CN108880692B - Modulation format recognition and optical signal-to-noise ratio monitoring method for coherent optical communication system - Google Patents

Modulation format recognition and optical signal-to-noise ratio monitoring method for coherent optical communication system Download PDF

Info

Publication number
CN108880692B
CN108880692B CN201810576751.6A CN201810576751A CN108880692B CN 108880692 B CN108880692 B CN 108880692B CN 201810576751 A CN201810576751 A CN 201810576751A CN 108880692 B CN108880692 B CN 108880692B
Authority
CN
China
Prior art keywords
signals
signal
optical signal
different
monitoring
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
CN201810576751.6A
Other languages
Chinese (zh)
Other versions
CN108880692A (en
Inventor
易安林
闫连山
罗斌
潘炜
蒋林
盘艳
刘恒江
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.)
Southwest Jiaotong University
Original Assignee
Southwest Jiaotong University
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 Southwest Jiaotong University filed Critical Southwest Jiaotong University
Priority to CN201810576751.6A priority Critical patent/CN108880692B/en
Publication of CN108880692A publication Critical patent/CN108880692A/en
Application granted granted Critical
Publication of CN108880692B publication Critical patent/CN108880692B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • H04B10/60—Receivers
    • H04B10/61—Coherent receivers
    • 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
    • H04B10/60—Receivers
    • H04B10/61—Coherent receivers
    • H04B10/616—Details of the electronic signal processing in coherent optical receivers
    • 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
    • H04B10/60—Receivers
    • H04B10/61—Coherent receivers
    • H04B10/616—Details of the electronic signal processing in coherent optical receivers
    • H04B10/6161—Compensation of chromatic dispersion

Landscapes

  • Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Optical Communication System (AREA)

Abstract

The invention discloses a method for identifying modulation format and monitoring optical signal-to-noise ratio of a coherent optical communication system, which comprises the following steps: receiving at two polarization statesSignal ExAnd EyCarrying out dispersion compensation on the two signals, and carrying out pre-equalization on the signals by adopting a constant modulus algorithm to obtain a pre-equalized signal E'xAnd E'y(ii) a Signal E'xAnd E'yMapping to Stokes space to obtain the data in S1And S2Statistical distribution in vector direction S1dAnd S2dTo S1dAnd S2dPerforming first-order derivation on the fitted curve to obtain signals with different modulation formats and signals with different optical signal-to-noise ratios (OSNR) characteristic enhancement signals S'1And S'2(ii) a DNN algorithm-based neural network pair characteristic enhancement signal S'1And S'2Training is carried out, the characteristic information of signals with different modulation formats and different optical signal to noise ratios is extracted, and the identification of coherent optical communication modulation formats and the monitoring of the optical signal to noise ratios are carried out according to the information. The invention can adopt a single digital signal processing module to simultaneously realize signal modulation format identification and optical signal-to-noise ratio monitoring without changing the configuration of a coherent receiver.

