CN115173940B - Method and system for monitoring link joint damage of multi-channel optical transmission system - Google Patents

Method and system for monitoring link joint damage of multi-channel optical transmission system Download PDF

Info

Publication number
CN115173940B
CN115173940B CN202210741672.2A CN202210741672A CN115173940B CN 115173940 B CN115173940 B CN 115173940B CN 202210741672 A CN202210741672 A CN 202210741672A CN 115173940 B CN115173940 B CN 115173940B
Authority
CN
China
Prior art keywords
amplitude
optical transmission
link joint
joint damage
channel
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210741672.2A
Other languages
Chinese (zh)
Other versions
CN115173940A (en
Inventor
罗风光
吉妍
杨柳
杨静宇
谭勇
王旭
陈聪
丁畅
邱天
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huazhong University of Science and Technology
Original Assignee
Huazhong University of Science and Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huazhong University of Science and Technology filed Critical Huazhong University of Science and Technology
Priority to CN202210741672.2A priority Critical patent/CN115173940B/en
Publication of CN115173940A publication Critical patent/CN115173940A/en
Application granted granted Critical
Publication of CN115173940B publication Critical patent/CN115173940B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
    • H04B10/07—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems
    • H04B10/075—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal
    • H04B10/079—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal using measurements of the data signal
    • H04B10/0795—Performance monitoring; Measurement of transmission parameters
    • H04B10/07953—Monitoring or measuring OSNR, BER or Q
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
    • H04B10/07—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems
    • H04B10/075—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal
    • H04B10/079—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal using measurements of the data signal
    • H04B10/0795—Performance monitoring; Measurement of transmission parameters
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Optical Communication System (AREA)

Abstract

The invention provides a method and a system for monitoring link joint damage of a multi-channel optical transmission system, wherein the method comprises the following steps: based on asynchronous sampling, acquiring I-path signal time domain data and Q-path signal time domain data of a receiving end of a target multi-channel coherent optical transmission system; determining an amplitude phase histogram vector based on the I-channel signal time domain data and the Q-channel signal time domain data; the amplitude phase histogram vector is used for representing the change of the I path signal and the Q path signal under the corresponding amplitude and phase states; inputting the amplitude phase histogram vector into an optical transmission link joint damage monitoring model, identifying a modulation format of a signal and determining link joint damage of a target multi-channel coherent optical transmission system; wherein the link joint impairment comprises: optical signal to noise ratio and nonlinear noise power. The method can reflect the amplitude damage and the phase damage of the signals at the same time, and realize the comprehensive monitoring of the damage of the optical signal link.

