Power distribution network partitioning method and system for distributed voltage regulation and control

Abstract

The invention relates to a power distribution network partitioning method and system for distributed voltage regulation and control. The method comprises the following steps: acquiring power and voltage data of a target power distribution network; based on the power and voltage data of the target power distribution network, constructing a power distribution network power flow fitting model based on data driving; calculating voltage sensitivity among nodes in the target power distribution network based on a power distribution network flow fitting model; calculating an electrical distance between nodes in the target power distribution network through the voltage sensitivity; and constructing a partition performance index based on the electrical distance, iteratively performing a partition configuration scheme of each node in the target power distribution network according to a preset partition number until an optimal partition performance index is obtained, and outputting a corresponding partition configuration scheme.

Description

Technical Field

[0001] The invention relates to a distribution network zoning method and system for decentralized voltage regulation, belonging to the technical field of distribution network control. Background Art

[0002] With the continuous popularization and access of distributed renewable energy, the stable operation of the distribution network faces many challenges, the most serious of which is the voltage over-limit problem caused by reverse current. Overvoltage not only threatens the safe operation of distributed renewable energy generators and causes damage to electrical equipment, but also limits the access scale of distributed renewable energy in the distribution network. In order to reduce the overvoltage risk that may be caused by the access of distributed renewable energy, many scholars have proposed methods for regulating the voltage of the distribution network, which can be mainly divided into four categories, namely centralized control, local control, distributed control and decentralized control. Among them, decentralized control combines the characteristics of centralized control and distributed control to control the voltage of the distribution network through partition control and inter-cluster coordination based on network partitions, which has great potential.

[0003] Most of the current research on voltage control in distribution networks based on distributed control requires analysis and calculation based on power flow, which means that such methods are mainly suitable for ideal scenarios where the distribution network line parameters are accurate and the topology is clear. However, the actual distribution network has the characteristics of incomplete ledger information, unclear topology, and inaccurate line parameters. As a result, many current voltage control research schemes are difficult to apply to actual distribution network scenarios and lack engineering application value.

[0004] Decentralized voltage regulation with great potential requires zoning of the distribution network, but existing zoning methods often ignore the impact of active power injection on the voltage amplitude of each node in the distribution network, and rarely consider the voltage regulation capability of distributed renewable energy generators in the cluster. Summary of the invention

[0005] In order to solve the above problems existing in the prior art, the present invention proposes a distribution network partitioning method and system for decentralized voltage regulation.

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

[0007] On the one hand, the present invention provides a distribution network partitioning method for decentralized voltage regulation, comprising the following steps:

[0008] Obtain power and voltage data of the target distribution network;

[0009] Based on the power and voltage data of the target distribution network, a data-driven distribution network power flow fitting model is constructed;

[0010] Based on the distribution network power flow fitting model, the voltage sensitivity between nodes in the target distribution network is calculated;

[0011] Calculate the electrical distance between nodes in the target distribution network through voltage sensitivity;

[0012] Construct a partition performance index based on electrical distance, iterate the partition configuration plan of each node in the target distribution network according to the preset number of partitions, until the optimal partition performance index is obtained, and output the corresponding partition configuration plan.

[0013] As a preferred implementation, in the step of constructing a data-driven distribution network power flow fitting model, a RBF neural network model is specifically used to construct a distribution network power flow fitting model, wherein:

[0014] The input layer of the RBF neural network model is set to input the active and reactive power data of each node in the distribution network, the activation function of the hidden layer adopts the radial basis function, and the output layer is set to output the voltage data of each node;

[0015] The RBF neural network model is trained through the power and voltage data of the target distribution network in the historical period to obtain the distribution network power flow fitting model;

[0016] Obtain the explicit expression of the relationship between node voltage and input variables of the trained distribution network power flow fitting model.

[0017] As a preferred implementation, the step of calculating the voltage sensitivity between nodes in the target distribution network based on the distribution network power flow fitting model is specifically as follows:

[0018] Based on the explicit expression of the distribution network power flow fitting model, the voltage of the corresponding node is partial derivatived with respect to each input variable to obtain the voltage active power sensitivity and voltage reactive power sensitivity between the corresponding nodes.

[0019] The step of calculating the electrical distance between nodes in the target distribution network by voltage sensitivity is specifically to calculate the electrical distance between nodes by voltage active power sensitivity and voltage reactive power sensitivity between corresponding nodes.

[0020] As a preferred implementation, the construction of the partition performance index based on electrical distance is specifically as follows:

[0021]

[0022] Among them, Q is the partition performance index, N is the number of nodes, W is the weight matrix of all nodes, A is the sum of all elements in the weight matrix W, and W i is the sum of the elements in the i-th row of the weight matrix W. δ(i,j) is 1, indicating that nodes i and j are in the same partition k. δ(i,j) is 0, indicating that they are not in the same partition k. ij represents the electrical distance between node i and node j;

[0023] The larger the value of the partition performance index Q is, the closer the nodes in the same partition are.

[0024] On the other hand, the present invention also proposes a distribution network partitioning system for decentralized voltage regulation, comprising:

[0025] A data acquisition module, used to acquire power and voltage data of the target distribution network;

[0026] The distribution network power flow fitting model construction module builds a data-driven distribution network power flow fitting model based on the power and voltage data of the target distribution network;

[0027] The node relationship calculation module is used to calculate the voltage sensitivity between nodes in the target distribution network based on the distribution network power flow fitting model;

[0028] An electrical distance calculation module, used to calculate the electrical distance between nodes in the target distribution network through voltage sensitivity;

[0029] The partitioning module is used to construct a partitioning performance index based on electrical distance, iterate the partitioning configuration plan of each node in the target distribution network according to the preset number of partitions, until the optimal partitioning performance index is obtained, and output the corresponding partitioning configuration plan.

[0030] As a preferred implementation, in the step of constructing a data-driven distribution network power flow fitting model, a RBF neural network model is specifically used to construct a distribution network power flow fitting model, wherein:

[0031] The input layer of the RBF neural network model is set to input the active and reactive power data of each node in the distribution network, the activation function of the hidden layer adopts the radial basis function, and the output layer is set to output the voltage data of each node;

[0032] The RBF neural network model is trained through the power and voltage data of the target distribution network in the historical period to obtain the distribution network power flow fitting model;

[0033] Obtain the explicit expression of the relationship between node voltage and input variables of the trained distribution network power flow fitting model.

[0034] As a preferred implementation, the step of calculating the voltage sensitivity between nodes in the target distribution network based on the distribution network power flow fitting model is specifically as follows:

[0035] Based on the explicit expression of the distribution network power flow fitting model, the voltage of the corresponding node is partial derivatived with respect to each input variable to obtain the voltage active power sensitivity and voltage reactive power sensitivity between the corresponding nodes.

[0036] The step of calculating the electrical distance between nodes in the target distribution network by voltage sensitivity is specifically to calculate the electrical distance between nodes by voltage active power sensitivity and voltage reactive power sensitivity between corresponding nodes.

[0037] As a preferred implementation, the construction of the partition performance index based on electrical distance is specifically as follows:

[0038]

[0039] Among them, Q is the partition performance index, N is the number of nodes, W is the weight matrix of all nodes, A is the sum of all elements in the weight matrix W, and W i is the sum of the elements in the i-th row of the weight matrix W. δ(i,j) is 1, indicating that nodes i and j are in the same partition k. δ(i,j) is 0, indicating that they are not in the same partition k. ij represents the electrical distance between node i and node j;

[0040] The larger the value of the partition performance index Q is, the closer the nodes in the same partition are.

[0041] On the other hand, the present invention further proposes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the distribution network partitioning method for decentralized voltage control as described in any embodiment of the present invention is implemented.

[0042] On the other hand, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the distribution network partitioning method for decentralized voltage regulation as described in any embodiment of the present invention.

[0043] Additional aspects and advantages of the present invention will be set forth in the following description, and some of them will be apparent from the description, or may be understood by practicing the present invention. In addition, the various aspects and advantages of the present invention may be realized and obtained by the method steps and combinations particularly pointed out in the appended claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flow chart of a method according to Embodiment 1 of the present invention;

[0045] Figure 2 Schematic diagram of the structure of the RBF neural network in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0048] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0049] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0050] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0051] Embodiment 1:

[0052] See also Figure 1 This embodiment provides a distribution network partitioning method for decentralized voltage control, comprising the following steps:

[0053] S100, obtaining power and voltage data of a target distribution network;

[0054] S200, based on the power and voltage data of the target distribution network, construct a data-driven distribution network power flow fitting model;

[0055] S300, calculating voltage sensitivity between nodes in the target distribution network based on a distribution network power flow fitting model;

[0056] S400, calculating the electrical distance between nodes in the target distribution network by voltage sensitivity;

[0057] S500, constructing a partition performance index based on electrical distance, iterating the partition configuration scheme of each node in the target distribution network according to a preset number of partitions, until the optimal partition performance index is obtained, and outputting the corresponding partition configuration scheme.

[0058] As a preferred implementation of this embodiment, in step S200, since the actual distribution network has the characteristics of unclear topology and unclear line parameters, and the existing decentralized voltage control method needs to consider the traditional power flow constraints, it cannot adapt to the actual scenario of the power grid. Therefore, this embodiment first constructs a distribution network power flow fitting model based on data-driven to provide a power flow basis for subsequent voltage control. This embodiment specifically uses the RBF neural network model to construct the distribution network power flow fitting model, where:

[0059] The RBF neural network model is a neural network structure that covers the input layer, the middle layer, and the output layer. The radial basis function is used as the activation function. The input signal is transmitted from the input layer node to the hidden layer with a nonlinear basis function, which will produce a localized response to the input signal. Each hidden node in the hidden layer has a parameter vector, which will produce a radially symmetric response when compared with the input vector of the neural network. The hidden node will only make a meaningful non-zero response with a response value between 0 and 1 when the input falls in a very small specified area. The hidden node response increases as the distance between the input and the center of the basis function becomes closer. Each node in the output layer is linear, which is a linearly weighted combination of the output of the hidden layer nodes. It is widely used in research on function approximation, intelligent optimization, etc. Because the model has the characteristics of strong ability to approximate complex nonlinear functions and high fault tolerance, it is suitable for establishing a power flow fitting model for distribution networks.

[0060] The radial basis function is shown below.

[0061]

[0062] Where: x is the input vector, c i is the center point of the i-th hidden layer neuron, σ i is the center point width of the i-th hidden layer neuron.

[0063] In this embodiment, the RBF neural network is trained to fit the distribution network flow through the power and voltage data of the target distribution network at 96 collection points in a day. The required historical data period is 7 days. The radial basis function is used as the activation function. The input layer is the active and reactive power data s of each user node under the distribution network. i =[p i ,q i ], and the output layer is the voltage data u of each node. i The ratio of the test set to the validation set is 6:1, that is, the historical data of the first 6 days is used as the test set, and the historical data of the last day is used as the validation set. The internal structure of the network is shown in the figure below: Figure 2 shown.

[0064] The RBF neural network model is an explicit neural network model, so its explicit expression can be constructed as follows.

[0065]

[0066] Where: M is the number of model input variables, the input variables are the active and reactive power data of each node in the distribution network; N is the number of training samples, s m is the mth power data, u i is the voltage value of the i-th node, w1 and b1 are the weight and bias parameter matrices of the input layer neurons, with dimensions of N×M and N×1 respectively, w 1,nm Corresponding to the element in the nth row and mth column of the w1 weight parameter matrix, b 1,i Corresponding to the i-th element in the b1 bias parameter matrix; w2 and b2 are the weight and bias parameter matrices of the hidden layer neurons, with dimensions of K×N and K×1 respectively, w 2,in Corresponding to the element in row i and column n of the weight parameter matrix w2, b 2,i Corresponding to the i-th element of the b2 bias parameter matrix, K is the total number of output node voltages.

[0067] As a preferred implementation of this embodiment, in step S300, the step of calculating the voltage sensitivity between nodes in the target distribution network based on the distribution network power flow fitting model is specifically as follows:

[0068] Based on the explicit expression of the distribution network power flow fitting model, the voltage of the corresponding node is partial derivatived with respect to each input variable to obtain the voltage active power sensitivity and voltage reactive power sensitivity between the corresponding nodes, as follows:

[0069]

[0070] Among them, s j,p is the active power of the jth node, s j,q is the reactive power of the jth node, and are the sensitivity of node i voltage to active power and reactive power injected into node j respectively; w 1,nm Corresponding to the element in the nth row and mth column of the w1 weight parameter matrix, w 1,ni Corresponding to the element in the nth row and ith column of the w1 weight parameter matrix, w 2,in Corresponding to the element in the i-th row and n-th column of the w2 weight parameter matrix.

[0071] The purpose of partitioning nodes based on their electrical characteristics is to reasonably divide the distribution network into several sub-areas, so as to regulate the voltage of the distribution network in a decentralized manner. This embodiment uses the electrical distance based on voltage sensitivity to divide the distribution network nodes with similar electrical characteristics. Define the electrical distance d between node i and node j as ij as follows:

[0072]

[0073] in, and They represent the electrical distance defined according to the voltage active power sensitivity and the voltage reactive power sensitivity respectively;

[0074]

[0075] As a preferred implementation of this embodiment, the construction of the partition performance index based on electrical distance is specifically as follows:

[0076] Electrical distance d ij The smaller it is, the closer the electrical connection between node i and node j is. Therefore, the distribution network can be partitioned by electrical distance. The partition performance index Q considering electrical distance is as follows:

[0077]

[0078] Among them, Q is the partition performance index, N is the number of nodes, W is the weight matrix of all nodes, A is the sum of all elements in the weight matrix W, and W i is the sum of the elements in the i-th row of the weight matrix W. δ(i,j) is 1, indicating that nodes i and j are in the same partition k. δ(i,j) is 0, indicating that they are not in the same partition k. ij represents the electrical distance between node i and node j; Indicates the maximum electrical distance between nodes.

[0079] The larger the value of the partition performance index Q is, the closer the nodes in the same partition are.

[0080] Therefore, in this embodiment, the required number of partitions k and the maximum number of iterations iter allowed for finding the optimal Q value are first set, and then the nodes of the distribution network are partitioned and numbered by traversal, and then the Q value is calculated, and finally the optimal Q value is extracted to obtain the optimal distribution network partitioning scheme.

[0081] Embodiment 2:

[0082] This embodiment provides a distribution network partition system for decentralized voltage control, including:

[0083] A data acquisition module, used to acquire power and voltage data of the target distribution network; this module is used to implement the function of step S100 in the first embodiment, and will not be described in detail here;

[0084] A distribution network power flow fitting model construction module is used to construct a data-driven distribution network power flow fitting model based on the power and voltage data of the target distribution network; this module is used to implement the function of step S200 in the first embodiment, and will not be described in detail here;

[0085] A node relationship calculation module is used to calculate the voltage sensitivity between nodes in the target distribution network based on the distribution network power flow fitting model; this module is used to implement the function of step S300 in the first embodiment, and will not be repeated here;

[0086] An electrical distance calculation module, used to calculate the electrical distance between nodes in the target distribution network by voltage sensitivity; this module is used to implement the function of step S400 in the first embodiment, which will not be described in detail here;

[0087] A partitioning module is used to construct a partitioning performance index based on electrical distance, iterate the partitioning configuration plan of each node in the target distribution network according to a preset number of partitions, until the optimal partitioning performance index is obtained, and output the corresponding partitioning configuration plan; this module is used to implement the function of step S500 in Example 1, which will not be repeated here.

[0088] As a preferred implementation of this embodiment, in the step of constructing a data-driven distribution network power flow fitting model, a RBF neural network model is specifically used to construct a distribution network power flow fitting model, wherein:

[0089] The input layer of the RBF neural network model is set to input the active and reactive power data of each node in the distribution network, the activation function of the hidden layer adopts the radial basis function, and the output layer is set to output the voltage data of each node;

[0090] The RBF neural network model is trained through the power and voltage data of the target distribution network in the historical period to obtain the distribution network power flow fitting model;

[0091] Obtain the explicit expression of the relationship between node voltage and input variables of the trained distribution network power flow fitting model.

[0092] As a preferred implementation of this embodiment, the step of calculating the voltage sensitivity between nodes in the target distribution network based on the distribution network power flow fitting model is specifically as follows:

[0093] Based on the explicit expression of the distribution network power flow fitting model, the voltage of the corresponding node is partial derivatived with respect to each input variable to obtain the voltage active power sensitivity and voltage reactive power sensitivity between the corresponding nodes.

[0094] The step of calculating the electrical distance between nodes in the target distribution network by voltage sensitivity is specifically to calculate the electrical distance between nodes by voltage active power sensitivity and voltage reactive power sensitivity between corresponding nodes.

[0095] As a preferred implementation of this embodiment, the construction of the partition performance index based on electrical distance is specifically as follows:

[0096]

[0097]

[0098] Among them, Q is the partition performance index, N is the number of nodes, W is the weight matrix of all nodes, A is the sum of all elements in the weight matrix W, and W i is the sum of the elements in the i-th row of the weight matrix W. δ(i,j) is 1, indicating that nodes i and j are in the same partition k. δ(i,j) is 0, indicating that they are not in the same partition k. ij represents the electrical distance between node i and node j;

[0099] The larger the value of the partition performance index Q is, the closer the nodes in the same partition are.

[0100] Embodiment three:

[0101] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present invention when executing the program.

[0102] Embodiment 4:

[0103] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in any embodiment of the present invention is implemented.

[0104] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0105] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0106] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0107] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0108] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A distribution network partitioning method for decentralized voltage regulation, characterized in that: The following steps are involved: Obtain power and voltage data of the target distribution network; Based on the power and voltage data of the target distribution network, a data-driven distribution network power flow fitting model is constructed; Based on the distribution network power flow fitting model, the voltage sensitivity between nodes in the target distribution network is calculated; Calculate the electrical distance between nodes in the target distribution network through voltage sensitivity; Construct a partition performance index based on electrical distance, iterate the partition configuration plan of each node in the target distribution network according to the preset number of partitions, until the optimal partition performance index is obtained, and output the corresponding partition configuration plan.

2. A distribution network partitioning method for decentralized voltage control according to claim 1, characterized in that: In the step of constructing a data-driven distribution network power flow fitting model, a RBF neural network model is specifically used to construct a distribution network power flow fitting model, wherein: The input layer of the RBF neural network model is set to input the active and reactive power data of each node in the distribution network, the activation function of the hidden layer adopts the radial basis function, and the output layer is set to output the voltage data of each node; The RBF neural network model is trained through the power and voltage data of the target distribution network in the historical period to obtain the distribution network power flow fitting model; Obtain the explicit expression of the relationship between node voltage and input variables of the trained distribution network power flow fitting model.

3. A distribution network partitioning method for decentralized voltage control according to claim 2, characterized in that: The step of calculating the voltage sensitivity between nodes in the target distribution network based on the distribution network power flow fitting model is specifically as follows: Based on the explicit expression of the distribution network power flow fitting model, the voltage of the corresponding node is partial derivatived with respect to each input variable to obtain the voltage active power sensitivity and voltage reactive power sensitivity between the corresponding nodes. The step of calculating the electrical distance between nodes in the target distribution network by voltage sensitivity is specifically to calculate the electrical distance between nodes by voltage active power sensitivity and voltage reactive power sensitivity between corresponding nodes.

4. A distribution network partitioning method for decentralized voltage control according to claim 1, characterized in that: The performance index of the partition based on electrical distance is as follows: Among them, Q is the partition performance index, N is the number of nodes, W is the weight matrix of all nodes, A is the sum of all elements in the weight matrix W, and W i is the sum of the elements in the i-th row of the weight matrix W. δ(i,j) is 1, indicating that nodes i and j are in the same partition k. δ(i,j) is 0, indicating that they are not in the same partition k. ij represents the electrical distance between node i and node j; The larger the value of the partition performance index Q is, the closer the nodes in the same partition are.

5. A distribution network partitioning system for decentralized voltage regulation, characterized in that: include: A data acquisition module, used to acquire power and voltage data of the target distribution network; The distribution network power flow fitting model construction module builds a data-driven distribution network power flow fitting model based on the power and voltage data of the target distribution network; The node relationship calculation module is used to calculate the voltage sensitivity between nodes in the target distribution network based on the distribution network power flow fitting model; An electrical distance calculation module, used to calculate the electrical distance between nodes in the target distribution network through voltage sensitivity; The partitioning module is used to construct a partitioning performance index based on electrical distance, iterate the partitioning configuration plan of each node in the target distribution network according to the preset number of partitions, until the optimal partitioning performance index is obtained, and output the corresponding partitioning configuration plan.

6. A distribution network partition system for decentralized voltage control according to claim 5, characterized in that: In the step of constructing a data-driven distribution network power flow fitting model, a RBF neural network model is specifically used to construct a distribution network power flow fitting model, wherein: The input layer of the RBF neural network model is set to input the active and reactive power data of each node in the distribution network, the activation function of the hidden layer adopts the radial basis function, and the output layer is set to output the voltage data of each node; The RBF neural network model is trained through the power and voltage data of the target distribution network in the historical period to obtain the distribution network power flow fitting model; Obtain the explicit expression of the relationship between node voltage and input variables of the trained distribution network power flow fitting model.

7. A distribution network partitioning system for decentralized voltage control according to claim 6, characterized in that: The step of calculating the voltage sensitivity between nodes in the target distribution network based on the distribution network power flow fitting model is specifically as follows: Based on the explicit expression of the distribution network power flow fitting model, the voltage of the corresponding node is partial derivatived with respect to each input variable to obtain the voltage active power sensitivity and voltage reactive power sensitivity between the corresponding nodes. The step of calculating the electrical distance between nodes in the target distribution network by voltage sensitivity is specifically to calculate the electrical distance between nodes by voltage active power sensitivity and voltage reactive power sensitivity between corresponding nodes.

8. A distribution network partition system for decentralized voltage control according to claim 5, characterized in that: The performance index of the partition based on electrical distance is as follows: Among them, Q is the partition performance index, N is the number of nodes, W is the weight matrix of all nodes, A is the sum of all elements in the weight matrix W, and W i is the sum of the elements in the i-th row of the weight matrix W. δ(i,j) is 1, indicating that nodes i and j are in the same partition k. δ(i,j) is 0, indicating that they are not in the same partition k. ij represents the electrical distance between node i and node j; The larger the value of the partition performance index Q is, the closer the nodes in the same partition are.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the distribution network partitioning method for decentralized voltage regulation according to any one of claims 1 to 4 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the distribution network partitioning method for decentralized voltage regulation as described in any one of claims 1 to 4 is implemented.

Images