Multi-level power grid coordination control method and device based on clustering

Abstract

The invention provides a multi-level power grid coordination control method and device based on clustering, and relates to the technical field of power systems. The method comprises the following steps: acquiring an equipment data set of a power grid of a target area, dividing the equipment data set based on the power grid levels of the power grid to obtain a sub-equipment data set of each power grid level, obtaining an identification code of each power equipment in the corresponding power grid level according to the sub-equipment data set, and clustering the power equipment of the corresponding power grid level to obtain a clustering result; obtaining a first clustering result; determining a first influence degree of each power device according to the device feature of each power device and the first clustering result; generating a first fault scheduling scheme of each power grid level in combination with the first clustering result; and optimizing the first fault scheduling scheme based on the clustering features to obtain a second fault scheduling scheme of the power grid of the target area. The accuracy of the scheduling scheme can be ensured, the normal operation of the power grid in the target area is ensured, and the power supply stability of the power grid is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of power systems, and in particular, relates to a multi-level power grid coordination control method and device based on clustering. Background Art

[0002] At present, the usage amount of power equipment in the power grid is very large. With the access of distributed energy to the power grid, the manufacturing threshold of power equipment has gradually decreased, and more and more manufacturers can participate in manufacturing. The types of power equipment connected to the power grid are diverse and the quality is uneven.

[0003] Since the production addresses and production environments of different manufacturers are different, and the production technical standards and production concepts are also different, the characteristics of power equipment produced by different manufacturers are different. As a result, for the same model of equipment produced by different manufacturers, the reasons for failures and the time required for fault repair are different during use. At present, for faulty equipment, after-sales service is usually provided by the manufacturer.

[0004] However, the after-sales service standards of different manufacturers are different, and the operation proficiency of employees performing after-sales work is also different. This makes it difficult to determine the recovery time of equipment failures, and moreover, the timeliness of after-sales service provided by manufacturers is often poor, resulting in the inability to perform power dispatching in a timely and effective manner, which greatly affects the power supply stability of the power grid. Summary of the Invention

[0005] Embodiments of the present invention provide a multi-level power grid coordination control method and device based on clustering to solve the problem that power dispatching cannot be performed in a timely manner when power equipment fails, affecting the power supply stability of the power grid.

[0006] The present invention is implemented through the following technical solutions:

[0007] In a first aspect, embodiments of the present invention provide a multi-level power grid coordination control method based on clustering, including:

[0008] Obtain an equipment data set of the power grid in the target area, and divide the equipment data set based on the power grid levels of the power grid to obtain sub-equipment data sets for each power grid level;

[0009] Based on the sub-equipment data set, obtain the identification code of each power equipment in the corresponding power grid level, and cluster the power equipment in the corresponding power grid level based on the identification code to obtain a first clustering result;

[0010] Obtain the equipment characteristics of each power equipment, and determine the first influence degree of each power equipment based on the first clustering result and the equipment characteristics;

[0011] Generate a first fault scheduling plan for each power grid level based on the first influence degree and the first clustering result;

[0012] Optimize the corresponding first fault scheduling plan based on the clustering characteristics of each first clustering result to obtain a second fault scheduling plan for the power grid in the target area.

[0013] In a second aspect, an embodiment of the present invention provides a clustering-based multi-level power grid coordination control device, including:

[0014] An acquisition module, configured to acquire a device data set of the power grid in the target area, and divide the device data set based on the power grid levels of the power grid to obtain sub-device data sets for each power grid level;

[0015] A clustering module, configured to obtain the identification codes of each power device in the corresponding power grid level based on the sub-device data set, and cluster the power devices in the corresponding power grid level based on the identification codes to obtain a first clustering result;

[0016] A determination module, configured to obtain the device characteristics of each power device, and determine the first influence degree of each power device based on the first clustering result and the device characteristics;

[0017] A scheduling module, configured to generate a first fault scheduling plan for each power grid level based on the first influence degree and the first clustering result;

[0018] An optimization module, configured to optimize the corresponding first fault scheduling plan based on the clustering characteristics of each first clustering result to obtain a second fault scheduling plan for the power grid in the target area.

[0019] An embodiment of the present invention provides a clustering-based multi-level power grid coordination control method and device. By acquiring the device data set of the power grid in the target area and dividing it to obtain sub-device data sets for each power grid level, then obtaining the identification codes of each power device in each power grid level through the sub-device data sets, clustering the power devices to obtain a first clustering result, determining the first fault scheduling plan for each power grid level according to the first clustering result, and optimizing the first fault scheduling plan according to the clustering characteristics to obtain a second fault scheduling plan for the power grid in the target area. By clustering the power devices through the power device identification codes, when a fault occurs in the power grid in the target area, the time required for accurate equipment repair can be determined according to the clustering result, and a suitable scheduling plan can be determined according to the time required for the power devices. By optimizing the scheduling plan through the clustering characteristics, the accuracy of the scheduling plan can be ensured, further ensuring the normal operation of the power grid in the target area and improving the stability of the power grid power supply. Description of the Drawings

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of related technologies. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 FIG. 4 is a schematic flowchart of a multi-level power grid coordinated control method based on clustering provided by an embodiment of the present invention;

[0022] Figure 2 FIG. 8 is a schematic diagram of the first clustering result of a multi-level power grid coordinated control method based on clustering provided by an embodiment of the present invention;

[0023] Figure 3 FIG. 12 is a schematic structural diagram of a multi-level power grid coordinated control device based on clustering provided by an embodiment of the present invention. Detailed implementation manners

[0024] In the following description, specific details such as specific system structures and technologies are proposed for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. However, those skilled in the art should clearly understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, the detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present invention.

[0025] Figure 1 FIG. 21 is a schematic flowchart of a multi-level power grid coordinated control method based on clustering provided by an embodiment of the present invention. Referring to Figure 1 FIG. 23, the detailed description of the multi-level power grid coordinated control method based on clustering is as follows:

[0026] S110. Obtain the device data set of the power grid in the target area, and divide the device data set based on the power grid levels of the power grid to obtain sub-device data sets for each power grid level.

[0027] In some embodiments, the target area can be an administrative area or an area divided according to power supply. The device data set of the power grid in the target area may include the device types and manufacturer identifiers of all power devices in the target area, as well as the operation data of each device, the fault handling data of the same type of devices, and the statistical data of the fault occurrence of the power devices produced by each manufacturer. The power grid levels of the power grid may include a power generation level, a substation level, a transmission level, and a distribution level.

[0028] In a possible implementation, obtaining a device dataset of the power grid in the target area includes: obtaining area division information of the power grid and determining the target area based on the area division information; collecting device characteristics and operation data of each device in the power grid within the target area to obtain a device dataset of the power grid in the target area.

[0029] In some embodiments, the area division information refers to the area division information of the power grid, which is related to the area division rules of the power grid. It can be an existing power grid division area or can be re-divided based on the existing power grid division area. For example, when a certain area is divided, the coverage ranges of three substations are taken as one area.

[0030] In some embodiments, the device characteristics include information such as device type, manufacturer of the device, usage time of the device, and expected service life of this type of device.

[0031] Among them, the device dataset includes the device characteristics of all power devices in the power grid of the target area and the corresponding operation data.

[0032] S120, based on the sub-device dataset, obtain the identification code of each power device in the corresponding power grid level, and cluster the power devices in the corresponding power grid level based on the identification code to obtain a first clustering result.

[0033] The first clustering result contains multiple clustering categories, and each clustering category contains multiple power devices and a clustering center. As Figure 2 shown, Figure 2 There are a total of 4 clustering categories shown in the first clustering result, and each clustering category contains a clustering center, and the clustering centers are A1, A2, A3, and A4 respectively.

[0034] In a possible implementation, based on the sub-device dataset, obtaining the identification code of each power device in the corresponding power grid level includes: extracting data from the sub-device dataset to obtain a device information set of each power device in the corresponding power grid level; extracting data from the device information set to obtain the identification code of each power device; among them, the identification code of the power device includes device type, manufacturer identification of each power device, average fault handling time of the same type of device, and fault occurrence probability of power devices of the same manufacturer.

[0035] The identification code of the power device is presented in the form of an array. For example, if the device type of power device A is 21, the manufacturer identification is 03, the average fault handling duration of the same type of device is 29 hours, and the fault occurrence probability of power devices of the same manufacturer is 0.11, then the identification code of power device A is (21, 03, 29, 0.11).

[0036] The device information collection includes the device characteristics and operation data of each power device.

[0037] In a possible implementation, the power devices at the corresponding grid level are clustered based on the identification codes to obtain the first clustering result, including: setting the clustering parameter set for each grid level; clustering all the power devices at the corresponding grid level based on the clustering data set and the identification codes of each power device in the corresponding power level to obtain the initial clustering result; updating the clustering parameter set a preset number of times based on the initial clustering result to obtain a new clustering parameter set; clustering all the power devices at the corresponding grid level based on the new clustering parameter set to obtain the first clustering result.

[0038] Among them, the clustering parameter set includes multiple clustering categories and corresponding clustering centers, which are usually set manually. However, when setting the clustering centers, since the setters do not know enough about the devices, the set clustering centers may not be accurate enough.

[0039] To improve the accuracy of the clustering centers, usually the clustering centers of each clustering category are readjusted based on the clustering results. After adjusting the clustering centers, clustering is performed again to obtain a new clustering result.

[0040] Repeating the above process a preset number of times can obtain relatively accurate clustering centers and corresponding clustering categories.

[0041] In this embodiment, the first clustering result refers to the clustering result obtained by reclustering all the power devices in each grid level based on the finally determined clustering parameter set. Each first clustering result corresponds to a grid level.

[0042] By setting the identification codes of the power devices, each power device can be accurately represented. By initially setting the clustering centers, all the power devices are clustered, and the clustering centers are continuously updated until the number of updates reaches the preset number. Then, all the power devices in the corresponding grid level are clustered using the new clustering parameter set to obtain the first clustering result, effectively ensuring the accuracy of the first clustering result.

[0043] S130, obtain the device characteristics of each power device, and determine the first influence degree of each power device based on the first clustering result and the device characteristics.

[0044] Among them, the device characteristics of the power device include device type, device operation data, the average fault repair time of the same type of devices of this manufacturer, the maximum workload of the device, and the workload under normal operation of the device.

[0045] In this embodiment, the first influence degree refers to the influence degree of each power device on the corresponding grid level.

[0046] In a possible implementation, obtaining the device characteristics of each power device and determining the first influence degree of each power device based on the first clustering result and the device characteristics includes: obtaining the device characteristics of each power device and determining the device coverage range of the corresponding power device based on the device characteristics; for each first clustering result, determining the coverage range of each clustering category based on the first clustering result; and determining the first influence degree of each power device based on the coverage range of each clustering category and the coverage range of each power device within each clustering category.

[0047] Optionally, obtain the work content of each power device in the first clustering result of each level, and determine the coverage range of each power device according to the total workload of the power devices with the same work content and the workload of each power device.

[0048] The calculation formula of the first influence degree is as follows:

[0049]

[0050] where n represents that there are n clustering categories with the same function in the first clustering result, D ij represents the first influence degree of the jth power device in the ith clustering category, represents the total coverage range of the n clustering categories with the same function in the first clustering result, Ff ij represents the coverage range of the ith clustering category among the n clustering categories with the same function in the first clustering result, ff ij represents the coverage range of the jth power device in the ith clustering category.

[0051] Determining the coverage range of the device according to the device characteristics of each power device, determining the coverage range of each clustering category of the first clustering result corresponding to each level, and determining the first influence degree of each power device according to the coverage range ensure that the influence degree of each power device on the power grid in the target area when a fault occurs can be accurately calculated, providing a guarantee for accurate power dispatching.

