Raman gain adaptive regulation and control method and system for multiband optical network

Abstract

The invention provides a Raman gain adaptive regulation and control method and system for a multiband optical network, and the method comprises the steps: supplementing a gain value of a non-target channel, constructing a gain vector based on a target gain value of a target channel and the supplemented gain value of the non-target channel, and carrying out the iteration of at least one round; in each iteration, values in the population are input into a pre-trained reverse model, and the reverse model outputs corresponding pumping adjustment parameters; determining gain values of all channels based on the pumping adjustment parameters, screening a gain value of a target channel from the gain values of all channels, and calculating fitness based on the target gain value of the target channel and the screened gain value of the target channel; and adjusting a gain value supplemented by a non-target channel based on the target function value, reconstructing a gain vector, carrying out next round of iteration, and screening a final pumping adjustment parameter from all the pumping adjustment parameters after the last iteration is completed.

Description

Technical Field

[0001] The present invention relates to the technical field of optical amplifiers, and in particular to a Raman gain adaptive control method and system for a multi-band optical network. Background Art

[0002] With the development of new technologies such as 5G / 6G mobile communications and the continuous evolution of next-generation applications, large-capacity access traffic such as machine-to-machine communications continues to increase, and the data traffic of transmission networks is growing rapidly. As basic transmission facilities, optical networks are facing huge traffic demands and are in urgent need of further capacity expansion. The introduction of advanced modulation formats and constellation shaping is a cost-effective solution to expand single-channel capacity, but the single-channel capacity will eventually be limited by the nonlinear Shannon limit and is insufficient to support the network's capacity expansion needs. Multi-band optical networks that introduce new bands for transmission are a promising solution that can utilize the entire communication window of standard single-mode fiber (SSMF) to expand the capacity of deployed optical networks. It has been proven to be the preferred solution for short- and medium-term capacity expansion of optical networks.

[0003] In multi-band optical networks, different signal channels are unevenly affected by the interaction between Kerr nonlinearity, amplified spontaneous emission noise and stimulated Raman scattering. In such a system, the signal channel power curve may take on an arbitrary shape. In order to ensure the quality of the transmitted signal and optimize the information rate in multiple bands, it is necessary to be able to achieve ultra-fast gain profile reconfiguration.

[0004] Fiber Raman amplifiers are optical amplifiers based on nonlinear optical effects. Compared with other types of optical amplifiers, they have a very low noise index, which can ensure high-quality signal transmission. More importantly, fiber Raman amplifiers allow flexible gain profile design by adjusting pump power and wavelength, and provide multi-band gain availability when operating in a multi-pump configuration, which is very suitable for realizing arbitrary gain profiles in multi-band optical networks in a controllable manner.

[0005] However, in commercial Raman pump modules, the pump wavelength and quantity are set in advance, and the only parameter that can be adjusted is the pump power. Such limited pump adjustment parameters cannot support the Raman amplifier to achieve accurate and arbitrary gain on all wavelength channels in the entire amplification band. In actual optical transmission, not all channels have business transmission, and usually only the wavelength channels of some links are used. The existing technology can only adjust the pump parameters for the gain of all channels, and cannot guarantee the pertinence for the wavelength channels of some links. Summary of the invention

[0006] In view of this, an embodiment of the present invention provides a Raman gain adaptive control method and system for a multi-band optical network to eliminate or improve one or more defects in the prior art.

[0007] One aspect of the present invention provides a Raman gain adaptive control method for a multi-band optical network, the method comprising the steps of:

[0008] Obtaining a gain value of a target channel target, supplementing a gain value of a non-target channel, constructing a gain vector based on the gain value of the target channel target and the supplemented gain value of the non-target channel, and performing at least one round of iteration;

[0009] In each round of iteration, the value in the gain vector is input into a pre-trained inverse model, and the inverse model outputs a corresponding pump adjustment parameter;

[0010] Determine the gain values ​​of all channels based on the pump adjustment parameters, select the gain value of the target channel from the gain values ​​of all channels, and calculate the objective function value based on the gain value of the target channel and the gain value of the target channel selected from the gain values ​​of all channels;

[0011] The gain value supplemented by the non-target channel is adjusted based on the objective function value, and the gain vector is reconstructed to perform the next round of iteration. After the last iteration is completed, the final pump adjustment parameter is selected from all the pump adjustment parameters.

