Intelligent monitoring system and method for 400g coherent optical module

Abstract

The application discloses an intelligent monitoring system and method for a 400G coherent optical module, and relates to the technical field of optical communication.The system comprises a historical band switching data acquisition module, which is used for loading historical band data, including a received signal, a switching type, environmental information and an accuracy label; a band boundary locking template construction module, which can construct a band boundary locking template based on the historical band switching data; a real-time band switching data monitoring module, which can acquire real-time band switching data according to a band switching instruction; and a band boundary adjustment module, which is used for adjusting the band boundary of the 400G coherent optical module according to template analysis data.The application solves the technical problem that the existing 400G coherent optical module is prone to losing lock during band switching, which affects the stability of communication, and achieves the technical effects of accurately responding to dynamic changes in band switching through an intelligent monitoring and dynamic adjustment mechanism, effectively reducing band lock loss and improving the stability of communication.

Description

Technical Field

[0001] This invention relates to the field of optical communication technology, and more specifically to an intelligent monitoring system and method for 400G coherent optical modules. Background Technology

[0002] In modern high-speed communication networks, 400G coherent optical modules serve as critical transmission equipment, undertaking the task of efficiently transmitting massive amounts of data. However, during band switching, they often experience band lock-up issues due to fiber characteristics, environmental changes, and the complexity of signal processing. This means the signal cannot be stably locked onto the target band, leading to transmission interruptions or quality degradation, severely impacting the stability and reliability of the communication system. Traditional band switching methods mostly rely on fixed preset parameters, lacking adaptability to environmental changes and network load fluctuations. This makes them prone to inaccurate adjustments during band switching, resulting in lock-up or signal attenuation. Summary of the Invention

[0003] This application provides an intelligent monitoring system and method for 400G coherent optical modules, which solves the technical problem that existing 400G coherent optical modules are prone to loss of lock during band switching, affecting communication stability.

[0004] The first aspect of this application provides an intelligent monitoring system for a 400G coherent optical module. The system includes: a historical band switching data acquisition module, used to load historical band switching data of the 400G coherent optical module within a preset period. The historical band switching data includes historical band received signals, band switching type labels, band signal transmission environment information, and accuracy labels characterizing the band signal reception accuracy. The band switching type labels at least include switching types from C-band to L-band and from L-band to C-band. A band boundary locking template is also provided. The system includes a construction module for constructing a band boundary locking template based on the historical band switching data; a real-time band switching data monitoring module for determining whether the 400G coherent optical module receives a band switching command; and a band boundary adjustment module for analyzing the real-time band switching data using the constructed band boundary locking template, obtaining the first band boundary corresponding to the band switching command, and adjusting the band boundary of the tunable laser in the 400G coherent optical module based on the first band boundary.

[0005] A second aspect of this application provides an intelligent monitoring method for a 400G coherent optical module. The method includes: loading historical band switching data of the 400G coherent optical module within a preset period, the historical band switching data including historical band received signals, band switching type labels, band signal transmission environment information, and accuracy labels characterizing the band signal reception accuracy. The band switching type labels at least include switching types from C-band to L-band and from L-band to C-band. A band boundary locking template is constructed based on the historical band switching data. It is determined whether the 400G coherent optical module receives a band switching command. If the 400G coherent optical module receives a band switching command, real-time band switching data is acquired. The real-time band switching data is analyzed using the constructed band boundary locking template to obtain a first band boundary corresponding to the band switching command. The band boundary of the tunable laser in the 400G coherent optical module is adjusted based on the first band boundary.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The intelligent monitoring system and method for 400G coherent optical modules provided in this application relate to the field of optical communication technology. It constructs a band boundary locking template based on historical band switching data, and after band switching, uses this template to analyze real-time band switching data to dynamically adjust the band boundaries of the tunable laser in the 400G coherent optical module. This solves the technical problem of existing 400G coherent optical modules easily losing lock during band switching, affecting communication stability. It achieves the technical effect of accurately responding to dynamic changes during band switching through intelligent monitoring and dynamic adjustment mechanisms, effectively reducing band lock loss and improving communication stability. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 A schematic diagram of an intelligent monitoring system for a 400G coherent optical module provided in an embodiment of this application;

[0010] Figure 2 This is a schematic diagram of an intelligent monitoring method for a 400G coherent optical module provided in an embodiment of this application.