[0052] S140. Generate the first fault dispatching plan for each power grid level based on the first influence degree and the first clustering result.

[0053] In this embodiment, the first fault dispatching plan refers to the plan for power dispatching according to the fault situation of the power device when there is a power device fault in the power grid of the target area. There is a first fault dispatching plan for each power grid level.

[0054] In a possible implementation, determining a first fault scheduling scheme for each power grid level based on the influence degree and the first clustering result includes: collecting in real time the fault information of the power grid in the target area, and locating the fault level and the faulty power equipment based on the fault information; for each fault level, performing the following steps: obtaining the influence degree and the corresponding clustering category of each faulty power equipment in this fault level; based on the first clustering result, determining the adjustable degree of the power equipment operating normally in this clustering category; obtaining the equipment characteristics of the faulty power equipment, and determining the fault repair time of the corresponding faulty power equipment based on the equipment characteristics; based on the adjustable degree of the power equipment operating normally, the repair time of the faulty power equipment, and the first influence degree of each faulty power equipment, determining the first fault scheduling scheme for this power grid level.

[0055] It should be noted that the fault information will include the specific location where the fault occurs. According to the specific location where the fault occurs, the power grid level where the fault occurs and the power equipment where the fault occurs can be judged. The power grid level where the fault occurs is the fault level, and the power equipment where the fault occurs is the faulty power equipment.

[0056] After determining the clustering category where the fault occurs, according to the first clustering result, the number of power equipment in this clustering category, the maximum workload of each power equipment, and the workload when each power equipment operates normally can be determined. According to the maximum workload and the workload when operating normally of each equipment, the working margin of each power equipment is determined. The sum of the working margins of all the power equipment operating normally in this clustering category is the adjustable degree.

[0057] According to the first influence degree of each power equipment, determine the total workload of one or more faulty power equipment when operating normally, and compare the total workload with the adjustable degree.

[0058] If the adjustable degree is greater than the total workload, obtain the distance between each power equipment operating normally in the clustering category and the faulty power equipment, determine the power equipment operating normally participating in the adjustment and the corresponding adjustment degree according to the distance and the working margin of each power equipment, and determine the participation adjustment duration of the power equipment participating in the adjustment according to the fault repair time.

[0059] If the adjustable degree is less than the total workload, determine the number of faulty power equipment in the clustering category and the repair time of each faulty power equipment, and determine the distance between each faulty power equipment and the clustering center, and sort them in ascending order of the distance. Determine the faulty power equipment that can be adjusted in this clustering category according to the sorting result, and determine the repair time respectively according to the repair time of the faulty power equipment that can be adjusted.

[0060] At this time, if there are clustering categories with the same work content in this clustering category, retrieve the normally operating power equipment from the corresponding categories to participate in power dispatching. If there are no clustering categories with the same work content, let all the normally operating power equipment in this clustering category participate in the dispatching, determine the minimum hard impact duration, and replace some of the faulty power equipment.

[0061] Locate the fault level and faulty power equipment based on the fault information, and determine the first fault dispatching plan according to the adjustable degree, fault repair time, and first impact degree of the normally operating power equipment, which maximally ensures the normal operation of the power grid when a power equipment fails.

[0062] S150. Optimize the corresponding first fault dispatching plan based on the clustering characteristics of each first clustering result to obtain the second fault dispatching plan for the power grid in the target area.

[0063] The second fault plan is the fault dispatching plan for the entire power grid, and the power grid in the target area corresponds to a second fault dispatching plan.

[0064] In a possible implementation, optimizing the corresponding first fault dispatching plan based on the clustering characteristics of each first clustering result includes: determining the distance between the clustering centers of every two clustering categories within the corresponding first clustering result based on the clustering characteristics of each first clustering result; for each clustering category, determining the second impact degree of the remaining clustering categories on this clustering category based on the distance between the remaining clustering categories and this clustering category; optimizing the first fault dispatching plan at the corresponding power grid level based on all the second impact degrees and the corresponding distances to obtain the optimized first fault dispatching plan; where the first fault dispatching plan includes the power equipment to be adjusted and the corresponding adjustment parameters.

[0065] In a possible implementation, optimizing the first fault dispatching plan at the corresponding power grid level based on all the second impact degrees and the corresponding distances to obtain the optimized first fault dispatching plan includes: determining the adjustment degree optimization parameters corresponding to each clustering category containing faulty power equipment based on all the second impact degrees and the corresponding distances; optimizing the adjustment degree of the corresponding power equipment in the first fault dispatching plan based on the adjustment degree optimization parameters to obtain the optimized first fault adjustment plan.

[0066] Optionally, the clustering characteristics include the clustering center of each clustering category in the first clustering result and the number of power equipment included.

[0067] Among them, the second influence degree refers to the influence degree of each of the remaining clustering categories on the clustering category with a fault. For example, in the first clustering result, there are three clustering categories in total, the clustering category with a fault is the second clustering category, the distance between clustering category 1 and clustering category 2 is a, and the distance between clustering category 3 and clustering category 2 is b. Then the second influence degrees of the other two clustering categories on this fault clustering category are respectively: Among them, 3 is because there are three clustering categories in total in this first clustering result.

[0068] The adjustment degree optimization parameter is mainly used to optimize the adjustment degree of the normally operating power equipment participating in the adjustment in the first fault scheduling plan. Multiply the original adjustment degree by the adjustment degree optimization parameter to obtain the first fault adjustment plan. Each clustering category corresponds to an adjustment degree optimization parameter.

[0069] The process of obtaining the adjustment degree optimization parameter is as follows:

[0070] Determine the distance optimization parameter, and multiply the second influence degree by the distance and the distance optimization parameter to obtain the adjustment degree optimization parameter.

[0071] In a possible implementation manner, a second fault scheduling plan for the target area power grid is obtained based on the optimized first fault scheduling plan, including: sorting the power grid levels based on the power flow direction, and obtaining the association information between each power grid level and the previous power grid level; for each power grid level, perform the following steps: based on the association information of this power grid level, determine the association degree between each clustering category in the first clustering result corresponding to this power grid level and the corresponding association information; determine the weight of each clustering category based on each association degree; correct the corresponding optimized first fault scheduling plan based on the weight to obtain the corrected first fault scheduling plan for this power grid level; combine all the first fault scheduling plans to obtain the second fault scheduling plan for the target area power grid.

[0072] Optionally, the power flow direction refers to the flow direction of power during the transmission process, which can be the power generation level - the substation level - the power transmission level - the power consumption level.

[0073] Since the coordinated work of each level of the power grid can ensure that electricity users can use electricity normally, when a fault occurs in one of the levels, the other levels will also be affected accordingly. The association information refers to the relationship between each power grid level and the previous power grid level. For example, the upper level of the substation level is the power generation level, and the association information refers to the connection relationship between the substation level and the power generation level, and the information such as which part of the substation level will be affected when a fault occurs in the power generation level.

[0074] In this embodiment, the association degree refers to the association degree between each clustering category in the clustering result and the association information. For example, in the association information between grid level 1 and grid level 2, if the relevant information about clustering category 2 of grid level 2 exceeds the preset number, then the association degree between clustering category 2 and grid level 2 is relatively high.

[0075] Optionally, the higher the association degree, the higher the weight, and the value of the weight ranges from 0.8 to 1.

[0076] The correction of the optimized first fault scheduling scheme is obtained by multiplying the workload of each power device participating in the scheduling in the first fault scheduling scheme by the weight, and at the same time dividing the workload of the remaining normally operating power devices that do not participate in the scheduling by the weight.

[0077] The second fault scheduling scheme refers to the fault scheduling scheme of the target area power grid, which is obtained by arranging all the first fault scheduling schemes in the order between levels.

[0078] The distance between the clustering centers of every two clustering categories is determined through the clustering characteristics of each first clustering result, and then the second influence degree is obtained according to the distance, and the first fault scheduling scheme is optimized to obtain the optimized first scheduling scheme for each grid level. Then, through the correlation relationship between each grid level, each optimized first scheduling scheme is corrected to obtain the corrected first scheduling scheme. This effectively takes into account the relationship between different clustering categories and the relationship between different grid levels, ensuring the accuracy of the first scheduling scheme. Sorting the first scheduling scheme in the order of grid levels to obtain the second fault scheduling scheme of the power grid in the target area ensures the effective implementation of the second scheduling scheme.

[0079] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0080] Corresponding to the above embodiment, a multi-level power grid coordination control method based on clustering Figure 3 The structure diagram of a multi-level power grid coordination control device provided by an embodiment of the present invention is shown. For the sake of convenience of description, only the parts related to the embodiment of the present invention are shown.

[0081] See Figure 3 , a multi-level power grid coordination control device 3 in an embodiment of the present invention may include:

[0082] An acquisition module 31, configured to acquire the device data set of the power grid in the target area, and divide the device data set based on the grid levels of the power grid to obtain the sub-device data sets of each grid level;

[0083] A clustering module 32, configured to obtain the identification codes of each power device in the corresponding power grid level based on the sub-device data set, and cluster the power devices in the corresponding power grid level based on the identification codes to obtain a first clustering result;

[0084] A determination module 33, configured to obtain the device characteristics of each power device, and determine the first influence degree of each power device based on the first clustering result and the device characteristics;

[0085] A scheduling module 34, configured to generate a first fault scheduling plan for each power grid level based on the first influence degree and the first clustering result;

[0086] An optimization module 35, configured to optimize the corresponding first fault scheduling plan based on the clustering characteristics of each first clustering result to obtain a second fault scheduling plan for the power grid in the target area.

[0087] In a possible implementation manner, the clustering module 32 is specifically configured to:

[0088] Set a clustering parameter set for each power grid level;

[0089] Cluster all the power devices in the corresponding power grid level based on the clustering data set and the identification codes of each power device in the corresponding power level to obtain an initial clustering result;

[0090] Update the clustering parameter set a preset number of times based on the initial clustering result to obtain a new clustering parameter set;

[0091] Cluster all the power devices in the corresponding power grid level based on the new clustering parameter set to obtain a first clustering result.

[0092] In a possible implementation manner, the determination module 33 is specifically configured to:

[0093] Obtain the device characteristics of each power device, and determine the device coverage range of the corresponding power device based on the device characteristics;

[0094] For each first clustering result, determine the coverage range of each clustering category based on the first clustering result;

[0095] Determine the first influence degree of each power device based on the coverage range of each clustering category and the coverage range of each power device within each clustering category.

[0096] In a possible implementation manner, the scheduling module 34 is specifically configured to:

[0097] Collect the fault information of the power grid in the target area in real time, and locate the fault level and the faulty power device based on the fault information;

[0098] For each fault level, perform the following steps:

[0099] Obtain the impact degree of each faulty power device within the fault level and the corresponding clustering category;

[0100] Based on the first clustering result, determine the adjustable degree of the power devices operating normally in the clustering category;

[0101] Obtain the device characteristics of the faulty power devices, and determine the fault repair time of the corresponding faulty power devices based on the device characteristics;

[0102] Based on the adjustable degree of the power devices operating normally, the repair time of the faulty power devices, and the first impact degree of each faulty power device, determine the first fault scheduling plan for the power grid level.

[0103] In a possible implementation, the optimization module 35 is specifically used for:

[0104] Based on the clustering characteristics of each first clustering result, determine the distance between the clustering centers of every two clustering categories within the corresponding first clustering result;

[0105] For each clustering category, based on the distance between the remaining clustering categories and this clustering category, determine the second impact degree of the remaining clustering categories on this clustering category;

[0106] Based on all the second impact degrees and the corresponding distances, optimize the first fault scheduling plan for the corresponding power grid level to obtain the optimized first fault scheduling plan;

[0107] Among them, the first fault scheduling plan includes the power devices to be adjusted and the corresponding adjustment parameters.