Description

Modulation format recognition and optical signal-to-noise ratio monitoring method for coherent optical communication system
Technical Field
The invention belongs to the technical field of optical fiber communication, and particularly relates to a modulation format identification and optical signal-to-noise ratio monitoring method for a coherent optical communication system.
Background
In recent years, coherent optical detection and digital signal processing techniques have driven the capacity and transmission distance of optical fiber communication systems to increase. Meanwhile, the optical network construction becomes more dynamic, complex, transparent, flexible and reconfigurable. The link impairments experienced by signals in future long-haul, high capacity, dynamic and reconfigurable optical fiber communication systems will exhibit dynamic behavior. The real-time and accurate link characteristic monitoring technology is the key to realize the reliable transmission of the maximum capacity and the longest distance of signals by utilizing the existing system resources to the maximum extent. The optical signal to noise ratio (OSNR) is one of the key parameters that determine the performance of optical signal transmission, and largely determines the error rate of the system. Therefore, OSNR monitoring is one of the key technologies for performance monitoring of fiber optic communication systems. At present, the OSNR monitoring technology implemented by digital signal processing in the coherent optical communication system mainly includes: statistical moment based on equalized signals, Error Vector Magnitude (EVM) based, time delay interference technology, Stokes parameter monitoring, Gray sequence, shift filtering and power monitoring, RF spectrum monitoring, amplitude-dependent noise monitoring technology and the like.
In a dynamic, reconfigurable and efficient optical fiber communication network, in order to fully utilize system resources to realize reliable transmission of maximum capacity and longest distance of signals, parameters such as modulation formats, rates, signal powers and the like of signals are adaptively adjusted in the optical fiber communication system according to the scale of the system, application scenes and even system link conditions, so that the maximum utilization of the system resources and the reliable transmission of the signals are realized. The OSNR monitoring technique in a dynamic, reconfigurable, efficient fiber optic communication system must be able to adapt to different modulation formats. In addition, part of digital signal processing techniques at the coherent receiving end are also related to signal debugging formats, such as carrier phase recovery, polarization demultiplexing, and the like. Therefore, signal modulation format identification is also one of the key technologies in a dynamic, reconfigurable, efficient optical fiber communication system. Currently, the main techniques for modulation format identification are: k-means algorithm, signal clustering, variational Bayesian expectation maximization algorithm, peak-to-average power ratio estimation, Stokes space cluster point distribution and the like.
Most of the above techniques can only realize a single function, i.e., OSNR monitoring or modulation format recognition.
Disclosure of Invention
The present invention provides a method for identifying modulation format and monitoring optical signal-to-noise ratio of coherent optical communication system to solve the problem that the prior art only has single function of OSNR monitoring or modulation format identification.
In order to achieve the purpose, the invention adopts the technical scheme that:
a method for identifying modulation format and monitoring optical signal-to-noise ratio of coherent optical communication system includes:
receiving signals E in two polarization statesxAnd EyCarrying out dispersion compensation on the two signals, and carrying out pre-equalization on the signals by adopting a constant modulus algorithm to obtain a pre-equalized signal E'xAnd E'y；
Signal E'xAnd E'yMapping to Stokes space to obtain the data in S1And S2Statistical distribution in vector direction S1dAnd S2dTo S1dAnd S2dPerforming first-order derivation on the fitted curve to obtain signals with different modulation formats and signals with different optical signal-to-noise ratios (OSNR) characteristic enhancement signals S'1And S'2；
DNN algorithm-based neural network pair characteristic enhancement signal S'1And S'2Training is carried out, the characteristic information of signals with different modulation formats and different optical signal to noise ratios is extracted, and the identification of coherent optical communication modulation formats and the monitoring of the optical signal to noise ratios are carried out according to the information.
Preferably, for signal ExAnd EyThe method for performing dispersion compensation and pre-equalizing signals by adopting a constant modulus algorithm comprises the following steps:
combining signals E in two coherent states of polarizationxAnd EyPerforming dispersion compensation to obtain dispersion compensated signal
Figure GDA0002541520060000021
And
Figure GDA0002541520060000022
Figure GDA0002541520060000031
wherein the content of the first and second substances,
Figure GDA0002541520060000032
frequency domain impulse response function for CD compensation, where CD is dispersion, j is an imaginary unit, D is dispersion value of optical fiber, λ is signal center wavelength, z is optical fiber length, ω is angular frequency, c is speed of light in vacuum, IFFT [ ·]And FFT [ ·]Respectively, inverse fourier transform and fourier transform;
will signal
Figure GDA0002541520060000033
And
Figure GDA0002541520060000034
pre-equalizing by adopting a Constant Modulus Algorithm (CMA) to obtain a pre-equalized signal E'xAnd E'y：
Figure GDA0002541520060000035
Wherein h isxx，hxy，hyxAnd hyyThe four tap coefficients are based on a constant modulus algorithm FIR equalization filter.
Preferably, different modulation format signals and different optical signal-to-noise ratio signal characteristic enhancement signals S 'are obtained'1And S'2The method comprises the following steps:
signal E'xAnd E'yMapping into stokes space yields:
Figure GDA0002541520060000036
wherein S is0Is the total power, S, of the signals of two polarization states1、S2、S3Three mutually perpendicular direction vectors of a Stokes space are respectively;