Description

Method and system for monitoring link joint damage of multi-channel optical transmission system
Technical Field
The invention relates to the technical field of optical communication, in particular to a method and a system for monitoring link joint damage of a multi-channel optical transmission system.
Background
Transmission impairments of optical signals in optical fiber links result from a variety of factors such as fiber dispersion, nonlinearity, etc. In a multi-channel fiber optic transmission link, the nonlinear impairments caused by the kerr effect include self-phase modulation, cross-phase modulation, and four-wave mixing. The self-phase modulation and the cross-phase modulation bring about phase damage to the optical signal, and the four-wave mixing brings about amplitude damage to the optical signal, which is represented by common degradation of the real part and the imaginary part of the complex signal.
The deep learning can automatically extract characteristic information from abstract data, has strong self-learning capability, effectively reduces manual intervention, can easily solve some key problems which are difficult to solve by using the traditional method, and is widely applied to the field of optical performance monitoring (Optical performance monitoring, OPM) at present. In order to detect the joint damage of the optical transmission link, the input of the deep learning model often selects an amplitude histogram, but the input can only reflect the change of the real part of the signal, the nonlinear damage is monitored according to the degradation of the signal amplitude information, the phase damage represented on the change of the imaginary part is ignored, and the link damage of the optical signal cannot be comprehensively reflected.
Therefore, how to provide a method and a system for monitoring the link joint damage of a multi-channel optical transmission system, and reflect the amplitude damage and the phase damage of signals at the same time, so as to realize the comprehensive monitoring of the damage of the optical signal link.
Disclosure of Invention
Aiming at the defects in the prior art, the embodiment of the invention provides a method and a system for monitoring the link joint damage of a multi-channel optical transmission system.
The invention provides a method for monitoring link joint damage of a multi-channel optical transmission system, which comprises the following steps: based on asynchronous sampling, acquiring I-path signal time domain data and Q-path signal time domain data of a receiving end of a target multi-channel coherent optical transmission system;
determining an amplitude phase histogram vector based on the I-channel signal time domain data and the Q-channel signal time domain data; the amplitude phase histogram vector is used for representing the change of the I path signal and the Q path signal under the corresponding amplitude and phase states;
inputting the amplitude phase histogram vector into an optical transmission link joint damage monitoring model, identifying a modulation format of a signal and determining link joint damage of a target multi-channel coherent optical transmission system; wherein the link joint impairment comprises: optical signal to noise ratio and nonlinear noise power.
According to the method for monitoring the joint damage of the multi-channel optical transmission system link, provided by the invention, the amplitude phase histogram vector is determined based on the I-path signal time domain data and the Q-path signal time domain data, and the method specifically comprises the following steps:
Converting the I-path signal time domain data and the Q-path signal time domain data into complex signals;
an amplitude-phase histogram vector is determined based on the amplitude and phase distribution of the complex signal. According to the method for monitoring the joint damage of the multi-channel optical transmission system link, which is provided by the invention, the amplitude phase histogram vector is determined according to the distribution condition of the amplitude and the phase of the complex signal, and the method specifically comprises the following steps:
determining a plurality of amplitude intervals according to the amplitude of the complex signal;
determining a plurality of phase intervals according to the phase change of the complex signal;
determining the number of times of occurrence of the complex signal in the amplitude interval and the phase interval according to the distribution condition of the amplitude and the phase of the complex signal based on the amplitude interval and the phase interval;
determining an amplitude phase histogram according to a preset histogram generation rule based on the occurrence times of complex signals in an amplitude interval and a phase interval;
the amplitude phase histogram is represented by a vector, and an amplitude phase histogram vector is determined.
According to the method for monitoring the joint damage of the multi-channel optical transmission system link, the optical transmission link joint damage monitoring model is a multi-task learning model; the optical transmission link joint damage monitoring model comprises: an input layer, a hidden layer and an output layer; the hidden layer comprises a plurality of neuron nodes; the input layer is connected with the neuron node;
inputting the amplitude phase histogram vector into an optical transmission link joint damage monitoring model, identifying a modulation format of a signal and determining link joint damage of a target multi-channel coherent optical transmission system, wherein the method specifically comprises the following steps of:
Transmitting the amplitude phase histogram vector into the hidden layer based on the input layer;
classifying different signal types in the amplitude phase histogram vector based on the hidden layer, and determining modulation format characteristic information;
determining link joint damage characteristic information according to the amplitude phase histogram vector based on the hidden layer;
And inputting the modulation format characteristic information and the link joint damage characteristic information into an output layer, and determining and outputting the modulation format and the link joint damage according to the output layer.
According to the method for monitoring the link joint damage of the multi-channel optical transmission system, before the steps of inputting the amplitude-phase histogram vector into the optical transmission link joint damage monitoring model, identifying the modulation format of the signal and determining the link joint damage of the target multi-channel coherent optical transmission system, the method further comprises the following steps: training an optical transmission link joint damage monitoring model;
Training an optical transmission link joint damage monitoring model, specifically comprising:
Determining an amplitude phase histogram vector sample data set based on sample I-path signal time domain data and sample Q-path signal time domain data obtained under the conditions of a plurality of different signal modulation formats, optical signal to noise ratios, transmitting power and optical fiber link lengths; wherein each set of data in the amplitude phase histogram vector sample dataset comprises: amplitude phase histogram vector and corresponding osnr, modulation format and nonlinear noise power;
training an optical transmission link joint damage monitoring model by using the amplitude phase histogram vector sample data set;
Based on the target loss function, the learning rate is adjusted by adopting a gradient descent optimization algorithm, gradient estimation and correction are carried out, network parameters of the optical transmission link joint damage monitoring model are updated, and iterative training is carried out on the optical transmission link joint damage monitoring model based on the updated network parameters until the optical transmission link joint damage monitoring model converges.
According to the method for monitoring the joint damage of the multi-channel optical transmission system link, provided by the invention, the amplitude phase histogram vector sample dataset is determined based on the sample I-path signal time domain data and the sample Q-path signal time domain data which are acquired under the conditions of a plurality of different signal modulation formats, optical signal to noise ratios, transmitting power and optical fiber link lengths, and the method specifically comprises the following steps:
constructing a corresponding target multi-channel coherent light transmission simulation system based on the target multi-channel coherent light transmission system;
Based on a target multi-channel coherent light transmission simulation system, acquiring a plurality of sample I-path signal time domain data and sample Q-path signal time domain data according to a target modulation format change type, an optical signal-to-noise ratio change range, a transmitting power change range and an optical fiber link length change range;
An amplitude phase histogram vector sample dataset is determined based on the number of sample I signal time domain data and the sample Q signal time domain data.
According to the method for monitoring the link joint damage of the multi-channel optical transmission system, provided by the invention, a corresponding target multi-channel coherent optical transmission simulation system is built based on the target multi-channel coherent optical transmission system, and the method specifically comprises the following steps:
acquiring link parameters and system parameters of a target multi-channel coherent light transmission system; wherein the link parameters include: attenuation coefficient, nonlinear refractive index and dispersion coefficient of the optical fiber; the system parameters include: link parameters, number of channels, and channel spacing;
Based on the link parameters and the system parameters, a corresponding target multi-channel coherent light transmission simulation system is built.
The invention also provides a system for monitoring the link joint damage of the multi-channel optical transmission system, which comprises: the device comprises a signal acquisition unit, a vector determination unit and a damage monitoring unit;
The signal acquisition unit is used for acquiring I-path signal time domain data and Q-path signal time domain data of a receiving end of the target multi-channel coherent optical transmission system based on asynchronous sampling;
The vector determining unit is used for determining an amplitude phase histogram vector based on the I-path signal time domain data and the Q-path signal time domain data; the amplitude phase histogram vector is used for representing the change of the I path signal and the Q path signal under the corresponding amplitude and phase states;
The damage monitoring unit is used for inputting the amplitude phase histogram vector into the optical transmission link joint damage monitoring model, identifying the modulation format of the signal and determining the link joint damage of the target multi-channel coherent optical transmission system; wherein the link joint impairment comprises: optical signal to noise ratio and nonlinear noise power.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the steps of any one of the multi-channel optical transmission system link joint damage monitoring methods when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of any of the multi-channel optical transmission system link joint impairment monitoring methods described above.
According to the method and the system for monitoring the joint damage of the multi-channel optical transmission system link, the time domain data of the I-path signal and the time domain data of the Q-path signal are obtained through asynchronous sampling, and the amplitude-phase histogram vector capable of representing the change of the I-path signal and the Q-path signal under the corresponding amplitude and phase states is determined based on the time domain data. The amplitude-phase histogram vector is used as a carrier of the characteristic information, the amplitude-phase histogram vector contains rich characteristic information, and the problems of amplitude information degradation and phase rotation of the signals can be simultaneously reflected. The amplitude-phase histogram vector is used as the input of the joint damage monitoring model of the optical transmission link, and the optical signal-to-noise ratio, the modulation format and the nonlinear noise power of the target multi-channel coherent optical transmission system can be determined, so that the damage condition of signals in the link is comprehensively reflected.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a method for monitoring link joint damage of a multi-channel optical transmission system provided by the invention;
