based on a feedforward neural network or a convolutional neural network.

10. The method according to any one of claims 1 to 3, characterized in that, The target signal comprises signals of one or more modulation formats.

11. The method according to any one of claims 1 to 3, characterized in that, The target signal comprises a signal of a preset length intercepted from signals of the optical network in the at least part of the monitoring duration, and / or the target signal comprises a signal of a preset length monitored by the optical network in the at least part of the monitoring duration.

12. An electronic device, comprising: The method comprises: The transceiver module is configured to obtain a target signal of an optical network; the target signal comprises signals of the optical network in at least part of a monitoring duration of a monitoring period; The processing module is configured to determine signal quality of the optical network in the monitoring period in which the target signal is located according to an error vector magnitude of the target signal.

13. An electronic device comprising a processor connected with a memory, the memory storing a computer program operable on the processor, characterized in that, The processor implements the method of any one of claims 1-11 when executing the program.

14. An electronic device with optical receiving function, characterized in that, The electronic device comprises the electronic apparatus of claim 12 or claim 13.

15. A vehicle characterized by comprising: The vehicle comprises the electronic apparatus of claim 12 or 13, or the vehicle comprises the electronic device of claim 14.

16. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the method of any one of claims 1-11.

17. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the method of any one of claims 1-11.

Images