mapping signal points to S1Vector direction sum S2Vector direction, respectively obtaining signals at S1VectorDirection and S2Statistical distribution S of vector directions1dAnd S2d；
To S1dAnd S2dPerforming curve fitting, and performing first-order derivation on the curve to obtain signals with different modulation formats and signals with different optical signal-to-noise ratios (OSNR) characteristic enhancement signals S'1And S'2。
Preferably, the method for extracting and identifying the feature information comprises the following steps:
enhancing the characteristic signal S'1And S'2The method comprises the steps of sending the signals into a neural network based on a DNN algorithm for training, and obtaining characteristic information of signals with different modulation formats and signals with different optical signal-to-noise ratios;
and performing feature extraction and identification on signals with different modulation formats and different optical signal to noise ratios according to the trained neural network based on the DNN algorithm, so as to realize identification of signal modulation format types and monitoring of corresponding signal optical signal to noise ratios.
The method for identifying the modulation format and monitoring the optical signal-to-noise ratio of the coherent optical communication system has the following beneficial effects:
the invention realizes the identification of the signal modulation format and the monitoring of the OSNR by using the same signal processing module on the premise of not changing the configuration of the coherent receiver, reduces the cost and the complexity of the system, and has important practical significance and application prospect in a dynamic, reconfigurable and high-efficiency optical fiber communication system. Besides, the invention is not only suitable for coherent optical communication systems, but also can be further expanded to mode multiplexing and multi-core multiplexing optical fiber communication systems, and has stronger practicability.
Drawings
Fig. 1 is a schematic block diagram of a modulation format identification and optical signal-to-noise ratio monitoring method of a coherent optical communication system.
Fig. 2 is a system block diagram of a modulation format identification and osnr monitoring method for a coherent optical communication system.
FIG. 3 shows S corresponding to different modulation formats of coherent optical communication system modulation format identification and optical signal-to-noise ratio monitoring method1And S2The statistical distribution of the vector directions fits a curve.
FIG. 4 shows S corresponding to different modulation formats of coherent optical communication system modulation format identification and optical signal-to-noise ratio monitoring method1Vector direction sum S2The statistical distribution of vector directions is fitted to a curve first derivative.
FIG. 5 shows S corresponding to PDM-QPSK signals under different OSNR conditions in a method for identifying modulation formats and monitoring optical signal-to-noise ratio of coherent optical communication systems1And S2The statistical distribution of the vector directions fits a curve.
FIG. 6 shows S corresponding to PDM-QPSK signals under different OSNR conditions in a coherent optical communication system modulation format recognition and optical signal-to-noise ratio monitoring method1And S2The statistical distribution of vector directions is fitted to a curve first derivative.
Fig. 7 is a structure diagram of a modulation format identification and osnr monitoring method DNN neural network of a coherent optical communication system.
Fig. 8 is a diagram of the modulation format recognition result of the coherent optical communication system modulation format recognition and optical signal-to-noise ratio monitoring method.
Fig. 9 is a diagram of a result of OSNR monitoring by coherent optical communication system modulation format identification and optical signal-to-noise ratio monitoring.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all matters produced by the invention using the inventive concept are protected.
According to an embodiment of the present application, referring to fig. 1 to 7, a modulation format identification and osnr monitoring method for a coherent optical communication system in the present solution includes the following specific steps:
referring to fig. 1, signal preprocessing.
Receiving signals E in two polarization statesxAnd EyPerforming dispersion compensation on the two signals to obtain dispersion-compensated signals
Figure GDA0002541520060000051
And
Figure GDA0002541520060000052
Figure GDA0002541520060000053
wherein the content of the first and second substances,
Figure GDA0002541520060000054
frequency domain impulse response function for CD compensation, where CD is dispersion, j is an imaginary unit, D is dispersion value of optical fiber, λ is signal center wavelength, z is optical fiber length, ω is angular frequency, c is speed of light in vacuum, IFFT [ ·]And FFT [ ·]Respectively an inverse fourier transform and a fourier transform.
Will signal
Figure GDA0002541520060000055
And
Figure GDA0002541520060000056
pre-equalizing by adopting a Constant Modulus Algorithm (CMA) to obtain a pre-equalized signal E'xAnd E'y：
Figure GDA0002541520060000061
Wherein h isxx，hxy，hyxAnd hyyThe four tap coefficients are based on a constant modulus algorithm FIR equalization filter.
The signal characteristics are enhanced.
Signal E'xAnd E'yMapping to a Stokes space, wherein the mapping process is as follows:
Figure GDA0002541520060000062
wherein S is0Is the total power, S, of the signals of two polarization states1、S2、S3Three mutually perpendicular direction vectors of the stokes space.
Mapping signal points to S in Stokes space1Vector direction sum S2Vector direction, respectively obtaining signals at S1Vector direction sum S2Statistical distribution S of vector directions1dAnd S2d. Different modulation format signals and different optical signal-to-noise ratio signals are at S1Vector direction sum S2The statistical distribution of vector directions will exhibit different characteristics.
To further enhance the signal at S for different modulation formats and different optical signal-to-noise ratios1Vector direction sum S2Statistical difference features in vector direction, and signal obtained by the method at S1Vector direction sum S2Statistical distribution S of vector directions1dAnd S2dFitting, and performing one-stage derivation on the fitted curve to obtain signals with different modulation formats and signals with different optical signal-to-noise ratios (OSNR) characteristic enhancement signals S'1And S'2。