FIG. 2 is a schematic diagram of the amplitude phase histogram sampling principle provided by the present invention;
FIG. 3 is one of the amplitude phase histograms provided by the present invention;
FIG. 4 is a second amplitude phase histogram provided by the present invention;
FIG. 5 is a third amplitude phase histogram provided by the present invention;
FIG. 6 is a fourth amplitude phase histogram provided by the present invention;
FIG. 7 is a fifth amplitude phase histogram provided by the present invention;
FIG. 8 is a sixth amplitude phase histogram provided by the present invention;
FIG. 9 is a seventh diagram of an amplitude phase histogram provided by the present invention;
Fig. 10 is a schematic structural diagram of an optical transmission link joint damage monitoring model provided by the invention;
FIG. 11 is a diagram of an eighth amplitude phase histogram provided by the present invention;
FIG. 12 is a ninth view of an amplitude phase histogram provided by the present invention;
FIG. 13 is a graph of ten amplitude phase histograms provided by the present invention;
FIG. 14 is an eleventh view of an amplitude phase histogram provided by the present invention;
FIG. 15 is a graph showing twelve amplitude phase histograms provided by the present invention;
FIG. 16 is a thirteen of amplitude phase histograms provided by the present invention;
FIG. 17 is a fourteen amplitude phase histogram provided by the present invention;
FIG. 18 is a fifteen of amplitude phase histograms provided by the present invention;
FIG. 19 is sixteen of the amplitude phase histogram provided by the present invention;
FIG. 20 is a seventeen of the amplitude phase histograms provided by the present invention;
FIG. 21 is a diagram of eighteen of the amplitude phase histograms provided by the present invention;
FIG. 22 is a nineteen of the amplitude phase histograms provided by the present invention;
FIG. 23 is a schematic diagram of a multi-channel coherent optical transmission simulation system according to the present invention;
Fig. 24 is a schematic structural diagram of a link joint damage monitoring system of a multi-channel optical transmission system provided by the present invention;
Fig. 25 is a schematic diagram of an entity structure of an electronic device according to the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Fig. 1 is a flowchart of a method for monitoring link joint damage of a multi-channel optical transmission system provided by the present invention, and as shown in fig. 1, an embodiment of the present invention provides a method for monitoring link joint damage of a multi-channel optical transmission system, including:
Step S1, acquiring I-path signal time domain data and Q-path signal time domain data of a receiving end of a target multi-channel coherent optical transmission system based on asynchronous sampling;
Step S2, determining an amplitude phase histogram vector based on the I-path signal time domain data and the Q-path signal time domain data; the amplitude phase histogram vector is used for representing the change of the I path signal and the Q path signal under the corresponding amplitude and phase states;
S3, inputting the amplitude phase histogram vector into an optical transmission link joint damage monitoring model, identifying a modulation format of a signal and determining link joint damage of a target multi-channel coherent optical transmission system; wherein the link joint impairment comprises: optical signal to noise ratio and nonlinear noise power. Specifically, in step S1, based on asynchronous sampling, the I-channel signal time domain data and the Q-channel signal time domain data of the receiving end of the target multi-channel coherent optical transmission system are obtained according to the photoelectric sensor. The sampling period is irrelevant to the symbol period of the signal during asynchronous sampling, and the complicated clock synchronization process is omitted.
In step S2, an amplitude-phase histogram vector representing the variation of the I-and Q-signals in the respective amplitude and phase states is determined based on the I-and Q-signal time-domain data.
The amplitude-phase histogram can reflect the changes of the I-path signal and the Q-path signal in the corresponding amplitude and phase states (the degree of the phase rotation caused by the nonlinear effect is reflected on the change of the shape of the amplitude-phase histogram), and the information contained in the amplitude-phase histogram is expressed in the form of a vector to obtain an amplitude-phase histogram vector.
It will be appreciated that the meaning of the amplitude phase histogram in terms of its concrete form and the abscissa may be set according to the actual situation, and the invention is not limited thereto. For example: the abscissa is amplitude, the ordinate is phase, and the intersection point of the abscissa and the ordinate is the number of occurrences in the corresponding amplitude and phase states. Or, the abscissa represents the amplitude and phase in combination, and the ordinate represents the number of times of occurrence in the corresponding amplitude and phase state, etc.
In step S3, the amplitude phase histogram vector is input into a trained optical transmission link joint damage monitoring model, signal modulation format identification (Modulation format identification, MFI) is implemented based on the characteristics reflected by the amplitude phase histogram vector by the optical transmission link joint damage monitoring model, and link joint damage of the target multi-channel coherent optical transmission system is determined.
Link joint impairment includes: optical signal-to-noise ratio (OSNR) and nonlinear noise power.
It can be understood that before the link joint damage monitoring is performed based on the trained optical transmission link joint damage monitoring model, the optical transmission link joint damage monitoring model needs to be trained based on the sample amplitude-phase histogram vector data set, and in addition, the sample set used in the training of the corresponding influence model is subjected to different expression forms of the amplitude-phase histogram. The specific model structure and the training method of the model can be selected according to actual requirements, and the invention is not limited to the specific model structure and the training method.
According to the method for monitoring the joint damage of the multi-channel optical transmission system link, the time domain data of the I-path signal and the time domain data of the Q-path signal are obtained through asynchronous sampling, and the amplitude-phase histogram vector capable of representing the change of the I-path signal and the Q-path signal under the corresponding amplitude and phase states is determined based on the time domain data. The amplitude-phase histogram vector is used as a carrier of the characteristic information, the amplitude-phase histogram vector contains rich characteristic information, and the problems of amplitude information degradation and phase rotation of the signals can be simultaneously reflected. The amplitude-phase histogram vector is used as the input of the joint damage monitoring model of the optical transmission link, and the optical signal-to-noise ratio, the modulation format and the nonlinear noise power of the target multi-channel coherent optical transmission system can be determined, so that the damage condition of signals in the link is comprehensively reflected.
Optionally, according to the method for monitoring link joint damage of a multi-channel optical transmission system provided by the present invention, the determining of the amplitude-phase histogram vector based on the I-channel signal time domain data and the Q-channel signal time domain data specifically includes:
Converting the I-path signal time domain data and the Q-path signal time domain data into complex signals;
An amplitude-phase histogram vector is determined based on the amplitude and phase distribution of the complex signal.
Specifically, the time domain data of the signal is processed to determine an amplitude phase histogram vector, the time domain data of the I-channel signal and the time domain data of the Q-channel signal are converted into complex signals, the I-channel is the real part of the complex signals, the Q-channel is the imaginary part of the complex signals, and the expression of the complex signals is as follows:
DataACH＝Ii+jQi(i＝1,2,...,N)
where i represents the sequence number of each sample point.
After converting the I-path and Q-path time domain data of the signals into complex signals with different amplitudes and phases, determining an amplitude-phase histogram vector according to the distribution condition of the amplitudes and phases of the complex signals.
It can be understood that the amplitude phase histogram is used as a good carrier of amplitude damage and phase damage of signals, contains characteristic information of common degradation of real parts and imaginary parts of complex signals after the signals pass through a transmission link, reflects the amplitude change of the signals and the phase rotation problem of the signals, can distinguish the degree of the nonlinear effect on the phase damage of the signals, has abundant contained characteristic information, and can comprehensively measure the nonlinear effect in the multichannel optical transmission link.
The link joint damage monitoring method of the multi-channel optical transmission system provided by the invention takes the amplitude-phase histogram vector as the carrier of the characteristic information, the amplitude-phase histogram vector contains rich characteristic information, and the problems of amplitude information degradation and phase rotation of signals can be simultaneously reflected. The amplitude-phase histogram vector is used as the input of the joint damage monitoring model of the optical transmission link, and the optical signal-to-noise ratio, the modulation format and the nonlinear noise power of the target multi-channel coherent optical transmission system can be determined, so that the damage condition of signals in the link is comprehensively reflected.
Optionally, according to the method for monitoring link joint damage of a multi-channel optical transmission system provided by the present invention, the determining an amplitude-phase histogram vector according to the distribution condition of the amplitude and the phase of the complex signal specifically includes:
determining a plurality of amplitude intervals according to the amplitude of the complex signal;
determining a plurality of phase intervals according to the phase change of the complex signal;
determining the number of times of occurrence of the complex signal in the amplitude interval and the phase interval according to the distribution condition of the amplitude and the phase of the complex signal based on the amplitude interval and the phase interval;
determining an amplitude phase histogram according to a preset histogram generation rule based on the occurrence times of complex signals in an amplitude interval and a phase interval;
the amplitude phase histogram is represented by a vector, and an amplitude phase histogram vector is determined.
Specifically, fig. 2 is a schematic diagram of an amplitude-phase histogram sampling principle provided by the present invention, and as shown in fig. 2, a plurality of amplitude intervals are determined according to the amplitude of a complex signal. For example: the amplitude is determined to be 0-10, and divided into five intervals of 0-2, 2-4, 4-6, 6-8 and 8-10, respectively.
A plurality of phase intervals are determined based on the phase change of the complex signal. For example: the phase is determined to be 0-2 pi, and divided into 4 intervals, namelyAnd/>
