Reactive voltage control method and device for regional power distribution network

Abstract

The embodiment of the application discloses a kind of reactive voltage control methods and devices of regional distribution network, the method comprises: obtaining each regional node sample corresponding to regional distribution network, each regional node sample includes the voltage and power factor corresponding to each regional node;The voltage and power factor corresponding to each regional node sample are input into Gaussian mixture distribution function, determine the target distribution probability corresponding to regional node sample;Based on target distribution probability and preset interval threshold, each regional node is clustered, to determine the target regional category cluster corresponding to each regional node;According to the electrical parameter characteristics corresponding to each target regional category cluster, determine the target control strategy of regional distribution network.Gaussian mixture distribution function is used for the clustering of regional distribution network VQC control, and the characteristics of each electrical parameter characteristic can be obtained according to the category cluster in the regional VQC control, and a targeted target control strategy can be used.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of reactive power and voltage control of power distribution network, and particularly relates to a reactive power and voltage control method and device for regional power distribution network. BACKGROUND

[0002] At present, the reactive power and voltage control (VQC) strategy at the level of substation mainly is the VQC control strategy based on the classic nine-region diagram, or the thirteen-region diagram, fifteen-region diagram, seventeen-region diagram, and optimized nine-region diagram improved from the nine-region diagram. At the level of substation, the VQC regulation and control strategy can improve the power quality of power grid, and has good effect on the voltage and reactive power regulation and control at the level of substation. However, at the level of power distribution network, it is also important to take appropriate VQC regulation and control strategy for the voltage and reactive power regulation and control of regional power distribution network, but the traditional VQC control is a control method for a certain power grid node, and there is still lack of effective reactive power and voltage control method for the level of regional power distribution network. SUMMARY

[0003] The main purpose of the present application is to provide a reactive power and voltage control method and device for regional power distribution network, which can solve the problem of lack of effective reactive power and voltage control method in the prior art.

[0004] To achieve the above purpose, the first aspect of the present application provides a reactive power and voltage control method for regional power distribution network, which comprises the following steps:

[0005] obtaining each regional node sample corresponding to the regional power distribution network, wherein each regional node sample comprises voltage and power factor corresponding to each regional node;

[0006] inputting the voltage and power factor corresponding to each regional node sample into a Gaussian mixture distribution function to determine the target distribution probability corresponding to the regional node sample;

[0007] based on the target distribution probability and a preset interval threshold, clustering each regional node to determine the target regional category cluster corresponding to each regional node;

[0008] determining the target regulation and control strategy of the regional power distribution network according to the electrical parameter characteristics corresponding to each target regional category cluster.

[0009] In a feasible implementation manner, the electrical parameter characteristics corresponding to the target regional category cluster include voltage characteristics and power factor characteristics, and the determination of the target regulation and control strategy of the regional power distribution network according to the electrical parameter characteristics corresponding to each target regional category cluster comprises:

[0010] If the electrical parameter characteristics corresponding to the target region category cluster are that the voltage characteristics and the power factor characteristics of the region nodes within the cluster are qualified, the target regulation strategy of the regional power distribution network is not to act;

[0011] If the electrical parameter characteristics corresponding to the target region category cluster are that the voltage characteristics of the region nodes within the cluster are qualified, and the power factor characteristics are low, the target regulation strategy of the regional power distribution network is to perform a capacitor operation;

[0012] If the electrical parameter characteristics corresponding to the target region category cluster are that the voltage characteristics of the region nodes within the cluster are low, and the power factor characteristics are qualified, the target regulation strategy of the regional power distribution network is to adjust the transformer gear to perform a step-down voltage boosting operation;

[0013] If the electrical parameter characteristics corresponding to the target region category cluster are that the voltage characteristics of the region nodes within the cluster are high, and the power factor characteristics are qualified, the target regulation strategy of the regional power distribution network is to adjust the transformer gear to perform a step-up voltage lowering operation;

[0014] If the electrical parameter characteristics corresponding to the target region category cluster are that the voltage characteristics of the region nodes within the cluster are low, and the power factor characteristics are low, the target regulation strategy of the regional power distribution network is to perform a capacitor operation and adjust the transformer gear to perform a step-down voltage boosting operation.

[0015] In a feasible implementation manner, the inputting the voltage and the power factor corresponding to each region node sample into a Gaussian mixture distribution function to determine the target distribution probability corresponding to the region node sample comprises:

[0016] The voltage and the power factor corresponding to each region node sample are inputted into a Gaussian mixture distribution function to obtain a first distribution probability corresponding to each region node sample;

[0017] The Gaussian distribution parameters are updated by using the each region node sample and the first distribution probability to obtain an updated Gaussian mixture distribution function, and the step of inputting the voltage and the power factor corresponding to each region node sample into a Gaussian mixture distribution function to obtain a first distribution probability corresponding to each region node sample is returned to be executed until the update iteration of the Gaussian mixture distribution function reaches a convergence precision, and the target distribution probability corresponding to the region node sample is obtained.

[0018] In a feasible implementation manner, the Gaussian mixture distribution function comprises:

[0019]

[0020] Wherein, α i is the probability that the region node sample belongs to the i-th cluster, μi ,σ i respectively represent the Gaussian distribution mean and the Gaussian distribution standard deviation of the i th cluster.

[0021] In a possible implementation, the inputting the voltage and the power factor corresponding to each regional node sample into a Gaussian mixture distribution function to obtain a first distribution probability corresponding to each regional node sample comprises:

[0022]

[0023] wherein, y j = i represents the i th distribution, a i represents the probability that the regional node sample belongs to the i th cluster, m i ,σ i respectively represent the Gaussian distribution mean and the Gaussian distribution standard deviation of the i th cluster, a k represents the probability that the regional node sample belongs to the k th cluster, m k ,σ k respectively represent the Gaussian distribution mean and the Gaussian distribution standard deviation of the k th cluster.

[0024] In a possible implementation, the Gaussian distribution parameters comprise a Gaussian distribution mean and a Gaussian distribution standard deviation, and the updating the Gaussian distribution parameters by using the regional node samples and the first distribution probability comprises:

[0025] updating the Gaussian distribution mean by using the regional node samples and the first distribution probability;

[0026] updating the Gaussian distribution standard deviation according to the Gaussian distribution mean, the regional node samples and the first distribution probability.

[0027] In a possible implementation, the updating the Gaussian distribution mean by using the regional node samples and the first distribution probability comprises:

[0028]

[0029] wherein, p ji represents the probability that the data j corresponding to the j th regional node sample conforms to the distribution i, m represents the sample quantity, m i represents the Gaussian distribution mean of the i th cluster, and x j represents the j th regional node sample.

[0030] In a possible implementation, the updating the Gaussian distribution standard deviation according to the Gaussian distribution mean, the regional node samples and the first distribution probability comprises:

[0031]

[0032] wherein p ji is the probability that the data j corresponding to the jth regional node sample conforms to the distribution i, m is the number of samples, μ i ,σ i are the Gaussian distribution mean and Gaussian distribution standard deviation of the ith cluster respectively, and x j is the jth regional node sample.

[0033] In a feasible implementation manner, the clustering of the regional nodes based on the target distribution probability and the preset interval threshold, and the determination of the target regional category cluster corresponding to each regional node include:

[0034] According to the formula:

[0035] max(p ji ), i∈{1,...,n}

[0036] The maximum value of the distribution probability of each distribution i to which the jth regional node sample x j conforms is obtained, so as to determine the target regional category cluster a corresponding to the jth regional node sample x j , and the regional node j corresponding to the jth regional node sample x j is divided into the corresponding target regional category cluster a, and the target regional category cluster is the cluster corresponding to the maximum value of the distribution probability;

[0037] Each regional node sample is traversed, and each regional node is divided into the corresponding target regional category cluster to complete the clustering.

[0038] To achieve the above object, the second aspect of the present application provides a reactive voltage control device for a regional power distribution network, which comprises:

[0039] A sample acquisition module is configured to acquire each regional node sample corresponding to the regional power distribution network, wherein each regional node sample comprises the voltage and power factor corresponding to each regional node.

[0040] A probability determination module is configured to input the voltage and power factor corresponding to each regional node sample into a Gaussian mixture distribution function, and determine the target distribution probability corresponding to the regional node sample.

[0041] A category clustering module is configured to cluster each regional node based on the target distribution probability and a preset interval threshold, and determine the target regional category cluster corresponding to each regional node.

[0042] A strategy generation module is configured to determine the target regulation strategy of the regional power distribution network according to the electrical parameter characteristics corresponding to each target regional category cluster.

[0043] To achieve the above object, the third aspect of the present application provides a computer readable storage medium, which stores a computer program, and the computer program, when executed by a processor, causes the processor to perform the steps of the first aspect or any possible implementation.

[0044] To achieve the above object, the fourth aspect of the present application provides a computer device, which comprises a memory and a processor, and the memory stores a computer program, and the computer program, when executed by the processor, causes the processor to perform the steps of the first aspect or any possible implementation.

[0045] The embodiments of the present application have the following beneficial effects:

[0046] The present application provides a reactive voltage control method for a regional power distribution network, which comprises: obtaining each regional node sample corresponding to the regional power distribution network, each regional node sample comprising a voltage and a power factor corresponding to each regional node; inputting the voltage and the power factor corresponding to each regional node sample into a Gaussian mixture distribution function to determine a target distribution probability corresponding to the regional node sample; clustering each regional node based on the target distribution probability and a preset interval threshold to determine a target regional category cluster corresponding to each regional node; and determining a target control strategy for the regional power distribution network according to an electrical parameter characteristic corresponding to each target regional category cluster. The Gaussian mixture distribution function has a good effect on the clustering of the VQC control of the regional power distribution network, and the regional VQC control can be performed according to the characteristics of each electrical parameter characteristic of the category cluster obtained by the clustering, and a targeted target control strategy can be used. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the drawings needed in the embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0048] Among them:

[0049] Figure 1 A flowchart of a reactive voltage control method for a regional power distribution network in an embodiment of the present application;

[0050] Figure 2 Another flowchart of a reactive voltage control method for a regional power distribution network in an embodiment of the present application;

[0051] Figure 3 A clustering result schematic diagram of a target regional category cluster corresponding to a regional node in an embodiment of the present application;

[0052] Figure 4 Figure 1 is a structural block diagram of a reactive voltage control device of a regional power distribution network according to an embodiment of the present application;

[0053] Figure 5 Figure 1 is a structural block diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0054] The technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0055] Please refer to Figure 1 , Figure 1 Figure 1 is a flowchart of a reactive voltage control method of a regional power distribution network according to an embodiment of the present application. Figure 1 The method shown in Figure 1 can be applied to a terminal or a server. The embodiment is described by taking the application to the terminal as an example. The method shown in Figure 1 includes the following steps. Figure 1

[0056] 101, obtain each regional node sample corresponding to the regional power distribution network, wherein each regional node sample includes voltage and power factor corresponding to each regional node;

[0057] It should be noted that the embodiment obtains each regional node sample corresponding to the regional power distribution network for subsequent clustering. The regional node sample includes voltage and power factor corresponding to each regional node. The obtaining manner can be input by a user or transmitted by a detection device, and the detection device includes but is not limited to a sensor and other electronic devices with detection capability. The power distribution network can be a regional power distribution network composed of multiple 10kV power distribution lines.

[0058] 102, input the voltage and power factor corresponding to each regional node sample into a Gaussian mixture distribution function to determine a target distribution probability corresponding to the regional node sample;

[0059] Further, the voltage and power factor corresponding to the regional node sample are input into the Gaussian mixture distribution function to determine the target distribution probability corresponding to the regional node sample. The target distribution probability is the probability of the regional node sample belonging to each distribution.

[0060] ​It should be noted that the Gaussian mixture distribution function belongs to the Gaussian mixture model clustering algorithm, which is a clustering analysis algorithm and a probabilistic clustering method. It is assumed that all data samples are generated by a mixed distribution composed of multiple mixed multivariate Gaussian distributions. For each sample point, the posterior probability of belonging to each cluster is calculated according to Bayes' theorem, and the sample is divided into the cluster with the maximum posterior probability. The Gaussian mixture model clustering algorithm can be used for data classification and has good effect in data classification.

[0061] 103. Clustering each of the area nodes based on the target distribution probability and a preset interval threshold to determine a target area category cluster corresponding to each of the area nodes;

[0062] It can be understood that in the embodiment, the target distribution probability and the preset interval threshold are used to cluster each area node to determine the target area category cluster corresponding to each area node. Then the category corresponding to the area node is determined.

[0063] 104. Determining a target control strategy of the regional power distribution network according to electrical parameter characteristics corresponding to each of the target area category clusters.

[0064] It should be noted that the area category cluster is divided based on electrical parameters such as voltage and power factor, so different area category clusters correspond to different electrical parameter characteristics. Therefore, in the embodiment, the target control strategy of the regional power distribution network is determined according to the electrical parameter characteristics corresponding to each target area category cluster. The target control strategy is used for reactive voltage control of the regional power distribution network and is set for different electrical parameter characteristics.

[0065] The present application provides a reactive voltage control method for a regional power distribution network, which comprises: obtaining each area node sample corresponding to the regional power distribution network, each area node sample comprising voltage and power factor corresponding to each area node; inputting the voltage and power factor corresponding to each area node sample into a Gaussian mixture distribution function to determine a target distribution probability corresponding to the area node sample; clustering each area node based on the target distribution probability and a preset interval threshold to determine a target area category cluster corresponding to each area node; and determining a target control strategy of the regional power distribution network according to electrical parameter characteristics corresponding to each target area category cluster. The Gaussian mixture distribution function has good effect on clustering of VQC control of the regional power distribution network, and the target control strategy can be used for regional VQC control according to the characteristics of the category cluster obtained by clustering in each electrical parameter characteristic.

[0066] Please refer to Figure 2 , Figure 2 Another flowchart of the reactive voltage control method for a regional power distribution network in the embodiment of the present application is shown in FIG. 4. Figure 2The method comprises the following steps:

[0067] 201. Obtain each regional node sample corresponding to the regional power distribution network, wherein the each regional node sample comprises voltage and power factor corresponding to each regional node;

[0068] It should be noted that the content shown in step 201 is similar to the content of step 101, and to avoid repetition, the details are not described here, and the content of the foregoing step 101 can be referred to. Figure 1 The content of step 101 is similar, to avoid repetition, the details are not described here, and the content of the foregoing step 101 can be referred to.

[0069] 202. Input the voltage and power factor corresponding to each regional node sample into the Gaussian mixture distribution function to obtain the first distribution probability corresponding to each regional node sample;

[0070] It should be noted that in this embodiment, the voltage and power factor corresponding to each regional node sample are input into the Gaussian mixture distribution function to obtain the first distribution probability corresponding to each regional node sample, and the first distribution probability is used to update the iterative Gaussian mixture distribution function.

[0071] For example, taking the voltage and power factor data of each regional node as two clustering factors, the Gaussian mixture model clustering method is used, and the number of clusters is first set, and the Gaussian mixture probability density is constructed. The input clustering data is a set of two-dimensional data composed of node voltage and power factor, the number of clusters is set to n, and the Gaussian mixture distribution function can be referred to as the following expression:

[0072]

[0073] Wherein, α i is the probability that the regional node sample belongs to the i-th cluster, μ i , σ i are the Gaussian distribution mean and Gaussian distribution standard deviation corresponding to the i-th cluster, and n is the number of clusters.

[0074] Further, step 202 can be represented as:

[0075]

[0076] Wherein, p(y j =i|x j ) represents the probability that the j-th sample data x j belongs to the i-th distribution, y j =i represents the i-th distribution, α i is the probability that the regional node sample belongs to the i-th cluster, μ i , σ i are the Gaussian distribution mean and Gaussian distribution standard deviation of the i-th cluster, and αk μ represents the probability that a node sample in the region belongs to the k-th cluster. k ,σ k are the mean and standard deviation of the Gaussian distribution of the k-th cluster, respectively, and n is the number of clusters.

[0077] Furthermore, the two-dimensional data x of the j-th representative region node sample, composed of power factor and voltage, is obtained through the above equation. j The probability of belonging to the i-th distribution can be calculated. By iterating through all the input regional node sample data and each Gaussian distribution, the probability of the two-dimensional data of the representative regional node sample composed of the power factor and voltage of each node belonging to each Gaussian distribution can be obtained.

[0078] 203. Update the Gaussian distribution parameters using the samples of each region node and the first distribution probability to obtain the updated Gaussian mixture distribution function. Then, return to the step of inputting the voltage and power factor corresponding to each region node sample into the Gaussian mixture distribution function to obtain the first distribution probability corresponding to each region node sample. Continue this process until the update iteration of the Gaussian mixture distribution function reaches convergence accuracy to obtain the target distribution probability corresponding to the region node sample.

[0079] It should be noted that in this embodiment, the Gaussian distribution parameters need to be updated using the first distribution probability to iteratively update the Gaussian mixture distribution function, ensuring that the Gaussian mixture distribution function meets the required convergence accuracy, thereby obtaining a more accurate distribution probability. Therefore, each time the first distribution probability is obtained, the Gaussian distribution parameters need to be recalculated using the first distribution probability and the samples of each region node to update the Gaussian mixture distribution function, until the Gaussian mixture distribution function reaches the convergence accuracy. The distribution probability that has reached the convergence accuracy is taken as the target distribution probability corresponding to the region node sample. For example, based on the new distribution of the updated Gaussian mixture distribution function, step 202 is repeated to update the Gaussian distribution parameters using the calculated distribution probability. This iterative update continues until the model reaches the convergence accuracy, at which point step 202 is no longer repeated. At this point, the final parameters of each Gaussian distribution and the final probability, i.e., the target distribution probability, of the two-dimensional data composed of the power factor and voltage of each node belonging to each Gaussian distribution are obtained. The Gaussian distribution parameters include the Gaussian distribution mean and the Gaussian distribution standard deviation.

[0080] In one feasible implementation, the Gaussian distribution parameters include the Gaussian distribution mean and the Gaussian distribution standard deviation. Then, updating the Gaussian distribution parameters using the samples from each region node and the first distribution probability can include: updating the Gaussian distribution mean using the samples from each region node and the first distribution probability; and updating the Gaussian distribution standard deviation based on the Gaussian distribution mean, the samples from each region node, and the first distribution probability, thereby updating the Gaussian distribution parameters. Specifically, the Gaussian distribution parameters can be updated according to the following formula:

[0081]

[0082]

[0083] wherein, p ji is the probability that the data j of the jth regional node sample conforms to the distribution i, m is the sample quantity, μ i ,σ i are the Gaussian distribution mean and Gaussian distribution standard deviation of the ith cluster respectively, and x j is the jth regional node sample.

[0084] 204. Clustering the regional nodes based on the target distribution probability and a preset interval threshold, to determine the target regional category cluster corresponding to each regional node;

[0085] It should be noted that the content shown in step 204 is similar to the content of step 103 shown in Figure 1 , to avoid repetition, the specific content can be referred to the content of the foregoing step 103.

[0086] In a feasible implementation manner, step 204 can include:

[0087] According to the formula:

[0088] max(p ji ), i∈{1,...,n}

[0089] The jth regional node sample x j conforms to the maximum value of the distribution probability in each distribution i, so as to determine the target regional category cluster a corresponding to the jth regional node sample x j , and the regional node j corresponding to the jth regional node sample x j is divided into the target regional category cluster a, and the target regional category cluster a is the cluster corresponding to the maximum value of the distribution probability. Each regional node sample is traversed, and each regional node is divided into the corresponding target regional category cluster to complete clustering. That is, the target distribution probability of each regional node sample is finally obtained, and then the maximum value is taken to divide each regional node into the cluster corresponding to the maximum value to complete clustering. Please refer to Figure 3 , Figure 3 is a clustering result schematic diagram of the target regional category cluster corresponding to a regional node in the embodiment of the application, Figure 3The clustering results of the node voltage and power factor of the node area distribution network shown represent that the node voltage and power factor of the first end of the substation can be clustered into two clusters, the first cluster (cluster 1) presents the characteristics that the node voltage in the cluster is close to qualified and the power factor is low, and the second cluster (cluster 2) presents the characteristics that the node voltage in the cluster is low and the power factor is low.

[0090] 205. Determine the target control strategy of the area distribution network according to the electrical parameter characteristics corresponding to each of the target area category clusters.

[0091] It should be noted that the content shown in step 205 is similar to the content of step 104. Figure 1 The content of step 104 is not repeated here, and the specific content can be referred to the aforementioned content of step 104.

[0092] In a feasible implementation manner, step 205 can include the following steps A1-A5:

[0093] A1. If the electrical parameter characteristics corresponding to the target area category cluster are that the voltage characteristics and the power factor characteristics of the area nodes in the cluster are qualified, the target control strategy of the area distribution network is not to take action;

[0094] A2. If the electrical parameter characteristics corresponding to the target area category cluster are that the voltage characteristics of the area nodes in the cluster are qualified and the power factor characteristics are low, the target control strategy of the area distribution network is to take the operation of adding capacitors;

[0095] A3. If the electrical parameter characteristics corresponding to the target area category cluster are that the voltage characteristics of the area nodes in the cluster are low and the power factor characteristics are qualified, the target control strategy of the area distribution network is to take the operation of reducing the gear of the transformer to increase the voltage;

[0096] A4. If the electrical parameter characteristics corresponding to the target area category cluster are that the voltage characteristics of the area nodes in the cluster are high and the power factor characteristics are qualified, the target control strategy of the area distribution network is to take the operation of increasing the gear of the transformer to reduce the voltage;

[0097] A5. If the electrical parameter characteristics corresponding to the target area category cluster are that the voltage characteristics of the area nodes in the cluster are low and the power factor characteristics are low, the target control strategy of the area distribution network is to take the operation of adding capacitors and adjusting the gear of the transformer to reduce the voltage.

[0098] For example, referring to Figure 3At this time, the node voltage power factor of the regional power distribution network can be clustered into two clusters, for the first type, the node voltage in the cluster is close to the qualified characteristics in the voltage aspect, and the power factor is low in the power factor aspect, so the capacitor operation can be performed, for the second type, the node voltage in the cluster is low in the voltage aspect, and the power factor is low in the power factor aspect, so the step-down voltage boosting operation of adjusting the transformer gear can be performed. The embodiment is aimed at the 11-node regional power distribution network, the clustering of the node voltage and the power factor of the 11-node regional power distribution network is displayed, the clusters obtained by clustering, the node voltage and the power factor in the cluster are different from the node voltage and the power factor in another cluster, and the clustering of the VQC regulation of the regional power distribution network has good effect, and the generalized VQC regulation can be further performed according to the characteristics of the clusters in the voltage and the power factor.

[0099] The present application provides a kind of reactive voltage control method of regional power distribution network, which comprises: obtaining each regional node sample corresponding to regional power distribution network, each regional node sample includes the voltage and power factor corresponding to each regional node;The voltage and power factor corresponding to each regional node sample are input into Gaussian mixture distribution function, to obtain the first distribution probability corresponding to each regional node sample;Each regional node sample and the first distribution probability are used to update Gaussian distribution parameter, to obtain the updated Gaussian mixture distribution function, return to execute the step of inputting the voltage and power factor corresponding to each regional node sample into Gaussian mixture distribution function, to obtain the first distribution probability corresponding to each regional node sample, until the updating iteration of Gaussian mixture distribution function reaches convergence precision, to obtain the target distribution probability corresponding to regional node sample;Based on target distribution probability and preset interval threshold, each regional node is clustered, to determine the target regional category cluster corresponding to each regional node;According to the electrical parameter characteristics corresponding to each target regional category cluster, determine the target regulation strategy of regional power distribution network.Gaussian mixture distribution function has good effect for the clustering of VQC regulation of regional power distribution network, and the regional VQC regulation can be performed according to the characteristics of the category cluster obtained by clustering in each electrical parameter characteristics, and targeted target regulation strategy can be used.

[0100] Please refer to Figure 4 , Figure 4 The structure block diagram of a reactive voltage control device of regional power distribution network in the embodiment of the present application is shown as Figure 4 The device comprises:

[0101] Sample acquisition module 401: for obtaining each regional node sample corresponding to the regional power distribution network, each regional node sample includes the voltage and power factor corresponding to each regional node;

[0102] Probability determination module 402: used to input the voltage and power factor corresponding to each regional node sample into a Gaussian mixture distribution function to determine the target distribution probability corresponding to the regional node sample;

[0103] Category clustering module 403: used to cluster each of the region nodes based on the target distribution probability and a preset interval threshold, and determine the target region category cluster corresponding to each of the region nodes;

[0104] Strategy generation module 404: used to determine the target control strategy of the regional power distribution network based on the electrical parameter characteristics corresponding to each target region category cluster.

[0105] This invention provides a reactive power and voltage control device for a regional distribution network. The device includes: a sample acquisition module for acquiring samples of each regional node in the regional distribution network, each sample including its voltage and power factor; a probability determination module for inputting the voltage and power factor of each regional node sample into a Gaussian mixture distribution function to determine the target distribution probability of the regional node sample; a clustering module for clustering each regional node based on the target distribution probability and a preset interval threshold to determine the target regional cluster; and a strategy generation module for determining the target control strategy for the regional distribution network based on the electrical parameter characteristics of each target regional cluster. Using a Gaussian mixture distribution function for clustering in regional distribution network VQC control has good results, and regional VQC control can be performed based on the characteristics of the clustered clusters in various electrical parameters, allowing for targeted target control strategies.

[0106] Figure 5 An internal structural diagram of a computer device in one embodiment is shown. This computer device can specifically be a terminal or a server. Figure 5 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and may also store a computer program, which, when executed by the processor, causes the processor to perform the aforementioned methods. The internal memory may also store a computer program, which, when executed by the processor, causes the processor to perform the aforementioned methods. Those skilled in the art will understand that… Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0107] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform actions such as... Figure 1 or Figure 2 The steps of the method shown.

[0108] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, causes the processor to perform the following actions: Figure 1 or Figure 2 The steps of the method shown.

[0109] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0110] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0111] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method of reactive voltage control for a regional electric power distribution network, characterized by, The method comprises: obtaining each regional node sample corresponding to the regional power distribution network, wherein the each regional node sample comprises voltage and power factor corresponding to each regional node; inputting the voltage and power factor corresponding to each regional node sample into a Gaussian mixture distribution function to determine a target distribution probability corresponding to the regional node sample; based on the target distribution probability and a preset interval threshold, clustering the each regional node to determine a target regional category cluster corresponding to the each regional node; determining a target control strategy of the regional power distribution network according to electrical parameter characteristics corresponding to each target regional category cluster.

2. The method of claim 1, wherein, If the electrical parameter characteristics corresponding to the target regional category cluster are that the voltage characteristics and the power factor characteristics of the regional nodes in the cluster are both qualified, the target control strategy of the regional power distribution network is not to act. If the electrical parameter characteristics corresponding to the target regional category cluster are that the voltage characteristics of the regional nodes in the cluster are qualified and the power factor characteristics are low, the target control strategy of the regional power distribution network is to perform a capacitor operation. If the electrical parameter characteristics corresponding to the target regional category cluster are that the voltage characteristics of the regional nodes in the cluster are low and the power factor characteristics are qualified, the target control strategy of the regional power distribution network is to adjust the transformer gear to perform a step-down voltage boosting operation. If the electrical parameter characteristics corresponding to the target regional category cluster are that the voltage characteristics of the regional nodes in the cluster are high and the power factor characteristics are qualified, the target control strategy of the regional power distribution network is to adjust the transformer gear to perform a step-up voltage lowering operation. If the electrical parameter characteristics corresponding to the target regional category cluster are that the voltage characteristics of the regional nodes in the cluster are low and the power factor characteristics are low, the target control strategy of the regional power distribution network is to perform a capacitor operation and adjust the transformer gear to perform a step-down voltage boosting operation. The method comprises:

3. The method of claim 1, wherein, inputting the voltage and power factor corresponding to each regional node sample into a Gaussian mixture distribution function to obtain a first distribution probability corresponding to each regional node sample; updating the Gaussian distribution parameters by using the each regional node sample and the first distribution probability to obtain an updated Gaussian mixture distribution function, returning to execute the step of inputting the voltage and power factor corresponding to each regional node sample into the Gaussian mixture distribution function to obtain a first distribution probability corresponding to each regional node sample until the updating iteration of the Gaussian mixture distribution function reaches a convergence accuracy to obtain a target distribution probability corresponding to the regional node sample. The Gaussian mixture distribution function comprises:

4. The method of claim 3, wherein, ​ wherein α i is the probability that the zone node sample belongs to the i-th cluster, μ i and σ i are the mean and the standard deviation of the Gaussian distribution corresponding to the i-th cluster, respectively.

5. The method of claim 3, wherein, The voltage and power factor corresponding to each regional node sample are input into a Gaussian mixture distribution function to obtain a first distribution probability corresponding to each regional node sample, including: where y j = i represents the i-th distribution, a i is the probability that the regional node sample belongs to the i-th cluster, μ i , σ i are the Gaussian distribution mean and Gaussian distribution standard deviation of the i-th cluster, respectively, a k is the probability that the regional node sample belongs to the k-th cluster, μ k , σ k are the Gaussian distribution mean and Gaussian distribution standard deviation of the k-th cluster, respectively.

6. The method of claim 3, wherein, The Gaussian distribution parameters include a Gaussian distribution mean and a Gaussian distribution standard deviation, and the Gaussian distribution parameters are updated using the regional node samples and the first distribution probability, including: The Gaussian distribution mean is updated using the regional node samples and the first distribution probability. The Gaussian distribution standard deviation is updated according to the Gaussian distribution mean, the regional node samples, and the first distribution probability.

7. The method of claim 6, wherein, The Gaussian distribution mean is updated using the regional node samples and the first distribution probability, including: where p ji is the probability that the data j corresponding to the jth regional node sample conforms to the distribution i, m is the number of samples, μ i is the Gaussian distribution mean of the ith cluster, x j is the jth regional node sample.

8. The method of claim 7, wherein, The Gaussian distribution standard deviation is updated according to the Gaussian distribution mean, the regional node samples, and the first distribution probability, including: where p ji is the probability that the data j corresponding to the jth regional node sample conforms to the distribution i, m is the number of samples, μ i ,σ i are the Gaussian distribution mean and Gaussian distribution standard deviation of the ith cluster, respectively, and x j is the jth regional node sample.

9. The method of claim 1, wherein, The regional nodes are clustered based on the target distribution probability and a preset interval threshold to determine a target regional category cluster corresponding to each regional node, including: According to the formula: max(p ji ),i∈{1,...,n} get the jth regional node sample x j the maximum value of the distribution probability in each distribution i, thereby determining the jth regional node sample x j the corresponding target regional category cluster a, and put the jth regional node sample x j the corresponding regional node j is divided into the corresponding target regional category cluster a, which is the cluster corresponding to the maximum value of the distribution probability. Each regional node sample is traversed, and each regional node is divided into a corresponding target regional category cluster to complete clustering.

10. A reactive voltage control device for a regional electric power distribution network, characterized by The device includes: A sample acquisition module is configured to acquire each regional node sample corresponding to the regional power distribution network, and each regional node sample includes a voltage and a power factor corresponding to each regional node. A probability determination module is configured to input the voltage and power factor corresponding to each regional node sample into a Gaussian mixture distribution function to determine a target distribution probability corresponding to the regional node sample. A category clustering module is configured to cluster each regional node based on the target distribution probability and a preset interval threshold to determine a target regional category cluster corresponding to each regional node. A strategy generation module is configured to determine a target regulation strategy of the regional power distribution network according to an electrical parameter characteristic corresponding to each target regional category cluster.

Images