CN114629785B - Alarm position detection and prediction method, device, equipment and medium - Google Patents
Alarm position detection and prediction method, device, equipment and medium Download PDFInfo
- Publication number
- CN114629785B CN114629785B CN202210240162.7A CN202210240162A CN114629785B CN 114629785 B CN114629785 B CN 114629785B CN 202210240162 A CN202210240162 A CN 202210240162A CN 114629785 B CN114629785 B CN 114629785B
- Authority
- CN
- China
- Prior art keywords
- alarm
- node
- nodes
- determining
- management system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0677—Localisation of faults
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
- H04L41/065—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis involving logical or physical relationship, e.g. grouping and hierarchies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/04—Processing captured monitoring data, e.g. for logfile generation
- H04L43/045—Processing captured monitoring data, e.g. for logfile generation for graphical visualisation of monitoring data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Environmental & Geological Engineering (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The application discloses a method, a device and a medium for detecting and predicting an alarm position, which are applied to a power grid operation management system, wherein the method comprises the following steps: determining each alarm position with an alarm function in a power grid operation management system, creating a network topology structure comprising a plurality of nodes based on each alarm position, determining association information among the nodes in the network topology structure, collecting performance indexes in the power grid operation management system according to a preset period, performing corresponding calculation by using the performance indexes, determining alarm nodes from all the nodes in the network topology structure based on calculation results, and determining key alarm positions from all the alarm positions in the power grid operation management system by using the alarm nodes and combining the association information among the nodes. Therefore, the method can detect and predict the key alarm position in the power grid operation management system, and improves the management efficiency of the power grid operation management system.
Description
Technical Field
The present invention relates to the field of fault location, and in particular, to a method, an apparatus, a device, and a medium for detecting and predicting an alarm position.
Background
In the prior art, a plurality of sensors are configured in a power grid, and when a certain position of the power grid fails, alarm information is acquired through the sensors. However, in the current power grid management system, the monitoring, analysis and positioning of a large amount of alarm information are not comprehensive, which is mainly represented by the isolation of the monitoring data of each professional network management system, and when individual fault alarms occur in the network, the fault source can be easily positioned by utilizing the existing network management and monitoring means. However, when a large amount of fault alarm information is monitored in the network, a serious comprehensive fault problem of the power grid often occurs, and often not every alarm information means that the corresponding power grid facilities are faulty, and faults of some power grid nodes or power grid links at key positions may cause large-area fault alarms.
The current mainstream automatic fault positioning method comprises a Bayesian network fault positioning method based on a fault propagation model and a fault positioning method based on case and pattern matching. The Bayesian network fault positioning method based on the fault propagation model solves the problem of fault positioning by identifying the association between the network fault and the alarm information, represents the relationship between the fault source and the fault alarm by probability edges and obtains the fault source capable of explaining the maximum probability of the current fault alarm by using conditional probability. The problem with this approach is that the algorithm complexity is too high. In the modified heuristic algorithm, the algorithm finds all fault sources that can produce the symptom for each fault alarm and calculates their probabilities, ranks all situation probabilities from high to low and selects to join the fault sources in turn until the fault source can interpret the current fault alarm. The improved algorithm improves efficiency, but loses a part of probability information of fault-warning and the solution is not guaranteed to be optimal, so that the fault positioning result may deviate from the actual situation. The fault positioning method based on case and pattern matching is to sum up the matching models such as fault-alarm event tree and code book by analyzing the fault case database and perform fault positioning in a combined mode. The method ignores the influence caused by suspected faults in fault location, and reduces the actual location effect of the method.
From the above, how to avoid the situation that the positioning effect of fault positioning is not good in the prior art in the automatic fault positioning process is a problem to be solved in the field.
Disclosure of Invention
Accordingly, the present application aims to provide a method, apparatus, device and medium for detecting and predicting an alarm position, which can realize accurate positioning of a key alarm position in a power grid operation management system, thereby improving management efficiency of the power grid operation management system. The specific scheme is as follows:
in a first aspect, the present application discloses a method for detecting and predicting an alarm position, which is applied to a power grid operation management system, and includes:
determining each alarm position with an alarm function in a power grid operation management system, creating a network topology structure comprising a plurality of nodes based on each alarm position, and then determining association information among nodes in the network topology structure; the alarm position in the power grid operation management system corresponds to a node in the network topology structure; the association information is information reflecting the association degree between the nodes;
acquiring performance indexes in the power grid operation management system according to a preset period, performing corresponding calculation by utilizing the performance indexes, and determining alarm nodes from all nodes in the network topological structure based on a calculation result;
And determining a key alarm position from all alarm positions in the power grid operation management system by utilizing the alarm nodes and combining the association information among the nodes.
Optionally, the determining the association information between nodes in the network topology includes:
determining historical alarm information corresponding to each alarm position in the power grid operation management system, and determining an association rule between alarm positions by using a preset association rule mining algorithm based on the historical alarm information;
and determining association information among nodes in the network topology structure based on association rules among the alarm positions.
