Multi-band dynamic optical network transmission optimization method and system

Abstract

The invention provides a multiband dynamic optical network transmission optimization method and system, and the method comprises the steps: determining whether an optical fiber node is a compensation point or not based on a power spectrum of the optical fiber node in an unoptimized optical network; calculating a target gain curve corresponding to the compensation point based on the power spectrum corresponding to the compensation point; inputting the target gain curve into a pre-trained machine learning model, and constructing an initial pumping power vector based on an output value of the machine learning model; the method comprises the steps of performing iterative calculation on an initial pumping power vector through a plurality of iteration rounds, determining final applied pumping power, in each iteration round, determining a circulating pumping power vector based on a current iteration pumping power vector, calculating an environment difference based on the circulating pumping power vector and the initial pumping power vector, and determining the final applied pumping power according to the environment difference. A new round of iterative pump power vector is calculated based on the environmental difference, and it is determined whether the new round of iterative pump power vector corresponds to a final applied pump power.

Description

Technical Field

[0001] The present invention relates to the technical field of optical amplifiers, and in particular to a multi-band dynamic optical network transmission optimization method and system. Background Art

[0002] With the rapid development of new Internet technologies and the explosive growth of terminals and applications, traffic has been growing exponentially. As the underlying network for transmission, optical networks are in urgent need of new capacity expansion methods to cope with the huge growth in traffic. Multi-band transmission is considered a promising alternative for recent optical network upgrades. This approach utilizes existing spectrum outside the traditional C-band, including O, E, S, and L bands. Given that widely deployed ITU-T G.652D optical fibers exhibit low attenuation in these bands, the necessity to deploy additional optical fibers can be effectively avoided in multi-band systems, and the various devices required in these bands are relatively mature. At present, multi-band wavelength division multiplexing systems have been proven to be an effective way to achieve greater optical network capacity.

[0003] However, while expanding the band, it will lead to more significant nonlinear effects, especially the stimulated Raman scattering effect between channels, which will cause non-uniform impact on signals in different bands, directly leading to complex changes in the power spectrum of the transmitted signal. Specifically, the channel power is transferred from the high-frequency channel to the low-frequency channel. This phenomenon will cause the signal quality of the high-frequency channel to be significantly lower than that of the low-frequency channel signal. In severe cases, it will lead to the inability to transmit signals at high frequencies. This problem reduces the effectiveness of multi-band expansion. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a multi-band dynamic optical network transmission optimization method and system to eliminate or improve one or more defects existing in the prior art.

[0005] One aspect of the present invention provides a multi-band dynamic optical network transmission optimization method, the method comprising the steps of:

[0006] Obtaining a power spectrum of each optical fiber node in the unoptimized optical network, wherein the power spectrum records power values ​​corresponding to the position of the optical fiber node at different frequencies, and determining whether the position corresponding to the optical fiber node is a compensation point based on the maximum and minimum values ​​of the power values ​​in the power spectrum;

[0007] Calculating a target gain curve corresponding to the compensation point based on a power spectrum corresponding to the compensation point, wherein the target gain curve includes gain values ​​corresponding to a plurality of different frequencies;

[0008] Inputting the target gain curve into a pre-trained machine learning model, and constructing an initial pump power vector based on an output value of the machine learning model;

[0009] The initial pump power vector is iteratively calculated through multiple iteration rounds to determine the pump power finally applied. In each iteration round, a cyclic pump power vector is calculated based on the current iterative pump power vector, an environmental difference is calculated based on the cyclic pump power vector and the initial pump power vector, an iterative pump power vector of a new round is calculated based on the environmental difference, and it is determined whether the iterative pump power vector of the new round corresponds to the pump power finally applied.

[0010] In the above scheme, since in the actual application of the Raman amplifier, the channel power is transferred from the high-frequency channel to the low-frequency channel, this phenomenon will cause the signal quality of the high-frequency channel to be significantly lower than the low-frequency channel signal. In severe cases, it will cause the signal to be unable to be transmitted at the high frequency. This problem reduces the effectiveness of multi-band capacity expansion. In the compensation point confirmation step of this scheme, the compensation point is determined based on the maximum and minimum values ​​of the power value in the power spectrum. The compensation point ensures that the compensation point is set at the maximum and minimum positions of the power value in the power spectrum, thereby ensuring the effectiveness of multi-band capacity expansion; and this scheme calculates through multiple rounds of iterative calculations, and in each round, the environmental difference is calculated based on the circulating pump power vector and the initial pump power vector, so that the circulating pump power vector is close to the initial pump power vector corresponding to the target gain curve, thereby ensuring that the final pump power realization effect matches the expected target.

