Method and device for determining voltage control parameters of power distribution network and electronic equipment

Abstract

The invention discloses a power distribution network voltage control parameter determination method and device and electronic equipment. The method comprises the following steps: acquiring topological structure parameters and power grid operation parameters of a power distribution network; determining a plurality of coupling correlation indexes respectively corresponding to the plurality of equipment connection points according to the topological structure parameters and the power grid operation parameters; dividing the power distribution network according to the plurality of coupling correlation indexes corresponding to the plurality of equipment connection points to obtain a plurality of sub-networks; determining subnet control parameters respectively corresponding to the plurality of subnets according to the power grid operation parameters; and determining a voltage control parameter corresponding to the power distribution network according to the sub-network control parameter. According to the method and the device, the technical problem of low voltage control reliability of the power distribution network caused by inaccurate determination of the voltage control parameters of the power distribution network in related technologies is solved.

Description

Technical Field

[0001] This invention relates to the field of power distribution network control, and more specifically, to a method, apparatus, and electronic device for determining power distribution network voltage control parameters. Background Technology

[0002] Distribution network voltage control parameters are the key basis and foundation for distribution network voltage control, directly affecting the network's operating efficiency, power supply quality, and reliability. However, in related technologies, there are technical problems where inaccurate determination of distribution network voltage control parameters leads to low reliability of distribution network voltage control.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a method, apparatus, and electronic device for determining voltage control parameters in a distribution network, to at least solve the technical problem in the related art where inaccurate determination of voltage control parameters leads to low reliability of voltage control in the distribution network.

[0005] According to one aspect of the present invention, a method for determining voltage control parameters of a distribution network is provided, comprising: acquiring topology parameters and operating parameters of the distribution network; determining, based on the topology parameters and the operating parameters, a plurality of coupling correlation indices corresponding to a plurality of equipment connection points, wherein the plurality of coupling correlation indices represent the degree of correlation between the power variation index of the corresponding equipment connection point and the voltage variation index of other equipment connection points; dividing the distribution network into a plurality of subnetworks based on the plurality of coupling correlation indices corresponding to the plurality of equipment connection points; determining, based on the operating parameters, subnetwork control parameters corresponding to the plurality of subnetworks; and determining, based on the subnetwork control parameters, voltage control parameters corresponding to the distribution network.

[0006] Optionally, dividing the power distribution network into multiple subnets based on multiple coupling correlation indices corresponding to the multiple device connection points includes: determining coupling correlation features corresponding to the multiple device connection points based on the multiple coupling correlation indices corresponding to the multiple device connection points; determining multiple target similarity indices corresponding to the multiple device connection points based on the coupling correlation features corresponding to the multiple device connection points, wherein the multiple target similarity indices represent the degree of similarity between the coupling correlation features of the corresponding device connection points and the coupling correlation features of other device connection points; clustering the multiple device connection points of the power distribution network based on the multiple target similarity indices corresponding to the multiple device connection points to obtain multiple connection point sets; and determining multiple subnets corresponding to the power distribution network based on the multiple connection point sets, wherein the multiple subnets correspond one-to-one with the multiple connection point sets.

[0007] Optionally, when the coupling correlation features corresponding to the plurality of device connection points respectively include voltage influence trend features and voltage influence amplitude features, the step of determining the plurality of target similarity indices corresponding to the plurality of device connection points based on the coupling correlation features corresponding to the plurality of device connection points respectively includes: determining a first similarity index corresponding to the plurality of device connection points based on the voltage influence trend features corresponding to the plurality of device connection points respectively, wherein the corresponding first similarity index represents the degree of similarity between the voltage influence trend features of the corresponding device connection point and the voltage influence trend features of other device connection points respectively; determining a second similarity index corresponding to the plurality of device connection points based on the voltage influence amplitude features corresponding to the plurality of device connection points respectively, wherein the corresponding first similarity index represents the degree of similarity between the voltage influence amplitude features of the corresponding device connection point and the voltage influence amplitude features of other device connection points respectively; and determining the plurality of target similarity indices corresponding to the plurality of device connection points based on the first similarity index and the second similarity index corresponding to the plurality of device connection points respectively.

[0008] Optionally, determining the sub-network control parameters corresponding to the plurality of sub-networks based on the power grid operating parameters includes: determining the control level corresponding to the plurality of sub-networks, wherein the control level includes any one of the following: a first level, a second level, wherein the voltage control range of the distribution network corresponding to the first level is greater than the voltage control range of the distribution network corresponding to the second level; determining the control target corresponding to the plurality of sub-networks based on the control level corresponding to the plurality of sub-networks; and determining the sub-network control parameters corresponding to the plurality of sub-networks based on the control target corresponding to the plurality of sub-networks and the power grid operating parameters.

[0009] Optionally, determining the subnet control parameters corresponding to each of the plurality of subnets based on the control objectives corresponding to each of the plurality of subnets and the power grid operating parameters includes: determining the subnet operating parameters corresponding to each of the plurality of subnets based on the power grid operating parameters; determining the state adjustment range corresponding to each of the plurality of subnets based on the subnet operating parameters corresponding to each of the plurality of subnets, wherein the corresponding state adjustment range is the adjustment range of the operating state of the corresponding subnet; and determining the subnet control parameters corresponding to each of the plurality of subnets based on the control objectives and state adjustment ranges corresponding to each of the plurality of subnets.

[0010] Optionally, determining the subnet control parameters corresponding to the plurality of subnets based on the control objectives and state adjustment ranges corresponding to the plurality of subnets includes: determining a plurality of candidate control parameters corresponding to the plurality of subnets based on the state adjustment ranges corresponding to the plurality of subnets; determining the selection index corresponding to the plurality of candidate control parameters of the target subnet for any target subnet among the plurality of subnets; determining the subnet control parameters of the target subnet based on the selection index corresponding to the plurality of candidate control parameters of the target subnet; and determining the subnet control parameters corresponding to the other subnets among the plurality of subnets besides the target subnet by using the same method as determining the subnet control parameters of the target subnet.

[0011] Optionally, determining multiple coupling correlation indices corresponding to multiple device connection points based on the topology parameters and the power grid operating parameters includes: determining connection point characteristics corresponding to multiple device connection points based on the topology parameters and the power grid operating parameters, wherein the corresponding connection point characteristics include voltage characteristics and power characteristics; and determining multiple coupling correlation indices corresponding to multiple device connection points based on the connection point characteristics corresponding to the multiple device connection points.

[0012] According to one aspect of the present invention, a distribution network voltage control parameter determination device is provided, comprising: an acquisition module for acquiring topology parameters and power grid operating parameters of the distribution network; a first determination module for determining, based on the topology parameters and the power grid operating parameters, a plurality of coupling correlation indices corresponding to a plurality of equipment connection points, wherein the plurality of coupling correlation indices represent the degree of correlation between the power variation index of the corresponding equipment connection point and the voltage variation index of other equipment connection points; a second determination module for dividing the distribution network into a plurality of subnetworks based on the plurality of coupling correlation indices corresponding to the plurality of equipment connection points; a third determination module for determining, based on the power grid operating parameters, subnetwork control parameters corresponding to the plurality of subnetworks; and a fourth determination module for determining, based on the subnetwork control parameters, voltage control parameters corresponding to the distribution network.