[0012] The above scheme is adopted. This scheme first randomly supplements the gain value of the non-target channel, obtains the corresponding pump adjustment parameter through the inverse model, and then determines the gain value of all channels based on the pump adjustment parameter until the fitness meets the requirements. Since the pump adjustment parameter of this scheme is related to the gain value of all channels, this scheme obtains the corresponding pump adjustment parameter by supplementing, but the obtained pump adjustment parameter may not correspond to the gain value of the target channel. Then, this scheme further calculates the objective function value based on the gain value of the target channel and the gain value of the target channel selected from the gain values ​​of all channels, processes the target channel, and determines the final pump adjustment parameter through multiple rounds of iterations to ensure the pertinence to the specified wavelength channel of the link.

[0013] In some embodiments of the present invention, in the step of constructing a gain vector based on the gain value of the target channel and the gain value supplemented by the non-target channel, a random value is taken in a preset gain interval or the gain value of the non-target channel is supplemented based on the target gain values ​​of two adjacent target channels of the non-target channel to obtain the gain value supplemented by the non-target channel;

[0014] In the step of supplementing the gain value of the non-target channel based on the target gain values ​​of two adjacent target channels of the non-target channel, a line graph is constructed based on the target gain values ​​of all channels and the target channels, the horizontal axis of the line graph is the channel number, and the vertical axis is the gain value, and the points corresponding to the target gain values ​​of two adjacent target channels of the non-target channel are connected by a line, and the gain value corresponding to the vertical axis height corresponding to the horizontal axis position of the connecting line passing through the non-target channel is used as the gain value supplemented by the non-target channel.

[0015] In some embodiments of the present invention, in the step of determining the gain values ​​of all channels based on the pump adjustment parameters, the pump adjustment parameters are input into a preset forward model, and the forward model outputs the gain values ​​of all channels.

[0016] In some embodiments of the present invention, the forward model and the reverse model both adopt the structure of a feedforward neural network, a random forest or a convolutional neural network.

[0017] In the specific implementation process, the forward model and the inverse model of this solution can have a variety of structures, including but not limited to the structure of a feedforward neural network, a random forest or a convolutional neural network, or a combination of the structures of a feedforward neural network, a random forest or a convolutional neural network.

[0018] In some embodiments of the present invention, in the step of calculating the objective function value based on the gain value of the target channel target and the gain value of the target channel screened from the gain values ​​of all channels:

[0019] Calculating a root mean square error based on a gain value of a target channel target and a gain value of the target channel screened from gain values ​​of all channels;

[0020] An objective function value is calculated based on the root mean square error.

[0021] In some embodiments of the present invention, in the step of calculating the objective function value based on the root mean square error, if a genetic algorithm is used, the objective function value is the fitness value, and in the step of calculating the objective function value based on the root mean square error, the objective function value is calculated based on the following formula:

[0022]

[0023] Among them, S is the calculated objective function value, is the calculated root mean square error, C known Indicates the target channel.

[0024] In some embodiments of the present invention, after completing the last iteration, in the step of screening the final pump adjustment parameters from all pump adjustment parameters, a first screening strategy or a second screening strategy is adopted, wherein the first screening strategy sets a preset round of iterations, and after completing all the iteration rounds, screens out one set of pump adjustment parameters as the final pump adjustment parameters; the second screening strategy determines the final pump adjustment parameters during the iteration process based on a preset screening threshold.

[0025] In some embodiments of the present invention, in the step of selecting one group of pump adjustment parameters as the final pump adjustment parameters, the pump adjustment parameters corresponding to the highest fitness value are used as the final pump adjustment parameters.

[0026] In some embodiments of the present invention, in the step of determining the final pump adjustment parameters in the iterative process based on a preset screening threshold, after each round of iteration is completed, the calculated fitness value is compared with the preset fitness threshold. If the calculated fitness value is greater than the preset fitness threshold, then this round of iteration is regarded as the last round of iteration, and the pump adjustment parameters of this round are output as the final pump adjustment parameters.

[0027] The second aspect of the present invention also provides a Raman gain adaptive control system for a multi-band optical network, the system comprising a computer device, the computer device comprising a processor and a memory, the memory storing computer instructions, the processor being used to execute the computer instructions stored in the memory, and when the computer instructions are executed by the processor, the system implements the steps implemented by the method described above.