[0011] In some embodiments of the present invention, in the step of calculating the cyclic pump power vector based on the current iterative pump power vector, the corresponding actual gain value is determined based on the current iterative pump power vector, and the cyclic pump power vector is determined based on the actual gain value.

[0012] In some embodiments of the present invention, the step of calculating a new round of iterative pump power vector based on the environmental difference includes:

[0013] Calculating a tuning parameter based on the initial pump power vector and the current iterative pump power vector;

[0014] A new round of iterative pump power vector is calculated based on the current iterative pump power vector, tuning parameters and environmental differences.

[0015] In some embodiments of the present invention, in the step of calculating a tuning parameter based on the initial pump power vector and the current iterative pump power vector, a quotient of the initial pump power vector and the current iterative pump power vector is calculated as the tuning parameter.

[0016] In some embodiments of the present invention, in the step of calculating a new round of iterative pump power vector based on the current iterative pump power vector, the tuning parameters and the environmental difference, the new round of iterative pump power vector is calculated based on the following formula:

[0017] P_new=P_last-λ*P_dif;

[0018] Among them, P_new represents the iterative pump power vector of a new round, P_last represents the current iterative pump power vector, P_dif represents the poor environment, and λ represents the tuning parameter.

[0019] In some embodiments of the present invention, in the step of determining whether a new round of iterative pump power vectors corresponds to a finally applied pump power, the new round of iterative pump power vectors are compared with a target gain curve to determine whether the new round of iterative pump power vectors corresponds to the finally applied pump power.

[0020] In some embodiments of the present invention, in the step of comparing an iterative pump power vector of a new round with a target gain curve to determine whether the iterative pump power vector of a new round corresponds to the pump power finally applied, a root mean square error and a maximum absolute error are calculated based on the gain values ​​corresponding to each power point in the iterative pump power vector of the new round and the gain values ​​corresponding to each power point in the target gain curve, and the root mean square error and the maximum absolute error are respectively compared with the corresponding root mean square error threshold and the maximum absolute error threshold to determine whether the iterative pump power vector of the new round corresponds to the pump power finally applied.

[0021] In some embodiments of the present invention, in the step of comparing the root mean square error and the maximum absolute error with the corresponding root mean square error threshold and the maximum absolute error threshold respectively to determine whether the iterative pump power vector of a new round corresponds to the pump power finally applied, if the root mean square error is less than the root mean square error threshold and the maximum absolute error is less than the maximum absolute error threshold, then the pump powers of each dimension in the iterative pump power vector of the new round are determined to be the pump powers finally applied.

[0022] In some embodiments of the present invention, in the step of determining whether the position corresponding to the optical fiber node is a compensation point based on the maximum and minimum values ​​of the power values ​​in the power spectrum, the difference between the maximum and minimum values ​​of the power values ​​in the power spectrum is calculated. If the difference between the maximum and minimum values ​​of the power values ​​in the power spectrum is greater than a preset difference threshold, the position corresponding to the optical fiber node is determined to be a compensation point.

[0023] The second aspect of the present invention also provides a multi-band dynamic optical network transmission optimization system, which includes a computer device, the computer device includes a processor and a memory, the memory stores computer instructions, the processor is 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.

[0024] The third aspect of the present invention also 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 multi-band dynamic optical network transmission optimization method.

[0025] 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.

[0026] 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

[0027] 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.

[0028] Figure 1 A schematic diagram of an implementation method of the multi-band dynamic optical network transmission optimization method of the present scheme;

[0029] Figure 2 A schematic diagram of another implementation of the multi-band dynamic optical network transmission optimization method of the present scheme;

[0030] Figure 3 This is the overall workflow diagram of this program;

[0031] Figure 4 This is the single compensation point pump configuration and iterative tuning workflow diagram of this solution;

[0032] Figure 5 This is the signal transmission quality optimization effect diagram of this solution. DETAILED DESCRIPTION

[0033] 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.

[0034] 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.

[0035] Existing technologies will lead to more significant nonlinear effects while expanding the band, especially the stimulated Raman scattering effect between channels, which will cause non-uniform effects on signals in different bands, directly leading to complex changes in the power spectrum of the transmitted signal, specifically manifested as the transfer of channel power from high-frequency channels to low-frequency channels. This phenomenon will cause the signal quality of high-frequency channels to be significantly lower than that of low-frequency channel signals. In severe cases, it will lead to the inability to transmit signals at high frequencies, which reduces the effectiveness of multi-band capacity expansion. In addition, when the network is highly dynamic, signals with different damages will bring greater challenges to relay devices when they are transmitted together in the channel, specifically manifested as more complex changes in the signal power spectrum, which requires relay devices to have more flexible characteristics to cope with different scenarios.

[0036] The existing solution mainly uses optical switches and optical attenuators for power balancing, that is, attenuating the power of all signals to the minimum power level of the signal, flattening the power spectrum and then re-amplifying to ensure the normal transmission of the signal, and repeating this process in the subsequent transmission process to ensure that the signal can be received normally at the transmission end. However, this solution will lead to a significant degradation of the signal transmission quality, thereby shortening the signal transmission distance, which is very unfavorable for long-distance signal transmission.

[0037] Raman amplifiers have wide-spectrum amplification capabilities, the potential to generate arbitrary gain spectra, and low noise coefficients, and are considered to be excellent relay amplifiers under multi-band expansion solutions. The introduction of machine learning methods has made it possible to quickly adjust Raman amplifiers. By collecting data and building an inverse mapping model, the corresponding pump parameters can be predicted based on the desired target parameters. In response to the problems in multi-band dynamic optical networks, it is a very promising solution to design and introduce Raman amplifier gain spectra based on specific situations and use multi-stage Raman amplifiers to cope with ultra-long-distance transmission scenarios.

[0038] However, the current research on the Raman amplifier gain spectrum generation scheme based on machine learning relies on specific scenarios, and the performance evaluation of the scheme only focuses on the same or similar scenarios. Due to the sensitivity of the Raman amplifier to changes in application scenarios, that is, changes in scenarios will directly lead to a decrease in the accuracy of gain spectrum generation, which is specifically manifested in the large difference between the gain spectrum actually introduced by the Raman amplifier and the expected gain spectrum. The introduction of network dynamics further enhances the uncertainty of the Raman amplifier deployment scenario. Only using the existing Raman amplifier based on machine learning is not enough to achieve transmission optimization in multi-band dynamic optical networks. To address this issue, it is unreasonable to re-collect data in new scenarios for new model training or to build a general model through multiple scenarios. It is costly and inefficient, and cannot guarantee efficient optimization of signal transmission in multi-band dynamic optical networks.

[0039] In view of the above situation, there is an urgent need for a transmission optimization method based on Raman amplifiers that can be deployed in multi-band dynamic optical networks. This method should be able to ensure the accurate generation of the Raman amplifier gain spectrum in a variety of scenarios, thereby avoiding the degradation of the optimization effect due to Raman amplifier errors. Compared with existing methods, this method should be able to effectively improve the signal transmission quality and ensure that the transmission in multi-band dynamic optical networks can be effectively optimized.

[0040] like Figure 1 and 3 As shown, the present invention proposes a multi-band dynamic optical network transmission optimization method, the steps of the method include:

[0041] Step S100, obtaining a power spectrum of each optical fiber node in the unoptimized optical network, wherein the power spectrum records power values ​​corresponding to the position of the optical fiber node at different frequencies, and determining whether the position corresponding to the optical fiber node is a compensation point based on the maximum and minimum power values ​​in the power spectrum;

[0042] In the specific implementation process, the optical network is composed of multiple optical fibers, the connection points between the optical fibers are optical fiber nodes, and the power spectrum of the optical fiber nodes is measured by a power measurement device.

[0043] In the specific implementation process, in the step of determining whether the position corresponding to the optical fiber node is a compensation point based on the maximum and minimum values ​​of the power values ​​in the power spectrum, the difference between the maximum and minimum values ​​of the power values ​​in the power spectrum is calculated, and based on the difference between the maximum and minimum values ​​of the power values ​​in the power spectrum, it is determined whether the position corresponding to the optical fiber node is a compensation point.

[0044] In the specific implementation process, a Raman amplifier needs to be set at the compensation point.

[0045] Step S200, calculating a target gain curve corresponding to the compensation point based on a power spectrum corresponding to the compensation point, wherein the target gain curve includes gain values ​​corresponding to a plurality of different frequencies;

[0046] Step S300, inputting the target gain curve into a pre-trained machine learning model, and constructing an initial pump power vector based on an output value of the machine learning model;

[0047] In some embodiments of the present invention, the machine learning model is a feedforward neural network model. In the process of training the machine learning model, the pump output power of the Raman amplifier is adjusted in the existing scenario, the power curves when the pump is not turned on and when the pump is turned on are collected respectively, the switch gain curve corresponding to the current power is calculated, the original data set is constructed, and the machine learning model used in the optimization scheme is trained based on the original data set;

[0048] In order to build a machine learning model, the original data set is collected. The specific data collection scenarios are as follows: First, in the light source part, a broadband noise light source is used to generate a multi-band optical signal. This light source can achieve high flatness and high power stability, and can ensure long-term normal operation. An adjustable optical attenuator is connected after the ASE light source to adjust the optical signal power; in the transmission medium part, the collection scenario is a standard single-mode optical fiber; in the deployment part of the Raman amplifier, the Raman amplifier used is equipped with multiple pump wavelengths, including multiple forward or backward pump input directions. It is worth noting that when using backward pumping, an optical isolator needs to be deployed at the optical fiber input port to avoid damage to the light source equipment; in the optical signal receiving part, the signal is output to the spectrum analyzer after passing through the optical fiber, and the optical power spectrum within the signal wavelength range is measured.

[0049] In this embodiment, the method for collecting data and performing data processing is as follows: first, when the Raman pump is turned off, the gain-free spectrum is recorded and set as the original state power spectrum; then the Raman pump is turned on, the output power of each pump source is adjusted, and then the corresponding signal power spectrum lines when different pump powers are input are recorded respectively, which are recorded as the open gain spectrum lines. After subtracting the open gain spectrum lines from the original state power spectrum, the switching gain of the Raman amplifier can be obtained. After the switching gain and the output power are matched one by one, several groups of original two-dimensional data sets for machine learning model training and verification are obtained. The machine learning model used here is a feedforward neural network, in which the switching gain is the model input, and the model input dimension is consistent with the switching gain dimension. The pump power is the model output, and the model output dimension is consistent with the power dimension. The learning goal is to minimize the prediction error of the pump configuration parameters, and the specific error evaluation parameter is the root mean square error. and the maximum absolute error And optimize the model parameters based on gradient descent.

[0050] like Figure 4 As shown, step S400, the initial pump power vector is iteratively calculated through multiple iteration rounds to determine the pump power finally applied, in each iteration round, a cyclic pump power vector is calculated based on the current iteration pump power vector, an environmental difference is calculated based on the cyclic pump power vector and the initial pump power vector, an iterative pump power vector of a new round is calculated based on the environmental difference, and it is determined whether the iterative pump power vector of the new round corresponds to the pump power finally applied.

[0051] In the above scheme, since in the actual application of the Raman amplifier, the channel power is transferred from the high-frequency channel to the low-frequency channel, this phenomenon will cause the signal quality of the high-frequency channel to be significantly lower than the low-frequency channel signal. In severe cases, it will cause the signal to be unable to be transmitted at the high frequency. This problem reduces the effectiveness of multi-band capacity expansion. In the compensation point confirmation step of this scheme, the compensation point is determined based on the maximum and minimum values ​​of the power value in the power spectrum. The compensation point ensures that the compensation point is set at the maximum and minimum positions of the power value in the power spectrum, thereby ensuring the effectiveness of multi-band capacity expansion; and this scheme calculates through multiple rounds of iterative calculations, and in each round, the environmental difference is calculated based on the circulating pump power vector and the initial pump power vector, so that the circulating pump power vector is close to the initial pump power vector corresponding to the target gain curve, thereby ensuring that the final pump power realization effect matches the expected target.

[0052] like Figure 2 As shown, in some embodiments of the present invention, in the step of calculating a cyclic pump power vector based on a current iterative pump power vector, step S410 is included, determining a corresponding actual gain value based on the current iterative pump power vector, and determining the cyclic pump power vector based on the actual gain value.

[0053] In the specific implementation process, in the step of determining the corresponding actual gain value based on the current iterative pump power vector, the pump power of the Raman amplifier is adjusted to each power value in the iterative pump power vector, and the corresponding gain value is collected as the actual gain value corresponding to the iterative pump power vector.