And determining the number of times of occurrence of the complex signal in the amplitude interval and the phase interval according to the distribution condition of the amplitude and the phase of the complex signal based on the amplitude interval and the phase interval. For example, all the interval combinations are recorded as bin, divided according to the amplitude values from small to large, and then counted according to the phase from large to small in each interval.
And determining an amplitude phase histogram according to a preset histogram generation rule based on the number of times of occurrence of complex signals in the amplitude interval and the phase interval. For example, in the amplitude phase histogram of fig. 2, different bin intervals on the horizontal axis correspond to different complex information I i+jQi, i.e., to different amplitude and phase states of the complex signal, while the vertical axis represents the number of occurrences in the corresponding amplitude and phase states.
Fig. 3 is one of the amplitude phase histograms provided by the present invention, fig. 4 is the second of the amplitude phase histograms provided by the present invention, fig. 5 is the third of the amplitude phase histograms provided by the present invention, fig. 6 is the fourth of the amplitude phase histograms provided by the present invention, fig. 7 is the fifth of the amplitude phase histograms provided by the present invention, fig. 8 is the sixth of the amplitude phase histograms provided by the present invention, fig. 9 is the seventh of the amplitude phase histograms provided by the present invention, fig. 3-9 are amplitude phase histograms of QPSK (Quadrature phase shift keying) signals collected under the conditions of-3, -2, -1, 0, 1, 2, 3dBm, respectively, of optical signal to noise ratio of 25 dB.
As can be seen from fig. 3-9, the amplitude-phase histogram reflects the phase rotation of the signal well, and when the transmission power increases, the nonlinear power increases, and the degree of phase rotation caused by the nonlinear effect is reflected on the change of the shape of the amplitude-phase histogram. The change of the peak position of the QPSK signal reflects the phase rotation degree of the signal, thereby representing the phase damage of the nonlinear effect to the signal.
The amplitude phase histogram is represented by a vector, and an amplitude phase histogram vector is determined. It will be appreciated that the amplitude phase histogram may be represented by a column vector or a row vector, each value in the vector representing the number of times the complex signal occurs in the corresponding amplitude and phase state.
It should be noted that the specific rule of the interval division and the specific expression form of the amplitude phase histogram may be set according to the actual situation, which is not limited in the present invention.
The method for monitoring the joint damage of the multi-channel optical transmission system link provided by the invention has the advantages that the amplitude information of the complex signal is deteriorated due to the link damage, and meanwhile, the problem of phase rotation is also introduced. The magnitude of the amplitude change varies from one link condition to another and from the degree of phase rotation. The invention takes the amplitude phase histogram vector as the input of the optical transmission link joint damage monitoring model, the phase rotation degree caused by the nonlinear effect is reflected on the change of the amplitude phase histogram shape, and the quantification of the nonlinear damage degree can be realized by combining a neural network. Under different modulation formats and link conditions, the shape, the number of peaks, the peak positions and the steepness degree of the peaks of the amplitude phase histogram are also different, so that the amplitude phase histogram is a good carrier for signal amplitude damage and phase damage, the contained characteristic information is rich, and the nonlinear effect in the multichannel optical transmission link is comprehensively measured.
Optionally, according to the method for monitoring the joint damage of the multi-channel optical transmission system link provided by the invention, the optical transmission link joint damage monitoring model is a multi-task learning model; the optical transmission link joint damage monitoring model comprises: an input layer, a hidden layer and an output layer; the hidden layer comprises a plurality of neuron nodes; the input layer is connected with the neuron node;
inputting the amplitude phase histogram vector into an optical transmission link joint damage monitoring model, identifying a modulation format of a signal and determining link joint damage of a target multi-channel coherent optical transmission system, wherein the method specifically comprises the following steps of:
Transmitting the amplitude phase histogram vector into the hidden layer based on the input layer;
classifying different signal types in the amplitude phase histogram vector based on the hidden layer, and determining modulation format characteristic information;
determining link joint damage characteristic information according to the amplitude phase histogram vector based on the hidden layer;
And inputting the modulation format characteristic information and the link joint damage characteristic information into an output layer, and determining and outputting the modulation format and the link joint damage according to the output layer.
Specifically, in order to reduce algorithm complexity and save computing resources, the optical transmission link joint damage monitoring model in the invention is a Multi-task learning model, which can be simply called MT-DNN (Multi-task deep neural network ). The optical transmission link joint damage monitoring model comprises: an input layer, a hidden layer and an output layer; the hidden layer comprises a plurality of neuron nodes; the input layer is connected with the neuron node and is used for processing the task I, the task II and the task III.
At each neuron node, the activity value of the neuron is obtained through weighted summation and nonlinear activation function, and the activity value is transmitted to the neuron of the next layer as input. The amplitude phase histogram vector is transmitted to the hidden layer through the input layer, is automatically operated by a plurality of nonlinear units in the multi-layer hidden layer, and is transmitted to the output layer, and the result is output after the activation function. Through the operation process, the characteristic information of the input amplitude phase histogram vector can be extracted, the corresponding output is calculated, and the prediction result of the modulation format type and the link joint damage is output based on the output layer.
It should be noted that, the above transmission link joint damage monitoring model may set the number of hidden layers and the number of neurons in each layer according to the actual application requirement of the model, besides the above functional modules. The neurons of each layer are in a fully-connected mode, the input of the input layer is an amplitude phase histogram, the hidden layer is a multi-task shared hidden layer, a ReLU activation function is adopted, and the output layer outputs a model result.
It will be appreciated that since the hidden layer is made up of several neuron nodes, the neurons between layers are all fully connected, with the output of the neuron of the upper layer being the input of the neuron of the next layer. The more the number of neuron nodes and the hidden layers of each hidden layer are, the higher the complexity of the model is, the more complex problem can be handled, the performance is improved to a certain extent, but the too large hidden layers or too many hidden layers can cause overfitting, and the performance is reduced. Therefore, the size and number of the hidden layers can be set according to practical requirements, which is not limited by the present invention.
Fig. 10 is a schematic structural diagram of an optical transmission link joint damage monitoring model provided by the present invention, as shown in fig. 10, and the specific steps of inputting an amplitude-phase histogram vector into the optical transmission link joint damage monitoring model, identifying a modulation format of a signal, and determining a link joint damage of a target multi-channel coherent optical transmission system are described with reference to an actual application process as an example:
And inputting the amplitude-phase histogram vector into an optical transmission link joint damage monitoring model, and jointly completing a task I, a task II and a task III by a shared hidden layer formed by three hidden layers.
Task one, classifying different signal types in the amplitude phase histogram vector, and determining a modulation format. For example: the Softmax activation function was used. The output value is discrete, switching the output between 0 and 1. The combination of the different outputs represents different signal types, in this embodiment, "001" represents a QPSK signal, "010" represents a 16QAM (Quadrature Amplitude Modulation ) signal, and "100" represents a 32QAM signal.
And secondly, determining the optical signal to noise ratio according to the amplitude phase histogram vector. And thirdly, determining nonlinear noise power according to the amplitude phase histogram vector. Because the second task and the third task belong to regression tasks, the linear activation function can be adopted to directly output, and the output value is continuous.
The shared hidden layer of the model uses the same mapping model, so that the method avoids using a plurality of neural networks, improves the calculation efficiency, can monitor a plurality of communication system parameters simultaneously, replaces a plurality of communication parameter monitoring algorithms by one model, and has the advantages that the input information carrier is an asynchronous amplitude phase histogram, is a column vector substantially, has lower algorithm complexity and saves calculation resources.
Optionally, according to the method for monitoring link joint damage of a multi-channel optical transmission system provided by the present invention, before the step of inputting the amplitude-phase histogram vector into the optical transmission link joint damage monitoring model, identifying a modulation format of a signal and determining link joint damage of a target multi-channel coherent optical transmission system, the method further includes: training an optical transmission link joint damage monitoring model;
Training an optical transmission link joint damage monitoring model, specifically comprising:
Determining an amplitude phase histogram vector sample data set based on sample I-path signal time domain data and sample Q-path signal time domain data obtained under the conditions of a plurality of different signal modulation formats, optical signal to noise ratios, transmitting power and optical fiber link lengths; wherein each set of data in the amplitude phase histogram vector sample dataset comprises: amplitude phase histogram vector and corresponding osnr, modulation format and nonlinear noise power;
training an optical transmission link joint damage monitoring model by using the amplitude phase histogram vector sample data set;
Based on the target loss function, the learning rate is adjusted by adopting a gradient descent optimization algorithm, gradient estimation and correction are carried out, network parameters of the optical transmission link joint damage monitoring model are updated, and iterative training is carried out on the optical transmission link joint damage monitoring model based on the updated network parameters until the optical transmission link joint damage monitoring model converges.
Specifically, before using the optical transmission link joint damage monitoring model, it is also necessary to: training an optical transmission link joint damage monitoring model.
Firstly, determining samples used in training a model, and determining corresponding amplitude phase histogram vectors based on sample I-path signal time domain data and sample Q-path signal time domain data obtained under the conditions of a plurality of different signal modulation formats, optical signal to noise ratios, transmitting powers and optical fiber link lengths.