Optionally, the performing corresponding calculation by using the performance index, and then determining an alarm node from all nodes in the network topology based on a calculation result includes:
calculating each performance index corresponding to each node by using a preset anomaly detection algorithm to obtain an index normal probability value corresponding to each performance index, and determining a node normal probability value of each node based on the index normal probability value;
normalizing the node normal probability values of the nodes to obtain health values of the nodes;
And determining the node with the health value smaller than the preset health threshold as an alarm node.
Optionally, after the performance indexes in the power grid operation management system are collected according to a preset period, the method further includes:
extracting performance indexes of the latest N periods corresponding to each node from all the collected performance indexes; n is a positive integer;
correspondingly, the performance index is used for carrying out corresponding calculation, and then the alarm node is determined from all nodes in the network topology structure based on the calculation result, and the method comprises the following steps:
drawing a scatter diagram by using the performance indexes of the latest N periods and the corresponding period time, and performing curve fitting by using a plurality of preset fitting methods and the scatter diagram to obtain a plurality of corresponding fitting curves;
determining an optimal curve from the plurality of fitting curves, and predicting corresponding performance indexes based on the optimal curve;
if the prediction result of any performance index is abnormal, determining the node corresponding to the performance index with the abnormal prediction result as an alarm node.
Optionally, after determining the key alarm positions from all alarm positions in the power grid operation management system, the method further includes:
Determining a node corresponding to the key alarm position in the network topology structure as a key alarm node;
and creating a backup node corresponding to the key alarm node by using a software-defined network technology, and replacing the key alarm node by the backup node to keep the normal operation of the power grid operation management system.
Optionally, after the creating a backup node corresponding to the key alarm node by using a software defined network technology and replacing the key alarm node with the backup node to maintain the normal operation of the power grid operation management system, the method further includes:
checking and repairing the alarm positions corresponding to the key alarm nodes so as to switch the nodes corresponding to the key alarm positions in the network topology structure to the key alarm nodes again after repairing;
and the corresponding backup node is withdrawn, and the key alarm node is switched to an operation node.
Optionally, after the performance indexes in the power grid operation management system are collected according to a preset period, the method further includes:
respectively carrying out data detection on the collected performance indexes;
if any data corresponding to the performance index is detected to be abnormal data, the performance index is adjusted according to a preset data adjustment rule; wherein the abnormal data includes incomplete data, erroneous data, and repeated data.
In a second aspect, the present application discloses a device for detecting and predicting an alarm position, including:
the system comprises a correlation information determining module, a processing module and a processing module, wherein the correlation information determining module is used for determining each alarm position with an alarm function in a power grid operation management system, creating a network topology structure comprising a plurality of nodes based on each alarm position, and then determining correlation information among nodes in the network topology structure; the alarm position in the power grid operation management system corresponds to a node in the network topology structure; the association information is information reflecting the association degree between the nodes;
the alarm node determining module is used for collecting performance indexes in the power grid operation management system according to a preset period, performing corresponding calculation by utilizing the performance indexes, and determining alarm nodes from all nodes in the network topological structure based on a calculation result;
and the key position determining module is used for determining the key alarm position from all alarm positions in the power grid operation management system by utilizing the alarm nodes and combining the association information among the nodes.
In a third aspect, the present application discloses an electronic device, comprising:
A memory for storing a computer program;
and the processor is used for executing the computer program to realize the detection and prediction method of the alarm position.
In a fourth aspect, the present application discloses a computer storage medium for storing a computer program; wherein the computer program when executed by the processor implements the steps of the alert location detection and prediction method disclosed above.
The application firstly establishes a network topology structure comprising a plurality of nodes based on each alarm position by determining each alarm position with an alarm function in a power grid operation management system, then determines the association information among the nodes in the network topology structure, wherein the alarm positions in the power grid operation management system correspond to the nodes in the network topology structure, the association information is information reflecting the association degree among the nodes, then collects performance indexes in the power grid operation management system according to a preset period, carries out corresponding calculation by utilizing the performance indexes, then determines alarm nodes from all the nodes in the network topology structure based on a calculation result, and finally determines key alarm positions from all the alarm positions in the power grid operation management system by utilizing the alarm nodes and combining the association information among the nodes. In this way, the key alarm position in the system is determined by firstly creating a network topology structure and then utilizing the collected performance indexes and combining the association information among the nodes. The method can carry out alarm judgment on each node of the power grid operation management system, and can realize accurate positioning of key alarm positions in the power grid operation management system, so that the management efficiency of the power grid operation management system is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for detecting and predicting an alarm position according to the present application;
FIG. 2 is a schematic diagram of an association generated according to association rules provided by the present application;
FIG. 3 is a flowchart of a specific method for detecting and predicting an alarm position according to the present application;
FIG. 4 is a schematic diagram of a detecting and predicting device for an alarm position according to the present application;
fig. 5 is a block diagram of an electronic device according to the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the prior art, the mainstream automatic fault positioning method generally uses a Bayesian network fault positioning method based on a fault propagation model and a fault positioning method based on case and pattern matching, and the two methods have the problems of inaccurate fault positioning result and poor fault positioning effect. The application provides a method, a device, equipment and a medium for detecting and predicting the alarm position, which can realize the accurate positioning of the key alarm position in the power grid operation management system, thereby improving the management efficiency of the power grid operation management system.
The embodiment of the application discloses a method for detecting and predicting an alarm position, which is applied to a power grid operation management system, and is described with reference to fig. 1, and the method comprises the following steps:
step S11: determining each alarm position with an alarm function in a power grid operation management system, creating a network topology structure comprising a plurality of nodes based on each alarm position, and then determining association information among nodes in the network topology structure; the alarm position in the power grid operation management system corresponds to a node in the network topology structure; the association information is information reflecting the association degree between the nodes.
In this embodiment, the determining the association information between nodes in the network topology may include: determining historical alarm information corresponding to each alarm position in the power grid operation management system, and determining an association rule between alarm positions by using a preset association rule mining algorithm based on the historical alarm information; and determining association information among nodes in the network topology structure based on association rules among the alarm positions.
It should be noted that, in this embodiment, when determining association information between nodes in the network topology, the preset association rule mining algorithm includes, but is not limited to, an Apriori algorithm, and when using the Apriori algorithm to mine association rules between nodes, the specific method may include: firstly, collecting historical performance indexes of all alarm positions in a power grid operation management system, determining an alarm threshold according to each historical performance index, judging whether to add a term value Ip (wherein p is an alarm position ID) according to whether each alarm position alarms, for example, IDs at 5 alarm positions are A, B, C, D, E respectively, and recording alarm results as (I2 and I4) when B, D alarms simultaneously. Then, all frequent bivariate sets are determined from the recorded results, and association rules are extracted from all the frequent bivariate sets. Fig. 2 is a schematic diagram of association generated according to association rules, in which association rules among nodes are determined by arrow pointing, for example, a→b is an association rule, and B and C do not point, which indicates that there is no association rule among BC. It will be appreciated that after the association rules between the nodes are mined according to the Apriori algorithm, the nodes where the association rules exist may be determined as nodes having association, the nodes where the association rules do not exist may be determined as nodes having no association, and the association information may be generated therefrom.
It will be appreciated that in a particular embodiment, the network topology may be initialized after creating a network topology comprising a plurality of nodes based on the alert locations.
Step S12: and acquiring performance indexes in the power grid operation management system according to a preset period, performing corresponding calculation by utilizing the performance indexes, and determining alarm nodes from all nodes in the network topological structure based on a calculation result.
In this embodiment, after the performance indexes in the power grid operation management system are collected according to the preset period, the method may further include: respectively carrying out data detection on the collected performance indexes; if any data corresponding to the performance index is detected to be abnormal data, the performance index is adjusted according to a preset data adjustment rule; wherein the abnormal data includes incomplete data, erroneous data, and repeated data. It should be noted that, due to abnormal factors such as hardware faults, software faults, network time-out, etc., some indexes in some collection batches may not take values, and the collected incomplete data will be cleaned at this time, so that, for the convenience of recognition and processing in the subsequent steps, some default values, such as 0, -1, null, etc., may be used for filling logic to complete. Due to abnormal factors such as hardware faults, software faults, statistical errors and the like, the situation that error data appear in some indexes in some acquisition batches may occur, the collected error data are cleaned at this time, and in order to ensure that the subsequent steps work normally, some replacement logic can be used for correction, such as replacement with 0 or a previous period value and the like. Due to abnormal factors such as hardware faults, software faults, network time-out and the like, the condition that certain indexes in certain acquisition batches have more than one value can occur, the collected repeated data can be cleaned at the moment, and certain reserved logic can be used for correction in order to ensure that the subsequent steps work normally. Further, when the abnormal data occurs in the process of collecting the performance indexes, the abnormal data is adjusted by the method, and then subsequent operation is performed according to the adjusted performance index data.
In this embodiment, the performing corresponding calculation by using the performance index, and then determining the alarm node from all nodes in the network topology based on the calculation result may include: calculating each performance index corresponding to each node by using a preset anomaly detection algorithm to obtain an index normal probability value corresponding to each performance index, and determining a node normal probability value of each node based on the index normal probability value; normalizing the node normal probability values of the nodes to obtain health values of the nodes; and determining the node with the health value smaller than the preset health threshold as an alarm node. It will be appreciated that by this operation, detection of the current alarm condition in the current grid operation management system may be accomplished. In a specific embodiment, the performance index of the last period may be extracted from all the performance indexes in the power grid operation management system, and subsequent calculation is performed by using the performance index of the last period to determine the alarm condition of the current system.
Further, in one possible implementation manner, if a plurality of network topologies exist in the current power grid operation management system, after the health value of each node is obtained, the health value of each network topology of the power grid operation management system at the current moment can be calculated according to the health value of each node, if the health value of any network topology is lower than a preset threshold, it is determined that a fault or a load is higher at the current topology position, and the corresponding network topology is determined as an alarm structure. Correspondingly, when the key alarm positions are determined from all alarm positions in the power grid operation management system by utilizing the alarm nodes and combining the association information among the nodes, the key alarm positions can be determined from all alarm positions in the power grid operation management system by utilizing the alarm nodes and the alarm structure and combining the association information among the nodes.
In this embodiment, after the performance indexes in the power grid operation management system are collected according to the preset period, the method may further include: extracting performance indexes of the latest N periods corresponding to each node from all the collected performance indexes; n is a positive integer. Correspondingly, the performing corresponding calculation by using the performance index, and then determining the alarm node from all nodes in the network topology structure based on the calculation result may include: drawing a scatter diagram by using the performance indexes of the latest N periods and the corresponding period time, and performing curve fitting by using a plurality of preset fitting methods and the scatter diagram to obtain a plurality of corresponding fitting curves; determining an optimal curve from the plurality of fitting curves, and predicting corresponding performance indexes based on the optimal curve; if the prediction result of any performance index is abnormal, determining the node corresponding to the performance index with the abnormal prediction result as an alarm node. It will be appreciated that prediction of future alarm conditions in the current grid operation management system may be accomplished by this operation.
Further, the value of N may be determined during implementation according to performance index collection frequency, required fault prediction accuracy, and other considerations. If the acquisition frequency is 1 minute, n can be set to 10, 30 or 60.
In a specific embodiment, when curve fitting is performed, first, the values of the last N periods of the cluster dimension are aggregated for the index name and the time period of the last N periods of each topology position, and for a certain index and a certain period, the median index value of all the nodes is used as the index value of the whole cluster. Let the values of the last N cycles of the cluster dimension of the calculated index Y be yi, where i=1, 2, …, N, respectively. Let xi be the number of system time milliseconds at the ith index acquisition instant, then these n values can be represented by (xi, yi). There is a curve y=Φ (x) that needs to be made to pass approximately through these n points. The curve fitting method described in the present embodiment includes, but is not limited to, a least square method, an exponential smoothing method.
Step S13: and determining a key alarm position from all alarm positions in the power grid operation management system by utilizing the alarm nodes and combining the association information among the nodes.
It will be appreciated that there may be multiple critical alert locations in the system or there may be only one, depending on the particular implementation.
According to the embodiment, firstly, each alarm position with an alarm function in a power grid operation management system is determined, a network topology structure comprising a plurality of nodes is created based on each alarm position, then association information among the nodes in the network topology structure is determined, wherein the alarm positions in the power grid operation management system correspond to the nodes in the network topology structure, the association information is information reflecting the association degree among the nodes, then performance indexes in the power grid operation management system are acquired according to a preset period, the performance indexes are utilized to perform corresponding calculation, alarm nodes are determined from all the nodes in the network topology structure based on a calculation result, and finally, key alarm positions are determined from all the alarm positions in the power grid operation management system by utilizing the alarm nodes and combining the association information among the nodes. In this embodiment, two methods for determining the alarm node are provided, one is a method for detecting the alarm condition of the node in the current system operation, and the other is a method for predicting the alarm condition of all nodes in the system, so that the current alarm node in the system can be detected by combining the two methods, the future alarm node of the system can be estimated at the same time, finally, the key alarm position of the system is determined by combining the association information among the nodes, and finally, the accurate positioning of the key alarm position in the power grid operation management system is realized, thereby improving the management efficiency of the power grid operation management system.
Fig. 3 is a flowchart of a specific method for detecting and predicting an alarm position, which is provided in an embodiment of the present application, and is applied to a power grid operation management system. Referring to fig. 3, the method includes:
step S21: determining each alarm position with an alarm function in a power grid operation management system, creating a network topology structure comprising a plurality of nodes based on each alarm position, and then determining association information among nodes in the network topology structure; the alarm position in the power grid operation management system corresponds to a node in the network topology structure; the association information is information reflecting the association degree between the nodes.
Step S22: and acquiring performance indexes in the power grid operation management system according to a preset period, performing corresponding calculation by utilizing the performance indexes, and determining alarm nodes from all nodes in the network topological structure based on a calculation result.
Step S23: and determining a key alarm position from all alarm positions in the power grid operation management system by utilizing the alarm nodes and combining the association information among the nodes.
Step S24: and determining the node corresponding to the key alarm position in the network topology structure as a key alarm node.
It can be understood that, in this step, the node corresponding to the key alarm position is determined as the key alarm node, so that the backup processing is performed on the key alarm node subsequently.
Step S25: and creating a backup node corresponding to the key alarm node by using a software-defined network technology, and replacing the key alarm node by the backup node to keep the normal operation of the power grid operation management system.
It should be noted that the techniques of creating backup nodes of the present invention include, but are not limited to, the software defined networking techniques.
In this embodiment, after determining the key alarm node, metadata of the key alarm node may be obtained from the distributed file system, where the metadata is used to copy a service processing function of the key alarm node, and then a backup node is generated based on SDN (i.e. Software Defined Network, software defined network) technology, and an upstream node and a downstream node corresponding to the key alarm node are obtained from a network topology structure, so as to generate a backup network topology and a backup path for the key alarm node, synchronize the metadata of the key alarm node to the backup node, and connect the backup node with the upstream node and the downstream node, thereby completing reconstruction of the network topology structure, so that a power grid operation management system can use the backup node to perform normal operation, and avoid that the normal operation of the power grid management system is not affected when the topology node at the key alarm position is checked in subsequent steps, and truly achieve maintenance of the non-inductive system. It is understood that the backup node is connected to a logical node corresponding to the critical alert node.
In this embodiment, after the creating, by using a software-defined network technology, a backup node corresponding to the key alarm node and replacing the key alarm node with the backup node to maintain the normal operation of the power grid operation management system, the method may further include: checking and repairing the alarm positions corresponding to the key alarm nodes so as to switch the nodes corresponding to the key alarm positions in the network topology structure to the key alarm nodes again after repairing; and the corresponding backup node is withdrawn, and the key alarm node is switched to an operation node. After the backup node is established and the normal operation of the system is carried out by utilizing the backup node, the key alarm node is checked, and after the fault risk is removed, the key alarm node is switched to the checked key alarm node again to realize the normal operation again.
It should be noted that, in general, by checking the key alarm node, removing the fault risk, and re-switching to the checked key alarm node, the normal operation can be realized again, and the problem will not occur when the alarm detection and prediction are performed again by using the method for detecting and predicting the alarm position in the method. But if it is predicted that the topology node after inspection still fails, the backup node needs to be regenerated for inspection again.
Flexible network configuration and management is made possible by the software defined networking technology separating the data plane and the control plane of a legacy network. In an SDN network, network equipment is only responsible for simple data forwarding and can adopt general hardware; the original operating system in charge of control is extracted into an independent network operating system in charge of adapting different service characteristics, and the communication between the network operating system and the service characteristics and between the network operating system and the hardware devices can be realized through programming.
In the invention, as only one backup node is needed to be generated as long as the key alarm node exists, only one backup node can be needed at the same time, and a plurality of backup nodes can be needed at the same time, so that the unknown situation is many, if all the topology nodes are backed up with one backup node in advance, the cost is too high, therefore, through the software defined network technology, one backup node is generated when one backup node is needed to be generated, when the generated backup node is not needed any more, the backup node is withdrawn, the process does not need extra hardware expenditure, and the cost can be greatly saved.
According to the embodiment, the node backup is carried out on the determined key alarm nodes, the corresponding backup nodes are generated by utilizing the software defined network technology to replace the original key alarm nodes to work, the normal operation of the power grid operation management system is not affected when all the nodes are checked later, the noninductive maintenance of the system is truly realized, and when the key alarm nodes are checked and repaired, the corresponding backup nodes are withdrawn, so that the cost can be greatly saved, and the high efficiency and the flexibility of power grid management are realized.
Referring to fig. 4, an embodiment of the present application discloses a device for detecting and predicting an alarm position, which may specifically include:
the association information determining module 11 is configured to determine each alarm position with an alarm function in the power grid operation management system, create a network topology structure including a plurality of nodes based on each alarm position, and then determine association information between nodes in the network topology structure; the alarm position in the power grid operation management system corresponds to a node in the network topology structure; the association information is information reflecting the association degree between the nodes;
the alarm node determining module 12 is configured to collect performance indexes in the power grid operation management system according to a preset period, perform corresponding calculation by using the performance indexes, and then determine alarm nodes from all nodes in the network topology structure based on a calculation result;
and the key position determining module 13 is used for determining the key alarm position from all alarm positions in the power grid operation management system by utilizing the alarm nodes and combining the association information among the nodes.
In some specific embodiments, the association information determining module 11 includes:
The system comprises an association rule determining unit, a control unit and a control unit, wherein the association rule determining unit is used for determining historical alarm information corresponding to each alarm position in the power grid operation management system and determining association rules among alarm positions by utilizing a preset association rule mining algorithm based on the historical alarm information;
and the information determining unit is used for determining the association information among the nodes in the network topological structure based on the association rule among the alarm positions.
In some embodiments, the alert node determining module 12 includes:
the probability value determining unit is used for calculating each performance index corresponding to each node by using a preset anomaly detection algorithm to obtain an index normal probability value corresponding to each performance index, and determining a node normal probability value of each node based on the index normal probability value;
the health degree value determining unit is used for carrying out normalization processing on the node normal probability values of the nodes so as to obtain health degree values of the nodes;
and the first node determining unit is used for determining the node with the health degree value smaller than the preset health degree threshold value as the alarm node.
In some embodiments, the method for detecting and predicting an alarm position further includes:
The performance index extraction unit is used for extracting the performance index of the latest N periods corresponding to each node from all the collected performance indexes; n is a positive integer;
accordingly, the alarm node determining module 12 includes:
a curve fitting unit, configured to draw a scatter diagram by using the performance indexes of the last N periods and the corresponding period time, and perform curve fitting by using a preset plurality of fitting methods and the scatter diagram, so as to obtain a corresponding plurality of fitting curves;
the optimal curve determining unit is used for determining an optimal curve from the plurality of fitting curves and predicting corresponding performance indexes based on the optimal curve;
and the second node determining unit is used for determining the node corresponding to the performance index with the abnormal predicted result as the alarm node if the predicted result of any performance index is abnormal.
In some embodiments, the method for detecting and predicting an alarm position further includes:
a key alarm node determining unit, configured to determine a node corresponding to the key alarm position in the network topology structure as a key alarm node;
and the backup node creation unit is used for creating backup nodes corresponding to the key alarm nodes by using a software defined network technology, and using the backup nodes to replace the key alarm nodes to keep the normal operation of the power grid operation management system.
In some embodiments, the method for detecting and predicting an alarm position further includes:
the node checking unit is used for checking and repairing the alarm position corresponding to the key alarm node so as to switch the node corresponding to the key alarm position in the network topology structure to the key alarm node again after repairing;
and the backup node revocation unit is used for revoke the corresponding backup node and switching the key alarm node into an operation node.
In some embodiments, the method for detecting and predicting an alarm position further includes:
the data detection unit is used for respectively carrying out data detection on the collected performance indexes;
the data adjustment unit is used for adjusting the performance index according to a preset data adjustment rule if the data corresponding to any performance index is detected to be abnormal data; wherein the abnormal data includes incomplete data, erroneous data, and repeated data.
The application firstly establishes a network topology structure comprising a plurality of nodes based on each alarm position by determining each alarm position with an alarm function in a power grid operation management system, then determines the association information among the nodes in the network topology structure, wherein the alarm positions in the power grid operation management system correspond to the nodes in the network topology structure, the association information is information reflecting the association degree among the nodes, then collects performance indexes in the power grid operation management system according to a preset period, carries out corresponding calculation by utilizing the performance indexes, then determines alarm nodes from all the nodes in the network topology structure based on a calculation result, and finally determines key alarm positions from all the alarm positions in the power grid operation management system by utilizing the alarm nodes and combining the association information among the nodes. In this way, the key alarm position in the system is determined by firstly creating a network topology structure and then utilizing the collected performance indexes and combining the association information among the nodes. The method can carry out alarm judgment on each node of the power grid operation management system, and can realize accurate positioning of key alarm positions in the power grid operation management system, so that the management efficiency of the power grid operation management system is improved.
Further, the embodiment of the present application further discloses an electronic device, and fig. 5 is a block diagram of an electronic device 20 according to an exemplary embodiment, where the content of the diagram is not to be considered as any limitation on the scope of use of the present application.
Fig. 5 is a schematic structural diagram of an electronic device 20 according to an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a display screen 24, an input-output interface 25, a communication interface 26, and a communication bus 27. Wherein the memory 22 is configured to store a computer program that is loaded and executed by the processor 21 to implement relevant steps in the alert location detection and prediction method disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in the present embodiment may be specifically an electronic computer.
In this embodiment, the power supply 23 is configured to provide an operating voltage for each hardware device on the electronic device 20; the communication interface 26 can create a data transmission channel between the electronic device 20 and an external device, and the communication protocol to be followed is any communication protocol applicable to the technical solution of the present application, which is not limited herein in detail; the input/output interface 25 is used for acquiring external input data or outputting external output data, and the specific interface type thereof may be selected according to the specific application requirement, which is not limited herein.
The memory 22 may be a carrier for storing resources, such as a read-only memory, a random access memory, a magnetic disk, or an optical disk, and the resources stored thereon may include an operating system 221, a computer program 222, and the like, and the storage may be temporary storage or permanent storage.
The operating system 221 is used for managing and controlling various hardware devices on the electronic device 20 and computer programs 222, which may be Windows Server, netware, unix, linux, etc. The computer program 222 may further include a computer program that can be used to perform other specific tasks in addition to the computer program that can be used to perform the method of detecting and predicting the location of an alert performed by the electronic device 20 as disclosed in any of the previous embodiments.
Further, the present application also discloses a computer readable storage medium, where the computer readable storage medium includes a random access Memory (Random Access Memory, RAM), a Memory, a Read-Only Memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a magnetic disk, or any other form of storage medium known in the art. The computer program, when executed by the processor, implements the foregoing disclosed alert location detection and prediction method. For specific steps of the method, reference may be made to the corresponding contents disclosed in the foregoing embodiments, and no further description is given here.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section. Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The method, the device, the equipment and the storage medium for detecting and predicting the alarm position provided by the invention are described in detail, and specific examples are applied to the description of the principle and the implementation mode of the invention, and the description of the examples is only used for helping to understand the method and the core idea of the invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (9)
1. A detection and prediction method for alarm position is applied to a power grid operation management system, and comprises the following steps:
determining each alarm position with an alarm function in a power grid operation management system, creating a network topology structure comprising a plurality of nodes based on each alarm position, and then determining association information among nodes in the network topology structure; the alarm position in the power grid operation management system corresponds to a node in the network topology structure; the association information is information reflecting the association degree between the nodes;
acquiring performance indexes in the power grid operation management system according to a preset period, performing corresponding calculation by utilizing the performance indexes, and determining alarm nodes from all nodes in the network topological structure based on a calculation result;
determining key alarm positions from all alarm positions in the power grid operation management system by utilizing the alarm nodes and combining the association information among the nodes;
wherein, after the performance indexes in the power grid operation management system are collected according to a preset period, the method further comprises: extracting performance indexes of the latest N periods corresponding to each node from all the collected performance indexes; n is a positive integer; correspondingly, the performance index is used for carrying out corresponding calculation, and then the alarm node is determined from all nodes in the network topology structure based on the calculation result, and the method comprises the following steps: drawing a scatter diagram by using the performance indexes of the latest N periods and the corresponding period time, and performing curve fitting by using a plurality of preset fitting methods and the scatter diagram to obtain a plurality of corresponding fitting curves; determining an optimal curve from the plurality of fitting curves, and predicting corresponding performance indexes based on the optimal curve; if the prediction result of any performance index is abnormal, determining the node corresponding to the performance index with the abnormal prediction result as an alarm node.