[0108] In a possible implementation, the optimization module 35 is also used for:

[0109] Sort the power grid levels based on the power flow direction, and obtain the association information between each power grid level and the previous power grid level;

[0110] For each power grid level, perform the following steps:

[0111] Based on the association information of the power grid level, determine the association degree between each clustering category in the first clustering result corresponding to the power grid level and the corresponding association information;

[0112] Based on each association degree, determine the weight of each clustering category;

[0113] Based on the weights, correct the corresponding optimized first fault scheduling plan to obtain the corrected first fault scheduling plan for the power grid level;

[0114] Combine all the first fault scheduling schemes to obtain the second fault scheduling scheme for the power grid in the target area.

[0115] In a possible implementation, the optimization module 35 is further configured to:

[0116] Determine the adjustment degree optimization parameter corresponding to each clustering category containing faulty power equipment based on all the second influence degrees and the corresponding distances;

[0117] Optimize the adjustment degree of the corresponding power equipment in the first fault scheduling scheme based on the adjustment degree optimization parameter to obtain the optimized first fault adjustment scheme.

[0118] In a possible implementation, the acquisition module 31 is specifically configured to:

[0119] Obtain the area division information of the power grid and determine the target area based on the area division information;

[0120] Collect the device characteristics and operation data of each device in the power grid in the target area to obtain the device dataset of the power grid in the target area.

[0121] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0122] Those of ordinary skill in the art can realize that the templates, units, and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0123] If the above-mentioned 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 such understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various embodiments of the multi-level power grid coordinated control method based on clustering can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0124] The above-mentioned embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A multi-level power grid coordinated control method based on clustering, characterized in that: include: Acquire a device data set of a power grid in a target area, and divide the device data set based on the power grid level of the power grid to obtain a sub-device data set of each power grid level; Based on the sub-device data set, an identification code of each electric power device in the corresponding power grid level is obtained, and the electric power devices in the corresponding power grid level are clustered based on the identification code to obtain a first clustering result; Acquire a device feature of each electric device, and determine a first influence of each electric device based on the first clustering result and the device feature; Based on the first impact degree and the first clustering result, generating a first fault scheduling plan for each power grid level; The corresponding first fault scheduling scheme is optimized based on the clustering characteristics of each first clustering result to obtain a second fault scheduling scheme for the power grid in the target area.

2. The clustering-based multi-level power grid coordinated control method according to claim 1, characterized in that: The obtaining, based on the sub-device data set, an identification code of each power device in the corresponding power grid level comprises: Extract data from the sub-device data set to obtain a device information set for each power device in the corresponding power grid level; Data is extracted from the equipment information set to obtain an identification code for each electrical equipment; wherein the identification code for the electrical equipment includes the equipment type, the manufacturer identification of each electrical equipment, the average fault handling time for equipment of the same type, and the fault probability of electrical equipment of the same manufacturer.

3. The clustering-based multi-level power grid coordinated control method according to claim 1, characterized in that: The clustering of the electric power equipment at the corresponding grid level based on the identification code to obtain a first clustering result includes: Set the clustering parameter set for each grid level; Based on the clustering data set and the identification code of each electric device in the corresponding electric power level, clustering all electric devices at the corresponding power grid level to obtain an initial clustering result; Based on the initial clustering result, the clustering parameter set is updated a preset number of times to obtain a new clustering parameter set; All power equipment at the corresponding power grid level are clustered based on the new clustering parameter set to obtain a first clustering result.

4. The clustering-based multi-level power grid coordinated control method according to claim 1, characterized in that: The acquiring device characteristics of each power device and determining a first influence of each power device based on the first clustering result and the device characteristics includes: Acquire device characteristics of each electric device, and determine the device coverage of the corresponding electric device based on the device characteristics; For each first clustering result, determining the coverage of each clustering category based on the first clustering result; Based on the coverage of each cluster category and the coverage of each electrical device within each cluster category, a first influence of each electrical device is determined.

5. The clustering-based multi-level power grid coordinated control method according to claim 1, characterized in that: The determining a first fault scheduling scheme for each power grid level based on the impact degree and the first clustering result includes: Collect fault information of the power grid in the target area in real time, and locate the fault level and faulty power equipment based on the fault information; For each fault level, perform the following steps: Obtaining the influence degree of each faulty power equipment in the fault level and the corresponding clustering category; Based on the first clustering result, determining the adjustability of the normally operating electrical equipment in the clustering category; Acquire equipment characteristics of the faulty electric equipment, and determine a fault repair time of the corresponding faulty electric equipment based on the equipment characteristics; Based on the adjustability of the normally operating power equipment, the repair time of the faulty power equipment and the first impact of each faulty power equipment, a first fault scheduling plan of the power grid level is determined.

6. The clustering-based multi-level power grid coordinated control method according to claim 1, characterized in that: The optimizing the corresponding first fault scheduling scheme based on the clustering feature of each first clustering result includes: Based on the clustering feature of each first clustering result, determining the distance between the cluster centers of every two clustering categories in the corresponding first clustering result; For each cluster category, based on the distances between the remaining cluster categories and the cluster category, determine a second influence degree of the remaining cluster categories on the cluster category; Based on all the second influence degrees and the corresponding distances, the first fault scheduling plan of the corresponding power grid level is optimized to obtain an optimized first fault scheduling plan; The first fault scheduling plan includes the power equipment to be adjusted and the corresponding adjustment parameters.

7. The clustering-based multi-level power grid coordinated control method according to claim 1, characterized in that: The second fault dispatching scheme for the target area power grid is obtained based on the optimized first fault dispatching scheme, including: Sort the grid levels based on the power flow direction, and obtain association information between each grid level and the previous grid level; For each grid level, perform the following steps: Based on the association information of the power grid level, determining the association degree between each cluster category in the first clustering result corresponding to the power grid level and the corresponding association information; Determining a weight of each cluster category based on each degree of association; Based on the weight, the corresponding optimized first fault scheduling plan is modified to obtain a modified first fault scheduling plan at the power grid level; All the first fault dispatching schemes are combined to obtain a second fault dispatching scheme for the power grid in the target area.

8. The clustering-based multi-level power grid coordinated control method according to claim 6, characterized in that: The first fault scheduling scheme of the corresponding power grid level is optimized based on all the second influence degrees and the corresponding distances to obtain the optimized first fault scheduling scheme, including: Based on all the second influence degrees and the corresponding distances, determining the corresponding adjustment degree optimization parameter of each cluster category including the faulty power equipment; Based on the adjustment degree optimization parameter, the adjustment degree of the corresponding power equipment in the first fault scheduling plan is optimized to obtain an optimized first fault adjustment plan.

9. The clustering-based multi-level power grid coordinated control method according to claim 1, characterized in that: The step of obtaining a data set of equipment in a power grid in a target area includes: Acquire regional division information of the power grid, and determine the target area based on the regional division information; The device characteristics and operation data of each device in the power grid in the target area are collected to obtain a device data set of the power grid in the target area.

10. A multi-level power grid coordination control device based on clustering, characterized in that: include: An acquisition module, used for acquiring a device data set of a power grid in a target area, and dividing the device data set based on the power grid level of the power grid to obtain a sub-device data set of each power grid level; A clustering module, configured to obtain an identification code of each electric power device in a corresponding power grid level based on the sub-device data set, and cluster the electric power devices in the corresponding power grid level based on the identification code to obtain a first clustering result; A determination module, configured to obtain a device feature of each electric device, and determine a first influence of each electric device based on the first clustering result and the device feature; A scheduling module, configured to generate a first fault scheduling plan for each power grid level based on the first impact degree and the first clustering result; The optimization module is used to optimize the corresponding first fault scheduling plan based on the clustering characteristics of each first clustering result to obtain a second fault scheduling plan for the power grid in the target area.

Images