Fig. 11 is an eighth of the amplitude phase histogram provided by the present invention, fig. 12 is a ninth of the amplitude phase histogram provided by the present invention, fig. 13 is a tenth of the amplitude phase histogram provided by the present invention, fig. 11-13 are amplitude phase histograms under the conditions that the optical fiber length is 1200km, the optical signal to noise ratio is 25dB, and the transmission power is 0dBm, and the modulation formats are respectively QPSK, 16QAM, and 32 QAM.
Fig. 14 is eleven of the amplitude phase histogram provided by the present invention, fig. 15 is twelve of the amplitude phase histogram provided by the present invention, fig. 16 is thirteen of the amplitude phase histogram provided by the present invention, fig. 14-16 are amplitude phase histograms with an optical fiber length of 500km, a transmitting power of 0dBm, a modulation format of the signal of QPSK, and optical signal-to-noise ratios of 15, 20, 25dB, respectively.
Fig. 17 is fourteen of the amplitude phase histogram provided by the present invention, fig. 18 is fifteen of the amplitude phase histogram provided by the present invention, fig. 19 is sixteen of the amplitude phase histogram provided by the present invention, fig. 17-19 are amplitude phase histograms with a transmitting power of 0dBm, an optical signal to noise ratio of 20dB, a modulation format of the signal of 16QAM, and optical fiber lengths of 800, 1200, 1500km, respectively.
Fig. 20 is seventeen of the amplitude phase histograms provided by the present invention, fig. 21 is eighteen of the amplitude phase histograms provided by the present invention, fig. 22 is nineteen of the amplitude phase histograms provided by the present invention, fig. 20-22 are amplitude phase histograms under the conditions that the optical signal-to-noise ratio is 25dB, the optical fiber length is 1200km, the modulation format of the signal is 32QAM, and the transmitting power is-3, 0, and 3dBmdBm respectively.
As can be seen from fig. 11-22, when the modulation format, the osnr and the nonlinear noise are changed, the asynchronous amplitude phase histogram of the signal shows obvious differences, the shape, the number of peaks, the peak positions and the steepness of the peaks are different, the contained characteristic information is rich, and the differences are the basis for jointly monitoring the damage and identifying the modulation format by the neural network. The phase rotation degree caused by the nonlinear effect is reflected on the change of the amplitude phase histogram, the nonlinear effect in the multichannel optical transmission link can be comprehensively measured and the nonlinear damage degree is quantized by taking the amplitude phase histogram as the carrier input MT-DNN of characteristic information, and the method is very suitable for completing the tasks of monitoring nonlinear noise power and optical signal to noise ratio with high precision and identifying modulation formats.
And taking each group of amplitude phase histogram vectors and the corresponding optical signal to noise ratio, modulation format and nonlinear noise power as a group of sample data, and forming an amplitude phase histogram vector sample data set by a plurality of sample data.
And training an optical transmission link joint damage monitoring model by using the amplitude phase histogram vector sample data set.
Based on the target loss function, the learning rate is adjusted by adopting a gradient descent optimization algorithm, gradient estimation correction is performed, the training speed is optimized, the network parameters of the optical transmission link joint damage monitoring model are updated, and iterative training is performed on the optical transmission link joint damage monitoring model based on the updated network parameters until the optical transmission link joint damage monitoring model converges.
For example: the sample set is randomly divided into a training set (70%) and a testing set (30%), the training set is utilized to train a model, the model automatically learns information about modulation formats and link damage from the proposed amplitude-phase histogram, and after multiple iterations, when the loss function is lower than a set minimum value, the training is considered to be completed. The test data set is input into a model which is completed with training to carry out performance test, modulation format identification is completed on the currently input amplitude phase histogram test data through the past learning experience, and the optical signal to noise ratio and nonlinear noise power are monitored and used for testing the performance of the method.
The training test method is only used as a specific example of model training to describe the training process of the model of the invention, and in the practical application process of the invention, the objective function applied during training, the condition of model stopping training and the model verification method can be adjusted according to the practical situation, and the invention is not limited to this.
According to the method for monitoring the joint damage of the multi-channel optical transmission system link, provided by the invention, when the modulation format, the optical signal to noise ratio and the nonlinear noise are changed, the asynchronous amplitude phase histogram of the signal shows obvious differences, the shape, the number of peaks, the positions of the peaks and the steepness degree of the peaks are different, the contained characteristic information is rich, and the method is a good carrier for the amplitude damage and the phase damage of the signal, and the differences are the basis for the joint monitoring damage and the recognition of the modulation format of the neural network. The phase rotation degree caused by the nonlinear effect is reflected on the change of the amplitude phase histogram, the nonlinear effect in the multichannel optical transmission link can be comprehensively measured and the nonlinear damage degree is quantized by taking the phase rotation degree as a carrier transmission model of characteristic information, and the method is very suitable for completing the task of monitoring the optical signal-to-noise ratio, modulation format and nonlinear noise power of a target multichannel coherent optical transmission system with high precision, so that the damage condition of signals in the link is comprehensively reflected.
Optionally, according to the method for monitoring link joint damage of a multi-channel optical transmission system provided by the present invention, the set of amplitude phase histogram vector sample data is determined based on sample I-path signal time domain data and sample Q-path signal time domain data obtained under the conditions of a plurality of different signal modulation formats, optical signal to noise ratios, transmitting powers and optical fiber link lengths, and specifically includes:
constructing a corresponding target multi-channel coherent light transmission simulation system based on the target multi-channel coherent light transmission system;
Based on a target multi-channel coherent light transmission simulation system, acquiring a plurality of sample I-path signal time domain data and sample Q-path signal time domain data according to a target modulation format change type, an optical signal-to-noise ratio change range, a transmitting power change range and an optical fiber link length change range;
An amplitude phase histogram vector sample dataset is determined based on the number of sample I signal time domain data and the sample Q signal time domain data.
Specifically, since the joint damage of the multi-channel coherent optical transmission system is affected by the system itself, the accuracy of the method for monitoring the joint damage of the multi-channel optical transmission system link is further improved. Based on a target multi-channel coherent light transmission system to be monitored, a corresponding target multi-channel coherent light transmission simulation system is built. The simulation system is used for obtaining samples for training the optical transmission link joint damage monitoring model.
Based on a target multi-channel coherent light transmission simulation system, a plurality of sample I-path signal time domain data and sample Q-path signal time domain data are obtained according to a target modulation format change type, an optical signal-to-noise ratio change range, a transmitting power change range and an optical fiber link length change range.
For example: based on the construction of the multi-channel coherent light transmission simulation system by commercial software VPI Transmission Maker, fig. 23 is a schematic structural diagram of the multi-channel coherent light transmission simulation system provided by the invention, and as shown in fig. 23, the light transmission system adopts a wavelength division multiplexing technology and comprises 5 channels (4 interference channels and 1 test channel), the central frequency of the laser is 193.1THz, and the channel interval is 50GHz.
After constellation mapping, the pseudo-random binary sequences are modulated respectively to generate signals with three widely applied modulation formats: QPSK, 16QAM, and 32QAM, single channel symbol rate is set to 28GBaud. In an optical transmission system, different nonlinear noise powers are obtained by adjusting the length of an optical fiber link and the incoming optical power of an optical signal, and the transmitting power range of each channel is set to be-3.0 dBm, and the interval is 1dBm. The fiber link contains a plurality of spans, each span comprising 100km of standard single mode fiber and erbium-doped fiber amplifiers. The span number of the optical fiber link is set between 1 and 15, the total length variation range of the transmission optical fiber is 100-1500 km, and the interval is 100km.
The OSNR reference value is a set value of an OSNR setting module, through which corresponding ASE noise (AMPLIFIER SPONTANEOUSEMISSION NOISE ) is added to the multi-channel optical transmission system.
The nonlinear noise power reference value is obtained by calculation through a wiener filtering decorrelation algorithm, and the specific method comprises the following steps: the optical signal after wavelength division multiplexing is divided into two paths, wherein the nonlinear refractive index of an optical fiber link through which a first path of signal passes is set to be 2.6X10-20 m 2/W, namely nonlinear noise is added, and the nonlinear noise is not added to the other path of signal; after the two paths of signals are subjected to dispersion equalization, a reference value of nonlinear noise power is obtained through calculation of a wiener filter decorrelation algorithm, and the reference value is shown in the following formula:
Wherein t is a time parameter, f is a frequency parameter, gamma is a noise influencing factor, beta is a spectrum layer parameter, |X (t, f) | 2 is a signal power spectrum containing nonlinear noise, Nonlinear noise power spectrum.
The corresponding amplitude phase histogram vector is determined based on the sample I-channel signal time domain data and the sample Q-channel signal time domain data, and the specific method is as above, and will not be described herein.
And determining an amplitude phase histogram vector sample data set according to the obtained amplitude phase histogram vector, the corresponding optical signal to noise ratio reference value, the nonlinear noise power reference value and the actual modulation format.
According to the method for monitoring the link joint damage of the multi-channel optical transmission system, the corresponding target multi-channel coherent optical transmission simulation system is built aiming at the target multi-channel coherent optical transmission system to be monitored, and the simulation system is used for acquiring the samples for training the optical transmission link joint damage monitoring model, so that the data quantity required by model training can be effectively reduced, the time required by model training is shortened, and the accuracy of monitoring the link damage performance of the model is improved.
Optionally, according to the method for monitoring link joint damage of a multi-channel optical transmission system provided by the invention, a corresponding target multi-channel coherent optical transmission simulation system is built based on the target multi-channel coherent optical transmission system, and the method specifically comprises the following steps:
acquiring link parameters and system parameters of a target multi-channel coherent light transmission system; wherein the link parameters include: attenuation coefficient, nonlinear refractive index and dispersion coefficient of the optical fiber; the system parameters include: link parameters, number of channels, and channel spacing;
Based on the link parameters and the system parameters, a corresponding target multi-channel coherent light transmission simulation system is built.
Specifically, when the multi-channel coherent light transmission simulation system is built, the link parameters and the system parameters of the target multi-channel coherent light transmission system are required to be used. Wherein the link parameters include: attenuation coefficient, nonlinear refractive index and dispersion coefficient of the optical fiber; the system parameters include: link parameters, number of channels, and channel spacing.
Based on the link parameters and the system parameters, a corresponding target multi-channel coherent light transmission simulation system is built, and the operation and the changed working state of an actual system are simulated through the target multi-channel coherent light transmission simulation system.
According to the method for monitoring the link joint damage of the multi-channel optical transmission system, for an actual multi-channel coherent optical transmission system needing to monitor the link damage, the fixed link parameters such as the attenuation coefficient, the nonlinear refractive index and the dispersion coefficient of an optical fiber and other fixed system parameter settings such as the number of channels and the channel spacing are obtained, four variable parameters such as the variable type of a signal modulation format, the variable range of an optical signal to noise ratio, the variable range of transmitting power and the variable range of the length of the optical fiber link are obtained, and the operation and the variable working state of the actual system are simulated by constructing a corresponding coherent optical transmission simulation system. The simulation system is used for obtaining the samples for training the optical transmission link joint damage monitoring model, so that the data volume required by model training can be effectively reduced, the time required by model training is shortened, and the accuracy of link damage performance monitoring of the model is improved.
Fig. 24 is a schematic structural diagram of a link joint damage monitoring system of a multi-channel optical transmission system provided by the present invention, and as shown in fig. 24, the present invention also provides a link joint damage monitoring system of a multi-channel optical transmission system, including: a signal acquisition unit 241, a vector determination unit 242, and a damage monitoring unit 243;
A signal obtaining unit 241, configured to obtain, based on asynchronous sampling, I-channel signal time domain data and Q-channel signal time domain data of a receiving end of the target multi-channel coherent optical transmission system;
A vector determining unit 242 for determining an amplitude phase histogram vector based on the I-path signal time domain data and the Q-path signal time domain data; the amplitude phase histogram vector is used for representing the change of the I path signal and the Q path signal under the corresponding amplitude and phase states;
The impairment monitoring unit 243 is configured to input the amplitude-phase histogram vector into an optical transmission link joint impairment monitoring model, identify a modulation format of a signal, and determine a link joint impairment of the target multi-channel coherent optical transmission system; wherein the link joint impairment comprises: optical signal to noise ratio and nonlinear noise power.
Specifically, the signal obtaining unit 241 is configured to obtain, based on asynchronous sampling, I-path signal time domain data and Q-path signal time domain data of the receiving end of the target multi-channel coherent optical transmission system according to the photoelectric sensor. The sampling period is irrelevant to the symbol period of the signal during asynchronous sampling, and the complicated clock synchronization process is omitted.
A vector determination unit 242 for determining an amplitude-phase histogram vector for representing the variation of the I-and Q-signals in the respective amplitude and phase states based on the I-and Q-signal time-domain data.
The amplitude-phase histogram can reflect the changes of the I-path signal and the Q-path signal in the corresponding amplitude and phase states (the degree of the phase rotation caused by the nonlinear effect is reflected on the change of the shape of the amplitude-phase histogram), and the information contained in the amplitude-phase histogram is expressed in the form of a vector to obtain an amplitude-phase histogram vector.
It will be appreciated that the meaning of the amplitude phase histogram in terms of its concrete form and the abscissa may be set according to the actual situation, and the invention is not limited thereto. For example: the abscissa is amplitude, the ordinate is phase, and the intersection point of the abscissa and the ordinate is the number of occurrences in the corresponding amplitude and phase states. Or, the abscissa represents the amplitude and phase in combination, and the ordinate represents the number of times of occurrence in the corresponding amplitude and phase state, etc.
The impairment monitoring unit 243 is configured to input the amplitude-phase histogram vector into a trained optical transmission link joint impairment monitoring model, implement signal modulation format identification based on the characteristics reflected by the amplitude-phase histogram vector based on the optical transmission link joint impairment monitoring model, and determine link joint impairment of the target multi-channel coherent optical transmission system.
Link joint impairment includes: optical signal to noise ratio and nonlinear noise power.
It can be understood that before the link joint damage monitoring is performed based on the trained optical transmission link joint damage monitoring model, the optical transmission link joint damage monitoring model needs to be trained based on the sample amplitude-phase histogram vector data set, and in addition, the sample set used in the training of the corresponding influence model is subjected to different expression forms of the amplitude-phase histogram. The specific model structure and the training method of the model can be selected according to actual requirements, and the invention is not limited to the specific model structure and the training method.
According to the link joint damage monitoring system of the multi-channel optical transmission system, the time domain data of the I-path signals and the time domain data of the Q-path signals are obtained through asynchronous sampling, and the amplitude-phase histogram vectors capable of representing the changes of the I-path signals and the Q-path signals under the corresponding amplitude and phase states are determined based on the time domain data. The amplitude-phase histogram vector is used as a carrier of the characteristic information, the amplitude-phase histogram vector contains rich characteristic information, and the problems of amplitude information degradation and phase rotation of the signals can be simultaneously reflected. The amplitude-phase histogram vector is used as the input of the joint damage monitoring model of the optical transmission link, and the optical signal-to-noise ratio, the modulation format and the nonlinear noise power of the target multi-channel coherent optical transmission system can be determined, so that the damage condition of signals in the link is comprehensively reflected.
It should be noted that, the system for monitoring link joint damage of a multi-channel optical transmission system provided by the present invention is used for executing the method for monitoring link joint damage of a multi-channel optical transmission system, and specific embodiments and method embodiments thereof are consistent, and are not described herein.
Fig. 25 is a schematic physical structure of an electronic device according to the present invention, as shown in fig. 25, the electronic device may include: a processor 251, a communication interface (CommunicationsInterface) 252, a memory 253 and a communication bus 254, wherein the processor 251, the communication interface 252, and the memory 253 communicate with each other via the communication bus 254. The processor 251 may invoke logic instructions in the memory 253 to perform a multi-channel optical transmission system link joint impairment monitoring method comprising: based on asynchronous sampling, acquiring I-path signal time domain data and Q-path signal time domain data of a receiving end of a target multi-channel coherent optical transmission system; determining an amplitude phase histogram vector based on the I-channel signal time domain data and the Q-channel signal time domain data; the amplitude phase histogram vector is used for representing the change of the I path signal and the Q path signal under the corresponding amplitude and phase states; inputting the amplitude phase histogram vector into an optical transmission link joint damage monitoring model, identifying a modulation format of a signal and determining link joint damage of a target multi-channel coherent optical transmission system; wherein the link joint impairment comprises: optical signal to noise ratio and nonlinear noise power.
Further, the logic instructions in the memory 253 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a separate product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-only memory (ROM), a random access memory (RAM, randomAccessMemory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer, the computer is capable of executing the method for monitoring joint damage of a multi-channel optical transmission system link provided by the above methods, the method comprising: based on asynchronous sampling, acquiring I-path signal time domain data and Q-path signal time domain data of a receiving end of a target multi-channel coherent optical transmission system; determining an amplitude phase histogram vector based on the I-channel signal time domain data and the Q-channel signal time domain data; the amplitude phase histogram vector is used for representing the change of the I path signal and the Q path signal under the corresponding amplitude and phase states; inputting the amplitude phase histogram vector into an optical transmission link joint damage monitoring model, identifying a modulation format of a signal and determining link joint damage of a target multi-channel coherent optical transmission system; wherein the link joint impairment comprises: optical signal to noise ratio and nonlinear noise power.
In yet another aspect, the present invention further provides a non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, is implemented to perform the above-provided method for joint impairment monitoring of a multi-channel optical transmission system link, the method comprising: based on asynchronous sampling, acquiring I-path signal time domain data and Q-path signal time domain data of a receiving end of a target multi-channel coherent optical transmission system; determining an amplitude phase histogram vector based on the I-channel signal time domain data and the Q-channel signal time domain data; the amplitude phase histogram vector is used for representing the change of the I path signal and the Q path signal under the corresponding amplitude and phase states; inputting the amplitude phase histogram vector into an optical transmission link joint damage monitoring model, identifying a modulation format of a signal and determining link joint damage of a target multi-channel coherent optical transmission system; wherein the link joint impairment comprises: optical signal to noise ratio and nonlinear noise power.
The apparatus embodiments described above are merely illustrative, wherein elements illustrated as separate elements may or may not be physically separate, and elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product, which may be stored in a computer-readable storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the various embodiments or methods of some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (8)