[0028] The third aspect of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps implemented by the aforementioned Raman gain adaptive control method for a multi-band optical network.

[0029] Additional advantages, purposes, and features of the present invention will be described in part in the following description, and will become apparent to those skilled in the art after studying the following, or may be learned from the practice of the present invention. The purposes and other advantages of the present invention can be specifically pointed out and obtained in the specification and the accompanying drawings.

[0030] Those skilled in the art will appreciate that the objectives and advantages that can be achieved with the present invention are not limited to the above specific description, and the above and other objectives that can be achieved by the present invention will be more clearly understood from the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The drawings described herein are used to provide a further understanding of the present invention, constitute a part of this application, and do not constitute a limitation of the present invention.

[0032] Figure 1 A schematic diagram of an implementation method of the Raman gain adaptive control method for multi-band optical networks in this scheme;

[0033] Figure 2 This is a schematic diagram of the architecture of this solution;

[0034] Figure 3 This is a schematic diagram of the system application of this solution;

[0035] Figure 4 is a configuration curve of the experimental example;

[0036] Figure 5 Another configuration curve of the experimental example. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments and the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0038] It should also be noted that, in order to avoid obscuring the present invention due to unnecessary details, only structures and / or processing steps closely related to the solutions according to the present invention are shown in the accompanying drawings, while other details that are not closely related to the present invention are omitted.

[0039] like Figure 1 , 2 As shown in 3, the present invention proposes a Raman gain adaptive control method and system for a multi-band optical network, the steps of the method comprising:

[0040] Step S100, obtaining a gain value of a target channel target, supplementing a gain value of a non-target channel, constructing a gain vector based on the gain value of the target channel target and the supplemented gain value of the non-target channel, and performing at least one round of iteration;

[0041] In the specific implementation process, the target gain of non-specified wavelength channels is filled by setting rules. The non-specified wavelength channels are channels without specific gain requirements, and a target curve space containing a series of target gain values ​​passing through the specified channels is obtained.

[0042] Step S200, in each round of iteration, inputting the value in the gain vector into a pre-trained inverse model, and the inverse model outputs a corresponding pump adjustment parameter;

[0043] Step S300, determining the gain values ​​of all channels based on the pump adjustment parameters, screening out the gain value of the target channel from the gain values ​​of all channels, and calculating the objective function value based on the gain value of the target channel and the gain value of the target channel screened out from the gain values ​​of all channels;

[0044] In some embodiments of the present scheme, in the step of determining the gain values ​​of all channels based on the pump adjustment parameters, a gain estimation model of a multi-band programmable Raman amplifier for providing real-time feedback is constructed, and the evaluation of the quality of the curves in the target curve space is completed based on the model. The modeling process can be implemented based on numerical modeling, simulation modeling, and machine learning pre-training methods, in a single or combined manner, to simulate the pump prediction and amplification process of the programmable Raman amplifier, and the effect achieved should be able to accurately simulate the pump prediction and amplification process of the programmable Raman amplifier, that is, under the condition of having the same input gain curve, the gain curve generated by the real programmable Raman amplifier should be as consistent as possible with the gain curve generated by the simulation process. After all the curves in the target curve space pass through the gain estimation model of the programmable Raman amplifier, a generation curve space composed of several one-to-one corresponding generation curves will be obtained, and the difference between the configuration curve and its one-to-one corresponding generation curve will be used as a measure of the gain generation effect of the programmable Raman amplifier.

[0045] Specifically, based on the feedback provided by the constructed gain estimation model and the input target parameters, Raman gain control optimization is performed on the target curve space, that is, the curve containing the target gain value of the specified channel in the target curve space is screened and optimized until the curve with the best gain generation effect is found, and the found curve is used as the output result of the optimization method. When this curve is used as the input of the programmable Raman amplifier, the curve can achieve the best gain generation accuracy on the specified wavelength channel.

[0046] The optimal curve found by Raman gain control optimization is used as the input target gain curve of the programmable Raman amplifier. Based on this curve, the programmable Raman amplifier completes the gain control process after pump prediction and instruction issuance.

[0047] Among them, the propagation equation of the Raman amplifier needs to consider the distribution of forward and backward pump, signal and ASE noise power, and the nonlinear differential equation satisfied by its propagation is as follows:

[0048]

[0049] Among them, P + (z,v i ) and P - (z,v i ) respectively when the frequency v iThe forward and reverse transmission optical powers nearby; α, η, h, k, T are the fiber attenuation coefficient, Rayleigh scattering coefficient, Planck constant, Boltzmann constant and absolute temperature respectively; A eff is the optical fiber at frequency v m The effective area of ​​g R is the Raman gain coefficient; Γ is the polarization factor.

[0050] Step S400, adjusting the gain value supplemented by the non-target channel based on the objective function value, and reconstructing the gain vector, and performing the next round of iteration. After completing the last iteration, the final pump adjustment parameter is selected from all the pump adjustment parameters.

[0051] In the specific implementation process, this scheme adopts a genetic algorithm, in which the initial population is constructed based on the gain value of the target channel target and the gain value of the non-target channel supplement, and the fitness is calculated in each round of iteration, and the population is updated to complete the iteration. Through continuous selection, crossover, and mutation, an optimal individual is iteratively found and used as the output of the algorithm.

[0052] In some embodiments of the present invention, selection, crossover, and mutation are performed cyclically, and individuals in the population are continuously evaluated until the termination condition of the iteration is met or the set number of iterations is completed. First, the selection operation is performed, the purpose is to select excellent individuals from the current population, and provide a basis for subsequent crossover and mutation operations. The selection process is usually based on the fitness of the individual, and individuals with high fitness have a higher probability of being selected. In the present invention, the fitness is calculated based on the inverse of the RMSE, so the selection process will tend to those individuals whose corresponding generated gain curves have a smaller error with the target gain on the specified wavelength channel; the crossover operation will be performed on the gain curve of the selected parent individual, and a new gain curve will be generated by exchanging the gain values ​​of some of their wavelength channels, thereby introducing new genetic diversity, while retaining the excellent characteristics of the parent individual; finally, the gain curve of the individual is adjusted in a small range through the mutation operation, that is, the gain value of a specific wavelength channel is fine-tuned to avoid the algorithm from converging to a local optimal solution too early and maintain the diversity of the population. It is worth noting that when performing crossover and mutation operations, they are only performed on unspecified wavelength channels, and for specified wavelength channels, the target gain value is always kept unchanged. Set the initial number of iterations, set the iteration optimization threshold and the iteration termination threshold. Once an individual's fitness exceeds the iteration optimization threshold, the iteration is accelerated appropriately; when an individual's fitness is greater than the termination threshold, the iteration is stopped and the individual is output as the result. Otherwise, iterate continuously until the set initial number of iterations is completed, and the optimal individual that appears in the iteration process is output as the final result.

[0053] In the specific implementation process, this scheme achieves high gain generation accuracy on the specified wavelength channel by adaptively optimizing the target gain of the programmable Raman amplifier on some specified transmission channels, thereby making full use of limited pump resources to maximize the gain generation accuracy of the multi-band programmable Raman amplifier on the specified wavelength channel. It is used to overcome the problem of limited gain generation accuracy of all-wavelength channels caused by the small number of adjustable parameters of the programmable Raman amplifier, and promote the application and effective deployment of programmable Raman amplifiers.

[0054] This solution is applicable to a variety of optical transmission scenarios, including but not limited to multi-band fixed grid optical network transmission, multi-band flexible grid optical network transmission, and multi-band ultra-long distance transmission system. Such transmission scenarios have an urgent need for adaptive gain control of multi-band optical network amplifiers due to large transmission bandwidth and uneven transmission spectrum.

[0055] The above scheme is adopted. This scheme first randomly supplements the gain value of the non-target channel, obtains the corresponding pump adjustment parameter through the inverse model, and then determines the gain value of all channels based on the pump adjustment parameter until the fitness meets the requirements. Since the pump adjustment parameter of this scheme is related to the gain value of all channels, this scheme obtains the corresponding pump adjustment parameter by supplementing, but the obtained pump adjustment parameter may not correspond to the gain value of the target channel. Then, this scheme further calculates the objective function value based on the gain value of the target channel and the gain value of the target channel selected from the gain values ​​of all channels, processes the target channel, and determines the final pump adjustment parameter through multiple rounds of iterations to ensure the pertinence to the specified wavelength channel of the link.

