[go: up one dir, main page]

WO2025120715A1 - Dispositif d'estimation, dispositif d'entraînement et procédé d'estimation - Google Patents

Dispositif d'estimation, dispositif d'entraînement et procédé d'estimation Download PDF

Info

Publication number
WO2025120715A1
WO2025120715A1 PCT/JP2023/043360 JP2023043360W WO2025120715A1 WO 2025120715 A1 WO2025120715 A1 WO 2025120715A1 JP 2023043360 W JP2023043360 W JP 2023043360W WO 2025120715 A1 WO2025120715 A1 WO 2025120715A1
Authority
WO
WIPO (PCT)
Prior art keywords
feature
unit
communication path
electric field
optical communication
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.)
Pending
Application number
PCT/JP2023/043360
Other languages
English (en)
Japanese (ja)
Inventor
稜 五十嵐
遼 胡間
一貴 原
淳一 可児
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.)
NTT Inc
Original Assignee
Nippon Telegraph and Telephone Corp
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 Nippon Telegraph and Telephone Corp filed Critical Nippon Telegraph and Telephone Corp
Priority to PCT/JP2023/043360 priority Critical patent/WO2025120715A1/fr
Publication of WO2025120715A1 publication Critical patent/WO2025120715A1/fr
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • 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

Definitions

  • the present invention relates to an estimation device, a learning device, and an estimation method.
  • ROADM reconfigurable optical add/drop multiplexer
  • optical signals sent from a communication device are forwarded at the node and transmitted to a destination communication device.
  • Figure 20 shows an overview of a network composed of ROADM.
  • Each node (first node to fifth node) is composed of an optical switch.
  • An optical signal sent from a communication device (e.g., first communication device) is forwarded without being photoelectrically converted at the node, and is delivered as light to the destination communication device (e.g., second communication device).
  • an all-optical network that connects such end-to-end optical paths without photoelectric conversion, when a new connection request is made from a communication device, it is necessary to select and assign an appropriate route from among many optical path candidates.
  • Each candidate optical path has a different transmission distance, type of fiber, gain of the optical amplifier through which it passes, etc. This changes the transmission quality (e.g. bit error rate) obtained by the receiving communication device. For this reason, it is necessary to select and assign the optical path with the highest transmission quality (e.g. one that allows error-free transmission) from among the optical paths. It may be possible to actually send a signal through each optical path to check the high transmission quality (e.g. whether it is error-free) and then assign an appropriate one. However, such work takes an enormous amount of time. Therefore, in order to open optical paths in a short time, it is effective to estimate the transmission quality of each optical path and assign the optical paths.
  • a method for estimating the bit error rate as a specific example of a method for estimating transmission quality in an optical communication system.
  • One method for estimating the bit error rate in optical communication systems is to use a propagation simulation.
  • the received waveform can be simulated by adding appropriate noise to the waveform after fiber propagation calculated by the propagation simulation, and the received code sequence can be identified by threshold judgment, and the bit error rate can be calculated from the difference with the transmitted code sequence (for example, a VPI simulator).
  • the change in waveform due to fiber propagation can be calculated with high accuracy by applying an algorithm called the split step Fourier method (SSFM) to the nonlinear Schrödinger equation.
  • SSFM split step Fourier method
  • the signal waveform can be calculated taking into account not only linear waveform changes (chromatic dispersion) due to fiber propagation, but also nonlinear waveform changes (such as self-phase modulation). Therefore, the bit error rate can be accurately estimated even when nonlinear waveform distortion occurs.
  • Figure 21 shows an example of a configuration for simulating transmission using SSFM in a network model consisting of N spans.
  • optical amplifiers are inserted between each fiber span to compensate for the propagation loss of the optical fiber.
  • the optical signal (electric field waveform E_0) output from the transmitter first enters an optical fiber of length L_1 with input optical power P_1, and electric field waveform E_1 is output.
  • Electric field waveform E_1 becomes the input electric field waveform of the next span, and light propagates in a similar manner. This process is repeated, and finally the receiver receives electric field waveform E_N with received optical power P_Rx.
  • a transmission simulator based on the split-step Fourier method (SSFM) is used as a method for calculating the bit error rate obtained at the receiver.
  • SSFM split-step Fourier method
  • the output electric field waveform E_n+1 for the relevant section can be calculated by providing the optical intensity and transmission distance for the input electric field waveform E_n. By repeating this process, the final received electric field waveform E_N can be obtained.
  • the receiver then performs processes such as square-law detection, noise addition, and threshold judgment on E_N to calculate the received code sequence.
  • the bit error rate is calculated based on a comparison between the transmitted code sequence and the received code sequence.
  • Digital coherent transmission systems which are often used in core systems, are capable of compensating for linear waveform distortion such as chromatic dispersion. This makes long-distance transmission possible with digital coherent transmission systems.
  • nonlinear waveform distortion can be approximated by Gaussian noise. For this reason, a high-speed transmission quality estimation system using Gaussian noise approximation has been proposed.
  • the present invention aims to provide technology that can quickly calculate the transmission quality of optical paths in optical communication networks while taking into account nonlinear waveform changes.