1. The method for monitoring the joint damage of the links of the multi-channel optical transmission system is characterized by comprising the following steps of:
Based on asynchronous sampling, acquiring I-path signal time domain data and Q-path signal time domain data of a receiving end of a target multi-channel coherent optical transmission system;
Determining an amplitude phase histogram vector based on the I-channel signal time domain data and the Q-channel signal time domain data; the amplitude-phase histogram vector is used for representing the change of the I-path signal and the Q-path signal under the corresponding amplitude and phase states;
Inputting the amplitude phase histogram vector into an optical transmission link joint damage monitoring model, identifying a modulation format of a signal and determining link joint damage of a target multi-channel coherent optical transmission system; wherein the link joint impairment comprises: optical signal to noise ratio and nonlinear noise power;
The optical transmission link joint damage monitoring model is a multi-task learning model; the optical transmission link joint damage monitoring model comprises: an input layer, a hidden layer and an output layer; the hidden layer comprises a plurality of neuron nodes; the input layer is connected with the neuron node;
the step of inputting the amplitude phase histogram vector into an optical transmission link joint damage monitoring model, identifying a modulation format of a signal and determining link joint damage of a target multi-channel coherent optical transmission system, specifically comprises the following steps:
transmitting the amplitude phase histogram vector into the hidden layer based on the input layer;
Classifying different signal types in the amplitude phase histogram vector based on the hidden layer, and determining modulation format characteristic information;
Determining link joint damage characteristic information according to the amplitude phase histogram vector based on the hidden layer;
Inputting the modulation format characteristic information and the link joint damage characteristic information into the output layer, and determining and outputting a modulation format and link joint damage according to the output layer;
Before the step of inputting the amplitude phase histogram vector into the optical transmission link joint impairment monitoring model, identifying a modulation format of a signal and determining the link joint impairment of the target multi-channel coherent optical transmission system, the method further comprises: training the optical transmission link joint damage monitoring model;
training the optical transmission link joint damage monitoring model specifically comprises the following steps:
Determining an amplitude phase histogram vector sample data set based on sample I-path signal time domain data and sample Q-path signal time domain data obtained under the conditions of a plurality of different signal modulation formats, optical signal to noise ratios, transmitting power and optical fiber link lengths; wherein each set of data in the amplitude phase histogram vector sample dataset comprises: amplitude phase histogram vector and corresponding osnr, modulation format and nonlinear noise power;
Training the optical transmission link joint damage monitoring model by using the amplitude phase histogram vector sample data set;
Based on a target loss function, a gradient descent optimization algorithm is adopted to adjust the learning rate, gradient estimation and correction are carried out, network parameters of the optical transmission link joint damage monitoring model are updated, and iterative training is carried out on the optical transmission link joint damage monitoring model based on the updated network parameters until the optical transmission link joint damage monitoring model converges.
2. The method for monitoring link joint impairment of a multi-channel optical transmission system according to claim 1, wherein determining an amplitude-phase histogram vector based on the I-channel signal time-domain data and the Q-channel signal time-domain data comprises:
Converting the I-path signal time domain data and the Q-path signal time domain data into complex signals;
And determining the amplitude-phase histogram vector according to the distribution condition of the amplitude and the phase of the complex signal.
3. The method for monitoring link joint impairment of a multi-channel optical transmission system according to claim 2, wherein determining the amplitude-phase histogram vector according to the distribution of the amplitude and phase of the complex signal comprises:
determining a plurality of amplitude intervals according to the amplitude of the complex signal;
Determining a plurality of phase intervals according to the phase change of the complex signal;
Determining the number of times of occurrence of the complex signal in the amplitude interval and the phase interval according to the distribution condition of the amplitude and the phase of the complex signal based on the amplitude interval and the phase interval;
Determining an amplitude phase histogram according to a preset histogram generation rule based on the occurrence times of complex signals in the amplitude interval and the phase interval;
and representing the amplitude phase histogram by a vector, and determining the amplitude phase histogram vector.
4. The method for monitoring link joint impairment of a multi-channel optical transmission system according to claim 1, wherein determining the amplitude-phase histogram vector sample dataset based on sample I-path signal time-domain data and sample Q-path signal time-domain data obtained under several different signal modulation formats, optical signal-to-noise ratios, transmission powers, and optical fiber link lengths, comprises:
Based on the target multi-channel coherent light transmission system, a corresponding target multi-channel coherent light transmission simulation system is built;
Based on the target multi-channel coherent optical transmission simulation system, acquiring a plurality of sample I-path signal time domain data and sample Q-path signal time domain data according to a target modulation format change type, an optical signal-to-noise ratio change range, a transmitting power change range and an optical fiber link length change range;
and determining an amplitude phase histogram vector sample data set based on the sample I-path signal time domain data and the sample Q-path signal time domain data.
5. The method for monitoring link joint damage of a multi-channel optical transmission system according to claim 4, wherein the constructing a corresponding target multi-channel coherent optical transmission simulation system based on the target multi-channel coherent optical transmission system specifically comprises:
acquiring link parameters and system parameters of the target multi-channel coherent light transmission system; wherein the link parameters include: attenuation coefficient, nonlinear refractive index and dispersion coefficient of the optical fiber; the system parameters include: link parameters, number of channels, and channel spacing;
And building a corresponding target multi-channel coherent light transmission simulation system based on the link parameters and the system parameters.
6. A multi-channel optical transmission system link joint impairment monitoring system, comprising: the device comprises a signal acquisition unit, a vector determination unit, a damage monitoring unit and a model training unit;
The signal acquisition unit is used for acquiring I-path signal time domain data and Q-path signal time domain data of a receiving end of the target multi-channel coherent optical transmission system based on asynchronous sampling;
The vector determining unit is used for determining an amplitude phase histogram vector based on the I-path signal time domain data and the Q-path signal time domain data; the amplitude-phase histogram vector is used for representing the change of the I-path signal and the Q-path signal under the corresponding amplitude and phase states;
The damage monitoring unit is used for inputting the amplitude phase histogram vector into an optical transmission link joint damage monitoring model, identifying a modulation format of a signal and determining link joint damage of a target multi-channel coherent optical transmission system; wherein the link joint impairment comprises: optical signal to noise ratio and nonlinear noise power;
The optical transmission link joint damage monitoring model is a multi-task learning model; the optical transmission link joint damage monitoring model comprises: an input layer, a hidden layer and an output layer; the hidden layer comprises a plurality of neuron nodes; the input layer is connected with the neuron node;
The damage monitoring unit is specifically configured to:
transmitting the amplitude phase histogram vector into the hidden layer based on the input layer;
Classifying different signal types in the amplitude phase histogram vector based on the hidden layer, and determining modulation format characteristic information;
Determining link joint damage characteristic information according to the amplitude phase histogram vector based on the hidden layer;
Inputting the modulation format characteristic information and the link joint damage characteristic information into the output layer, and determining and outputting a modulation format and link joint damage according to the output layer;
model training unit for:
Determining an amplitude phase histogram vector sample data set based on sample I-path signal time domain data and sample Q-path signal time domain data obtained under the conditions of a plurality of different signal modulation formats, optical signal to noise ratios, transmitting power and optical fiber link lengths; wherein each set of data in the amplitude phase histogram vector sample dataset comprises: amplitude phase histogram vector and corresponding osnr, modulation format and nonlinear noise power;
Training the optical transmission link joint damage monitoring model by using the amplitude phase histogram vector sample data set;
Based on a target loss function, a gradient descent optimization algorithm is adopted to adjust the learning rate, gradient estimation and correction are carried out, network parameters of the optical transmission link joint damage monitoring model are updated, and iterative training is carried out on the optical transmission link joint damage monitoring model based on the updated network parameters until the optical transmission link joint damage monitoring model converges.
7. An electronic device comprising a memory and a processor, said processor and said memory completing communication with each other via a bus; the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the multi-channel optical transmission system link joint damage monitoring method of any of claims 1-5.
8. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the multi-channel optical transmission system link joint damage monitoring method of any one of claims 1 to 5.
CN202210741672.2A 2022-06-27 2022-06-27 Method and system for monitoring link joint damage of multi-channel optical transmission system Active CN115173940B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210741672.2A CN115173940B (en) 2022-06-27 2022-06-27 Method and system for monitoring link joint damage of multi-channel optical transmission system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210741672.2A CN115173940B (en) 2022-06-27 2022-06-27 Method and system for monitoring link joint damage of multi-channel optical transmission system