And extracting and identifying signal features.
Enhancing the characteristic signal S'1And S'2The method comprises the steps of sending the signals into a neural network based on a DNN algorithm for training, and obtaining characteristic information of signals with different modulation formats and signals with different optical signal-to-noise ratios;
and performing feature extraction and identification on signals with different modulation formats and different optical signal to noise ratios according to the trained neural network based on the DNN algorithm, so as to realize identification of signal modulation format types and monitoring of corresponding signal optical signal to noise ratios.
Referring to fig. 2, a block diagram of a communication system for transmitting and receiving signals of the present invention is shown.
The whole communication system comprises a sending end, a transmission link and a receiving end which are in signal connection in sequence.
The transmitting end utilizes two IQ modulators and a polarization coupler (PBC) to generate various modulation formats such as PDM-QPSK, PDM-8QAM, PDM-16QAM and PDM-32QAM with a Baud rate of 2 × 28G, wherein the linewidth of the laser is 100kHz, and the central wavelength is 1550 nm.
The transmission chain is composed of an adjustable attenuator, a fiber amplifier (EDFA1) and a transmission fiber, wherein the adjustable attenuator and the fiber amplifier (EDFA1) are used for adjusting the OSNR and the fiber power of the system.
The receiving end mainly comprises a preamplifier (EDFA1), a local oscillator laser (L O), a 90-degree optical mixer, a balance detector, an analog-to-digital converter and a digital signal processing part (DSP), wherein the DSP part is used for identifying the signal modulation format and monitoring the OSNR of the invention.
Referring to fig. 3, two sets of subgraphs are included, graph (a) and graph (b). Wherein, the graph (a) corresponds to PDM-QPSK, PDM-8QAM, PDM-16QAM and PDM-32QAM S, respectively1The statistical distribution of the vector directions fits a curve.
Graph (b) corresponds to PDM-QPSK, PDM-8QAM, PDM-16QAM and PDM-32QAM S, respectively2The statistical distribution of the vector directions fits a curve.
As can be seen from fig. 3, graphs (a) and (b), the fitted curves corresponding to different modulation formats show different signal characteristics.
Referring to fig. 4, two sets of subgraphs are included, graph (a) and graph (b). Wherein, the graph (a) is corresponding to PDM-QPSK, PDM-8QAM, PDM-16QAM and PDM-32QAM S respectively1First-order derivation S of statistical distribution fitting curve in vector direction1'。
Graph (b) corresponds to PDM-QPSK, PDM-8QAM, PDM-16QAM and PDM-32QAM S, respectively2Statistical distribution fitting curve first-order derivation S 'in vector direction'2。
Comparing the graphs in fig. 3, the curve characteristics corresponding to different modulation formats are more obvious after the first derivation. That is, enhancement of signal characteristics of different modulation formats can be achieved by first order derivation.
Referring to fig. 5, two sets of subgraphs are included, fig. 5 (a) and fig. 5 (b). Wherein, fig. 5 (a) and fig. 5 (b) are S corresponding to PDM-QPSK signals with OSNR of 8dB, 10dB, 12dB, 14dB, 16dB and 18dB, respectively1And S2The statistical distribution of the vector directions fits a curve. As can be seen, the signal is at S under different OSNR conditions1And S2The statistical distribution of the vector directions shows different characteristics to the fitted curve.
Referring to fig. 6, two groups including (a) of fig. 6 and (b) of fig. 6 are includedAnd (4) sub-graph. Wherein, fig. 6 (a) and fig. 6 (b) are S corresponding to PDM-QPSK signals with OSNR of 8dB, 10dB, 12dB, 14dB, 16dB and 18dB, respectively1And S2First-order derivation S of vector direction statistical distribution fitting curve1'and S'2。
As can be seen from comparison with fig. 5, the curve characteristics corresponding to different modulation formats are more obvious after the first derivation. That is, enhancement of different OSNR signal characteristics can be achieved by 1-order derivation.
Referring to fig. 7, we used a 4-layer DNN neural network in experimental validation of the present invention, where the numbers of neurons in the first, second, third and fourth layers were 160, 80, 100 and 4, respectively. Based on the neural network, the method is used for realizing the identification of the signal modulation format type and the monitoring of the corresponding signal optical signal to noise ratio.
Referring to fig. 8, fig. 8 includes four sub-graphs, and the four graphs are sorted by a, b, c, and d, with the sequence number located at the upper left corner of the graph. (a), (b), (c) and (d) of FIG. 8 correspond to the recognition rates of PDM-QPSK, PDM-8QAM, PDM-16QAM and PDM-32QAM under different OSNR conditions, respectively. As can be seen from the figure, the present invention can achieve 100% identification of modulation formats in the OSNR corresponding to the 7% FEC threshold and the range above the OSNR.
Referring to fig. 9, which includes four subgraphs, the ordering is the same as fig. 8. Wherein (a), (b), (c) and (d) of FIG. 9 correspond to the monitoring results of PDM-QPSK, PDM-8QAM, PDM-16QAM and PDM-32QAM within different OSNR ranges, respectively. As can be seen from the figure, the invention can realize the accurate monitoring of the system OSNR at the OSNR value corresponding to the 7% FEC threshold value and the range above the OSNR value.
In conclusion, the method of the present invention is further verified by a plurality of drawings, and it can be obtained that the present invention can simultaneously realize signal modulation format identification and OSNR monitoring by using a single digital signal processing module without changing the hardware configuration of a coherent receiver, and has important practical significance and application prospect in a dynamic, reconfigurable and efficient optical fiber communication system, and strong practicability and popularization.
While the embodiments of the invention have been described in detail in connection with the accompanying drawings, it is not intended to limit the scope of the invention. Various modifications and changes may be made by those skilled in the art without inventive step within the scope of the appended claims.