  • One aspect of the present invention is an estimation device that includes an optical communication path formed by concatenating one or more unit sections, an optical signal transmitted from a transmitter and input to the optical communication path, and a waveform feature estimation unit that estimates, for each unit section constituting the optical communication path, a feature of an electric field waveform output from the unit section based on a feature of an electric field waveform of the optical signal input to that unit section, and a transmission quality estimation unit that estimates the transmission quality of the optical communication path based on the feature of the electric field waveform output from the last unit section of the optical communication path estimated by the waveform feature estimation unit.
  • One aspect of the present invention is a learning device that includes a learning control unit that generates a trained model by performing a learning process using multiple teacher data sets for an optical communication path formed by connecting one or more unit sections, and an optical signal transmitted from a transmitter and input to the optical communication path, in which, for each unit section constituting the optical communication path, the feature amount of the electric field waveform of the optical signal input to that unit section is used as an explanatory variable, and the feature amount of the electric field waveform output from the unit section is used as a target variable.
  • One aspect of the present invention is a learning device that includes a learning control unit that generates a trained model by performing a learning process using multiple teaching data sets in which, for an optical communication path formed by connecting one or more unit sections, and an optical signal transmitted from a transmitter and input to the optical communication path, the feature amount of the electric field waveform output from the last unit section of the optical communication path is used as an explanatory variable, and the transmission quality of the optical communication path is used as a target variable.
  • One aspect of the present invention is an estimation method for an optical communication path formed by concatenating one or more unit sections and an optical signal transmitted from a transmitter and input to the optical communication path, the method comprising: a waveform feature estimation step of estimating, for each unit section constituting the optical communication path, a feature of an electric field waveform output from the unit section based on a feature of an electric field waveform of the optical signal input to the unit section; and a transmission quality estimation step of estimating the transmission quality of the optical communication path based on the feature of the electric field waveform output from the last unit section of the optical communication path estimated by the waveform feature estimation unit.
  • the present invention makes it possible to quickly calculate the transmission quality of optical paths in optical communication networks while taking into account nonlinear waveform changes.
  • FIG. 1 is a schematic diagram of an all-optical network envisaged in the present invention.
  • FIG. 1 is a diagram showing a network model of an all-optical network 900 that is a target for transmission quality estimation by an estimation device 30.
  • FIG. 2 is a diagram showing an outline of the processing of an estimation device 30 in the present embodiment.
  • FIG. 13 is a diagram showing an example of a neural network, which is a specific example of machine learning used in the waveform calculation unit 82.
  • FIG. 13 is a diagram showing an example of a neural network, which is a specific example of machine learning used in the transmission quality calculation unit 83.
  • FIG. 2 is a diagram showing a specific example of a configuration for acquiring the above-mentioned teacher data.
  • FIG. 1 is a diagram showing a network model of an all-optical network 900 that is a target for transmission quality estimation by an estimation device 30.
  • FIG. 2 is a diagram showing an outline of the processing of an estimation device 30 in the present embodiment.
  • FIG. 2 is a diagram showing a specific example of the configuration of a feature amount acquiring unit 26. 2 is a diagram showing an outline of the configuration of an electric field waveform deriving section 27.
  • FIG. FIG. 1 is a diagram illustrating an example of a system configuration of a transmission quality estimation system. 2 is a schematic block diagram showing a specific example of the functional configuration of the learning device 20.
  • FIG. 4 is a flowchart showing a specific example of processing by the learning device 20.
  • 2 is a schematic block diagram showing a specific example of a functional configuration of a determination device 30.
  • FIG. 13 is a diagram illustrating an outline of the processing of a waveform feature amount estimating unit 333 and a transmission quality estimating unit 334.
  • FIG. 13 is a diagram showing a network model of an all-optical network 900 whose transmission quality is to be estimated by an estimation device 30 of the second embodiment.
  • FIG. 11 is a diagram illustrating an outline of the process of an estimation device 30 according to a second embodiment.
  • FIG. 13 is a diagram showing an example of a neural network, which is a specific example of machine learning used in the waveform calculation unit 82 of the second embodiment.
  • FIG. 11 is a diagram illustrating an example of a neural network, which is a specific example of machine learning used in the transmission quality calculation unit 83 of the second embodiment.
  • FIG. 13 is a diagram showing a network model of an all-optical network 900 whose transmission quality is to be estimated by an estimation device 30 of the second embodiment.
  • FIG. 11 is a diagram illustrating an outline of the process of an estimation device 30 according to a second embodiment.
  • FIG. 13 is a diagram showing an example of a neural network, which is a specific example of machine learning used in the waveform calculation unit
