WO2024034082A1 - Failure prediction device, failure prediction method, and failure prediction program - Google Patents

Abstract

In the present invention, upon detection of a predetermined optical path in which a quality value of an optical signal measured at a first time is less than a first threshold, the prediction server (SV) determines an abnormality level at the first time from a parameter measurement value of a photophysical property parameter that is measured at a point of passage of the predetermined optical path at the first time, and, when a correlation between the quality value of the optical signal obtained at the first time and the abnormality level obtained at the first time matches correlation data stored in a storage unit, the prediction server (SV) predicts that a sign of failure will occur in a sign detection part obtained from a point of measurement of the parameter measurement value at a time later than the first time.

Description

Failure prediction device, failure prediction method, and failure prediction program

The present invention relates to a failure prediction device, a failure prediction method, and a failure prediction program.

In the maintenance and operation of optical transmission systems, it is required to detect failures early and to identify the detected locations with high accuracy. Therefore, methods have been developed to automatically detect failures in optical transmission systems and identify the locations where they are detected.
Patent Document 1 discloses a method of narrowing down the range of suspected failure points based on upper layer packet loss information and the accommodation relationship of optical-channel data unit (ODU) paths.

Patent Document 2 describes how to determine the range of a suspected location based on the optical signal characteristics at the receiving end of an optical path such as an optical multiplex section (OMS) and the accommodation relationship of optical transport unit (OTU) paths. A method has been disclosed in which the search is narrowed down in units of optical paths and furthermore, a suspect location in this optical path is identified based on optical signal characteristics.

JP2018-64160A JP2020-88628A

Conventional techniques such as Patent Documents 1 and 2 do not use parameter measurement values for each relay section of the optical path, and are insufficient in narrowing down the failure detection range and in its detection accuracy. Therefore, we will consider detecting suspected failure points from parameter measurements for each relay section of the optical path.

For example, when determining that a parameter measurement value that has fluctuated more than the normal fluctuation width is determined to have a fluctuation, there may be many relay sections in which fluctuation is detected (for example, 90% of the relay sections have fluctuations). In that case, it is difficult to identify the failure location from those relay sections.
Note that even if no failure has occurred, fluctuations greater than the steady fluctuation range may occur. For example, when a maintenance worker temporarily touches a fiber, a disturbance occurs at the contact point, causing the measured parameter value to fluctuate instantaneously, but then recovers quickly. If such a false failure is erroneously detected as a failure location, unnecessary warnings will impede the maintenance work of maintenance personnel.

Therefore, the main objective of the present invention is to narrow down the failure detection range in an optical transmission system with high accuracy.

In order to solve the above problems, the failure prediction device of the present invention has the following features.
The present invention provides a failure prediction device including a storage unit and a control unit,
The storage unit stores the correlation between the quality value of the optical signal measured at the receiving end point of the optical path in the optical transmission system and the degree of abnormality for each type of optical physical property parameter measured at the passing point of the optical path. data is stored,
The control section,
When a predetermined optical path in which the quality value of the optical signal measured at the first time is less than the first threshold value is detected, the optical physical characteristic parameter measured at the passing point of the predetermined optical path at the first time is detected. Determining the degree of abnormality at the first time from the parameter measurement value,
When the correlation between the quality value of the optical signal at the first time and the degree of abnormality at the first time matches the correlation data stored in the storage unit, the parameter measurement value The present invention is characterized in that it is predicted that a failure sign will occur at a time later than the first time at the sign detection site determined from the measurement point.

According to the present invention, the detection range of failures in the optical transmission system can be narrowed down with high precision.

FIG. 1 is a configuration diagram of an optical transmission system and a prediction server according to the present embodiment. FIG. 2 is a hardware configuration diagram of the prediction server of FIG. 1 according to the present embodiment. FIG. 2 is a configuration diagram of the transponder and relay transmission device of FIG. 1 according to the present embodiment. 3 is a table showing the results of evaluating the presence or absence of fluctuations in parameter measurement values of the optical transmission system according to the present embodiment. 12 is a table showing the results of evaluating the deviation from the correlation line for the parameter measurement values of the optical transmission system according to the present embodiment. 2 is a flowchart illustrating an example of a procedure for operating the optical transmission system of FIG. 1 according to the present embodiment. It is a flowchart which shows the details of the failure prediction process of the prediction server regarding this embodiment. It is a graph which shows the correlation line between the degree of abnormality of parameter x and Q value regarding this embodiment. It is a graph which shows the correlation line between the degree of abnormality of parameter y and Q value regarding this embodiment. It is a time series graph showing an error prediction line when an error occurs according to the present embodiment. 7 is a graph showing an error prediction line when a false error occurs according to the present embodiment.

Hereinafter, each embodiment of the present invention will be described in detail with reference to the drawings.

FIG. 1 is a configuration diagram of an optical transmission system NW and a prediction server (failure prediction device) SV.
The optical transmission system NW includes transponders TS1, TS2, TR1, TR2, TR3, and TR4, and relay transmission devices WA, WB, WC, WD, WE, and WF.
A transponder is a logical transmission path through which optical signals pass, and is an optical path constructed as an optical-channel data unit (ODU) path and an optical transport unit (OTU) path (in Figure 1, an optical This is a device located at the start point or end point of path P1). Note that the optical path can also be constructed as one ODU path by combining a plurality of OTU paths using a 3R transponder, but in this case as well, fault isolation is performed for each minimum unit OTU path. In this embodiment, transponders TS1 and TS2 (the second character of the code is S) are the starting points of the optical path, and transponders TR1, TR2, TR3, and TR4 (the second character of the code is R) are the end points of the optical path. exemplify.

The relay transmission device is an optical cross connect (OXC) that relays optical signals along an optical path. In this embodiment, six relay transmission devices WA, WB, WC, WD, WE, and WF are connected to other adjacent relay transmission devices by links L1 to L6. For example, the optical path P1 includes, in order from the transmitting side, transponder TS2 → relay transmission device WA → link L1 → relay transmission device WB → link L4 → relay transmission device WC → link L6 → relay transmission device WD → transponder TR4 (receiving side) are connected by the route.

The prediction server SV predicts the optical transmission system NW by combining information indicating the impact on the communication service at the receiving end point and information indicating changes in the parts that are predictive of failure (predictive detection parts) through the following procedure. Identify signs of potential failures.
(Procedure 1) A failure that may occur in the optical path P1 is predicted based on the quality information at the time of signal reception notified from the transponder TR4, which is the receiving end point of the optical path P1. The quality information at the time of signal reception is information that indicates the impact on the communication service at the receiving end point.For example, the quality factor (unit: [dB]) indicates the optical signal quality of the optical path, and the The lower the value, the higher the quality, and the lower the value, the lower the quality.
(Procedure 2) The sign detection site is identified from the parameter measurement values for each relay section of each relay transmission device WA, WB, WC, and WD through which the optical path P1 predicted in (Procedure 1) passes. Note that the parameter measurement value is a measurement value measured for each measurement point and for each type of parameter of photophysical characteristics (hereinafter referred to as "parameter type"). The parameter measurement value is information indicating a change in the sign detection site.

Therefore, the prediction server SV has a storage unit and a control unit, and the storage unit stores the quality value of the optical signal measured at the receiving end point of the optical path in the optical transmission system NW, and the Correlation data (hereinafter referred to as a correlation line) between the degree of abnormality of each type of photophysical property parameter measured at a point is stored.
Then, when the prediction server SV detects a predetermined optical path in which the quality value of the optical signal measured at the first time is less than the first threshold value, the prediction server SV detects the quality value of the optical signal measured at the passing point of the predetermined optical path at the first time. The degree of abnormality at the first time is determined from the parameter measurement value of the photophysical property parameter.
Furthermore, when the correlation between the quality value of the optical signal at the first time and the degree of abnormality at the first time matches the correlation data stored in the storage unit, the prediction server SV It is predicted that a failure sign will occur at a time after the first time at the sign detection site determined from the measurement point of the parameter measurement value.

FIG. 2 is a hardware configuration diagram of the prediction server SV of FIG. 1.
The prediction server SV is a computer 900 having a CPU (control unit) 901, a RAM 902, a ROM 903, an HDD (storage unit) 904, a communication I/F 905, an input/output I/F 906, and a media I/F 907. configured.
Communication I/F 905 is connected to external communication device 915. The input/output I/F 906 is connected to the input/output device 916. The media I/F 907 reads and writes data from the recording medium 917. Further, the CPU 901 controls each unit by executing a program (also referred to as an application) read into the RAM 902 . This program can also be distributed via a communication line or recorded on a recording medium 917 such as a CD-ROM.

FIG. 3 is a configuration diagram of the transponder TS2 and the relay transmission device WC of FIG. 1.
The transponder TS2 has a package 10 that accommodates an OTN (Optical Transport Network) framer 11, a DSP (Digital Signal Processor) 12, and an optical device 13.
The OTN framer 11 is an LSI (Large Scale Integration) that converts a data signal to be transmitted into a signal frame format of OTN, which is an optical transmission network.
The DSP 12 is an LSI that performs digital signal processing for signal conversion and correction for long-distance, large-capacity transmission, and monitors various analog information data used for conversion and correction processing at the receiving end point.
The optical device 13 transmits and receives optical signals.

The relay transmission device WC includes three packages WC1, WC2, and WC3, and an optical physical property monitor 21 connected to a port of each package.
Each package WC1, WC2, and WC3 includes an AMP (Amplifier) 22 and a WSS (Wavelength Selective Switch) 23, respectively.
The optical physical characteristic monitor 21 measures time-series data of analog information regarding the optical physical characteristics in the relay section of the optical signal as a parameter measurement value. The optical physical property monitor 21 is configured to, for example, provide optical spectrum information that represents an optical signal as light intensity with respect to wavelength or frequency, waveform symmetry of the optical signal that can be confirmed from the optical spectrum information, and the ratio of each optical signal to noise. Measures signal quality such as OSNR (Optical Signal to Noise Ratio).
AMP22 is an optical amplifier. WSS23 is a wavelength selective switch.

An overview of the process of predicting failure of the prediction server SV will be described below with reference to FIGS. 4 and 5.
FIG. 4 is a table showing the results of evaluating the presence or absence of fluctuations in the measured parameter values of the optical transmission system NW. The row elements of this table indicate each parameter (full wave power, etc.), and the column elements indicate the relay transmission device (relay transmission device WA, etc.) at the measurement point.
Here, in Figure 4, all of the (4 measurement points) x (4 parameter types) = 16 parameter measurement values are in a state where fluctuations greater than the steady fluctuation range have occurred (variation is "present" in the figure). It is had. In this case, it is difficult for the prediction server SV to identify the failure location using the method of identifying the location where the parameter measurement value has changed as the sign detection location.

Note that the measurement point may be a device unit called a relay transmission device, or a component unit (for example, a package part) inside the relay transmission device. For example, the relay transmission device WC in FIG. 3 accommodates three packages WC1 to WC3, and the points of contact between each package and the outside (circles in FIG. 3) are the measurement points. As a result, nine measurement points are provided within one relay transmission device WC.
Further, the sign detection portion may be a device unit called a relay transmission device, or may be a component unit inside the relay transmission device.

FIG. 5 is a table showing the results of evaluating the deviation from the correlation line for the parameter measurement values of the optical transmission system NW.
The correlation line is a graph line (see FIG. 8 for details) that shows the correlation between the Q value of the optical path and the degree of abnormality (hereinafter referred to as "degree of abnormality") of the measured parameter value. For example, in FIG. 4, (4 types of measurement points) x (4 types of parameter types) = 16 types of correlation lines are prepared in advance.
In addition, the degree of abnormality is an indicator that the larger the value, the more the area where the parameter measurement value is measured deviates from the normal state, and the larger the deviation from the normal value of the parameter measurement value, the higher the degree of abnormality. value. The degree of abnormality may be calculated not only from the deviation of each parameter from its normal value, but also from the frequency with which each parameter deviates from its normal value in a certain unit time.
In addition, when a parameter measurement value is input, an abnormality evaluation function that outputs the abnormality degree is prepared in advance for each parameter type, and the prediction server SV calculates the abnormality evaluation function to calculate the abnormality degree for each parameter measurement value. Evaluate the degree of abnormality.

First, the row elements and column elements of the table of FIG. 5 are the same as those of the table of FIG. 4. However, in Figure 4, the values in the table for each combination of row elements and column elements are ``presence or absence of variation in parameter measurement values'', but in Figure 5, ``parameter measurement values do not correspond to the correlation line determined in advance.''"Are they divergent or consistent?"
For example, in the table of FIG. 5, the value in the table indicates "match" only for the parameter type "OSNR (Optical Signal to Noise Ratio)" measured by the relay transmission device WB. Thereby, the prediction server SV evaluates the cause of failure (failure sign) related to the OSNR at the sign detection part=relay transmission device WB using the correlation line.

Therefore, the prediction server SV creates a correlation line in advance based on the relationship between the Q value of the optical path and the parameter type. The process of creating the correlation line is executed by the prediction server SV based on, for example, data acquisition using a failure simulation system or a QoT simulator (such as Gnpy) in advance. Acquiring data in a failure simulation system means, for example, acquiring data of parameter measurement values obtained by simulating a failure simulation pattern exemplified below.
・Decrease in output of AMP22 or WSS23 (decrease in single wave power or total wavelength power)
・Increase the output of AMP22 or WSS23 (increase in 1 wave power or all wavelength power)
・WSS23 filter abnormality (disturbance of waveform symmetry)
・AMP22 noise abnormality (OSNR decrease)

FIG. 6 is a flowchart illustrating an example of a procedure for operating the optical transmission system NW of FIG. 1.
The communication carrier prepares a core/metro network system to which an optical cross-connect (OXC) configuration is applied as the optical transmission system NW shown in FIG. 1 (S101).
The optical transmission system NW detects an optical path with degraded signal quality and notifies the prediction server SV of the detection result (S102). S102 is a process in which the transponder TR4 detects the deterioration of the Q value of the optical path P1, for example, as described in (procedure 1) of FIG. 1.
As explained in (Step 1) and (Step 2) in FIG. 1, the prediction server SV predicts a failure in the optical transmission system NW from the optical path detected in S102 (S103, details in FIG. 7).
The prediction server SV notifies a maintenance terminal operated by a maintenance worker of the communication carrier of the failure prediction result obtained in S103 (portion where the sign is detected and failure occurrence time) (S104).
After receiving the notification in S104, the maintenance staff performs preventive maintenance against the failure by switching routes and replacing the failed section (S105).

FIG. 7 is a flowchart showing details of the failure prediction process (S103) of the prediction server SV. This flowchart starts from a normal state in which no failure has occurred in the optical transmission system NW.
The prediction server SV determines whether the Q value of the optical path notified in S102 is less than the sign detection threshold (FIG. 8) (S11, details are shown in FIGS. 8 and 9). If Yes in S11, proceed to S12. If No in S11, the Q value of the optical path is good, so the process returns to the determination in S11 again.
The prediction server SV checks whether the parameter measurement value measured at the measurement point through which the optical path has passed and the correlation line of the parameter type match by brute force as shown in the table of FIG. The sign detection area is extracted based on the parameter measurement values of the matched area (S12). For example, in FIG. 5, only the relay transmission device WB is “matched”, so the sign detection part=the relay transmission device WB.

On the other hand, when there are a plurality of matching locations in S12, the prediction server SV specifies the sign detection location based on the one with the highest accuracy from the multiple locations and parameters. Among the multiple locations that match in S12, the upstream (starting point side) has the highest accuracy; for example, in the order in which the optical path P1 passes, relay transmission device WA "deviation" → relay transmission device WB "deviation" → relay transmission device WC ""match" → relay transmission device WD If "match", the prediction server SV sets the most upstream (starting point side) position (relay transmission device WC) of the matching locations (relay transmission devices WC, WD) as the sign detection location. do.
In addition, there is a causal relationship between parameter changes, and the location where the parameter that causes the change in the cause and effect of the parameter change is highly accurate. For example, if the full-wave power or single-wave power fluctuates, the OSNR of the subsequent stage will fluctuate, so if both parameters match, the location where the full-wave power or single-wave power fluctuates is determined to be the sign detection location.
As a result, the prediction server SV evaluated the predictive detection site that may be a cause of failure based on the distribution of coincidence or deviation between the measured parameter value and the correlation line.

The prediction server SV identifies the light path with the minimum margin that passes through the sign detection site among the light paths detected by Yes in S11 (S21). The "margin" is the difference between the measured Q value of the optical path and an error occurrence boundary (FEC (Forward Error Correction) Limit) that is smaller than the Q value.
In other words, if there are multiple optical paths on the same path or sharing part of the path in which Q-factor degradation has been detected, the prediction server SV selects the Q-value of the optical path with the minimum margin that is considered to generate an error first. Pay attention. Note that since the optical path changes over time due to additions or subtractions, it is desirable to execute the process (S21) for identifying the optical path with the minimum margin each time the optical path changes.

The prediction server SV acquires the Q value for the optical path with the minimum margin in S21 and the parameter measurement value at the omen detection site extracted in S12 as a measurement pair every measurement period (t seconds) (S22). . The prediction server SV predicts the failure occurrence time by predicting the tendency of deterioration over time as an error prediction line from the measurement pair acquired in S22 (S23, details are shown in FIG. 10).

Similar to S22, the prediction server SV obtains measurement pairs for the optical path with the minimum margin (S31). The prediction server SV determines whether the influence of the failure indicated by the measurement pair acquired in S31 matches the error prediction line (S32, details in FIG. 11). If Yes in S32, the process advances to S33, and if No in S32, the notification in S34 is canceled as a false error and the process returns to the determination in S11. A false error is an event in which a failure was initially predicted, but the failure was subsequently recovered from the predicted condition. Thereby, the prediction server SV can prevent erroneous detection due to the coincidence determination with the error prediction line (S32).

The prediction server SV determines whether the current time is z days before the error occurrence time (z=notification threshold) (S33). If Yes in S33, proceed to S34; if No in S33, return to S31. The prediction server SV notifies the maintenance terminal of the maintenance worker of the failure prediction result at the sign detection site (S34).
In addition, the prediction server SV calculates the correlation line used in S12 and the error prediction line used in S32 based on the feedback (correctness) of the prediction result from the maintenance terminal of the maintenance worker who has notified the failure prediction result. It may be updated (S35). That is, the prediction server SV notifies the maintenance terminal of the maintenance worker of the prediction of a failure at the sign detection site and the prediction of the failure occurrence time before the failure occurrence time. Then, the prediction server SV obtains the correctness of the prediction based on the feedback information responded from the maintenance terminal of the maintenance worker after the failure occurrence time, and based on the obtained correctness of the prediction, the prediction server SV calculates the correlation stored in the storage unit. Update relationship data. The prediction server SV updates the error prediction data from information on the time-series change relationship of the measured and accumulated Q value and abnormality degree, which is stored in the storage unit together with the correlation data.
Thereby, the precision of the correlation line and the precision of the error prediction line can be improved.

FIG. 8 is a graph showing a correlation line between the degree of abnormality of the parameter x and the Q value.
The prediction server SV regards the combination <E, Q> of the degree of abnormality (E) of parameter type = x (for example, full wave power) and the Q value (Q) of the optical path as a measurement pair measured at the same time. . In FIG. 8, it is assumed that the following measurement pairs are obtained by two measurements.
- First measurement pair p1<E1,Q1>. However, Q1 is the normal average value.
- Second measurement pair p2<E2, Q2>. However, Q2 is the sign detection threshold of S11.
Since both of the two measurement pairs p1 and p2 are located on or near the correlation line Qf1, the prediction server SV determines in S12 that the parameter measurement value matches the correlation line at this stage. Note that the threshold may be adjusted to a neighborhood range that allows deviation from the correlation line that is determined to be a match.

FIG. 9 is a graph showing a correlation line between the degree of abnormality of the parameter y and the Q value.
As in FIG. 8, the prediction server SV regards the combination <E, Q> of the abnormality degree of parameter type = y (for example, 1-wave power) and the Q value of the optical path as a measurement pair measured at the same time. . In FIG. 9, it is assumed that the following measurement pairs are obtained by two measurements.
- First measurement pair p3<E3, Q3>. However, Q3 is the normal average value.
- Second measurement pair p4<E4,Q4>. However, Q4 is the sign detection threshold of S11.
Since the measurement pair p4<E4, Q4> is not located at or near the point <E5, Q4> on the correlation line Qf2, the prediction server SV detects that the parameter measurement value deviates from the correlation line at this stage. It is determined in S12. Note that the threshold may be adjusted to a neighborhood range that allows deviation from the correlation line that is determined to be a match.

FIG. 10 is a time series graph showing an error prediction line when an error occurs.
In Figure 10, the vertical axis of the upper graph is the Q value (same as the vertical axis of Figures 8 and 9), and the lower graph is the degree of abnormality by parameter (same as the horizontal axis of Figures 8 and 9). , the upper and lower graphs are associated with the same time axis. Also, on the time axis, times t1, t2, t3, and t4 are times in the past when measurement pairs (indicated by triangle icons) have already been measured, and time t5 is a time in the future when no measurement pairs have been measured yet. be. The prediction server SV acquires measurement pairs multiple times (four times in total in FIG. 10) for the parameter measurement values that match the correlation line as shown in FIG. 8, even after the third time.
Below, in two methods (method using the upper graph in Figure 10 and method using the lower graph), the error occurrence boundary (error boundary threshold) is calculated by predicting the deterioration, and the time at which the error occurrence boundary is reached. The processing of the prediction server SV that predicts the failure occurrence time will be explained.

In the upper graph of FIG. 10, the prediction server SV, for example, extends the solid line of the graph with the same slope based on the trend of the measured Q value (the solid line connecting the triangular icons in FIG. 10). By doing so, an error prediction line Ef1 is created. The prediction server SV then predicts the timing of error occurrence according to the degree of quality deterioration of the optical path with the minimum margin that passes through the sign detection site. Specifically, the prediction server SV predicts the time t5 at which the error prediction line Ef1 falls below the threshold of the Q value at which the error occurs (error boundary threshold Q9) as the failure occurrence time.

That is, the prediction server SV measures the quality value of the optical signal at the reception end point of a predetermined optical path multiple times in a period after the first time t2 (times t3 to t4). The prediction server SV determines a second time at which the quality value of the optical signal is predicted to be less than the second threshold (error boundary threshold Q9) based on the time-series change relationship of the measured quality value of the optical signal over time. The time t5 is predicted as the failure occurrence time at the sign detection part.
In this way, a time-series change relationship exists between the change in the Q value and the change in time. Therefore, the time at which the failure occurs can be predicted based on the time t5 at which the quality (Q value) of the received signal of the optical path reaches its limit. For example, the time-series change relationship can be predicted by drawing an approximate line from the measured values up to t4. Alternatively, it can also be predicted from the time-series change relationship of Q values of the same configuration that have been measured and accumulated in the past. For prediction from past measurement data, statistical methods or machine learning may be used. In this embodiment, a case is described in which it is predicted to be linear, but the time-series change relationship does not have to be linear.

In the lower graph of FIG. 10, the prediction server SV uses, for example, the solid line of the graph to change the slope as it is, based on the trend of the measured abnormality degree (in FIG. 10, the solid line connecting the triangular icons). By extending, an error prediction line Ef2 is created. Then, the prediction server SV predicts the time of error occurrence according to the degree of progress of the degree of abnormality of the sign detection site. Specifically, the prediction server SV may predict the time t6 at which the error prediction line Ef1 exceeds the abnormality degree threshold (error boundary threshold E9) at which the error borders, as the failure occurrence time. Note that E1=normal average value of the degree of abnormality, and E2=predictive detection threshold of the degree of abnormality.

That is, the prediction server SV measures the parameter measurement value at the omen detection site multiple times in a period after the first time t2 (times t3 to t4). The prediction server SV sets the degree of abnormality at the sign detection site to a third threshold (error boundary threshold E9) based on the time-series change relationship over time of the degree of abnormality obtained from the measured parameter values at the measured sign detection site. ) is predicted as the failure occurrence time t6 at the sign detection site. For example, the time-series change relationship can be predicted by drawing an approximate line from the measured values up to t4. Alternatively, prediction can be made from the time-series change relationship of abnormalities of the same parameters and the same configuration that have been measured and accumulated in the past. For prediction from past measurement data, statistical methods or machine learning may be used. In this embodiment, a case is described in which it is predicted to be linear, but the time-series change relationship does not have to be linear.
In this way, a time-series change relationship exists between the change in the degree of abnormality and the change in time. Therefore, as shown in FIG. 8, the time at which a failure occurs can be predicted based on the time t6 at which the degree of abnormality measured at the sign detection site that coincides with the correlation line reaches its limit. Furthermore, since the degree of abnormality is an element directly linked to the failure that has occurred, it is possible to improve accuracy compared to prediction based only on the Q value. Further, although the Q value deteriorates along the predicted time-series change relationship, there is a possibility that the degree of abnormality does not deteriorate along the time-series change relationship. In this case, it is possible that the part extracted from the initially matched correlation may have deviated and another part may match the correlation, so check the correlation of each parameter measurement value on the optical path again. It is possible to switch to failure prediction for the following parts.

FIG. 11 is a graph showing an error prediction line when a false error occurs. A false error is one in which the failure time was predicted, but the failure did not actually occur.
In FIGS. 10 and 11, the axes of the two upper and lower graphs and the measurement pairs up to time t4 are common. On the other hand, in FIG. 11, after time t4, the situation of the measurement pair improves, the Q value of the measurement pair increases (the actual measurement line Ef1a of the Q value slopes upward to the right), and the degree of abnormality of the measurement pair decreases ( The actual measurement line Ef2a of the degree of abnormality slopes downward to the right). Note that the actual measurement line Ef1a of the Q value indicates the relationship between the change in the Q value and the change in time. Furthermore, the actual measurement line Ef2a of the degree of abnormality shows the relationship between the change in the degree of abnormality and the change in time.
One example of the cause of instantaneous improvement in the measurement pair is that a maintenance worker temporarily comes into contact with the optical fiber (fiber touch). On the other hand, examples of failures occurring without improvement in the Q value include failures such as noise deterioration of the AMP 22, filter failure of the WSS 23, and output control failure of the optical device 13.

In the graph in the upper part of FIG. 11, the prediction server SV predicts the sign of failure (failure sign) predicted at time t4 according to the deviation between the actual Q value measured line Ef1a and the Q value error prediction line Ef1 after time t4. (time of occurrence) and determines that no failure has occurred.
That is, after predicting the failure occurrence time, the prediction server SV subsequently measures the quality value of the optical signal at the receiving end point of the predetermined optical path. The prediction server SV detects that the time-series change relationship (actual measurement line Ef1a) of the quality value of the measured optical signal over time deviates from the time-series change relationship (error prediction line Ef1) at the time when the failure occurrence time is predicted. If the deviation occurs (for example, if the difference in slope between the two lines is 60 degrees or more), or if the quality value of the measured optical signal recovers to the first threshold value (Q2) or higher, a failure occurs at the predictive detection part. and the prediction of the failure occurrence time at the second time t5 are canceled.

In the graph on the lower side of FIG. 11, the prediction server SV detects a sign of failure (failure (occurrence time) and determine that no failure has occurred.
That is, after predicting the failure occurrence time, the prediction server SV continues to measure the parameter measurement value at the sign detection site. The prediction server SV determines whether the time-series change relationship (actual measurement line Ef2a) of the degree of abnormality over time obtained from the measured parameter measurement values is based on the time-series change relationship (error prediction line Ef2) at the time when the failure occurrence time is predicted. If the two lines deviate from each other (for example, if the difference in slope between the two lines is 60 degrees or more), the prediction of the failure at the sign detection site and the prediction of the failure occurrence time at the third time t6 are canceled.
Note that the failure observation period until the failure occurrence time prediction is canceled is, for example, from time t2 when the Q value becomes less than the sign detection threshold in FIG. This is the period until the maintenance terminal is notified. This can reduce the influence of false errors.

[effect]
In the present invention, the prediction server SV has a storage unit and a control unit,
The storage unit stores the correlation between the quality value of the optical signal measured at the receiving end point of the optical path in the optical transmission system NW and the degree of abnormality for each type of optical physical property parameter measured at the passing point of the optical path. The data (correlation line) is stored,
The control unit is
Parameter measurement of optical physical property parameters measured at a passing point of a predetermined optical path at a first time when a predetermined optical path whose quality value of the optical signal measured at the first time is less than a first threshold is detected. Find the degree of abnormality at the first time from the value,
If the correlation between the quality value of the optical signal at the first time and the degree of abnormality at the first time matches the correlation data stored in the storage unit, from the measurement point of the parameter measurement value The present invention is characterized in that it is predicted that a failure sign will occur at a time after the first time in the determined sign detection site.

This takes into account the correlation between changes in the quality value of the optical signal and changes in the measured parameter values. Therefore, compared to a method in which only changes in parameter measurement values are observed, the detection range of failures in the optical transmission system can be narrowed down to the predictive detection parts with high precision.

The present invention provides a control unit that measures the quality value of an optical signal at a receiving end point of a predetermined optical path multiple times in a period after a first time, and determines when the quality value of the measured optical signal changes over time. The present invention is characterized in that a second time at which the quality value of the optical signal is predicted to be less than a second threshold is predicted as the failure occurrence time at the sign detection site based on the sequence change relationship.

As a result, the time at which the quality value (Q value) of the optical signal reaches its limit can be predicted as the failure occurrence time.

In the present invention, after predicting the failure occurrence time, the control unit continues to measure the quality value of the optical signal at the receiving end point of a predetermined optical path, and the time-series change in the quality value of the measured optical signal over time. If the relationship deviates from the time-series change relationship at the time when the failure occurrence time was predicted, or if the quality value of the measured optical signal recovers to the first threshold or higher, the failure prediction and The feature is that the prediction of the failure occurrence time at the second time is canceled.

As a result, the accuracy of failure prediction can be improved by appropriately excluding false errors such as fiber touch from failure prediction.

In the present invention, the control unit measures the parameter measurement value at the sign detection site multiple times in a period after the first time, and the degree of abnormality over time is determined from the parameter measurement value at the measured sign detection site. The present invention is characterized in that a third time at which the degree of abnormality at the precursor detection site is predicted to be less than a third threshold is predicted as the failure occurrence time at the precursor detection site based on the time-series change relationship.

With this, it is possible to predict the time at which the degree of abnormality at the sign detection site reaches its limit as the failure occurrence time.

In the present invention, after the control unit predicts the failure occurrence time, the control unit subsequently measures the parameter measurement value at the sign detection site, and the time-series change relationship of the abnormality degree obtained from the measured parameter measurement value over time is If the failure occurrence time deviates from the time-series change relationship at the predicted time, the prediction of the failure at the sign detection site and the prediction of the failure occurrence time at the third time are canceled.

As a result, the accuracy of failure prediction can be improved by appropriately excluding false errors such as fiber touch from failure prediction.

In the present invention, the control unit predicts a failure at a sign detection site and reports the prediction of the failure occurrence time to a maintenance worker's maintenance terminal before the failure occurrence time, and reports the prediction of the failure occurrence time to the maintenance worker's maintenance terminal after the failure occurrence time. The correctness of the prediction is obtained based on the feedback information responded from the maintenance terminal, and based on the obtained correctness of the prediction, the correlation data stored in the storage unit and the time-series change in the quality value of the optical signal over time are calculated. It is characterized by updating the relationship and the time-series change relationship over time of the degree of abnormality obtained from the parameter measurement values at the sign detection site.

This makes it possible to improve the accuracy of correlation data (correlation line), optical signal quality value, and time-series change prediction (error prediction line) of the degree of abnormality.

10 Package 11 OTN Framer 12 DSP
13 Optical device 21 Optical physical property monitor 22 AMP
23 WSS
L1 to L6 Link NW Optical transmission system SV Prediction server (failure prediction device)
TS1, TS1, TR1, TR2, TR3, TR4 Transponder WA, WB, WC, WD, WE, WF Relay transmission equipment

Claims (8)

1. The failure prediction device has a storage unit and a control unit,
   The storage unit stores the correlation between the quality value of the optical signal measured at the receiving end point of the optical path in the optical transmission system and the degree of abnormality for each type of optical physical property parameter measured at the passing point of the optical path. data is stored,
   The control unit includes:
   When a predetermined optical path in which the quality value of the optical signal measured at the first time is less than the first threshold value is detected, the optical physical characteristic parameter measured at the passing point of the predetermined optical path at the first time is detected. Determining the degree of abnormality at the first time from the parameter measurement value,
   When the correlation between the quality value of the optical signal at the first time and the degree of abnormality at the first time matches the correlation data stored in the storage unit, the parameter measurement value A failure prediction device, characterized in that it is predicted that a failure sign will occur at a time later than the first time in a sign detection part determined from a measurement point.
2. The control unit measures a quality value of an optical signal at a reception end point of a predetermined optical path multiple times in a period after the first time, and detects a time-series change in the quality value of the measured optical signal over time. The failure according to claim 1, characterized in that, based on the relationship, a second time at which the quality value of the optical signal is predicted to be less than a second threshold is predicted as the failure occurrence time at the sign detection part. Prediction device.
3. After predicting the failure occurrence time, the control unit subsequently measures the quality value of the optical signal at the receiving end point of the predetermined optical path, and determines the time-series change relationship of the measured quality value of the optical signal over time. If the failure occurrence time deviates from the time-series change relationship at the predicted time, or if the quality value of the measured optical signal recovers to the first threshold or more, the prediction of the failure at the sign detection part and the The failure prediction device according to claim 2, characterized in that the prediction of the failure occurrence time at the second time is canceled.
4. The control unit measures the parameter measurement value at the sign detection site multiple times in a period after the first time, and determines the degree of abnormality over time determined from the measured parameter measurement value at the sign detection site. A third time at which the degree of abnormality at the sign detection part is predicted to be less than a third threshold is predicted as the failure occurrence time at the sign detection part based on the time series change relationship according to The failure prediction device according to claim 1.
5. After predicting the failure occurrence time, the control unit continues to measure the parameter measurement values at the sign detection site, and determines that the time-series change relationship of the degree of abnormality over time determined from the measured parameter measurement values indicates the failure occurrence time. According to claim 4, when the time deviates from the time-series change relationship at the predicted time, the prediction of the failure at the sign detection part and the prediction of the failure occurrence time at the third time are canceled. The failure prediction device described.
6. The control unit notifies a maintenance terminal of a prediction of a failure at the sign detection part and a prediction of the time of failure occurrence before the failure occurrence time, and receives feedback information responded from the maintenance terminal after the failure occurrence time. The correctness of the prediction is obtained, and based on the obtained correctness of the prediction, the correlation data stored in the storage unit, the time-series change relationship over time of the quality value of the optical signal, and the predictive sign are determined. The failure prediction device according to claim 2, wherein the failure prediction device updates a time-series change relationship over time of the degree of abnormality determined from parameter measurements at the detection site.
7. The failure prediction device has a storage unit and a control unit,
   The storage unit stores the correlation between the quality value of the optical signal measured at the receiving end point of the optical path in the optical transmission system and the degree of abnormality for each type of optical physical property parameter measured at the passing point of the optical path. data is stored,
   The control unit includes:
   When a predetermined optical path in which the quality value of the optical signal measured at the first time is less than the first threshold value is detected, the optical physical characteristic parameter measured at the passing point of the predetermined optical path at the first time is detected. Determining the degree of abnormality at the first time from the parameter measurement value,
   When the correlation between the quality value of the optical signal at the first time and the degree of abnormality at the first time matches the correlation data stored in the storage unit, the parameter measurement value A failure prediction method, comprising predicting that a failure sign will occur at a time later than the first time at a sign detection site determined from a measurement point.
8. A failure prediction program for causing a computer to function as the failure prediction device according to any one of claims 1 to 6.

Images