Publications (2)

Publication Number Publication Date
CN115173940A CN115173940A (en) 2022-10-11
CN115173940B true CN115173940B (en) 2024-04-23

Family

ID=83486705

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210741672.2A Active CN115173940B (en) 2022-06-27 2022-06-27 Method and system for monitoring link joint damage of multi-channel optical transmission system

Country Status (1)

Country Link
CN (1) CN115173940B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2804334A1 (en) * 2013-05-13 2014-11-19 Xieon Networks S.à.r.l. Method, device and communication system for reducing optical transmission impairments
CN113472435A (en) * 2021-06-30 2021-10-01 华中科技大学 Method for simultaneously extracting optical signal modulation parameters and damage factors
CN113556173A (en) * 2021-09-18 2021-10-26 北京邮电大学 Method and device for monitoring optical signal-to-noise ratio of nonlinear region
CN113938188A (en) * 2021-09-02 2022-01-14 华中科技大学 Construction method and application of optical signal-to-noise ratio monitoring model

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2804334A1 (en) * 2013-05-13 2014-11-19 Xieon Networks S.à.r.l. Method, device and communication system for reducing optical transmission impairments
CN113472435A (en) * 2021-06-30 2021-10-01 华中科技大学 Method for simultaneously extracting optical signal modulation parameters and damage factors
CN113938188A (en) * 2021-09-02 2022-01-14 华中科技大学 Construction method and application of optical signal-to-noise ratio monitoring model
CN113556173A (en) * 2021-09-18 2021-10-26 北京邮电大学 Method and device for monitoring optical signal-to-noise ratio of nonlinear region

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
Multi-channel multi-task optical performance monitoring based multi-input multi-output deep learning and transfer learning for SDM;Fengguang Luo;《Optics Communications 》;20210512;全文 *
一种基于卷积神经网络的结构损伤检测方法;张盼盼;张健飞;;河南科学;20200415(第04期);全文 *
光分组交换系统中载波抑制光标签的研究;罗风光;《激光技术》;20160325;全文 *
光纤通信系统中非线性损伤补偿技术的研究;徐梦然;崔晟;李俊;;光通信研究;20130924(第05期);全文 *

Also Published As

Publication number Publication date
CN115173940A (en) 2022-10-11

Similar Documents

Publication Publication Date Title
CN107342962B (en) deep learning intelligent constellation diagram analysis method based on convolutional neural network
Khan et al. Modulation format identification in coherent receivers using deep machine learning
CN110598677B (en) Space-time multi-channel deep learning system for automatic modulation recognition
CN110730037B (en) Optical signal-to-noise ratio monitoring method of coherent optical communication system based on momentum gradient descent method
CN109361471B (en) Optical communication signal modulation format identification method based on amplitude deviation analysis
CN111541483A (en) Optical signal-to-noise ratio monitoring method of coherent optical communication system based on high-order statistical moment
Guesmi et al. Experimental demonstration of simultaneous modulation format/symbol rate identification and optical performance monitoring for coherent optical systems
CN109379132B (en) Device and method for estimating optical fiber dispersion by low-speed coherent detection and neural network
CN113938188B (en) Construction method and application of optical signal-to-noise ratio monitoring model
CN110212976B (en) Optical signal-to-noise ratio monitoring method based on artificial neural network
CN111093123A (en) Flexible optical network time domain equalization method and system based on composite neural network
CN111541484A (en) Optical fiber communication system optical signal-to-noise ratio monitoring method based on time delay sampling
CN114553315B (en) Optical fiber nonlinear equalization method and system based on CNN-biRNN
Guesmi et al. Modulation formats recognition technique using artificial neural networks for radio over fiber systems
Liu et al. A three-stage training framework for customizing link models for optical networks
Lippiatt et al. Joint linear and nonlinear noise estimation of optical links by exploiting carrier phase recovery
CN113472435B (en) Method for simultaneously extracting optical signal modulation parameters and damage factors
Li et al. Modulation format identification based on an improved RBF neural network trained with asynchronous amplitude histogram
CN115173940B (en) Method and system for monitoring link joint damage of multi-channel optical transmission system
CN110855354B (en) Measuring device for shaping index of all-optical regenerator
Zhou et al. Simultaneous baud rate/modulation format identification and multi-parameter optical performance monitoring using multi-task learning with enhanced picture of Radon transform
Gao et al. Joint baud-rate and modulation format identification based on asynchronous delay-tap plots analyzer by using convolutional neural network
Xu et al. Optical performance monitoring in transparent fiber-optic networks using neural networks and asynchronous amplitude histograms
Guo et al. Deep neural network based chromatic dispersion estimation with ultra-low sampling rate for optical fiber communication systems
Cai et al. Optical filtering impairment monitoring based on artificial neural network in coherent receiver

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant