A method and apparatus for deployment of power quality monitoring devices

Abstract

The embodiment of the present application discloses a method and device for deployment of power quality monitoring (PQM) equipment. The method comprises: determining a maximum number of the PQM equipment and historical power data of candidate deployment points, wherein the number of the candidate deployment points is greater than the maximum number of the PQM equipment; clustering the historical power data of the candidate deployment points, wherein the number of target categories is determined based on a Silhouette Coefficient of each candidate category number and the maximum number of the PQM equipment; and determining the deployment points of the PQM equipment based on the center of each category in the target category number. The embodiment of the present application can automatically determine the deployment points of the PQM equipment, reduce the complexity of deployment, optimize the deployment result, and improve the accuracy of deployment.

Description

Technical Field

[0001] This invention relates to the field of power technology, and in particular to a method and apparatus for deploying power quality monitoring (PQM) equipment. Background Technology

[0002] Power quality is crucial not only for the safe and economical operation of power grid companies but also for the safe operation and product quality of users. The integration of numerous distributed energy sources (such as wind and solar power) further deteriorates power quality. Continuous monitoring, analysis, and evaluation of power quality information are prerequisites for identifying power quality problems and improving power quality levels.

[0003] Power Quality Management (PQM) systems utilize PQM devices installed on the grid or user side to transmit monitoring data back to the monitoring center via a network, enabling simultaneous monitoring of multiple locations and disseminating power quality-related information. This is an effective means of power quality monitoring and assessment. To ensure a stable power supply for industrial parks, commercial parks, and other similar locations, many places require the deployment of PQM devices. However, PQM devices are expensive, making the optimization of their deployment locations crucial.

[0004] In existing technologies, determining PQM deployment locations based on individual expertise and experience increases deployment complexity. Furthermore, personally chosen deployment locations may not be optimal, leading to over-monitoring of unimportant areas or neglect of important areas. Summary of the Invention

[0005] This invention provides a method and apparatus for deploying PQM equipment.

[0006] The technical solution of the embodiments of the present invention is as follows:

[0007] A method for deploying a PQM device, the method comprising:

[0008] Determine the maximum number of PQM devices and the historical power data of candidate deployment points, wherein the number of candidate deployment points is greater than the maximum number of PQM devices;

[0009] The historical power data of the candidate deployment points are clustered, wherein the number of target categories is determined based on the silhouette coefficient of each candidate category and the maximum number of PQM devices;

[0010] The deployment point of the PQM device is determined based on the center of each of the target categories.

[0011] As can be seen, in this embodiment of the invention, clustering is performed based on historical power data of candidate deployment points. The target number of categories is constrained by the silhouette coefficient of each candidate category and the maximum number of PQM devices. The deployment points of PQM devices are then determined based on the center of each category corresponding to the target number of categories. This achieves automatic determination of PQM device deployment points and reduces deployment difficulty. Furthermore, clustering based on historical power data of candidate deployment points and optimizing the target number of categories improves the clustering effect and further ensures optimized deployment locations.

[0012] In one implementation, the historical power data includes at least one of the following:

[0013] Current value within a predetermined time period; voltage value within a predetermined time period; power value within a predetermined time period; temperature value within a predetermined time period.

[0014] Therefore, historical power data can be implemented in a variety of ways.

[0015] In one implementation, the method further includes:

[0016] The candidate deployment points are determined from the transformer deployment points located between the substation and the power grid.

[0017] It is evident that by identifying candidate deployment points from the transformer deployment points between the power distribution room and the power grid, the reliability of the candidate deployment points is improved.

[0018] In one implementation, determining the number of target categories based on the silhouette coefficient of each candidate category and the maximum number of PQM devices includes:

[0019] Determine the maximum value of the silhouette coefficient for each candidate category;

[0020] When the maximum value is less than or equal to the maximum number of PQM devices, the number of candidate categories corresponding to the maximum value is determined as the target category number.

[0021] Therefore, when all profile coefficients are small, the number of PQM devices deployed can be reduced by determining the number of candidate categories corresponding to the maximum value as the number of target categories, thereby saving costs.

[0022] In one implementation, determining the number of target categories based on the silhouette coefficient of each candidate category and the maximum number of PQM devices includes:

[0023] Determine the maximum value of the silhouette coefficient for each candidate category;

[0024] When the maximum value is greater than the maximum number of PQM devices, a subset T of the contour coefficient set containing the contour coefficients of each candidate category is determined, wherein each contour coefficient in the subset T is less than or equal to the maximum number of PQM devices, and all contour coefficients in the contour coefficient set except for the subset T are greater than the maximum number of PQM devices.

[0025] The number of candidate categories corresponding to the maximum value in subset T is determined as the target category number.

[0026] It is evident that when all contour coefficients are large, the number of candidate categories with the best clustering effect can be selected, thereby optimizing deployment performance.

[0027] In one implementation, determining the deployment point of the PQM device based on the center of each of the target categories includes:

[0028] When the center of a category coincides with a candidate deployment point, deploy the PQM device at the candidate deployment point.

[0029] When the center of a category does not coincide with a candidate deployment point, the PQM device is deployed at the candidate deployment point that has the closest distance to the center of the category; wherein the distance includes at least one of the following:

[0030] Euclidean distance; Manhattan distance; Chebyshev distance; Cosine similarity; Mahalanobis distance; Minkowski distance.

[0031] Therefore, deploying PQM devices at the center of the clustered categories optimizes deployment performance.

[0032] A deployment apparatus for a PQM (Purpose Quality Management) device, the apparatus comprising:

[0033] The first determining module is used to determine the maximum number of PQM devices and the historical power data of candidate deployment points, wherein the number of candidate deployment points is greater than the maximum number of PQM devices.

[0034] The clustering module is used to cluster the historical power data of the candidate deployment points, wherein the number of target categories is determined based on the silhouette coefficient of each candidate category and the maximum number of PQM devices;

[0035] The second determining module is used to determine the deployment point of the PQM device based on the center of each of the target categories.

[0036] As can be seen, in this embodiment of the invention, clustering is performed based on historical power data of candidate deployment points. The target number of categories is constrained by the silhouette coefficient of each candidate category and the maximum number of PQM devices. The deployment points of PQM devices are then determined based on the center of each category corresponding to the target number of categories. This achieves automatic determination of PQM device deployment points and reduces deployment difficulty. Furthermore, clustering based on historical power data of candidate deployment points and optimizing the target number of categories improves the clustering effect and further ensures optimized deployment locations.

[0037] In one implementation, the historical power data includes at least one of the following:

[0038] Current value within a predetermined time period; voltage value within a predetermined time period; power value within a predetermined time period; temperature value within a predetermined time period.

[0039] Therefore, historical power data can be implemented in a variety of ways.

[0040] In one embodiment, the device further includes:

[0041] The third determining module is used to determine the transformer deployment point between the power distribution room and the power grid as the candidate deployment point.

[0042] It is evident that by identifying candidate deployment points from the transformer deployment points between the power distribution room and the power grid, the reliability of the candidate deployment points is improved.

[0043] In one implementation, a clustering module is used to determine the maximum value of the silhouette coefficient for each candidate category number; when the maximum value is less than or equal to the maximum number of PQM devices, the candidate category number corresponding to the maximum value is determined as the target category number.

[0044] Therefore, when all profile coefficients are small, the number of PQM devices deployed can be reduced by determining the number of candidate categories corresponding to the maximum value as the number of target categories, thereby saving costs.

[0045] In one implementation, a clustering module is used to determine the maximum value of the silhouette coefficient for each candidate category number; when the maximum value is greater than the maximum number of PQM devices, a subset T of the silhouette coefficient set containing the silhouette coefficients for each candidate category number is determined, wherein each silhouette coefficient in subset T is less than or equal to the maximum number of PQM devices, and the silhouette coefficients in the silhouette coefficient set other than subset T are greater than the maximum number of PQM devices; the candidate category number corresponding to the maximum value in subset T is determined as the target category number.

[0046] It is evident that when all contour coefficients are large, the number of candidate categories with the best clustering effect can be selected, thereby optimizing deployment performance.

[0047] In one implementation method

[0048] The second determining module is configured to deploy a PQM device at a candidate deployment point when the center of a category coincides with the candidate deployment point; and to deploy a PQM device at a candidate deployment point that has the closest distance to the center of the category when the center of a category does not coincide with the candidate deployment point; wherein the distance includes at least one of the following:

[0049] Euclidean distance; Manhattan distance; Chebyshev distance; Cosine similarity; Mahalanobis distance; Minkowski distance.