2. The method for detecting and predicting an alarm location according to claim 1, wherein determining association information between nodes in the network topology includes:
determining historical alarm information corresponding to each alarm position in the power grid operation management system, and determining an association rule between alarm positions by using a preset association rule mining algorithm based on the historical alarm information;
and determining association information among nodes in the network topology structure based on association rules among the alarm positions.
3. The method for detecting and predicting an alarm location according to claim 1, wherein the performing a corresponding calculation using the performance index and then determining alarm nodes from all nodes in the network topology based on a calculation result comprises:
calculating each performance index corresponding to each node by using a preset anomaly detection algorithm to obtain an index normal probability value corresponding to each performance index, and determining a node normal probability value of each node based on the index normal probability value;
normalizing the node normal probability values of the nodes to obtain health values of the nodes;
And determining the node with the health value smaller than the preset health threshold as an alarm node.
4. The method for detecting and predicting an alarm location according to claim 1, wherein after determining a key alarm location from all alarm locations in the grid operation management system, the method further comprises:
determining a node corresponding to the key alarm position in the network topology structure as a key alarm node;
and creating a backup node corresponding to the key alarm node by using a software-defined network technology, and replacing the key alarm node by the backup node to keep the normal operation of the power grid operation management system.
5. The method for detecting and predicting an alarm position according to claim 4, wherein after creating a backup node corresponding to the key alarm node by using a software-defined network technology and replacing the key alarm node with the backup node to maintain normal operation of the power grid operation management system, further comprising:
checking and repairing the alarm positions corresponding to the key alarm nodes so as to switch the nodes corresponding to the key alarm positions in the network topology structure to the key alarm nodes again after repairing;
And the corresponding backup node is withdrawn, and the key alarm node is switched to an operation node.
6. The method for detecting and predicting an alarm position according to any one of claims 1 to 5, wherein after the performance indexes in the power grid operation management system are collected according to a preset period, the method further comprises:
respectively carrying out data detection on the collected performance indexes;
if any data corresponding to the performance index is detected to be abnormal data, the performance index is adjusted according to a preset data adjustment rule; wherein the abnormal data includes incomplete data, erroneous data, and repeated data.
7. A device for detecting and predicting an alarm position, comprising:
the system comprises a correlation information determining module, a processing module and a processing module, wherein the correlation information determining module is used for determining each alarm position with an alarm function in a power grid operation management system, creating a network topology structure comprising a plurality of nodes based on each alarm position, and then determining correlation information among nodes in the network topology structure; the alarm position in the power grid operation management system corresponds to a node in the network topology structure; the association information is information reflecting the association degree between the nodes;
The alarm node determining module is used for collecting performance indexes in the power grid operation management system according to a preset period, performing corresponding calculation by utilizing the performance indexes, and determining alarm nodes from all nodes in the network topological structure based on a calculation result;
the key position determining module is used for determining key alarm positions from all alarm positions in the power grid operation management system by utilizing the alarm nodes and combining the association information among the nodes;
the device is also used for extracting the performance indexes of the latest N periods corresponding to each node from all the collected performance indexes; n is a positive integer; correspondingly, the alarm node determining module is specifically further configured to draw a scatter diagram by using the performance indexes of the latest N periods and the corresponding period time, and perform curve fitting by using a preset plurality of fitting methods and the scatter diagram to obtain a corresponding plurality of fitting curves; determining an optimal curve from the plurality of fitting curves, and predicting corresponding performance indexes based on the optimal curve; if the prediction result of any performance index is abnormal, determining the node corresponding to the performance index with the abnormal prediction result as an alarm node.
8. An electronic device comprising a processor and a memory; wherein the processor, when executing the computer program stored in the memory, implements the method for detecting and predicting an alert location according to any one of claims 1 to 6.
