Electric power information system alarm traceability method and system based on redundancy processing and observation

Abstract

The invention belongs to the technical field of observable technology, and provides an electric power information system alarm traceability method and system based on redundancy processing and observation, after alarm information corresponding to a traceability object is determined, alarm types are matched according to the determined alarm information, and the alarm information is displayed on a graphical interface according to the matched alarm types; specifically, when graphical interface display is carried out, whether the alarm type is index alarm is judged, if yes, index graphical interface display is carried out, if not, whether the alarm type is link alarm is judged, if yes, link graphical interface display is carried out, and if not, log graphical interface display is carried out; according to the method, the type matching is performed according to the alarm source, and the graphical interface display object is automatically judged and determined according to different alarm types, so that the judgment efficiency is improved, the overall alarm traceability and the observability of fault information are realized, and the traceability accuracy is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of observable technologies, and in particular relates to a method and system for tracing the source of alarms in an electric power information system based on redundant processing and observation. Background Art

[0002] The alarm tracing of the power information system is an important part of the digital transformation of power enterprises for cloud-native monitoring and controlled systems. The accuracy of alarm positioning and the rationality of tracing directly affect the availability and quality of the controlled information system. In IT monitoring, alarm tracing has been widely used in monitoring, operation and maintenance, etc., but due to the differences in alarm data, it will be affected by factors such as alarm type and quantity, resulting in the inability to accurately locate the alarm, thus affecting the alarm tracing of the power information system.

[0003] The existing solution mainly checks the specific alarm source, manually determines the specific alarm details based on the alarm source, and then finds the specific corresponding indicators, links or log graphical interfaces by analyzing the alarm details. However, this will increase the operation and maintenance workload of alarm tracing and increase the system operation and maintenance costs. Manual judgment will also make it impossible to trace the alarm of the controlled system as a whole, resulting in a lack of accurate positioning and tracing, affecting the stability and security of the system.

[0004] According to the alarm source, the type is first matched based on the neural network, and then a graphical interface is displayed and judged, which can improve the judgment efficiency; however, the neural network model for classifying the alarm source has the problems of large data volume and poor accuracy. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a method and system for tracing the alarm of an electric power information system based on redundant processing and observation. The present invention uses a sparse basis to iterate, obtains the input data of the neural network classification model, uses the alarm information and input data as a training set, and performs redundant data processing on the training set, thereby improving the quality of the alarm information and reducing the amount of data. On the basis of providing a guarantee for improving the accuracy of tracing, the data pressure is reduced and the efficiency is improved; based on this, the type matching is performed according to the alarm source, and the automatic judgment and determination of the graphical interface display object is performed according to the different types of alarms. Further, on the basis of ensuring accuracy, the judgment efficiency is improved, and the screening and judgment of the indicator graphical interface display, the link graphical interface display or the log graphical interface display are performed, so as to realize the overall alarm tracing and the observability of the fault information, and further ensure the accuracy of tracing. In order to achieve the above purpose, the present invention is implemented through the following technical solutions:

[0006] In a first aspect, the present invention provides a method for tracing the source of an alarm in a power information system based on redundant processing and observation, comprising:

[0007] Determine the traceability object;

[0008] Determine the alarm information corresponding to the traceability object;

[0009] According to the determined alarm information, match the alarm type;

[0010] According to the matching alarm type, the graphical interface corresponding to the alarm information is obtained;

[0011] Among them, when matching the alarm type, the trained neural network classification model is used. When the neural network classification model is trained and classified, the sparse basis is used for iteration to obtain the input data of the neural network classification model; the alarm information and input data are used as training sets, and the training sets are processed with redundant data; the neural network classification model is obtained by training with redundantly processed data; when determining the graphical interface, it is determined whether the alarm type is an indicator alarm, if so, an indicator graphical interface is obtained, otherwise it is determined whether the alarm type is a link alarm, if so, a link graphical interface is obtained, otherwise a log graphical interface is obtained. Further, the traceability objects include systems, services, middleware and infrastructure.

[0012] Furthermore, the alarm objects of the services or hosts corresponding to the system, service, middleware and infrastructure are merged into similar items, and the merged alarm objects are mapped into link alarms, indicator alarms and log alarms.

[0013] Furthermore, the service identifier of the corresponding alarm type is transmitted to the corresponding graphical interface.

[0014] Furthermore, a graphical interface of a corresponding alarm object is queried according to the service identifier to display the alarm information.

[0015] Furthermore, the specific alarm object is queried through the alarm source when the alarm occurs, the corresponding alarm type is determined by the type of alarm object, and then the corresponding drill-down content is matched by the alarm type, and the service identifier of the corresponding alarm type is passed to the corresponding graphical interface.

[0016] Furthermore, the graphical interface includes a dashboard, a histogram, a column chart, a line chart, a topology chart, a table, a span, a relationship chart, and a list.

[0017] In a second aspect, the present invention further provides an electric power information system alarm tracing system based on redundant processing and observation, comprising:

[0018] The object determination module is configured to: determine the traceability object;

[0019] The alarm information determination module is configured to: determine the alarm information corresponding to the traceability object;

[0020] The matching module is configured to: match the alarm type according to the determined alarm information;

[0021] The graphical interface determination module is configured to: obtain a graphical interface corresponding to the alarm information according to the matched alarm type;

[0022] Among them, when matching the alarm type, the trained neural network classification model is used. When the neural network classification model is trained and classified, it is iterated with the help of sparse basis to obtain the input data of the neural network classification model; the alarm information and input data are used as training sets, and the training sets are processed with redundant data; the neural network classification model is trained with the redundantly processed data; when determining the graphical interface, it is judged whether the alarm type is an indicator alarm, if so, an indicator graphical interface is obtained, otherwise it is judged whether the alarm type is a link alarm, if so, a link graphical interface is obtained, otherwise a log graphical interface is obtained.

[0023] In a third aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for tracing the alarm source of an electric power information system based on redundant processing and observation as described in the first aspect.

[0024] In a fourth aspect, the present invention further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for tracing the alarm of an electric power information system based on redundant processing and observation described in the first aspect are implemented.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] In the present invention, a sparse basis is used for iteration to obtain input data of a neural network classification model, the alarm information and the input data are used as a training set, and redundant data processing is performed on the training set, thereby improving the quality of the alarm information and reducing the amount of data, thereby providing a guarantee for improving the accuracy of traceability, reducing data pressure, and improving efficiency; based on this, type matching is performed according to the alarm source, and automatic judgment and determination of the graphical interface display object are performed according to the different types of alarms, and further on the basis of ensuring accuracy, the judgment efficiency is improved, and screening and judgment of the indicator graphical interface display, the link graphical interface display, or the log graphical interface display are performed, thereby realizing the overall alarm traceability and observability of fault information, and further ensuring the accuracy of traceability.

[0027] The present invention queries the specific alarm object through the alarm source when the alarm occurs, determines the corresponding alarm type through the type of the alarm object, and then matches the corresponding drill-down content through the alarm type; based on the drill-down content, it is effectively guaranteed that the controlled power information system has the ability to quickly troubleshoot from the alarm to the specific indicator graphical interface when an alarm occurs in each service, thereby ensuring the stable operation of the controlled power information system.

[0028] The present invention can provide service support for data tracing analysis and alarm tracing of the alarm tracing method of the power information system by querying alarm information, matching alarm drill-down content and drill-down display graphic program; it effectively ensures the accuracy of alarm positioning and rationality of tracing in the entire range of the controlled power information system. The use of alarm tracing can expand the analysis scope of alarm data and improve the accuracy of problem location, thereby achieving more reliable alarm monitoring and control.

[0029] The present invention first determines the graphic interface types with the top two weights of a certain type of fault information through a weight comparison method, and then determines a final graphic interface type through similarity; specifically, a certain type of fault information is represented according to the determined two graphic interface types, and then compared with the pre-stored historical graphic interfaces, and the graphic interface with the highest similarity is selected as the final graphic interface for display, which solves the problem that when there are a large number of image interface types and alarm information, it takes a long time to screen and match when determining which graphic interface to use to display the alarm information. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The drawings in the specification that constitute a part of this embodiment are used to provide a further understanding of this embodiment. The schematic embodiments of this embodiment and their descriptions are used to explain this embodiment and do not constitute improper limitations on this embodiment.

[0031] Figure 1 is a functional block diagram of Embodiment 1 of the present invention;

[0032] Figure 2 This is a judgment flow chart of Example 1 of the present invention. DETAILED DESCRIPTION

[0033] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0034] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0035] Embodiment 1:

[0036] Due to the differences in alarm data, it will be affected by factors such as the type and quantity of alarms, resulting in the inability to accurately locate alarms, thus affecting the alarm tracing of the power information system. For example, a power information system includes several services, each of which has several link alarms, indicator alarms, and log alarms that need to be analyzed. When each alarm occurs, the specific corresponding interface cannot be viewed through the alarm source, resulting in the inability to effectively trace the source of the monitored power information system during alarm tracing. Based on the limited drill-down of existing alarm sources, the alarm tracing will become more complicated as the number of controlled systems increases. Therefore, for monitoring various services in the observable system, it is easy to have too much alarm data but unable to trace the alarm, resulting in the alarm tracing related to the power information system failing to meet actual needs.

[0037] At present, when tracing the alarm of the power information system, it is mainly through checking the specific alarm source, manually determining the specific alarm details according to the alarm source, and then finding the specific corresponding indicators, links or log graphical interfaces by analyzing the alarm details. However, this will increase the operation and maintenance workload of alarm tracing and increase the system operation and maintenance costs. At the same time, manual judgment will also make it impossible to trace the alarm of the controlled system as a whole, resulting in a lack of accurate positioning and tracing, affecting the stability and security of the system.

[0038] In response to the above problems, Figure 1 and Figure 2 As shown, this embodiment provides a method for tracing the source of an alarm in a power information system based on redundant processing and observation, including:

[0039] Determine the traceability object;

[0040] Determine the alarm information corresponding to the traceability object;

[0041] According to the determined alarm information, match the alarm type;

[0042] According to the matching alarm type, the graphical interface corresponding to the alarm information is obtained;

[0043] Among them, when matching the alarm type, the trained neural network classification model is used. When the neural network classification model is trained and classified, it is iterated with the help of sparse basis to obtain the input data of the neural network classification model; the alarm information and input data are used as training sets, and the training sets are processed with redundant data; the neural network classification model is trained with the redundantly processed data; when determining the graphical interface, it is judged whether the alarm type is an indicator alarm, if so, an indicator graphical interface is obtained, otherwise it is judged whether the alarm type is a link alarm, if so, a link graphical interface is obtained, otherwise a log graphical interface is obtained.

[0044] Specifically, when displaying the graphical interface, it is determined whether the alarm type is an indicator alarm. If so, the indicator graphical interface is displayed. Otherwise, it is determined whether the alarm type is a link alarm. If so, the link graphical interface is displayed, otherwise, the log graphical interface is displayed. Type matching is performed according to the alarm source, and the graphical interface display object is automatically judged and determined according to the different alarm types, thereby improving the judgment efficiency, and screening and judgment of the indicator graphical interface display, link graphical interface display or log graphical interface display are performed, thereby achieving overall alarm tracing and observability of fault information, and ensuring the accuracy of tracing. It is effectively guaranteed that the controlled power information system has the ability to quickly troubleshoot from the alarm to the specific graphical interface when an alarm occurs in each service, thereby ensuring the stable operation of the power information system.

[0045] In the method of this embodiment, first, after selecting the system, service, middleware and infrastructure, the corresponding alarm information is queried, and the corresponding drill-down button is matched according to the alarm type; secondly, according to the specific transmission alarm source and time parameters, drill down to the specific graphical interface; finally, the graphical interface is used to locate and display the specific indicators of the alarm. Optionally, it is divided into the steps of querying alarm information, matching alarm drill-down button and drill-down display graphics according to the preset requirements, specifically: when querying the alarm information of the system to which it belongs, query and trace the source display in turn through querying alarm information, matching alarm drill-down button and drill-down display graphics.

[0046] The training process of the neural network classification model for alarm information includes

[0047] The warning information is reconstructed through deep learning compressed sensing to achieve cleaning, elimination and repair of the warning information. The knowledge simplification method in the rough set theory is used to remove redundant attribute features and samples in the warning information, and typical user features are extracted through simplification; the warning information is classified through clustering neural networks.

[0048] Optionally, a Shearlet sparse basis is used as a sparse basis in the compressed sensing reconstruction stage, and iteration is performed to obtain input data of the neural network model; the alarm information and the input data are input into the DnCNN network for training.

[0049] When querying alarm information, you can optionally determine the corresponding alarm type by the type of alarm object. First, merge the alarm objects of the services or hosts corresponding to the system, service, middleware and infrastructure into similar items; secondly, map the merged alarm objects into three categories, namely link alarms, indicator alarms and log alarms.

[0050] When matching the alarm drill-down button, optionally, the corresponding drill-down button is matched by the alarm type, and the service identifier of the corresponding alarm type is passed to the corresponding graphical interface; the drill-down button / drill-down content can be understood as the implementation process of a method, or a page for displaying related content.

[0051] When drilling down to display graphics, it is optional to receive a service ID, and then query the graphical interface of the corresponding alarm object based on the service ID, and then display the alarm information that is convenient for troubleshooting.

[0052] The method in this embodiment queries the specific alarm object through the alarm source when the alarm occurs, determines the corresponding alarm type through the type of alarm object, and then matches the corresponding drill-down button / drill-down content through the alarm type; based on the drill-down button / drill-down content, it is effectively ensured that the controlled power information system has the ability to quickly troubleshoot from the alarm to the specific indicator graphical interface when an alarm occurs in each service, thereby ensuring the stable operation of the controlled power information system.

[0053] In this embodiment, the graphical interface includes a dashboard, a histogram, a bar chart, a line chart, a topology diagram, a table, a span, a relationship diagram, and a list; there are many types of graphical interfaces, and there are many alarm messages in the power information system. It takes a long time to screen and match to determine which graphical interface to use to display the alarm messages. Based on this problem, in some embodiments, a combination of a weight comparison method and a similarity comparison method is introduced to determine the type of graphical interface corresponding to the data group; specifically, different weights are assigned to each type of fault information and each type of graphical interface. The larger the weight, the higher the conformity of the graphical interface type.

[0054] The weight comparison method is used to determine the graphic interface types that rank first and second in weight with a certain type of fault information, and then the final graphic interface type is determined by similarity; specifically, a certain type of fault information is represented according to the determined graphic interface type, and then compared with the pre-stored historical graphic interfaces, and the final graphic interface with the highest similarity is selected for display; it should be noted that the historical graphic interface and the graphic interface with which it is compared are the same in type and the type of alarm information contained; the similarity is equal to the ratio of the overlap between the graphic interface and the historical graphic interface, such as the area overlap of a bar graph or the curvature overlap of a line graph.

[0055] Embodiment 2:

[0056] This embodiment provides an electric power information system alarm tracing system based on redundant processing and observation, including:

[0057] The object determination module is configured to: determine the traceability object;

[0058] The alarm information determination module is configured to: determine the alarm information corresponding to the traceability object;

[0059] The matching module is configured to: match the alarm type according to the determined alarm information;

[0060] The graphical interface determination module is configured to: obtain a graphical interface corresponding to the alarm information according to the matched alarm type;

[0061] Among them, when matching the alarm type, the trained neural network classification model is used. When the neural network classification model is trained and classified, it is iterated with the help of sparse basis to obtain the input data of the neural network classification model; the alarm information and input data are used as training sets, and the training sets are processed with redundant data; the neural network classification model is trained with the redundantly processed data; when determining the graphical interface, it is judged whether the alarm type is an indicator alarm, if so, an indicator graphical interface is obtained, otherwise it is judged whether the alarm type is a link alarm, if so, a link graphical interface is obtained, otherwise a log graphical interface is obtained.

[0062] The working method of the system is the same as the power information system alarm tracing method based on redundant processing and observation in Example 1, and will not be repeated here.

[0063] Embodiment 3:

[0064] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method for tracing the source of an alarm in a power information system based on redundant processing and observation described in Embodiment 1 are implemented.

[0065] Embodiment 4:

[0066] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the method for tracing the alarm source of an electric power information system based on redundant processing and observation described in Example 1 are implemented.

[0067] The above description is only a preferred embodiment of the present embodiment and is not intended to limit the present embodiment. For those skilled in the art, the present embodiment may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present embodiment shall be included in the protection scope of the present embodiment.

Claims

1. A power information system alarm tracing method based on redundant processing and observation, characterized in that: include: Determine the traceability object; Determine the alarm information corresponding to the traceability object; According to the determined alarm information, match the alarm type; According to the matching alarm type, the graphical interface corresponding to the alarm information is obtained; Among them, when matching the alarm type, the trained neural network classification model is used. When the neural network classification model is trained and classified, it is iterated with the help of sparse basis to obtain the input data of the neural network classification model; the alarm information and input data are used as training sets, and the training sets are processed with redundant data; the neural network classification model is trained with the redundantly processed data; when determining the graphical interface, it is judged whether the alarm type is an indicator alarm, if so, an indicator graphical interface is obtained, otherwise it is judged whether the alarm type is a link alarm, if so, a link graphical interface is obtained, otherwise a log graphical interface is obtained.

2. The method for tracing the source of alarms in a power information system based on redundant processing and observation according to claim 1, characterized in that: Traceability objects include systems, services, middleware and infrastructure.

3. The method for tracing the source of alarms in a power information system based on redundant processing and observation according to claim 2, characterized in that: The alarm objects of the services or hosts corresponding to the system, services, middleware and infrastructure are merged into similar items, and the merged alarm objects are mapped into link alarms, indicator alarms and log alarms.

4. The method for tracing the source of alarms in a power information system based on redundant processing and observation according to claim 1, characterized in that: The service identifier of the corresponding alarm type is passed to the corresponding graphical interface.

5. The method for tracing the source of alarms in a power information system based on redundant processing and observation according to claim 4, characterized in that: According to the service identifier, the graphical interface of the corresponding alarm object is queried to display the alarm information.

6. The method for tracing the source of alarms in a power information system based on redundant processing and observation according to claim 1, characterized in that: Through the alarm source when the alarm occurs, the specific alarm object is queried, the corresponding alarm type is determined by the type of alarm object, and then the corresponding drill-down content is matched by the alarm type, and the service identifier of the corresponding alarm type is passed to the corresponding graphical interface.

7. The method for tracing the source of alarms in a power information system based on redundant processing and observation according to claim 1, characterized in that: Graphical interfaces include dashboards, histograms, bar charts, line graphs, topology graphs, tables, spans, relationship graphs, and lists; The weight comparison method is used to determine the two graphic interface types with the highest weights for a certain type of fault information, and then the final graphic interface type is determined by similarity; specifically, a certain type of fault information is represented according to the two determined graphic interface types, and then compared with the pre-stored historical graphic interfaces, and the graphic interface with the highest similarity is selected as the final graphic interface for display.

8. The power information system alarm tracing system based on redundant processing and observation is characterized by: include: The object determination module is configured to: determine the traceability object; The alarm information determination module is configured to: determine the alarm information corresponding to the traceability object; The matching module is configured to: match the alarm type according to the determined alarm information; The graphical interface determination module is configured to: obtain a graphical interface corresponding to the alarm information according to the matched alarm type; Among them, when matching the alarm type, the trained neural network classification model is used. When the neural network classification model is trained and classified, it is iterated with the help of sparse basis to obtain the input data of the neural network classification model; the alarm information and input data are used as training sets, and the training sets are processed with redundant data; the neural network classification model is trained with the redundantly processed data; when determining the graphical interface, it is judged whether the alarm type is an indicator alarm, if so, an indicator graphical interface is obtained, otherwise it is judged whether the alarm type is a link alarm, if so, a link graphical interface is obtained, otherwise a log graphical interface is obtained.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method for tracing the source of an alarm of an electric power information system based on redundant processing and observation are implemented as described in any one of claims 1 to 7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the power information system alarm tracing method based on redundant processing and observation are implemented as described in any one of claims 1-7.

Images