Fault handling strategy determination method and apparatus, electronic device, and storage medium

Abstract

Embodiments of the present application disclose a fault processing strategy determination method and device, electronic equipment and a storage medium, and relate to the technical field of smart grids. The specific implementation scheme is: obtaining fault information of a smart grid, and determining a fault classification to which the fault information belongs according to a preset fault decision tree; determining a fault level according to attribute information of the fault information in the fault classification; and determining a fault processing strategy according to the fault level. According to the embodiments of the present application, the fault information is divided into fault classifications according to the preset fault decision tree, and corresponding fault processing strategies for processing fault information are determined for different fault classifications, so that quick matching of fault information and fault processing strategies can be realized, the accuracy of determination of a fault processing scheme is improved, and the fault identification time can be reduced.

Description

Technical Field

[0001] This invention relates to the field of smart grid technology, and in particular to a method, apparatus, electronic device, and storage medium for determining fault handling strategies. Background Technology

[0002] With the promotion and popularization of smart substations, the physical circuits between equipment within the station have become a logical connection, and the information transmission method has become concealed transmission. The fault alarm data of the secondary circuit of the smart substation is mainly obtained through the alarm information of the integrated automation system and the monitoring information of the network analysis device.

[0003] Currently, faults in the secondary circuit still rely on the work experience of the staff and the corresponding professional equipment. When a fault information comes in, the fault location is roughly located based on experience, and then the specific location is searched upstream and downstream of the fault location.

[0004] However, existing solutions rely heavily on staff, increasing workload, and make it difficult to accurately classify faults, preventing faults from being quickly matched with fault handling strategies and increasing fault handling time. Summary of the Invention

[0005] This invention provides a method, apparatus, electronic device, and storage medium for determining fault handling strategies, so as to achieve rapid matching of fault information and fault handling strategies, improve the accuracy of fault handling scheme determination, and reduce fault identification time.

[0006] In a first aspect, embodiments of the present invention provide a method for determining a fault handling strategy, including:

[0007] Acquire fault information of the smart grid and determine the fault classification to which the fault information belongs based on a preset fault decision tree;

[0008] The fault level is determined based on the attribute information of the fault information within the fault category.

[0009] Determine the fault handling strategy based on the fault level.

[0010] Secondly, embodiments of the present invention also provide a smart grid fault handling strategy determination device, comprising:

[0011] The fault classification module is used to acquire fault information of the smart grid and determine the fault classification to which the fault information belongs based on a preset fault decision tree.

[0012] The fault level determination module is used to determine the fault level based on the attribute information of the fault information within the fault category.

[0013] The strategy determination module is used to determine the fault handling strategy based on the fault level.

[0014] Thirdly, embodiments of the present invention also provide an electronic device, comprising:

[0015] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the smart grid fault handling strategy determination method according to any one of the embodiments of the present invention.

[0016] Fourthly, embodiments of the present invention also provide a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, which are used to cause a processor to execute and implement the smart grid fault handling strategy determination method of any one of the embodiments of the present invention.

[0017] According to the technical solution of the present invention, the acquired fault information is classified according to a preset fault decision tree, the fault level of the fault information is determined according to the attribute information of the fault information in the fault classification, and the corresponding fault handling strategy is determined for different fault levels. This realizes the rapid matching of fault information and fault handling strategy, improves the accuracy of fault handling scheme determination, and reduces fault identification time.

[0018] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart of a fault handling strategy determination method provided in Embodiment 1 of the present invention;

[0021] Figure 2 This is a flowchart of another fault handling strategy determination method provided according to Embodiment 2 of the present invention;

[0022] Figure 3 A flowchart of another fault handling strategy determination method provided in Embodiment 3 of the present invention;

[0023] Figure 4 This is a flowchart of another fault handling strategy determination method provided in Embodiment 4 of the present invention;

[0024] Figure 5 This is a schematic diagram of a smart grid fault handling strategy determination device according to Embodiment 5 of the present invention;

[0025] Figure 6 This is a schematic diagram of the structure of an electronic device according to Embodiment Six of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] Example 1

[0029] Figure 1 The flowchart of a fault handling strategy determination method is provided in Embodiment 1 of the present invention. This embodiment is applicable to the analysis and identification of fault information of smart grids. The method can be executed by a smart grid fault handling strategy determination device, which can be implemented in hardware and / or software. The smart grid fault handling strategy determination device can be configured in an electronic device, which may include a laptop, desktop computer, smart tablet, etc. The present invention does not limit this.

[0030] like Figure 1 As shown, the fault handling strategy determination method provided in this embodiment may include:

[0031] S110. Obtain fault information of the smart grid and determine the fault classification to which the fault information belongs based on the preset fault decision tree.

[0032] In this embodiment, fault information can be understood as fault data generated when equipment in the smart grid has problems / errors. For example, alarm information of the integrated automation system is obtained: abnormal alarm signals of smart devices, monitoring alarm signals of circuit breakers and alarm signals of power systems, SV sampling messages and GOOSE communication messages recorded by network analysis devices, and alarm signals of smart devices: abnormal data sampling, abnormal device self-test, power failure, etc.

[0033] A pre-defined fault decision tree can be understood as a tree structure pre-set according to actual conditions, where each internal node represents a test on an attribute, each branch represents a test output, and each leaf node represents a fault category. A pre-defined fault decision tree can be understood as a method for specifically classifying fault information; fault classification can include different fault categories, for example, data sampling anomalies, device self-test anomalies, power failure faults, etc.

[0034] Specifically, when a fault occurs in the smart grid, fault information can be collected, which may include abnormal alarm signals from smart devices, monitoring alarm signals from circuit breakers, alarm signals from the power system, SV sampling messages and GOOSE communication messages recorded by network analysis devices, and alarm signals from smart devices such as abnormal data sampling, abnormal device self-test, and power failure. A preset fault decision tree is used to classify the fault information, starting from the root node and classifying sequentially into smaller partitions until the leaf node is reached, thus determining the specific category of the collected fault information.

[0035] S120. Determine the fault level according to the attribute information of the fault information within the fault category.

[0036] In this embodiment, the attribute information of the fault information includes the distribution / quantity of attribute parameters in the fault information; the fault level is preset according to the actual situation and represents the severity of the fault. For example, if the result of the fault information analysis is that it will have a significant impact on the smart grid and affect the normal use and operation of the smart grid, then the fault level is high; if the result of the fault information analysis is that it only affects the function of a device but does not affect the normal use and operation, then the fault level is low.

[0037] Specifically, when a fault occurs, the information of the attribute parameters in the fault classification can be analyzed, the distribution of faulty devices, fault content and fault causes in each attribute information can be statistically analyzed, the severity of the fault can be analyzed, and then the fault level can be determined according to the pre-set fault level.

[0038] S130. Determine the fault handling strategy based on the fault level.

[0039] In this embodiment, the fault handling strategy is a pre-set method for handling different levels of faults, based on the actual situation.

[0040] Specifically, when a fault occurs, the fault level can be determined by the severity of the fault and whether it requires immediate handling by maintenance personnel. Then, a pre-set fault handling strategy corresponding to the fault level can be found.

[0041] According to the technical solution provided in the embodiments of the present invention, when a fault occurs in the smart grid, fault information is collected, and the fault classification of the fault information is determined according to a preset fault decision tree. The attribute information of the fault information in the fault classification is analyzed to determine the fault level, and the fault handling strategy is determined according to the determined fault level. This realizes the rapid matching of fault information and fault handling strategy, improves the accuracy of fault handling scheme determination, and reduces fault identification time.

[0042] Based on the above embodiments, obtaining fault information of the smart grid includes:

[0043] Collect fault alarm information from smart devices, circuit breakers, and power systems within the smart grid as fault information;

[0044] Network anomaly messages recorded by the network analysis device of the smart grid are extracted as fault information.

[0045] In this embodiment, a circuit breaker refers to a switching device capable of closing, carrying, and interrupting current under normal circuit conditions and capable of closing, carrying, and interrupting current under abnormal circuit conditions within a specified time; fault alarm information is an alarm signal issued when a fault occurs; a network analysis device is a device used in intelligent substations that has the functions of recording network messages, online and offline analysis of network events, and uploading information, and consists of one or more network recording and analysis units and a management unit equipped with integrated human-machine interface software; a network abnormal message is a data unit that contains network abnormal information and is exchanged and transmitted in the network, that is, a data block that the station sends at one time, containing complete data information to be sent, and its length varies greatly, with no limit and variable length.

[0046] Specifically, alarm information can be collected when the current cannot be properly closed, carried, or interrupted under loop conditions, alarm information when the power supply cannot be properly switched on or off, and network abnormal messages given by the network analysis device when it cannot record or communicate normally. These can include SV sampling messages, GOOSE communication messages, and MMS communication messages as fault information. Fault information can be collected in cycles of one turn-on and one turn-off of the smart device.

[0047] Based on the above embodiments, when it is determined that at least one attribute parameter is missing in the fault information, target attribute parameters of the same category as each attribute parameter are determined in other fault information, and the average value of each target attribute parameter is taken as the corresponding missing attribute parameter in the fault information.

[0048] In this embodiment, the attribute parameters are the specific information contained in the fault information, which may include the specific device that malfunctioned, the content of the fault information, and the cause of the fault. The target attribute parameter is a target parameter of the same type as the missing attribute parameter in other fault information. For example, if the missing parameter is the cause of the fault, then the target attribute parameter is the fault cause parameter in other fault information.

[0049] Specifically, when at least one attribute parameter is missing in the fault information, attribute parameters of the same type as the missing attribute parameter in other fault information can be found as target attribute parameters. The average value of all found target attribute parameters can be used as the corresponding missing attribute parameter in the fault information, calculated as follows:

[0050]

[0051] In the formula, n represents the length of the sequence containing the missing values; x1, x2, ..., x n Represents all values ​​in the sequence except for missing values; x i This indicates missing data.

[0052] Based on the above embodiments, a fault handling strategy is determined according to the fault level, including:

[0053] When the fault level is the first fault level, the fault handling strategy includes generating an immediate fault notification message and transmitting the immediate fault notification message to the operation and maintenance personnel.

[0054] When the fault level is the second fault level, the fault handling strategy is determined by determining the fault handling time limit and determining the completion of fault handling within the fault handling time limit.

[0055] In this embodiment, the first fault level is the most serious fault level, which will affect normal operation and cause significant losses, and the fault needs to be dealt with immediately. The second fault level is a relatively serious fault level, which will not affect normal use or operation, and the fault needs to be dealt with within a specified time.

[0056] Specifically, when the fault level is Level 1, it can be considered that the fault will affect normal operation and cause significant losses. Maintenance personnel need to handle the fault immediately, find the fault handling strategy corresponding to Level 1, and immediately generate a Level 1 fault notification message to notify maintenance personnel of the fault occurrence and transmit the corresponding fault information. When the fault level is Level 2, it can be understood that the fault information affects the function of a device but does not affect normal use or operation. Maintenance personnel need to handle the fault within a specified period, determine the fault handling strategy corresponding to Level 2, and stipulate a fault handling time limit, which maintenance personnel must complete within the time limit. When the fault is a problem caused by aging / damage of equipment, the fault information can be transmitted to maintenance personnel, reminding them to replace the equipment as soon as possible each time the equipment is used.

[0057] Example 2

[0058] Figure 2 This is a flowchart of another fault handling strategy determination method provided in Embodiment 2 of the present invention. Based on the above embodiments, this embodiment provides an implementation of a fault classification method for determining the fault information attribution according to a preset fault decision tree.

[0059] like Figure 2 As shown, another fault handling strategy determination method provided in this embodiment may include:

[0060] S210. Obtain fault information of the smart grid.

[0061] S220. Determine whether there is a fault classification to which fault information belongs, wherein each fault classification corresponds to an initial root node.

[0062] In this embodiment, the initial root node is a unique component in the preset fault decision tree, which stores fault information of the same category as the preset fault decision tree.

[0063] Specifically, when a fault occurs, the system can analyze whether the acquired fault information can be classified into an existing fault category and determine whether the fault information has the same category as the initial root node of the preset fault decision tree.

[0064] S230. If it exists, determine the information gain corresponding to each attribute parameter in the fault information, and take the attribute parameter with the largest information gain as the classification attribute of the fault information in the fault classification. Add the fault information as a leaf node to the sub-branch corresponding to the classification attribute of the initial root node to which it belongs.

[0065] In this embodiment, information gain is the degree to which information complexity (uncertainty) is reduced under a given condition. The maximum information gain represents the greatest reduction in information complexity (uncertainty), and the calculation is as follows:

[0066] G (X,A) =I (X) -I (X∣A)

[0067]

[0068]

[0069] In the formula, G (X,A) Represents information gain; I (X) Represents information entropy; I (X∣A) S represents conditional entropy; k X represents a subset of samples belonging to the k-th class in set X; i X represents a subset of samples in X that take the i-th value of attribute A; ik X represents i The subset of samples belonging to the k-th class.

[0070] Specifically, the information gain corresponding to each attribute parameter in the fault information can be calculated, the attribute parameter with the largest information gain can be selected as the classification attribute of the fault information in the fault classification, the fault classification corresponding to the existing fault information can be found, the sub-branch corresponding to the attribute parameter with the largest information gain can be found, and the fault information can be added as a leaf node.

