Passive optical network weak light root cause positioning method, device, medium and product

Abstract

The embodiment of the invention relates to a passive optical network weak light root cause positioning method and device, a medium and a product. The method comprises the following steps: continuously collecting optical power data of each optical network unit under a passive optical network port, carrying out segmented statistics according to a preset interval to obtain optical power distribution characteristic data collected for multiple times, then carrying out division clustering on the characteristic data based on different clustering numbers, determining an optimal clustering number according to a contour coefficient, and finally obtaining the optical power distribution characteristic data according to the optimal clustering number. Then similar clusters are combined according to the Euclidean distance, fault root cause analysis is carried out, finally, the root cause corresponding to the cluster with the maximum sample number is used as a weak light fault positioning result of the port, traditional manual judgment is replaced by data-driven clustering analysis, and fault judgment does not need to be carried out by manually presetting a fixed threshold value. The passive optical network port weak light fault root cause can be actively, accurately and adaptively positioned, so that the weak light fault positioning accuracy and efficiency are improved.

Description

Technical Field

[0001] This application relates to the field of optical communication technology, and in particular to a method, device, medium and product for locating the root cause of weak light in a passive optical network. Background Technology

[0002] With the widespread deployment of passive optical networks (PONs), low light intensity in user-side optical network units has become a common network fault. Current mainstream methods for locating low light intensity typically rely on user complaints as a trigger, using single-shot optical power data combined with a preset fixed threshold (e.g., -27dBm) for fault diagnosis and rough localization. This approach has significant drawbacks: first, it relies on a single, fixed optical power threshold, which becomes less effective due to variations in actual equipment models and environments, leading to potential misjudgments; second, it operates on a passive response model and cannot support proactive network-wide inspections and early warning of potential problems. Therefore, existing technologies lack an effective means to proactively, accurately, and adaptively locate the root cause of low light intensity faults in PONs. Summary of the Invention

[0003] To address the aforementioned issues, embodiments of this application provide a method, device, medium, and product for locating the root cause of weak light in a passive optical network.

[0004] According to a first aspect of the embodiments of this application, a method for identifying the root causes of weak light in a passive optical network is provided, the method comprising: The optical power data of the optical network unit under the target port of the target passive optical network is collected multiple times within a continuous time period. The optical power data collected in each acquisition is segmented and statistically analyzed according to a preset optical power range to obtain the optical power distribution characteristic data corresponding to each acquisition. Based on multiple different preset cluster numbers, the optical power distribution feature data corresponding to each acquisition is clustered according to the partition-based target clustering algorithm, and the optimal number of clusters is determined based on the contour coefficients corresponding to each preset cluster number. Based on the clustering results corresponding to the optimal number of clusters, cluster merging and fault root cause analysis are performed according to Euclidean distance, and the fault root cause corresponding to the cluster with the largest number of samples is determined as the weak light root cause localization result of the target port.

[0005] In one embodiment, the step of performing interval segmentation and statistical analysis on the optical power data acquired in each acquisition according to a preset optical power interval to obtain the optical power distribution characteristic data corresponding to each acquisition includes: Count the number of optical power data points that fall within each preset optical power range; Based on the number of optical power data points falling into each preset optical power range, an optical power distribution feature data vector is obtained, with the number of optical power data points in each preset optical power range as the element.

[0006] In one implementation, the target clustering algorithm includes the K-Means clustering algorithm or the K-Medoids clustering algorithm.

[0007] In one implementation, the step of clustering the optical power distribution feature data corresponding to each acquisition according to a partition-based target clustering algorithm based on multiple different preset cluster numbers, and determining the optimal number of clusters based on the silhouette coefficients corresponding to each preset cluster number, includes: Based on the preset range of cluster number K, clustering calculations are performed on multiple sets of optical power distribution feature data under different K values; Calculate the silhouette coefficient of the clustering results corresponding to each K value, and select the K value corresponding to the maximum silhouette coefficient as the optimal number of clusters.

