Power grid intelligent monitoring method and device

Abstract

The invention is suitable for the technical field of electric digital data processing, and provides a power grid intelligent monitoring method and device, and the method comprises the steps: obtaining various types of historical power grid data and a plurality of historical power grid states; calculating relative importance degrees of different types of power grid data based on the multiple types of historical power grid data and the multiple historical power grid states; determining a target type set based on the relative importance degrees of different types of power grid data; obtaining target data with the same type as that in the target type set in the target power grid; wherein the types in the target type set are types with relatively large influence degree on the power grid state; and determining the power grid state of the target power grid based on the multiple types of historical power grid data, the multiple historical power grid states and the target data. According to the invention, the processing speed and accuracy of mass data can be improved.

Description

Technical Field

[0001] The present application belongs to the technical field of electrical digital data processing, and in particular to a method and device for intelligent monitoring of a power grid. Background Art

[0002] With the development of economy and society, people's demand for electricity is increasing, and the scale of power system is also expanding. In this context, the stability and reliability of power grid has become a key issue. Traditional power grid monitoring methods can no longer meet the needs of modern power system, especially when facing the access of new loads such as new energy, distributed generation, smart home appliances, etc. to the power grid, the complexity of the power grid has greatly increased.

[0003] In addition, external factors such as extreme climate events and natural disasters may also affect the power grid, resulting in unstable power supply. In order to deal with these problems, real-time monitoring technology for power grids has emerged. This technology uses advanced sensors, communication technology and data processing methods to monitor the operation status of the power grid in real time to ensure the safe and stable operation of the power system.

[0004] As the power grid becomes increasingly large, the data throughput is also increasing. Conventional power grid monitoring systems can no longer meet current needs, especially in terms of processing massive data and improving algorithm accuracy. It is no longer possible to accurately and effectively monitor. Summary of the invention

[0005] The embodiments of the present application provide a method and device for intelligent monitoring of power grids to improve the processing speed and accuracy of massive data, timely discover potential problems in the power grid, respond quickly in emergency situations, reduce power outage time, protect equipment from damage, and ensure personnel safety.

[0006] This application is implemented through the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a method for intelligent monitoring of a power grid, including:

[0008] Acquire various types of historical power grid data and multiple historical power grid states.

[0009] Based on multiple types of historical power grid data and multiple historical power grid states, the relative importance of different types of power grid data is calculated.

[0010] Based on the relative importance of different types of power grid data, a target type set is determined; target data of the same type as that in the target type set in the target power grid is obtained; wherein the types in the target type set are types that have a greater degree of influence on the power grid state.

[0011] Based on multiple types of historical grid data, multiple historical grid states and target data, a grid state of a target grid is determined.

[0012] In combination with the first aspect, in some possible implementations, the historical power grid state includes an abnormal state and a normal state; based on multiple types of historical power grid data and historical power grid states, the relative importance of different types of power grid data is calculated, including:

[0013] When the historical power grid state is calculated as a normal state, the average values ​​of multiple types of historical power grid data are recorded as multiple types of historical average values.

[0014] Calculate the change rate of various types of historical power grid data and the corresponding historical mean when the historical power grid state is abnormal.

[0015] Based on multiple change rates, the relative importance of different types of power grid data is obtained.

[0016] In combination with the first aspect, in some possible implementations, when the historical power grid state is an abnormal state, the change rates of multiple types of historical power grid data and corresponding historical averages are calculated, including:

[0017] Combined with the first formula, the change rates of various types of historical power grid data and corresponding historical averages are calculated when the historical power grid state is an abnormal state.

[0018] The first formula is:

[0019]

[0020] Among them, C j Indicates the change rate of type j power grid data, N j1 represents the historical mean of type j, N j Represents historical power grid data of type j.

[0021] In combination with the first aspect, in some possible implementations, the relative importance of different types of power grid data is obtained based on the minimum change rate, including:

[0022] Based on the multiple change rates and in combination with the second formula, the relative importance of different types of power grid data is obtained.

[0023] The second formula includes:

[0024]

[0025] Among them, a ij Indicates the relative importance of type i power grid data to type j power grid data, C i1 C represents the minimum change rate of the grid state caused by type i grid data without the influence of other types of grid data. j1It represents the minimum change rate of the grid state caused by the j-type grid data without the influence of other types of grid data.

[0026] In conjunction with the first aspect, in some possible implementations, each historical power grid state corresponds to a set of multiple types of historical power grid data; based on the multiple types of historical power grid data, the multiple historical power grid states and the target data, determining the power grid state of the target power grid includes:

[0027] The data in each historical power grid state is processed based on the random forest algorithm to obtain aggregated data.

[0028] Based on the aggregated data, a data center of the aggregated data is obtained.

[0029] The distance from the target data to the data center is calculated. If the distance is less than or equal to a preset threshold, the grid state of the target grid is normal.

[0030] The distance from the target data to the data center is calculated. If the distance is greater than a preset threshold, the grid state of the target grid is abnormal.

[0031] In conjunction with the first aspect, in some possible implementations, calculating the distance from the target data to the data center includes:

[0032] Take the nearest integer value to the center of the data and record it as the first approximation.

[0033] Take the nearest integer value of the target data and record it as the second approximation.

[0034] The distance from the first approximation value to the second approximation value is taken as the distance from the target data to the data center.

[0035] In conjunction with the first aspect, in some possible implementations, determining a target type set based on the relative importance of different types of power grid data includes:

[0036] According to the relative importance of different types of power grid data, the types of multiple power grid data are sorted from large to small according to their importance, and a preset number of power grid data types are selected as a target type set.

[0037] In conjunction with the first aspect, in some possible implementations, multiple types of historical power grid data and multiple historical power grid states are obtained, including:

[0038] For any historical moment, the historical power grid status at that moment and various types of historical power grid initial data at that moment are obtained; missing value completion, duplicate data elimination and noise reduction are performed on the historical power grid initial data to obtain various types of historical power grid data at that moment.

[0039] Various types of historical power grid data and historical power grid states at multiple historical moments are aggregated to obtain various types of historical power grid data and multiple historical power grid states.

[0040] In combination with the first aspect, in some possible implementations, the method further includes:

[0041] When the grid state of the target grid is determined, the grid state of the target grid and various types of grid data of the target grid are saved in a historical database.

[0042] In a second aspect, an embodiment of the present application provides a power grid intelligent monitoring device, including:

[0043] The data acquisition module is used to acquire various types of historical power grid data and multiple historical power grid states.

[0044] The first calculation module is used to calculate the relative importance of different types of power grid data based on multiple types of historical power grid data and multiple historical power grid states.

[0045] The second calculation module is used to determine the target type set based on the relative importance of different types of power grid data; obtain target data of the same type as that in the target type set in the target power grid; wherein the types in the target type set are types that have a greater impact on the power grid state.

[0046] The result output module is used to determine the grid state of the target grid based on multiple types of historical grid data, multiple historical grid states and target data.

[0047] It can be understood that the beneficial effects of the second aspect mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0048] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0049] Based on historical power grid data and historical power grid status, this application calculates the relative importance of different types of power grid data and determines a target type set. Then, based on the target data of the same type as the target type set in the target power grid, as well as the historical power grid data and historical power grid status, the power grid status of the target power grid can be accurately determined to achieve power grid monitoring. Because the target type set is determined, the types of power grid data that have a greater impact on the power grid status can be screened out, thereby reducing the amount of data input and increasing the processing speed of massive data. Because the types of power grid data with a greater impact are selected, the accuracy of data processing can also be improved. In short, this solution can promptly discover potential problems in the power grid, respond quickly in emergency situations, reduce power outage time, protect equipment from damage, and ensure personnel safety.

[0050] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0052] Figure 1 It is a flowchart of a method for intelligent monitoring of a power grid provided in one embodiment of the present application;

[0053] Figure 2 It is a structural diagram of a power grid intelligent monitoring device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0054] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0055] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0056] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0057] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0058] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0059] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0060] The present application provides a method for intelligent monitoring of a power grid. Figure 1 is a schematic diagram of the process of the power grid intelligent monitoring method provided by an embodiment of the present application, with reference to Figure 1 , the detailed description of the intelligent monitoring method of the power grid is as follows:

[0061] Step 101 : Acquire multiple types of historical power grid data and multiple historical power grid states.

[0062] Exemplarily, step 101 may include:

[0063] For any historical moment, the historical power grid status at that moment and various types of historical power grid initial data at that moment are obtained; missing value completion, duplicate data elimination and noise reduction are performed on the historical power grid initial data to obtain various types of historical power grid data at that moment.

[0064] Various types of historical power grid data and historical power grid states at multiple historical moments are aggregated to obtain various types of historical power grid data and multiple historical power grid states.

[0065] Each historical power grid state may correspond to a set of multiple types of historical power grid data.

[0066] In order to better understand the present solution, illustratively, each historical power grid state may correspond to historical power grid data of types b, c, d, e and f. When the historical power grid state is A1, the corresponding multiple types of historical power grid data may be b1, c1, d1, e1 and f1; when the historical power grid state is A2, the corresponding multiple types of historical power grid data may be b2, c2, d2, e2 and f2; when the historical power grid state is A3, the corresponding multiple types of historical power grid data may be b3, c3, d3, e3 and f3. Among them, the historical power grid state A1 may represent a normal state, the historical power grid state A2 may represent an abnormal state, such as a circuit break, and the historical power grid state A3 may represent another abnormal state, such as a circuit short circuit.

[0067] Step 102: Calculate the relative importance of different types of power grid data based on multiple types of historical power grid data and multiple historical power grid states.

[0068] Exemplarily, the historical power grid state includes an abnormal state and a normal state.

[0069] Exemplarily, step 102 may include:

[0070] When the historical power grid state is calculated as a normal state, the average values ​​of multiple types of historical power grid data are recorded as multiple types of historical average values.

[0071] Calculate the change rate of various types of historical power grid data and the corresponding historical mean when the historical power grid state is abnormal.

[0072] Based on multiple change rates, the relative importance of different types of power grid data is obtained.

[0073] Exemplarily, when calculating the historical power grid state as an abnormal state, the change rate of multiple types of historical power grid data and the corresponding historical mean value may include:

[0074] Combined with the first formula, the change rates of various types of historical power grid data and corresponding historical averages are calculated when the historical power grid state is an abnormal state.

[0075] The first formula can be:

[0076]

[0077] Among them, C j Indicates the change rate of type j power grid data, N j1 represents the historical mean of type j, N j Represents historical power grid data of type j.

[0078] Specifically, based on the above hypothetical example, the historical averages of multiple types are b1, c1, d1, e1 and f1. The change rates of the first type of power grid data are: and The change rates of the second type of power grid data are: and The change rates of the third type of power grid data are: and The change rates of the fourth type of power grid data are: and The change rates of the fifth type of power grid data are:

[0079] and

[0080] Exemplarily, based on the minimum change rate, obtaining the relative importance of different types of power grid data may include:

[0081] Based on the multiple change rates and in combination with the second formula, the relative importance of different types of power grid data is obtained.

[0082] The second formula may include:

[0083]

[0084] Among them, a ij Indicates the relative importance of type i power grid data to type j power grid data, C i1 C represents the minimum change rate of the grid state caused by type i grid data without the influence of other types of grid data. j1 It represents the minimum change rate of the grid state caused by the j-type grid data without the influence of other types of grid data.

[0085] Specifically, for the change rate of the i-th type of power grid data, C i1 It represents the minimum rate of change of the grid state from normal to abnormal when the i-th type of grid data changes alone, when the other types of grid data do not change significantly with the historical mean of the corresponding type of grid data. Using the above example, assuming that the i-th type of grid data is the first type of grid data, c2 = c1, d2 = d1, e2 = e1, f2 = f1 (which means that at this time, except for the first type of grid data, the other types of grid data do not change significantly with the historical mean of the corresponding grid data), then C i1 is equivalent to and The minimum value in .

[0086] Step 103, based on the relative importance of different types of power grid data, determine a target type set; obtain target data of the same type as that in the target type set in the target power grid; wherein the types in the target type set are types that have a greater impact on the power grid state.

[0087] Exemplarily, determining a target type set based on the relative importance of different types of power grid data may include:

[0088] According to the relative importance of different types of power grid data, the types of multiple power grid data are sorted from large to small according to their importance, and a preset number of power grid data types are selected as a target type set.

[0089] Specifically, after obtaining the relative importance of different types of power grid data, it is equivalent to understanding the proportion of each type of power grid data affecting the power grid status, so the relative influence of each type can be sorted, and the greater the degree, the greater the impact on the power grid status. At the same time, in order to consider the speed and accuracy of data processing, a preset number of types are selected as the set of target types.

[0090] Step 104 : determining a grid state of a target grid based on multiple types of historical grid data, multiple historical grid states, and target data.

[0091] Exemplarily, step 104 may include:

[0092] The data in each historical power grid state is processed based on the random forest algorithm to obtain aggregated data.

[0093] Based on the aggregated data, a data center of the aggregated data is obtained.

[0094] The distance from the target data to the data center is calculated. If the distance is less than or equal to a preset threshold, the grid state of the target grid is normal.

[0095] The distance from the target data to the data center is calculated. If the distance is greater than a preset threshold, the grid state of the target grid is abnormal.

[0096] Exemplarily, calculating the distance from the target data to the data center may include:

[0097] Take the nearest integer value to the center of the data and record it as the first approximation.

[0098] Take the nearest integer value of the target data and record it as the second approximation.

[0099] The distance from the first approximation value to the second approximation value is taken as the distance from the target data to the data center.

[0100] Specifically, in order to improve the calculation speed of the algorithm, the idea of ​​approximate numbers is used to convert the distance value into an approximate integer value. In this way, calculating the distance between integer values ​​can speed up the calculation and improve the processing speed of power grid monitoring data. At the same time, since the power grid data is large, even if the approximate value is used for calculation, it will not produce a large error and can still maintain the accuracy of the calculation.

[0101] Exemplarily, the method may further include:

[0102] When the grid state of the target grid is determined, the grid state of the target grid and various types of grid data of the target grid are saved in a historical database.

[0103] Specifically, adding the newly determined status data to the historical database can enrich the data in the database, and can obtain a more accurate data center over time, thereby ensuring the accuracy of power grid status monitoring.

[0104] The above-mentioned intelligent power grid monitoring method calculates the relative importance of different types of power grid data based on historical power grid data and historical power grid status, and determines the target type set. Then, the power grid status of the target power grid can be accurately determined based on the target data of the same type as the target type set in the target power grid, as well as the historical power grid data and historical power grid status, to achieve power grid monitoring. Because the target type set is determined, the types of power grid data that have a greater impact on the power grid status can be screened out, thereby reducing the input of data volume and improving the processing speed of massive data. Because the types of power grid data with a greater impact are selected, the accuracy of data processing can also be improved. In short, this solution can promptly discover potential problems in the power grid, respond quickly in emergency situations, reduce power outage time, protect equipment from damage, and ensure personnel safety.

[0105] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0106] Corresponding to the intelligent monitoring method for power grid described in the above embodiment, Figure 2 A structural block diagram of an intelligent monitoring device for a power grid provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0107] See also Figure 2 , the power grid intelligent monitoring device in the embodiment of the present application may include:

[0108] The data acquisition module 201 is used to acquire various types of historical power grid data and multiple historical power grid states.

[0109] The first calculation module 202 is used to calculate the relative importance of different types of power grid data based on multiple types of historical power grid data and multiple historical power grid states.

[0110] The second calculation module 203 is used to determine the target type set based on the relative importance of different types of power grid data; obtain target data of the same type as that in the target type set in the target power grid; wherein the types in the target type set are types that have a greater impact on the power grid state.

[0111] The result output module 204 is used to determine the grid state of the target grid based on multiple types of historical grid data, multiple historical grid states and target data.

[0112] Exemplarily, the historical power grid state includes an abnormal state and a normal state.

[0113] Exemplarily, the first calculation module 202 may be used for:

[0114] When the historical power grid state is calculated as a normal state, the average values ​​of multiple types of historical power grid data are recorded as multiple types of historical average values.

[0115] Calculate the change rate of various types of historical power grid data and the corresponding historical mean when the historical power grid state is abnormal.

[0116] Based on multiple change rates, the relative importance of different types of power grid data is obtained.

[0117] Exemplarily, the first calculation module 202 may be used for:

[0118] Combined with the first formula, the change rates of various types of historical power grid data and corresponding historical averages are calculated when the historical power grid state is an abnormal state.

[0119] The first formula can be:

[0120]

[0121] Among them, C j Indicates the change rate of type j power grid data, N j1 represents the historical mean of type j, N j Represents historical power grid data of type j.

[0122] Exemplarily, the first calculation module 202 may be used for:

[0123] Based on the multiple change rates and in combination with the second formula, the relative importance of different types of power grid data is obtained.

[0124] The second formula may include:

[0125]

[0126] Among them, a ij Indicates the relative importance of type i power grid data to type j power grid data, C i1 C represents the minimum change rate of the grid state caused by type i grid data without the influence of other types of grid data. j1 It represents the minimum change rate of the grid state caused by the j-type grid data without the influence of other types of grid data.

[0127] Exemplarily, each historical power grid state corresponds to a set of multiple types of historical power grid data.

[0128] Exemplarily, the result output module 204 may be used to:

[0129] The data in each historical power grid state is processed based on the random forest algorithm to obtain aggregated data.

[0130] Based on the aggregated data, a data center of the aggregated data is obtained.

[0131] The distance from the target data to the data center is calculated. If the distance is less than or equal to a preset threshold, the grid state of the target grid is normal.

[0132] The distance from the target data to the data center is calculated. If the distance is greater than a preset threshold, the grid state of the target grid is abnormal.

[0133] Exemplarily, the result output module 204 may be used to:

[0134] Take the nearest integer value to the center of the data and record it as the first approximation.

[0135] Take the nearest integer value of the target data and record it as the second approximation.

[0136] The distance from the first approximation value to the second approximation value is taken as the distance from the target data to the data center.

[0137] Exemplarily, the second calculation module 203 may be used for:

[0138] According to the relative importance of different types of power grid data, the types of multiple power grid data are sorted from large to small according to their importance, and a preset number of power grid data types are selected as a target type set.

[0139] Exemplarily, the data acquisition module 201 may be used for:

[0140] For any historical moment, the historical power grid status at that moment and various types of historical power grid initial data at that moment are obtained; missing value completion, duplicate data elimination and noise reduction are performed on the historical power grid initial data to obtain various types of historical power grid data at that moment.

[0141] Various types of historical power grid data and historical power grid states at multiple historical moments are aggregated to obtain various types of historical power grid data and multiple historical power grid states.

[0142] Exemplarily, the result output module 204 may be used to:

[0143] When the grid state of the target grid is determined, the grid state of the target grid and various types of grid data of the target grid are saved in a historical database.

[0144] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0145] Those of ordinary skill in the art will appreciate that the templates, units, and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0146] If the module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned embodiments of the intelligent monitoring method of the power grid can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal and software distribution medium.

[0147] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for intelligent monitoring of a power grid, characterized in that: include: Acquire various types of historical power grid data and multiple historical power grid states; Based on the multiple types of historical power grid data and multiple historical power grid states, calculating the relative importance of different types of power grid data; Determining a target type set based on the relative importance of the different types of power grid data; Acquire target data of the same type as that in the target type set in the target power grid; wherein the types in the target type set are types that have a greater degree of influence on the power grid state; A grid state of the target grid is determined based on the multiple types of historical grid data, the multiple historical grid states, and the target data.

2. The intelligent monitoring method for a power grid according to claim 1, characterized in that: The historical power grid state includes an abnormal state and a normal state; the calculating the relative importance of different types of power grid data based on the multiple types of historical power grid data and historical power grid states includes: Calculating the average of multiple types of historical power grid data when the historical power grid state is in a normal state, and recording the average of multiple types of historical power grid data; Calculating the change rates of multiple types of historical power grid data and corresponding historical averages when the historical power grid state is an abnormal state; Based on the multiple change rates, the relative importance of the different types of power grid data is obtained.

3. The intelligent monitoring method for power grid according to claim 2, characterized in that: The calculation of the change rate of multiple types of historical power grid data and corresponding historical mean values ​​when the historical power grid state is an abnormal state includes: In combination with the first formula, calculating the change rate of multiple types of historical power grid data and the corresponding historical mean when the historical power grid state is an abnormal state; The first formula is: Among them, C j Indicates the change rate of type j power grid data, N j1 represents the historical mean of type j, N j Represents historical power grid data of type j.

4. The intelligent monitoring method for a power grid according to claim 2, characterized in that: The obtaining of the relative importance of the different types of power grid data based on the multiple change rates includes: Based on the multiple change rates and in combination with the second formula, the relative importance of the different types of power grid data is obtained; The second formula includes: Among them, a ij Indicates the relative importance of type i power grid data to type j power grid data, C i1 C represents the minimum change rate of the grid state caused by type i grid data without the influence of other types of grid data. j1 It represents the minimum change rate of the grid state caused by the j-type grid data without the influence of other types of grid data.

5. The intelligent monitoring method for a power grid according to claim 1, characterized in that: Each of the historical power grid states corresponds to a group of multiple types of historical power grid data; and determining the power grid state of the target power grid based on the multiple types of historical power grid data, the multiple historical power grid states and the target data includes: The data in each historical power grid state is processed based on the random forest algorithm to obtain aggregated data; Based on the aggregated data, obtaining a data center of the aggregated data; Calculating the distance from the target data to the data center, if the distance is less than or equal to a preset threshold, the power grid state of the target power grid is normal; The distance from the target data to the data center is calculated, and if the distance is greater than the preset threshold, the power grid state of the target power grid is an abnormal state.

6. The intelligent monitoring method for a power grid according to claim 5, characterized in that: The calculating the distance from the target data to the data center includes: Take the nearest integer value of the center of the data as the first approximation; Take the nearest integer value of the target data and record it as the second approximation; The distance from the first approximate value to the second approximate value is used as the distance from the target data to the data center.

7. The intelligent monitoring method for a power grid according to claim 1, characterized in that: The determining of a target type set based on the relative importance of the different types of power grid data includes: According to the relative importance of the different types of power grid data, the types of multiple power grid data are sorted from large to small according to their importance, and a preset number of power grid data types are selected as the target type set.

8. The intelligent monitoring method for a power grid according to claim 1, characterized in that: The acquiring of multiple types of historical power grid data and multiple historical power grid states includes: For any historical moment, the historical power grid state at that moment and various types of historical power grid initial data at that moment are obtained; missing value completion, duplicate data elimination and noise reduction processing are performed on the historical power grid initial data to obtain various types of historical power grid data at that moment; The multiple types of historical power grid data and historical power grid states at multiple historical moments are aggregated to obtain the multiple types of historical power grid data and multiple historical power grid states.

9. The intelligent monitoring method for a power grid according to claim 1, characterized in that: The method further comprises: After the grid state of the target grid is determined, the grid state of the target grid and various types of grid data of the target grid are saved in a historical database.

10. An intelligent monitoring device for a power grid, characterized in that: include: A data acquisition module, used to acquire various types of historical power grid data and multiple historical power grid states; A first calculation module, configured to calculate relative importance of different types of power grid data based on the multiple types of historical power grid data and multiple historical power grid states; A second calculation module, configured to determine a target type set based on the relative importance of the different types of power grid data; Acquire target data of the same type as that in the target type set in the target power grid; wherein the types in the target type set are types that have a greater degree of influence on the power grid state; The result output module is used to determine the grid state of the target grid based on the multiple types of historical grid data, the multiple historical grid states and the target data.

Images