Method and device for intelligent perception of poor quality data and fault early warning of Internet of Things, and storage medium

Abstract

The invention discloses a method and device for intelligently sensing poor-quality data and early warning faults of the Internet of Things and a storage medium, and belongs to the technical field of intelligent operation and maintenance, and the method comprises the steps: employing a poor-quality index to sense a network service in the operation and maintenance guarantee of OLT equipment, obtaining the poor-quality data, constructing a grid topological relation, and expanding the sensing range; filtering the perceived poor-quality data to obtain abnormal fluctuation data which is used for network equipment fault early warning; and when the abnormal environment of the network is sensed, network reconstruction is carried out to obtain an optimal ad hoc network. According to the invention, the network equipment with fault hidden dangers can be identified, and ad-hoc networking is carried out, so that the purpose of carrying out preventive maintenance on the network equipment is achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent operation and maintenance technology, and in particular to a method, device and storage medium for intelligently sensing poor quality data and fault warning of the Internet of Things. Background Art

[0002] Intelligent sensing technology refers to mapping signals from the physical world to the digital world through hardware devices such as cameras, microphones or other sensors, with the help of cutting-edge technologies such as voice recognition and image recognition, and then further elevating the digital information to a recognizable level.

[0003] For the operator's operation and maintenance guarantee system, there are two main means for the operation and maintenance system to guarantee network equipment. The first is post-event maintenance, that is, after a serious fault occurs, it has already affected the user's service experience. After the technicians are informed, they rush to the site to quickly repair the fault. It has many natural defects. For example, since most faults occur randomly, it is difficult to guarantee the time it takes for the operation and maintenance personnel to arrive at the site to solve the problem. The fault cannot be restored in a short time, resulting in large losses. The other is preventive maintenance, that is, through regular maintenance by initial personnel, periodic abnormal detection and dispatch maintenance, the occurrence of faults can be reduced, or early intervention can be carried out before major faults occur. The traditional ecological closed loop of fault discovery, fault diagnosis, and fault repair can only be regarded as meeting the basic needs of network equipment operation and maintenance and solving the problem of rapid repair of faults that have occurred. In order to prevent the occurrence of faults and ensure that network equipment is maintained in a stable and monitored operating state as much as possible, it is necessary to consider whether some network equipment that has not yet failed but has potential faults based on the recent operating status can be identified, so as to achieve the purpose of preventive maintenance of network equipment. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a method, device and storage medium for intelligently sensing poor quality data and fault warning in the Internet of Things.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

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

[0007] 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;

[0008] Filter the perceived poor quality data to obtain abnormal fluctuation data for network equipment failure warning;

[0009] When an abnormal network environment is sensed, the network is reconstructed to obtain the optimal self-organizing network.

[0010] To optimize the above technical solutions, the specific measures taken also include:

[0011] Furthermore, the quality difference indicators include packet loss rate and freeze rate.

[0012] Further, the grid topology relationship includes neighbor relationship, group relationship and complete grid topology structure relationship;

[0013] 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;

[0014] The clique relationship is defined as the set of grids that are neighbors of each other;

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

[0016] Furthermore, filtering the perceived poor quality data is specifically performed as follows:

[0017] 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 is filtered out from the data set using the poor quality fluctuation characteristics, and the obtained data is used as abnormal fluctuation data.

[0018] Furthermore, the network reconstruction is specifically as follows:

[0019] The random domain method is used in the grid to form a regional self-organizing network. When the network environment in the grid is detected to be abnormal, the nodes in the grid are reorganized. Specifically:

[0020] The network jitter logs of the self-organizing network to be allocated are analyzed, and the self-organizing network with the least jitter times in the log records is selected as the optimal self-organizing network. The self-organizing 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.

[0021] Furthermore, the indicators used in cluster analysis of poor quality data include root mean square standard deviation and coefficient of determination;

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

[0023]

[0024] In the formula, 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;

[0025]

[0026] In the formula, p is the total number of indicators, n is the total number of data in the cluster, and X is Represents the value of the sth indicator of the i-th data, Represents the overall mean.

[0027] The present invention also proposes an electronic device, comprising: 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 above is implemented.

[0028] The present invention also proposes a computer-readable storage medium storing a computer program, wherein 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 above.

[0029] The beneficial effect of the present invention is that the present invention can identify network devices with potential faults and conduct self-organizing networking to achieve the purpose of preventive maintenance of the network devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is an overall flow chart of the method for intelligently sensing poor quality data and fault warning in the Internet of Things proposed by the present invention;

[0031] Figure 2 A schematic diagram of service types and user types associated with OLT. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0033] Embodiment 1

[0034] OLT (Optical Line Terminal) equipment hidden danger prediction scenario, OLT network equipment is an important central office equipment, mainly used to realize the control, management, ranging and other functions of the user end equipment ONU. Figure 2As shown in the figure, from the perspective of network service structure, OLT undertakes various upstream tasks such as the Internet and network TV, and is connected to each user terminal that uses network services, including individual users and hotels. Therefore, for operators, the operation and maintenance of OLT equipment occupies a very important position in the operation and maintenance of network equipment. The health of OLT equipment is directly related to the perception of downstream users when using network services.

[0035] The present invention proposes a method for intelligently sensing poor quality data and fault warning in the Internet of Things. The overall process of the method is as follows: Figure 1 As shown, the following steps are included:

[0036] In the operation and maintenance of OLT equipment, quality difference indicators are used to perceive network services, obtain quality difference data, and build a grid topology relationship to expand the perception range; quality difference indicators include packet loss rate and jamming rate.

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

[0038] 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;

[0039] The clique relationship is defined as the set of grids that are neighbors of each other;

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

[0041] The perceived poor quality data is filtered to obtain abnormal fluctuation data for network equipment failure warning; the specific filtering of the perceived poor quality data is as follows:

[0042] Performing cluster analysis on the quality difference data to obtain a data set with quality difference fluctuation characteristics; the indicators used in the cluster analysis on the quality difference data include root mean square standard deviation (RMSSTD) and determination coefficient;

[0043] The smaller the RMSSTD, the higher the similarity of individual objects within the group (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 coefficient of determination, the size of the difference between groups after clustering, that is, the proportion of variance of the original data that can be explained by the clustering results. The larger the R-Square, the higher the difference between groups (clusters), and the better the clustering effect. 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;

[0047]

[0048] In the formula, p is the total number of indicators, n is the total number of data in the cluster, and X is Represents the value of the sth indicator of the i-th data, Represents the overall average. According to the idea of ​​clustering, a good clustering result should be within the range of R-Square E[0,11], and the closer Sanare is to 1, the better. This shows that the difference between each group, that is, B is larger, and the difference between objects in the same group (within the group), that is, W is smaller, which is exactly the effect that cluster analysis hopes to achieve.

[0049] The quality fluctuation characteristics are extracted from the data set. After filtering out the abnormal diagnostic feature data from the data set using the quality fluctuation characteristics, the data obtained are used as abnormal fluctuation data. After a case analysis of the selected type of poor quality equipment, two common characteristics of poor quality equipment can be summarized; one is that the proportion of users with poor quality fluctuations has fluctuated frequently over the past period of time, that is, the historical operating health of the equipment is low; the other is that the proportion of poor quality users of the equipment has remained at a high level for a long time or even has an increasing trend, that is, poor quality may continue to occur in the future. The feature extraction method is used to analyze the historical data and extract features, so as to discover the hidden characteristics of poor quality fluctuations that may be hidden.

[0050] When an abnormal network environment is detected, the network is reconstructed to obtain the optimal self-organizing network. Specifically:

[0051] A random domain method is used in the grid to conduct regional self-organizing network. When the network environment in the grid is detected to be abnormal, including security attacks, intrusion attacks, node destruction, electromagnetic interference, etc., in order to meet the needs of wireless network scheduling, upper-layer application requirements, business service quality, etc., the nodes in the grid are reorganized, specifically:

[0052] In order to prevent the reduction of the efficiency of the self-organizing network due to network jitter during the self-organizing network process, a network jitter log analysis is performed on the self-organizing network to be allocated, and the self-organizing network with the least jitter times in the log record is selected as the optimal self-organizing network. The self-organizing 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.

[0053] Embodiment 2

[0054] The present invention proposes an electronic device, comprising: 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 Example 1 is implemented.

[0055] Embodiment 3

[0056] The present invention provides a computer-readable storage medium storing a computer program, wherein 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 the first embodiment.

[0057] In the embodiments disclosed in the present application, the computer storage medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. The computer storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the above. More specific examples of computer storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0058] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0059] The above are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should be regarded as the protection scope of the present invention.

Claims

1. A method for intelligently sensing poor quality data and fault warning in the Internet of Things, characterized in that: 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 sensed, the network is reconstructed to obtain the optimal self-organizing network.

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

3. The method for intelligently sensing poor quality data and fault warning of the Internet of Things as claimed in 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 clique relationship is defined as the set of grids that are neighbors of each other; The complete mesh topology structure relationship is specifically an independent mesh topology structure.

4. The method for intelligently sensing poor quality data and fault warning of the Internet of Things as claimed in 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 is 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 of the Internet of Things as claimed in claim 1, characterized in that: The network reconstruction is specifically as follows: The random domain method is used in the grid to form a regional self-organizing network. When the network environment in the grid is detected to be abnormal, the nodes in the grid are reorganized. Specifically: The network jitter logs of the self-organizing network to be allocated are analyzed, and the self-organizing network with the least jitter times in the log records is selected as the optimal self-organizing network. The self-organizing 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.

6. The method for intelligently sensing poor quality data and fault warning of the Internet of Things as claimed in 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: In the formula, 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; In the formula, p is the total number of indicators, n is the total number of data in the cluster, and X is Represents the value of the sth indicator of the i-th data, Represents the overall mean.

7. 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 6 is implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: The computer program enables the 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 1-6.

Images