[0013] According to one aspect of the present invention, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the distribution network voltage control parameter determination method described in any of the preceding embodiments.

[0014] According to one aspect of the present invention, a computer-readable storage medium is provided, comprising: when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enabling the electronic device to perform the distribution network voltage control parameter determination method described in any of the preceding claims.

[0015] In this embodiment of the invention, the topology parameters and operating parameters of the distribution network are obtained; based on the topology parameters and operating parameters, multiple coupling correlation indices corresponding to multiple device connection points are determined, wherein the multiple coupling correlation indices represent the degree of correlation between the power variation index of the corresponding device connection point and the voltage variation index of other device connection points; based on the multiple coupling correlation indices corresponding to the multiple device connection points, the distribution network is divided into multiple subnetworks; based on the operating parameters, subnetwork control parameters corresponding to the multiple subnetworks are determined; based on the subnetwork control parameters, voltage control parameters corresponding to the distribution network are determined. By determining multiple coupling correlation indices corresponding to various equipment connection points based on the topology parameters and operating parameters of the distribution network, the correlation between power changes and voltage changes among the connection points can be accurately quantified. The distribution network is then divided according to the coupling correlation indices, ensuring strong coupling at connection points within each subnetwork (adjusting one point can stabilize the subnetwork voltage) and weak coupling between subnetworks (avoiding cross-subnetwork regulation interference). This allows for the targeted determination of subnetwork control parameters for each subnetwork, accurately determining the global voltage control parameters of the distribution network. This solves the technical problem of low reliability of distribution network voltage control due to inaccurate determination of distribution network voltage control parameters in related technologies. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings: Figure 1 This is a flowchart of a method for determining distribution network voltage control parameters according to an embodiment of the present invention; Figure 2 This is a flowchart of the voltage control model training process in an optional embodiment of the present invention; Figure 3 This is a hierarchical reactive voltage control framework for power distribution networks in an optional embodiment of the present invention; Figure 4 This is a structural block diagram of a power distribution network voltage control parameter determination device according to an embodiment of the present invention. Detailed Implementation

[0017] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0018] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0019] First, some nouns or terms that appear in the description of the embodiments of this application shall be interpreted as follows: Python: Python is a cross-platform, object-oriented, high-level programming language.

[0020] MATD3 Algorithm: The MATD3 algorithm (Multi-Agent Twin Delayed Deep Deterministic Policy Gradient Algorithm) is a multi-agent reinforcement learning algorithm that extends the single-agent TD3 (Twin Delayed DDPG) algorithm.

[0021] Example 1 According to an embodiment of the present invention, an embodiment of a method for determining voltage control parameters of a distribution network is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0022] Figure 1 This is a flowchart of a method for determining distribution network voltage control parameters according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps: Step S102: Obtain the topology parameters and operating parameters of the distribution network.

[0023] In step S102 of this application, the topology parameters and operating parameters of the distribution network are obtained.

[0024] This involves the distribution network, which is a power network that distributes electricity to various load terminals (such as users) through distribution facilities. The structure and operating status of the distribution network directly affect the power quality and reliability for users.

[0025] This involves topology parameters, which describe the connection relationships and structural characteristics of the distribution network. These parameters include nodes formed by multiple device connection points, and edges formed by the connection characteristics between these points. Connection characteristics include the connection methods between nodes and the tightness of their relationships. The topology parameters reflect the power transmission characteristics of the distribution network.

[0026] This involves power grid operating parameters, which are used to reflect the operating status of the distribution network. The operating status of the distribution network includes historical operating status and current operating status.

[0027] Obtaining the topology parameters and operating parameters of the distribution network enables a comprehensive understanding of the network structure and operating status, thus providing an accurate data foundation for determining subsequent voltage control parameters.

[0028] S104. Based on the topology parameters and the power grid operating parameters, determine multiple coupling correlation indices corresponding to multiple equipment connection points. The multiple coupling correlation indices represent the degree of correlation between the power variation index of the corresponding equipment connection point and the voltage variation index of other equipment connection points.

[0029] In step S104 provided in this application, multiple coupling correlation indices corresponding to multiple device connection points are determined based on topology parameters and power grid operating parameters.

[0030] This involves equipment connection points, which are nodes in the power distribution network used to connect different devices or different parts. These nodes can be distribution transformers, switching stations, smart capacitor banks, distributed generation access points, static var compensator access points, user access points, etc. Equipment connection points are key nodes in power transmission and distribution, and changes in their status and parameters directly affect the operating status and voltage level of the power distribution network.

[0031] This involves several coupling correlation indices, which are indicators used to quantify the degree of correlation between power and voltage variations between device connection points. They reflect the impact of power changes at one device connection point on voltage changes at other device connection points.

[0032] This includes the power variation index, which is the amount or rate of change of power at the equipment connection point. It reflects the power change at the equipment connection point over a certain period of time.

[0033] This includes the voltage variation index, which is the amount or rate of change of voltage at the equipment connection point. It reflects the voltage change at the equipment connection point over a certain period of time.

[0034] Determining the coupling correlation index of equipment connection points based on topology parameters and power grid operating parameters can quantify the mutual influence of power and voltage variations between equipment connection points, thereby helping to accurately identify the coupling strength between equipment connection points in the distribution network and providing a data foundation for subsequent optimization of distribution network zoning.

[0035] S106. Based on the multiple coupling correlation indices corresponding to the multiple device connection points, the power distribution network is divided into multiple subnetworks.

[0036] In step S106 provided in this application, the power distribution network is divided into multiple subnetworks based on multiple coupling correlation indices corresponding to multiple device connection points.

[0037] This involves multiple subnets, which are several relatively independent regions obtained by dividing the distribution network. These subnets are divided based on the coupling correlation index between equipment connection points, with the aim of decomposing the distribution network into multiple regions with strong internal coupling (i.e., significant mutual influence between power and voltage fluctuations at equipment connection points within the subnet) and weak external coupling (i.e., minimal mutual influence between subnets).

[0038] The power distribution network is divided into multiple subnetworks based on multiple coupling correlation indices corresponding to multiple device connection points, and these subnetworks have the following characteristics: Strong internal coupling: The connection points of devices within the subnet exhibit a high coupling correlation index, implying a strong mutual influence between power and voltage fluctuations. Therefore, coordinated control of devices within the subnet can effectively stabilize the voltage level.

[0039] Weak external coupling: The coupling correlation index between different subnets is low, which means that the mutual influence between subnets is small, thereby reducing the complexity and interference of cross-subnet regulation and improving control efficiency and reliability.

[0040] Flexible control: By dynamically dividing the subnet through coupling correlation index, adjustments can be made in real time according to changes in the actual operating status and topology of the distribution network, adapting to different operating scenarios and control requirements. In other words, adjustments can be made based on changes in the actual operating status and topology of the distribution network to adapt to different operating scenarios, thereby achieving dynamic subnetting. This enhances the adaptability of control parameter determination, leading to more accurate and reliable voltage control parameters for the subsequent distribution network.

[0041] S108 determines the subnet control parameters corresponding to each of the multiple subnets based on the power grid operating parameters.

[0042] In step S108 provided in this application, the subnet control parameters corresponding to the multiple subnets are determined based on the power grid operating parameters.

[0043] This involves subnet control parameters, which are parameters used to control the voltage of the corresponding subnet.

[0044] By determining the subnet control parameters corresponding to each of the multiple subnets, each subnet can perform local optimization based on its own control objectives and operating status, which will help to achieve reliable operation of the entire distribution network in the future.

[0045] S110 determines the voltage control parameters corresponding to the distribution network based on the subnet control parameters.

[0046] In step S110 provided in this application, the voltage control parameters corresponding to the distribution network are determined based on the subnet control parameters.

[0047] This involves voltage control parameters, which are determined comprehensively based on the control parameters of each sub-network and are the power parameters corresponding to the voltage control of the distribution network.

[0048] By integrating the subnet control parameters of each subnet, it is possible to accurately determine the voltage control parameters that are suitable for both local and global distribution networks, thereby improving power supply reliability and adaptability.

[0049] By determining the voltage control parameters of the distribution network through subnet control parameters, the local control objectives of each subnet are combined with the global optimization requirements, thereby achieving accurate voltage control of the entire distribution network.

[0050] Through the above steps S102-S110, the topology parameters and operating parameters of the distribution network are obtained; based on the topology parameters and operating parameters, multiple coupling correlation indices corresponding to multiple equipment connection points are determined, wherein the corresponding multiple coupling correlation indices represent the degree of correlation between the power variation index of the corresponding equipment connection point and the voltage variation index of other equipment connection points; based on the multiple coupling correlation indices corresponding to the multiple equipment connection points, the distribution network is divided into multiple subnetworks; based on the operating parameters, the subnetwork control parameters corresponding to the multiple subnetworks are determined; based on the subnetwork control parameters, the voltage control parameters corresponding to the distribution network are determined. By determining multiple coupling correlation indices corresponding to various equipment connection points based on the topology parameters and operating parameters of the distribution network, the correlation between power changes and voltage changes among the connection points can be accurately quantified. The distribution network is then divided according to the coupling correlation indices, ensuring strong coupling at connection points within each subnetwork (adjusting one point can stabilize the subnetwork voltage) and weak coupling between subnetworks (avoiding cross-subnetwork regulation interference). This allows for the targeted determination of subnetwork control parameters for each subnetwork, accurately determining the global voltage control parameters of the distribution network. This solves the technical problem of low reliability of distribution network voltage control due to inaccurate determination of distribution network voltage control parameters in related technologies.

[0051] As an optional embodiment, the power distribution network is divided into multiple subnets based on multiple coupling correlation indices corresponding to multiple device connection points, including: determining coupling correlation features corresponding to multiple device connection points based on the multiple coupling correlation indices corresponding to multiple device connection points; determining multiple target similarity indices corresponding to multiple device connection points based on the coupling correlation features corresponding to multiple device connection points, wherein the corresponding multiple target similarity indices represent the degree of similarity between the coupling correlation features of the corresponding device connection point and the coupling correlation features of other device connection points; clustering the multiple device connection points of the power distribution network based on the multiple target similarity indices corresponding to multiple device connection points to obtain multiple connection point sets; and determining multiple subnets corresponding to the power distribution network based on the multiple connection point sets, wherein the multiple subnets correspond one-to-one with the multiple connection point sets.

[0052] This embodiment describes the specific steps for dividing the power distribution network into multiple subnetworks based on multiple coupling correlation indices corresponding to multiple device connection points.

[0053] This involves coupling correlation features, which are determined based on multiple coupling correlation indices for the corresponding device connection points. These features represent the influence between power variations at the corresponding device connection point and voltage variations at other device connection points. The coupling correlation features include voltage influence trend characteristics and voltage influence amplitude characteristics.

[0054] This includes the target similarity index, which is an indicator used to quantify the similarity of coupling and association characteristics between device connection points. It reflects the similarity between the coupling and association characteristics of two device connection points.

[0055] This involves clustering, which is used to divide multiple device connection points into several clusters (i.e., sets), such that device connection points within the same cluster have high similarity, while device connection points between different clusters have low similarity.

[0056] This involves multiple sets of connection points, which are collections of device connection points obtained through clustering. The device connection points within each connection point set have high similarity in coupling characteristics, meaning that their power changes affect voltage changes in a similar way and to a similar degree. However, the device connection points in different connection point sets have low similarity in coupling characteristics, meaning that their power changes affect voltage changes in a different way and to a different degree.

[0057] By determining the coupling correlation characteristics and target similarity index of the equipment connection points and performing clustering, the distribution network is divided into multiple subnets. This results in strong internal coupling of the equipment connection points within each subnet, while the coupling between different subnets is weak. This ensures that adjusting one point within a subnet can stabilize the subnet voltage, while the weak coupling between different subnets avoids mutual interference from cross-subnet regulation.

[0058] As an optional embodiment, when the coupling correlation features corresponding to multiple device connection points respectively include voltage influence trend features and voltage influence amplitude features, multiple target similarity indices corresponding to the multiple device connection points are determined based on the coupling correlation features corresponding to the multiple device connection points respectively. This includes: determining a first similarity index corresponding to the multiple device connection points based on the voltage influence trend features corresponding to the multiple device connection points respectively, wherein the corresponding first similarity index represents the degree of similarity between the voltage influence trend features of the corresponding device connection point and the voltage influence trend features of other device connection points respectively; determining a second similarity index corresponding to the multiple device connection points based on the voltage influence amplitude features corresponding to the multiple device connection points respectively, wherein the corresponding first similarity index represents the degree of similarity between the voltage influence amplitude features of the corresponding device connection point and the voltage influence amplitude features of other device connection points respectively; and determining multiple target similarity indices corresponding to the multiple device connection points based on the first and second similarity indices corresponding to the multiple device connection points respectively.

[0059] This embodiment describes the specific steps for determining multiple target similarity indices corresponding to multiple device connection points based on the coupling correlation features corresponding to the multiple device connection points, when the coupling correlation features corresponding to the multiple device connection points include voltage influence trend features and voltage influence amplitude features.

[0060] This involves voltage influence trend characteristics, which represent the direction (trend) of the impact of power changes at one of the multiple device connection points on the voltage changes at other device connection points. This voltage influence trend characteristic reflects whether the voltage at other device connection points increases or decreases when the power at one device connection point changes. This voltage influence trend characteristic includes both positive and negative influence trends.

[0061] A positive trend (i.e., positive correlation) means that when the power of one device connection point among multiple device connection points increases, the voltage of other device connection points also increases.

[0062] A negative influence trend (i.e., negative correlation) means that when the power of one device connection point among multiple device connection points increases, the voltage of other device connection points decreases.

[0063] This involves the voltage impact amplitude characteristic, which measures the magnitude of the impact of a power change at one of multiple device connection points on the voltage changes at other device connection points. Specifically, this voltage impact amplitude characteristic is used to quantify the magnitude of voltage changes at other device connection points caused by a power change at one of the multiple device connection points.

[0064] This involves a first similarity index, which is a similarity indicator calculated based on voltage influence trend characteristics. This first similarity index is used to represent the degree of similarity between the voltage influence trend characteristics of two device connection points.

[0065] This involves a second similarity index, which is a similarity indicator calculated based on voltage influence amplitude characteristics. It represents the degree of similarity between the voltage influence amplitude characteristics of two device connection points.