[0050] Therefore, deploying PQM devices at the center of the clustered categories optimizes deployment performance.

[0051] A deployment apparatus for a PQM device, characterized in that it includes: a processor and a memory;

[0052] The memory contains an application program that can be executed by the processor to cause the processor to perform the deployment method of the PQM device as described in any of the preceding claims.

[0053] As can be seen, the embodiments of the present invention propose a deployment device with a processor-memory architecture, which realizes automatic determination of the deployment point of PQM equipment and reduces the deployment difficulty. Moreover, based on the historical power data clustering of candidate deployment points and the optimized design of the number of target categories, the clustering effect is improved, further ensuring the optimization of deployment location.

[0054] A computer-readable storage medium storing computer-readable instructions for performing a deployment method of a PQM device as described in any of the preceding claims.

[0055] Therefore, this invention proposes a computer-readable storage medium storing computer-readable instructions, which enables automatic determination of the deployment point of PQM equipment and reduces deployment difficulty. Furthermore, clustering based on historical power data of candidate deployment points and optimizing the number of target categories improves the clustering effect, further ensuring optimized deployment location. Attached Figure Description

[0056] Figure 1 This is a flowchart illustrating the deployment method of the PQM device according to an embodiment of the present invention.

[0057] Figure 2 This is an exemplary schematic diagram of the clustering results according to an embodiment of the present invention.

[0058] Figure 3 This is an exemplary schematic diagram showing the deployment location of the PQM device according to an embodiment of the present invention.

[0059] Figure 4 This is a structural diagram of the deployment device for the PQM equipment according to an embodiment of the present invention.

[0060] Figure 5 This is a structural diagram of a deployment apparatus for a PQM device with a memory-processor architecture, according to an embodiment of the present invention.

[0061] The reference numerals in the attached figures are as follows:

[0062] label meaning 100 PQM equipment deployment method 101～103 step 20、30、40 kind 51 Commercial electricity load 52 Auxiliary access device 53 Industrial electrical load 54 power distribution room 55 PQM equipment 56 power grid 400 PQM equipment deployment device 401 Third Determination Module 402 First Determination Module 403 Clustering module 404 Second determination module 500 PQM equipment deployment device 501 processor 502 memory Detailed Implementation

[0063] To make the technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the scope of protection of the present invention.

[0064] For the sake of brevity and intuitiveness, the following description uses several representative embodiments to illustrate the solution of the present invention. Numerous details in the embodiments are only used to aid in understanding the solution of the present invention. However, it is obvious that the technical solution of the present invention can be implemented without being limited to these details. To avoid unnecessarily obscuring the solution of the present invention, some embodiments are not described in detail, but only a framework is given. In the following text, "comprising" means "including but not limited to," and "according to..." means "at least according to..., but not limited to only according to...". Due to Chinese language habits, unless the quantity of a component is specifically indicated below, it means that the component can be one or more, or can be understood as at least one.

[0065] Figure 1 This is a flowchart illustrating the deployment method of the PQM device according to an embodiment of the present invention.

[0066] like Figure 1 As shown, the method 100 includes:

[0067] Step 101: Determine the maximum number of PQM devices and the historical power data of candidate deployment sites.

[0068] Here, the maximum number of PQM devices can be determined based on cost accounting conditions. For example, assuming a deployment cost budget of 600,000 RMB and a cost of 40,000 RMB per PQM device, the maximum number of PQM devices is determined to be 15.

[0069] Optionally, the maximum number of PQM devices can be determined based on inventory conditions. For example, if the total number of available PQM devices in the inventory is known to be 20, then the maximum number of PQM devices can be determined to be 20.

[0070] Candidate deployment points are predetermined locations where PQM equipment may be deployed. In one implementation, considering the importance of the transformer's location, the transformer deployment point between the distribution room and the power grid is identified as a candidate deployment point.

[0071] Here, the historical power data for candidate deployment points includes at least one of the following: current value within a predetermined time period; voltage value within a predetermined time period; power value within a predetermined time period; temperature value within a predetermined time period, etc. Identifying transformer deployment points as candidate deployment points allows for convenient retrieval of their historical power data from a database containing such data.

[0072] The above exemplary descriptions illustrate typical examples of determining the maximum number of PQM devices and historical power data for candidate deployment points. Those skilled in the art will recognize that such descriptions are merely exemplary and are not intended to limit the implementation of the present invention.

[0073] Step 102: Cluster the historical power data of the candidate deployment points, wherein the target number of categories is determined based on the silhouette coefficient of each candidate category and the maximum number of PQM devices.

[0074] First, let's explain the meaning of clustering. The process of dividing a collection of physical or abstract objects into multiple classes composed of similar objects is called clustering. The clusters (or categories) generated by clustering are a set of data objects that are similar to objects in the same cluster and different from objects in other clusters.

[0075] In one implementation, a vector model containing each dimension (i.e., data type) of historical power data can be predetermined. For each candidate deployment point, the historical statistical data of each dimension of the candidate deployment point are assigned to the vector model. The vector model after the above assignment is the vector of the historical power data of the candidate deployment point, which facilitates clustering based on vector distance.

[0076] The clustering algorithms that can be used in the embodiments of the present invention include, but are not limited to, partition-based clustering algorithms, hierarchical clustering algorithms, density-based clustering algorithms, grid-based clustering algorithms, neural network-based clustering algorithms, or statistical clustering algorithms, etc.

[0077] Preferably, the clustering algorithm used in the embodiments of the present invention includes: k-means algorithm, k-modes algorithm, k-prototypes algorithm, or k-medoid algorithm, etc. The dimension used in clustering can be any dimension in the vector model used in historical power data, or a combination of at least two dimensions. Vector distance algorithms such as Euclidean distance, Manhattan distance, Mahalanobis distance, or Minkowski distance can be used to determine the vector distance between the vector of each candidate deployment point and the vectors of other candidate deployment points.

[0078] Figure 2 This is an exemplary schematic diagram of the clustering results according to an embodiment of the present invention. As can be seen, the candidate deployment points are clustered into three classes along the two dimensions of the horizontal axis X and the vertical axis Y, namely class 20, class 30 and class 40.

[0079] The above description uses two dimensions as an example to illustrate exemplary clustering results. Those skilled in the art will recognize that the number of dimensions can also be other (e.g., 1, 3, 4, or more), and the embodiments of the present invention are not limited in this regard.

[0080] The silhouette coefficient is a method for evaluating the quality of clustering. It combines two factors: cohesion and separation. It can be used to evaluate the impact of different algorithms or different ways of running an algorithm on the clustering results, based on the same original data.

[0081] For example, clustering can be performed on the historical power data (data to be classified) of candidate deployment points, such as using the K-means clustering algorithm, to divide the data into K clusters (categories). In this embodiment of the invention, the value of K ranges from [2, (maximum number of PQM devices - 1)]. For each point in each cluster, their silhouette coefficients can be calculated separately. For point i: calculate a(i) and calculate b(i); then the silhouette coefficient S(i) of point i is:

[0082]

[0083] Where a(i) is the average dissimilarity of point i to other points in the same cluster; b(i) is the minimum average dissimilarity of point i to other clusters; max() is the function to find the maximum value. If S(i) is close to 1, it means that sample i is clustered reasonably; if S(i) is close to -1, it means that sample i should be classified into another cluster; if S(i) is approximately 0, it means that sample i is on the boundary between two clusters.

[0084] The mean of S(i) for all points is called the silhouette coefficient of the clustering effect for each number of candidate categories. In other words, averaging the silhouette coefficients of all points gives the silhouette coefficient of the clustering effect for K clusters.

[0085] For each K value, a silhouette coefficient of the corresponding clustering effect is calculated, that is, the silhouette coefficient of each candidate category number is calculated. Then, the target category number can be determined based on the silhouette coefficient of each candidate category number and the maximum number of PQM devices.

[0086] In one implementation, determining the target number of categories based on the profile coefficient of each candidate category and the maximum number of PQM devices includes: determining the maximum value of the profile coefficient of each candidate category; and when the maximum value is less than or equal to the maximum number of PQM devices, determining the candidate category corresponding to the maximum value as the target number of categories.