  • FIG. 2 is a diagram illustrating an outline of a hardware configuration example of an information processing device 90 applied to the present embodiment.
  • 1 shows an outline of a network configured using ROADM.
  • FIG. 1 is a diagram showing an example of a configuration for performing transmission simulation using SSFM in a network model consisting of N spans.
  • FIG. 1 is a diagram showing an outline of an all-optical network assumed in the present invention.
  • Remote communication devices a first communication device 810 and a second communication device 840
  • the optical nodes 820 have an optical switch 821 therein, and transfer signals in a predetermined direction as light without photoelectric conversion.
  • the route within each optical node 820 is controlled by a controller 830.
  • the controller 830 acquires the transmission quality (e.g., bit error rate) of multiple candidate optical paths. From among the candidate optical paths, the controller 830 selects and assigns an optical path having a predetermined transmission quality (e.g., an optical path having a bit error rate below a specified value).
  • a predetermined transmission quality e.g., an optical path having a bit error rate below a specified value.
  • the controller 830 acquires the transmission quality of the optical path, for example, by the following process.
  • the controller 830 provides the estimation device 30 with information about the optical path (e.g., the distance L of each section, the input light intensity P, and the received light intensity P_Rx).
  • the estimation device 30 uses a transmission quality estimation technique to calculate the transmission quality (e.g., the bit error rate) of multiple candidate optical paths.
  • the controller 830 acquires information about the transmission quality estimated by the estimation device 30 from the estimation device 30.
  • the 2 is a diagram showing a network model of an all-optical network 900, the transmission quality of which is estimated by the estimation device 30.
  • the all-optical network 900 is the transmission quality of which is estimated by the estimation device 30, and is the control target of the controller 830.
  • a transmitter (Tx) and a receiver (Rx) are connected to the all-optical network 900 as specific examples of the first communication device 810 and the second communication device 840, respectively.
  • the all-optical network 900 is composed of N fiber spans. An optical amplifier is inserted between each fiber span. The optical amplifier compensates for the propagation loss of the optical fiber.
  • the optical signal (electric field waveform E_0) output from the transmitter first enters an optical fiber of length L_1 with input optical power P1.
  • an optical signal (electric field waveform E_1) is output from the optical fiber of length L_1.
  • E_1 becomes the input electric field waveform of the next span, and light propagates in a similar manner.
  • the optical signal (electric field waveform E_N) is received at the receiver with the received optical power P_Rx.
  • a transmission simulator based on the split-step Fourier method (SSFM) is used to calculate the bit error rate obtained at the receiver.
  • FIG. 3 is a diagram showing an outline of the processing of the estimation device 30 in this embodiment.
  • the estimation device 30 can calculate the feature amount A_n of the output electric field waveform E_n for a certain section based on the feature amount A_n-1 of the input electric field waveform E_n-1 for that section, the light intensity P_n, and the transmission distance L_n.
  • the feature amount A_n of this output electric field waveform E_n becomes the feature amount A_n of the input electric field waveform E_n for the next section.
  • the final transmission quality (e.g., bit error rate) is estimated using feature A linked to electric field waveform E instead of electric field waveform E.
  • the amount of calculations can be reduced by using feature A of a lower dimension that has a one-to-one correspondence with electric field waveform E.
  • the feature (transmission feature) of electric field waveform E0 output from the transmitter is set to A_0.
  • a transmission feature transmission unit 81 transmits the transmission feature A_0.
  • a waveform calculation unit 82 is provided for each span, and calculates a feature A according to the waveform change of each span.
  • the waveform calculation units 82 are cascaded in the same number as the number of spans, as shown in Figure 3.
  • the waveform calculation unit 82 calculates an output feature A_n+1 from the input feature A_n of the span.
  • the transmission feature transmission unit 81 may store a value calculated in advance for the feature A_0 in memory and output (transmit) the stored feature A_0 to the waveform calculation unit 82, or may calculate the feature A_0 according to the electric field waveform E_0 transmitted each time and output (transmit) it to the waveform calculation unit 82.
  • the waveform calculation unit 82 may be realized using a machine learning technique such as a neural network. That is, the waveform calculation unit 82 may obtain output features from input features using a trained model obtained by a learning process. The feature A_N of the received waveform finally obtained via the waveform calculation unit 82 is input to the transmission quality calculation unit 83.
  • a machine learning technique such as a neural network. That is, the waveform calculation unit 82 may obtain output features from input features using a trained model obtained by a learning process. The feature A_N of the received waveform finally obtained via the waveform calculation unit 82 is input to the transmission quality calculation unit 83.
  • FIG. 4 is a diagram showing an example of a neural network, which is a specific example of machine learning used in the waveform calculation unit 82.
  • Input features and attribute information related to transmission are input to the learning model as explanatory variables.
  • the transmission distance L may be used as the attribute information related to transmission.
  • the input light intensity P may also be used as the explanatory variable.
  • the learning model outputs an output feature An+1 as a response variable.