[0071] For example, if a fault information belongs to the fault category of device self-test anomaly, and the fault category of device self-test anomaly already exists, and the information gain of the attribute parameter fault alarm information in the fault information is the largest, then the fault information is added as a leaf node to the branch corresponding to the fault alarm information in the fault category of device self-test anomaly.

[0072] S240. If it does not exist, create a new fault category, use the fault information as the initial root node of the new fault category, and create a new sub-branch according to each attribute parameter of the fault information.

[0073] Specifically, if the fault classification of the fault information is not an existing fault classification, a new fault classification can be created, and a new fault decision tree corresponding to the fault classification can be created. The fault information mentioned above is used as the initial root node of the new fault classification, and each attribute parameter of the fault information is used as a sub-branch of the created initial root node.

[0074] S250. Determine the fault level according to the attribute information of the fault information within the fault category.

[0075] S260. Determine the fault handling strategy based on the fault level.

[0076] According to the technical solution provided by the embodiments of the present invention, by determining whether a corresponding category exists for the fault information, when a fault category exists, the information gain corresponding to each attribute parameter in the fault information is determined, and the attribute parameter with the largest information gain among all information gains is taken as the category attribute of the fault information in the fault category. The fault information is added as a leaf node to the sub-branch corresponding to the category attribute of the initial root node to which it belongs. When a fault category does not exist, a new fault category is created, the fault information is taken as the initial root node of the new fault category, and a new sub-branch is created according to each attribute parameter of the fault information. This avoids relying on the work experience of staff to classify and identify fault information, improves the accuracy of fault information classification and identification, realizes rapid classification of fault information and rapid matching of fault information with fault handling strategies, and reduces fault information identification time.

[0077] Based on the above embodiments, when the maximum information gain of fault information is greater than or equal to a preset threshold, a new fault category is created, the fault information is used as the initial root node of the new fault category, and a sub-branch is created according to each attribute parameter of the fault information.

[0078] In this embodiment, the preset threshold is an information gain value pre-set according to the actual situation, which is used to determine whether the maximum information gain of the fault information reaches the condition for creating a new fault classification.

[0079] Specifically, when the maximum information gain of the attribute parameters in the fault information is greater than or equal to a preset threshold, it can be understood that the fault information is significantly different from the category of that classification, and can be understood as belonging to a different category. In this case, a fault classification for that category can be created, which is to create a new fault decision tree. The fault information is used as the initial root node of the new fault classification, and each attribute parameter of the fault information is used as a sub-branch of the created initial root node.

[0080] Example 3

[0081] Figure 3 This is a flowchart of another fault handling strategy determination method provided in Embodiment 3 of the present invention. Based on the above embodiments, this embodiment provides an implementation method for determining the fault level according to the attribute information of fault information within the fault category.

[0082] like Figure 3 As shown, another fault handling strategy determination method provided in this embodiment may include:

[0083] S310. Obtain fault information of the smart grid and determine the fault classification to which the fault information belongs based on the preset fault decision tree.

[0084] S320. Extract a preset number of fault information within the fault category.

[0085] In this embodiment, the preset number of fault information is a certain number of fault information pre-set according to the actual situation. The fault information may include information such as the specific equipment that malfunctioned, the content of the fault information, and the cause of the fault, and the specific form is as follows:

[0086] N = (n1, n2, n3)

[0087] In the formula: n1 represents the specific device that is malfunctioning; n2 represents the fault alarm information; n3 represents the cause of the fault.

[0088] Specifically, based on the pre-set number of fault information to be extracted, a corresponding number of fault information can be extracted from the fault category. This can include abnormal alarm signals from intelligent devices, monitoring alarm signals from circuit breakers, alarm signals from power systems, SV sampling messages and GOOSE communication messages recorded by network analysis devices, and alarm signals from intelligent devices such as data sampling abnormalities, device self-test abnormalities, and power failure.

[0089] S330. Statistically analyze the distribution of fault devices, fault content, and fault causes within the attribute information of each fault information.

[0090] Specifically, the attribute parameters in the extracted fault information can be statistically analyzed, and the distribution of each attribute parameter of the faulty device, fault content, and fault cause can be statistically analyzed.

[0091] S340. Use the fault level parameter that matches the distribution in the preset configuration file as the fault level of the attribute information.

[0092] In this embodiment, the preset configuration file is a file that pre-sets how different fault levels are classified according to actual conditions. The fault level is matched based on the distribution of different attribute parameters in the fault information. Specifically, the severity of the fault can be analyzed based on the distribution of various attribute parameters related to the faulty device, fault content, and fault cause in the fault information, and the corresponding fault level parameter in the preset configuration file that matches the distribution can be used as the fault level of the fault information.

[0093] S350. Determine the fault handling strategy based on the fault level.

[0094] According to the technical solution provided by the embodiments of the present invention, the fault level is determined according to the attribute information of the fault information within the fault category, the attribute parameter information of the fault information is statistically analyzed, that is, the distribution of each attribute parameter of the fault device, the fault content and the fault cause is statistically analyzed, and the corresponding fault level is found according to the preset configuration file. This realizes the rapid matching of fault feature information and fault level, reduces the time for determining the fault information level, and improves the time for determining the fault handling strategy.

[0095] Example 4

[0096] Figure 4 This is a flowchart of another fault handling strategy determination method provided in Embodiment 4 of the present invention. Based on the above embodiments, this embodiment provides an implementation method for verifying the fault classification accuracy of determining the fault information attribution according to a preset fault decision tree.

[0097] like Figure 4 As shown, another fault handling strategy determination method provided in this embodiment may include:

[0098] S410. Obtain fault information and build a fault information database.

[0099] Specifically, it can acquire the main alarm information of the integrated automation system, the messages recorded by the network analysis device configured in the intelligent station, and the alarm signals of the intelligent device to construct a fault information database.

[0100] S420. Fault information classification based on decision tree.

[0101] Specifically, the fault information dataset can be recursively divided into smaller partitions based on the step-by-step construction of the decision tree. In each partition, the tuples tend to be of the same type compared to before the partition. The root node stores all fault information data, and the existing nodes are continuously classified recursively, thereby dividing them into more nodes and completing the classification of fault information.

[0102] The S430 and DS evidence theories verify the accuracy and precision of fault information classification.

[0103] In this embodiment, the principle of the DS evidence theory is to reduce the uncertainty of all evidence by using a fusion rule based on the established credibility allocation function of the original evidence, before making a judgment. Its fusion rule employs orthogonal calculations to compute a trust matching function for two or more criteria.

[0104] Specifically, it can be understood that evidence E1 and E2 exist in the above fault information classification architecture, and the corresponding trust ratios are e1 and e2, M. i and N j Since it is a pyroxene element, the synthesis rules are as follows:

[0105]

[0106]

[0107] Where V is the impact factor, a larger value indicates a greater impact between pieces of evidence. The effectiveness of the model is judged by classification accuracy and precision metrics, calculated as follows:

[0108]

[0109] Where TP represents the fault data correctly identified by the model; FP represents the amount of fault data that the model identifies as unreliable but is actually reliable; and FN represents the amount of fault data that the model does not identify.

[0110]

[0111] For example, initialize fault information data by inputting m training samples and creating an initial root node; determine whether the samples are fault information data of the same type. If so, mark the node as a leaf node and label it as category P. i Using the ID3 algorithm, select the attribute parameter with the largest information gain as the classification attribute of the node; determine whether the maximum information gain is less than the set threshold. If so, return to the step of creating an initial root node; otherwise, proceed to the next step; form a classification decision tree; using DS evidence theory, construct orthogonal and calculate trust matching functions of two or more criteria to quantify the results; judge the effectiveness of the model through classification accuracy and precision indicators; obtain the correct classification of secondary loop fault data.

[0112] S440. Determine the fault level according to the attribute information of the fault information within the fault category.

[0113] S450. Determine the fault handling strategy based on the fault level.

[0114] According to the technical solution provided in the embodiments of the present invention, when a fault occurs in the smart grid, fault information is collected, a fault information database is constructed, and the fault information is classified based on a decision tree. Then, the accuracy and precision of the fault information classification are verified by using the DS evidence theory. The fault level is determined according to the attribute information of the fault information within the fault classification, and the fault handling strategy is determined according to the fault level. This improves the accuracy and precision of fault information classification, realizes rapid classification of fault information and rapid matching of fault information with fault handling strategies, and reduces the fault information identification time.

[0115] Based on the above embodiments, the acquired fault information includes:

[0116] Alarm signals from intelligent devices in integrated automation systems, alarm signals from circuit breakers and power systems; SV sampling messages and GOOSE communication messages recorded by network analysis devices; alarm signals from intelligent devices such as abnormal data sampling, abnormal device self-test, and power failure.

[0117] Based on the above embodiments, the acquired fault information is preprocessed, including:

[0118] Identify abnormal fault information within the fault information sample set;

[0119] The identified abnormal fault information is populated, modified, and deleted to form a new fault information sample set;

[0120] The fault information is normalized and transformed.

[0121] In this embodiment, normalization is a method of changing the absolute value of a state variable to a relative value. It is a dimensionless processing method. Since there are large differences in the units of some power grid equipment state data, this processing can solve the differences in the properties and measurement units of different data and reduce the impact of units on the data. For example, mining the relationship between alarm content and fault information type and finding the correlation between alarm information and fault cause can help operators make diagnosis more conveniently.

[0122] Specifically, some of the acquired fault information is incomplete or missing; some is incorrect and constitutes interference; and some contains duplicate information, with identical data appearing repeatedly. These abnormal data can be filled, modified, or deleted to form a new fault information sample set. Then, normalization processing is performed to transform the fault information into the following set format:

[0123] N = (n1, n2, n3)

[0124] In the formula: n1 represents the specific device that is malfunctioning; n2 represents the fault alarm information; n3 represents the cause of the fault.

[0125] To fill in the missing parts of the fault information and ensure the integrity of the fault information data, the average value of the data sequence containing the missing value is calculated, and the average value is used to fill in the missing positions. The calculation is as follows:

[0126]

[0127] In the formula, n represents the length of the sequence containing the missing values; x1, x2, ..., x n Represents all values ​​in the sequence except for missing values; x i This indicates missing data.

[0128] Based on the above embodiments, a decision tree is constructed using information gain as the attribute selection metric based on the ID3 algorithm.

[0129] In this embodiment, the ID3 algorithm can be understood as a greedy algorithm used to construct a decision tree. The rate of decrease of information entropy is used as the criterion for selecting test attributes. That is, at each node, the attribute with the highest information gain that has not yet been used for partitioning is selected as the partitioning criterion. Then, this process continues until the generated decision tree can perfectly classify the training examples.

[0130] Specifically, the information gain of attribute parameters in the fault information can be calculated, and the attribute parameter corresponding to the maximum information gain can be selected to construct a splitting rule, thereby realizing the fault information classification calculation as shown below:

[0131] G (X,A) =I (X) -I (X∣A)

[0132]

[0133]

[0134] In the formula, G (X,A) Represents information gain; I (X) Represents information entropy; I (X∣A) S represents conditional entropy; k X represents a subset of samples belonging to the k-th class in set X; i X represents a subset of samples in X that take the i-th value of attribute A; ik X represents i The subset of samples belonging to the k-th class.

[0135] Based on the above embodiments, when the maximum information gain of fault information is greater than or equal to a preset threshold, a new fault category is created, the fault information is used as the initial root node of the new fault category, and a sub-branch is created according to each attribute parameter of the fault information.

[0136] Specifically, when the maximum information gain of the attribute parameters in the fault information is greater than or equal to a preset threshold, it can be understood that the fault information is significantly different from the category of that classification, and can be understood as belonging to a different category. In this case, a fault classification for that category can be created, which is to create a new fault decision tree. The fault information is used as the initial root node of the new fault classification, and each attribute parameter of the fault information is used as a sub-branch of the created initial root node.

[0137] For example, input m training samples; create an initial root node; determine whether the samples are fault information data of the same type; if so, mark the node as a leaf node and label it as category P. iCalculate all attribute parameters and select the attribute parameter with the largest information gain as the classification attribute of the node; determine whether the maximum information gain is greater than or equal to the set threshold. If so, return to the step of creating an initial root node; otherwise, proceed to the next step; split each value in the attribute parameter to extend a corresponding branch, and divide the samples according to the attribute value to obtain the corresponding decision tree, thereby achieving the effect of classifying secondary loop fault information data.

[0138] Example 5

[0139] Figure 5 This is a schematic diagram of a smart grid fault handling strategy determination device provided in Embodiment 5 of the present invention. This embodiment can execute the above-described implementation method. This embodiment is applicable to situations where, when a fault occurs in the smart grid, the fault information of the smart grid can be analyzed and identified without relying on the experience of the personnel. The device can be implemented in hardware / software and can be configured in an electronic device.

[0140] like Figure 5 As shown, the fault classification module 501, the level determination module 502, and the strategy determination module 503 provided in this embodiment include:

[0141] The fault classification module 501 is used to acquire fault information of the smart grid and determine the fault classification to which the fault information belongs based on a preset fault decision tree.

[0142] The fault level determination module 502 is used to determine the fault level according to the attribute information of the fault information within the fault category.

[0143] The strategy determination module 503 is used to determine the fault handling strategy based on the fault level.

[0144] According to the technical solution provided in the embodiments of the present invention, when a fault occurs in the smart grid, fault information is collected, and the acquired fault information is classified according to a preset fault decision tree to find the fault category to which it belongs. The fault level of the fault information is determined by analyzing the attribute information of the fault information in the fault category, and the fault handling strategy corresponding to the fault level is found. This realizes the rapid matching of fault information and fault handling strategy, improves the accuracy of fault handling solution determination, and reduces fault identification time.

[0145] Based on the above embodiments, the fault classification module 501 includes:

[0146] The alarm collection unit is used to collect fault alarm information from smart devices, circuit breakers, and power systems within the smart grid as fault information.

[0147] The message collection unit is used to extract abnormal network messages recorded by the network analysis device of the smart grid as fault information.

[0148] Based on the above embodiments, the fault classification module 501 further includes:

[0149] The attribute parameter supplementation unit is used to determine the target attribute parameter of the same type as each attribute parameter in other fault information when the fault information is missing at least one attribute parameter, and to take the average value of each target attribute parameter as the corresponding missing attribute parameter in the fault information.

[0150] Based on the above embodiments, the fault classification module 501 determines the fault classification to which the fault information belongs according to a preset fault decision tree, including:

[0151] The fault classification judgment unit is used to determine whether there is a fault classification to which fault information belongs, wherein each fault classification corresponds to an initial root node.

[0152] The classification unit is used to determine the information gain corresponding to each attribute parameter in the fault information if it exists, and to take the attribute parameter with the largest information gain as the classification attribute of the fault information in the fault classification. The fault information is then added as a leaf node to the sub-branch corresponding to the classification attribute of the initial root node to which it belongs.

[0153] If a category does not exist, a new fault category is created. The fault information is used as the initial root node of the new fault category, and a new sub-branch is created according to each attribute parameter of the fault information.

[0154] Based on the above embodiments, the fault classification module 501 further includes:

[0155] The fault classification new unit is used to create a new fault classification when the maximum information gain of the fault information is greater than or equal to a preset threshold. The fault information is used as the initial root node of the new fault classification, and a sub-branch is created according to each attribute parameter of the fault information.

[0156] Based on the above embodiments, the fault level determination module 502 determines the fault level according to the attribute information of the fault information within the fault category, including:

[0157] The fault information extraction unit is used to extract a preset number of fault information within the fault category.

[0158] The attribute information statistics unit is used to statistically analyze the distribution of fault devices, fault content, and fault causes within the attribute information of each fault information.

[0159] The fault level matching unit is used to use the fault level parameters that match the distribution in the preset configuration file as the fault level of the attribute information.

[0160] Based on the above embodiments, the strategy determination module 503 determines a fault handling strategy according to the fault level, including:

[0161] The first fault level unit is used to determine the fault handling strategy when the fault level is the first fault level, including generating an immediate fault notification message and transmitting the immediate fault notification message to the operation and maintenance personnel.

[0162] The second fault level unit is used to determine the fault handling strategy when the fault level is the second fault level, including determining the fault handling time limit and determining to complete the fault handling within the fault handling time limit.

[0163] The smart grid fault handling strategy determination device provided in Embodiment 5 of the present invention can execute any fault handling strategy determination method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects of the method execution. Content not described in detail in this embodiment can be referred to the description in any method embodiment of the present invention.

[0164] Example 6

[0165] Figure 6 This is a schematic diagram of an electronic device provided in Embodiment Six of the present invention. The electronic device 60, which can be used to implement embodiments of the present invention, is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0166] like Figure 6 As shown, the electronic device 60 includes at least one processor 61 and a memory, such as a read-only memory (ROM) 62 and a random access memory (RAM) 63, communicatively connected to the at least one processor 61. The memory stores computer programs executable by the at least one processor. The processor 61 can perform various appropriate actions and processes based on the computer program stored in the ROM 62 or loaded from storage unit 68 into the RAM 63. The RAM 63 can also store various programs and data required for the operation of the electronic device 60. The processor 61, RAM 62, and RAM 63 are interconnected via a bus 64. An input / output (I / O) interface 66 is also connected to the bus 64.

[0167] Multiple components in electronic device 60 are connected to I / O interface 66, including: input unit 66, such as keyboard, mouse, etc.; output unit 67, such as various types of displays, speakers, etc.; storage unit 68, such as disk, optical disk, etc.; and communication unit 69, such as network card, modem, wireless transceiver, etc. Communication unit 69 allows electronic device 60 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0168] Processor 61 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 61 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 61 performs the various methods and processes described above, such as fault handling strategy determination methods.

[0169] In some embodiments, the fault handling strategy determination method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 68. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 60 via ROM 62 and / or communication unit 69. When the computer program is loaded into RAM 63 and executed by processor 61, one or more steps of the fault handling strategy determination method described above may be performed. Alternatively, in other embodiments, processor 61 may be configured to perform the fault handling strategy determination method by any other suitable means (e.g., by means of firmware).

[0170] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0171] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0172] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0173] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0174] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0175] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0176] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0177] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining a fault handling strategy, characterized in that, The method includes: Obtain fault information of the smart grid and determine the fault category to which the fault information belongs based on a preset fault decision tree; The fault level is determined according to the attribute information of the fault information within the fault category; Determine the fault handling strategy based on the fault level; The step of determining the fault classification to which the fault information belongs based on a preset fault decision tree includes: Determine whether there is a fault category to which the fault information belongs, wherein each fault category corresponds to an initial root node; If it exists, determine the information gain corresponding to each attribute parameter in the fault information, and take the attribute parameter with the largest information gain among the information gains as the classification attribute of the fault information in the fault classification, and add the fault information as a leaf node to the sub-branch corresponding to the classification attribute of the initial root node to which it belongs. If it does not exist, a new fault category is created, the fault information is used as the initial root node of the new fault category, and a new sub-branch is created according to each attribute parameter of the fault information. Determining the fault level based on the attribute information of the fault information within the fault category includes: Extract a preset number of fault information items within the fault category; The distribution of faulty devices, fault content, and fault causes within the attribute information of each fault information is statistically analyzed. The fault level parameter that matches the distribution in the preset configuration file is used as the fault level of the attribute information.

2. The method according to claim 1, characterized in that, The acquisition of fault information in the smart grid includes: The fault alarm information of the smart devices, circuit breakers and power systems in the smart grid is collected as the fault information. The network anomaly messages recorded by the network analysis device of the smart grid are extracted as the fault information.

3. The method according to claim 1, characterized in that, Also includes: When it is determined that the fault information is missing at least one attribute parameter, target attribute parameters of the same type as each of the attribute parameters are identified in other fault information, and the average value of each of the target attribute parameters is taken as the corresponding missing attribute parameter in the fault information.

4. The method according to claim 1, characterized in that, Also includes: If the maximum information gain of the fault information is greater than or equal to a preset threshold, a new fault category is created, the fault information is used as the initial root node of the new fault category, and a sub-branch is created according to each attribute parameter of the fault information.

5. The method according to claim 1, characterized in that, The step of determining the fault handling strategy based on the fault level includes: When the fault level is the first fault level, the fault handling strategy is determined to include generating an immediate fault notification message and transmitting the immediate fault notification message to the operation and maintenance personnel. When the fault level is the second fault level, determining the fault handling strategy includes determining the fault handling time limit and determining to complete the fault handling within the fault handling time limit.

6. A device for determining a fault handling strategy for a smart grid, characterized in that, The device includes: The fault classification module is used to acquire fault information of the smart grid and determine the fault classification to which the fault information belongs based on a preset fault decision tree. The fault level determination module is used to determine the fault level according to the attribute information of the fault information within the fault category. A strategy determination module is used to determine a fault handling strategy based on the fault level. The fault classification module determines the fault category to which the fault information belongs based on a preset fault decision tree, including: A fault classification judgment unit is used to determine whether there is a fault classification to which the fault information belongs, wherein each fault classification corresponds to an initial root node; The classification unit is used to determine the information gain corresponding to each attribute parameter in the fault information if it exists, and to take the attribute parameter with the largest information gain among the information gains as the classification attribute of the fault information in the fault classification, and to add the fault information as a leaf node to the sub-branch corresponding to the classification attribute of the initial root node to which it belongs. If a category does not exist, a new fault category is created, with the fault information serving as the initial root node of the new fault category, and a new sub-branch created according to each attribute parameter of the fault information. The fault level determination module determines the fault level according to the attribute information of the fault information within the fault category, including: The fault information extraction unit is used to extract a preset number of fault information within the fault category. The attribute information statistics unit is used to statistically analyze the distribution of fault devices, fault content, and fault causes within the attribute information of each fault information. The fault level matching unit is used to use the fault level parameters that match the distribution in the preset configuration file as the fault level of the attribute information.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the smart grid fault handling strategy determination method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the smart grid fault handling strategy determination method according to any one of claims 1-5.

Images