[0087] For example, assuming the maximum number of PQM devices is 30, the silhouette coefficient of each candidate category is less than 30, and the maximum silhouette coefficient among all candidate categories is 25, then the target category number can be determined to be 25, i.e., the final K value is determined to be 25. Then, the deployment points of the PQM devices can be determined using the centers of the 25 clustered categories.

[0088] In one implementation, determining the target number of categories based on the profile coefficients of each candidate category and the maximum number of PQM devices includes: determining the maximum value of the profile coefficients of each candidate category; when the maximum value is greater than the maximum number of PQM devices, determining a subset T of the profile coefficient set containing the profile coefficients of each candidate category, wherein each profile coefficient in subset T is less than or equal to the maximum number of PQM devices, and all profile coefficients in the profile coefficient set except for subset T are greater than the maximum number of PQM devices; and determining the candidate category number corresponding to the maximum value in subset T as the target number of categories.

[0089] For example, assuming the maximum number of PQM devices is 30, when the maximum profile coefficient among the candidate category numbers is 40, since the maximum value (40) is greater than the maximum number of PQM devices (30), the maximum value (40) cannot be selected as the target category number. In this case, a subset T is determined from the profile coefficient set containing the profile coefficients of each candidate category number, where each profile coefficient in subset T is less than or equal to the maximum number of PQM devices (40), and all profile coefficients in the profile coefficient set other than subset T are greater than the maximum number of PQM devices (40). Then, the candidate category number corresponding to the maximum value in subset T is determined as the target category number. In other words, the profile coefficient of the determined target category number must be less than the maximum number of PQM devices and also be the maximum value in subset T containing all values ​​less than that maximum number. For example, assuming the final determined target category number is 20, that is, the final K value is determined to be 20. Then, the deployment points of the PQM devices can be determined using the centers of the 20 clustered categories.

[0090] Step 103: Determine the deployment point of the PQM device based on the center of each of the target categories.

[0091] In one implementation, when the center of a category coincides with a candidate deployment point, a PQM device is deployed at the candidate deployment point. Preferably, a single PQM device is placed at the coinciding candidate deployment point.

[0092] In one implementation, when the center of a category does not coincide with a candidate deployment point, a PQM device is deployed at the candidate deployment point closest to the center of the category; wherein the distance includes at least one of the following: Euclidean distance; Manhattan distance; Chebyshev distance; cosine similarity; Mahalanobis distance; Minkowski distance, etc. Preferably, a single PQM device is deployed at the candidate deployment point closest to the center of the category.

[0093] For example, assuming the number of target categories determined in step 102 is 10, then 10 categories are clustered. Each of these 10 categories has its own category center, that is, there are 10 category centers.

[0094] For each of the 10 categories, determine whether the category center coincides with a candidate deployment point. If they coincide, the coincident candidate deployment point is determined as the deployment point for that category, and the PQM device is deployed at that candidate deployment point. If the category center does not coincide with a candidate deployment point, the candidate deployment point with the closest distance to the category center is determined as the deployment point for that category, and the PQM device is deployed at that candidate deployment point.

[0095] Preferably, each deployment point is equipped with a single PQM device, so the actual total number of PQM devices deployed is equal to the number of destination categories.

[0096] Specifically, PQM equipment, deployed at the point of deployment, can measure and analyze the AC power quality supplied from the public power grid to the user's receiving end. The measured and analyzed indicators include: power supply frequency deviation, power supply voltage deviation, power supply voltage fluctuation and flicker, allowable imbalance of the three-phase voltage, and harmonics of the power grid. Wavelet transform is used to measure and analyze harmonics of non-stationary time-varying signals, etc. PQM equipment can also measure and analyze the impact of various electrical devices on the power quality of the public power grid under different operating conditions. It can also test and analyze the dynamic parameters of reactive power compensation and filtering devices in the power system and provide quantitative evaluations of their functions and technical indicators.

[0097] Figure 1 The process shown is particularly suitable for applications requiring a stable power supply, such as industrial parks and commercial parks.

[0098] The following examples illustrate embodiments of the present invention.

[0099] Suppose an industrial park has 100 candidate deployment sites x1, x2, ..., x100, each requiring the deployment of PQM equipment. However, the number of PQM devices is limited, with funding only for a maximum of 30 devices (i.e., the maximum number of PQM devices is 30). Therefore, selective deployment of PQM devices is necessary. Each candidate deployment site has its own historical power data, and the historical power data of all candidate deployment sites share the same data types.

[0100] K-means clustering was performed using a clustering algorithm with Euclidean distance. Furthermore, silhouette coefficients were used to define the appropriate number of clusters.

[0101] Taking the generation of 10 classes c1, c2, c3, c4...c10 as an example: Each class has a center, and there are a total of 10 centers, namely m1, m2...m10. These centers may be real candidate deployment points or calculated virtual candidate deployment points. Specifically: For each point, the silhouette coefficient s is calculated, resulting in s1, s2...s100. Then, the average of these 100 silhouette coefficients s is calculated, K = mean(s1, s2...s100), and this value is denoted as K10 (corresponding to the division into 10 classes).

[0102] Referring to the above example, the number of categories can be from 2 to 99, and the silhouette coefficient set (K2, K3, K4, ..., K99) can be calculated for each category. The number of categories corresponding to the maximum silhouette coefficient value in this set is the optimal number of categories.

[0103] For example, assuming K22 is the maximum value, the most suitable number of categories is 22. Since 22 is less than the maximum number of PQM devices (30), deploying 22 PQM devices is sufficient, thus saving 8 PQM devices.

[0104] For example, K44 is the maximum value in the set of profile coefficients, so the most suitable number of categories is 44. However, when 44 is greater than the maximum number of PQM devices (30), then we look for the second largest profile coefficient. If the second largest profile coefficient is still greater than 30, we continue to look down until we find a profile coefficient less than or equal to 30.

[0105] Figure 3 This is an exemplary schematic diagram showing the deployment location of the PQM device according to an embodiment of the present invention.

[0106] Depend on Figure 3 As can be seen, commercial electrical load 51 is connected to the substation 54 via auxiliary access device 52. Industrial electrical load 53 is connected to the substation 54. The substation 54 is connected to the power grid 56. The transformer deployment point between the substation 54 and the power grid 56 can be identified as a candidate deployment point.

[0107] Based on the above description, the present invention provides a deployment apparatus for PQM equipment.

[0108] Figure 4 This is a structural diagram of the deployment device for the PQM equipment according to an embodiment of the present invention.

[0109] like Figure 4 As shown, the device 400 includes:

[0110] The first determining module 402 is used to determine the maximum number of PQM devices and the historical power data of candidate deployment points, wherein the number of candidate deployment points is greater than the maximum number of PQM devices.

[0111] Clustering module 403 is used to cluster the historical power data of the candidate deployment points, wherein the number of target categories is determined based on the silhouette coefficient of each candidate category and the maximum number of PQM devices;

[0112] The second determining module 404 is used to determine the deployment point of the PQM device based on the center of each of the target categories.

[0113] In one embodiment, the historical power data includes at least one of the following: current value over a predetermined time period; voltage value over a predetermined time period; power value over a predetermined time period; temperature value over a predetermined time period, etc.

[0114] In one embodiment, the device 400 further includes a third determining module 401, used to determine the transformer deployment point between the power distribution room and the power grid as the candidate deployment point.

[0115] In one implementation, clustering module 403 is used to determine the maximum value of the silhouette coefficient for each candidate category number; when the maximum value is less than or equal to the maximum number of PQM devices, the candidate category number corresponding to the maximum value is determined as the target category number.

[0116] In one implementation, clustering module 403 is used to determine the maximum value of the silhouette coefficient for each candidate category number; when the maximum value is greater than the maximum number of PQM devices, a subset T of the silhouette coefficient set containing the silhouette coefficients for each candidate category number is determined, wherein each silhouette coefficient in subset T is less than or equal to the maximum number of PQM devices, and the silhouette coefficients in the silhouette coefficient set other than subset T are greater than the maximum number of PQM devices; the candidate category number corresponding to the maximum value in subset T is determined as the target category number.

[0117] In one implementation, the second determining module (404) is configured to deploy a PQM device at a candidate deployment point when the center of a category coincides with the candidate deployment point; and to deploy a PQM device at a candidate deployment point that has the closest distance to the center of the category when the center of a category does not coincide with the candidate deployment point; wherein the distance includes at least one of the following: Euclidean distance; Manhattan distance; Chebyshev distance; cosine similarity; Mahalanobis distance; Minkowski distance, etc.

[0118] Based on the above description, embodiments of the present invention also propose a deployment apparatus for a PQM device with a memory-processor architecture.

[0119] Figure 5 This is a block diagram of a deployment apparatus for a PQM device with a memory-processor architecture according to an embodiment of the present invention.

[0120] like Figure 5 As shown, the PQM device deployment apparatus 500 includes a processor 501, a memory 502, and a computer program stored in the memory 502 and executable on the processor 501. When the computer program is executed by the processor 501, it implements the PQM device deployment method as described above.

[0121] Specifically, the memory 502 can be implemented as various storage media such as electrically erasable programmable read-only memory (EEPROM), flash memory, and programmable programmable read-only memory (PROM). The processor 501 can be implemented as including one or more central processing units (CPUs) or one or more field-programmable gate arrays (FPGAs), wherein the FPGA integrates one or more CPU cores. Specifically, the CPU or CPU core can be implemented as a CPU, MCU, DSP, etc.

[0122] It should be noted that not all steps and modules in the above processes and structural diagrams are mandatory; some steps or modules can be omitted as needed. The execution order of the steps is not fixed and can be adjusted as required. The division of modules is merely for the convenience of description and functional division. In actual implementation, a module can be implemented by multiple modules, and the functions of multiple modules can also be implemented by the same module. These modules can be located in the same device or in different devices.

[0123] The hardware modules in each embodiment can be implemented mechanically or electronically. For example, a hardware module may include specially designed permanent circuitry or logic devices (such as dedicated processors, such as FPGAs or ASICs) to perform specific operations. A hardware module may also include programmable logic devices or circuitry (such as general-purpose processors or other programmable processors) temporarily configured by software to perform specific operations. The choice between mechanical implementation, dedicated permanent circuitry, or temporarily configured circuitry (such as software-configured circuitry) can be made based on cost and time considerations.

[0124] The present invention also provides a machine-readable storage medium storing instructions for causing a machine to perform the methods described herein. Specifically, a system or apparatus equipped with a storage medium storing software program code implementing the functions of any of the embodiments described above can be provided, and the computer (or CPU or MPU) of the system or apparatus can read and execute the program code stored in the storage medium. Furthermore, an operating system or similar device operating on a computer can perform some or all of the actual operations through instructions based on the program code. The program code read from the storage medium can also be written to a memory located in an expansion board inserted into a computer or to a memory located in an expansion unit connected to the computer, and then, based on the instructions of the program code, a CPU or similar device installed on the expansion board or expansion unit can execute some or all of the actual operations, thereby implementing the functions of any of the embodiments described above. Storage medium embodiments for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, the program code can be downloaded from a server computer or the cloud via a communication network.

[0125] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for deploying power quality monitoring equipment (100), characterized in that, The method (100) includes: Determine the maximum number of power quality monitoring devices and the historical power data of candidate deployment points, wherein the number of candidate deployment points is greater than the maximum number of power quality monitoring devices (101); The historical power data of the candidate deployment points are clustered, wherein the number of target categories is determined based on the silhouette coefficient of each candidate category and the maximum number of power quality monitoring devices (102); The deployment points of the power quality monitoring equipment are determined based on the center of each of the target categories (103).

2. The deployment method (100) of the power quality monitoring equipment according to claim 1, characterized in that, The historical power data includes at least one of the following: Current value within a predetermined time period; voltage value within a predetermined time period; power value within a predetermined time period; temperature value within a predetermined time period.

3. The deployment method (100) of the power quality monitoring equipment according to claim 1, characterized in that, The method (100) further includes: The candidate deployment points are determined from the transformer deployment points located between the substation and the power grid.

4. The deployment method (100) of the power quality monitoring equipment according to claim 1, characterized in that, The determination of the target category number based on the silhouette coefficient of each candidate category number and the maximum number of power quality monitoring devices includes: Determine the maximum value of the silhouette coefficient for each candidate category; When the maximum value is less than or equal to the maximum number of power quality monitoring devices, the number of candidate categories corresponding to the maximum value is determined as the target category number.

5. The deployment method (100) of the power quality monitoring equipment according to claim 1, characterized in that, The determination of the target category number based on the silhouette coefficient of each candidate category number and the maximum number of power quality monitoring devices includes: Determine the maximum value of the silhouette coefficient for each candidate category; When the maximum value is greater than the maximum number of power quality monitoring devices, a subset T of the contour coefficient set containing the contour coefficients of each candidate category is determined, wherein each contour coefficient in the subset T is less than or equal to the maximum number of power quality monitoring devices, and all contour coefficients in the contour coefficient set except for the subset T are greater than the maximum number of power quality monitoring devices. The number of candidate categories corresponding to the maximum value in subset T is determined as the target category number.

6. The deployment method (100) of the power quality monitoring equipment according to claim 1, characterized in that, The determination of the deployment points of the power quality monitoring equipment based on the center of each of the target categories (103) includes: When the center of a category coincides with a candidate deployment point, power quality monitoring equipment is deployed at the candidate deployment point. When the center of a category does not coincide with a candidate deployment point, the power quality monitoring device is deployed at the candidate deployment point that has the closest distance to the center of the category; wherein the distance includes at least one of the following: Euclidean distance; Manhattan distance; Chebyshev distance; Cosine similarity; Mahalanobis distance; Minkowski distance.

7. A deployment device (400) for power quality monitoring equipment, characterized in that, The device (400) includes: The first determining module (402) is used to determine the maximum number of power quality monitoring devices and the historical power data of candidate deployment points, wherein the number of candidate deployment points is greater than the maximum number of power quality monitoring devices; Clustering module (403) is used to cluster the historical power data of the candidate deployment points, wherein the number of target categories is determined based on the silhouette coefficient of each candidate category and the maximum number of power quality monitoring devices; The second determining module (404) is used to determine the deployment point of the power quality monitoring equipment based on the center of each of the target categories.

8. The deployment device (400) for power quality monitoring equipment according to claim 7, characterized in that, The historical power data includes at least one of the following: Current value within a predetermined time period; voltage value within a predetermined time period; power value within a predetermined time period; temperature value within a predetermined time period.

9. The deployment device (400) for power quality monitoring equipment according to claim 7, characterized in that, The device (400) also includes: The third determining module (401) is used to determine the transformer deployment point between the power distribution room and the power grid as the candidate deployment point.

10. The deployment device (400) for power quality monitoring equipment according to claim 7, characterized in that, Clustering module (403) is used to determine the maximum value of the silhouette coefficient of each candidate category number; when the maximum value is less than or equal to the maximum number of power quality monitoring devices, the candidate category number corresponding to the maximum value is determined as the target category number.

11. The deployment device (400) for power quality monitoring equipment according to claim 7, characterized in that, Clustering module (403) is used to determine the maximum value of the profile coefficient for each candidate category number; when the maximum value is greater than the maximum number of power quality monitoring devices, a subset T of the profile coefficient set containing the profile coefficients of each candidate category number is determined, wherein each profile coefficient in subset T is less than or equal to the maximum number of power quality monitoring devices, and the profile coefficients in the profile coefficient set other than subset T are greater than the maximum number of power quality monitoring devices; the candidate category number corresponding to the maximum value in subset T is determined as the target category number.

12. The deployment device (400) for power quality monitoring equipment according to claim 7, characterized in that, The second determining module (404) is configured to deploy a power quality monitoring device at a candidate deployment point when the center of the category coincides with the candidate deployment point; and to deploy a power quality monitoring device at a candidate deployment point that has the closest distance to the center of the category when the center of the category does not coincide with the candidate deployment point; wherein the distance includes at least one of the following: Euclidean distance; Manhattan distance; Chebyshev distance; Cosine similarity; Mahalanobis distance; Minkowski distance.

13. A deployment device (500) for power quality monitoring equipment, characterized in that, include: Processor (501) and memory (502); The memory (502) contains an application program that can be executed by the processor (501) to cause the processor (501) to execute the deployment method (100) of the power quality monitoring device as described in any one of claims 1 to 6.

14. A computer-readable storage medium, characterized in that, It contains computer-readable instructions for performing the deployment method (100) of the power quality monitoring equipment as described in any one of claims 1 to 6.

Images