  • supervised learning such as a support vector machine, a random forest, or a neural network may be used as a specific example of such a learning model.
  • a plurality of teacher data are prepared to perform the learning process in such machine learning.
  • Each teacher data includes an explanatory variable and a response variable (correct answer label) obtained from the explanatory variable.
  • the teacher data may be data obtained by performing an actual transmission, or may be data obtained by executing a simulation.
  • the transmission quality calculation unit 83 estimates the transmission quality based on the feature quantity A_N of the received waveform.
  • a specific example of the transmission quality is the bit error rate.
  • the transmission quality calculation unit 83 calculates the transmission quality based on the feature quantity of the received waveform, the received light intensity, and the like.
  • the transmission quality calculation unit 83 may be realized using a machine learning technique such as a neural network. In other words, the transmission quality calculation unit 83 may obtain the transmission quality from the feature quantity of the received waveform using a trained model obtained by a learning process.
  • FIG. 5 is a diagram showing an example of a neural network, which is a specific example of machine learning used in the transmission quality calculation unit 83.
  • the reception feature A_N is input to the learning model as an explanatory variable.
  • the received light intensity P_Rx may also be used as an explanatory variable.
  • Information about the transmission quality is output from the learning model as a target variable.
  • the bit error rate is used as a specific example of information about the transmission quality.
  • supervised learning such as a support vector machine, a random forest, or a neural network may be used.
  • a plurality of teacher data are prepared to perform the learning process in such machine learning.
  • Each teacher data includes an explanatory variable and a target variable (correct answer label) obtained from the explanatory variable.
  • the teacher data may be data obtained by performing an actual transmission, or may be data obtained by executing a simulation.
  • FIG. 6 is a diagram showing a specific example of a configuration for acquiring the above-mentioned teacher data.
  • FIG. 6 shows an outline of a communication system 221 used to acquire teacher data.
  • the communication system 221 has a plurality (N) of unit sections 25. Each unit section 25 is provided with an optical fiber as a transmission path, and its length is represented by L.
  • the electric field waveform of the optical signal transmitted from the transmitter Tx is represented by an electric field waveform E_0.
  • This electric field waveform E_0 of the optical signal is the input electric field waveform in the first section corresponding to the first unit section 25.
  • the input electric field waveform and the input light intensity are the input electric field waveform E_0 and the input light intensity P_1 in the first section.
  • the optical signal becomes the output electric field waveform E_1 via the optical path of the fiber length L_1 of the first section, and this output electric field waveform E_1 is input to the next unit section 25 (second section) as the input electric field waveform E_1.
  • the optical signal output from the optical fiber is the output electric field waveform E_n.
  • the output electric field waveform E_n may be obtained by a transmission simulation, may be obtained by actual device verification, or may be obtained by other means.
  • the feature acquisition unit 26 acquires the input feature A_n-1 of the input electric field waveform E_n-1 and the output feature A_n of the output electric field waveform E_n.
  • a set of data in which the input feature A_n-1, input light intensity P_n, and fiber length L_n are used as explanatory variables and the output feature A_n is used as the correct answer label of the objective variable is prepared by collecting multiple sets of data and using them as the first teacher data (dataset 1).
  • the receiver Rx also receives the optical signal of the output electric field waveform E_N output from the Nth unit section 25 with the received optical intensity P_Rx.
  • the feature acquisition unit 26 acquires the output feature A_N of the output electric field waveform E_N.
  • a set of data in which the feature A_N and the optical intensity P_N are used as explanatory variables and the transmission quality (e.g., the value of the bit error rate) is used as the correct label of the objective variable is collected and used as the second teacher data (data set 2).
  • the trained model described above is obtained.
  • the trained model obtained by the learning process using dataset 1 is used in each waveform calculation unit 82.
  • the trained model obtained by the learning process using dataset 2 is used in the transmission quality calculation unit 83.
  • the waveform calculation units 82 shown in FIG. 3 are cascaded, for example, in the number of transmission fibers or unit sections in the optical communication path being processed, and finally the transmission quality calculation unit 83 is connected. Using such a model, it is possible to estimate the transmission quality in the optical communication path being processed.
  • FIG. 7 is a diagram showing a specific example of the configuration of the feature acquisition unit 26.
  • the feature An obtained by the configuration shown in FIG. 7 is linked one-to-one with the electric field waveform E_n.
  • the feature acquisition unit 26 includes a transmitter 261, a VNLF 262, and an LMS 263.
  • the transmitter 261 virtually generates an optical signal transmitted from an actual communication device (transmitter Tx) and outputs it to the VNLF to simulate a phenomenon.
  • the VNLF 262 is a nonlinear filter.
  • the transmitter 261 outputs an ideal transmission electric field waveform E_ideal to the VNLF 262 based on an arbitrary code sequence.
  • the ideal transmission electric field waveform may be, for example, a state in which the eye opening of the eye pattern is large.
  • the transfer function of the VNLF 262 is represented by a tap coefficient.