Claims (3)

1. A method for identifying modulation format and monitoring optical signal-to-noise ratio of coherent optical communication system is characterized by comprising the following steps:
receiving signals E in two polarization statesxAnd EyCarrying out dispersion compensation on the two signals, and carrying out pre-equalization on the signals by adopting a constant modulus algorithm to obtain a pre-equalized signal E'xAnd E'y；
Will the signal E'xAnd E'yMapping to Stokes space to obtain the data in S1And S2Statistical distribution in vector direction S1dAnd S2dTo said S1dAnd S2dPerforming first-order derivation on the fitted curve to obtain signals with different modulation formats and signals with different optical signal-to-noise ratios (OSNR) characteristic enhancement signals S'1And S'2The method comprises the following steps:
will the signal E'xAnd E'yMapping into stokes space yields:
Figure FDA0002506274430000011
wherein S is0Is the total power, S, of the signals of two polarization states1、S2、S3Three mutually perpendicular direction vectors of a Stokes space are respectively;
mapping signal points to S1Vector direction sum S2Vector direction, respectively obtaining signals at S1Vector direction sum S2Statistical distribution S of vector directions1dAnd S2d；
For the S1dAnd S2dPerforming curve fitting, and performing first-order derivation on the curve to obtain signals with different modulation formats and signals with different optical signal-to-noise ratios (OSNR) characteristic enhancement signals S'1And S'2；
DNN algorithm-based neural network pair characteristic enhancement signal S'1And S'2Training is carried out, feature signals of signals with different modulation formats and different optical signal to noise ratios are extracted, and identification of coherent optical communication modulation formats and monitoring of the optical signal to noise ratios are carried out according to the extracted feature signals of the signals with different modulation formats and different optical signal to noise ratios.
2. The method as claimed in claim 1, wherein the signal E is a signal ExAnd EyThe method for performing dispersion compensation and pre-equalizing signals by adopting a constant modulus algorithm comprises the following steps:
combining signals E in two coherent states of polarizationxAnd EyPerforming dispersion compensation to obtain dispersion compensated signal
Figure FDA0002506274430000021
And
Figure FDA0002506274430000022
Figure FDA0002506274430000023
wherein the content of the first and second substances,
Figure FDA0002506274430000024
frequency domain impulse response function for CD compensation, where CD is dispersion, j is an imaginary unit, D is dispersion value of optical fiber, λ is signal center wavelength, z is optical fiber length, ω is angular frequency, c is speed of light in vacuum, IFFT [ ·]And FFT [ ·]Respectively, inverse fourier transform and fourier transform;
will the signal
Figure FDA0002506274430000025
And
Figure FDA0002506274430000026
pre-equalizing by adopting a constant modulus algorithm CMA to obtain a pre-equalized signal E'xAnd E'y：
Figure FDA0002506274430000027
Wherein h isxx，hxy，hyxAnd hyyThe four tap coefficients are based on a constant modulus algorithm FIR equalization filter.
3. The method for modulation format recognition and optical signal-to-noise ratio monitoring of the coherent optical communication system according to claim 1, wherein the method for extracting and recognizing the characteristic signal comprises:
enhancing the characteristic by a signal S'1And S'2Sending the signals into a neural network based on a DNN algorithm for training to obtain characteristic signals of signals with different modulation formats and signals with different optical signal-to-noise ratios;
and performing feature extraction and identification on signals with different modulation formats and different optical signal to noise ratios according to the trained neural network based on the DNN algorithm, so as to realize identification of signal modulation format types and monitoring of corresponding signal optical signal to noise ratios.
CN201810576751.6A 2018-06-05 2018-06-05 Modulation format recognition and optical signal-to-noise ratio monitoring method for coherent optical communication system Active CN108880692B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810576751.6A CN108880692B (en) 2018-06-05 2018-06-05 Modulation format recognition and optical signal-to-noise ratio monitoring method for coherent optical communication system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810576751.6A CN108880692B (en) 2018-06-05 2018-06-05 Modulation format recognition and optical signal-to-noise ratio monitoring method for coherent optical communication system

Publications (2)

Publication Number Publication Date
CN108880692A CN108880692A (en) 2018-11-23
CN108880692B true CN108880692B (en) 2020-08-04

Family

ID=64336968

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810576751.6A Active CN108880692B (en) 2018-06-05 2018-06-05 Modulation format recognition and optical signal-to-noise ratio monitoring method for coherent optical communication system

Country Status (1)

Country Link
CN (1) CN108880692B (en)

Families Citing this family (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109450836B (en) * 2018-12-14 2020-05-29 北京理工大学 Method for identifying modulation format of optical digital communication with state transition probability distribution
CN109474336B (en) * 2019-01-08 2020-11-06 北京科技大学 Optical signal-to-noise ratio monitoring device and monitoring method
CN109587091B (en) * 2019-01-23 2020-09-29 西南交通大学 Modulation format identification method of coherent optical communication system based on logistic regression algorithm
CN110048781B (en) * 2019-04-17 2020-06-09 武汉邮电科学研究院有限公司 Method and device for identifying optical signal modulation format
CN110445550A (en) * 2019-08-08 2019-11-12 深圳市深光谷科技有限公司 A kind of coherent light direct detecting method, device and optical communication system
CN110601764A (en) * 2019-09-16 2019-12-20 西南交通大学 Radio frequency modulation format identification method based on optical assistance
CN110830404A (en) * 2019-10-31 2020-02-21 西南交通大学 Digital mobile forward signal quantization method based on vector linear prediction
CN111314254A (en) * 2019-12-25 2020-06-19 中国传媒大学 Signal modulation mode identification method and equipment
CN111313974A (en) * 2020-02-14 2020-06-19 北京理工大学 Modulation format identification method for signal amplitude sequencing and ratio calculation
CN111970050B (en) * 2020-07-14 2022-03-15 电子科技大学 System for jointly monitoring modulation format and optical signal-to-noise ratio based on anomaly detection
CN114070684B (en) * 2020-08-05 2024-02-09 西南交通大学 Modulation signal identification method based on two-dimensional convolutional neural network
CN112039586A (en) * 2020-08-21 2020-12-04 武汉邮电科学研究院有限公司 OSNR measuring method, device and system based on digital signal processing
CN112532314B (en) * 2020-11-27 2022-03-04 烽火通信科技股份有限公司 Method and device for predicting transmission performance of optical network
CN112565133B (en) * 2021-02-26 2021-05-28 南京信息工程大学 Complex format analysis method based on high-dimensional information feature extraction
CN113452439B (en) * 2021-06-28 2022-07-01 聊城大学 Key parameter joint monitoring method in elastic optical network
CN114257888B (en) * 2021-12-03 2023-09-15 武汉邮电科学研究院有限公司 Adaptive coding and equalization method for PON system and PON system
CN114584212B (en) * 2022-04-15 2023-12-08 中国电子科技集团公司第三十四研究所 Modulation format and optical signal to noise ratio monitoring method for feature similarity analysis
CN115589264B (en) * 2022-08-29 2024-03-22 电子科技大学 All-digital coherent receiving system of all-neural network

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103944638A (en) * 2014-04-18 2014-07-23 华中科技大学 Optical signal modulation format recognition method and system based on nonlinear digital processing

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103281120B (en) * 2013-05-30 2015-10-14 华中科技大学 A kind of optical signal modulation format identification method and system
RU2696560C2 (en) * 2015-03-09 2019-08-05 ИСиАй ТЕЛЕКОМ ЛТД. Method of controlling operation of channels and optical communication system
CN105790849B (en) * 2016-05-10 2018-05-22 中山大学 A kind of modulation format recognition methods towards coherent optical communication system
CN107018108B (en) * 2017-05-10 2019-12-20 西南交通大学 Modulation format identification method for two-dimensional plane of Stokes space

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103944638A (en) * 2014-04-18 2014-07-23 华中科技大学 Optical signal modulation format recognition method and system based on nonlinear digital processing

Also Published As

Publication number Publication date
CN108880692A (en) 2018-11-23

Similar Documents

Publication Publication Date Title
CN108880692B (en) Modulation format recognition and optical signal-to-noise ratio monitoring method for coherent optical communication system
US9735991B1 (en) System and methods for autonomous signal modulation format identification
US8472813B2 (en) Computationally-efficient MIMO equalization algorithm for high-speed, real-time, adaptive polarization multiplexed (POLMUX) OFDM transmission with direct detection
US20130138375A1 (en) System and Methods for Adaptive Equalization for Optical Modulation Formats
CN109347776B (en) Method for identifying modulation format of optical communication signal with differential phase-to-amplitude ratio
CN105790849A (en) Modulation format recognition method for coherent optical communication system
CN105281862A (en) Polarization multiplexing direct detection system and method
CN111541483A (en) Optical signal-to-noise ratio monitoring method of coherent optical communication system based on high-order statistical moment
WO2023245828A1 (en) Compensation method for distorted signal of multi-carrier access network, and nonlinear equalizer
Yu et al. A modified PSO assisted blind modulation format identification scheme for elastic optical networks
CN113364527B (en) Nonlinear damage compensation method suitable for high-speed coherent polarization multiplexing system
CN113542172B (en) Elastic optical network modulation format identification method and system based on improved PSO clustering
CN109587091B (en) Modulation format identification method of coherent optical communication system based on logistic regression algorithm
CN116389207A (en) Modulation format identification method based on signal amplitude histogram
CN113285762B (en) Modulation format identification method based on relative entropy calculation
CN113364519B (en) Optical performance monitoring method and device, electronic equipment and storage medium
Wang et al. A novel modulation format identification based on amplitude histogram space
CN113452439B (en) Key parameter joint monitoring method in elastic optical network
CN114531328B (en) Modulation format identification method based on signal envelope flatness
CN114584212B (en) Modulation format and optical signal to noise ratio monitoring method for feature similarity analysis
He et al. Advanced modulation formats for 4× 100Gbps computing power optical networks and AI-based format recognition
CN115378507B (en) Noise equalization method and device suitable for multi-eigenvalue nonlinear frequency division multiplexing system
Yao et al. MPT-Transformer based post equalizer utilized in underwater visible light communication system
Felipe et al. Reduced-complexity chromatic dispersion compensation method
Liu et al. A Machine Learning Method for Fiber Nonlinear Compensation

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