CN109587091B - Modulation format identification method of coherent optical communication system based on logistic regression algorithm - Google Patents
Modulation format identification method of coherent optical communication system based on logistic regression algorithm Download PDFInfo
- Publication number
- CN109587091B CN109587091B CN201910062075.5A CN201910062075A CN109587091B CN 109587091 B CN109587091 B CN 109587091B CN 201910062075 A CN201910062075 A CN 201910062075A CN 109587091 B CN109587091 B CN 109587091B
- Authority
- CN
- China
- Prior art keywords
- signals
- variance
- modulation format
- signal
- formula
- 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
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L27/00—Modulated-carrier systems
- H04L27/0012—Modulated-carrier systems arrangements for identifying the type of modulation
-
- 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
-
- 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
- H04B10/6164—Estimation or correction of the frequency offset between the received optical signal and the optical local oscillator
-
- 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
- H04B10/6165—Estimation of the phase of the received optical signal, phase error estimation or phase error correction
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Optical Communication System (AREA)
Abstract
The invention discloses a coherent light communication system modulation format identification method based on a logistic regression algorithm, which comprises the following steps: s1: transmitting an original signal; s2: preprocessing a received signal; s3: carrying out PSK and QAM signal classification; s4: carrying out modulation format identification; the invention solves the problems of higher algorithm complexity and high cost investment in the prior art.
Description
Technical Field
The invention belongs to the technical field of coherent optical fiber communication, and particularly relates to a modulation format identification method of a coherent optical communication system based on a logistic regression algorithm.
Background
Global IP traffic continues to grow exponentially due to bandwidth scarcity and cloud services. Optical networks are evolving into more flexible and adaptive architectures. Next generation optical fiber communication systems can allocate bandwidth and modulation formats according to the needs of each user. In order to implement an intelligent network, an important component of a dynamic receiver is a modulation format identification module, which configures the corresponding receiver according to the code pattern of the received signal. Various modulation format identification techniques have been proposed in the prior art, such as from amplitude distribution, nonlinear power spectra, clustering in stokes space, constellation identification based on Convolutional Neural Networks (CNN), and so on.
The complexity of the algorithms is high, and a scheme with low complexity and high robustness is required to be used for realizing lower time delay under the premise of keeping stability in an optical communication system; in addition, when the system is improved in the prior art, equipment needs to be added, and the cost investment is large.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the coherent optical communication system modulation format identification method which is low in complexity, good in robustness, more flexible and self-adaptive for the next generation and based on the logistic regression algorithm, reduces the cost investment and is used for solving the problems of high algorithm complexity and large cost investment in the prior art.
In order to achieve the purpose of the invention, the invention adopts the technical scheme that:
a coherent optical communication system modulation format identification method based on a logistic regression algorithm comprises the following steps:
s1: preprocessing a received signal: receiving the modulated signals on the two polarization states, and preprocessing the signals to obtain preprocessed signals;
s2: and (3) carrying out PSK and QAM signal classification: selecting a preprocessed signal, calculating the amplitude variance of the preprocessed signal, and classifying the preprocessed signal according to the distribution characteristics of the amplitude variance;
the classification category comprises PSK signals and QAM signals;
s3: carrying out modulation format identification: and carrying out 4-power operation and Fourier transformation on the classified signals in sequence to obtain transformed signals, calculating the variance and the mean of the transformed signals, and identifying a specific modulation format by using a logistic regression-based algorithm according to the distribution characteristics of the variance and the mean and the classification category corresponding to the current transformed signals to obtain the modulation format type of the signals.
Further, in step S1, the preprocessing includes a dispersion compensation process and a pre-equalization process performed in sequence.
Further, a CMA algorithm is used for pre-equalization processing.
Further, in step S2, the calculation formula of the amplitude variance is:
d=D(|E'|)
in the formula, d is an amplitude variance; | · | is the modulo operation; d (-) is the variance calculation; e' is the selected preprocessed signal.
Further, in step S3, 4 th power operation and fourier transform are sequentially performed on the classified signal to obtain a transformed signal, and the calculation formula is as follows:
EFFT=|FFT[(E')4]|
in the formula, EFFTIs a transformed signal; (.)44 power operation is carried out; FFT (-) is a Fourier transform operation; | · | is the modulo operation.
Further, in step S3, the calculation formula of the variance and the mean is:
in the formula, σ2Is the variance; d (-) is the variance calculation; e is the mean value; e (-) is the mean value calculation operation; eFFTIs a transformed signal.
Further, the specific formula of the variance calculation is as follows:
in the formula, D (·) is a variance calculation operation; h ismIs the value of the current sampling point;is the mean of the current signal; m is a sampling point variable; m is the total number of sampling points of the current signal.
Further, the specific formula of the mean value solving operation is as follows:
in the formula, E (-) is the average value calculation operation; h ismIs the value of the current sampling point; m is a sampling point variable; m is the total number of sampling points of the current signal.
Further, in step S4, a logistic regression algorithm is used to fit a cubic polynomial curve for specific modulation format identification.
The invention has the beneficial effects that:
on the premise of not changing the configuration of a coherent receiver, the modulation format recognition function is realized by using the low-complexity logistic regression algorithm, the complexity is greatly reduced, the logistic regression algorithm has better robustness, and the method has important practical significance and application prospect in the next generation optical fiber communication system, does not need to add equipment, and reduces the cost input.
Drawings
FIG. 1 is a flow chart of a modulation format identification method for a coherent optical communication system based on a logistic regression algorithm;
FIG. 2 is a plot of variance versus amplitude for each modulation format;
FIG. 3 is an amplitude variance distribution plot;
FIG. 4 is a variance-mean distribution plot of a PSK signal and a QAM signal;
FIG. 5 is a comparison of the recognition accuracy of each modulation format;
fig. 6 is a block diagram of a coherent optical communication system.
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.
A coherent optical communication system modulation format identification method based on a logistic regression algorithm is disclosed, as shown in FIG. 1, and comprises the following steps:
s1: preprocessing a received signal: receiving the modulated signals E in two polarization statesxAnd EyAnd pre-processing the signal by using a digital signal processing module to obtain a pre-processed signal E'xAnd E'y;
The pretreatment comprises dispersion compensation treatment and pre-equalization treatment which are sequentially carried out;
firstly, carrying out dispersion compensation processing to obtain a signal after dispersion compensationAnd
compensating the processed signal for dispersionAndperforming preliminary demultiplexing and channel equalization by adopting a CMA-based pre-equalization algorithm to obtain a pre-equalized signal E'xAnd E'yAnd used as a pre-processed signal;
s2: and (3) carrying out PSK and QAM signal classification: selecting a preprocessed Signal E'xOr E'yCalculating the amplitude variance d of the signals, and classifying according to the amplitude variance d and the signal modulation mode;
the classification category comprises PSK signals and QAM signals;
the theoretical basis is as follows: as shown in fig. 2, the amplitude of the PSK signal is a gaussian distribution, while the amplitude of the QAM signal is a superposition of a plurality of gaussian distributions, as shown in fig. 3, the difference of the variance increases with the increase of the signal-to-noise ratio, and a threshold is set between the QAM and the PSK amplitude variance to classify the PSK signal and the QAM signal;
s3: carrying out modulation format identification: 4 power operation and Fourier transformation are carried out on the classified signals in sequence to obtain transformed signals EFFTCalculating its variance σ2And the mean e, and according to the variance σ2Fitting a cubic polynomial curve by using a logistic regression-based algorithm according to the distribution characteristics of the mean value e and the classification category corresponding to the current transformed signal, as shown in fig. 4, identifying a specific modulation format to obtain the modulation format type of the signal, wherein the accuracy of the identification result is shown in fig. 5;
the theoretical basis is as follows: the 4 th power operation of the signal will eliminate the phase differenceA point of (a);
distinguish between 16QAM and QPSK: e according to 16QAM and QPSKFFTThe profile has a peak value, 16QAM has a total of 3 amplitudes, and the phase difference between the two amplitudes isAfter the phase difference transformation is eliminated by the power of 4, a peak value appears, and similarly, the phase difference between every two points of QPSKA peak value appears after 4-power phase difference elimination transformation;
differentiate between QPSK and 8 PSK: e of QPSKFFTThe profile has a peak value, E of 8PSKFFTThe distribution map has no peak, according to its variance σ2And the mean value e, the mean value-variance distribution of the obtained values is different, and the obtained values are distinguished according to a cubic polynomial curve fitted based on a logistic regression algorithm;
similarly, 16QAM and 32QAM are distinguished.
In this embodiment, in step S3, the calculation formula of the amplitude variance is:
d=D(|E'|)
in the formula, d is an amplitude variance; | · | is the modulo operation; d (-) is the variance calculation; e' is the selected preprocessed signal.
In this embodiment, in step S4, 4 th power operation and fourier transform are sequentially performed on the classified signals to obtain transformed signals, and the calculation formula is as follows:
EFFT=|FFT[(E')4]|
in the formula, EFFTIs a transformed signal; (.)44 power operation is carried out; FFT (-) is a Fourier transform operation; | · | is the modulo operation.
In this embodiment, in step S4, the formula for calculating the variance and the mean is:
in the formula, σ2Is the variance; d (-) is the variance calculation; e is the mean value; e (-) is the mean value calculation operation; eFFTIs a transformed signal;
the specific formula of the variance calculation is as follows:
in the formula, D (·) is a variance calculation operation; h ismIs the value of the current sampling point;is the mean of the current signal; m is a sampling point variable; m is the total number of sampling points of the current signal.
The specific formula of the mean value calculation operation is as follows:
in the formula, E (-) is the average value calculation operation; h ismIs the value of the current sampling point; m is a sampling point variable; m is the total number of sampling points of the current signal.
In this embodiment, the coherent optical communication system, as shown in fig. 6, includes a transmitting end, a transmission link, and a receiving end, which are connected in sequence;
the transmitting end comprises a laser and a coherent modulator which are sequentially connected, the line width of the laser is 100kHz, and the central wavelength of the laser is 1550 nm; the coherent modulator comprises two IQ modulators which are arranged in parallel, and two ends of the two IQ modulators are respectively connected with the laser and the first optical fiber amplifier;
the transmission link comprises a first optical fiber amplifier, an optical fiber and a second optical fiber amplifier which are connected in sequence;
the receiving end comprises a preamplifier, a coherent demodulation receiver and a digital signal processing module which are connected in sequence;
the coherent modulator is connected with the first optical fiber amplifier, and the second optical fiber amplifier is connected with the coherent demodulation receiver; the first optical fiber amplifier and the second optical fiber amplifier are both erbium-doped fiber amplifiers EDFAs;
the digital signal processing module is used for processing digital signals, and the digital signal processing comprises dispersion compensation, clock recovery, CMA (constant amplitude equalization), modulation format identification, adaptive equalization, frequency offset estimation, phase recovery and code element judgment and decoding which are sequentially performed, wherein the dispersion compensation, the clock recovery and the CMA pre-equalization are not required to obtain modulation format information.
The coherent optical communication system modulation format identification method based on the logistic regression algorithm is low in complexity, good in robustness, more flexible and adaptive for the next generation, reduces cost investment, and solves the problems of high algorithm complexity and high cost investment in the prior art.
Claims (6)
1. A coherent optical communication system modulation format identification method based on a logistic regression algorithm is characterized by comprising the following steps:
s1: preprocessing a received signal: receiving the modulated signals in the two polarization states, and performing dispersion compensation processing on the two signals to obtain two signals after dispersion compensation; carrying out primary demultiplexing and channel equalization on the two signals subjected to dispersion compensation by adopting a CMA-based pre-equalization algorithm to obtain two preprocessed signals;
s2: and (3) carrying out PSK and QAM signal classification: selecting a preprocessed signal, calculating the amplitude variance of the preprocessed signal, and classifying the preprocessed signal according to the distribution characteristics of the amplitude variance;
the classification categories include PSK signals and QAM signals;
s3: carrying out modulation format identification: and sequentially carrying out 4-power operation and Fourier transformation on the classified signals to obtain transformed signals, calculating the variance and the mean value of the transformed signals, fitting a cubic polynomial curve by using a logistic regression-based algorithm according to the distribution characteristics of the variance and the mean value and the classification category corresponding to the current transformed signals, identifying a specific modulation format, and obtaining the modulation format type of the signals.
2. The method for identifying the modulation format of the coherent optical communication system based on the logistic regression algorithm as claimed in claim 1, wherein in the step S2, the calculation formula of the amplitude variance is:
d=D(|E'|)
in the formula, d is an amplitude variance; | · | is the modulo operation; d (-) is the variance calculation; e' is the selected preprocessed signal.
3. The method for identifying the modulation format of the coherent optical communication system based on the logistic regression algorithm as claimed in claim 2, wherein in step S3, the classified signals are sequentially processed by 4 th power operation and fourier transform to obtain transformed signals, and the calculation formula is as follows:
EFFT=|FFT[(E')4]|
in the formula, EFFTIs a transformed signal; (.)44 power operation is carried out; FFT (-) is a Fourier transform operation; | · | is the modulo operation.
4. The method for identifying the modulation format of the coherent optical communication system based on the logistic regression algorithm as claimed in claim 1, wherein in the step S3, the calculation formula of the variance and the mean value is:
in the formula, σ2Is the variance; d (-) is the variance calculation; e is the mean value; e (-) is the mean value calculation operation; eFFTIs a transformed signal.
5. The method for identifying the modulation format of the coherent optical communication system based on the logistic regression algorithm according to claim 4, wherein the specific formula of the variance calculation is as follows:
6. The method for identifying the modulation format of the coherent optical communication system based on the logistic regression algorithm according to claim 5, wherein the specific formula of the mean value solving operation is as follows:
in the formula, E (-) is the average value calculation operation; h ismIs the value of the current sampling point; m is a sampling point variable; m is the total number of sampling points of the current signal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910062075.5A CN109587091B (en) | 2019-01-23 | 2019-01-23 | Modulation format identification method of coherent optical communication system based on logistic regression algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910062075.5A CN109587091B (en) | 2019-01-23 | 2019-01-23 | Modulation format identification method of coherent optical communication system based on logistic regression algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109587091A CN109587091A (en) | 2019-04-05 |
CN109587091B true CN109587091B (en) | 2020-09-29 |
Family
ID=65917733
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910062075.5A Active CN109587091B (en) | 2019-01-23 | 2019-01-23 | Modulation format identification method of coherent optical communication system based on logistic regression algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109587091B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
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 |
CN115643141A (en) * | 2022-10-17 | 2023-01-24 | 西南交通大学 | Modulation format identification method of probability shaping coherent optical communication system based on signal nonlinear power change |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104301056A (en) * | 2014-11-03 | 2015-01-21 | 成都中星世通电子科技有限公司 | Frequency spectrum monitoring method based on signal feature analysis |
CN104796366A (en) * | 2015-04-10 | 2015-07-22 | 长春理工大学 | Communication signal system identification system and method |
US9729362B1 (en) * | 2013-03-20 | 2017-08-08 | Georgia Tech Research Corporation | Systems and methods for autonomous signal modulation format identification |
CN108768907A (en) * | 2018-01-05 | 2018-11-06 | 南京邮电大学 | A kind of Modulation Identification method based on temporal characteristics statistic and BP neural network |
CN108900454A (en) * | 2018-06-28 | 2018-11-27 | 北京邮电大学 | A kind of modulation system parameter blind detection method and device based on machine learning |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130028306A1 (en) * | 2011-07-26 | 2013-01-31 | Cristina Seibert | Systems and methods for multimode signal acquisition |
CN103684600B (en) * | 2012-09-14 | 2016-08-31 | 富士通株式会社 | The updating device of equalizer coefficients and method and receiver and optical communication system |
CN103199945B (en) * | 2013-03-29 | 2016-06-01 | 南京信息职业技术学院 | Method for identifying modulation mode of cognitive radio signal under low signal-to-noise ratio condition |
CN104009951B (en) * | 2014-06-17 | 2017-10-03 | 北京邮电大学 | Signal modulation mode recognition methods and system based on multi-scale wavelet transformation |
CN106059969B (en) * | 2016-06-16 | 2019-12-03 | 中国科学院信息工程研究所 | A kind of Modulation Identification method and device based on envelope square spectrum analysis |
CN106330805B (en) * | 2016-08-29 | 2019-08-09 | 重庆会凌电子新技术有限公司 | A kind of signal modulation mode automatic identifying method and system |
CN106789788B (en) * | 2016-12-26 | 2019-05-10 | 北京邮电大学 | A kind of wireless digital signal Modulation Mode Recognition method and device |
CN106899531B (en) * | 2017-03-01 | 2020-04-07 | 西安电子科技大学 | Method for identifying satellite communication signal modulation mode |
CN108880692B (en) * | 2018-06-05 | 2020-08-04 | 西南交通大学 | Modulation format recognition and optical signal-to-noise ratio monitoring method for coherent optical communication system |
CN109067678B (en) * | 2018-06-22 | 2020-12-11 | 达新宇 | WFRFT signal cascade modulation identification method based on high-order cumulant and wireless communication system |
-
2019
- 2019-01-23 CN CN201910062075.5A patent/CN109587091B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9729362B1 (en) * | 2013-03-20 | 2017-08-08 | Georgia Tech Research Corporation | Systems and methods for autonomous signal modulation format identification |
CN104301056A (en) * | 2014-11-03 | 2015-01-21 | 成都中星世通电子科技有限公司 | Frequency spectrum monitoring method based on signal feature analysis |
CN104796366A (en) * | 2015-04-10 | 2015-07-22 | 长春理工大学 | Communication signal system identification system and method |
CN108768907A (en) * | 2018-01-05 | 2018-11-06 | 南京邮电大学 | A kind of Modulation Identification method based on temporal characteristics statistic and BP neural network |
CN108900454A (en) * | 2018-06-28 | 2018-11-27 | 北京邮电大学 | A kind of modulation system parameter blind detection method and device based on machine learning |
Also Published As
Publication number | Publication date |
---|---|
CN109587091A (en) | 2019-04-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108880692B (en) | Modulation format recognition and optical signal-to-noise ratio monitoring method for coherent optical communication system | |
Wang et al. | Nonlinear decision boundary created by a machine learning-based classifier to mitigate nonlinear phase noise | |
CN109587091B (en) | Modulation format identification method of coherent optical communication system based on logistic regression algorithm | |
CN109347776B (en) | Method for identifying modulation format of optical communication signal with differential phase-to-amplitude ratio | |
CN113141325B (en) | Training method, identification method and device for optical OFDM signal subcarrier modulation format identification model | |
Bo et al. | Modulation format recognition for optical signals using connected component analysis | |
CN109347775B (en) | Modulation format identification method combining intensity fluctuation and phase fluctuation characteristics | |
EP3146690B1 (en) | Method and apparatus for recovering time-domain hybrid modulated qam signals | |
CN109450836B (en) | Method for identifying modulation format of optical digital communication with state transition probability distribution | |
Xiang et al. | Joint and accurate OSNR estimation and modulation format identification scheme using the feature-based ANN | |
Yu et al. | A modified PSO assisted blind modulation format identification scheme for elastic optical networks | |
Hao et al. | Stokes space modulation format identification for optical signals using probabilistic neural network | |
CN102035602A (en) | Optimal channel coding modulation-based adaptive optical transmission system and method | |
CN113364527B (en) | Nonlinear damage compensation method suitable for high-speed coherent polarization multiplexing system | |
CN113542172A (en) | Elastic optical network modulation format identification method and system based on improved PSO clustering | |
CN112511472B (en) | Time-frequency second-order equalization method based on neural network and communication system | |
CN111313974A (en) | Modulation format identification method for signal amplitude sequencing and ratio calculation | |
CN116389207A (en) | Modulation format identification method based on signal amplitude histogram | |
CN113285762B (en) | Modulation format identification method based on relative entropy calculation | |
Chen et al. | Blind identification of the shaping rate for probabilistic shaping QAM signal | |
CN114531328A (en) | Modulation format identification method based on signal envelope flatness | |
CN115276818B (en) | Deep learning-based optical-load wireless transmission link demodulation method | |
CN114584212B (en) | Modulation format and optical signal to noise ratio monitoring method for feature similarity analysis | |
CN113452439B (en) | Key parameter joint monitoring method in elastic optical network | |
CN115173952B (en) | Optimized receiving method of optical universal filtering multi-carrier optical access network |
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 |