Method, device and storage medium for intelligent sensing of quality difference data and fault early warning of internet of things

Abstract

The application discloses a kind of Internet of Things intelligent sensing quality difference data and fault early warning method, equipment and storage medium, belong to intelligent operation and maintenance technical field, method includes: in the operation and maintenance guarantee of OLT equipment, quality difference index is used to carry out sensing to network service, obtain quality difference data, construct grid topological relationship to expand sensing range;The quality difference data sensed is filtered, and abnormal fluctuation data is obtained, for network equipment fault early warning;When sensing network abnormal environment, network reconstruction is carried out, and the optimal ad hoc network is obtained.The application can identify network equipment with hidden trouble, and carry out ad hoc network, to achieve the purpose of preventive maintenance to network equipment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent operation and maintenance, and particularly relates to a method, device and storage medium for intelligent sensing of poor-quality data and fault early warning of Internet of Things. BACKGROUND

[0002] Intelligent sensing technology refers to mapping signals of the physical world to the digital world through camera, microphone or other sensor hardware devices, with the aid of voice recognition, image recognition and other leading technologies, and further improving the digital information to a recognizable level.

[0003] For the operation and maintenance system of an operator, there are mainly two means for the operation and maintenance system to protect network equipment. The first means is post-maintenance, that is, after a more serious fault occurs and has affected the user's service experience, the technician is informed and rushes to the scene to quickly repair the fault. It has many natural defects, such as the occurrence of the fault is mostly random, the time spent by the maintenance personnel to arrive at the scene to solve the problem is difficult to guarantee, the fault cannot be recovered in a short time, and the loss is large. The other means is preventive maintenance, that is, through regular maintenance by initial personnel, periodic anomaly detection and dispatching maintenance, to reduce the occurrence of faults or intervene in advance before a major fault occurs. The traditional ecological closed loop of fault discovery, fault diagnosis and fault repair can only meet the basic needs of network equipment maintenance and solve the problem of rapid repair of the fault that has occurred. For how to prevent the occurrence of faults and ensure that the network equipment is maintained in a stable monitoring state as much as possible, it is necessary to consider whether some network equipment that has not yet failed but has hidden faults in the recent operation state can be identified to achieve the purpose of preventive maintenance of the network equipment. SUMMARY

[0004] The present application provides a method, device and storage medium for intelligent sensing of poor-quality data and fault early warning of Internet of Things to overcome the defects in the prior art.

[0005] To achieve the above object, the present application adopts the following technical scheme:

[0006] A method for intelligent sensing of poor-quality data and fault early warning of Internet of Things, comprising the following steps:

[0007] In the operation and maintenance of the OLT device, the quality difference index is used to sense the network service to obtain quality difference data, and a grid topology relationship is constructed to expand the sensing range;

[0008] The sensed quality difference data is filtered to obtain abnormal fluctuation data for network equipment fault early warning;

[0009] When the network abnormal environment is perceived, network reconstruction is performed to obtain an optimal ad hoc network.

[0010] To optimize the above technical solution, the specific measures taken further include:

[0011] Further, the quality difference index includes a packet loss rate and a lag rate.

[0012] Further, the grid topology relationship includes a neighbor relationship, a group relationship, and a complete grid topology relationship.

[0013] The neighbor relationship is specifically: for any grid that is not at the edge of the network, the four immediately adjacent grids are considered to be its neighbors.

[0014] The group relationship is defined as a set of grids that are each other's neighbors.

[0015] The complete grid topology relationship is specifically an independent grid topology.

[0016] Further, the filtering of the perceived quality difference data is specifically:

[0017] Performing cluster analysis on the quality difference data to obtain a data set with quality difference fluctuation characteristics; extracting quality difference fluctuation characteristics from the data set, and using the quality difference fluctuation characteristics to filter out abnormal diagnosis characteristic data from the data set to obtain data as abnormal fluctuation data.

[0018] Further, the network reconstruction is specifically:

[0019] Using a random domain method to perform regional ad hoc networking within the grid, and when the network environment within the grid is perceived to be abnormal, recombining the nodes within the grid, specifically:

[0020] Performing network jitter log analysis on the ad hoc network to be distributed, selecting the ad hoc network with the least number of jitters in the log record as the optimal ad hoc network, the ad hoc network to be distributed being composed of all possible neighbor relationships or group relationships, and the all possible neighbor relationships or group relationships being marked by traversing the grid topology relationship.

[0021] Further, the index used for the cluster analysis of the quality difference data includes a root mean square standard deviation and a determination coefficient.

[0022] The calculation formula of the determination coefficient is as follows:

[0023]

[0024] In the formula, R_Square represents the determination coefficient, W represents the difference degree within each group after clustering, B represents the difference degree between each group after clustering, and T represents the total difference degree of all data after clustering.

[0025]

[0026] wherein p is the total number of indexes, n represents the total number of data in the cluster, X is represents the value of the ith data s index, represents the overall average value.

[0027] The application further provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the method for intelligently sensing poor-quality data and failure warning of the Internet of Things when executing the computer program.

[0028] The application further provides a computer readable storage medium, which stores a computer program, wherein the computer program enables a computer to execute the method for intelligently sensing poor-quality data and failure warning of the Internet of Things.

[0029] The application has the beneficial effect that the application can identify network devices with hidden failure risks and form an ad hoc network, so as to achieve the purpose of preventive maintenance of the network devices. BRIEF DESCRIPTION OF DRAWINGS

[0030] Figure 1 The application provides a method for intelligently sensing poor-quality data and failure warning of the Internet of Things.

[0031] Figure 2 The figure shows the service type and user type associated with the OLT. DETAILED DESCRIPTION

[0032] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the application.

[0033] Embodiment one

[0034] The hidden risk prediction scene of the OLT (optical line terminal) device, the OLT network device is an important local terminal device, mainly used to control, manage, measure the distance and other functions of the user terminal device ONU. By Figure 2As shown in the figure, from the network service structure, the OLT undertakes various types of upstream tasks such as the Internet and network television, and is connected downward to each user terminal using network services, including personal users and hotels. Therefore, for the operator, the OLT device operation and maintenance guarantee occupies a very important position in network device operation and maintenance, and the running health degree of the OLT device is directly related to the perception of the downstream users when using network services.

[0035] The present application provides a kind of Internet of Things intelligent sensing quality difference data and fault early warning method, the overall process of this method as shown in Figure 1 As shown in the figure, the method comprises the following steps:

[0036] In the operation and maintenance of OLT device, quality difference index is used to perceive network service to obtain quality difference data, and grid topology relationship is constructed to expand the perception range; Quality difference index includes packet loss rate and stall rate.

[0037] The grid topology relationship includes neighbor relationship, group relationship and complete grid topology structure relationship;

[0038] The neighbor relationship is specifically: for any grid not at the edge of the network, 4 adjacent grids are considered as its neighbors;

[0039] The group relationship is defined as a set of grids that are each other's neighbors;

[0040] The complete grid topology structure relationship is specifically an independent grid topology structure.

[0041] The perceived quality difference data is filtered to obtain abnormal fluctuation data for network device fault early warning; The perceived quality difference data is filtered specifically as follows:

[0042] The quality difference data is clustered and analyzed to obtain a data set with quality difference fluctuation characteristics; The index used for clustering and analyzing the quality difference data includes root-mean-square standard deviation (RMSSTD) and determination coefficient;

[0043] The smaller the RMSSTD, the higher the similarity of individual objects within the group (within the cluster), and the better the clustering effect.

[0044] The calculation formula of the determination coefficient is as follows:

[0045]

[0046] In the formula, R Square represents the determination coefficient, the size of the difference between the groups after clustering, that is, the clustering result can explain the variance of the original data in what proportion, the larger the R-Square indicates that the higher the difference between the groups (between clusters), the better the clustering effect. W represents the difference degree of each group after clustering grouping, B represents the difference degree between each group after clustering grouping, and T represents the total difference degree of all data after clustering grouping;

[0047]

[0048] In the formula, p is the total number of indexes, n represents the total number of data in the cluster, X is represents the value of the ith data s index, According to the idea of clustering, a good clustering result should be within the range of R-Square E[0,11], and Sanare is closer to 1, which indicates the difference between the groups, that is, B is larger, and the difference between the objects in the same group (within the group) is smaller, that is, W is smaller, which is the effect that clustering analysis hopes to achieve.

[0049] After extracting the quality difference fluctuation characteristics from the data set and filtering out the abnormal diagnosis characteristic data from the data set using the quality difference fluctuation characteristics, the obtained data is used as abnormal fluctuation data. After individual analysis of the selected quality difference equipment type, two common characteristics of the quality difference equipment can be summarized; one is that the quality difference fluctuation user ratio fluctuates frequently in the past period of time, that is, the historical operation health degree of the equipment is low; the other is that the quality difference user ratio of the equipment remains high for a long time or even has a growth trend, that is, the quality difference may continue to appear in the future. The feature extraction method is used to analyze and extract features from the historical data, so as to find the hidden quality difference fluctuation hidden characteristics.

[0050] When the network abnormal environment is perceived, the network is reconfigured to obtain the optimal ad hoc network. Specifically:

[0051] In the grid, a random domain method is used for regional ad hoc network. When it is perceived that the network environment in the grid is abnormal, including security attack, intrusion attack, destroyed node, electromagnetic interference, etc.; in order to meet the demand of wireless network scheduling, upper application demand, service quality demand, etc., the nodes in the grid are recombined, specifically:

[0052] In order to prevent the efficiency of ad hoc network from being reduced due to network jitter during the ad hoc network process, network jitter log analysis is performed on the to-be-allocated ad hoc network, and the ad hoc network with the least jitter times in the log record is selected as the optimal ad hoc network. The to-be-allocated ad hoc network is composed of all possible neighbor relationships or group relationships, and the all possible neighbor relationships or group relationships are marked by traversing the grid topology relationship.

[0053] Embodiment two

[0054] The application provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the method for intelligently sensing poor-quality data and failure warning of Internet of Things according to the computer program.

[0055] Embodiment three

[0056] The application provides a computer readable storage medium, which stores a computer program, and the computer program enables a computer to execute the method for intelligently sensing poor-quality data and failure warning of Internet of Things according to the embodiment one.

[0057] In the embodiments disclosed in the present application, the computer storage medium can be a tangible medium, which can contain or store programs for use by or in connection with an instruction execution system, apparatus or device. The computer storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, apparatus or device, or any suitable combination of the above. More specific examples of the computer storage medium can include one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device or any suitable combination of the above.

[0058] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present application can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0059] The above is only the preferred embodiment of the present application, and the protection scope of the present application is not limited to the above-mentioned embodiments. Any technical solution falling within the concept of the present application belongs to the protection scope of the present application. It should be noted that, for ordinary skilled persons in the art, some improvements and refinements without departing from the principles of the present application should be considered as the protection scope of the present application.

Claims

1. A method for intelligently sensing poor quality data and fault warning in the Internet of Things, characterized by: The following steps are involved: In the operation and maintenance of OLT equipment, quality difference indicators are used to perceive network services, obtain quality difference data, and build grid topology relationships to expand the perception range; Filter the perceived poor quality data to obtain abnormal fluctuation data for network equipment failure warning; When an abnormal network environment is detected, network reconstruction is performed to obtain an optimal ad hoc network. The network reconstruction is specifically performed as follows: A random domain approach is used within the grid to conduct regional self-organizing networks. When an abnormality is detected in the network environment within the grid, the nodes within the grid are reorganized. Specifically: A network jitter log analysis is performed on the ad hoc network to be allocated, and the ad hoc network with the least jitter in the log record is selected as the optimal ad hoc network. The ad hoc network to be allocated is composed of all possible neighbor relationships or group relationships, and all possible neighbor relationships or group relationships are marked by traversing the grid topology relationship.

2. The method for intelligently sensing poor quality data and fault warning in the Internet of Things according to claim 1, characterized in that: The quality poor indicators include packet loss rate and freeze rate.

3. The method for intelligently sensing poor quality data and fault warning in the Internet of Things according to claim 1, characterized in that: The grid topology relationship includes neighbor relationship, group relationship and complete grid topology structure relationship; The neighbor relationship is specifically as follows: for any grid that is not at the edge of the network, the four adjacent grids are considered to be its neighbors; The group relationship is defined as a set of grids that are neighbors of each other; The complete mesh topology relationship is specifically an independent mesh topology.

4. The method for intelligently sensing poor quality data and fault warning in the Internet of Things according to claim 1, characterized in that: The filtering of the perceived poor quality data is specifically as follows: Cluster analysis is performed on the poor quality data to obtain a data set with poor quality fluctuation characteristics; the poor quality fluctuation characteristics are extracted from the data set, and the abnormal diagnostic feature data are filtered out from the data set using the poor quality fluctuation characteristics, and the obtained data is used as abnormal fluctuation data.

5. The method for intelligently sensing poor quality data and fault warning in the Internet of Things according to claim 4, characterized in that: The indicators used in cluster analysis of poor quality data include root mean square standard deviation and coefficient of determination; The calculation formula of the determination coefficient is as follows: ； Where R_Square represents the coefficient of determination, W represents the degree of difference within each group after clustering, B represents the degree of difference between each group after clustering, and T represents the total degree of difference of all data after clustering; ； Where, p is the total number of indicators, n Indicates the total number of data in the cluster, Indicates the value of the sth indicator of the i-th data, Represents the overall mean.

6. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for intelligently sensing poor quality data and fault warning of the Internet of Things as described in any one of claims 1 to 5 is implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: The computer program enables a computer to execute the method for intelligently sensing poor quality data and fault warning of the Internet of Things as described in any one of claims 1 to 5.

Images