[0054] In some embodiments of the present invention, the step of calculating the environmental difference based on the circulating pump power vector and the initial pump power vector includes step S420, calculating the difference between the values ​​of each dimension of the circulating pump power vector and the initial pump power vector to obtain the environmental difference.

[0055] In the specific implementation process, in the step of calculating the difference between the values ​​of each dimension of the circulating pump power vector and the initial pump power vector to obtain the environmental difference, the difference between the values ​​of each dimension of the circulating pump power vector and the initial pump power vector is calculated as the corresponding vector of the environmental difference.

[0056] In some embodiments of the present invention, the step of calculating a new round of iterative pump power vector based on the environmental difference includes:

[0057] Step S430, calculating a tuning parameter based on the initial pump power vector and the current iterative pump power vector;

[0058] Step S440: Calculate a new round of iterative pump power vector based on the current iterative pump power vector, the tuning parameters and the environmental difference.

[0059] In some embodiments of the present invention, in the step of calculating the tuning parameter based on the initial pump power vector and the current iterative pump power vector, a quotient of the initial pump power vector and the current iterative pump power vector is calculated as the tuning parameter.

[0060] In some embodiments of the present invention, in the step of calculating a new round of iterative pump power vector based on the current iterative pump power vector, the tuning parameters and the environmental difference, the new round of iterative pump power vector is calculated based on the following formula:

[0061] P_new=P_last-λ*P_dif;

[0062] Among them, P_new represents the iterative pump power vector of a new round, P_last represents the current iterative pump power vector, P_dif represents the poor environment, and λ represents the tuning parameter.

[0063] The above scheme is adopted. The principle of the formula is to fine-tune the previous pump configuration parameters according to the scene differences in each iteration. This process can gradually approach the optimal pump configuration, so that the actual gain curve gradually approaches the target gain curve.

[0064] In a specific implementation process, in the step of calculating the target gain curve corresponding to the compensation point based on the power spectrum corresponding to the compensation point, the gain value corresponding to each frequency point in the target gain curve is calculated based on the following formula:

[0065]

[0066] in, represents the gain value corresponding to frequency point i, N represents the total number of frequency points, P i Indicates the power value corresponding to frequency point i in the power spectrum, G 平均 represents the average gain across all frequencies introduced by the desired Raman amplifier.

[0067] In the specific implementation process, since the Raman pump source has an upper limit on the power output, in order to avoid the unreasonable target gain curve affecting the normal output of the Raman amplifier, an upper limit is set for the maximum gain value introduced by the Raman amplifier, and the gain of the original amplifier needs to be corrected according to the introduced average Raman gain; it is worth noting that in the actual network, due to the behavior of wavelength exchange in transmission, the power spectrum will cause power jumps between frequency points, and the gain curve generated by the above formula may be unreasonable, resulting in abnormal values ​​when the machine learning model predicts Raman pumping, which is not conducive to achieving full transmission optimization; for the power jump phenomenon, in this embodiment, the gain value of individual frequency points is corrected by interpolation method to ensure that the Raman amplifier generates gain with high precision.

[0068] In this embodiment, after the design of the target gain curve is completed, the initially trained machine learning model can be used to predict Raman pumping. Specifically, the gain curve is input into the machine learning model from large to small according to the frequency point, and the model predicts the initial Raman pumping configuration through calculation output; the configuration is deployed to the Raman compensation point, and the originally used amplifier is adjusted according to the introduced average gain value so that the average value of the output signal power remains unchanged after the compensation is completed; the power spectrum at the compensation point is re-collected, and the power spectrum is subtracted from the power spectrum before compensation according to the frequency point, and then summed with the introduced average gain value, so as to calculate the actual gain curve introduced under the current pumping configuration.

[0069] In some embodiments of the present invention, the step of determining whether a new round of iterative pump power vector corresponds to a finally applied pump power includes step S450, comparing a new round of iterative pump power vector with a target gain curve to determine whether the new round of iterative pump power vector corresponds to the finally applied pump power.

[0070] In some embodiments of the present invention, in the step of comparing an iterative pump power vector of a new round with a target gain curve to determine whether the iterative pump power vector of a new round corresponds to the pump power finally applied, a root mean square error and a maximum absolute error are calculated based on the gain values ​​corresponding to each power point in the iterative pump power vector of the new round and the gain values ​​corresponding to each power point in the target gain curve, and the root mean square error and the maximum absolute error are respectively compared with the corresponding root mean square error threshold and the maximum absolute error threshold to determine whether the iterative pump power vector of the new round corresponds to the pump power finally applied.

[0071] In some embodiments of the present invention, in the step of comparing the root mean square error and the maximum absolute error with the corresponding root mean square error threshold and the maximum absolute error threshold respectively to determine whether the iterative pump power vector of a new round corresponds to the pump power finally applied, if the root mean square error is less than the root mean square error threshold and the maximum absolute error is less than the maximum absolute error threshold, then the pump powers of each dimension in the iterative pump power vector of the new round are determined to be the pump powers finally applied.

[0072] In a specific implementation process, the thresholds of the root mean square error (RMSE) and the maximum absolute error (Emax) may be determined according to specific conditions of the optical network.

[0073] Using the above scheme, if both evaluation indicators are lower than the threshold, the point is deemed to have successfully completed the pump configuration of the Raman compensation point; if any of the evaluation indicators is higher than the threshold, iterative tuning is required according to the specific error situation.

[0074] In some embodiments of the present invention, in the step of determining whether the position corresponding to the optical fiber node is a compensation point based on the maximum and minimum values ​​of the power values ​​in the power spectrum, the difference between the maximum and minimum values ​​of the power values ​​in the power spectrum is calculated. If the difference between the maximum and minimum values ​​of the power values ​​in the power spectrum is greater than a preset difference threshold, the position corresponding to the optical fiber node is determined to be a compensation point.

[0075] In the specific implementation process, the Raman amplifier pump configuration at all compensation points is completed, and the quality parameters when all service transmissions are completed are recorded. The evaluation index for signal transmission quality is mainly the generalized signal-to-noise ratio GSNR, which takes into account the influence of linear noise P_ASE and nonlinear noise P_NLI on the signal. The formula is as follows:

[0076]

[0077] P is the actual measured signal power.

[0078] In the specific implementation process, due to the need to optimize the transmission of multi-band dynamic optical networks, it is necessary to perceive and evaluate the actual network status in the current state. Due to the strong nonlinear influence of stimulated Raman scattering, the most significant manifestation of the affected signal status is the signal power spectrum; in addition, it is currently difficult to measure other parameters except power during signal transmission. In summary, the specific method for perceiving and evaluating the actual network status is to collect the signal power spectrum at the end of each span of optical fiber. The specific evaluation method for the signal power spectrum situation is to calculate the degree of power spectrum tilt. The calculation method is to use the power of the signal at the maximum wavelength minus the power of the signal at the minimum wavelength, and record it as the maximum signal power difference; when the maximum signal power difference exceeds the set threshold, it is necessary to determine this point as the Raman compensation point.

[0079] By adopting the above scheme, before the compensation point is determined, the signal power spectrum is collected at each optical fiber end in turn, and the collected power spectrum is analyzed. Usually, a certain threshold is set. When the power spectrum tilt exceeds the threshold for the first time, the point is set as the compensation point. Subsequent compensation points can be set backward in sequence according to the distance between the first compensation point and the source node. The position of the compensation point in this step can also be determined by the position of the traditional optical switch equalization station, that is, the Raman amplifier is directly used to replace each optical switch equalization station in turn.

[0080] Since the power spectrum at the end of the subsequent optical fiber always exceeds the preset threshold when the set Raman compensation is not performed, the compensation point cannot be determined by measuring the power spectrum. The number of spans from the starting point to the first compensation point can be calculated and recorded as the maximum uncompensated span number. For subsequent compensation points, the maximum uncompensated span number can be used to calculate backward from the first compensation point and set in sequence until the transmission end.

[0081] This solution addresses the problem that the existing multi-band power equalization solution only considers the use of optical switches and optical attenuators for all situations, lacks consideration of the actual transmission power spectrum, and leads to significant degradation of signal transmission quality. It provides an alternative solution other than the traditional optical switch equalization station, providing strong technical support for the multi-band expansion solution. This solution uses machine learning methods to regulate the gain spectrum generated by the Raman amplifier, and iteratively optimizes the gain accuracy based on the gap between the deployment scenario and the original scenario, achieving effective regulation of the signal power spectrum, and ultimately achieving significant improvement in signal transmission quality while ensuring normal signal transmission.

[0082] In the specific implementation process, the iterative tuning process includes two steps: error evaluation and pump configuration update. The condition for terminating the iteration is consistent with that described in the error evaluation, that is, the iterative tuning is considered to be completed when the error is lower than the threshold, otherwise the pump configuration update is continued for multiple iterations. In this embodiment, the upper limit of the number of iterations is set to 7 times, and the iterative tuning of the compensation point is usually completed within 5 iterations. If the error evaluation still fails when the iteration is terminated, the design of the initial gain curve needs to be re-evaluated and some numerical adjustments need to be made.

[0083] In this embodiment, when the Raman compensation point successfully completes the pump configuration after iterative tuning, the same process as above can be performed in sequence along the propagation direction of the optical signal according to the expected estimated Raman compensation points. After all the pre-estimated Raman compensation points are compensated, the signal transmission quality at the signal transmission end point is recorded. It is worth noting that since the optical signal transmission in the multi-band dynamic optical network is not limited to a certain transmission end point, we need to record the optical signals at different transmission end points at each end point separately. In this embodiment, in order to fully evaluate the impact of linear interference and nonlinear interference on the signal, the generalized signal-to-noise ratio GSNR is used as the evaluation index for signal quality.

[0084] In this embodiment, in order to illustrate the optimization effect of the multi-band dynamic optical network transmission optimization method based on a multi-stage Raman amplifier, the baseline solution is selected as the existing method of jointly constructing an equalizing station with an optical switch and an optical attenuator. The method for adjusting the relay device in the specific topology is to remove the Raman pumps at all compensation points, deploy an equalizing station at each Raman compensation point, and adjust the input gain of the amplifier to ensure that the average power value of the signal remains unchanged when the relay device outputs in order to fully demonstrate the contrast. The GSNR at the end point of the signal transmission is recorded similarly to the above method. In addition, in this embodiment, the network topology is modified to a situation where the Raman compensation scheme and the equalizing station scheme are used at the same time, and the GSNR at the end point of the signal transmission is recorded similarly to the above method.

[0085] In this embodiment, the GSNR curves of the two solutions are graphically illustrated according to the corresponding frequency points, and the signal transmission quality optimization effect diagram is shown in FIG. Figure 5 As shown, the baseline solution uses a three-stage optical switch equalization station; the two-stage Raman amplifier uses the Raman compensation solution for the first two compensation points under the same service situation, and the last compensation point uses the equalization station solution; the three-stage Raman amplifier uses the Raman compensation solution for all compensation points. The GSNR curves are subtracted according to the frequency points as a quantitative representation of the significant optimization effect of the optimization scheme. In this embodiment, the GSNR mean is used for specific characterization. The two-stage Raman amplifier can increase the GSNR mean of the optical signal by about 1.6dB, while the three-stage Raman amplifier can increase the GSNR mean of the optical signal by about 2.2dB.

[0086] The beneficial effects of this program include:

[0087] 1. Adaptively optimize the multi-band dynamic optical network according to the actual transmission situation, avoiding the limitation of the equalization scheme of the traditional optical switch attenuation mode that takes the same treatment method for all situations, overcoming the dependence on the use of optical switch attenuation scheme, and thus avoiding the problem of transmission quality degradation caused by the introduction of optical switches and optical attenuators.

[0088] 2. This method can adapt to the dynamic network environment and effectively handle the dynamic changes in the network. In the process of signal processing, it efficiently utilizes the parameter characteristics of the signal transmission process. The optimization scheme uses a Raman amplifier with better noise performance, which can significantly improve the transmission quality and extend the transmission distance.

[0089] 3. In the process of regulating the Raman amplifier, the traditional control scheme based on machine learning methods is overcome by being restricted by the limitations of application scenarios. It can adaptively iteratively tune the pump parameter configuration according to the changes in the scenario, ensuring high-efficiency and high-precision Raman amplifier configuration, thereby greatly ensuring the effectiveness of the optimization scheme in improving signal quality in various scenarios.

[0090] An embodiment of the present invention also provides a multi-band dynamic optical network transmission optimization system, which includes a computer device, wherein the computer device includes a processor and a memory, wherein the memory stores computer instructions, and 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 described above.

[0091] 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 multi-band dynamic optical network transmission optimization method 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.

[0092] 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.

[0093] 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.

[0094] 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 or replace features of other embodiments.

[0095] 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 multi-band dynamic optical network transmission optimization method, characterized in that: The steps of the method include: Obtaining a power spectrum of each optical fiber node in the unoptimized optical network, wherein the power spectrum records power values ​​corresponding to the position of the optical fiber node at different frequencies, and determining whether the position corresponding to the optical fiber node is a compensation point based on the maximum and minimum values ​​of the power values ​​in the power spectrum; Calculating a target gain curve corresponding to the compensation point based on a power spectrum corresponding to the compensation point, wherein the target gain curve includes gain values ​​corresponding to a plurality of different frequencies; Inputting the target gain curve into a pre-trained machine learning model, and constructing an initial pump power vector based on an output value of the machine learning model; The initial pump power vector is iteratively calculated through multiple iteration rounds to determine the pump power finally applied. In each iteration round, a cyclic pump power vector is calculated based on the current iterative pump power vector, an environmental difference is calculated based on the cyclic pump power vector and the initial pump power vector, an iterative pump power vector of a new round is calculated based on the environmental difference, and it is determined whether the iterative pump power vector of the new round corresponds to the pump power finally applied.

2. The multi-band dynamic optical network transmission optimization method according to claim 1, characterized in that: In the step of calculating and determining the cyclic pump power vector based on the current iterative pump power vector, a corresponding actual gain value is determined based on the current iterative pump power vector, and the cyclic pump power vector is determined based on the actual gain value.

3. The multi-band dynamic optical network transmission optimization method according to claim 1, characterized in that: The step of calculating a new round of iterative pump power vector based on the environmental difference comprises: Calculating a tuning parameter based on the initial pump power vector and the current iterative pump power vector; A new round of iterative pump power vector is calculated based on the current iterative pump power vector, tuning parameters and environmental differences.

4. The multi-band dynamic optical network transmission optimization method according to claim 3, characterized in that: In the step of calculating the tuning parameter based on the initial pump power vector and the current iterative pump power vector, a quotient of the initial pump power vector and the current iterative pump power vector is calculated as the tuning parameter.

5. The multi-band dynamic optical network transmission optimization method according to claim 3, characterized in that: In the step of calculating a new round of iterative pump power vector based on the current iterative pump power vector, the tuning parameters and the environmental difference, the new round of iterative pump power vector is calculated based on the following formula: P_new=P_last-λ*P_dif; Among them, P_new represents the iterative pump power vector of a new round, P_last represents the current iterative pump power vector, P_dif represents the poor environment, and λ represents the tuning parameter.

6. The multi-band dynamic optical network transmission optimization method according to any one of claims 1 to 5, characterized in that: In the step of determining whether the iterative pump power vector of a new round corresponds to the final applied pump power, the iterative pump power vector of a new round is compared with the target gain curve to determine whether the iterative pump power vector of a new round corresponds to the final applied pump power.

7. The multi-band dynamic optical network transmission optimization method according to claim 6, characterized in that: In the step of comparing the iterative pump power vector of a new round with the target gain curve to determine whether the iterative pump power vector of the new round corresponds to the pump power finally applied, a root mean square error and a maximum absolute error are calculated based on the gain values ​​corresponding to each power point in the iterative pump power vector of the new round and the gain values ​​corresponding to each power point in the target gain curve, and the root mean square error and the maximum absolute error are respectively compared with the corresponding root mean square error threshold and maximum absolute error threshold to determine whether the iterative pump power vector of the new round corresponds to the pump power finally applied.

8. The multi-band dynamic optical network transmission optimization method according to claim 1, characterized in that: In the step of calculating the target gain curve corresponding to the compensation point based on the power spectrum corresponding to the compensation point, the gain value corresponding to each frequency point in the target gain curve is calculated based on the following formula: in, represents the gain value corresponding to frequency point i, N represents the total number of frequency points, P i represents the power value corresponding to the frequency point i in the power spectrum, and Gaverage represents the average gain of all frequency points introduced by the desired Raman amplifier.

9. The multi-band dynamic optical network transmission optimization method according to claim 1 or 8, characterized in that: In the step of determining whether the position corresponding to the optical fiber node is a compensation point based on the maximum and minimum values ​​of the power values ​​in the power spectrum, the difference between the maximum and minimum values ​​of the power values ​​in the power spectrum is calculated. If the difference between the maximum and minimum values ​​of the power values ​​in the power spectrum is greater than a preset difference threshold, the position corresponding to the optical fiber node is determined to be a compensation point.

10. A multi-band dynamic optical network transmission optimization system, 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