[0011] Figure labeling: Historical band switching data acquisition module 10, band boundary locking template construction module 20, real-time band switching data monitoring module 30, band boundary adjustment module 40. Detailed Implementation

[0012] This application provides an intelligent monitoring system and method for 400G coherent optical modules, which solves the technical problem that existing 400G coherent optical modules are prone to loss of lock during band switching, affecting communication stability.

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0014] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or devices.

[0015] Example 1, as Figure 1 As shown, this application provides an intelligent monitoring system for a 400G coherent optical module, the system comprising:

[0016] The historical band switching data acquisition module 10 is used to load historical band switching data of the 400G coherent optical module within a preset period. The historical band switching data includes historical band received signals, band switching type tags, band signal transmission environment information, and accuracy tags characterizing the band signal reception accuracy. The band switching type tags at least include switching types from C-band to L-band and from L-band to C-band. Furthermore, the 400G coherent optical module also includes an extension module, which extends multiple bands and updates multiple band switching type tags based on these multiple bands.

[0017] Furthermore, when acquiring the accuracy tag that characterizes the accuracy of band signal reception, the historical band switching data acquisition module 10 is also used to perform the following steps:

[0018] P11: Evaluate the band accuracy of historical band received signals, including wavelength attenuation slope, filter loss gain, and signal bit error rate; P12: Calculate the weights of the wavelength attenuation slope, filter loss gain, and signal bit error rate to obtain the accuracy label representing the band signal reception accuracy corresponding to the historical band received signals.

[0019] It should be understood that the main task of the historical band switching data acquisition module 10 of this application is to load and process the historical band switching data of the 400G coherent optical module within a preset period, so as to provide the system with decision-making basis based on historical data.

[0020] First, historical band switching data contains several important data items, including historical band received signals, band switching type labels, band signal transmission environment information, and accuracy labels. The historical band received signals refer to the signal strength received by the 400G coherent optical module at different bands. Band switching type labels clearly identify the switching type between different bands. For example, switching from C-band to L-band, and switching from L-band to C-band. The band switching type labels at least include switching types from C-band to L-band and from L-band to C-band, allowing the system to distinguish the types and characteristics of different band switching. Band signal transmission environment information records environmental changes during transmission, such as temperature, humidity, and other external factors that affect the transmission quality of the band signal. The accuracy label characterizes the accuracy of band signal reception, generated based on the evaluated signal quality.

[0021] Accuracy labeling is a core indicator for measuring the quality of band signal reception. It comprehensively evaluates the accuracy and reliability of the signal by integrating multiple key parameters. Specifically, when obtaining accuracy labels that characterize the accuracy of band signal reception, the band accuracy is first evaluated on historical band received signals. The evaluation includes wavelength attenuation slope, filter loss gain, and bit error rate (BER). Wavelength attenuation slope is the degree of attenuation caused by wavelength changes during signal transmission, reflecting the transmission loss of the signal in different bands. Filter loss gain reflects the impact of filters on the signal; signal gain or loss may occur during filtering. The bit error rate (BER) is a key indicator for evaluating signal transmission quality, representing the ratio of error between the received and transmitted signals. Each evaluation indicator represents a dimension of signal quality.

[0022] Next, based on a pre-defined weighting model, the wavelength attenuation slope, filter loss gain, and signal bit error rate are comprehensively weighted to generate an accuracy label. Each factor has a different degree of influence on the final accuracy label, and the weight of each evaluation indicator can be calculated using empirical rules or regression analysis based on historical data. For example, the signal bit error rate may have a more significant impact on accuracy than the wavelength attenuation slope, and therefore its weight will be higher. In this way, the influence of different factors can be comprehensively considered when assigning weight coefficients, and the final accuracy label can be calculated based on these weights to indicate the accuracy of the received signal in a specific band.

[0023] Building upon this, the 400G coherent optical module also includes an expansion module to extend the band count to handle more complex band switching requirements. As the number of bands increases, the band switching type label is updated to cover more band switching scenarios. For example, when the expansion module introduces a new O band, the band switching type label will be updated promptly, adding new switching types such as C-band to O band and O-band to L band. This enables the system to handle more complex band switching tasks, improving the flexibility and reliability of band switching.

[0024] The band boundary locking template construction module 20 is used to construct a band boundary locking template based on the historical band switching data.

