Optical network attenuation analysis method and system suitable for long-distance transmission

Abstract

The invention discloses an optical network attenuation analysis method and system suitable for long-distance transmission, and the method comprises the steps: collecting an environment parameter at each collection moment, the link length of each optical fiber cross-section in an optical network, and the optical power of each optical fiber cross-section in the optical network at each collection moment; the method comprises the following steps: constructing each environment change time sequence and an optical power time sequence of each optical fiber span, calculating attenuation lag time length of each optical fiber span, constructing a lag attenuation sequence of each optical fiber span, obtaining each attenuation mode component, calculating an unconventional attenuation evolution index, and obtaining an abnormal attenuation span. And calculating an attenuation analysis key factor and a non-exogenous attenuation confidence index of each attenuation mode component, and obtaining an optical network attenuation reason of each abnormal attenuation span. According to the optical network attenuation analysis method and system suitable for long-distance transmission provided by the embodiment of the invention, the optical network attenuation reason analysis efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of optical fiber communication technology, and in particular to an optical network attenuation analysis method and system suitable for long-distance transmission. Background Art

[0002] Optical fiber communication uses light waves to transmit information in optical fibers, and has the characteristics of high bandwidth, low loss, and strong anti-interference ability. Optical network generally refers to wide area network, metropolitan area network or newly built large-scale local area network that uses optical fiber as the main transmission medium. With the continuous upgrading and development of communication technology, modern optical communication technology has gradually replaced traditional communication methods, and has a trend of developing into intelligent optical networks, and the complexity of the network has increased significantly.

[0003] As the transmission distance increases, the absorption and scattering losses in the optical fiber will cause the optical network signal strength to weaken. Optical network attenuation may cause signal attenuation or distortion, which in turn affects the integrity and accuracy of the data. Therefore, analyzing the optical network attenuation is of great practical significance.

[0004] However, since optical signals are affected by many factors when transmitted in optical fibers, the efficiency of analyzing the causes of optical network attenuation is not high. Summary of the invention

[0005] The present invention provides an optical network attenuation analysis method and system suitable for long-distance transmission, so as to solve the technical problem that it is difficult to analyze the attenuation cause of the optical network because the optical signal is affected by many factors when transmitted in the optical fiber.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides an optical network attenuation analysis method suitable for long-distance transmission.

[0007] Collecting environmental parameters at each collection time, the link length of each optical fiber span in the optical network, and the optical power of each optical fiber span in the optical network at each collection time, and constructing each environmental change time series and the optical power time series of each optical fiber span;

[0008] Calculating the attenuation lag time of each optical fiber span based on the correlation hysteresis characteristics between the optical power time series of adjacent optical fiber spans, and constructing a hysteresis attenuation sequence of each optical fiber span based on the correlation difference of the optical powers of adjacent optical fiber spans and each attenuation lag time;

[0009] Obtaining corresponding decay modal components based on the modal decomposition result of each of the hysteresis decay sequences, and calculating corresponding unconventional decay evolution indexes based on the difference between each of the decay modal components and the corresponding fitting result;

[0010] Acquire an abnormal attenuation span based on all the attenuation hysteresis durations, all the link lengths, and all the unconventional attenuation evolution indices;

[0011] Calculating a corresponding attenuation shift key factor based on each of the attenuation modal components and the corresponding unconventional attenuation evolution index, and calculating an attenuation analysis key factor of each of the attenuation modal components based on the correlation between all of the attenuation modal components and each of the attenuation shift key factors;

[0012] Based on the correlation degree between each attenuation modal component and each of the environmental change time series and each of the unconventional attenuation evolution indexes, the non-exogenous attenuation confidence index of each attenuation modal component is obtained; based on all of the non-exogenous attenuation confidence indices and all of the attenuation analysis key factors, the cause of optical network attenuation in each abnormal attenuation span is obtained.

[0013] As one of the preferred solutions, the method of constructing the hysteresis attenuation sequence of each optical fiber span based on the correlation difference of the optical powers of adjacent optical fiber spans and each attenuation hysteresis time length includes:

[0014] The hysteresis attenuation factor of each optical fiber span at each acquisition time is calculated based on the correlation difference characteristics of the optical power of two adjacent optical fiber spans:

[0015]

[0016] Among them, TDY i t is the hysteresis attenuation factor of the ith optical fiber span at the tth acquisition time, is the i-1th fiber span at the t-τth i The optical power at each acquisition moment, LP i t is the optical power of the ith fiber span at the tth acquisition time, τ i is the attenuation lag time of the i-th optical fiber span;

[0017] The hysteresis attenuation factors of each optical fiber span at all acquisition moments are arranged in ascending order according to the time sequence of acquisition, as the hysteresis attenuation sequence of each optical fiber span.

[0018] As one of the preferred solutions, the attenuation lag time of each optical fiber span is calculated based on the correlation hysteresis characteristics between the optical power time series of adjacent optical fiber spans, including:

[0019] The maximum value of the TLCC time lag correlation coefficient between the optical power time series of each optical fiber span and the optical power time series of the adjacent previous optical fiber span at all lag orders is taken as the signal attenuation correlation coefficient between each optical fiber span and the adjacent previous optical fiber span, and the lag order corresponding to the signal attenuation correlation coefficient is taken as the attenuation lag duration of each optical fiber span.

[0020] As one of the preferred solutions, the calculation of the corresponding unconventional attenuation evolution index based on the difference between each of the attenuation modal components and the corresponding fitting result includes:

[0021] Perform linear fitting processing on each of the attenuation modal components to obtain the attenuation fitting sequence of each of the attenuation modal components, take the absolute value of the difference between each of the attenuation modal components and the corresponding attenuation fitting sequence as the attenuation fitting difference sequence of each of the attenuation modal components, and take the average value of all element values ​​in each of the attenuation fitting difference sequences as the unconventional attenuation evolution index of the corresponding attenuation modal component.

[0022] As one of the preferred solutions, the specific method of obtaining the abnormal attenuation span based on all the attenuation hysteresis time lengths, all the link lengths and all the unconventional attenuation evolution indexes is as follows:

[0023] Record the ratio of the attenuation lag time of each optical fiber span to the corresponding link length as the corresponding line attenuation ratio, use the line attenuation ratios of all the optical fiber spans as inputs of anomaly detection algorithms, and output the line attenuation anomaly score of each optical fiber span;

[0024] Based on the linear relationship between the line attenuation anomaly score of each optical fiber span and all corresponding unconventional attenuation evolution indices, the attenuation deviation anomaly index of each optical fiber span is calculated;

[0025] All the attenuation offset anomaly indexes are normalized to obtain the attenuation offset anomaly normalized index of each light span, and the light span whose attenuation offset anomaly normalized index is greater than a preset anomaly threshold is taken as an abnormal attenuation span.

[0026] As one of the preferred solutions, the specific method for calculating the corresponding attenuation offset key factor based on each of the attenuation modal components and the corresponding unconventional attenuation evolution index is as follows:

[0027] Taking the average value of all element values ​​of each of the decaying modal components as the stage attenuation value of each of the decaying modal components;

[0028] Based on the linear relationship between the stage attenuation value of each attenuation modal component and the corresponding unconventional attenuation evolution index, the attenuation deviation key factor of each attenuation modal component is calculated.

[0029] As one of the preferred solutions, the attenuation analysis key factor of each attenuation modal component is calculated based on the correlation degree between all the attenuation modal components and each attenuation offset key factor, including:

[0030] taking the average value of the Pearson correlation coefficients between each of the attenuation modal components and the remaining attenuation modal components of the corresponding light span as the attenuation shift correlation index of each of the attenuation modal components of each of the light spans;

[0031] Based on the linear relationship between each of the attenuation shift key factors and the corresponding attenuation shift correlation index, the attenuation analysis key factor of each of the attenuation modal components is calculated.

[0032] As one of the preferred solutions, the non-exogenous attenuation confidence index of each attenuation modal component is obtained based on the correlation between each attenuation modal component and each environmental change time series and each unconventional attenuation evolution index, including:

[0033] The average value of the Pearson correlation coefficient between each of the attenuation mode components and all the environmental change time series plus a preset parameter adjustment factor is used as the external cause correlation factor of each of the attenuation mode components;

[0034] The ratio of each of the unconventional attenuation evolution indexes to the corresponding external cause correlation factor is used as the non-external attenuation confidence index of each attenuation modal component.

[0035] As one of the preferred solutions, the step of obtaining the optical network attenuation cause of each abnormal attenuation span based on all the non-external attenuation confidence indexes and all the attenuation analysis key factors includes:

[0036] Normalizing the attenuation analysis key factors of all the attenuation modal components of each abnormal attenuation span to obtain the attenuation analysis weight of each attenuation modal component of each abnormal attenuation span, wherein the sum of all the attenuation analysis key factors of each abnormal attenuation span is 1;

[0037] The product of the non-exogenous attenuation confidence index of each attenuation modal component and the corresponding attenuation analysis weight is used as the weighted non-exogenous attenuation confidence index of each attenuation modal component, the average value of all the weighted non-exogenous attenuation confidence indexes of each abnormal attenuation span is used as the fiber fault attenuation confidence index of each abnormal attenuation span, and each fiber fault attenuation confidence index is normalized to obtain the normalized fiber fault attenuation confidence index of each abnormal attenuation span;

[0038] When the normalized fiber fault attenuation confidence index is greater than a preset fault threshold, the optical network attenuation cause of the abnormal attenuation span is determined to be a fiber fault; otherwise, the optical network attenuation cause of the abnormal attenuation span is determined to be normal attenuation.

[0039] Yet another embodiment of the present invention provides an optical network attenuation analysis system suitable for long-distance transmission, the system comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the optical network attenuation analysis method suitable for long-distance transmission as described above.

[0040] Compared with the prior art, the embodiments of the present invention have the following advantages:

[0041] (1) Collecting environmental parameters at each collection time, the link length of each optical fiber span in the optical network, and the optical power of each optical fiber span in the optical network at each collection time, constructing each environmental change time series and the optical power time series of each optical fiber span, first analyzing the correlation hysteresis characteristics between the optical power time series of adjacent optical fiber spans, calculating the attenuation hysteresis time of each optical fiber span, and then constructing the hysteresis attenuation sequence of each optical fiber span based on the correlation difference of the optical power of adjacent optical fiber spans and the attenuation hysteresis time of each optical fiber span, and then analyzing the attenuation cause of the optical network according to the hysteresis attenuation sequence of each optical fiber span, rather than directly analyzing the attenuation cause of the optical network according to the optical power time series, thereby improving the efficiency of analyzing the attenuation cause of the optical network;

[0042] (2) First, the overall abnormality of each optical fiber span is analyzed, and the line attenuation abnormality score of each optical fiber span is calculated based on the attenuation lag time and link length of all optical fiber spans. Considering that the optical signal is affected by many factors when it is transmitted in the optical fiber, in order to improve the reliability of the analysis of the optical network attenuation cause of each optical fiber span, the attenuation caused by different factors is analyzed separately, and the corresponding attenuation modal components are obtained based on the modal decomposition results of each delayed attenuation sequence. The corresponding unconventional attenuation evolution index is calculated based on the difference between each attenuation modal component and the corresponding fitting result, and the abnormal attenuation span is obtained in combination with the line attenuation abnormality scores of all optical fiber spans, thereby improving the reliability of the acquisition of the abnormal attenuation span. Subsequently, only the optical network attenuation cause of the abnormal attenuation span is analyzed, thereby improving the real-time performance of the analysis of the optical network attenuation cause.

[0043] (3) Based on each attenuation modal component and the corresponding unconventional attenuation evolution index, the attenuation offset key factor of each attenuation modal component is calculated, and the attenuation analysis key factor of each attenuation modal component is calculated in combination with the correlation between all attenuation modal components of each optical fiber span. Based on the correlation between each attenuation modal component and each environmental change time series and the unconventional attenuation evolution index of each attenuation modal component, the non-exogenous attenuation confidence index of each attenuation modal component is obtained. Based on the non-exogenous attenuation confidence index and the attenuation analysis key factor of all attenuation modal components of each abnormal attenuation span, the attenuation cause of the optical network of each abnormal attenuation span is obtained. Different weights are set for each attenuation modal component according to the severity of attenuation, the degree of abnormality and the degree of correlation with other attenuation modal components, thereby further improving the efficiency of the analysis of the attenuation cause of the optical network. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a schematic diagram of an optical network attenuation analysis process suitable for long-distance transmission in one embodiment of the present invention;

[0045] Figure 2 It is a schematic diagram of obtaining the unconventional attenuation evolution index in one embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0048] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used in this article are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used in this article includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0049] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0050] An embodiment of the present invention provides an optical network attenuation analysis method suitable for long-distance transmission. For details, see Figure 1 , Figure 1 The figure shows a schematic diagram of an optical network attenuation analysis process suitable for long-distance transmission in one embodiment of the present invention.

[0051] Step S1: Collect environmental parameters at each collection time, the link length of each optical fiber span in the optical network, and the optical power of each optical fiber span in the optical network at each collection time, and construct each environmental change time series and the optical power time series of each optical fiber span.

[0052] It should be noted that in long-distance transmission, the optical power loss in optical fibers and optical nodes can be compensated by erbium-doped fiber amplifiers. However, as the signal gain increases, each erbium-doped fiber amplifier will introduce amplifier spontaneous emission noise, which accumulates in the transmission link. The loss of each span has an important impact on the optical signal-to-noise ratio of each span of the optical communication network. The optical signal-to-noise ratio is an important indicator for measuring the performance of optical communication systems and an important parameter for performance monitoring. It is also the key to achieving fault diagnosis and location in optical transmission systems and networks. Therefore, accurately analyzing the optical network attenuation of each optical fiber span and then compensating the optical network accordingly can enable the optical network to maintain optimal network performance.

[0053] In order to analyze the optical network attenuation of each optical fiber span, it is necessary to first collect the optical power of each optical fiber span in the optical network. Specifically, the optical power and environmental parameters of each optical fiber span are collected every t minutes, and the link length of each optical fiber span is recorded.

[0054] It should be further explained that the collection time interval t is a manually preset value. In this embodiment, the collection time interval t is 15. As for the value of the collection time interval, as other implementation methods, the implementer can choose it at will, and this application does not impose any special restrictions on this.

[0055] Since optical signals are affected by many factors when transmitted in optical fibers, in order to improve the accuracy of analyzing the causes of optical network attenuation in each optical fiber span, the changes in optical power of each optical fiber span in the optical network over a period of time are analyzed, and the optical power of each optical fiber span at all acquisition moments is arranged in ascending order according to the acquisition time sequence as the optical power time series of each optical fiber span.

[0056] Furthermore, the same environmental parameters at all acquisition moments are arranged in ascending order according to the chronological order of acquisition as the environmental change time series.

[0057] As an embodiment of the present application, the environmental parameters include temperature and humidity, and the environmental change time series includes a temperature change time series and a humidity change time series.

[0058] Step S2: Calculate the attenuation lag time of each optical fiber span based on the correlation hysteresis characteristics between the optical power time series of adjacent optical fiber spans, and construct the hysteresis attenuation sequence of each optical fiber span based on the correlation difference of the optical power of adjacent optical fiber spans and the attenuation lag time of each optical fiber span.

[0059] It should be noted that when light enters from one end of the optical fiber and exits from the other end, the intensity of the light will weaken, which means that there are certain substances in the optical fiber or for some reason that block the passage of the light signal. After the light signal propagates through the optical fiber, part of the light energy is attenuated. This is the transmission loss of the optical fiber.

[0060] First, the correlation of the optical power time series of adjacent optical fiber spans at different lag orders is analyzed. Specifically, the TLCC time lag mutual correlation coefficient of the optical power time series of each optical fiber span and the optical power time series of the adjacent previous optical fiber span at different lag orders is calculated, and the maximum value of the TLCC time lag mutual correlation coefficient of the optical power time series of each optical fiber span and the optical power time series of the adjacent previous optical fiber span at all lag orders is taken as the signal attenuation correlation coefficient of each optical fiber span and the adjacent previous optical fiber span, and the lag order corresponding to the signal attenuation correlation coefficient is taken as the attenuation lag duration of each optical fiber span.

[0061] It should be noted that the TLCC time-lagged cross-correlation refers to the correlation between two time series after relative movement in time. The calculation of the TLCC time-lagged cross-correlation coefficient is a well-known technology and will not be elaborated in this application. The value range of the lag order is 1 to d, where d is the number of acquisition moments.

[0062] In order to evaluate the attenuation of the optical network of each fiber span at different acquisition times, the hysteresis attenuation factor of each fiber span at each acquisition time is expressed as follows:

[0063]

[0064] Among them, TDY i t is the hysteresis attenuation factor of the ith optical fiber span at the tth acquisition time, is the i-1th fiber span at the t-τth i The optical power at each acquisition moment, LP i t is the optical power of the ith fiber span at the tth acquisition time, τ i is the attenuation lag time of the i-th optical fiber span.

[0065] It should be noted that the optical powers of two adjacent optical fiber spans at different acquisition times are matched by the attenuation lag time. The greater the difference in optical power between a fiber span and the adjacent previous fiber span at the corresponding acquisition time, the greater the attenuation of the optical power of the fiber span at the corresponding acquisition time, and the greater the lag attenuation factor value.

[0066] Furthermore, the hysteresis attenuation factors of each optical fiber span at all acquisition moments are arranged in ascending order according to the time sequence of acquisition to serve as the hysteresis attenuation sequence of each optical fiber span.

[0067] Step S3: Calculate the line attenuation anomaly score of each optical fiber span based on the attenuation lag time and link length of all optical fiber spans, obtain the corresponding attenuation modal components based on the modal decomposition result of each delayed attenuation sequence, calculate the corresponding unconventional attenuation evolution index based on the difference between each attenuation modal component and the corresponding fitting result, and obtain the abnormal attenuation span based on the line attenuation anomaly score of all optical fiber spans and the unconventional attenuation evolution index of all attenuation modal components.

[0068] Fiber loss can be divided into intrinsic loss and additional loss. Additional loss includes microbending loss, bending loss and splicing loss, while intrinsic loss includes scattering loss, absorption loss and loss caused by imperfect fiber structure. The attenuation of optical network caused by conventional loss between light spans is roughly the same.

[0069] Specifically, the abnormal degree of attenuation of each optical fiber span is evaluated based on the attenuation lag time and link length of all optical fiber spans, and the ratio of the attenuation lag time of each optical fiber span to the corresponding link length is recorded as the line attenuation ratio of each optical fiber span. The line attenuation ratios of all optical fiber spans are used as the input of the anomaly detection algorithm, and the line attenuation anomaly score of each optical fiber span is output.

[0070] It should be noted that the anomaly detection algorithm is a well-known technology. This embodiment selects the isolated forest anomaly detection algorithm to perform anomaly detection on the line attenuation ratio of all optical fiber spans. The selection of the anomaly detection algorithm is other implementation methods that the implementer can choose at his own discretion, and this application does not impose any special restrictions on this.

[0071] Considering that optical signals are affected by many factors when transmitted in optical fibers, in order to improve the reliability of the analysis of the causes of optical network attenuation in each optical fiber span, the attenuation caused by different factors is analyzed separately. Specifically, the modal decomposition algorithm is used to decompose the delayed attenuation sequence of each optical fiber span into n attenuation modal components.

[0072] It should be noted that the modal decomposition algorithm is a well-known technology, and the number n of attenuation modal components of each optical fiber span is a preset value. In this embodiment, the VMD variational modal decomposition algorithm is selected to decompose the delayed attenuation sequence of each optical fiber span. The number of attenuation modal components of each optical fiber span is 6. The attenuation modal components of each optical fiber span represent the attenuation of the optical network caused by different factors. The algorithm of the modal decomposition algorithm and the number of attenuation modal components of each optical fiber span are other implementation methods that can be selected by the implementer, and this application does not impose any special restrictions on this.

[0073] Furthermore, the abnormality of each attenuation mode component of each optical fiber span is evaluated based on the difference between each attenuation mode component and the corresponding fitting result.

[0074] Specifically, a fitting algorithm is used to perform linear fitting on each attenuation modal component, and the attenuation fitting sequence of each attenuation modal component is output. The absolute value of the difference between each attenuation modal component and the corresponding attenuation fitting sequence is taken as the attenuation fitting difference sequence of each attenuation modal component, and the average value of all element values ​​in the attenuation fitting difference sequence of each attenuation modal component is taken as the unconventional attenuation evolution index of each attenuation modal component.

[0075] It should be noted that the fitting algorithm is a well-known technology. This embodiment selects the least square method to perform linear fitting on each attenuation mode component. As for the selection of the fitting algorithm, as other implementation methods, the implementer can select it at will, and this application does not impose any special restrictions on this. When the absolute value of the difference between the attenuation mode component and the corresponding attenuation fitting sequence is larger, it means that the fitting effect of the attenuation mode component is worse, the value of the unconventional attenuation evolution index is larger, the optical network attenuation caused by the factor represented by the attenuation mode component is more likely to be abnormal, and the attenuation of the optical network represented by the attenuation mode component is more likely to be caused by a fiber failure.

[0076] For details, see Figure 2 , Figure 2 It is a schematic diagram showing the acquisition of the unconventional attenuation evolution index in one embodiment of the present invention.

[0077] Furthermore, based on the linear relationship between the line attenuation anomaly score of each optical fiber span and the unconventional attenuation evolution index of all attenuation modal components, the attenuation deviation anomaly index of each optical fiber span is calculated.

[0078] It should be noted that, when the line attenuation anomaly score value of the optical fiber span is larger and the unconventional attenuation evolution index of each attenuation mode component is larger, it means that the attenuation of the optical network in the optical fiber span is more likely to be abnormal, and the attenuation deviation anomaly index value is larger.

[0079] As an embodiment of the present application, the attenuation deviation anomaly index of each optical fiber span is obtained by multiplying the average value of the unconventional attenuation evolution indexes of all attenuation mode components of each optical fiber span by the line attenuation anomaly score of each optical fiber span.

[0080] Furthermore, the attenuation deviation anomaly index of all optical fiber spans is normalized to obtain the attenuation deviation anomaly normalized index of each optical fiber span, and the optical fiber span whose attenuation deviation anomaly normalized index is greater than a preset anomaly threshold is taken as an abnormal attenuation span.

[0081] It should be noted that the preset abnormality threshold is a manually preset value. In this embodiment, the preset abnormality threshold is 0.5. As for the value of the preset abnormality threshold, as other implementation methods, the implementer can choose it at will, and this application does not impose any special restrictions on this.

[0082] Step S4: Calculate the attenuation deviation key factor of each attenuation modal component based on each attenuation modal component and the corresponding unconventional attenuation evolution index, and calculate the attenuation analysis key factor of each attenuation modal component based on the correlation degree between all attenuation modal components of each optical fiber span and the attenuation deviation key factor of all attenuation modal components.

[0083] Since different attenuation modal components represent different factors that cause optical network attenuation, and the degree of abnormality of optical network attenuation caused by different factors is also different, different weights should be set for different attenuation modal components when conducting a comprehensive analysis of the causes of optical network attenuation.

[0084] Specifically, the average value of all element values ​​of each attenuation modal component is taken as the stage attenuation value of each attenuation modal component, and the attenuation offset key factor of each attenuation modal component is calculated based on the linear relationship between the stage attenuation value of each attenuation modal component and the corresponding unconventional attenuation evolution index.

[0085] It should be noted that the larger the stage attenuation value of the attenuation modal component and the larger the value of the unconventional attenuation evolution index, the more serious the optical network attenuation caused by the factors represented by the attenuation modal component and the more likely an abnormality has occurred. When analyzing the attenuation of the optical network, more attention should be paid to the attenuation modal component, and the larger the value of the attenuation offset key factor.

[0086] As an embodiment of the present application, the stage attenuation value of each attenuation modal component is added to the corresponding unconventional attenuation evolution index as the corresponding attenuation offset key factor.

[0087] Furthermore, the correlation between each attenuation modal component and the remaining attenuation modal components is analyzed, and the average value of the Pearson correlation coefficient between each attenuation modal component of each light span and the remaining attenuation modal components of the corresponding light span is taken as the attenuation offset correlation index of each attenuation modal component of each light span.

[0088] It should be noted that the calculation of the Pearson correlation coefficient is a well-known technology and is not elaborated in this embodiment. The higher the correlation between the attenuation modal component and the other attenuation modal components, the more likely it is that the optical network attenuation caused by the factor represented by the attenuation modal component will cause optical network attenuation caused by other factors, and the larger the attenuation offset correlation index value.

[0089] Based on the linear relationship between the attenuation shift key factor of each attenuation modal component and the corresponding attenuation shift correlation index, the attenuation analysis key factor of each attenuation modal component is calculated.

[0090] It should be noted that the key factors of attenuation analysis of attenuation modal components are used to evaluate the degree of attention paid to attenuation modal components when analyzing the attenuation causes of optical networks. The more severe the attenuation of the optical network, the more likely it is that anomalies will occur, and the more highly correlated with other attenuation factors, the more attention should be paid to the attenuation factors.

[0091] As an embodiment of the present application, the sum of the attenuation shift key factor of each attenuation modal component and the corresponding attenuation shift correlation index is used as the corresponding attenuation analysis key factor.

[0092] Step S5: Based on the correlation between each attenuation modal component and each environmental change time series and the unconventional attenuation evolution index of each attenuation modal component, the non-exogenous attenuation confidence index of each attenuation modal component is obtained; based on the non-exogenous attenuation confidence index of all attenuation modal components of each abnormal attenuation span and the attenuation analysis key factors, the cause of optical network attenuation in each abnormal attenuation span is obtained.

[0093] The average value of the Pearson correlation coefficient between each attenuation modal component and all environmental change time series plus the preset adjustment factor is taken as the exogenous correlation factor of each attenuation modal component, and the ratio of the unconventional attenuation evolution index of each attenuation modal component and the corresponding exogenous correlation factor is taken as the non-exogenous attenuation confidence index of each attenuation modal component.

[0094] It should be noted that the non-external attenuation confidence index is used to evaluate the possibility that the attenuation of the attenuation mode component is caused by non-external factors. The larger the unconventional attenuation evolution index of the attenuation mode component and the smaller the Pearson correlation coefficient between the attenuation mode component and the environmental change time series, the less likely it is that the abnormal attenuation of the optical network represented by the attenuation mode component is caused by external environmental factors, and the larger the non-external attenuation confidence index value is.

[0095] Furthermore, the attenuation analysis key factors of all attenuation modal components of each abnormal attenuation span are normalized to obtain the attenuation analysis weight of each attenuation modal component of each abnormal attenuation span. The product of the non-exogenous attenuation confidence index of each attenuation modal component and the corresponding attenuation analysis weight is used as the weighted non-exogenous attenuation confidence index of each attenuation modal component, and the average value of the weighted non-exogenous attenuation confidence index of all attenuation modal components of each abnormal attenuation span is used as the fiber fault attenuation confidence index of each abnormal attenuation span. Each fiber fault attenuation confidence index is normalized to obtain the normalized fiber fault attenuation confidence index of each abnormal attenuation span.

[0096] It should be noted that the sum of the attenuation analysis key factors of all attenuation modal components of each abnormal attenuation span is 1. Different weights are set for each attenuation modal component according to the severity of attenuation, the degree of abnormality, and the degree of correlation with other attenuation modal components, thereby improving the accuracy of the analysis of the causes of optical network attenuation.

[0097] When the normalized fiber fault attenuation confidence index of the abnormal attenuation span is greater than the preset fault threshold, the optical network attenuation cause of the abnormal attenuation span is determined to be a fiber fault; otherwise, the optical network attenuation cause of the abnormal attenuation span is determined to be normal attenuation.

[0098] It should be noted that the preset fault threshold is a manually preset value. In this embodiment, the preset fault threshold is 0.7. As for the value of the preset fault threshold, as other implementation methods, the implementer can choose it at will, and this application does not impose any special restrictions on this.

[0099] Yet another embodiment of the present invention provides an optical network attenuation analysis system suitable for long-distance transmission, the system comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the optical network attenuation analysis method suitable for long-distance transmission as described above.

[0100] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. An optical network attenuation analysis method suitable for long-distance transmission, characterized in that: The method comprises: Collecting environmental parameters at each collection time, the link length of each optical fiber span in the optical network, and the optical power of each optical fiber span in the optical network at each collection time, and constructing each environmental change time series and the optical power time series of each optical fiber span; Calculating the attenuation lag time of each optical fiber span based on the correlation hysteresis characteristics between the optical power time series of adjacent optical fiber spans, and constructing a hysteresis attenuation sequence of each optical fiber span based on the correlation difference of the optical powers of adjacent optical fiber spans and each attenuation lag time; Obtaining corresponding decay modal components based on the modal decomposition result of each of the hysteresis decay sequences, and calculating corresponding unconventional decay evolution indexes based on the difference between each of the decay modal components and the corresponding fitting result; Acquire an abnormal attenuation span based on all the attenuation hysteresis durations, all the link lengths, and all the unconventional attenuation evolution indices; Calculating a corresponding attenuation shift key factor based on each of the attenuation modal components and the corresponding unconventional attenuation evolution index, and calculating an attenuation analysis key factor of each of the attenuation modal components based on the correlation between all of the attenuation modal components and each of the attenuation shift key factors; Based on the correlation degree between each attenuation modal component and each of the environmental change time series and each of the unconventional attenuation evolution indexes, the non-exogenous attenuation confidence index of each attenuation modal component is obtained; based on all of the non-exogenous attenuation confidence indices and all of the attenuation analysis key factors, the cause of optical network attenuation in each abnormal attenuation span is obtained.

2. The optical network attenuation analysis method suitable for long-distance transmission according to claim 1, characterized in that: The step of constructing a delayed attenuation sequence for each optical fiber span based on the correlation difference of the optical powers of adjacent optical fiber spans and each attenuation delay time comprises: The hysteresis attenuation factor of each optical fiber span at each acquisition time is calculated based on the correlation difference characteristics of the optical power of two adjacent optical fiber spans: Among them, TDY i t is the hysteresis attenuation factor of the ith optical fiber span at the tth acquisition time, is the i-1th fiber span at the t-τth i The optical power at each acquisition moment, is the optical power of the ith fiber span at the tth acquisition time, τ i is the attenuation lag time of the i-th optical fiber span; The hysteresis attenuation factors of each optical fiber span at all acquisition moments are arranged in ascending order according to the time sequence of acquisition, as the hysteresis attenuation sequence of each optical fiber span.

3. The optical network attenuation analysis method suitable for long-distance transmission according to claim 1, characterized in that: The calculating the attenuation lag time of each optical fiber span based on the correlation hysteresis characteristics between the optical power time series of adjacent optical fiber spans comprises: The maximum value of the TLCC time lag correlation coefficient between the optical power time series of each optical fiber span and the optical power time series of the adjacent previous optical fiber span at all lag orders is taken as the signal attenuation correlation coefficient between each optical fiber span and the adjacent previous optical fiber span, and the lag order corresponding to the signal attenuation correlation coefficient is taken as the attenuation lag duration of each optical fiber span.

4. The optical network attenuation analysis method suitable for long-distance transmission according to claim 1, characterized in that: The calculating the corresponding unconventional attenuation evolution index based on the difference between each of the attenuation modal components and the corresponding fitting result comprises: Perform linear fitting processing on each of the attenuation modal components to obtain the attenuation fitting sequence of each of the attenuation modal components, take the absolute value of the difference between each of the attenuation modal components and the corresponding attenuation fitting sequence as the attenuation fitting difference sequence of each of the attenuation modal components, and take the average value of all element values ​​in each of the attenuation fitting difference sequences as the unconventional attenuation evolution index of the corresponding attenuation modal component.

5. The optical network attenuation analysis method suitable for long-distance transmission according to claim 1, characterized in that: The specific method of obtaining the abnormal attenuation span based on all the attenuation hysteresis durations, all the link lengths and all the unconventional attenuation evolution indexes includes: Record the ratio of the attenuation lag time of each optical fiber span to the corresponding link length as the corresponding line attenuation ratio, use the line attenuation ratios of all the optical fiber spans as inputs of anomaly detection algorithms, and output the line attenuation anomaly score of each optical fiber span; Based on the linear relationship between the line attenuation anomaly score of each optical fiber span and all corresponding unconventional attenuation evolution indices, the attenuation deviation anomaly index of each optical fiber span is calculated; All the attenuation offset anomaly indexes are normalized to obtain the attenuation offset anomaly normalized index of each light span, and the light span whose attenuation offset anomaly normalized index is greater than a preset anomaly threshold is taken as an abnormal attenuation span.

6. The optical network attenuation analysis method suitable for long-distance transmission according to claim 1, characterized in that: The specific method of calculating the corresponding attenuation deviation key factor based on each of the attenuation modal components and the corresponding unconventional attenuation evolution index includes: Taking the average value of all element values ​​of each of the decaying modal components as the stage attenuation value of each of the decaying modal components; Based on the linear relationship between the stage attenuation value of each attenuation modal component and the corresponding unconventional attenuation evolution index, the attenuation deviation key factor of each attenuation modal component is calculated.

7. The optical network attenuation analysis method suitable for long-distance transmission according to claim 1, characterized in that: The calculating of the attenuation analysis key factor of each attenuation modal component based on the correlation degree between all the attenuation modal components and each attenuation offset key factor comprises: taking the average value of the Pearson correlation coefficients between each of the attenuation modal components and the remaining attenuation modal components of the corresponding light span as the attenuation shift correlation index of each of the attenuation modal components of each of the light spans; Based on the linear relationship between each of the attenuation shift key factors and the corresponding attenuation shift correlation index, the attenuation analysis key factor of each of the attenuation modal components is calculated.

8. The optical network attenuation analysis method suitable for long-distance transmission according to claim 1, characterized in that: The step of obtaining the non-exogenous attenuation confidence index of each attenuation mode component based on the correlation between each attenuation mode component and each of the environmental change time series and each of the unconventional attenuation evolution indexes includes: The average value of the Pearson correlation coefficient between each of the attenuation mode components and all the environmental change time series plus a preset parameter adjustment factor is used as the external cause correlation factor of each of the attenuation mode components; The ratio of each of the unconventional attenuation evolution indexes to the corresponding external cause correlation factor is used as the non-external attenuation confidence index of each attenuation modal component.

9. The optical network attenuation analysis method suitable for long-distance transmission according to claim 1, characterized in that: The obtaining of the optical network attenuation cause of each abnormal attenuation span based on all the non-external attenuation confidence indexes and all the attenuation analysis key factors includes: Normalizing the attenuation analysis key factors of all the attenuation modal components of each abnormal attenuation span to obtain the attenuation analysis weight of each attenuation modal component of each abnormal attenuation span, wherein the sum of all the attenuation analysis key factors of each abnormal attenuation span is 1; The product of the non-exogenous attenuation confidence index of each attenuation modal component and the corresponding attenuation analysis weight is used as the weighted non-exogenous attenuation confidence index of each attenuation modal component, the average value of all the weighted non-exogenous attenuation confidence indexes of each abnormal attenuation span is used as the fiber fault attenuation confidence index of each abnormal attenuation span, and each fiber fault attenuation confidence index is normalized to obtain the normalized fiber fault attenuation confidence index of each abnormal attenuation span; When the normalized fiber fault attenuation confidence index is greater than a preset fault threshold, the optical network attenuation cause of the abnormal attenuation span is determined to be a fiber fault; otherwise, the optical network attenuation cause of the abnormal attenuation span is determined to be normal attenuation.

10. An optical network attenuation analysis system suitable for long-distance transmission, characterized in that: The system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, an optical network attenuation analysis method suitable for long-distance transmission as described in any one of claims 1 to 9 is implemented.

Images