Optical line protection method

Abstract

The application relates to the technical field of electric communication transmission, in particular to an optical line protection method. The optical line protection method comprises the following steps: dividing an optical line network into multiple sub-line segments; setting a first sliding time window, and acquiring optical line indexes of main optical lines of each sub-line segment; respectively calculating risk values of each sub-line segment; respectively for each sub-line segment, the following steps are executed: determining multiple associated sub-line segments of a current sub-line segment; establishing a first input matrix, wherein the first input matrix comprises the risk value of the current sub-line segment, adjacency characteristics of each associated sub-line segment and the risk value of each associated sub-line segment; inputting the first input matrix into a risk prediction model to obtain a future maximum risk value of the current sub-line segment; and when the future maximum risk value of the current sub-line segment is greater than a preset first risk threshold, making a backup optical line execute a warning action. The method can more efficiently protect the optical line.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric communication transmission, in particular to an optical line protection method. BACKGROUND

[0002] In the existing communication network, optical fiber communication is the most important information transmission method. In order to ensure the reliability and continuity of communication, a dual-redundancy design of main optical line and backup optical line is usually adopted. In daily operation, the detection system monitors the state of the main optical line in real time. Once the key indicators (such as fiber attenuation, power or bit error rate) of the main optical line are detected to exceed the preset threshold, the system will automatically switch the communication to the backup optical cable, thereby avoiding communication interruption.

[0003] However, due to the difficulty in accurately predicting the occurrence time of optical fiber failure, in order to ensure that the communication can be switched immediately when the failure occurs, the backup optical line and its transmission equipment usually need to be in an open state all the time. This not only wastes energy, but also shortens the service life of the backup system.

[0004] Therefore, the existing main-backup optical line protection method is not intelligent and efficient enough. SUMMARY

[0005] In order to solve the above technical problems or at least partially solve the above technical problems, the present application provides an optical line protection method which can more intelligently and efficiently protect the optical line.

[0006] The present application provides an optical line protection method, which comprises the following steps:

[0007] According to the setting position of each optical line switching device of the optical line network, the optical line network is divided into a plurality of sub-line segments, each sub-line segment including a main optical line and a backup optical line controlled by itself;

[0008] A first sliding time window is set, and the optical line indicators of the main optical line of each sub-line segment within the time window are obtained;

[0009] The risk values of each sub-line segment are calculated respectively by a preset risk value calculation function according to the optical line indicators of each sub-line segment within the first sliding time window;

[0010] For each sub-line segment, the following steps are performed respectively:

[0011] According to the optical line indicator fluctuation of the current sub-line segment and the optical line indicator fluctuation of other sub-line segments within the first sliding time window, a plurality of associated sub-line segments of the current sub-line segment are determined;

[0012] establish a first input matrix, the first input matrix comprising a risk value of the current sub-section, an adjacency feature of each associated sub-section to the current sub-section, and a risk value of each associated sub-section;

[0013] input the first input matrix into a preset risk prediction model to obtain a future maximum risk value of the current sub-section;

[0014] when the future maximum risk value of the current sub-section is greater than a preset first risk threshold, causing the backup optical line of the current sub-section to perform a warning action.

[0015] Optionally, the optical line protection method further comprises the following steps:

[0016] obtaining a plurality of hypothetical associated sub-sections by obtaining sub-sections with a current risk value greater than a preset second risk threshold;

[0017] combining each hypothetical associated sub-section with the current sub-section one by one to establish a plurality of second data sets respectively;

[0018] the second data set comprises a risk value of the current sub-section, an adjacency feature of the current hypothetical associated sub-section to the current sub-section, and a risk value of the current hypothetical sub-section;

[0019] inputting the second data set into a preset risk prediction model to obtain a future maximum risk value of the current sub-section;

[0020] when the future maximum risk value of the current sub-section is greater than a third risk threshold, adjusting an association threshold of the current hypothetical associated sub-section being judged as an associated sub-section of the current sub-section according to a difference between the future maximum risk value and the third risk threshold, so that the greater the difference, the easier the current hypothetical associated sub-section is to be judged as an associated sub-section of the current sub-section;

[0021] the third risk threshold is less than the first risk threshold.

[0022] Optionally, the risk value of each sub-section is calculated by a preset risk value calculation function according to an optical line index of each sub-section in a first sliding time window, comprising the following steps:

[0023] the optical line index comprises: average optical power attenuation, port bit error rate, optical signal-to-noise ratio, optical line delay, and optical line jitter;

[0024] the preset risk value calculation function is

[0025]

[0026] wherein R represents a risk value of the current sub-segment, ΔP represents an average optical power attenuation, BER represents a port bit error rate, OSNR represents an optical signal-to-noise ratio, Delay represents an optical line delay, and Jitter represents an optical line jitter, 、 、 、 and are preset empirical parameters.

[0027] Optionally, the plurality of associated sub-segments of the current sub-segment are determined according to the optical line index fluctuation of the current sub-segment and the optical line index fluctuation of other sub-segments within the first sliding time window, and the determination comprises the following steps:

[0028] The optical line index fluctuation at least comprises one or more of the following time-varying data: a time sequence of changes in optical power attenuation, a time sequence of changes in port bit error rate, a time sequence of changes in optical signal-to-noise ratio, a time sequence of changes in optical line delay, and a time sequence of changes in optical line jitter;

[0029] The time sequence of changes in the optical line index of the current sub-segment within the first sliding time window is respectively compared with the time sequence of changes in the optical line index of other sub-segments within the same time window by using the DTW algorithm to obtain the similarity between each other sub-segment and the current sub-segment.

[0030] When the similarity between the other sub-segment and the current sub-segment is greater than the associated threshold corresponding to the other sub-segment, the other sub-segment is determined as an associated sub-segment of the current sub-segment.

[0031] Optionally, the preset risk prediction model is obtained by training through the following steps:

[0032] Step 1: using a convolutional neural network as a model framework of the risk prediction model;

[0033] Step 2: collecting a plurality of sets of first training data, and each set of first training data comprises:

[0034] a risk value of a target sub-segment, wherein the target sub-segment represents any sub-segment in the optical line network;

[0035] sub-segment data associated with the target sub-segment, including an adjacency feature between each associated sub-segment and the target sub-segment and a risk value of each associated sub-segment;

[0036] Step 3: for each set of first training data, collecting a corresponding future maximum risk value, i.e., a maximum risk value of the target sub-segment within a preset future time period;

[0037] Step 4: training a final risk prediction model by taking the first training data as input of the model framework and taking the future maximum risk value as the label of the model framework.

[0038] Optionally, when the future maximum risk value of the current sub-segment is greater than a preset first risk threshold, the standby optical line of the current sub-segment is caused to perform a pre-warning action, including the following steps:

[0039] The pre-warning action includes the standby optical line of the current sub-segment and completes signal quality testing and flow simulation switching testing on the standby optical line.

[0040] Compared with the prior art, the technical scheme provided in the application has the following advantages:

[0041] One of the beneficial effects and the working principle thereof is that in the conventional protection scheme of an optical network, switching is usually performed only after some values are monitored in real time and obvious abnormalities are found, for example, the switching of a standby line is triggered passively only after key indicators such as optical power attenuation or bit error rate are significantly degraded. This way often lacks forward-looking identification of potential risks and is difficult to provide sufficient response time in a timely manner.

[0042] To solve this problem, the method described in the application divides a plurality of sub-segments in an optical line network, continuously obtains optical line indicators (such as optical power attenuation, port bit error rate, time delay, and jitter) of each sub-segment within a first sliding time window, quantizes the indicators into risk values, combines associated sub-segment information identified by "fluctuation similarity", inputs the first input matrix to a preset risk prediction model, thereby predicting the future maximum risk value of the current sub-segment, and wakes up the standby optical line to perform a pre-warning action when the first risk threshold is exceeded.

[0043] The beneficial effects of the scheme are reflected in the following aspects:

[0044] Different sub-segments often have some correlation or associated effects. Through continuous data collection and model prediction mechanism, the system can actively explore the correlation between sub-segments and capture potential risks before the signs of failure have completely deteriorated.

[0045] When the risk is low, the standby optical line can be in a low-power or partially dormant state. When the pre-warning threshold is triggered, the risk is high, and the signal quality testing and flow simulation switching preparation are quickly completed, thereby effectively optimizing the standby resource scheduling strategy and balancing energy efficiency and cost efficiency.

[0046] Through the above cooperation, the initiative and resilience of optical line protection are significantly improved, and the balance between network energy efficiency and network robustness is maximized.

[0047] The second benefit and the working principle thereof is that in actual optical network line operation, some sub-sections associated with the current sub-section may have already appeared abnormal, but the abnormality of the current sub-section is not obvious, and since the similarity of the fluctuation characteristics thereof to the current sub-section has not reached the judgment standard, the sub-sections may be ignored in the association analysis. However, once the potential failure of the high-risk sub-sections breaks out comprehensively, and the current sub-section has not completed the starting of the standby optical line, the severity of the chain effect often far exceeds the expectation. For this unacceptable key scene, the application also proposes a dynamic optimization strategy of the pre-assumed association threshold.

[0048] Specifically, when the application monitors that the risk value of a certain sub-section exceeds the second risk threshold (significantly higher than the regular level), even if the index fluctuation thereof is not very similar to that of the current sub-section, the system will first include it in a special "assumed association set" and carry out a forward-looking combined risk prediction based thereon.

[0049] By comparing the gap between the maximum future risk value of the sub-section and the third risk threshold, the system can determine whether the severity of the sub-section is within a controllable range once the sub-section fails.

[0050] If the difference is large, that is, the risk is significantly beyond the warning line, it indicates that even if the association degree of the sub-section to the current sub-section is not certain, it must be considered as a "key abnormality" and given special attention in advance, at which time the system will automatically lower the association threshold of the sub-section, so as to include it in the joint risk assessment field of the current sub-section with higher sensitivity.

[0051] This dynamic optimization of the predictive association threshold can identify the implicit risks that may cause serious consequences once out of control although the relevance is not obvious, and capture them into the global linkage disposal process at the first time, so as to capture these potential threats as early as possible.

[0052] If the difference is not large, it means that even if the sub-section appears abnormal, it will not have too serious consequences, and the system can retain the original threshold judgment to avoid excessive consumption of resources.

[0053] In this way, the application can achieve more stringent prevention for high-risk sub-sections, and will not bring frequent unnecessary warnings to the whole network, thereby achieving an effective balance between the warning sensitivity and the global resource efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0054] Figure 1 The flowchart of the optical line protection method provided by the embodiment of the application. DETAILED DESCRIPTION

[0055] The technical solutions in the application will be described below with reference to the drawings.

[0056] Many particular details are set forth in the following description in order to provide a thorough understanding of the application. However, the application can be practiced according to the claims without some or all of these details. Indeed, the application is well suited to the use of a variety of different embodiments without departing from the scope of the application. Obviously, the scope of the application is not limited to the embodiments described in the specification.

[0057] The application provides an optical line protection method, comprising the following steps:

[0058] S101: According to the setting position of each optical line switching device of the optical line network, the optical line network is divided into a plurality of sub-line segments, each sub-line segment comprising a working optical line and a backup optical line controlled by itself.

[0059] S102: A first sliding time window is set, and the optical line index of the working optical line of each sub-line segment in the time window is obtained.

[0060] Specifically, the first sliding time window herein represents a data window regularly updated along the time axis, and in the embodiment of the application, the size of the first sliding time window is one week, and the time step of the update is 24 hours.

[0061] Specifically, the optical line index can be directly obtained from the log file generated by the optical line detection function configured in the optical line control device, and the optical line index comprises an average optical power attenuation, a port bit error rate, an optical signal-to-noise ratio, an optical line delay, and an optical line jitter.

[0062] S103: According to the optical line index of each sub-line segment in the first sliding time window, the risk value of each sub-line segment is calculated by a preset risk value calculation function.

[0063] Specifically, the following steps are included:

[0064] The optical line index of the working optical line of each sub-line segment is input into the risk value calculation function to obtain the risk value of each sub-line segment.

[0065] The preset risk value calculation function is

[0066]

[0067] Wherein, R represents the risk value of the current sub-line segment, ΔP represents the average optical power attenuation, BER represents the port bit error rate, OSNR represents the optical signal-to-noise ratio, Delay represents the optical line delay, and Jitter represents the optical line jitter. 、 、 、 and is a human preset experience parameter.

[0068] For each sub-segment, the following steps are performed respectively:

[0069] S104: According to the light path index fluctuation of the current sub-segment and the light path index fluctuation of other sub-segments in the first sliding time window, a plurality of associated sub-segments of the current sub-segment are determined.

[0070] Specifically, in the embodiment of the present application, steps S201-S202 are included.

[0071] S201: Obtain the association threshold value of each other sub-segment being determined as the associated sub-segment of the current sub-segment.

[0072] Step 1: Set the association threshold value of all other sub-segments being determined as the associated sub-segment of the current sub-segment to a human-set association reference value.

[0073] Step 2: Obtain sub-segments with a current risk value greater than a preset second risk threshold value to obtain a plurality of hypothetical associated sub-segments;

[0074] Each hypothetical associated sub-segment is combined with the current sub-segment one by one to establish a plurality of second data sets respectively;

[0075] The second data set includes the risk value of the current sub-segment, the adjacent feature of the current hypothetical associated sub-segment and the current sub-segment, and the risk value of the current hypothetical sub-segment;

[0076] Input the second data set into a preset risk prediction model to obtain the future maximum risk value of the current sub-segment;

[0077] When the future maximum risk value of the current sub-segment is greater than a third risk threshold value, adjust the association threshold value of the current hypothetical associated sub-segment being determined as the associated sub-segment of the current sub-segment according to the difference between the future maximum risk value and the third risk threshold value, so that the greater the difference, the easier the current hypothetical associated sub-segment is to be determined as the associated sub-segment of the current sub-segment;

[0078] The third risk threshold value is less than the first risk threshold value.

[0079] Specifically, in the embodiment of the present application, the association threshold value adjustment formula is used to adjust the association threshold value of the current hypothetical associated sub-segment being determined as the associated sub-segment of the current sub-segment according to the difference between the future maximum risk value and the third risk threshold value.

[0080] The association threshold value adjustment formula is:

[0081]

[0082] wherein, represents an adjusted correlation threshold value, represents a correlation reference value set artificially, represents a future maximum risk value obtained by a risk prediction model, represents a third risk threshold value, and η represents a linear adjustment coefficient set artificially, which should be a positive number.

[0083] S202: According to the correlation threshold value of each other sub-segment determined as the correlation sub-segment of the current sub-segment in S201, the similarity between each other sub-segment and the current sub-segment is obtained by the following steps, and the judgment of whether it is a correlation sub-segment is performed.

[0084] Specifically, the optical line index fluctuation at least includes one or more of the following data changing over time: a time sequence change sequence of optical power attenuation, a time sequence change sequence of port bit error rate, a time sequence change sequence of optical signal-to-noise ratio, a time sequence change sequence of optical line delay, and a time sequence change sequence of optical line jitter amount;

[0085] The optical line index fluctuation sequence of the current sub-segment in the first sliding time window is respectively compared with the optical line index fluctuation sequence of the other sub-segment in the same time window by the DTW algorithm to obtain the similarity between each other sub-segment and the current sub-segment.

[0086] When the similarity between the other sub-segment and the current sub-segment is greater than the correlation threshold value corresponding to the other sub-segment, the other sub-segment is determined as the correlation sub-segment of the current sub-segment.

[0087] S105: A first input matrix is established, which includes the risk value of the current sub-segment, the adjacency feature of each correlation sub-segment and the current sub-segment, and the risk value of each correlation sub-segment.

[0088] The first input matrix is input into a preset risk prediction model to obtain the future maximum risk value of the current sub-segment.

[0089] Specifically, in the embodiment of the present application, the preset risk prediction model is obtained by the following steps:

[0090] Step 1: using a convolutional neural network as a model framework of the risk prediction model;

[0091] Step 2: collecting a plurality of groups of first training data, each group of first training data including:

[0092] a risk value of a target sub-segment, the target sub-segment representing any sub-segment in the optical line network;

[0093] The sub-segment data associated with the target sub-segment includes the abutment characteristics of each associated sub-segment with the target sub-segment and the risk value of each associated sub-segment;

[0094] Step 3: For each set of first training data, a corresponding future maximum risk value is collected, that is, the maximum risk value of the target sub-segment within a preset future time period;

[0095] Step 4: The first training data is taken as the input of the model framework, and the future maximum risk value is taken as the label of the model framework, and a final risk prediction model is trained.

[0096] S106: When the future maximum risk value of the current sub-segment is greater than a preset first risk threshold, the standby optical line of the current sub-segment performs a warning action.

[0097] Specifically, the standby optical line of the current sub-segment performs a warning action, including the following steps:

[0098] The warning action includes the standby optical line of the current sub-segment, and completes signal quality testing and flow simulation switching testing of the standby optical line.

[0099] In summary, the technical scheme provided by the embodiments of the present application has the following advantages compared with the prior art:

[0100] One of the beneficial effects and the discussion of the working principle is that in the traditional protection scheme of the optical network, switching is usually performed based on the fact that some values have obvious abnormalities, for example, when the key indicators such as optical power attenuation or bit error rate deteriorate significantly, the standby line is passively triggered to switch. This way often lacks forward-looking identification of potential risks and is difficult to provide enough response time in a timely manner.

[0101] To solve this problem, the method described in the present application divides the optical line network into multiple sub-segments, and continuously obtains the optical line indicators (such as optical power attenuation, port bit error rate, delay, jitter, etc.) of each sub-segment within a first sliding time window, quantizes them into risk values, and then combines the associated sub-segment information identified by the "fluctuation similarity" to input into a preset risk prediction model in the form of a first input matrix, thereby predicting the future maximum risk value of the current sub-segment, and waking up the standby optical line to perform a warning action when the first risk threshold is exceeded.

[0102] The beneficial effects of this scheme are reflected in the following aspects:

[0103] Different sub-segments often have some association or influence, and through continuous data collection and model prediction mechanism, the system can actively explore the association effect between sub-segments and capture potential risks before the fault signs have completely deteriorated.

[0104] The standby optical line can be in a lower power consumption or partial hibernation state when the risk is low. When the early warning threshold is triggered, the risk is high, and the signal quality test and traffic simulation switching preparation are quickly completed, thereby effectively optimizing the standby resource scheduling strategy, and balancing energy efficiency and cost efficiency.

[0105] Through the above cooperation, the initiative and resilience of optical line protection are significantly improved, and the balance between network energy efficiency and network robustness is maximized.

[0106] The second beneficial effect and the working principle thereof are that in actual optical network line operation, some sub-line segments associated with the current sub-line segment may have abnormalities, but the abnormality of the current sub-line segment is not obvious, and since the similarity of the fluctuation characteristics thereof has not reached the determination standard, it may be ignored in the association analysis. However, once the potential failure of these high-risk sub-line segments breaks out comprehensively, and the current sub-line segment has not completed the start of the standby optical line, the severity of the chain effect is often far beyond expectation. For this unacceptable key scene, the application also proposes a dynamic optimization strategy of the pre-assumed association threshold.

[0107] Specifically, when the application monitors that the risk value of a sub-line segment exceeds the second risk threshold (significantly higher than the regular level), even if the index fluctuation thereof is not very similar to that of the current sub-line segment, the system will first include it in a special "assumed association set" and carry out a forward-looking combined risk prediction based thereon.

[0108] By comparing the gap between the maximum future risk value of the sub-line segment and the third risk threshold, the system can determine whether the severity of the sub-line segment failure is within a controllable range.

[0109] If the difference is large, that is, the risk is significantly beyond the warning line, it means that even if the association degree of the sub-line segment with the current sub-line segment is not determined, it must be considered as a "key abnormality" and given special attention, at this time the system will automatically lower the association threshold of the sub-line segment, so as to include it in the joint risk assessment field with the current sub-line segment with higher sensitivity.

[0110] This dynamic optimization of the predictive association threshold can identify implicit risks that may have serious consequences if they are out of control, and capture them into the global linkage disposal process as soon as possible, so as to capture these potential threats as soon as possible.

[0111] If the difference is not large, it means that even if the sub-line segment has an abnormality, it will not have too serious consequences, and the system can retain the original threshold to avoid excessive consumption of resources.

[0112] Thus, the application can achieve more strict prevention for high-risk sub-line segments, and does not bring frequent and unnecessary early warning to the whole network, so that an effective balance between early warning sensitivity and global resource efficiency is achieved.

[0113] It should be noted that, in this document, the terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply there is any such actual relationship or order between these entities or operations. In addition, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of other identical elements in the process, method, article or device including the element. Moreover, in the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this document is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. Moreover, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0114] The above is only the specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications of these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments described herein, but will conform to the widest range consistent with the principles and novel features disclosed herein.

Claims

1. A method of optical line protection, characterized by, The optical line protection method comprises the following steps: According to the setting position of each optical line switching device of the optical line network, the optical line network is divided into a plurality of sub-segments, each sub-segment comprising a working optical line and a backup optical line controlled by itself; A first sliding time window is set, and the optical line index of the working optical line of each sub-segment in the time window is obtained; The risk value of each sub-segment is calculated by a preset risk value calculation function according to the optical line index of each sub-segment in the first sliding time window; For each sub-segment, the following steps are performed: According to the optical line index fluctuation of the current sub-segment and the optical line index fluctuation of other sub-segments in the first sliding time window, a plurality of associated sub-segments of the current sub-segment are determined; A first input matrix is established, which includes the risk value of the current sub-segment, the adjacency characteristics of each associated sub-segment and the current sub-segment, and the risk value of each associated sub-segment; The first input matrix is input into a preset risk prediction model to obtain the future maximum risk value of the current sub-segment; When the future maximum risk value of the current sub-segment is greater than a preset first risk threshold, the backup optical line of the current sub-segment performs a warning action.

2. The optical line protection method according to claim 1, wherein: The risk value of each sub-segment is calculated by a preset risk value calculation function according to the optical line index of each sub-segment in the first sliding time window, comprising the following steps: The optical line index includes: average optical power attenuation, port bit error rate, optical signal-to-noise ratio, optical line delay and optical line jitter; The preset risk value calculation function is wherein R represents a risk value of the current sub-line segment, ΔP represents an average optical power attenuation, BER represents a port bit error rate, OSNR represents an optical signal-to-noise ratio, Delay represents an optical line delay, and Jitter represents an optical line jitter amount, , , , and are preset empirical parameters.

3. The optical line protection method according to claim 1, wherein, According to the optical line index fluctuation of the current sub-segment and the optical line index fluctuation of other sub-segments in the first sliding time window, a plurality of associated sub-segments of the current sub-segment are determined, comprising the following steps: The optical line index fluctuation includes at least one or more time-varying data: time sequence change sequence of optical power attenuation, time sequence change sequence of port bit error rate, time sequence change sequence of optical signal-to-noise ratio, time sequence change sequence of optical line delay and time sequence change sequence of optical line jitter; The optical line index fluctuation sequence of the current sub-segment in the first sliding time window is calculated by the DTW algorithm with the optical line index fluctuation sequence of other sub-segments in the same time window, to obtain the similarity between each other sub-segment and the current sub-segment; When the similarity between the other sub-segment and the current sub-segment is greater than the associated threshold corresponding to the other sub-segment, the other sub-segment is determined as the associated sub-segment of the current sub-segment.

4. The optical line protection method according to claim 3, wherein According to the optical line index fluctuation of the current sub-segment and the optical line index fluctuation of other sub-segments in the first sliding time window, a plurality of associated sub-segments of the current sub-segment are determined, further comprising the following steps: Obtain the sub-segment whose current risk value is greater than a preset second risk threshold to obtain a plurality of hypothetical associated sub-segments; Each hypothetical associated sub-segment is combined with the current sub-segment one by one to establish a plurality of second data sets respectively; The second data set includes the risk value of the current sub-segment, the adjacency characteristics of the current hypothetical associated sub-segment and the current sub-segment, and the risk value of the current hypothetical sub-segment; inputting the second data set into a preset risk prediction model to obtain a future maximum risk value of the current sub-section for adjusting the correlation threshold; when the future maximum risk value of the current sub-section for adjusting the correlation threshold is greater than a third risk threshold, adjusting the correlation threshold of the current hypothetical correlation sub-section being judged as the correlation sub-section of the current sub-section according to a difference between the future maximum risk value of the current sub-section for adjusting the correlation threshold and the third risk threshold, so that the current hypothetical correlation sub-section is more likely to be judged as the correlation sub-section of the current sub-section when the difference is greater; the third risk threshold is less than the first risk threshold.

5. The optical line protection method according to claim 1, wherein, the preset risk prediction model is obtained by the following steps: Step 1: using a convolutional neural network as a model framework of the risk prediction model; Step 2: collecting a plurality of groups of first training data, each group of first training data comprising: a risk value of a target sub-section, the target sub-section representing any sub-section in the optical network; sub-section data associated with the target sub-section, including the adjacency feature of each correlation sub-section with the target sub-section and the risk value of each correlation sub-section; Step 3: for each group of first training data, collecting a corresponding future maximum risk value, i.e. the maximum risk value of the target sub-section within a preset future time period; Step 4: using the first training data as the input of the model framework and using the future maximum risk value as the label of the model framework to train the final risk prediction model.

6. The optical line protection method according to claim 1, wherein, when the future maximum risk value of the current sub-section is greater than a preset first risk threshold, causing the standby optical line of the current sub-section to perform a warning action, comprising the following steps: the warning action includes starting the standby optical line of the current sub-section and completing the signal quality test and the flow simulation switching test of the standby optical line.

Images