[0066] The first similarity index reflects the similarity of voltage influence trends between device connection points, i.e., the degree to which power changes lead to voltage changes in the same or opposite directions; the second similarity index quantifies the similarity of voltage influence magnitudes, i.e., the consistency of voltage changes caused by power changes. By combining these two similarity indices to obtain the target similarity index, the coupling relationship between device connection points can be more comprehensively evaluated, thereby achieving more reasonable network partitioning.

[0067] As an optional embodiment, determining the sub-network control parameters corresponding to each of the multiple sub-networks based on the power grid operating parameters includes: determining the control levels corresponding to each of the multiple sub-networks, wherein the control levels include any one of the following: a first level, a second level, wherein the voltage control range of the distribution network corresponding to the first level is greater than the voltage control range of the distribution network corresponding to the second level; determining the control objectives corresponding to each of the multiple sub-networks based on the control levels corresponding to each of the multiple sub-networks; and determining the sub-network control parameters corresponding to each of the multiple sub-networks based on the control objectives corresponding to each of the multiple sub-networks and the power grid operating parameters.

[0068] This embodiment describes the specific steps for determining the subnet control parameters corresponding to multiple subnets based on the power grid operating parameters, including: determining the control levels corresponding to the multiple subnets.

[0069] This involves control levels, which are the different control hierarchy levels in the distribution network based on different functions and control ranges. This control hierarchy includes a first level and a second level.

[0070] This involves the first level, which is the level responsible for global or large-scale voltage control in the distribution network, such as the feeder level.

[0071] This involves a second level, which is responsible for voltage control within a relatively small area of ​​the distribution network, such as the transformer substation level.

[0072] This involves the voltage control range, which is the entire area of ​​the distribution network where voltage control is possible. For example: For the feeder level: the voltage control range covers the feeder network, that is, the distribution network section from the upper substation outgoing line to the incoming line of each distribution transformer.

[0073] For the distribution area level: the voltage control range covers the distribution network from the transformer inlet to the user side.

[0074] This involves control objectives, which are specific control tasks or optimization goals that need to be achieved. For example: For the feeder level: the control objective is to minimize the total network loss of the distribution network and reduce the overall voltage deviation of the distribution network.

[0075] For the distribution area level: maximize the voltage qualification rate of the corresponding area (corresponding sub-network) in the distribution network.

[0076] By first dividing multiple subnets into first-level and second-level subnets, the control boundaries and hierarchical positioning of different subnets can be clearly defined. Then, based on the control level of each subnet, appropriate control objectives can be determined. Combined with the power grid operating parameters, specific subnet control parameters can be determined, enabling precise control of different subnets in the distribution network. This ensures both the economy and stability of the overall operation of the distribution network, while also improving the reliability and quality of operation of each local subnet, thus optimizing the overall operation effect of the distribution network.

[0077] As an optional embodiment, the subnet control parameters corresponding to each of the multiple subnets are determined based on the control objectives corresponding to each of the multiple subnets and the power grid operating parameters, including: determining the subnet operating parameters corresponding to each of the multiple subnets based on the power grid operating parameters; determining the state adjustment range corresponding to each of the multiple subnets based on the subnet operating parameters corresponding to each of the multiple subnets, wherein the corresponding state adjustment range is the adjustment range of the operating state of the corresponding subnet; and determining the subnet control parameters corresponding to each of the multiple subnets based on the control objectives and state adjustment ranges corresponding to each of the multiple subnets.

[0078] This embodiment describes the specific steps for determining the subnet control parameters corresponding to the multiple subnets based on the control objectives corresponding to the multiple subnets and the power grid operating parameters.

[0079] This involves the state adjustment range, which is the range of permissible changes in the operating state within the corresponding subnet.

[0080] By determining the state adjustment range of each subnet, the adjustable boundary of the operating state of each subnet can be clearly defined, avoiding the determination of subnet control parameters from exceeding the allowable safe and stable operating range of the subnet. Thus, by combining the control objectives and state adjustment ranges corresponding to multiple subnets, it is ensured that the determined subnet control parameters not only conform to the subnet's own operating capabilities but also accurately point to and achieve the control objectives.

[0081] As an optional embodiment, based on the control objectives and state adjustment ranges corresponding to the multiple subnets respectively, the subnet control parameters corresponding to the multiple subnets are determined, including: determining multiple candidate control parameters corresponding to the multiple subnets based on the state adjustment ranges corresponding to the multiple subnets respectively; for any target subnet among the multiple subnets, determining the selection index corresponding to the multiple candidate control parameters of the target subnet respectively; determining the subnet control parameters of the target subnet based on the selection index corresponding to the multiple candidate control parameters of the target subnet respectively; and determining the subnet control parameters corresponding to the other subnets among the multiple subnets besides the target subnet by using the method of determining the subnet control parameters of the target subnet.

[0082] This embodiment describes the specific steps for determining the subnet control parameters corresponding to the multiple subnets based on the control objectives and state adjustment ranges corresponding to the multiple subnets.

[0083] This involves multiple candidate control parameters. These multiple candidate control parameters are generated based on the state adjustment range of the target subnet. Within its allowed operating state adjustment boundary, they are multiple control parameter options that can regulate the operating state of the subnet and meet the adjustment range restrictions. These multiple candidate control parameters all have the potential to achieve the subnet control objective, but further evaluation is needed to determine the optimal option.

[0084] This involves a target subnet, which is a specific subnet selected as the object of analysis and processing among multiple subnets whose control parameters need to be determined. It is the targeted analysis object for subsequent control parameter determination, and the processing flow of a single target subnet can be extended to other subnets. The selection of the target subnet can be arbitrary, including selection and processing from the feeder level to the substation level.

[0085] This involves a selection index, which is a quantitative indicator used to evaluate the performance of each candidate control parameter. The selection index reflects the degree to which the candidate control parameter satisfies or is well-suited to the subnet control objectives and state regulation range.

[0086] First, candidate control parameters that conform to the subnet's operating boundary are generated based on the state adjustment range, ensuring that parameter selection is always within a safe and feasible range. Then, the performance of each candidate parameter (adaptation to the control objective and degree of conformity to the adjustment range) is quantitatively evaluated by selecting an index, providing a basis for selecting the optimal parameters. Next, the subnet control parameters of the target subnet are determined and this process is reused to other subnets. This ensures the accuracy and effectiveness of the control parameters of individual subnets, and achieves uniformity and efficiency in determining the control parameters of all subnets through a standardized process. Ultimately, it ensures that the control parameters of all subnets can optimally adapt to their respective control objectives under the premise of compliance, thereby helping to improve the reliability of the overall control of the distribution network.

[0087] As an optional embodiment, based on topology parameters and power grid operating parameters, multiple coupling correlation indices corresponding to multiple device connection points are determined, including: determining connection point characteristics corresponding to multiple device connection points based on topology parameters and power grid operating parameters, wherein the corresponding connection point characteristics include voltage characteristics and power characteristics; and determining multiple coupling correlation indices corresponding to multiple device connection points based on the connection point characteristics corresponding to multiple device connection points.

[0088] This embodiment describes the specific steps for determining multiple coupling correlation indices corresponding to multiple device connection points based on topology parameters and power grid operating parameters.

[0089] This involves connection point characteristics, which are determined based on the topology parameters of the power grid (such as equipment connection relationships, line layout, etc.) and the power grid operating parameters (such as voltage, power, etc.). These characteristics reflect the operating status, functional attributes, and association characteristics of the equipment connection point with surrounding equipment / networks in the power grid.

[0090] This involves voltage characteristics, which are characteristics corresponding to the voltage at the corresponding device connection point.

[0091] This involves power characteristics, which are characteristics corresponding to the power of the corresponding device connection point.

[0092] By combining the topological parameters and operating parameters of the power grid to extract connection point features, the characteristics of each equipment connection point can be accurately identified. Then, based on these connection point features, the coupling correlation index can be calculated, which can quantify the mutual influence between each equipment connection point. This helps to accurately grasp the linkage characteristics of equipment connection points in the distribution network and provides a data foundation for the zonal optimization of the distribution network.

[0093] Based on the above embodiments and optional embodiments, an optional implementation method is provided, which is described in detail below.

[0094] In related technologies, distribution network voltage control parameters are the key basis and execution foundation for distribution network voltage control, directly affecting the operating efficiency, power supply quality, and reliability of the distribution network. However, there are technical problems in related technologies where inaccurate determination of distribution network voltage control parameters leads to low reliability of distribution network voltage control.

[0095] Its specific manifestations are as follows: 1) Defects in the algorithm architecture lead to insufficient foundation for parameter determination: For example, the single-agent deep deterministic policy gradient (DDPG) algorithm suffers from low training efficiency and inability to perform distributed collaboration due to the exponential growth of the action space with the number of nodes, making it difficult to quickly and accurately process large-scale distribution network data to support control parameter calculations. The multi-agent deep deterministic policy gradient (MADDPG) algorithm ignores network topology correlations, resulting in frequent redundant actions. Algorithms such as multi-agent near-end policy optimization (MAPPO) have poor training stability in continuous action spaces, insufficient adaptability to high-dimensional state spaces, and lack differentiated collaboration mechanisms between feeders and transformer substations. All of these algorithms fail to provide reasonable algorithmic support for determining control parameters based on the actual physical characteristics and hierarchical requirements of the distribution network, thus leading to inaccurate parameter determination.

[0096] 2) Parameter optimization affected by defects in multi-agent cooperative mechanisms: The MADDPG algorithm is prone to getting trapped in local optima and frequent changes in reactive power and voltage control commands, which makes it impossible to determine stable and suitable control parameters through effective collaborative optimization, thus exacerbating the problem of inaccurate parameters.

[0097] 3) Inappropriate regional division and information exchange hinder accurate parameter calculation: The unreasonable division of the distribution area makes it difficult to balance the control objectives between the areas. Furthermore, the lack of a matching mechanism between the distribution network structure partition and the intelligent agent, coupled with the reliance on global information interaction, results in a surge in communication overhead and decision-making delays. This not only makes it impossible to obtain the effective information required for calculation parameters in a timely manner, but also causes the parameters to be unable to adapt to the real-time distribution network status due to decision lag. Consequently, the voltage control parameters of the distribution network cannot match the current status.

[0098] This makes it impossible to accurately control the voltage parameters of the distribution network, resulting in low reliability of the voltage control in the distribution network.

[0099] There is currently no effective solution to the above problems.

[0100] In view of this, an optional embodiment of the present invention provides a method for determining voltage control parameters of a power distribution network, which can effectively solve the above-mentioned technical problems.

[0101] S1. Obtain the topology parameters and operating parameters of the distribution network; S2. Based on the topology parameters and power grid operating parameters, determine multiple coupling correlation indices corresponding to multiple equipment connection points. The multiple coupling correlation indices represent the degree of correlation between the power variation index of the corresponding equipment connection point and the voltage variation index of other equipment connection points. Specifically, S2 includes: Based on the topology parameters and power grid operating parameters, the connection point characteristics corresponding to multiple equipment connection points are determined, including voltage and power characteristics. Based on the connection point characteristics corresponding to multiple equipment connection points, multiple coupling correlation indices corresponding to multiple equipment connection points are determined.

[0102] S3. Based on the multiple coupling correlation indices corresponding to the multiple device connection points, the power distribution network is divided into multiple subnetworks; For example, based on the reactive power-voltage sensitivity matrix, the distribution network can be dynamically divided into multiple sub-regions (similar to the multiple sub-networks mentioned above) using the AP clustering algorithm. Each sub-region acts as an independent intelligent agent for collaborative control, solving the problem that traditional partitioning methods are insufficient in characterizing voltage coupling characteristics and improving control efficiency and regional adjustment capabilities.

[0103] Specifically, S3 includes: Based on multiple coupling correlation indices corresponding to multiple device connection points, coupling correlation features corresponding to each device connection point are determined. Based on the coupling correlation features corresponding to each device connection point, multiple target similarity indices corresponding to each device connection point are determined. These target similarity indices represent the degree of similarity between the coupling correlation features of the corresponding device connection point and the coupling correlation features of other device connection points. Based on these target similarity indices, the multiple device connection points of the distribution network are clustered to obtain multiple connection point sets. Based on these connection point sets, multiple subnets corresponding to the distribution network are determined, with each subnet corresponding to one connection point set.

[0104] Furthermore, when the coupling correlation features corresponding to multiple device connection points include voltage influence trend features and voltage influence amplitude features, based on the coupling correlation features corresponding to the multiple device connection points, multiple target similarity indices are determined, including: based on the voltage influence trend features corresponding to the multiple device connection points, determining a first similarity index corresponding to the multiple device connection points, wherein the corresponding first similarity index represents the degree of similarity between the voltage influence trend features of the corresponding device connection point and the voltage influence trend features of other device connection points; based on the voltage influence amplitude features corresponding to the multiple device connection points, determining a second similarity index corresponding to the multiple device connection points, wherein the corresponding first similarity index represents the degree of similarity between the voltage influence amplitude features of the corresponding device connection point and the voltage influence amplitude features of other device connection points; and based on the first and second similarity indices corresponding to the multiple device connection points, determining multiple target similarity indices corresponding to the multiple device connection points.

[0105] 1) Calculation of reactive power-voltage sensitivity matrix: Based on the distribution network topology parameters (same as the topology parameters mentioned above) and typical operating scenario data, a power flow calculation model is established, a node admittance matrix Y is generated, and multiple coupling correlation indices corresponding to multiple device connection points are calculated.

[0106] Among them, the multiple coupling correlation indices corresponding to the multiple device connection points can be represented by the global reactive power-voltage sensitivity matrix (SQ). U) indicates that the element The matrix represents the sensitivity of reactive power injection at node j to voltage at node i. To eliminate the influence of different dimensions on the clustering results, the elements in the matrix are normalized to obtain a normalized matrix. Each element of the matrix The calculation formula is:

[0107] in: , are the mean and standard deviation of the data in column j, respectively.

[0108] 2) Similarity matrix construction: Based on multiple coupling correlation indices corresponding to multiple device connection points, i.e., the normalized sensitivity matrix The cosine similarity (same as the first similarity index mentioned above) and the Euclidean distance (same as the second similarity index mentioned above) are combined to construct a similarity matrix (same as the multiple target similarity indices corresponding to the multiple device connection points mentioned above).