[0008] In one implementation, the clustering results based on the optimal number of clusters are clustered and merged according to Euclidean distance, and the root cause of the fault is determined as the weak light root cause localization result of the target port, including: Obtain the Euclidean distance between any two cluster centers in the clustering results corresponding to the optimal number of clusters; Clusters with a Euclidean distance less than a preset distance threshold will be merged; The number of optical power distribution characteristic data groups contained in each cluster after merging is counted. The fault state represented by the cluster with the most data groups is output as the weak light root cause location result. The weak light root cause location result includes one or more of the following: fault in the trunk optical cable, fault in the branch optical cable, and fault in the drop cable.

[0009] In one embodiment, the optical power data includes: received optical power data and / or transmitted optical power data of the optical network unit under the target port of the target passive optical network.

[0010] In one embodiment, the method further includes: Within a preset time period, optical power data of each port within the port range of the target passive optical network is collected at preset time intervals. Based on the optical power data of each port, the weak light root cause localization results corresponding to each port within the port range of the target passive optical network are obtained; Based on the weak light root cause localization results corresponding to each port within the port range of the target passive optical network, the weak light root cause localization results of the target passive optical network are determined.

[0011] According to a second aspect of the embodiments of this application, an electronic device is provided, comprising: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of the method of any one of the first aspects.

[0012] According to a third aspect of the embodiments of this application, a non-transitory computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0013] According to a fourth aspect of the embodiments of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0014] The embodiments of this application can achieve the following beneficial effects: by continuously collecting optical power data of each optical network unit under the passive optical network port, segmenting and statistically analyzing according to a preset interval, multiple collections of optical power distribution characteristic data are obtained. Then, the characteristic data are divided into clusters based on different numbers of clusters, the optimal number of clusters is determined according to the silhouette coefficient, and then similar clusters are merged according to Euclidean distance and fault root cause analysis is performed. Finally, the root cause corresponding to the cluster with the most samples is taken as the weak light fault location result of the port. By replacing traditional manual judgment with data-driven cluster analysis, fault judgment does not require manual preset fixed threshold values. It can actively, accurately, and adaptively locate the root cause of weak light faults in passive optical network ports, thereby improving the accuracy and efficiency of weak light fault location.

[0015] Other features and advantages of this application will be described in detail in the following detailed description section. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart of a passive optical network weak light root cause localization method provided in an embodiment of this application.

[0017] Figure 2 This is a flowchart of a passive optical network weak light root cause localization method provided in an embodiment of this application.

[0018] Figure 3 This is a flowchart of a passive optical network weak light root cause localization method provided in an embodiment of this application.

[0019] Figure 4This is a flowchart of a passive optical network weak light root cause localization method provided in an embodiment of this application.

[0020] Figure 5 This is a flowchart of a passive optical network weak light root cause localization method provided in an embodiment of this application.

[0021] Figure 6 This is a block diagram of an electronic device provided in one embodiment of this application. Detailed Implementation

[0022] The specific embodiments of this application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this application.

[0023] It should be understood that the term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the following description.

[0024] It should be noted that the concepts of "first" and "second" mentioned in this application are only used to distinguish different devices, modules, or units, and are not used to limit the order of functions performed by these devices, modules, or units or their interdependencies. The modifications of "one" and "multiple" mentioned in this application are illustrative rather than restrictive, and those skilled in the art should understand that, unless explicitly stated in the context, they should be understood as "one or more". In the description of this application, unless otherwise stated, "multiple" means two or more, and other quantifiers are similar; "at least one item", "one item or multiple items", or similar expressions refer to any combination of these items, including any combination of single or multiple items.

[0025] Although operations or steps are described in a specific order in the accompanying drawings in the embodiments of this application, this should not be construed as requiring these operations or steps to be performed in the specific order or serial order shown, or requiring all of the shown operations or steps to be performed to obtain the desired result. In the embodiments of this application, these operations or steps may be performed serially; they may be performed in parallel; or a portion of these operations or steps may be performed.

[0026] The names of the messages or information exchanged between multiple devices in the embodiments of this application are for illustrative purposes only and are not intended to limit the scope of these messages or information. It is understood that before using the technical solutions disclosed in the embodiments of this application, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this application in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0027] First, the application scenario of this application will be explained. With the popularization of PON (Passive Optical Network), major operators now use PON as the user access equipment between the access point and the user. Currently, the PON penetration rate in the home broadband field has reached over 95%. However, with the popularization of PON, a huge workload for maintenance has also been brought about. Currently, in the process of home network construction, major operators use the above method to build more than 86% of all networks. Due to the characteristics of PON, there is no monitoring and measurement capability at the optical distribution box and fiber distribution box. Therefore, once the ONU (Optical Network Unit) in the user's home experiences weak light, locating and resolving the weak light problem becomes a major time-consuming and labor-intensive problem for on-site fault handling personnel. Traditionally, when on-site technicians handle weak light reception faults of user-side ONUs, the following methods are typically used: (1) Use an optical power meter to measure the light emitted from the PON port on the equipment room side, and combine it with the initial value of the optical module from the OLT (Optical Line Terminal) manufacturer to determine whether the optical module is damaged.

[0028] (2) Use an optical power meter to measure the PON port emission on the optical distribution box side, and combine the emission measured on the equipment room side, the loss of the first-level splitter and the length of the trunk optical cable, and combine with operation and maintenance experience to judge whether the loss is too large.

[0029] (3) Use an optical power meter to measure the light emission of the PON port on the fiber distribution box side, and combine the light emission measured on the equipment room side and the optical distribution box side, as well as the splitting ratio of the branch optical cable and the secondary splitter, to calculate whether the loss is too large.

[0030] (4) Based on the measurement results of the above steps 1, 2, and 3, the weak light fault can be resolved by replacing the optical cable, cleaning the fiber splice head, and replacing the splitter at the location with excessive loss.

[0031] Currently, few systems support technical personnel in locating weak light sources. Most systems focus on supporting user complaints, analyzing the optical power received by the user's ONU (Optical Network Unit) after a complaint, determining if the ONU is receiving weak light, stopping the process, and reporting the cause of the fault. This current technology for weak light location is limited to scenarios where weak light is located after a user complaint and cannot provide guidance for comprehensive network-wide weak light management. Furthermore, the judgment criteria are too simplistic, and the obtained analysis results differ significantly from the actual root cause of the fault, failing to provide accurate guidance for installation and maintenance personnel in handling faults.

[0032] In view of this, there is an urgent need for an effective means to actively, accurately, and adaptively locate the root cause of weak light faults in passive optical networks. The present application will be described below with reference to specific embodiments.

[0033] Figure 1 This is a flowchart illustrating a passive optical network (PON) weak light root cause localization method according to an embodiment of this application. Figure 1 As shown in the figure, this application provides a method for identifying the root causes of weak light in a passive optical network, which may include the following steps: In step S10, optical power data of the optical network unit under the target port of the target passive optical network is collected multiple times within a continuous time period.

[0034] In this step, optical power data of the optical network unit under the target port of the target passive optical network can be collected multiple times within a continuous time period (e.g., 5 minutes) at preset time intervals (e.g., 10 seconds). The optical power data may include received optical power data and / or transmitted optical power data of the optical network unit under the target port of the target passive optical network. For example, the collected optical power data may be shown in the table below: Table 1:

[0035] In step S20, the optical power data collected in each acquisition is divided into interval segments according to a preset optical power interval to obtain the optical power distribution characteristic data corresponding to each acquisition.

[0036] For example, the number of optical power data points falling into each preset optical power range can be counted first, and then an optical power distribution feature data vector with the number of optical power data points in each preset optical power range as the element can be obtained based on the number of optical power data points falling into each preset optical power range.

[0037] In step S30, the optical power distribution feature data corresponding to each acquisition is clustered according to a partition-based target clustering algorithm based on multiple different preset cluster numbers, and the optimal cluster number is determined based on the contour coefficients corresponding to each preset cluster number.

[0038] For example, clustering calculations can be performed on multiple sets of optical power distribution feature data under different K values ​​according to the preset range of cluster number K. Then, the silhouette coefficient of the clustering results corresponding to each K value can be calculated, and the K value corresponding to the maximum silhouette coefficient can be selected as the optimal number of clusters.

[0039] In step S40, cluster merging and fault root cause analysis are performed based on the clustering results corresponding to the optimal number of clusters according to Euclidean distance, and the fault root cause corresponding to the cluster with the largest number of samples is determined as the weak light root cause localization result of the target port.

[0040] For example, the Euclidean distance between any two cluster centers in the clustering results corresponding to the optimal number of clusters can be obtained first. Then, clusters with an Euclidean distance less than a preset distance threshold can be merged. Then, the number of optical power distribution feature data groups contained in each merged cluster can be counted. The fault state represented by the cluster with the most data groups can be output as the weak light root cause location result. The weak light root cause location result includes one or more of the following: fault in the trunk optical cable, fault in the branch optical cable, and fault in the drop cable.

[0041] This application embodiment continuously collects optical power data of each optical network unit under the passive optical network port, performs segmented statistics according to preset intervals, obtains optical power distribution characteristic data collected multiple times, then divides the characteristic data into clusters based on different numbers of clusters, determines the optimal number of clusters based on the silhouette coefficient, then merges similar clusters according to Euclidean distance and performs fault root cause analysis, and finally takes the root cause corresponding to the cluster with the most samples as the weak light fault location result of the port. By replacing traditional manual judgment with data-driven cluster analysis, fault judgment does not require manual preset fixed threshold values, and can actively, accurately and adaptively locate the root cause of weak light faults in passive optical network ports, thereby improving the accuracy and efficiency of weak light fault location.

[0042] In one possible implementation, optical power data may include: received optical power data and / or transmitted optical power data of optical network units at the target port of the target passive optical network. During the data acquisition phase, the received optical power data and / or transmitted optical power data of the optical network units at the target port of the target passive optical network are specifically acquired. These two types of optical power data reflect the operating status of the optical network units from different dimensions, enriching the comprehensiveness of data acquisition and avoiding the analytical bias that may result from a single data dimension. This allows subsequent feature extraction and cluster analysis to better reflect the true network situation, further improving the reliability of weak light root cause localization.

[0043] In one possible implementation, the target clustering algorithm may include K-Means clustering or K-Medoids clustering. When performing clustering analysis on optical power distribution feature data, either K-Means or K-Medoids clustering is selected. These two partition-based clustering algorithms can efficiently process multiple sets of continuously acquired optical power distribution feature data, adapting to multi-time-period and multi-data-point acquisition scenarios in passive optical networks. This ensures a stable and efficient clustering process, providing reliable algorithmic support for subsequent determination of the optimal number of clusters using silhouette coefficients and for conducting root cause analysis of faults.

[0044] Figure 2 This is a flowchart illustrating a passive optical network (PON) weak light root cause localization method according to an embodiment of this application. Figure 2 As shown, the step of performing interval segmentation and statistical analysis on the optical power data collected in each acquisition according to a preset optical power interval to obtain the optical power distribution characteristic data corresponding to each acquisition may include the following steps: In step S201, the number of optical power data points that fall into each preset optical power range is counted.

[0045] For example, an optical power statistical range can be defined, for instance, starting from -18dBm and divided into steps of 1dB down to below -33dBm.

[0046] An example of the received optical power acquisition value for an ONU can be found in Table 2: Table 2:

[0047] Table 3 provides an example table showing the number of optical power data points falling within each preset optical power range: Table 3:

[0048] In step S202, based on the number of optical power data points falling into each preset optical power range, an optical power distribution feature data vector is obtained, with the number of optical power data points in each preset optical power range as the element.

[0049] For example, for all the ONU received optical power data collected in the first batch, the number of data points falling into each interval (-22,-23], (-23,-24], ..., (-29,-30] is counted. For instance, the interval (-25,-26] has 6 points, and the interval (-28,-29] has 5 points. This set of interval counts (e.g., [0,0,0,0,0,1,4,4,6,4,4,5,6,0,0,0,0]) constitutes the optical power distribution characteristic data of the first batch. The same operation is performed on 30 batches of data to obtain 30 sets of characteristic data. The same processing can also be performed on the PON port received optical power data.

[0050] In this embodiment, for each acquired optical power data point, the number of optical power data points falling into each preset optical power interval is first counted. Then, using the number of points corresponding to each preset optical power interval as elements, an optical power distribution feature data vector is constructed. This method transforms the discrete raw optical power data into a vector form with clear statistical characteristics, solving the problem of unclear fault characteristics in the raw data. It provides a standardized and effective data foundation for subsequent cluster analysis, helping to improve the accuracy of subsequent root cause localization.

[0051] Figure 3 This is a flowchart illustrating a passive optical network (PON) weak light root cause localization method according to an embodiment of this application. Figure 3 As shown, the step of clustering the optical power distribution feature data corresponding to each acquisition according to a partition-based target clustering algorithm based on multiple different preset cluster numbers, and determining the optimal number of clusters based on the silhouette coefficients corresponding to each preset cluster number, may include the following steps: In step S301, clustering calculations are performed on multiple sets of optical power distribution feature data under different K values ​​according to the preset range of cluster number K.

[0052] For example, the optical power distribution feature data of a PON port can be calculated using a preset clustering number K=2~5. For instance, if the same PON port is sampled 30 times, the clustering results when K=2~5 can be calculated using either the K-Means algorithm or the K-Medoids clustering algorithm.

[0053] In step S302, the silhouette coefficient of the clustering result corresponding to each K value is calculated, and the K value corresponding to the maximum silhouette coefficient is selected as the optimal number of clusters.

[0054] For example, the silhouette coefficients for K=2~5 can be obtained separately, and the clustering result with the maximum silhouette coefficient can be taken. That is, the silhouette values ​​of the four clustering results for K=2~5 can be read separately, and the analysis result with the largest silhouette value can be obtained. For example, when K=3, the silhouette value is the largest, that is, the classification is the most obvious, so K=3 can be taken as the optimal number of clusters.

[0055] This application embodiment adaptively determines the clustering method based on the data's own characteristics, avoiding the subjective bias of manually setting the number of clusters K, making the clustering results more in line with the natural distribution of the data, and laying a solid foundation for accurately locating the root causes of weak light.

[0056] Figure 4 This is a flowchart illustrating a passive optical network (PON) weak light root cause localization method according to an embodiment of this application. Figure 4 As shown, the clustering results based on the optimal number of clusters are merged and the root cause analysis of the fault is performed according to Euclidean distance, and the root cause of the fault corresponding to the cluster with the largest number of samples is determined as the weak light root cause localization result of the target port. This can include the following steps: In step S401, the Euclidean distance between any two cluster centers in the clustering results corresponding to the optimal number of clusters is obtained.

[0057] For example, when the optimal number of clusters K=3, the Euclidean distance between any two cluster centers in the three clusters can be obtained.

[0058] In step S402, clusters with a Euclidean distance less than a preset distance threshold are merged.

[0059] For example, clusters whose Euclidean distance is less than a preset distance threshold in the clustering results when the optimal number of clusters K=3 obtained in the previous step can be merged, where the preset distance threshold can be an empirical value.

[0060] In step S403, the number of optical power distribution characteristic data groups contained in each cluster after merging is counted, and the fault state represented by the cluster with the most data groups is output as the weak light root cause location result. The weak light root cause location result includes one or more of the following: trunk optical cable fault, branch optical cable fault, and drop cable fault.

[0061] For example, we can assume that the silhouette coefficient is maximized when K=3, and select the clustering result with K=3. Obtain the cluster centers C1, C2, and C3 for each of the three clusters in this result, and calculate the Euclidean distances between C1 and C2, C1 and C3, and C2 and C3. If the distance between C1 and C2 is found to be much smaller than their distances to C3, then cluster 1 and cluster 2 are merged. Ultimately, the 30 samples are divided into two major categories. Statistical analysis shows that 25 samples belong to the merged "Category A" and 5 samples belong to "Category B". The system predefines "Category A" as "backbone optical cable is normal" and "Category B" as "backbone optical cable has a fault". Since most samples (25) fall into Category A, the system outputs the weak light root cause localization result for this PON port as: "No fault in the backbone optical cable". Similarly, clustering analysis processes for "whether there is a fault in the branch optical cable" or "whether there is a fault in the drop cable" can be executed in parallel or subsequently.

[0062] In this embodiment, after obtaining the clustering results corresponding to the optimal number of clusters, the Euclidean distance between any two cluster centers is calculated, and clusters with a distance less than a preset distance threshold are merged. Then, the number of optical power distribution feature data groups contained in each merged cluster is counted. The fault state represented by the cluster with the most data groups, such as trunk optical cable fault, branch optical cable fault, or drop cable fault, is output as the weak light root cause localization result. This process effectively aggregates similar fault features, clearly distinguishes fault types in different network segments, provides maintenance personnel with a clear repair direction, and significantly reduces the time cost of on-site troubleshooting.

[0063] Figure 5 This is a flowchart illustrating a passive optical network (PON) weak light root cause localization method according to an embodiment of this application. Figure 5 As shown, the method may further include the following steps: In step S50, optical power data of each port within the port range of the target passive optical network is collected at preset time intervals within a preset time period.

[0064] In step S60, based on the optical power data of each port, the weak light root cause localization result corresponding to each port within the port range of the target passive optical network is obtained.

[0065] In step S70, based on the weak light root cause localization results corresponding to each port within the port range of the target passive optical network, the weak light root cause localization results of the target passive optical network are determined.

[0066] For example, within a preset time period, optical power data of all ports within the target passive optical network (PON) port range can be collected at set time intervals. For each port, a complete process of optical power distribution feature extraction, cluster analysis, cluster merging, and root cause determination is performed to obtain the weak light root cause location results for each port. Finally, the analysis results of all ports are summarized to comprehensively determine the weak light root cause location results of the entire target PON. This process realizes the investigation of weak light potential hazards from a single port to the entire network, supports proactive network inspection, discovers potential faults in advance, avoids reactive handling after user complaints, and effectively improves the overall network quality and user service experience.

[0067] Figure 6 This is a block diagram of an electronic device provided in one embodiment of this application. For example... Figure 6 As shown, the electronic device 600 may include a processor 601 and a memory 602. The electronic device 600 may also include one or more of a multimedia component 603, an input / output (I / O) interface 604, and a communication component 605.

[0068] The processor 601 controls the overall operation of the electronic device 600 to complete all or part of the steps in the passive optical network weak light root cause localization method described above. The memory 602 stores various types of data to support the operation of the electronic device 600. This data may include, for example, instructions for any application or method operating on the electronic device 600, and application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 602 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. Multimedia component 603 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 602 or transmitted via communication component 605. The audio component also includes at least one speaker for outputting audio signals. I / O interface 604 provides an interface between processor 601 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 605 is used for wired or wireless communication between the electronic device 600 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IoT, eMTC, or other 5G technologies, or combinations thereof, is not limited here. Therefore, the corresponding communication component 605 may include: a Wi-Fi module, a Bluetooth module, an NFC module, etc.

[0069] In an exemplary embodiment, the electronic device 600 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the passive optical network weak light root cause localization method described above.

[0070] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the passive optical network (PON) weak light source localization method described above. For example, the computer-readable storage medium may be the memory 602 including the program instructions described above, which may be executed by the processor 601 of the electronic device 600 to complete the passive optical network weak light source localization method described above.

[0071] In another exemplary embodiment, a computer program product is also provided, the computer program product comprising a computer program executable by a programmable device, the computer program having a code portion for performing the above-described passive optical network weak light root cause localization method when executed by the programmable device.

[0072] The preferred embodiments of this application have been described in detail above with reference to the accompanying drawings. However, this application is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this application, various simple modifications can be made to the technical solution of this application, and these simple modifications all fall within the protection scope of this application.

[0073] It should also be noted that the various specific technical features described in the above embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this application will not describe the various possible combinations separately.

[0074] Furthermore, various different implementations of this application can be combined in any way, as long as they do not violate the spirit of this application, they should also be regarded as the content disclosed in this application.

Claims

1. A method for identifying the root causes of weak light in passive optical networks, characterized in that, The method includes: The optical power data of the optical network unit under the target port of the target passive optical network is collected multiple times within a continuous time period. The optical power data collected in each acquisition is segmented and statistically analyzed according to a preset optical power range to obtain the optical power distribution characteristic data corresponding to each acquisition. Based on multiple different preset cluster numbers, the optical power distribution feature data corresponding to each acquisition is clustered according to the partition-based target clustering algorithm, and the optimal number of clusters is determined based on the contour coefficients corresponding to each preset cluster number. Based on the clustering results corresponding to the optimal number of clusters, cluster merging and fault root cause analysis are performed according to Euclidean distance, and the fault root cause corresponding to the cluster with the largest number of samples is determined as the weak light root cause localization result of the target port.

2. The method according to claim 1, characterized in that, The step of performing interval segmentation and statistical analysis on the optical power data collected in each acquisition according to a preset optical power interval to obtain the optical power distribution characteristic data corresponding to each acquisition includes: Count the number of optical power data points that fall within each preset optical power range; Based on the number of optical power data points falling into each preset optical power range, an optical power distribution feature data vector is obtained, with the number of optical power data points in each preset optical power range as the element.

3. The method according to claim 1, characterized in that, The target clustering algorithm includes the K-Means clustering algorithm or the K-Medoids clustering algorithm.

4. The method according to claim 3, characterized in that, The step involves clustering the optical power distribution feature data corresponding to each acquisition according to a partition-based target clustering algorithm based on multiple different preset cluster numbers, and determining the optimal number of clusters based on the silhouette coefficients corresponding to each preset cluster number, including: Based on the preset range of cluster number K, clustering calculations are performed on multiple sets of optical power distribution feature data under different K values; Calculate the silhouette coefficient of the clustering results corresponding to each K value, and select the K value corresponding to the maximum silhouette coefficient as the optimal number of clusters.

5. The method according to claim 1, characterized in that, The clustering results based on the optimal number of clusters are clustered and merged according to Euclidean distance, and the root cause of the fault is analyzed. The root cause of the fault corresponding to the cluster with the largest number of samples is determined as the weak light root cause localization result of the target port, including: Obtain the Euclidean distance between any two cluster centers in the clustering results corresponding to the optimal number of clusters; Clusters with a Euclidean distance less than a preset distance threshold will be merged; The number of optical power distribution characteristic data groups contained in each cluster after merging is counted. The fault state represented by the cluster with the most data groups is output as the weak light root cause location result. The weak light root cause location result includes one or more of the following: fault in the trunk optical cable, fault in the branch optical cable, and fault in the drop cable.

6. The method according to any one of claims 1-5, characterized in that, The optical power data includes: received optical power data and / or transmitted optical power data of the optical network unit under the target port of the target passive optical network.

7. The method according to claim 1, characterized in that, The method further includes: Within a preset time period, optical power data of each port within the port range of the target passive optical network is collected at preset time intervals. Based on the optical power data of each port, the weak light root cause localization results corresponding to each port within the port range of the target passive optical network are obtained; Based on the weak light root cause localization results corresponding to each port within the port range of the target passive optical network, the weak light root cause localization results of the target passive optical network are determined.

8. An electronic device, characterized in that, include: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of the method according to any one of claims 1-7.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-7.

Images