9. A computer-readable storage medium storing a computer program; wherein the computer program, when executed by a processor, implements the method for detecting and predicting an alert location according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210240162.7A CN114629785B (en) | 2022-03-10 | 2022-03-10 | Alarm position detection and prediction method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210240162.7A CN114629785B (en) | 2022-03-10 | 2022-03-10 | Alarm position detection and prediction method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114629785A CN114629785A (en) | 2022-06-14 |
| CN114629785B true CN114629785B (en) | 2023-08-11 |
Family
ID=81902327
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210240162.7A Active CN114629785B (en) | 2022-03-10 | 2022-03-10 | Alarm position detection and prediction method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114629785B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104796273A (en) * | 2014-01-20 | 2015-07-22 | 中国移动通信集团山西有限公司 | Method and device for diagnosing root of network faults |
| CN105515844A (en) * | 2015-12-01 | 2016-04-20 | 国家电网公司 | System for improving software defined network reliability |
| CN110445665A (en) * | 2019-09-06 | 2019-11-12 | 国网江苏省电力公司信息通信分公司 | Based on the powerline network alarm association method for digging for improving GSP |
| WO2021051618A1 (en) * | 2019-09-20 | 2021-03-25 | 平安科技（深圳）有限公司 | Abnormality early warning method, device, server and storage medium |
| CN112803592A (en) * | 2021-01-13 | 2021-05-14 | 广东省电力开发有限公司 | Intelligent fault early warning method and system suitable for distributed power station |
| CN112822052A (en) * | 2021-01-08 | 2021-05-18 | 河海大学 | Network fault root cause positioning method based on network topology and alarm |
| CN113254254A (en) * | 2021-07-14 | 2021-08-13 | 南京中兴新软件有限责任公司 | Root cause positioning method and device of system fault, storage medium and electronic device |
| WO2021179643A1 (en) * | 2020-03-12 | 2021-09-16 | 华为技术有限公司 | Fault processing method, apparatus and system |
| CN113612656A (en) * | 2021-07-26 | 2021-11-05 | 招商银行股份有限公司 | Network flow detection method and device, terminal equipment and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10739396B2 (en) * | 2016-10-03 | 2020-08-11 | General Electric Technology Gmbh | Enhanced disturbance management of a power grid system |
| US10547499B2 (en) * | 2017-09-04 | 2020-01-28 | International Business Machines Corporation | Software defined failure detection of many nodes |
| US20190361759A1 (en) * | 2018-05-22 | 2019-11-28 | At&T Intellectual Property I, L.P. | System and method to identify failed points of network impacts in real time |
-
2022
- 2022-03-10 CN CN202210240162.7A patent/CN114629785B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104796273A (en) * | 2014-01-20 | 2015-07-22 | 中国移动通信集团山西有限公司 | Method and device for diagnosing root of network faults |
| CN105515844A (en) * | 2015-12-01 | 2016-04-20 | 国家电网公司 | System for improving software defined network reliability |
| CN110445665A (en) * | 2019-09-06 | 2019-11-12 | 国网江苏省电力公司信息通信分公司 | Based on the powerline network alarm association method for digging for improving GSP |
| WO2021051618A1 (en) * | 2019-09-20 | 2021-03-25 | 平安科技（深圳）有限公司 | Abnormality early warning method, device, server and storage medium |
| WO2021179643A1 (en) * | 2020-03-12 | 2021-09-16 | 华为技术有限公司 | Fault processing method, apparatus and system |
| CN112822052A (en) * | 2021-01-08 | 2021-05-18 | 河海大学 | Network fault root cause positioning method based on network topology and alarm |
| CN112803592A (en) * | 2021-01-13 | 2021-05-14 | 广东省电力开发有限公司 | Intelligent fault early warning method and system suitable for distributed power station |
| CN113254254A (en) * | 2021-07-14 | 2021-08-13 | 南京中兴新软件有限责任公司 | Root cause positioning method and device of system fault, storage medium and electronic device |
| CN113612656A (en) * | 2021-07-26 | 2021-11-05 | 招商银行股份有限公司 | Network flow detection method and device, terminal equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 刘军 ; 楚家辉 ; .基于网络拓扑结构的告警事件关联分析算法研究.数字技术与应用.2017,(第04期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114629785A (en) | 2022-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5910727B2 (en) | Operation management apparatus, operation management method, and program | |
| US11294754B2 (en) | System and method for contextual event sequence analysis | |
| US11348023B2 (en) | Identifying locations and causes of network faults | |
| CN105325023A (en) | Method and network device for cell anomaly detection | |
| CN106685676B (en) | Node switching method and device | |
| CN112769605B (en) | Heterogeneous multi-cloud operation and maintenance management method and hybrid cloud platform | |
| CN104639368A (en) | Method and device for processing faults of communications network equipment | |
| CN111353911A (en) | Power equipment operation and maintenance method, system, equipment and storage medium | |
| CN102684902B (en) | Based on the network failure locating method of probe prediction | |
| CN116719664B (en) | Application and cloud platform cross-layer fault analysis method and system based on micro-service deployment | |
| CN117289085A (en) | Multi-line fault analysis and diagnosis method and system | |
| CN112000504A (en) | Fault processing method and device for computing node and electronic equipment | |
| CN115800272A (en) | Power grid fault analysis method, system, terminal and medium based on topology identification | |
| CN114878960A (en) | Fault diagnosis method, storage medium, power acquisition terminal, and fault diagnosis system | |
| CN109309594B (en) | Method, device, equipment and storage medium for analyzing power failure of communication equipment | |
| CN108512675B (en) | Network diagnosis method and device, control node and network node | |
| CN114629785B (en) | Alarm position detection and prediction method, device, equipment and medium | |
| CN115825656B (en) | Fault monitoring method, device and system for power distribution network of new energy photovoltaic power station | |
| CN115016976B (en) | Root cause positioning method, device, equipment and storage medium | |
| CN116299129A (en) | All-fiber current transformer state detection and analysis method, device and medium | |
| CN113533891A (en) | Fault diagnosis system and device | |
| CN113065001A (en) | Fault loss stopping method and device | |
| CN114629776A (en) | Fault analysis method and device based on graph model | |
| CN114414938B (en) | Dynamic response method and system for power distribution network faults | |
| CN117613908B (en) | Intelligent operation and maintenance method and system based on power distribution network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |