Multi-signal fusion distributed optical transmission method and system

Abstract

The invention provides a multi-signal fusion distributed optical transmission method and system. The method comprises the following steps: constructing a distributed node cluster comprising edge access nodes, regional collaborative nodes and core forwarding nodes; the edge access node marks phase stability requirement levels for multiple types of signals according to signal types and scenes and packs the signals into a logic transmission unit; the regional collaborative node predicts the load rate and the phase stability level of each link in a future time period, and distributes an optimal transmission link for the regional collaborative node in combination with the level label of the logic unit; and the core forwarding node screens an optimal path for cross-regional transmission based on multi-objective optimization. According to the invention, fine guarantee of transmission quality of multiple types of signals and efficient utilization of network resources can be realized, and the overall phase stability and reliability of the optical transmission system when bearing the fusion service are effectively improved.

Description

Technical Field

[0001] This application relates to the field of optical communication technology, and more specifically, to a distributed optical transmission method and system that integrates multiple signals. Background Technology

[0002] In current optical transmission technology applications, the demand for synchronous transmission of multiple types of service signals (such as control commands and multi-channel video surveillance) is becoming increasingly prominent. However, existing methods typically employ static or coarse-grained resource allocation strategies, making it difficult to dynamically adapt to the varying phase stability requirements of different signals. Firstly, existing technologies usually use coarse-grained scheduling based on priority or bandwidth, failing to accurately guarantee the critical indicator of phase stability. This results in the transmission quality of high-precision synchronous services (such as remote precision control and distributed sensing) not meeting requirements. Furthermore, existing routing mechanisms are mostly based on real-time or historical states, lacking the ability to predict future network load and performance. When the network experiences sudden load increases or performance fluctuations, the phase stability of the transmission path can drop sharply, affecting the normal operation of critical services. Simultaneously, existing technologies suffer from insufficient cross-regional coordination capabilities. Path selection often only considers hop count or bandwidth, ignoring inter-regional load balancing and overall phase synchronization deviation, potentially leading to local overload or global synchronization performance degradation. Therefore, there is an urgent need in this field for an optical transmission method that can intelligently predict network status and dynamically and finely allocate resources according to the differentiated needs of multiple signals (especially phase stability requirements) in order to achieve forward-looking assurance of the quality of service for multiple services and efficient utilization of network resources. Summary of the Invention

[0003] The purpose of this application is to provide a distributed optical transmission method and system for multi-signal fusion. By constructing a distributed architecture including edge access nodes, regional collaborative nodes, and core forwarding nodes, firstly, at the edge, differentiated phase stability requirement levels are assigned to multi-source signals based on signal type and scenario, and then encapsulated. Subsequently, regional collaborative nodes predict future link load and phase stability based on historical data, achieving forward-looking link allocation matching the signal level. Finally, the core node completes cross-regional path selection through multi-objective optimization. This application achieves refined assurance of transmission quality for multiple signal types and efficient utilization of network resources, effectively improving the overall phase stability, reliability, and intelligence level of the optical transmission system when carrying converged services.

[0004] This application also provides a distributed optical transmission method with multi-signal fusion, comprising the following steps:

[0005] Construct a distributed node cluster, including edge access nodes, regional collaboration nodes, and core forwarding nodes;

[0006] Edge access nodes fuse and group the collected signals of various types, generate logical transmission units with phase stability requirement level labels, and transmit them to regional collaborative nodes.

[0007] Regional collaborative nodes collect historical data of each link within their region and predict the load rate of each link for a preset time period in the future, thereby obtaining the predicted load rate value for each link.

[0008] Regional collaborative nodes predict the phase stability level of each link in a future preset time period based on historical data, and obtain the corresponding phase stability prediction level of each link.

[0009] Regional collaborative nodes allocate links and transmit data to each logical transmission unit based on phase stability requirement level, load rate prediction value, and phase stability prediction level.

[0010] The core forwarding node selects cross-regional transmission paths based on the load status and signal transmission requirements of each region.

[0011] Optionally, in the distributed optical transmission method for multi-signal fusion described in this application, the edge access node fuses and groups the collected multi-type signals to generate logical transmission units with phase stability requirement level labels and transmits them to the regional collaborative node, including:

[0012] Edge access nodes collect multiple types of signals and their corresponding signal type labels and scene labels;

[0013] Input the scene label and signal type label into the pre-established three-dimensional mapping table of application scene-signal type-phase stability level to obtain the phase stability requirement level corresponding to each type of signal;

[0014] Multiple types of signals are grouped according to signal type, scene label, and phase stability requirement level. Signals in the same group are packaged into a logical transmission unit and a phase stability requirement level label is added.

[0015] After wavelength division multiplexing of all logical transmission units, they are transmitted to the regional collaborative node along with the phase stability requirement level label.

[0016] Optionally, in the distributed optical transmission method for multi-signal fusion described in this application, the regional collaborative node collects historical data of each link within its region and predicts the load rate of each link for a preset future time period to obtain the predicted load rate value for each link, including:

[0017] Regional collaborative nodes collect historical data from each link in real time, including load time series data and phase stability time series data;

[0018] Load timing data includes link bandwidth utilization, packet throughput, and queue latency.

[0019] Phase stability time series data includes phase jitter, phase drift, and synchronization error;

[0020] Based on the load time series data of each link, an LSTM model is trained to obtain the load prediction model corresponding to each link.

[0021] The load time series data within the current preset time window is input into the load prediction model for processing to obtain the load rate prediction value of each link in the future preset time period.

[0022] Optionally, in the distributed optical transmission method for multi-signal fusion described in this application, the regional collaborative node predicts the phase stability level of each link for a future preset time period based on historical data, and obtains the predicted phase stability level corresponding to each link, including:

[0023] After normalizing the phase jitter value, phase drift amount, and synchronization error, a weighted sum is calculated, and the interval in which the weighted sum is located is mapped to the corresponding phase stability level.

[0024] Generate a training dataset by combining link load time-series data and the corresponding set of phase stability levels;

[0025] The pre-defined random forest regression model is trained under supervision based on the training dataset to obtain the load phase correlation model.

[0026] The load time series data within the current preset time window is input into the load phase correlation model for processing to obtain the predicted phase stability level of each link in the future preset time period.

[0027] Optionally, in the distributed optical transmission method of multi-signal fusion described in this application, the regional cooperative node allocates links to each logical transmission unit and transmits data based on the phase stability requirement level, the load rate prediction value, and the phase stability prediction level, including:

[0028] The comprehensive score of each link is obtained by processing the real-time load rate, predicted load rate, real-time phase stability level, and predicted phase stability level of each link.

[0029] For each logical transmission unit, select the link with the highest comprehensive link score that matches its phase stability requirement level as the final transmission path.

[0030] Optionally, in the multi-signal fusion distributed optical transmission method described in this application, the core forwarding node selects cross-regional transmission paths based on the load status and signal transmission requirements of each region, including:

[0031] The core forwarding node acquires cross-regional signal transmission demand parameters, as well as the regional load rate and regional phase synchronization deviation of each region in real time.

[0032] The cross-regional signal transmission requirement parameters include signal scenario priority, phase stability requirement level, and delay requirement threshold.

[0033] A multi-objective optimization model is constructed with the optimization objectives of minimizing the regional load rate difference, minimizing the transmission delay time, and minimizing the regional phase synchronization deviation, and with the constraints of matching the phase stability requirement level and the delay time not exceeding the delay requirement threshold.

[0034] The multi-objective optimization model is solved using a pre-defined multi-objective optimization algorithm to obtain the Pareto optimal path set;

[0035] The final transmission path is selected from the Pareto optimal path set based on the phase stability requirement level and signal scenario priority.

[0036] Optionally, the distributed optical transmission method for multi-signal fusion described in this application further includes:

[0037] If the predicted load rate of all links in the region is greater than the preset load rate threshold or the predicted phase stability level is lower than the required phase stability level;

[0038] Then, links with load rates less than the preset load rate threshold, phase stability levels matching the required phase stability levels, and predicted phase stability levels higher than or equal to the required phase stability levels are selected as candidate links.

[0039] Secondly, this application provides a distributed optical transmission system with multi-signal fusion, including:

[0040] Edge access node module, including:

[0041] Multi-type signal acquisition unit: used to acquire multiple types of signals and their corresponding signal type labels and scene labels;

[0042] Phase stability level mapping unit: Stores a three-dimensional mapping table of application scenario-signal type-phase stability level, used to determine the phase stability requirement level corresponding to each type of signal;

[0043] Signal grouping and packaging unit: Groups multiple types of signals according to signal type, scene label and phase stability requirement level, and packages signals in the same group into logical transmission units;

[0044] Tag Addition Unit: Add a phase stability requirement level tag to each logical transmission unit;

[0045] Wavelength division multiplexing processing unit: performs wavelength division multiplexing processing on all logical transmission units and transmits them to the regional cooperation node;

[0046] The regional collaborative node module includes:

[0047] Historical data acquisition unit: collects historical data of each link in real time, including load time series data and phase stability time series data;

[0048] Load prediction unit: The load prediction model is trained based on the LSTM model to obtain the predicted load rate of each link;

[0049] Phase stability prediction unit: The load phase correlation model is trained based on the random forest regression model to obtain the phase stability prediction level of each link;

[0050] Link allocation decision unit: Calculates the comprehensive link score based on the phase stability requirement level, load rate prediction value, and phase stability prediction level, and allocates the optimal transmission link to the logical transmission unit;

[0051] The core forwarding node module includes:

[0052] Cross-regional parameter acquisition unit: Real-time acquisition of cross-regional signal transmission demand parameters, as well as the regional load rate and regional phase synchronization deviation of each region;

[0053] Multi-objective optimization modeling unit: Constructs a multi-objective optimization model with the optimization objectives of minimizing the regional load rate difference, minimizing the transmission delay time, and minimizing the regional phase synchronization deviation;

[0054] Path finding unit: uses multi-objective optimization algorithms to find the Pareto optimal path set;

[0055] Final path selection unit: Selects the final transmission path based on the phase stability requirement level and signal scenario priority;

[0056] The link backup management module includes:

[0057] Anomaly detection unit: Monitors the predicted load rate and phase stability level of all links within the monitoring area;

[0058] Alternate link selection unit: When an anomaly is detected, an alternative link that meets the preset conditions is selected.

[0059] Optionally, in the multi-signal fusion distributed optical transmission system described in this application, the link allocation decision unit is used for:

[0060] The comprehensive score of each link is calculated based on its real-time load rate, predicted load rate, real-time phase stability level, and predicted phase stability level.

[0061] For each logical transmission unit, select the link with the highest comprehensive link score that matches its phase stability requirement level as the final transmission path.

[0062] Optionally, in the multi-signal fusion distributed optical transmission system described in this application, the multi-objective optimization modeling unit is used for:

[0063] With the optimization objectives of minimizing the regional load rate difference, minimizing the transmission delay time, and minimizing the regional phase synchronization deviation, and with the constraints of matching the phase stability requirement level and the delay time not exceeding the delay requirement threshold, a multi-objective optimization model is constructed.

[0064] As described above, the distributed optical transmission method and system for multi-signal fusion provided in this application constructs a distributed architecture including edge access nodes, regional collaborative nodes, and core forwarding nodes. First, at the edge, differentiated phase stability requirement levels are assigned to multi-source signals based on signal type and scenario, and then encapsulated. Subsequently, regional collaborative nodes predict future link load and phase stability based on historical data, achieving forward-looking link allocation matching the signal level. Finally, the core node completes cross-regional path selection through multi-objective optimization. This application achieves refined assurance of transmission quality for multiple signal types and efficient utilization of network resources, effectively improving the overall phase stability, reliability, and intelligence level of the optical transmission system when carrying converged services.

[0065] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0066] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0067] Figure 1 A flowchart illustrating the distributed optical transmission method for multi-signal fusion provided in this application embodiment;

[0068] Figure 2 A flowchart illustrating the fusion and grouping of multiple types of signals in a distributed optical transmission method for multi-signal fusion provided in this application embodiment;

[0069] Figure 3A flowchart illustrating the process of obtaining the load rate prediction value for each link in the multi-signal fusion distributed optical transmission method provided in this application embodiment;

[0070] Figure 4 This is an overall schematic diagram of a distributed optical transmission system with multi-signal fusion provided in an embodiment of this application. Detailed Implementation

[0071] 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 the embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0072] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0073] Please refer to Figure 1 , Figure 1 This is a flowchart of a multi-signal fusion distributed optical transmission method according to some embodiments of this application. This multi-signal fusion distributed optical transmission method is used in terminal devices, such as computers and mobile terminals. The multi-signal fusion distributed optical transmission method includes the following steps:

[0074] S11. Construct a distributed node cluster, including edge access nodes, regional collaboration nodes, and core forwarding nodes;

[0075] S12. The edge access node fuses and groups the collected multi-type signals, generates logical transmission units with phase stability requirement level labels, and transmits them to the regional collaborative node.

[0076] S13. The regional collaborative node collects historical data of each link in its region and predicts the load rate of each link in a future preset time period to obtain the predicted load rate value of each link.

[0077] S14. The regional collaborative node predicts the phase stability level of each link in a future preset time period based on historical data, and obtains the predicted phase stability level of each link.

[0078] S15. The regional collaborative node allocates links to each logical transmission unit and transmits data based on the phase stability requirement level, the load rate prediction value, and the phase stability prediction level.

[0079] S16. The core forwarding node selects cross-regional transmission paths based on the load status and signal transmission requirements of each region.

[0080] It should be noted that this application achieves precise matching between transmission demand and network supply capacity by marking signal phase stability requirement levels, ensuring service quality for phase-sensitive services. By introducing machine learning models such as LSTM and random forests to predict future link load and phase stability, link allocation decisions are made proactively, avoiding potentially congested or performance-degraded links, thus improving transmission stability and reliability. Furthermore, in cross-regional path selection, a multi-objective optimization model is employed, comprehensively considering regional load balancing, transmission delay, and phase synchronization deviation, avoiding bottlenecks caused by unilateral optimization and achieving overall network performance optimization. Additionally, by setting up a link backup management mechanism, when it is predicted that the transmission demand in the current region cannot be met, alternative links can be intelligently selected, enhancing the system's robustness and fault tolerance.

[0081] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating the multi-signal fusion distributed optical transmission method in some embodiments of this application, which involves fusing and grouping collected multi-type signals. According to an embodiment of the present invention, the edge access node fuses and groups the collected multi-type signals, generates logical transmission units with phase stability requirement level labels, and transmits them to the regional coordination node, including:

[0082] S21. Edge access nodes collect multiple types of signals and their corresponding signal type labels and scene labels;

[0083] S22. Input the scene label and signal type label into the pre-established three-dimensional mapping table of application scene-signal type-phase stability level to obtain the phase stability requirement level corresponding to each type of signal.

[0084] S23. Group multiple types of signals according to signal type, scene label and phase stability requirement level, package signals in the same group into a logical transmission unit and add a phase stability requirement level label;

[0085] S24. After performing wavelength division multiplexing on all logical transmission units, transmit them along with the phase stability requirement level label to the regional collaborative node.

[0086] It should be noted that signal type and scene label combinations are mapped to a preset grouping strategy table. This table defines the groups to which different signal types and scene label combinations belong. Simultaneously, considering the phase sensitivity requirement level, signals with the same phase sensitivity requirement level are grouped together, thus forming multiple logical transmission units. In this embodiment, the phase stability requirement level is divided into high, medium, and normal levels. For example, control command signals (such as equipment start / stop and parameter adjustment commands) are at the high level, operating status sensing signals are at the medium level, and background service data is at the normal level. For instance, the phase stability requirement level corresponding to the multi-vehicle collision avoidance interaction signal in a vehicle-road cooperative scenario is high, requiring stable phase to ensure synchronization of multi-vehicle position signals and accurate collision avoidance decisions.

[0087] Please refer to Figure 3 , Figure 3 This is a flowchart illustrating the process of obtaining load rate prediction values ​​for each link in a multi-signal fusion distributed optical transmission method according to some embodiments of this application. According to an embodiment of the present invention, the regional collaborative node collects historical data of each link within its region and predicts the load rate of each link for a preset future time period to obtain the load rate prediction value for each link, including:

[0088] S31. Regional collaborative nodes collect historical data of each link in real time, including load time series data and phase stability time series data;

[0089] S32. Load timing data includes link bandwidth utilization, packet throughput, and queue latency.

[0090] S33. Phase stability timing data includes phase jitter value, phase drift amount, and synchronization error;

[0091] S34. Based on the load time series data of each link, use the LSTM model to train and obtain the load prediction model corresponding to each link.

[0092] S35. Input the load time sequence data within the current preset time window into the load prediction model for processing to obtain the load rate prediction value of each link in the future preset time period.

[0093] It should be noted that using the LSTM (Long Short-Term Memory) model to train and predict load time-series data including bandwidth utilization, throughput, and queue latency can effectively capture the long-term dependencies and periodic patterns of load changes. This allows the system to predict the busy level of each link in a specific future time period, thereby providing accurate data support for forward-looking link allocation, effectively avoiding transmission delays and packet loss caused by link congestion, and optimizing network resource utilization.

[0094] According to an embodiment of the present invention, the regional collaborative node predicts the phase stability level of each link in a future preset time period based on historical data, and obtains the predicted phase stability level of each link, including:

[0095] After normalizing the phase jitter value, phase drift amount, and synchronization error, a weighted sum is calculated, and the interval in which the weighted sum is located is mapped to the corresponding phase stability level.

[0096] Generate a training dataset by combining link load time-series data and the corresponding set of phase stability levels;

[0097] The pre-defined random forest regression model is trained under supervision based on the training dataset to obtain the load phase correlation model.

[0098] The load time series data within the current preset time window is input into the load phase correlation model for processing to obtain the predicted phase stability level of each link in the future preset time period.

[0099] It's worth noting that by fusing multiple parameters such as phase jitter and drift, and using a random forest regression model to establish their correlation with load data, a leap from "load prediction" to "phase stability prediction" is achieved. This method not only predicts link availability but also predicts future changes in its "quality" level, enabling the system to proactively select and reserve high-quality links for services with high phase stability requirements, thus achieving an upgrade from "connectivity assurance" to "quality of service assurance."

[0100] According to an embodiment of the present invention, the regional collaborative node allocates links and transmits data to each logical transmission unit based on the phase stability requirement level, the load rate prediction value, and the phase stability prediction level, including:

[0101] The comprehensive score of each link is obtained by processing the real-time load rate, predicted load rate, real-time phase stability level, and predicted phase stability level of each link.

[0102] For each logical transmission unit, select the link with the highest comprehensive link score that matches its phase stability requirement level as the final transmission path.

[0103] It should be noted that the calculation process of the link comprehensive score is as follows: The real-time load rate and the predicted load rate are respectively input into the pre-established load rate-link score mapping table to obtain the corresponding real-time load rate score and the predicted load rate score. The real-time phase stability level and the predicted phase stability level are respectively input into the pre-established phase stability-link score mapping table to obtain the real-time phase stability score and the predicted phase stability score. The weighted sum of the real-time phase stability score and the predicted phase stability score is divided by the weighted sum of the real-time load rate score and the predicted load rate score to obtain the link comprehensive score.

[0104] According to an embodiment of the present invention, the core forwarding node filters cross-regional transmission paths based on the load status and signal transmission requirements of each region, including:

[0105] The core forwarding node acquires cross-regional signal transmission demand parameters, as well as the regional load rate and regional phase synchronization deviation of each region in real time.

[0106] The cross-regional signal transmission requirement parameters include signal scenario priority, phase stability requirement level, and delay requirement threshold.

[0107] A multi-objective optimization model is constructed with the optimization objectives of minimizing the regional load rate difference, minimizing the transmission delay time, and minimizing the regional phase synchronization deviation, and with the constraints of matching the phase stability requirement level and the delay time not exceeding the delay requirement threshold.

[0108] The multi-objective optimization model is solved using a pre-defined multi-objective optimization algorithm to obtain the Pareto optimal path set;

[0109] The final transmission path is selected from the Pareto optimal path set based on the phase stability requirement level and signal scenario priority.

[0110] It should be noted that, in this embodiment of the invention, the multi-objective optimization algorithm is the NSGA-II algorithm. For example: if the signal is a control command (scene priority: very high), it is most afraid of phase loss, so the path with the smallest "phase synchronization deviation" is selected in the Pareto set; if the signal is real-time video communication (scene priority: high), it is most afraid of stuttering, so the path with the smallest "transmission delay time" is selected in the Pareto set; if the signal is ordinary data backup (scene priority: medium), it is desirable not to occupy critical resources, so the path with the smallest "regional load rate difference" is selected in the Pareto set.

[0111] According to an embodiment of the present invention, it further includes:

[0112] If the predicted load rate of all links in the region is greater than the preset load rate threshold or the predicted phase stability level is lower than the required phase stability level;

[0113] Then, links with load rates less than the preset load rate threshold, phase stability levels matching the required phase stability levels, and predicted phase stability levels higher than or equal to the required phase stability levels are selected as candidate links.

[0114] It should be noted that by setting up a link backup management mechanism, when it is detected that all links in the region cannot meet future transmission needs (overload or substandard quality), the alternative link selection process can be automatically triggered. This mechanism provides the system with an important "escape route," enhancing its resilience and service continuity assurance capabilities in the face of local network performance degradation or sudden traffic surges, which is of great significance for the uninterrupted transmission of critical services.

[0115] Please refer to Figure 4 , Figure 4 This is an overall schematic diagram of a multi-signal fusion distributed optical transmission system in some embodiments of this application. The present invention also discloses a multi-signal fusion distributed optical transmission system, comprising:

[0116] Edge access node module, including:

[0117] Multi-type signal acquisition unit: used to acquire multiple types of signals and their corresponding signal type labels and scene labels;

[0118] Phase stability level mapping unit: Stores a three-dimensional mapping table of application scenario-signal type-phase stability level, used to determine the phase stability requirement level corresponding to each type of signal;

[0119] Signal grouping and packaging unit: Groups multiple types of signals according to signal type, scene label and phase stability requirement level, and packages signals in the same group into logical transmission units;

[0120] Tag Addition Unit: Add a phase stability requirement level tag to each logical transmission unit;

[0121] Wavelength division multiplexing processing unit: performs wavelength division multiplexing processing on all logical transmission units and transmits them to the regional cooperation node;

[0122] The regional collaborative node module includes:

[0123] Historical data acquisition unit: collects historical data of each link in real time, including load time series data and phase stability time series data;

[0124] Load prediction unit: The load prediction model is trained based on the LSTM model to obtain the predicted load rate of each link;

[0125] Phase stability prediction unit: The load phase correlation model is trained based on the random forest regression model to obtain the phase stability prediction level of each link;

[0126] Link allocation decision unit: Calculates the comprehensive link score based on the phase stability requirement level, load rate prediction value, and phase stability prediction level, and allocates the optimal transmission link to the logical transmission unit;

[0127] The core forwarding node module includes:

[0128] Cross-regional parameter acquisition unit: Real-time acquisition of cross-regional signal transmission demand parameters, as well as the regional load rate and regional phase synchronization deviation of each region;

[0129] Multi-objective optimization modeling unit: Constructs a multi-objective optimization model with the optimization objectives of minimizing the regional load rate difference, minimizing the transmission delay time, and minimizing the regional phase synchronization deviation;

[0130] Path finding unit: uses multi-objective optimization algorithms to find the Pareto optimal path set;

[0131] Final path selection unit: Selects the final transmission path based on the phase stability requirement level and signal scenario priority;

[0132] The link backup management module includes:

[0133] Anomaly detection unit: Monitors the predicted load rate and phase stability level of all links within the monitoring area;

[0134] Alternate link selection unit: When an anomaly is detected, an alternative link that meets the preset conditions is selected.

[0135] According to an embodiment of the present invention, the link allocation decision unit is used for:

[0136] The comprehensive score of each link is calculated based on its real-time load rate, predicted load rate, real-time phase stability level, and predicted phase stability level.

[0137] For each logical transmission unit, select the link with the highest comprehensive link score that matches its phase stability requirement level as the final transmission path.

[0138] According to an embodiment of the present invention, the multi-objective optimization modeling unit is used for:

[0139] With the optimization objectives of minimizing the regional load rate difference, minimizing the transmission delay time, and minimizing the regional phase synchronization deviation, and with the constraints of matching the phase stability requirement level and the delay time not exceeding the delay requirement threshold, a multi-objective optimization model is constructed.

[0140] This invention discloses a distributed optical transmission method and system for multi-signal fusion. By constructing a distributed architecture including edge access nodes, regional collaborative nodes, and core forwarding nodes, the system first labels and encapsulates differentiated phase stability requirement levels for multi-source signals at the edge based on signal type and scenario. Subsequently, regional collaborative nodes predict future link load and phase stability based on historical data, achieving forward-looking link allocation matching the signal level. Finally, the core node completes cross-regional path selection through multi-objective optimization. This application achieves refined assurance of transmission quality for multiple signal types and efficient utilization of network resources, effectively improving the overall phase stability, reliability, and intelligence level of the optical transmission system when carrying converged services.

[0141] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0142] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0143] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

Claims

1. A distributed optical transmission method with multi-signal fusion, characterized in that, Includes the following steps: Construct a distributed node cluster, including edge access nodes, regional collaboration nodes, and core forwarding nodes; Edge access nodes fuse and group the collected signals of various types, generate logical transmission units with phase stability requirement level labels, and transmit them to regional collaborative nodes. Regional collaborative nodes collect historical data of each link within their region and predict the load rate of each link for a preset time period in the future, thereby obtaining the predicted load rate value for each link. Regional collaborative nodes predict the phase stability level of each link in a future preset time period based on historical data, and obtain the corresponding phase stability prediction level of each link. Regional collaborative nodes allocate links and transmit data to each logical transmission unit based on phase stability requirement level, load rate prediction value, and phase stability prediction level. The core forwarding node selects cross-regional transmission paths based on the load status and signal transmission requirements of each region.

2. The distributed optical transmission method for multi-signal fusion according to claim 1, characterized in that, The edge access node fuses and groups the collected multi-type signals, generates logical transmission units with phase stability requirement level labels, and transmits them to the regional coordination node, including: Edge access nodes collect multiple types of signals and their corresponding signal type labels and scene labels; Input the scene label and signal type label into the pre-established three-dimensional mapping table of application scene-signal type-phase stability level to obtain the phase stability requirement level corresponding to each type of signal; Multiple types of signals are grouped according to signal type, scene label, and phase stability requirement level. Signals in the same group are packaged into a logical transmission unit and a phase stability requirement level label is added. After wavelength division multiplexing of all logical transmission units, they are transmitted to the regional collaborative node along with the phase stability requirement level label.

3. The distributed optical transmission method for multi-signal fusion according to claim 1, characterized in that, The regional collaborative node collects historical data of each link within its region and predicts the load rate of each link for a preset future time period, obtaining the predicted load rate value for each link, including: Regional collaborative nodes collect historical data from each link in real time, including load time series data and phase stability time series data; Load timing data includes link bandwidth utilization, packet throughput, and queue latency. Phase stability time series data includes phase jitter, phase drift, and synchronization error; Based on the load time series data of each link, an LSTM model is trained to obtain the load prediction model corresponding to each link. The load time series data within the current preset time window is input into the load prediction model for processing to obtain the load rate prediction value of each link in the future preset time period.

4. The distributed optical transmission method for multi-signal fusion according to claim 3, characterized in that, The regional collaborative nodes predict the phase stability level of each link for a preset future time period based on historical data, and obtain the predicted phase stability level for each link, including: After normalizing the phase jitter value, phase drift amount, and synchronization error, a weighted sum is calculated, and the interval in which the weighted sum is located is mapped to the corresponding phase stability level. Generate a training dataset by combining link load time-series data and the corresponding set of phase stability levels; The pre-defined random forest regression model is trained under supervision based on the training dataset to obtain the load phase correlation model. The load time series data within the current preset time window is input into the load phase correlation model for processing to obtain the predicted phase stability level of each link in the future preset time period.

5. The distributed optical transmission method for multi-signal fusion according to claim 1, characterized in that, The regional collaborative node allocates links and transmits data to each logical transmission unit based on the phase stability requirement level, load rate prediction value, and phase stability prediction level, including: The comprehensive score of each link is obtained by processing the real-time load rate, predicted load rate, real-time phase stability level, and predicted phase stability level of each link. For each logical transmission unit, select the link with the highest comprehensive link score that matches its phase stability requirement level as the final transmission path.

6. The distributed optical transmission method for multi-signal fusion according to claim 5, characterized in that, The core forwarding node selects cross-regional transmission paths based on the load status and signal transmission requirements of each region, including: The core forwarding node acquires cross-regional signal transmission demand parameters, as well as the regional load rate and regional phase synchronization deviation of each region in real time. The cross-regional signal transmission requirement parameters include signal scenario priority, phase stability requirement level, and delay requirement threshold. A multi-objective optimization model is constructed with the optimization objectives of minimizing the regional load rate difference, minimizing the transmission delay time, and minimizing the regional phase synchronization deviation, and with the constraints of matching the phase stability requirement level and the delay time not exceeding the delay requirement threshold. The multi-objective optimization model is solved using a pre-defined multi-objective optimization algorithm to obtain the Pareto optimal path set; The final transmission path is selected from the Pareto optimal path set based on the phase stability requirement level and signal scenario priority.

7. The distributed optical transmission method for multi-signal fusion according to claim 1, characterized in that, Also includes: If the predicted load rate of all links in the region is greater than the preset load rate threshold or the predicted phase stability level is lower than the required phase stability level; Then, links with load rates less than the preset load rate threshold, phase stability levels matching the required phase stability levels, and predicted phase stability levels higher than or equal to the required phase stability levels are selected as candidate links.

8. A distributed optical transmission system with multi-signal fusion, characterized in that, include: Edge access node module, including: Multi-type signal acquisition unit: used to acquire multiple types of signals and their corresponding signal type labels and scene labels; Phase stability level mapping unit: Stores a three-dimensional mapping table of application scenario-signal type-phase stability level, used to determine the phase stability requirement level corresponding to each type of signal; Signal grouping and packaging unit: Groups multiple types of signals according to signal type, scene label and phase stability requirement level, and packages signals in the same group into logical transmission units; Tag Addition Unit: Add a phase stability requirement level tag to each logical transmission unit; Wavelength division multiplexing processing unit: performs wavelength division multiplexing processing on all logical transmission units and transmits them to the regional cooperation node; The regional collaborative node module includes: Historical data acquisition unit: collects historical data of each link in real time, including load time series data and phase stability time series data; Load prediction unit: The load prediction model is trained based on the LSTM model to obtain the predicted load rate of each link; Phase stability prediction unit: The load phase correlation model is trained based on the random forest regression model to obtain the phase stability prediction level of each link; Link allocation decision unit: Calculates the comprehensive link score based on the phase stability requirement level, load rate prediction value, and phase stability prediction level, and allocates the optimal transmission link to the logical transmission unit; The core forwarding node module includes: Cross-regional parameter acquisition unit: Real-time acquisition of cross-regional signal transmission demand parameters, as well as the regional load rate and regional phase synchronization deviation of each region; Multi-objective optimization modeling unit: Constructs a multi-objective optimization model with the optimization objectives of minimizing the regional load rate difference, minimizing the transmission delay time, and minimizing the regional phase synchronization deviation; Path finding unit: uses multi-objective optimization algorithms to find the Pareto optimal path set; Final path selection unit: Selects the final transmission path based on the phase stability requirement level and signal scenario priority; The link backup management module includes: Anomaly detection unit: Monitors the predicted load rate and phase stability level of all links within the monitoring area; Alternate link selection unit: When an anomaly is detected, an alternative link that meets the preset conditions is selected.

9. The distributed optical transmission system with multi-signal fusion according to claim 8, characterized in that, The link allocation decision unit is used for: The comprehensive score of each link is calculated based on its real-time load rate, predicted load rate, real-time phase stability level, and predicted phase stability level. For each logical transmission unit, select the link with the highest comprehensive link score that matches its phase stability requirement level as the final transmission path.

10. The distributed optical transmission system with multi-signal fusion according to claim 9, characterized in that, The multi-objective optimization modeling unit is used for: With the optimization objectives of minimizing the regional load rate difference, minimizing the transmission delay time, and minimizing the regional phase synchronization deviation, and with the constraints of matching the phase stability requirement level and the delay time not exceeding the delay requirement threshold, a multi-objective optimization model is constructed.

Images