[0056] In some embodiments of the present invention, the target gain value of the specified wavelength channel is fixed, and the gain value of the non-specified wavelength channel is filled according to the specified rules. Through different filling values, several gain curves are obtained to form an initial population, and the population initialization is completed. Among them, the specified filling rule is to find the nearest channels with gain requirements on both sides of the channel. The value of the channel falling on the line connecting the two points will be used as the reference gain, and the filling value will oscillate randomly within a set range above and below the reference gain. Each individual in the initial population is a complete gain curve, which is composed of the target gain value of the specified wavelength channel and the filling gain value of the non-specified wavelength channel. This process involves the creation of the initial population, which determines the initial diversity of the algorithm search solution space. In this step, we set the number of initial populations to be negatively correlated with the number of channels with gain requirements. This means that when there are more channels with gain requirements, there are fewer locations where the target gain can fluctuate, and the number of initial populations can be relatively small, thereby reducing the complexity of algorithm retrieval; and when there are fewer channels with gain requirements, it means that the gain value of the target gain curve on many wavelength channels is fluctuating, and the number of initial populations is relatively large, thereby providing the algorithm with more candidate solutions to explore the optimal gain curve.

[0057] In some embodiments of the present invention, in the step of constructing a gain vector based on the gain value of the target channel and the gain value supplemented by the non-target channel, a random value is taken in a preset gain interval or the gain value of the non-target channel is supplemented based on the target gain values ​​of two adjacent target channels of the non-target channel to obtain the gain value supplemented by the non-target channel;

[0058] In the step of supplementing the gain value of the non-target channel based on the target gain values ​​of two adjacent target channels of the non-target channel, a line graph is constructed based on the target gain values ​​of all channels and the target channels, the horizontal axis of the line graph is the channel number, and the vertical axis is the gain value, and the points corresponding to the target gain values ​​of two adjacent target channels of the non-target channel are connected by a line, and the gain value corresponding to the vertical axis height corresponding to the horizontal axis position of the connecting line passing through the non-target channel is used as the gain value supplemented by the non-target channel.

[0059] In some embodiments of the present invention, in the step of determining the gain values ​​of all channels based on the pump adjustment parameters, the pump adjustment parameters are input into a preset forward model, and the forward model outputs the gain values ​​of all channels.

[0060] In some embodiments of the present invention, the forward model and the reverse model both adopt the structure of a feedforward neural network, a random forest or a convolutional neural network.

[0061] In the specific implementation process, a multi-band programmable Raman amplifier gain estimation model for providing real-time feedback is constructed. This step is the key to subsequent regulation and optimization. The modeling process can be based on numerical modeling, simulation modeling and machine learning pre-training methods, in a single or combined manner, to achieve simulation of pump prediction and amplification of programmable Raman amplifiers. In this embodiment, this scheme is modeled based on a machine learning method. By pre-training a machine learning model, a model that can accurately predict pumping and accurately simulate the amplification process of a programmable Raman amplifier is obtained to obtain the generation curve of the programmable Raman amplifier corresponding to different target gain curves. When simulating this process based on training a machine learning model, a large amount of data needs to be collected, including parameter settings of the programmable Raman amplifier under different pump configuration parameters and the corresponding Raman gain curve. These data can be generated by experimental measurement, simulation software or solving the propagation equation of the Raman amplifier. The quality and diversity of data collection are also crucial to the accuracy of the model. At the same time, it is necessary to select a sufficiently suitable machine learning method to build the model, and consider the complexity of the method, training time, prediction accuracy and generalization ability in the selection process. In this embodiment, this scheme selects a feedforward neural network to build the model.

[0062] In some embodiments of the present invention, in the step of calculating the objective function value based on the gain value of the target channel target and the gain value of the target channel screened from the gain values ​​of all channels:

[0063] Calculating a root mean square error based on a gain value of a target channel target and a gain value of the target channel screened from gain values ​​of all channels;

[0064] An objective function value is calculated based on the root mean square error.

[0065] In the specific implementation process, this scheme adopts genetic algorithm, reinforcement learning algorithm or particle swarm algorithm for iteration. Specifically, if genetic algorithm is adopted, the objective function value is the fitness value, and the gain vector is the population; if reinforcement learning algorithm is adopted, the objective function value is the reward function value; if particle swarm algorithm is adopted, the objective function value is the fitness value, and the gain vector is the particle swarm.

[0066] In some embodiments of the present invention, if a genetic algorithm is used, the objective function value is the fitness value. In the step of calculating the objective function value based on the root mean square error, the objective function value is calculated based on the following formula:

[0067]

[0068] Among them, S is the calculated objective function value, RMSE Cknown is the calculated root mean square error, C knownIndicates the target channel.

[0069] In some embodiments of the present invention, after completing the last iteration, in the step of screening the final pump adjustment parameters from all pump adjustment parameters, a first screening strategy or a second screening strategy is adopted, wherein the first screening strategy sets a preset round of iterations, and after completing all the iteration rounds, screens out one set of pump adjustment parameters as the final pump adjustment parameters; the second screening strategy determines the final pump adjustment parameters during the iteration process based on a preset screening threshold.

[0070] In some embodiments of the present invention, in the step of selecting one group of pump adjustment parameters as the final pump adjustment parameters, the pump adjustment parameters corresponding to the highest fitness value are used as the final pump adjustment parameters.

[0071] In some embodiments of the present invention, 1000 iterations are set to obtain 1000 configuration curves, and the one with the best configuration effect is selected as a comparison of the control method proposed by the present invention. The configuration curves obtained by the two methods are as follows: Figure 4 The two configuration curves are subjected to the programmable Raman amplifier simulation process to obtain two generated curves as shown in Figure 5 The results show that compared with the optimal configuration result in 1000 random configurations, the gain value of the generated curve obtained by the control method proposed in the present invention on the specified part of the channel is closer to the target gain value, achieving a higher gain generation accuracy.

[0072] In some embodiments of the present invention, in the step of determining the final pump adjustment parameters in the iterative process based on a preset screening threshold, after each round of iteration is completed, the calculated fitness value is compared with the preset fitness threshold. If the calculated fitness value is greater than the preset fitness threshold, then this round of iteration is regarded as the last round of iteration, and the pump adjustment parameters of this round are output as the final pump adjustment parameters.

[0073] This solution breaks through the current application limitations of programmable Raman amplifiers and enables them to meet the new requirements of multi-band optical networks for optical amplifiers. That is, by ensuring the gain generation accuracy on the specified wavelength channel, the programmable Raman amplifier can effectively play its role under limited pump resources, so that it can alleviate the degradation of signal transmission quality caused by the introduction of new bands and ensure the capacity expansion effect of multi-band optical networks.

[0074] This solution achieves high gain generation accuracy on a specified wavelength channel by finding an optimal input curve for the programmable Raman amplifier, breaking through the application limitations of programmable Raman amplifiers caused by the small number of pump adjustment parameters. At the same time, this method can provide users with real-time feedback on the gain generation effect, allowing them to make appropriate adjustments to the target gain based on the generation effect, providing a guarantee for the stable operation of the amplification process.

[0075] The beneficial effects of this program include:

[0076] 1. This scheme can achieve dynamic optimization and high gain generation accuracy: through adaptive control, it can adapt to the actual transmission status of the network in real time, and realize high-precision gain configuration for specific wavelength channels under limited pump resources, solving the problem of limited accuracy of arbitrary gain generation of full-wavelength channels caused by few pump adjustment parameters, and promoting the widespread application of programmable Raman amplifiers.

[0077] 2. This solution can provide real-time feedback: it can provide users with real-time feedback on the generation effect of the gain, so that they can make appropriate adjustments to the target gain based on the generation effect, providing a guarantee for the stable operation of the amplification process.

[0078] An embodiment of the present invention also provides a Raman gain adaptive control system for a multi-band optical network, the system comprising a computer device, the computer device comprising a processor and a memory, the memory storing computer instructions, the processor being used to execute the computer instructions stored in the memory, and when the computer instructions are executed by the processor, the system implements the steps implemented by the method described above.

[0079] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps implemented by the aforementioned Raman gain adaptive control method for multi-band optical networks are implemented. The computer-readable storage medium can be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0080] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier.

[0081] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0082] In the present invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with features of other embodiments or replace features of other embodiments.