  • the LMS 263 updates the tap coefficient of the VNLF using the LMS algorithm so as to reduce the error between E_n and E_out.
  • the LMS 263 acquires and outputs the tap coefficient when the error between E_n and E_out converges to a predetermined threshold value (e.g., zero) or less as a feature A_n.
  • a predetermined threshold value e.g., zero
  • the feature and the electric field waveform are linked one-to-one. Therefore, the original electric field waveform can be uniquely derived from the feature.
  • FIG. 8 is a diagram showing an outline of the configuration of the electric field waveform derivation unit 27.
  • the electric field waveform derivation unit 27 derives an electric field waveform from the feature quantity.
  • the electric field waveform derivation unit 27 includes a transmitter 271 and a VNLF 272.
  • the feature quantity A_n is input to the electric field waveform derivation unit 27.
  • the tap coefficient indicated by the input feature quantity A_n is set in the VNLF 272.
  • the transmitter 271 outputs E_ideal to the VNLF 272.
  • the output of the VNLF 272 is equal to E_n.
  • the feature quantity of the electric field waveform can be obtained by using, for example, a nonlinear filter. However, other values may be used as the feature quantity of the electric field waveform.
  • FIG. 9 is a diagram showing an example of the system configuration of the transmission quality estimation system.
  • the transmission quality estimation system 100 includes a learning device 20 and an estimation device 30.
  • the learning device 20 generates a trained model by executing a learning process using the above-mentioned data set 1 and data set 2.
  • the estimation device 30 estimates the transmission quality in the optical path being processed using the trained model generated by the learning device 20.
  • FIG. 10 is a schematic block diagram showing a specific example of the functional configuration of the learning device 20.
  • the learning device 20 is configured using an information processing device such as a personal computer or a server device.
  • the learning device 20 includes a memory unit 21 and a control unit 22.
  • the storage unit 21 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device.
  • the storage unit 21 stores data used by the control unit 22.
  • the storage unit 21 may function, for example, as a teacher data storage unit 211 and a trained model storage unit 212.
  • the teacher data storage unit 211 stores teacher data used in the learning process executed in the learning device 20.
  • the teacher data stored in the teacher data storage unit 221 is the above-mentioned dataset 1 and dataset 2.
  • the trained model storage unit 212 stores a trained model obtained by a learning process using the teacher data stored in the teacher data storage unit 211.
  • the control unit 22 is configured using a processor such as a CPU and a memory.
  • the control unit 22 functions as an information control unit 221 and a learning control unit 222 by the processor executing a program. All or part of the functions of the control unit 22 may be realized using hardware such as an ASIC, PLD, or FPGA.
  • the above program may be recorded on a computer-readable recording medium. Examples of computer-readable recording media include portable media such as flexible disks, optical magnetic disks, ROMs, CD-ROMs, and semiconductor storage devices (e.g., SSDs), and storage devices such as hard disks and semiconductor storage devices built into a computer system.
  • the above program may be transmitted via a telecommunications line.
  • the information control unit 221 controls the input and output of information.
  • the information control unit 221 acquires teacher data from another device (information processing device or storage medium) and records it in the teacher data storage unit 211.
  • the other device generates the teacher data (data set 1 and data set 2).
  • the information control unit 221 may generate either or both of the data set 1 and data set 2.
  • the information control unit 221 may acquire a data set by simulating a communication system 221 as shown in FIG. 6, or may acquire a data set by acquiring a feature amount by functioning as the feature amount acquisition unit 26 for values obtained from an actual device as shown in FIG. 6.
  • the information control unit 221 When acquiring a data set as described above, the information control unit 221 also functions as the feature amount acquisition unit 26 that acquires a feature amount from an electric field waveform.
  • the information control unit 221 may output, for example, a learned model stored in the learned model storage unit 212 to another device (for example, the estimation device 30).
  • the learning control unit 222 executes a learning process using the teacher data stored in the teacher data storage unit 211.
  • supervised learning for classification such as a support vector machine, a random forest, or a neural network may be used.
  • the learning control unit 222 generates a trained model for outputting an output feature amount A_n based on the input feature amount A_n-1, the input light intensity P_n, and the fiber length L_n, for example, by performing supervised learning.
  • the learning control unit 222 records the generated trained model in the trained model storage unit 212.
  • the trained model obtained by the learning control unit 222 is provided to the estimation device 30.
  • the trained model may be provided by communication via a network, may be provided via a recording medium, or may be provided by any method.
  • FIG. 11 is a flowchart showing a specific example of processing by the learning device 20.
  • the information control unit 221 acquires teacher data (step S101).
  • the teacher data may be, for example, input by a user, acquired by communication from another information device, or acquired from a recording medium connected to the learning device 20.
  • the learning control unit 222 executes a learning process using the teacher data, and records a learned model in the learned model storage unit 212 (step S102).
  • FIG. 12 is a schematic block diagram showing a specific example of the functional configuration of the determination device 30.
  • the determination device 30 is configured using an information processing device such as a personal computer or a server device.
  • the determination device 30 includes a communication unit 31, a storage unit 32, and a control unit 33.
  • the communication unit 31 is a communication device.
  • the communication unit 31 may be configured as, for example, a network interface.
  • the communication unit 31 communicates data with other devices via a network in response to the control of the control unit 33.
  • the communication unit 31 may be a device that performs wireless communication or a device that performs wired communication.
  • the communication unit 31 may communicate with the controller 830 via a network, for example.
  • the storage unit 32 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device.
  • the storage unit 32 stores data used by the control unit 33.
  • the storage unit 32 may function as, for example, an estimation model storage unit 321 and an estimation result storage unit 322.
  • the estimation model storage unit 321 stores an estimation model used by the waveform feature estimation unit 331 when performing the estimation process and an estimation model used by the transmission quality estimation unit 332 when performing the estimation process.
  • the estimation model may be configured using information of a trained model generated in advance by a learning process, for example. Such a learning process may be executed by another device (for example, the learning device 20) or may be executed by the device itself (the estimation device 30). Specific examples of the estimation model include a trained model acquired by the learning device 20 performing a learning process using a data set 1, and a trained model acquired by the learning device 20 performing a learning process using a data set 2.
  • the estimation model does not necessarily have to be generated by a learning process.
  • the estimation model may be configured using, for example, a lookup table in which the explanatory variables and the objective variables are associated with each other, or may be configured in another manner.
  • the estimation result storage unit 322 stores the estimation results of the waveform feature amount estimation unit 331 and the estimation results of the transmission quality estimation unit 332 .
  • the control unit 33 is configured using a processor such as a CPU and a memory.
  • the control unit 33 functions as an information control unit 331, a feature acquisition unit 332, a waveform feature estimation unit 333, and a transmission quality estimation unit 334 by the processor executing a program. All or part of the functions of the control unit 33 may be realized using hardware such as an ASIC, a PLD, or an FPGA.
  • the above program may be recorded on a computer-readable recording medium. Examples of computer-readable recording media include portable media such as flexible disks, optical magnetic disks, ROMs, CD-ROMs, and semiconductor storage devices (e.g., SSDs), and storage devices such as hard disks and semiconductor storage devices built into a computer system.
  • the above program may be transmitted via a telecommunications line.
  • the information control unit 331 acquires data from other devices such as the controller 830.
  • the information control unit 331 transmits information indicating the estimation results obtained by the transmission quality estimation unit 334 to other devices such as the controller 830.
  • Such exchange of information between the information control unit 331 and other devices may be performed, for example, by communication using the communication unit 31.
  • the feature acquisition unit 332 acquires a feature corresponding to the input electric field waveform in the optical communication path to be estimated.
  • the feature acquisition unit 332 may be configured in the same manner as the feature acquisition unit 26 shown in FIG. 7, for example.
  • the feature acquisition unit 332 may acquire the first electric field waveform E_0 transmitted from the transmitter in any way. For example, it may be stored in advance as a fixed value, or it may be acquired from the controller 830.
  • the acquired electric field waveform E_0 may be stored in advance in association with the type (e.g., model number, etc.) of the transmitter in the optical communication path to be processed.
  • Such associated information may be stored in the storage unit 32 of the determination device 30, or may be stored in the controller 830.
  • the controller 830 may determine the type of the transmitter in the optical communication path to be processed and acquire the electric field waveform E_0 based on the information, or may notify the determination device 30 of the determination result of the transmitter type.
  • the feature acquisition unit 332 of the determination device 30 that has received the notification may acquire the electric field waveform E_0 corresponding to the type of the transmitter from the storage unit 32.
  • the determination device 30 or the controller 830 may store in advance a feature quantity A_0 generated in accordance with the electric field waveform E_0, instead of the electric field waveform E_0 described above. In this case, the feature quantity A_0 may also be stored in advance in association with the type of transmitter.
  • the waveform feature estimation unit 333 estimates the feature A_1 of the electric field waveform E_1 output from the first unit section 25 using the learned model based on the feature A_0 of the optical signal transmitted by the transmitter in the optical communication path to be estimated.
  • the waveform feature estimation unit 333 estimates the feature over all N sections in the optical communication path to be estimated, and estimates the feature A_N of the electric field waveform E_N that is finally output.
  • the waveform feature estimation unit 333 obtains values from the controller 830 according to the explanatory variables of the learned model and performs estimation. For example, as shown in FIG.
  • the waveform feature estimation unit 333 outputs the feature A_N of the electric field waveform E_N of the optical signal that is finally output in the optical communication path to be estimated to the transmission quality estimation unit 334.