[0109] For cosine similarity, used to measure the consistency of voltage response trends in reactive power regulation among nodes, the formula is:

[0110] in: Let be the cosine similarity between device connection point i and device connection point j, that is, the first similarity index between device connection point i and device connection point j; Let i be the normalized sensitivity vector of the device connection point i; Let j be the normalized sensitivity vector of the device connection point; The norm of a vector is used to calculate its length.

[0111] For using Euclidean distance to quantify sensitivity differences, the formula is:

[0112] in: The Euclidean distance between device connection point i and device connection point j is also known as the second similarity index between device connection point i and device connection point j. Finally, the similarity matrix is ​​obtained by weighting the two, as shown in the formula:

[0113] in: Let be the target similarity index between device connection point i and device connection point j.

[0114] 3) Use the affinity propagation (AP) clustering algorithm for region partitioning: The AP clustering algorithm is used to process the similarity matrix and divide the distribution network into multiple sub-regions (similar to the multiple sub-networks mentioned above), ensuring high coupling within the region and low coupling between regions.

[0115] S4. Based on the power grid operating parameters, determine the sub-network control parameters corresponding to each of the multiple sub-networks; Specifically, S4 includes: Determine the control levels corresponding to the multiple subnets, wherein the control levels include any of the following: a first level, a second level, wherein the voltage control range of the distribution network corresponding to the first level is greater than the voltage control range of the distribution network corresponding to the second level; determine the control objectives corresponding to the multiple subnets based on the control levels corresponding to the multiple subnets; and determine the subnet control parameters corresponding to the multiple subnets based on the control objectives corresponding to the multiple subnets and the power grid operating parameters.

[0116] Furthermore, based on the control objectives corresponding to each of the multiple subnets and the power grid operating parameters, the subnet control parameters corresponding to each of the multiple subnets are determined, including: determining the subnet operating parameters corresponding to each of the multiple subnets based on the power grid operating parameters; determining the state adjustment range corresponding to each of the multiple subnets based on the subnet operating parameters, wherein the corresponding state adjustment range is the adjustment range of the operating state of the corresponding subnet; and determining the subnet control parameters corresponding to each of the multiple subnets based on the control objectives and state adjustment ranges corresponding to each of the multiple subnets.

[0117] Furthermore, based on the control objectives and state adjustment ranges corresponding to the multiple subnets, the subnet control parameters corresponding to each subnet are determined, including: determining multiple candidate control parameters corresponding to each subnet based on the state adjustment ranges corresponding to each subnet; for any target subnet among the multiple subnets, determining the selection index corresponding to each of the multiple candidate control parameters of the target subnet; determining the subnet control parameters of the target subnet based on the selection index corresponding to each of the multiple candidate control parameters of the target subnet; and determining the subnet control parameters corresponding to the other subnets among the multiple subnets besides the target subnet by using the same method as determining the subnet control parameters of the target subnet. Specifically, a Markov game process for the reactive power voltage control problem is constructed. Through the Markov game model, each subregion (i.e., each subnet) in the multiple subregions (same as the above multiple subnets) is treated as an independent intelligent agent. Through state space design, action space design, and reward function design, a dynamic decision-making process of global coordination and local optimization is constructed.

[0118] Specifically, it includes: 1) Determine the number of agents: The number of agents is the number of subnets, that is, the total number of subnets, with each subnet being an agent.

[0119] 2) Determine the state space (same as the state adjustment range above): This state space includes the voltage of nodes (device connection points), as well as the adjustable capacity and operating status of adjustable resources.

[0120] 3) Determine the action space (same as above for the multiple candidate control parameters corresponding to the multiple subnets): The action space includes the action strategies of all controllable resources within each sub-region (i.e., each sub-network) (the switching positions of distribution transformers and smart capacitor banks, the reactive power output of distributed power sources and static var compensators).

[0121] 4) Determine the state transition function: A state transition function describes how a system transitions to the next state given the current state and actions.

[0122] 5) Determine the discount factor: The discount factor is used to measure the current value of future rewards. Specifically, the discount factor balances the importance of immediate rewards and future rewards.

[0123] 6) Determine the reward function: The reward function is used to evaluate the immediate reward of an agent taking a certain action in a given state. The ultimate goal of agent training is to accumulate the maximum reward value so that the agent can adjust the reactive power output of equipment based on real-time power flow data returned from the distribution network, thereby minimizing network active power loss and voltage deviation. Therefore, the reward function is set as follows:

[0124] in: The reward value at time t; The total network loss at time t; Let be the voltage deviation at time t.

[0125] S5. Based on the subnet control parameters, determine the voltage control parameters corresponding to the distribution network.

[0126] For example, based on the constructed Markov game process, a reactive power voltage control model for a distribution network (hereinafter referred to as the voltage control model) based on the MATD3 algorithm is written using Python. Specifically, this includes: 1) Hierarchical control design: Based on the master-slave structure of the distribution network feeder-transformer area, and after network partitioning through reactive power-voltage sensitivity, a hierarchical control model (i.e., a voltage control model) adapted to the physical topology is constructed. By clarifying the control boundaries, objectives, and coordination mechanisms of each level, deep coordination between global optimization objectives and local autonomy requirements is achieved. This ensures both the overall economy and security of the feeder system and improves the voltage regulation accuracy at the transformer area level. The hierarchical control model includes a global optimal decision-making model at the feeder level and a reactive power-voltage control model at the transformer area level.

[0127] 2) Hierarchical division and control objectives: The feeder-level control scope covers the entire feeder network from the outgoing lines of the upper-level substation to the incoming lines of each distribution transformer. Its core task is to achieve the following optimization goals by coordinating the resources of the entire network: 1) Minimize total network loss and improve operational economy: 2) Reduce the overall voltage deviation of the entire network and ensure the voltage stability of the feeder backbone network: By integrating information such as active power, reactive power, and node voltage amplitude from the access points uploaded at the transformer substation level, and combining it with the feeder physical model for global reactive voltage control, it is necessary to generate control commands for controllable equipment at the feeder level based on the topology parameters and operating data of the feeder system. While meeting its own safety operation constraints and control objectives, it provides stable voltage support for the transformer substation level, ensuring that the voltage qualification rate of each transformer substation is maintained within the target range.

[0128] The control scope at the transformer substation level extends from the transformer's incoming line to the user side. Its core task is to maximize the voltage qualification rate within the substation by adjusting controllable resources based on real-time load power data, ensuring that the voltage on the user side remains within a safe range. After completing local optimization, the substation level connects itself as an equivalent load to the feeder level, feeding back active and reactive power demands to the feeder level. This allows the feeder level to incorporate it as a perceptible load unit into global optimization, achieving seamless integration between levels.

[0129] 3) Implementation of control at each level: Control at the feeder level and transformer substation level is achieved through a voltage control model, ensuring the consistency and coordination of the algorithm framework. For the feeder-level global optimal decision model, the control range of the global coordinating agent is determined based on the network partitioning results. Through the centralized training module of the MATD3 algorithm, the boundary information uploaded by each transformer area and the feeder physical model are integrated to generate the globally optimal equipment control strategy. For the reactive power and voltage control model at the transformer substation level, each transformer substation is deployed as an independent sub-region with a local intelligent agent. The distributed execution module of the MATD3 algorithm is used to independently complete the regulation of internal controllable resources based on local load data, and the execution results are converted into equivalent load parameters and fed back to the feeder level, forming a closed-loop control of "global optimization - local execution - dynamic feedback".

[0130] Figure 2 This is a flowchart of the voltage control model training process in an optional embodiment of the present invention, such as... Figure 2 As shown, the complete process from training to application can be divided into two parts: the training process and the control process. (1) Training process: A1. Initialization process: First, the agent's hyperparameters are initialized, the network parameters are initialized, and the experience replay area is cleared to prepare for subsequent training.

[0131] A2. Interaction and Data Storage: The intelligent agent interacts with the power distribution network environment, and the data generated during the interaction is stored in the experience playback area. This data includes the intelligent agent's actions in different states and the corresponding feedback.

[0132] A3. Sampling and Policy Output: Data is sampled from the experience replay area, and based on the sampled data, the agent provides the corresponding control strategy (i.e., the control parameters corresponding to each subnet).

[0133] A4. Reward Calculation and Network Update: The reward value is calculated based on the performance of the control strategy in the distribution network environment. Then, the reward value and related data are used to update the network parameters, enabling the network to better learn appropriate control strategies.

[0134] A5. Training termination judgment: Repeat the above steps from interaction to network update until the training requirements are met.

[0135] (2) Control process: Once the training process is complete, a trained reactive power voltage control model (i.e., a voltage control model) is obtained. During actual control, this model will output corresponding control strategies (i.e., voltage control parameters of the distribution network) based on the control objective and the state variables of the distribution network, thereby achieving effective control of the reactive power voltage of the distribution network.

[0136] Figure 3 This is a hierarchical reactive power and voltage control framework for distribution networks in an optional embodiment of the present invention, such as... Figure 3As shown, based on the above training process, the following section further describes the hierarchical structure, information interaction, and control logic.

[0137] 1) Hierarchical structure: Distribution area level (also known as distribution area layer): Each distribution area (such as distribution area 1, distribution area n) is equipped with capacitor banks (for reactive power compensation), on-load tap changers (OLTC), etc., and performs local control of reactive power equipment (capacitor banks, OLTC) within the distribution area according to the distribution area reactive power and voltage control model.

[0138] Feeder level (also known as feeder layer): Multiple transformer substations are connected by feeders to form a larger power grid unit. The upper layer has a global optimal decision model for feeders, which is responsible for coordinating the reactive power and voltage control of all transformer substations to achieve global optimization.

[0139] 2) Information exchange: Distribution area information flow: Information such as the action feedback of photovoltaic, capacitor bank, load, and OLTC within the distribution area will be input to the reactive power and voltage control model of the distribution area to obtain the local control decision (i.e., subgrid control parameters); at the same time, the key information of the distribution area will also be transmitted upward to the global optimal decision model of the feeder layer.

[0140] Feeder information flow: The global optimal decision model of the feeder layer will transmit the globally optimized instructions (such as voltage regulation targets, total reactive power compensation allocation, etc.) to the reactive power and voltage regulation device and the reactive power and voltage control model of each transformer area. In addition, the feeder layer also interacts with external loads.

[0141] 3) Control logic: Local control of distribution areas: The reactive power and voltage control model of each distribution area is based on the photovoltaic output and load changes of the area. It achieves the initial stabilization of reactive power and voltage in the area by controlling the switching of capacitor banks (adjusting reactive power compensation) and OLTC tap change (regulating voltage).

[0142] Global feeder optimization: After collecting the operating data of all transformer substations, the global optimal decision model of the feeder layer balances the reactive power supply and demand and voltage level of each transformer substation from the global perspective of the entire feeder, and corrects the control strategy of the transformer substation layer (such as coordinating the switching sequence of capacitor banks in different transformer substations and the voltage regulation range of OLTC), and finally achieves global optimal control of reactive power and voltage of the entire feeder, thereby improving the economy and reliability of the distribution network operation.

[0143] Based on the above, this hierarchical control approach not only leverages the advantages of the MATD3 algorithm in multi-agent collaborative decision-making but also fully adapts to the physical structural characteristics of the feeder-substation area, enabling efficient collaboration between global objectives and local requirements within a unified framework.

[0144] The above optional implementation methods can achieve at least the following beneficial effects: (1) Compared with related technologies, this invention determines multiple coupling correlation indices corresponding to multiple device connection points based on the topology parameters and operation parameters of the distribution network. This can accurately quantify the correlation between power changes and voltage changes between device connection points. The distribution network is divided according to the coupling correlation index to ensure that the internal connection points of the subnets are strongly coupled (adjusting one point can drive the subnet voltage to stabilize) and the inter-subnets are weakly coupled (avoiding cross-subnet regulation interference). Then, the subnet control parameters of each subnet are determined in a targeted manner, which can accurately determine the global voltage control parameters of the distribution network. This effectively solves the technical problem of low reliability of distribution network voltage control due to inaccurate determination of distribution network voltage control parameters.

[0145] (2) Compared with related technologies, the present invention decouples the distribution network into two control levels, feeder and transformer area, by using a partitioning method based on reactive power-voltage sensitivity, and comprehensively considers the control objectives of different levels and the collaborative control between levels. At the same time, the distribution network is decoupled into multiple sub-regions by using a partitioning method based on reactive power-voltage sensitivity, and a centralized training and distributed execution framework is adopted to solve the voltage oscillation problem caused by local optimization in traditional control methods.

[0146] (3) Compared with related technologies, this invention avoids single-objective decision-making by combining minimizing voltage deviation and network loss. Furthermore, through hierarchical target decomposition, feeder-level optimization focuses on global economy and overall voltage stability, while substation-level optimization focuses on local voltage qualification rate. This not only avoids local voltage exceeding limits caused by a single target, but also achieves coordinated optimization of global and local targets.

[0147] (4) Compared with related technologies, the reactive voltage control model of the distribution network based on the MATD3 algorithm of this invention divides the large-scale distribution network into multiple sub-regions by a network partitioning method based on reactive voltage sensitivity, and introduces a hierarchical control approach to achieve coordinated control of voltage control parameters of multiple agents. This solves the problems of poor coordination and insufficient real-time performance of traditional methods, improves the scalability of the algorithm and reduces computational complexity, and ultimately achieves rapid and stable voltage regulation and network loss reduction.

[0148] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0149] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0150] Example 2 According to an embodiment of the present invention, an apparatus for implementing the above-described method for determining distribution network voltage control parameters is also provided. Figure 4 This is a structural block diagram of a power distribution network voltage control parameter determination device according to an embodiment of the present invention, such as... Figure 4 As shown, the device includes: an acquisition module 402, a first determination module 404, a second determination module 406, a third determination module 408, and a fourth determination module 410. The device will be described in detail below.

[0151] The distribution network is configured with: an acquisition module 402 for acquiring topology parameters and operating parameters; a first determination module 404 connected to the acquisition module 402 for determining multiple coupling correlation indices corresponding to multiple device connection points based on the topology parameters and operating parameters, wherein the multiple coupling correlation indices represent the degree of correlation between the power variation index of the corresponding device connection point and the voltage variation index of other device connection points; a second determination module 406 connected to the first determination module 404 for dividing the distribution network into multiple subnets based on the multiple coupling correlation indices corresponding to the multiple device connection points; a third determination module 408 connected to the second determination module 406 for determining subnet control parameters corresponding to the multiple subnets based on the operating parameters; and a fourth determination module 410 connected to the third determination module 408 for determining voltage control parameters corresponding to the distribution network based on the subnet control parameters.

[0152] It should be noted that the above-mentioned acquisition module 402, first determination module 404, second determination module 406, third determination module 408 and fourth determination module 410 correspond to steps S102 to S110 in the method for determining distribution network voltage control parameters. The multiple modules and the corresponding steps are the same in terms of implementation examples and application scenarios, but are not limited to the content disclosed in the above embodiment 1.

[0153] Example 3 According to another aspect of the present invention, an electronic device is also provided, comprising: a processor; and a memory for storing processor-executable instructions, wherein the processor is configured to execute instructions to implement the power distribution network voltage control parameter determination method of any of the above embodiments.

[0154] Example 4 According to another aspect of the present invention, a computer-readable storage medium is also provided, which, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the distribution network voltage control parameter determination method described above.

[0155] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0156] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0157] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0158] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0159] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0160] If the integrated unit is implemented as 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 invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0161] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining voltage control parameters in a power distribution network, characterized in that, include: Obtain the topology parameters and operating parameters of the distribution network; Based on the topology parameters and the power grid operating parameters, multiple coupling correlation indices are determined for each of the multiple device connection points. The multiple coupling correlation indices represent the degree of correlation between the power variation index of the corresponding device connection point and the voltage variation index of the other device connection points. Based on the multiple coupling correlation indices corresponding to the multiple device connection points, the power distribution network is divided into multiple subnetworks; Based on the power grid operating parameters, determine the subgrid control parameters corresponding to each of the multiple subgrids; Based on the subnet control parameters, determine the voltage control parameters corresponding to the distribution network.

2. The method according to claim 1, characterized in that, The power distribution network is divided into multiple subnetworks based on the multiple coupling correlation indices corresponding to the multiple device connection points, including: Based on the multiple coupling association indices corresponding to the multiple device connection points, the coupling association characteristics corresponding to the multiple device connection points are determined. Based on the coupling association features corresponding to the plurality of device connection points, a plurality of target similarity indices corresponding to the plurality of device connection points are determined, wherein the plurality of target similarity indices represent the degree of similarity between the coupling association features of the corresponding device connection point and the coupling association features of other device connection points. Based on the multiple target similarity indices corresponding to the multiple device connection points, the multiple device connection points of the power distribution network are clustered to obtain multiple connection point sets; Based on the multiple sets of connection points, multiple subnets corresponding to the distribution network are determined, wherein each of the multiple subnets corresponds one-to-one with the multiple sets of connection points.

3. The method according to claim 2, characterized in that, When the coupling correlation features corresponding to the plurality of device connection points include voltage influence trend features and voltage influence amplitude features, the step of determining the plurality of target similarity indices corresponding to the plurality of device connection points based on the coupling correlation features corresponding to the plurality of device connection points includes: Based on the voltage influence trend characteristics corresponding to the plurality of device connection points, a first similarity index is determined for each of the plurality of device connection points, wherein the corresponding first similarity index represents the degree of similarity between the voltage influence trend characteristics of the corresponding device connection point and the voltage influence trend characteristics of other device connection points. Based on the voltage influence amplitude characteristics corresponding to the plurality of device connection points, a second similarity index is determined for each of the plurality of device connection points, wherein the corresponding first similarity index represents the degree of similarity between the voltage influence amplitude characteristics of the corresponding device connection point and the voltage influence amplitude characteristics of other device connection points. Based on the first similarity index and the second similarity index corresponding to the plurality of device connection points, a plurality of target similarity indices corresponding to the plurality of device connection points are determined.

4. The method according to claim 1, characterized in that, The step of determining the sub-network control parameters corresponding to the plurality of sub-networks based on the power grid operating parameters includes: Determine the control level corresponding to each of the plurality of subnets, wherein the control level includes any one of the following: a first level, a second level, wherein the voltage control range of the distribution network corresponding to the first level is greater than the voltage control range of the distribution network corresponding to the second level; Based on the control levels corresponding to the multiple subnets, determine the control objectives corresponding to the multiple subnets respectively; Based on the control objectives corresponding to the multiple subnets and the power grid operating parameters, the subnet control parameters corresponding to the multiple subnets are determined.

5. The method according to claim 4, characterized in that, The step of determining the subnet control parameters corresponding to each of the multiple subnets based on the control objectives corresponding to each of the multiple subnets and the power grid operating parameters includes: Based on the power grid operating parameters, determine the subgrid operating parameters corresponding to each of the plurality of subgrids; Based on the subnet operating parameters corresponding to the plurality of subnets respectively, determine the state adjustment range corresponding to the plurality of subnets respectively, wherein the corresponding state adjustment range is the adjustment range of the operating state of the corresponding subnet; Based on the control objectives and state adjustment ranges corresponding to the multiple subnets, the subnet control parameters corresponding to the multiple subnets are determined.

6. The method according to claim 5, characterized in that, The step of determining the subnet control parameters corresponding to each of the multiple subnets based on their respective control objectives and state adjustment ranges includes: Based on the state adjustment ranges corresponding to the multiple subnets, determine multiple candidate control parameters corresponding to the multiple subnets respectively; For any target subnet among the plurality of subnets, determine the selection index corresponding to the plurality of candidate control parameters of the target subnet respectively; Based on the selection indices corresponding to the multiple candidate control parameters of the target subnet, the subnet control parameters are determined. The subnet control parameters for each of the plurality of subnets other than the target subnet are determined by using the method of determining the subnet control parameters of the target subnet.

7. The method according to any one of claims 1 to 6, characterized in that, The determination of multiple coupling correlation indices corresponding to multiple device connection points based on the topology parameters and the power grid operating parameters includes: Based on the topology parameters and the power grid operating parameters, the connection point characteristics corresponding to the connection points of multiple devices are determined, wherein the corresponding connection point characteristics include voltage characteristics and power characteristics; Based on the connection point characteristics corresponding to the multiple device connection points, multiple coupling association indices corresponding to the multiple device connection points are determined.

8. A device for determining voltage control parameters in a power distribution network, characterized in that, include: The acquisition module is used to acquire the topology parameters and operating parameters of the distribution network. The first determining module is used to determine multiple coupling correlation indices corresponding to multiple device connection points based on the topology parameters and the power grid operating parameters, wherein the multiple coupling correlation indices represent the degree of correlation between the power variation index of the corresponding device connection point and the voltage variation index of the other device connection points. The second determining module is used to divide the power distribution network into multiple subnetworks based on the multiple coupling correlation indices corresponding to the multiple device connection points respectively. The third determining module is used to determine the subnet control parameters corresponding to the plurality of subnets respectively based on the power grid operating parameters; The fourth determining module is used to determine the voltage control parameters corresponding to the distribution network based on the subnet control parameters.

9. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the method for determining distribution network voltage control parameters as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the distribution network voltage control parameter determination method as described in any one of claims 1 to 7.

Images