[0083] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A Raman gain adaptive control method for multi-band optical networks, characterized in that: The steps of the method include: Obtaining a gain value of a target channel target, supplementing a gain value of a non-target channel, constructing a gain vector based on the gain value of the target channel target and the supplemented gain value of the non-target channel, and performing at least one round of iteration; In each round of iteration, the value in the gain vector is input into a pre-trained inverse model, and the inverse model outputs a corresponding pump adjustment parameter; Determine the gain values ​​of all channels based on the pump adjustment parameters, select the gain value of the target channel from the gain values ​​of all channels, and calculate the objective function value based on the gain value of the target channel and the gain value of the target channel selected from the gain values ​​of all channels; The gain value supplemented by the non-target channel is adjusted based on the objective function value, and the gain vector is reconstructed to perform the next round of iteration. After the last iteration is completed, the final pump adjustment parameter is selected from all the pump adjustment parameters.

2. The Raman gain adaptive control method for multi-band optical networks according to claim 1 is characterized in that: In the step of constructing a gain vector based on the target gain value of the target channel and the supplemented gain value of the non-target channel, a random value is taken in a preset gain interval or the gain value of the non-target channel is supplemented based on the target gain values ​​of two adjacent target channels of the non-target channel to obtain the supplemented gain value of the non-target channel; In the step of supplementing the gain value of the non-target channel based on the target gain values ​​of two adjacent target channels of the non-target channel, a line graph is constructed based on the target gain values ​​of all channels and the target channels, the horizontal axis of the line graph is the channel number, and the vertical axis is the gain value, and the points corresponding to the target gain values ​​of two adjacent target channels of the non-target channel are connected by a line, and the gain value corresponding to the vertical axis height corresponding to the horizontal axis position of the connecting line passing through the non-target channel is used as the gain value supplemented by the non-target channel.

3. The Raman gain adaptive control method for multi-band optical networks according to claim 1 is characterized in that: In the step of determining the gain values ​​of all channels based on the pump adjustment parameters, the pump adjustment parameters are input into a preset forward model, and the forward model outputs the gain values ​​of all channels.

4. The Raman gain adaptive control method for multi-band optical networks according to claim 3 is characterized in that: The forward model and the reverse model both adopt the structure of feedforward neural network, random forest or convolutional neural network.

5. The Raman gain adaptive control method for multi-band optical networks according to claim 1, characterized in that: In the step of calculating the objective function value based on the gain value of the target channel target and the gain value of the target channel screened from the gain values ​​of all channels: Calculating a root mean square error based on a gain value of a target channel target and a gain value of the target channel screened from gain values ​​of all channels; An objective function value is calculated based on the root mean square error.

6. The Raman gain adaptive control method for multi-band optical networks according to claim 5, characterized in that: If a genetic algorithm is used, the objective function value is the fitness value. In the step of calculating the objective function value based on the root mean square error, the objective function value is calculated based on the following formula: Among them, S is the calculated objective function value, is the calculated root mean square error, C known Indicates the target channel.

7. The Raman gain adaptive control method for multi-band optical networks according to any one of claims 1 to 6, characterized in that: After the last iteration is completed, in the step of selecting the final pump adjustment parameters from all the pump adjustment parameters, a first screening strategy or a second screening strategy is adopted, wherein the first screening strategy sets a preset number of iterations, and after all the iteration rounds are completed, one group of pump adjustment parameters is selected as the final pump adjustment parameters; The second screening strategy determines the final pump adjustment parameters in an iterative process based on a preset screening threshold.

8. The Raman gain adaptive control method for multi-band optical networks according to claim 7, characterized in that: In the step of selecting one set of pump adjustment parameters as the final pump adjustment parameters, if a genetic algorithm is used, the objective function value is the fitness value, and the pump adjustment parameters corresponding to the highest fitness value are used as the final pump adjustment parameters.

9. The Raman gain adaptive control method for multi-band optical networks according to claim 7, characterized in that: If a genetic algorithm is used, the objective function value is the fitness value. In the step of determining the final pump adjustment parameters in the iterative process based on a preset screening threshold, after each round of iteration is completed, the calculated fitness value is compared with the preset fitness threshold. If the calculated fitness value is greater than the preset fitness threshold, the iteration of this round is regarded as the last round of iteration, and the pump adjustment parameters of this round are output as the final pump adjustment parameters.

10. A Raman gain adaptive control system for multi-band optical networks, characterized in that: The system includes a computer device, which includes a processor and a memory. The memory stores computer instructions. The processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps implemented by the method as described in any one of claims 1 to 9.

Images