  • the transmission quality estimation unit 334 estimates the transmission quality in the optical communication path to be estimated using the learned model based on the features acquired by the feature acquisition unit 332.
  • the transmission quality estimation unit 334 records the estimation result in the estimation result storage unit 322.
  • the transmission quality estimation unit 334 performs estimation by acquiring values from the controller 830 according to the explanatory variables of the learned model. For example, the input light intensity P_Rx may also be used as an explanatory variable as shown in FIG. 13.
  • FIG. 14 is a flowchart showing a specific example of processing by the estimation device 30.
  • the information control unit 331 acquires optical path information (e.g., distance L of each section, input light intensity P, received light intensity P_Rx) of the optical communication path to be estimated from the controller 830 (step S201).
  • the waveform feature estimation unit 333 estimates feature A_N of the optical communication path to be estimated.
  • the transmission quality estimation unit 334 estimates the transmission quality using feature A_N (step S202).
  • the information control unit 331 transmits information indicating the estimation result to the controller 830 (step S203).
  • feature A is used instead of the electric field waveform E of the optical signal.
  • the number of dimensions of feature A is lower than that of the electric field waveform E. This makes it possible to reduce the amount of calculation required in the estimation process.
  • the optical fiber is of a single type.
  • a different type of fiber such as a dispersion compensating fiber (DCF) may be inserted in a part of the section.
  • DCF dispersion compensating fiber
  • the output electric field and its characteristic quantity vary depending not only on the input light intensity P and the transmission distance L but also on the type of optical fiber. Therefore, in a system in which different optical fibers are mixed, it is necessary to estimate the transmission quality according to the type of each optical fiber. For example, in order to take into account the magnitude of chromatic dispersion of each optical fiber, the value of the group velocity dispersion parameter ⁇ _2 must be taken into account.
  • bit error rate was used as a specific example of transmission quality
  • Q value is estimated as a specific example of transmission quality
  • FIG. 15 is a diagram showing a network model of an all-optical network 900, the transmission quality of which is estimated by the estimation device 30 of the second embodiment.
  • FIG. 16 is a diagram showing an outline of the processing of the estimation device 30 in the second embodiment.
  • the estimation device 30 in the second embodiment calculates the feature amount A_n of the output electric field waveform E_n for a certain section based on the feature amount of the input electric field waveform E_n-1 for that section, the light intensity P_n, the transmission distance L_n, and the value of ⁇ _2.
  • FIG. 17 is a diagram showing an example of a neural network, which is a specific example of machine learning used in the waveform calculation unit 82 of the second embodiment.
  • Input features and attribute information related to transmission are input to the learning model as explanatory variables, and the attribute information related to transmission includes the value of ⁇ _2.
  • FIG. 18 is a diagram showing an example of a neural network, which is a specific example of machine learning used in the transmission quality calculation unit 83 of the second embodiment.
  • the Q value is used as a specific example of information related to transmission quality.
  • the transmission quality estimation system 100 of the second embodiment configured in this way makes it possible to estimate the transmission quality of the optical communication path to be estimated more accurately even for a system in which different optical fibers are mixed.
  • FIG. 19 is a diagram showing an outline of an example of the hardware configuration of an information processing device 90 applied to this embodiment.
  • the information processing device 90 includes a processor 91, a main memory device 92, a communication interface 93, an auxiliary memory device 94, an input/output interface 95, and an internal bus 96.
  • the processor 91, the main memory device 92, the communication interface 93, the auxiliary memory device 94, and the input/output interface 95 are communicably connected to each other via the internal bus 96.
  • the information processing device 90 may be applied to, for example, the learning device 20 and the estimation device 30.
  • the communication unit 31 may be configured using the communication interface 93.
  • the memory unit 21 and the memory unit 32 may be configured using the auxiliary memory device 94.
  • the control unit 22 and the control unit 33 may be configured using the processor 91 and the main memory device 92.
  • the learning device 20 and the estimation device 30 are configured as separate devices, but they may be configured as an integrated device.
  • the learning device 20 may be implemented using a plurality of information processing devices.
  • the learning device 20 may be implemented using a device such as a cloud.
  • the memory unit 21 and the control unit 22 may be implemented in different information processing devices.
  • the memory unit 21 of the learning device 20 may be distributed and implemented in a plurality of information processing devices.
  • the estimation device 30 may be implemented using a plurality of information processing devices.
  • the estimation device 30 may be implemented using a device such as a cloud.
  • the memory unit 32 and the control unit 33 may be implemented in different information processing devices.
  • the memory unit 32 of the estimation device 30 may be distributed and implemented in a plurality of information processing devices.
  • the present invention can be applied to technology for estimating transmission quality.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Electromagnetism (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Optical Communication System (AREA)