[0025] Furthermore, the band boundary locking template construction module 20 is also used to perform the following steps:

[0026] P21: Collect the first set of historical band switching data from C-band to L-band, and the second set of historical band switching data from L-band to C-band; P22: Use the historical band received signal and band signal transmission environment information corresponding to the first and second sets of historical band switching data as input data, use the band boundary as the adjustable variable space, and use the accuracy labels corresponding to the first and second sets of historical band switching data as supervision labels to perform regression analysis to obtain the band boundary regression model; P23: Construct a band boundary locking template based on the band boundary regression model.

[0027] Optionally, the main function of the band boundary locking template construction module 20 in this application is to construct an intelligent locking template that can be used for band boundary adjustment by analyzing historical band switching data. This template can dynamically adjust the band boundary according to historical data during actual band switching, ensuring stability and signal quality during the switching process.

[0028] In constructing the band boundary locking template, the band boundary locking template construction module 20 first needs to collect two specific sets of historical band switching data. The first set of data comes from switching data from C-band to L-band, and the second set comes from switching from L-band to C-band. These two sets of data cover the different conditions and characteristics of switching between different bands, including information such as the received band signal, the band signal transmission environment, and accuracy labels during the actual switching process. Through this historical data, a detailed background on the band switching can be obtained, including the band signal quality, transmission environment, and corresponding accuracy.

[0029] Next, the historical band switching data from the first and second sets of historical band switching data, along with the corresponding historical band received signals and band signal transmission environment information, are used as input data. This data includes signal strength in different bands, influencing factors of the transmission environment, etc., and the accuracy labels in each set of data will be used as supervision labels. Simultaneously, using the band boundaries as an adjustable variable space, the accuracy labels corresponding to the first and second sets of historical band switching data are used as supervision labels. Through regression analysis, these input data and supervision labels are processed to obtain a band boundary regression model. This regression model can reveal the intrinsic relationship between band boundaries and signal reception accuracy, providing a theoretical basis for subsequent band boundary locking.

[0030] Finally, a band boundary locking template is constructed based on the obtained band boundary regression model. This template integrates and encapsulates the key parameters and rules in the band boundary regression model, forming a template that can be called in real time. During subsequent band switching, the system can quickly and accurately adjust the band boundaries according to the parameters and rules in this band boundary locking template, thereby effectively avoiding the occurrence of band lock-up and ensuring the stable transmission of communication signals.

[0031] Furthermore, in the band boundary locking template construction module 20:

[0032] The band boundary regression model includes a first interval regression model for switching from C-band to L-band and a second interval regression model for switching from L-band to C-band; the band switching type of the band switching command is decomposed, and the real-time band switching data is analyzed according to the band switching type using the first interval regression model or the second interval regression model.

[0033] In one possible embodiment of this application, the band boundary locking template construction module 20 can also accurately apply the corresponding regression model for analysis according to different band switching types during the construction of the band boundary regression model, thereby further improving the accuracy and reliability of band switching.

[0034] Specifically, the band boundary regression model includes a first-interval regression model for switching from C-band to L-band and a second-interval regression model for switching from L-band to C-band. These two regression models are used to process data of different band switching types and can provide more accurate band boundary adjustment suggestions for different switching directions and band characteristics.

[0035] When the band boundary locking template construction module 20 receives a band switching command, it first decomposes the command to determine the specific band switching type. This process can be achieved by analyzing key information in the band switching command, such as using the starting and target bands specified in the command for decomposition, and based on the decomposition results, determining whether the current band switching is from C-band to L-band or from L-band to C-band. Depending on the switching type, an appropriate interval regression model can be selected to analyze the real-time band switching data. For example, for a C-band to L-band switch, the first interval regression model can be used for analysis, while for an L-band to C-band switch, the second interval regression model can be used. This targeted analysis method can fully utilize the characteristics and advantages of each interval regression model, ensuring that the analysis results of the real-time band switching data are more accurate and reliable.

[0036] Through this design, the band boundary locking template building module 20 can more accurately adjust the band boundary dynamically according to different band switching types, optimize the performance of the 400G coherent optical module in various band environments, and ensure that the system can still maintain a high-efficiency and stable working state during complex band switching processes.

[0037] Furthermore, after obtaining the band boundary regression model, the band boundary locking template construction module 20 is also used to perform the following steps:

[0038] P22-1a: Train a generator based on the band boundary regression model. The generator is used to obtain incremental band switching data from the historical band switching data. P22-2a: Perform incremental optimization on the band boundary regression model based on the incremental band switching data, and output the optimized band boundary regression model.

[0039] Specifically, after completing the initial construction of the band boundary regression model, the band boundary locking template construction module 20 can further improve the accuracy and adaptability of the model through an incremental optimization mechanism.

[0040] After obtaining the band boundary regression model, a generator is first trained using it. The generator's main function is to generate incremental band switching data related to historical band switching data, based on the existing model. This incremental data does not simply replicate historical data; instead, it uses the prediction and simulation capabilities of the band boundary regression model to generate new band switching data with variations and diversity. This data reflects new situations that may arise under different environmental conditions, signal quality levels, and band switching types. Specifically, the generator utilizes the parameters and patterns in the band boundary regression model, combined with certain randomness and variation rules, to generate new band received signals, band signal transmission environment information, and corresponding accuracy labels—that is, incremental band switching data. This incremental band switching data supplements the deficiencies of historical data, increasing its richness and coverage, thus providing more comprehensive training material for subsequent model optimization.

[0041] After acquiring incremental band switching data, the band boundary locking template construction module 20 performs incremental optimization on the existing band boundary regression model based on this new data. By using the incremental data as new training samples, the model can learn more new features and patterns, thereby improving its adaptability and prediction accuracy to different band switching scenarios. For example, during the incremental optimization process, the band boundary regression model adjusts its internal parameters and weights according to the input features in the incremental data, such as the received band signal, the band signal transmission environment information, and the corresponding supervision label (accuracy label). The adjustment process can be based on regression analysis optimization algorithms, such as least squares and gradient descent, to minimize the error between the model's predicted value and the actual accuracy label. Unlike traditional batch training methods, incremental optimization can reduce repeated training on all historical data, save computational resources, and can adjust the model in real time as new data is added, ensuring that it adapts to new environments and band switching modes.

[0042] Finally, after incremental optimization, the optimized band boundary regression model is evaluated to verify its performance on new data. If the model's performance meets the expected standards, it is adopted as the new band boundary regression model for subsequent band boundary locking template construction and real-time band switching adjustments. Through this incremental optimization mechanism, the band boundary regression model can continuously learn and improve in practical applications, ensuring its performance is continuously enhanced during long-term operation, and better able to cope with changes in the communication environment and new band switching requirements.

[0043] Furthermore, when constructing the band boundary locking template based on the band boundary regression model, the band boundary locking template construction module 20 is also used to perform the following steps:

[0044] P23-1: Cluster the band signal transmission environment information of the first group of historical band switching data to obtain multiple representative transmission environment information. Obtain the preferred band boundaries corresponding to the multiple representative transmission environment information according to the first interval regression model, and construct the first band boundary locking template; P23-2: Cluster the band signal transmission environment information of the second group of historical band switching data to obtain multiple representative transmission environment information. Obtain the preferred band boundaries corresponding to the multiple representative transmission environment information according to the second interval regression model, and construct the second band boundary locking template; P23-3: Construct the band boundary locking template according to the first band boundary locking template and the second band boundary locking template.

[0045] Optionally, in the band boundary locking template construction module 20, the process of constructing the band boundary locking template can be further refined. By further performing detailed cluster analysis on historical data, the accuracy and adaptability of the template can be improved.

[0046] First, the first set of historical band switching data (data from C-band to L-band) is clustered to identify band signal transmission environment information. Similar transmission environment information is grouped together to obtain multiple representative transmission environment information sets. These representative transmission environment information sets can cover band switching under different conditions, providing diverse reference points for subsequent band boundary optimization.

[0047] Next, using the first interval regression model, the corresponding preferred band boundaries are calculated for these representative transmission environment information. The first interval regression model is specifically designed for C-band to L-band switching, thus accurately calculating the most suitable preferred band boundaries for different transmission environments. These preferred band boundaries are integrated into a first band boundary locking template, which can be used to guide band boundary adjustments during C-band to L-band switching.

[0048] Similarly, the second set of historical band switching data is clustered to obtain multiple representative transmission environment information. Then, using a second interval regression model, the corresponding preferred band boundaries are obtained for these representative transmission environment information. Based on these preferred band boundaries, a second band boundary locking template is constructed to guide the band boundary adjustment during L-band to C-band switching.

[0049] Finally, the first and second band boundary locking templates are integrated to construct a complete band boundary locking template. This final template will provide a set of band boundary settings suitable for different band switching conditions, taking into account the switching requirements from C-band to L-band and from L-band to C-band. This template not only considers historical data and regression analysis results but also optimizes band boundary values ​​according to different transmission environments, ensuring that the system maintains high performance in complex real-world application environments.

[0050] The real-time band switching data monitoring module 30 is used to determine whether the 400G coherent optical module receives a band switching command. If the 400G coherent optical module receives a band switching command, it acquires the monitored real-time band switching data.

[0051] It should be understood that the task of the real-time band switching data monitoring module 30 of this application is to monitor in real time whether the 400G coherent optical module has received a band switching command, and to promptly acquire relevant real-time band switching data upon receiving the command. To achieve this goal, the real-time band switching data monitoring module 30 first needs to effectively determine whether a band switching command has been received. These commands are typically issued by the system's control center or other modules to notify the 400G coherent optical module to switch to a specified band. The band switching command needs to contain explicit band switching requirements, such as switching from C-band to L-band, or vice versa.

[0052] Upon receiving a band switching command, the real-time band switching data monitoring module 30 activates and begins monitoring real-time band data related to the current band switching. This involves acquiring information about the band involved in the switching command, including signal reception quality, the transmission environment of the band signal, and signal reception accuracy. This data allows for a comprehensive understanding of the band's performance after the switch, enabling the evaluation of key performance indicators such as signal strength, noise interference, and bit error rate, ensuring that the signal quality after the band switch meets expected requirements.

[0053] In addition, the real-time band switching data monitoring module 30 also records the transmission environment information of the band signal, including environmental influences that may occur during transmission, such as temperature changes, humidity fluctuations, and other factors that may interfere with the signal. Continuous monitoring of this environmental information allows for the evaluation of band switching performance under different environments, thus providing a basis for subsequent band adjustments. Simultaneously, it is necessary to monitor the accuracy of band signal reception, including parameters such as wavelength attenuation slope, filter loss gain, and signal bit error rate. Real-time monitoring of these parameters helps the system evaluate signal quality during band switching, ensuring the reliability of the band switching process.

[0054] During band switching, the real-time band switching data monitoring module 30 can continuously update and provide the signal status of the current band, ensuring that other modules can adjust the band boundaries according to the latest data, avoiding band lock-up, and ensuring that the 400G coherent optical module maintains stable signal transmission during band switching.

[0055] The band boundary adjustment module 40 is used to analyze the real-time band switching data using the constructed band boundary locking template, obtain the first band boundary corresponding to the band switching command, and adjust the band boundary of the tunable laser in the 400G coherent optical module based on the first band boundary.

[0056] Furthermore, when the band boundary adjustment module 40 analyzes the real-time band switching data using the constructed band boundary locking template, it is also used to perform the following steps:

[0057] P41: Extract the band signal transmission environment information from the real-time band switching data; P42: Extract the band signal transmission environment information template of the band boundary locking template, and match the band signal transmission environment information based on the band signal transmission environment information template to obtain the matched band boundary; P43: Output the matched band boundary as the first band boundary corresponding to the band switching command.

[0058] Optionally, the main task of the band boundary adjustment module 40 in this application is to analyze and adjust the band boundary based on the constructed band boundary locking template and real-time band switching data, thereby ensuring that the 400G coherent optical module can accurately adjust the band setting of the laser during band switching, so as to improve system stability and signal quality.

[0059] When performing band boundary adjustments, the band boundary adjustment module 40 first extracts band signal transmission environment information from real-time band switching data, including the current band transmission conditions such as temperature, humidity, distance, and other factors that may affect signal quality. These environmental factors have a significant impact on signal quality and stability. By extracting this information, the band boundary adjustment module 40 can understand the specific environmental conditions of the current band switching.

[0060] Next, the band signal transmission environment information template is extracted from the band boundary locking template. This template is constructed based on historical data and an incrementally optimized band boundary regression model, and includes various representative transmission environment information and their corresponding preferred band boundaries. The band boundary adjustment module 40 can match the band signal transmission environment information in the real-time band switching data with the information in the band boundary locking template, and find the closest match through algorithm analysis. For example, multiple parameters can be comprehensively evaluated to obtain the matching band boundary, such as by calculating the similarity between the real-time environment information and the environment information in the template, or by predicting the optimal band boundary under the current environment through a regression model, to obtain a specific band boundary, i.e., the matching band boundary.

[0061] Finally, the obtained matched band boundary is output as the first band boundary corresponding to the band switching command, and this band boundary is precisely set by adjusting the tunable laser in the 400G coherent optical module. This first band boundary is the result of optimization based on the current transmission environment and historical data, which can effectively guide the tunable laser in the 400G coherent optical module to make precise band boundary adjustments. This allows the 400G coherent optical module to automatically adapt to different environmental conditions and band switching requirements, effectively avoiding loss of lock-up during band switching.

[0062] Furthermore, the band boundary adjustment module 40 is also used to perform the following steps:

[0063] P44: Match the band signal transmission environment information based on the band signal transmission environment information template. If the matching fails, call the first interval regression model or the first interval regression model again to make a prediction and output the predicted band boundary; P45: Output the predicted band boundary as the first band boundary corresponding to the band switching command.

[0064] Specifically, during the band boundary adjustment process, the band boundary adjustment module 40 not only relies on the band signal transmission environment information template for matching, but also incorporates an emergency mechanism to deal with matching failures. This ensures that even when the environment information template cannot be successfully matched with real-time data in certain situations, the system can still predict the appropriate band boundary through a regression model, thereby avoiding problems such as band lockout or signal instability.

[0065] During the matching process, the system first attempts to match the band signal transmission environment information in the real-time band switching data based on the pre-built band signal transmission environment information template. When the system successfully matches the environment information template, a suitable matching band boundary can be directly generated. However, if the matching based on the band signal transmission environment information template fails during the matching process, i.e., no template item matching the current transmission environment information can be found, an emergency mechanism is triggered. In this case, the band boundary adjustment module 40 will re-call either the first interval regression model or the second interval regression model for prediction. Which interval regression model is called depends on the type of band switching instruction. For example, if the band switching instruction is from C-band to L-band, the first interval regression model is called; if it is from L-band to C-band, the second interval regression model is called. Through the prediction of the regression model, a predicted band boundary is output, which is derived based on the current transmission environment information and the prediction results of the regression model.

[0066] Next, this predicted band boundary is used as the first band boundary output corresponding to the current band switching command. This predicted band boundary is derived through regression model analysis, taking into account current transmission environment information and patterns in historical data. Therefore, it can provide a reasonable band boundary adjustment suggestion for the tunable laser in the 400G coherent optical module. Even in the event of unsuccessful matching, the band boundary adjustment module 40 can ensure the stability and reliability of the band switching process through the predictive capability of the regression model. Ultimately, this predicted band boundary will adjust the tunable laser in the 400G coherent optical module to ensure that the laser's band boundary setting accurately meets the current band switching requirements, thereby guaranteeing the stability and quality of signal transmission.

[0067] In summary, the embodiments of this application have at least the following technical effects:

[0068] This application improves the stability of band switching and reduces band lock-out by intelligently adjusting band boundaries, ensuring signal quality and system stability during band switching. By dynamically adjusting band boundaries using historical data and real-time monitoring, it enhances the system's adaptability, enabling it to optimize transmission performance according to different band switching requirements and environmental changes. By precisely adjusting band boundaries, it improves the efficiency and reliability of 400G coherent optical modules in multi-band switching environments, while optimizing system resource utilization and avoiding unnecessary resource waste.

[0069] It achieves the technical effect of accurately responding to dynamic changes during band switching through intelligent monitoring and dynamic adjustment mechanisms, effectively reducing band lock-up and improving communication stability.

[0070] Example 2, based on the same inventive concept as the intelligent monitoring system for 400G coherent optical modules in the foregoing examples, such as... Figure 2 As shown, this application provides an intelligent monitoring method for 400G coherent optical modules. The system and method embodiments in this application are based on the same inventive concept. The method includes:

[0071] The system loads historical band switching data of the 400G coherent optical module within a preset period. This historical band switching data includes historical band received signals, band switching type labels, band signal transmission environment information, and accuracy labels characterizing the band signal reception accuracy. The band switching type labels include at least two switching types: C-band to L-band and L-band to C-band. A band boundary locking template is constructed based on the historical band switching data. It is determined whether the 400G coherent optical module receives a band switching command. If so, real-time band switching data is acquired. The constructed band boundary locking template is used to analyze the real-time band switching data to obtain the first band boundary corresponding to the band switching command. The band boundary of the tunable laser in the 400G coherent optical module is adjusted based on the first band boundary.

[0072] Furthermore, a band boundary locking template is constructed based on the historical band switching data, the method comprising:

[0073] Collect the first set of historical band switching data from C-band to L-band, and the second set of historical band switching data from L-band to C-band; use the historical band received signal and band signal transmission environment information corresponding to the first and second sets of historical band switching data as input data, use the band boundary as the adjustable variable space, and use the accuracy labels corresponding to the first and second sets of historical band switching data as supervision labels to perform regression analysis to obtain the band boundary regression model; construct a band boundary locking template based on the band boundary regression model.

[0074] Furthermore, the band boundary regression model includes a first interval regression model for switching from C-band to L-band, and a second interval regression model for switching from L-band to C-band; the band switching type of the band switching command is decomposed, and the real-time band switching data is analyzed according to the band switching type using the first interval regression model or the second interval regression model.

[0075] Furthermore, the method also includes:

[0076] A generator is trained based on the band boundary regression model. The generator is used to obtain incremental band switching data from the historical band switching data. The band boundary regression model is incrementally optimized based on the incremental band switching data, and the optimized band boundary regression model is output.

[0077] Furthermore, a band boundary locking template is constructed based on the band boundary regression model, the method comprising:

[0078] Clustering of band signal transmission environment information is performed on the first group of historical band switching data to obtain multiple representative transmission environment information. Preferred band boundaries corresponding to these multiple representative transmission environment information are obtained according to a first interval regression model, and a first band boundary locking template is constructed. Clustering of band signal transmission environment information is performed on the second group of historical band switching data to obtain multiple representative transmission environment information. Preferred band boundaries corresponding to these multiple representative transmission environment information are obtained according to a second interval regression model, and a second band boundary locking template is constructed. A band boundary locking template is constructed based on the first and second band boundary locking templates.

[0079] Furthermore, the real-time band switching data is analyzed using the constructed band boundary locking template, the method including:

[0080] Extract the band signal transmission environment information from the real-time band switching data; extract the band signal transmission environment information template of the band boundary locking template; match the band signal transmission environment information based on the band signal transmission environment information template to obtain the matched band boundary; output the matched band boundary as the first band boundary corresponding to the band switching command.

[0081] Furthermore, the band signal transmission environment information is matched based on the band signal transmission environment information template. If the matching fails, the first interval regression model is called again to make a prediction and the predicted band boundary is output. The predicted band boundary is output as the first band boundary corresponding to the band switching command.

[0082] Furthermore, the 400G coherent optical module also includes an extension module, which extends multiple bands and updates multiple band switching type labels according to the multiple bands.

[0083] Furthermore, methods for obtaining accuracy labels characterizing the reception accuracy of band signals include:

[0084] The accuracy of historical band received signals is evaluated, including wavelength attenuation slope, filter loss gain, and signal bit error rate. Weights are calculated for the wavelength attenuation slope, filter loss gain, and signal bit error rate to obtain an accuracy label representing the accuracy of the band signal received by the historical band received signals.

[0085] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0086] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0087] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. An intelligent monitoring system for 400G coherent optical modules, characterized in that, The system includes: The historical band switching data acquisition module is used to load the historical band switching data of the 400G coherent optical module within a preset period. The historical band switching data includes historical band received signals, band switching type labels, band signal transmission environment information, and accuracy labels characterizing the accuracy of band signal reception. The band switching type labels include at least the switching type from C-band to L-band and the switching type from L-band to C-band. A band boundary locking template construction module is used to construct a band boundary locking template based on the historical band switching data. The real-time band switching data monitoring module is used to determine whether the 400G coherent optical module receives a band switching command. If the 400G coherent optical module receives a band switching command, it acquires the monitored real-time band switching data. The band boundary adjustment module is used to analyze the real-time band switching data using the constructed band boundary locking template, obtain the first band boundary corresponding to the band switching command, and adjust the band boundary of the tunable laser in the 400G coherent optical module based on the first band boundary. The band boundary locking template construction module is also used for: Collect the first set of historical band switching data from C-band to L-band, and the second set of historical band switching data from L-band to C-band; Using the historical band received signal and band signal transmission environment information corresponding to the first set of historical band switching data and the second set of historical band switching data as input data, and the band boundary as the adjustable variable space, the accuracy labels corresponding to the first set of historical band switching data and the second set of historical band switching data are used as supervision labels for regression analysis to obtain the band boundary regression model. A band boundary locking template is constructed based on the band boundary regression model. In the band boundary locking template construction module: The band boundary regression model includes a first interval regression model for switching from C-band to L-band, and a second interval regression model for switching from L-band to C-band. The band switching type of the band switching command is decomposed, and the real-time band switching data is analyzed according to the band switching type using the first interval regression model or the second interval regression model; After obtaining the band boundary regression model, the band boundary locking template construction module is also used for: A generator is trained based on the band boundary regression model, and the generator is used to obtain incremental band switching data from the historical band switching data. Based on the incremental band switching data, the band boundary regression model is incrementally optimized, and the optimized band boundary regression model is output. When constructing a band boundary locking template based on the band boundary regression model, the band boundary locking template construction module is also used for: Cluster the first set of historical band switching data for band signal transmission environment information to obtain multiple representative transmission environment information. Obtain the preferred band boundaries corresponding to the multiple representative transmission environment information according to the first interval regression model, and construct the first band boundary locking template. Cluster the band signal transmission environment information of the second group of historical band switching data to obtain multiple representative transmission environment information. According to the second interval regression model, obtain the preferred band boundary corresponding to the multiple representative transmission environment information and construct the second band boundary locking template. A band boundary locking template is constructed based on the first band boundary locking template and the second band boundary locking template.

2. The intelligent monitoring system for a 400G coherent optical module as described in claim 1, characterized in that, When the band boundary adjustment module analyzes the real-time band switching data using the constructed band boundary locking template, it is also used for: Extract the band signal transmission environment information from the real-time band switching data; Extract the band signal transmission environment information template of the band boundary locking template, and match the band signal transmission environment information based on the band signal transmission environment information template to obtain the matched band boundary; The matching band boundary is output as the first band boundary corresponding to the band switching command.

3. The intelligent monitoring system for a 400G coherent optical module as described in claim 2, characterized in that, The band boundary adjustment module is also used for: The band signal transmission environment information is matched based on the band signal transmission environment information template. If the matching fails, the first interval regression model is called again to make a prediction and the predicted band boundary is output. The predicted band boundary is output as the first band boundary corresponding to the band switching command.

4. The intelligent monitoring system for a 400G coherent optical module as described in claim 1, characterized in that, The 400G coherent optical module also includes an extension module, which extends multiple bands and updates multiple band switching type labels based on the multiple bands.

5. The intelligent monitoring system for a 400G coherent optical module as described in claim 1, characterized in that, When acquiring the accuracy tag that characterizes the accuracy of band signal reception, the historical band switching data acquisition module is also used for: The band accuracy of historical band received signals is evaluated, including wavelength attenuation slope, filter loss gain, and signal bit error rate. The wavelength attenuation slope, filter loss gain, and signal error rate are weighted and calculated to obtain the accuracy label representing the signal reception accuracy of the historical band received signal.

6. An intelligent monitoring method for 400G coherent optical modules, characterized in that, The method for implementing the intelligent monitoring system for a 400G coherent optical module according to any one of claims 1 to 5 includes: Load the historical band switching data of the 400G coherent optical module within a preset period. The historical band switching data includes historical band received signals, band switching type labels, band signal transmission environment information, and accuracy labels characterizing the accuracy of band signal reception. The band switching type labels include at least the switching type from C-band to L-band and the switching type from L-band to C-band. A band boundary locking template is constructed based on the historical band switching data; Determine whether the 400G coherent optical module receives a band switching command. If the 400G coherent optical module receives a band switching command, obtain the real-time band switching data obtained from monitoring. The real-time band switching data is analyzed using the constructed band boundary locking template to obtain the first band boundary corresponding to the band switching command, and the band boundary of the tunable laser in the 400G coherent optical module is adjusted based on the first band boundary.

Images