Abstract

Un aspect de la présente invention concerne un dispositif d'estimation comprenant : une unité d'estimation de quantité de caractéristiques de forme d'onde qui, par rapport à un trajet de communication optique configuré par connexion d'au moins une section unitaire, et un signal optique transmis par un émetteur et entré dans le trajet de communication optique, estime, pour chaque section unitaire constituant le trajet de communication optique, la quantité de caractéristiques d'une forme d'onde de champ électrique émise par la section unitaire en fonction de la quantité de caractéristiques de la longueur d'onde de champ électrique du signal optique entré dans la section unitaire ; et une unité d'estimation de qualité de transmission qui, en fonction de la quantité de caractéristiques de la forme d'onde de champ électrique émise par la dernière section unitaire du trajet de communication optique, qui a été estimée par l'unité d'estimation de quantité de caractéristiques de forme d'onde, estime la qualité de transmission du trajet de communication optique.
PCT/JP2023/043360 2023-12-04 2023-12-04 Dispositif d'estimation, dispositif d'entraînement et procédé d'estimation Pending WO2025120715A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2023/043360 WO2025120715A1 (fr) 2023-12-04 2023-12-04 Dispositif d'estimation, dispositif d'entraînement et procédé d'estimation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2023/043360 WO2025120715A1 (fr) 2023-12-04 2023-12-04 Dispositif d'estimation, dispositif d'entraînement et procédé d'estimation

Publications (1)

Publication Number Publication Date
WO2025120715A1 true WO2025120715A1 (fr) 2025-06-12

Family

ID=95979658

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2023/043360 Pending WO2025120715A1 (fr) 2023-12-04 2023-12-04 Dispositif d'estimation, dispositif d'entraînement et procédé d'estimation

Country Status (1)

Country Link
WO (1) WO2025120715A1 (fr)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009512286A (ja) * 2005-10-13 2009-03-19 ナショナル・アイシーティ・オーストラリア・リミテッド サンプリングされた光信号の監視のための方法および装置
JP2018133725A (ja) * 2017-02-16 2018-08-23 富士通株式会社 伝送路監視装置及び伝送路の監視方法
WO2021124415A1 (fr) * 2019-12-16 2021-06-24 日本電信電話株式会社 Dispositif de réception optique et procédé d'estimation de caractéristiques de transmission

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009512286A (ja) * 2005-10-13 2009-03-19 ナショナル・アイシーティ・オーストラリア・リミテッド サンプリングされた光信号の監視のための方法および装置
JP2018133725A (ja) * 2017-02-16 2018-08-23 富士通株式会社 伝送路監視装置及び伝送路の監視方法
WO2021124415A1 (fr) * 2019-12-16 2021-06-24 日本電信電話株式会社 Dispositif de réception optique et procédé d'estimation de caractéristiques de transmission

Similar Documents

Publication Publication Date Title
CN109039472B (zh) 一种基于深度学习的数据中心光通信色散估计与管理方法
JP7303459B2 (ja) 光受信装置及び伝送特性推定方法
JP7311744B2 (ja) 光受信装置及び係数最適化方法
JP7393694B2 (ja) 光伝送システム及び特性推定方法
JP7701646B2 (ja) ネットワークコントローラ、推定方法及びコンピュータプログラム
CN114285715A (zh) 基于双向gru-条件随机场的非线性均衡方法
CN114338309A (zh) 基于深度强化学习优化Volterra均衡器结构的方法和系统
Shahkarami et al. Efficient deep learning of nonlinear fiber-optic communications using a convolutional recurrent neural network
Arpanaei et al. A novel approach for joint analytical and ML-assisted GSNR estimation in flexible optical network
Jiang et al. Joint CD, DGD, and PDL estimation enabled by FrFT based time-frequency reconstruction
CN116886192B (zh) 补偿imdd光纤系统损伤的比重共享非线性预编码方法
US12052055B2 (en) Method of equalizing waveform distortion, terminal device, and optical communication system
JP6387461B2 (ja) 光伝送のための伝送品質の推定器を作り出すための方法
WO2025120715A1 (fr) Dispositif d'estimation, dispositif d'entraînement et procédé d'estimation
CN119449167B (zh) 一种用于无源光网络通信系统的信道构建方法
US20240014906A1 (en) Photonic machine learning based signal recovery in self-coherent detectors
Pedyash et al. Evaluation of quality parameters of an intensity-modulated optical transmission system
CN116545804A (zh) 基于噪声适配网络的光通信系统端到端优化方法和系统
JP7755188B2 (ja) 光伝送特性推定装置、光伝送特性推定方法及びプログラム
Coelho et al. An algorithm for global optimization of optical communication systems
JP7557161B2 (ja) 通信システム、通信方法及びプログラム
Li et al. Which features most impact: prediction of ANN-based lightpath quality of transmission?
WO2024150301A1 (fr) Dispositif d'estimation, dispositif d'apprentissage, procédé d'estimation et procédé d'apprentissage
WO2024261943A1 (fr) Dispositif d'estimation de taux d'erreur sur les bits et procédé d'estimation de taux d'erreur sur les bits
Arik et al. Adaptive MIMO signal processing in mode-division multiplexing

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23960730

Country of ref document: EP

Kind code of ref document: A1