Distributed power source site selection and capacity determination method and device, computer equipment, readable storage medium and program product

Abstract

The application relates to a distributed power source site selection and capacity determination method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: converting a power distribution network into a network structure comprising nodes and branches; constructing an optimization objective function and configuring a selection probability for each node; selecting a preset number of different nodes to form a candidate site selection scheme; obtaining the installed capacity and the objective function value of each node matched in the candidate site selection scheme; evaluating the candidate site selection scheme through a feasible region boundary learning model to obtain a minimum operating margin; screening a plurality of candidate site selection schemes to obtain an intermediate site selection scheme; updating the selection probability of the corresponding node, selecting a preset number of different nodes from all nodes to form a candidate site selection scheme, and continuing to execute until a preset condition is reached; and obtaining a final site selection scheme based on the intermediate site selection scheme and performing site selection and capacity determination. The method can improve the solving efficiency and convergence stability.

Description

Technical Field

[0001] This application relates to the field of power distribution network planning technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for the location and capacity determination of distributed power sources. Background Technology

[0002] With the integration of distributed generation into the distribution network, a reasonable location and capacity determination technology for distributed generation has emerged. This technology helps to improve the absorption level of distributed energy and ensure the safe and stable operation of the distribution network and improve power quality.

[0003] In traditional technologies, the location and capacity determination of distributed power sources often adopts a two-step approach of "model building-optimization solution". The former is usually based on power flow equations and operating constraints to build a planning mathematical model with comprehensive objectives such as minimizing network loss, minimizing voltage deviation, and minimizing investment and operating costs. The latter usually uses heuristic or intelligent optimization algorithms to jointly optimize "location and capacity determination".

[0004] However, traditional methods require repeated power flow calculations when verifying the feasibility of candidate schemes for distributed generation location and capacity determination, which leads to increased computational load and low solution efficiency. In addition, common penalty functions or empirical weighting methods lack specificity for different constraints such as voltage over-limit and branch overload, resulting in a high proportion of infeasible solutions and insufficient convergence stability. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for the location and sizing of distributed power sources that can improve solution efficiency and convergence stability, in order to address the above-mentioned technical problems.

[0006] In a first aspect, this application provides a method for addressing and sizing distributed power sources, comprising:

[0007] Transform the distribution network into a network structure that includes nodes and branches;

[0008] Based on the deviation between the power loss of each branch when it is not connected to the distributed power source and the power loss when it is connected to the distributed power source during a preset time period, as well as the deviation between the actual voltage of each node when it is not connected to the distributed power source and the actual voltage when it is connected to the distributed power source, an optimization objective function is constructed.

[0009] Each node is configured with a selection probability, which characterizes the likelihood that the corresponding node will be selected as the access node of the distributed power source in the current iteration.

[0010] Based on the selection probability of each node, a predetermined number of different nodes are selected from all nodes to form candidate site selection schemes. Based on the optimization objective function and power flow algorithm, the installed capacity matched by each node in the candidate site selection scheme and the objective function value used to characterize the merits of the candidate site selection scheme are obtained. Based on the installed capacity matched by each node in the candidate site selection scheme, the candidate site selection scheme is evaluated through a feasible region boundary learning model to obtain the minimum operating margin used to characterize the feasibility of the candidate site selection scheme. Based on the corresponding minimum operating margin and objective function value of each candidate site selection scheme, multiple candidate site selection schemes are screened to obtain the first intermediate site selection scheme.

[0011] Based on the minimum operating margin and objective function value of the first intermediate location scheme, update the selection probability of the node, return the selection probability of each node, select a preset number of different nodes from all nodes to form a candidate location scheme, and continue to execute until the preset conditions are met to obtain the second intermediate location scheme.

[0012] Based on the obtained second intermediate site selection scheme, the final site selection scheme is obtained, and the site selection and capacity determination are performed based on the final site selection scheme and the installed capacity matched by each node in the final site selection scheme.

[0013] In one embodiment, based on the selection probability of each node, a preset number of different nodes are selected from all nodes to form a candidate location scheme, including:

[0014] Normalize the selection probability of all nodes to obtain the corresponding sampling weight for each node;

[0015] Based on the corresponding sampling weight of each node, a preset number of different nodes are selected sequentially from all nodes to form a candidate location scheme; the selected nodes are put back, and a preset number of different nodes are selected sequentially from all nodes to form a new candidate location scheme. The selection process is repeated until multiple candidate location schemes are obtained.

[0016] In one embodiment, before updating the selection probability of a node based on the minimum operational margin and objective function value corresponding to the first intermediate location scheme, the method further includes:

[0017] For candidate site selection schemes that were not selected as intermediate site selection schemes, if the minimum operating margin of the candidate site selection scheme is less than 0 and the difference between it and 0 is less than a preset value, a repair process is performed on the candidate site selection scheme. This includes determining whether there are any nodes in the candidate site selection scheme whose actual voltage exceeds the upper limit or falls below the lower limit. If there are any nodes whose actual voltage exceeds the upper limit or falls below the lower limit, the installed capacity matched to the corresponding node is adjusted. It also includes determining whether there are any branches in the candidate site selection scheme whose actual current effective value exceeds the maximum current carrying capacity. If there are any branches whose actual current effective value exceeds the maximum current carrying capacity, the reactive power output of the upstream and downstream nodes of the corresponding branch is adjusted to reduce the actual current effective value of the branch.

[0018] After the above-mentioned repair process is completed, the candidate site selection schemes are repaired. If the candidate site selection schemes pass the screening, they are used as intermediate site selection schemes.

[0019] In one embodiment, the node selection probability is updated based on the minimum operational margin and objective function value corresponding to the first intermediate location scheme, including:

[0020] Based on the minimum operating margin and objective function value of the first intermediate location scheme, the corresponding scheme weights of the first intermediate location scheme are determined; the magnitude of the scheme weights is negatively correlated with the objective function value and positively correlated with the minimum operating margin.

[0021] Based on the number of times a node is selected in the first intermediate location scheme and the corresponding scheme weight of the first intermediate location scheme, obtain the weighted occurrence count of the node; according to the cross-entropy update rule, update the selection probability of the node according to the weighted occurrence count of the node.

[0022] In one embodiment, according to the cross-entropy update rule, the selection probability of a node is updated based on its weighted occurrence count, including:

[0023] According to the cross-entropy update rule, the selection probability of a node is recalculated based on its weighted occurrence count.

[0024] Based on the update coefficients, the recalculated selection probability of a node is integrated with the selection probability of the node in the previous iteration to obtain the corresponding selection probability of the node.

[0025] In one embodiment, the preset conditions include that the change in the comprehensive objective function value of a consecutive preset number of rounds does not exceed a preset change or the total number of iterations reaches a preset number of rounds; the comprehensive objective function value of each round is obtained by integrating the objective function values ​​of the intermediate location schemes under each round.

[0026] Secondly, this application also provides an addressing and calibrating device for distributed power sources, comprising:

[0027] The conversion module is used to convert the distribution network into a network structure that includes nodes and branches;

[0028] The module is used to construct an optimization objective function based on the deviation between the power loss of each branch when it is not connected to the distributed power source and the power loss when it is connected to the distributed power source under a preset time period, as well as the deviation between the actual voltage of each node when it is not connected to the distributed power source and the actual voltage when it is connected to the distributed power source.

[0029] The configuration module is used to configure the selection probability for each node. The selection probability is used to characterize the probability that the corresponding node will be selected as the access node of the distributed power source in the current iteration.

[0030] The filtering module is used to select a preset number of different nodes from all nodes based on the selection probability of each node to form a candidate site selection scheme; based on the optimization objective function and power flow algorithm, it obtains the installed capacity matched by each node in the candidate site selection scheme and the objective function value used to characterize the merits of the candidate site selection scheme; based on the installed capacity matched by each node in the candidate site selection scheme, it evaluates the candidate site selection scheme through a feasible region boundary learning model to obtain the minimum operating margin used to characterize the feasibility of the candidate site selection scheme; based on the corresponding minimum operating margin and objective function value of each candidate site selection scheme, it filters multiple candidate site selection schemes to obtain the first intermediate site selection scheme;

[0031] The update module is used to update the selection probability of the nodes based on the minimum operating margin and objective function value of the first intermediate location scheme, return the selection probability of each node, select a preset number of different nodes from all nodes to form a candidate location scheme, and continue to execute the steps until the preset conditions are met to obtain the second intermediate location scheme.

[0032] The acquisition module is used to obtain the final location scheme based on the obtained second intermediate location scheme, and to perform location and capacity determination based on the final location scheme and the installed capacity matched by each node in the final location scheme.

[0033] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0034] Transform the distribution network into a network structure that includes nodes and branches;

[0035] Based on the deviation between the power loss of each branch when it is not connected to the distributed power source and the power loss when it is connected to the distributed power source during a preset time period, as well as the deviation between the actual voltage of each node when it is not connected to the distributed power source and the actual voltage when it is connected to the distributed power source, an optimization objective function is constructed.

[0036] Each node is configured with a selection probability, which characterizes the likelihood that the corresponding node will be selected as the access node of the distributed power source in the current iteration.

[0037] Based on the selection probability of each node, a predetermined number of different nodes are selected from all nodes to form candidate site selection schemes. Based on the optimization objective function and power flow algorithm, the installed capacity matched by each node in the candidate site selection scheme and the objective function value used to characterize the merits of the candidate site selection scheme are obtained. Based on the installed capacity matched by each node in the candidate site selection scheme, the candidate site selection scheme is evaluated through a feasible region boundary learning model to obtain the minimum operating margin used to characterize the feasibility of the candidate site selection scheme. Based on the corresponding minimum operating margin and objective function value of each candidate site selection scheme, multiple candidate site selection schemes are screened to obtain the first intermediate site selection scheme.

[0038] Based on the minimum operating margin and objective function value of the first intermediate location scheme, update the selection probability of the node, return the selection probability of each node, select a preset number of different nodes from all nodes to form a candidate location scheme, and continue to execute until the preset conditions are met to obtain the second intermediate location scheme.

[0039] Based on the obtained second intermediate site selection scheme, the final site selection scheme is obtained, and the site selection and capacity determination are performed based on the final site selection scheme and the installed capacity matched by each node in the final site selection scheme.

[0040] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0041] Transform the distribution network into a network structure that includes nodes and branches;

[0042] Based on the deviation between the power loss of each branch when it is not connected to the distributed power source and the power loss when it is connected to the distributed power source during a preset time period, as well as the deviation between the actual voltage of each node when it is not connected to the distributed power source and the actual voltage when it is connected to the distributed power source, an optimization objective function is constructed.

[0043] Each node is configured with a selection probability, which characterizes the likelihood that the corresponding node will be selected as the access node of the distributed power source in the current iteration.

[0044] Based on the selection probability of each node, a predetermined number of different nodes are selected from all nodes to form candidate site selection schemes. Based on the optimization objective function and power flow algorithm, the installed capacity matched by each node in the candidate site selection scheme and the objective function value used to characterize the merits of the candidate site selection scheme are obtained. Based on the installed capacity matched by each node in the candidate site selection scheme, the candidate site selection scheme is evaluated through a feasible region boundary learning model to obtain the minimum operating margin used to characterize the feasibility of the candidate site selection scheme. Based on the corresponding minimum operating margin and objective function value of each candidate site selection scheme, multiple candidate site selection schemes are screened to obtain the first intermediate site selection scheme.

[0045] Based on the minimum operating margin and objective function value of the first intermediate location scheme, update the selection probability of the node, return the selection probability of each node, select a preset number of different nodes from all nodes to form a candidate location scheme, and continue to execute until the preset conditions are met to obtain the second intermediate location scheme.

[0046] Based on the obtained second intermediate site selection scheme, the final site selection scheme is obtained, and the site selection and capacity determination are performed based on the final site selection scheme and the installed capacity matched by each node in the final site selection scheme.

[0047] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0048] Transform the distribution network into a network structure that includes nodes and branches;

[0049] Based on the deviation between the power loss of each branch when it is not connected to the distributed power source and the power loss when it is connected to the distributed power source during a preset time period, as well as the deviation between the actual voltage of each node when it is not connected to the distributed power source and the actual voltage when it is connected to the distributed power source, an optimization objective function is constructed.

[0050] Each node is configured with a selection probability, which characterizes the likelihood that the corresponding node will be selected as the access node of the distributed power source in the current iteration.

[0051] Based on the selection probability of each node, a predetermined number of different nodes are selected from all nodes to form candidate site selection schemes. Based on the optimization objective function and power flow algorithm, the installed capacity matched by each node in the candidate site selection scheme and the objective function value used to characterize the merits of the candidate site selection scheme are obtained. Based on the installed capacity matched by each node in the candidate site selection scheme, the candidate site selection scheme is evaluated through a feasible region boundary learning model to obtain the minimum operating margin used to characterize the feasibility of the candidate site selection scheme. Based on the corresponding minimum operating margin and objective function value of each candidate site selection scheme, multiple candidate site selection schemes are screened to obtain the first intermediate site selection scheme.

[0052] Based on the minimum operating margin and objective function value of the first intermediate location scheme, update the selection probability of the node, return the selection probability of each node, select a preset number of different nodes from all nodes to form a candidate location scheme, and continue to execute until the preset conditions are met to obtain the second intermediate location scheme.

[0053] Based on the obtained second intermediate site selection scheme, the final site selection scheme is obtained, and the site selection and capacity determination are performed based on the final site selection scheme and the installed capacity matched by each node in the final site selection scheme.

[0054] The aforementioned distributed power source location and capacity determination method, apparatus, computer equipment, computer-readable storage medium, and computer program product, by constructing an optimization objective function based on the power loss deviation and actual voltage deviation of each branch and node, can simultaneously ensure the global optimality of the location and capacity determination results. By configuring selection probabilities for each node and randomly generating candidate location schemes during the iteration process, the search range can be continuously expanded, avoiding the search process from prematurely falling into local optima. By introducing a feasible region boundary learning model to calculate the minimum operating margin, the feasibility of candidate schemes can be directly quantitatively evaluated, thereby eliminating obviously infeasible schemes in the early stages of optimization and effectively improving the overall solution efficiency of the algorithm. By updating the corresponding selection probabilities of nodes based on the minimum operating margin of the first intermediate location scheme and the objective function value, the iteration can be guided to converge towards a better search direction, improving the overall search efficiency. The final location and capacity determination scheme can effectively reduce the network loss of the distribution network and improve the voltage operation quality of the distribution network, adapting to the needs of different distribution network planning scenarios. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is an application environment diagram of the addressing and sizing method for distributed power sources in one embodiment;

[0057] Figure 2 This is a flowchart illustrating the addressing and sizing method for a distributed power source in one embodiment.

[0058] Figure 3 This is a flowchart illustrating the addressing and sizing method for a distributed power source in another embodiment;

[0059] Figure 4 This is a topology diagram of the distribution network structure for a distributed power source addressing and sizing method in one embodiment;

[0060] Figure 5 This is a structural block diagram of the addressing and calibrating device for a distributed power source in one embodiment;

[0061] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0063] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0064] The distributed power source addressing and capacity determination method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on a cloud or other network server. Specifically, terminal 102 or server 104 completes a distributed power supply addressing and capacity determination method, which includes:

[0065] Transform the distribution network into a network structure that includes nodes and branches;

[0066] Based on the deviation between the power loss of each branch when it is not connected to the distributed power source and the power loss when it is connected to the distributed power source during a preset time period, as well as the deviation between the actual voltage of each node when it is not connected to the distributed power source and the actual voltage when it is connected to the distributed power source, an optimization objective function is constructed.

[0067] Each node is configured with a selection probability, which characterizes the likelihood that the corresponding node will be selected as the access node of the distributed power source in the current iteration.

[0068] Based on the selection probability of each node, a predetermined number of different nodes are selected from all nodes to form candidate site selection schemes. Based on the optimization objective function and power flow algorithm, the installed capacity matched by each node in the candidate site selection scheme and the objective function value used to characterize the merits of the candidate site selection scheme are obtained. Based on the installed capacity matched by each node in the candidate site selection scheme, the candidate site selection scheme is evaluated through a feasible region boundary learning model to obtain the minimum operating margin used to characterize the feasibility of the candidate site selection scheme. Based on the corresponding minimum operating margin and objective function value of each candidate site selection scheme, multiple candidate site selection schemes are screened to obtain the first intermediate site selection scheme.

[0069] Based on the minimum operating margin and objective function value of the first intermediate location scheme, update the selection probability of the node, return the selection probability of each node, select a preset number of different nodes from all nodes to form a candidate location scheme, and continue to execute until the preset conditions are met to obtain the second intermediate location scheme.

[0070] Based on the obtained second intermediate site selection scheme, the final site selection scheme is obtained, and the site selection and capacity determination are performed based on the final site selection scheme and the installed capacity matched by each node in the final site selection scheme.

[0071] Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, and projection equipment. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0072] In one exemplary embodiment, such as Figure 2 As shown, a method for addressing and sizing distributed power sources is provided, which can be applied to... Figure 1 Taking the server in the example, the explanation includes the following steps 202 to 212. Wherein:

[0073] Step 202: Transform the distribution network into a network structure that includes nodes and branches.

[0074] For example, the distribution network can be represented as a generalized graph consisting of nodes and branches. , where each node All can be represented as generalized graphs One of the nodes, For generalized graph The edges connecting nodes are called branches.

[0075] Step 204: Based on the deviation between the power loss of each branch when it is not connected to the distributed power source and the power loss when it is connected to the distributed power source during the preset time period, and the deviation between the actual voltage of each node when it is not connected to the distributed power source and the actual voltage when it is connected to the distributed power source, construct an optimization objective function.

[0076] The objective function is used to optimize network losses and voltage deviations in the distribution network to minimize them, thus providing a data foundation for selecting the optimal location and capacity scheme of distributed generation based on the objective function.

[0077] The preset time period can be selected from one typical day each of the four seasons (spring, summer, autumn, and winter), and each typical day is divided into 24 time periods, thus forming a 96-hour operating cycle. Each preset time period... It can be 1 hour.

[0078] For example, each branch is started by the upstream node. and downstream nodes Its equivalent impedance can be expressed as:

[0079]

[0080] in, and These are the equivalent resistance and equivalent impedance, respectively.

[0081] Specifically, at the node Without access to distributed power sources, the node Within the preset time period The complex power can be expressed as:

[0082]

[0083] in, and They are nodes The active load power and reactive load power.

[0084] At the node When connected to a distributed power source, the node Within the preset time period The complex power injected into the distribution network system can be expressed as:

[0085]

[0086] in, and They are nodes The active and reactive power injected into the distribution network system. Additionally, nodes... The maximum active power and reactive power allowed to be connected are respectively and And satisfy:

[0087]

[0088]

[0089] in, It is a binary variable used to represent nodes. Whether to install distributed power supply, when the node When installing distributed power sources Otherwise, it is 0.

[0090] Furthermore, nodes The net power requirement is the difference between the load and the distributed generation injection, which can be expressed as:

[0091]

[0092] And under steady-state operating conditions, the node The complex power, voltage, and current satisfy the following:

[0093]

[0094] Therefore, node The injected current is:

[0095]

[0096] in, For conjugate operations on complex numbers.

[0097] For example, in a distribution network, a branch The current on the node is obtained by summing the current injected into its downstream nodes, that is:

[0098]

[0099] in, Represents a node The sum of the currents in all downstream branches.

[0100] Furthermore, the node voltage is recursively calculated along the feeder direction, satisfying:

[0101]

[0102] Furthermore, to ensure the safe operation of the power distribution network system, at all times... Internal requirements must meet node voltage requirements Constraints, namely:

[0103]

[0104] in, and These are the lower and upper limits of the voltage, respectively.

[0105] branch current RMS value Must meet:

[0106]

[0107] For example, under three-phase equilibrium conditions, the branch During the period The three-phase active power loss is given by resistance and current, that is:

[0108]

[0109] Therefore, the cumulative active power loss of the distribution network system within the preset entire operating cycle, i.e., within 96 hours, is:

[0110]

[0111] Meanwhile, to reflect the quality of voltage operation, the cumulative voltage deviation index within 96 hours is as follows:

[0112]

[0113] in, This is the reference voltage.

[0114] For example, a baseline operating condition is introduced. and Dimensionless processing is performed, that is, baseline values ​​are defined separately when no distributed power source is connected. and And the corresponding value after connecting to distributed power sources. and Then the dimensionless objective is defined as:

[0115]

[0116] Based on this, taking into account both network loss and voltage quality, the objective function is defined as follows:

[0117]

[0118] in, and These are weighting coefficients used to balance the proportions of network loss and voltage deviation in the objective function. It should be noted that... and The setting can be adjusted according to the planning focus. For example, α can be appropriately increased in scenarios where the primary goal is to reduce network losses, while β can be appropriately increased in scenarios where the primary goal is to improve voltage quality, while also satisfying the following requirements: .

[0119] Step 206: Configure the selection probability for each node. The selection probability is used to characterize the probability that the corresponding node will be selected as the access node of the distributed power source in the current iteration.

[0120] For example, configure the selection probability for each node. This allows us to define a node selection probability parameter vector. .in, This indicates the node in the current iteration state. The probability parameter for being selected as a distributed power source access node is used to guide the random sampling generation of candidate site selection schemes.

[0121] Furthermore, setting upper and lower limits for the selection probability is to prevent the probability parameter from converging prematurely or degrading during iteration, and to control the selection probability. The upper and lower limit constraints are represented as follows:

[0122]

[0123] in, This is the minimum probability lower bound, used to ensure that all nodes have a possibility of being selected during the search process; The maximum probability cap is used to prevent a single node from being over-strengthened in early iterations.

[0124] Step 208: Based on the selection probability of each node, select a preset number of different nodes from all nodes to form candidate site selection schemes; based on the optimization objective function and power flow algorithm, obtain the installed capacity matched by each node in the candidate site selection schemes and the objective function value used to characterize the merits of the candidate site selection schemes; based on the installed capacity matched by each node in the candidate site selection schemes, evaluate the candidate site selection schemes through a feasible region boundary learning model to obtain the minimum operating margin used to characterize the feasibility of the candidate site selection schemes; based on the corresponding minimum operating margin and objective function value of each candidate site selection scheme, screen multiple candidate site selection schemes to obtain the first intermediate site selection scheme.

[0125] The first intermediate location scheme is the intermediate location scheme obtained during the iteration process.

[0126] For example, the number of distributed power supply units planned to be installed is set to ,but

[0127]

[0128] Among them, binary variables Represents a node Whether to install distributed power. When the node... When installing distributed power sources When node When no distributed power source is installed, .

[0129] For example, based on the selection probability of each node Selecting without replacement from all nodes These are different nodes, that is, this The binary variables of the first node are all 1, and the binary variables of the remaining nodes are all 0, thus obtaining a candidate addressing scheme. By repeating this selection operation multiple times, multiple candidate addressing schemes can be formed.

[0130] In obtaining candidate site selection schemes Subsequently, power flow calculations can be used to obtain the node voltage and branch current distributions, thereby enabling the calculation of the corresponding values ​​for all installed nodes. and ,Should and This refers to the installed capacity matched to each node in the candidate site selection scheme. (In the capacity variable...) and Under the premise of meeting operational and capacity constraints, further optimization is performed based on the installed capacity and the objective function. Calculate the optimal objective function value for the given location and volume. , can be represented as:

[0131]

[0132] By mapping this candidate site selection scheme to a minimum target value with a clear physical meaning It can enable collaborative evaluation between site selection decisions and capacity allocation.

[0133] Furthermore, a feasible region boundary learning model is introduced to evaluate the margin of candidate site selection schemes under operational constraints, thereby obtaining the minimum operational margin. This minimum operating margin This indicates whether the capacity configuration meets voltage and current carrying capacity constraints. The minimum operating margin is also included. Represented as:

[0134]

[0135] And when When, it indicates that the capacity configuration meets voltage and current carrying constraints; when When, it indicates that there is an out-of-bounds error, and This indicates the severity of the most serious constraint violation.

[0136] Based on the minimum operational margin corresponding to each candidate site selection scheme and the optimal objective function value Multiple candidate site selection schemes are screened to obtain an intermediate site selection scheme.

[0137] Step 210: Based on the minimum operating margin and objective function value of the first intermediate location scheme, update the selection probability of the node, return the selection probability of each node, select a preset number of different nodes from all nodes to form a candidate location scheme, and continue to execute until the preset conditions are met to obtain the second intermediate location scheme.

[0138] The second intermediate location scheme is the intermediate location scheme selected when the iteration terminates.

[0139] For example, based on the minimum operational margin and objective function value corresponding to the first intermediate location scheme, the probability parameters of the nodes are corrected according to the cross-entropy update rule to obtain the updated node selection probabilities. Based on the updated node selection probabilities, a new round of iteration is performed, that is, selecting nodes again without replacement from all nodes. The process involves identifying several different nodes to form multiple new candidate location schemes. This process is repeated after obtaining the candidate location schemes until the iteration terminates. After the iteration terminates, the intermediate location scheme selected from the newly formed candidate location schemes is used as the second intermediate location scheme.

[0140] It should be noted that the selection process for the first intermediate location scheme and the second intermediate location scheme is the same. Here, the first intermediate location scheme is mainly used to update the node probability, and the second intermediate location scheme is mainly used to select the final location scheme in the subsequent screening.

[0141] Step 212: Based on the obtained second intermediate location scheme, obtain the final location scheme, and perform location and capacity determination based on the final location scheme and the installed capacity matched by each node in the final location scheme.

[0142] For example, after the iteration terminates, the scheme with the smallest objective function among all the second intermediate location schemes that satisfy the operating constraints is selected as the final location scheme, and the installed capacity matched by each node in the scheme is obtained, thereby obtaining the given number of distributed power sources. The optimal addressing and occupancy results under the given conditions.

[0143] In the aforementioned distributed generation location and capacity determination method, by constructing an optimization objective function based on the power loss deviation and actual voltage deviation of each branch and node, the global optimality of both location and capacity determination results can be guaranteed simultaneously. By configuring selection probabilities for each node and randomly generating candidate location schemes during the iteration process, the search range can be continuously expanded, avoiding the search process from getting trapped in local optima too early. By introducing a feasible region boundary learning model to calculate the minimum operating margin, the feasibility of candidate schemes can be directly quantitatively evaluated, thereby eliminating obviously infeasible schemes in the early stages of optimization and effectively improving the overall solution efficiency of the algorithm. By updating the corresponding selection probabilities of nodes based on the minimum operating margin of the first intermediate location scheme and the objective function value, the iteration can be guided to converge towards a better search direction, improving the overall search efficiency. The final location and capacity determination scheme can effectively reduce the network loss of the distribution network and improve the voltage operation quality of the distribution network, adapting to the needs of different distribution network planning scenarios.

[0144] In one embodiment, a predetermined number of different nodes are selected from all nodes based on the selection probability of each node to form a candidate location scheme. This includes: normalizing the selection probabilities of all nodes to obtain the corresponding sampling weight for each node; selecting a predetermined number of different nodes from all nodes sequentially based on the corresponding sampling weight for each node to form a candidate location scheme; replacing the selected nodes and selecting a predetermined number of different nodes from all nodes again to form a new candidate location scheme, repeating the selection process until multiple candidate location schemes are obtained.

[0145] For example, a probability is selected for each node. Its satisfaction ,and A smaller positive number can be chosen. Less than 1. Normalizing the selection probabilities of all nodes yields the sampling weight for each node, which can be expressed as:

[0146]

[0147] To ensure that the proposed candidate site selection schemes meet the requirements Based on the corresponding sampling weight of each node, nodes are selected sequentially without replacement from all nodes. The number of distinct nodes, and the number of nodes... Secondary selection node The conditional probability is:

[0148]

[0149] Based on the selected Construct a binary addressing vector from 1 distinct nodes. This satisfies the quantity constraint and forms a candidate site selection scheme.

[0150] For example, the selected node is replaced, and then a new node is selected from all nodes. There are several different nodes, and the one selected this time... Different nodes compared to the previously selected ones Different nodes are not completely identical, thus forming new candidate site selection schemes.

[0151] In each iteration, the process of selecting candidate location schemes is repeated to generate... One candidate site selection scheme.

[0152] In this embodiment, by normalizing the selection probabilities of all nodes, the sampling weights are ensured to be 1, which meets the preset requirement for the number of installable distributed power sources. The sampling without replacement method ensures that the generated candidate site selection schemes naturally meet the total number constraint. By repeatedly selecting multiple candidate schemes, the sample diversity of each iteration can be guaranteed, thereby providing a sample basis for subsequent probability updates.

[0153] In one embodiment, before updating the selection probability of a node based on the minimum operating margin and objective function value of the first intermediate location scheme, the method further includes: for candidate location schemes not selected as intermediate location schemes, if the minimum operating margin of the candidate location scheme is less than 0 and the difference between it and 0 is less than a preset value, performing a repair process on the candidate location scheme; wherein, it is determined whether there are any nodes in the candidate location scheme whose actual voltage exceeds the upper limit or falls below the lower limit, and if there are any nodes whose actual voltage exceeds the upper limit or falls below the lower limit, the installed capacity matched to the corresponding node is adjusted; it is determined whether there are any branches in the candidate location scheme whose effective value of actual current exceeds the maximum current carrying capacity, and if there are any branches whose effective value of actual current exceeds the maximum current carrying capacity, the reactive power output of the upstream and downstream nodes of the corresponding branch is adjusted to reduce the effective value of the actual current of the branch; after repairing the candidate location scheme through the above repair process, if the candidate location scheme passes the screening, the candidate location scheme is used as an intermediate location scheme.

[0154] For example, based on the minimum safety margin of the candidate site selection schemes, if a node voltage exceeds the upper limit or falls below the lower limit in a candidate site selection scheme, the installed capacity of the relevant node is targeted for repair according to the out-of-bounds type and the location of the out-of-bounds node, so that the repaired node voltage meets the node voltage constraint.

[0155] If the effective value of the actual current of a branch exceeds the maximum current carrying capacity in the candidate site selection scheme, the reactive power of the relevant node is targeted to be repaired according to the boundary type and the location of the boundary node, so that the effective value of the actual current of the repaired branch is less than the maximum current carrying capacity.

[0156] Based on this, when a voltage limit is exceeded or a branch is overloaded in a candidate location scheme, it is repaired in a targeted manner, so that the repaired candidate location scheme is backed into the feasible region instead of being discarded. Thus, the repaired candidate location scheme that has passed the screening is used as an intermediate location scheme.

[0157] In this embodiment, by performing targeted repair on candidate addressing schemes whose minimum operating margin does not meet the preset conditions, an intermediate addressing scheme can be obtained, which can improve the search efficiency of the overall algorithm and increase the probability of finding the globally optimal solution.

[0158] In one embodiment, updating the selection probability of a node based on the minimum operational margin and objective function value of the first intermediate location scheme includes: determining the scheme weight of the first intermediate location scheme based on the minimum operational margin and objective function value of the first intermediate location scheme; the scheme weight is negatively correlated with the objective function value and positively correlated with the minimum operational margin; obtaining the weighted occurrence count of a node based on the number of times a node is selected in the first intermediate location scheme and the scheme weight of the first intermediate location scheme; and updating the selection probability of a node according to the weighted occurrence count of the node in accordance with the cross-entropy update rule.

[0159] For example, for each iteration generated There are several candidate site selection schemes, and for each candidate site selection scheme... Calculate the corresponding optimal objective function value and minimum safety margin Then, the mean and standard deviation of the optimal objective function values ​​for all candidate site selection schemes are calculated, i.e.

[0160]

[0161]

[0162] All candidate site selection schemes are arranged according to Sort by size from smallest to largest, then sort by size from smallest to largest. The updated set consists of candidate site selection schemes. The first intermediate location scheme is obtained, and the set is... The first intermediate location scheme in the definition of weights, i.e.

[0163]

[0164] in, For this iteration, the minimum objective function value among the candidate location schemes; parameters Used to adjust the degree of influence of differences in the objective function; parameters The severity of penalties used to reflect the degree of violation of operational constraints.

[0165] Based on the number of times each node is selected in the first intermediate location scheme and the corresponding scheme weight of the first intermediate location scheme. Obtain the weighted frequency of each node. Then, according to the cross-entropy update rule, update the selection probability of each node based on its weighted frequency.

[0166] In this embodiment, by updating the selection probability of nodes using the objective function value and the running margin, it is possible to ensure that the probability update moves in a direction that is more conducive to finding the optimal solution, and to avoid the algorithm converging to a local optimum too early, thereby obtaining the optimal addressing and sizing result.

[0167] In one embodiment, according to the cross-entropy update rule, the selection probability of a node is updated based on the weighted occurrence count of the node, including: recalculating the selection probability of the node based on the weighted occurrence count of the node according to the cross-entropy update rule; and integrating the recalculated selection probability of the node with the selection probability of the node in the previous iteration based on the update coefficient to obtain the selection probability of the node.

[0168] For example, a set of candidate location schemes with better objective function values ​​and better satisfaction of operational constraints is formed. Then, the selection probability of each node is corrected according to the cross-entropy update rule, i.e.

[0169]

[0170] in, To update the coefficients, this is used to balance the influence between historical probability information and the current iteration's statistical results. When When the probability is smaller, the probability update process is smoother, which helps maintain search stability; when When the probability is larger, the probability update responds faster to the current best solution, which helps to speed up the convergence.

[0171] In this embodiment, by recalculating the selection probability of a node based on its weighted occurrence count and integrating it with the selection probability of the node in the previous iteration, a new node selection probability is obtained. This preserves the information of good nodes and thus effectively improves the reliability of the final location and capacity determination result. In addition, by introducing an update coefficient, a balance can be found between maintaining search stability and accelerating convergence speed, thereby improving the overall operating efficiency and result stability of the location and capacity determination method.

[0172] In one embodiment, the preset conditions include the change in the comprehensive objective function value over a preset number of consecutive rounds not exceeding a preset change or the total number of iterations reaching a preset number of rounds; the comprehensive objective function value for each round is obtained by integrating the objective function values ​​of the intermediate location schemes under each round.

[0173] For example, the iteration terminates if the change in the comprehensive objective function value over a preset number of iterations does not exceed a preset change or the total number of iterations reaches a preset number. After the iteration terminates, the candidate scheme with the smallest objective function is selected from all candidate schemes that satisfy the operational constraints, as the one with the given number of distributed power sources. The optimal addressing and ductility result under the given conditions, i.e.

[0174]

[0175]

[0176] Based on this, the final number of distributed power sources is obtained. The planning results of the optimal access node location, corresponding installed capacity, and operational margin under the given conditions.

[0177] In this embodiment, by setting a termination condition to control the iteration process, it is possible to ensure that the results are output in a timely manner when the algorithm converges to sufficient accuracy. This avoids premature termination, which would result in suboptimal addressing and sizing results, and also avoids repeated iterations that waste computational resources, thereby improving computational efficiency and accuracy.

[0178] like Figure 3 As shown, a specific embodiment illustrates the addressing and sizing method for distributed power sources, including:

[0179] Step S1: Input the distribution network topology, node load parameters, branch parameters, and operational constraints such as node voltage upper and lower limits and line current carrying capacity, and set the number of distributed generation sources to be installed. and related algorithm parameters.

[0180] Step S2: Initialize the node selection probability parameters to describe the initial probability state of each node being selected as a distributed power supply access node; based on this, a sampling method without replacement based on the probability model is used to generate candidate site selection schemes that meet the constraints on the number of distributed power supply installations.

[0181] Step S3: For each group of candidate site selection schemes, further perform the capacity configuration and operational feasibility assessment process. Use the feasible domain boundary learning model to quickly identify node voltage and line current carrying capacity. When a candidate scheme violates operational constraints, perform targeted repair on the installed capacity or reactive power of the relevant nodes according to the boundary violation type and the location of the boundary violation node, so that the scheme returns to the allowable operating range.

[0182] Step S4: After obtaining candidate site selection schemes that meet the operational constraints, calculate the dimensionless comprehensive objective function value under multi-time period operation conditions, and update the node selection probability parameters based on the objective function level and operational margin.

[0183] Step S5: The above process is executed iteratively until the preset convergence condition is met or the maximum number of iterations is reached. Finally, the planning results, such as the optimal access node location, corresponding installed capacity, and operational margin, are output under the given number of distributed power supply installations.

[0184] Specifically, the topology of the distribution network is as follows: Figure 4 As shown, the total active load power of the distribution network is set to 3415.0kW, the total reactive load power is set to 2300.0kvar, and the voltage reference value is set to 12.66kV. To reflect the impact of load changes in different seasons on the planning results, one typical day is selected from spring, summer, autumn, and winter, and each typical day is calculated in 24 time periods, totaling 96 hours.

[0185] In addition, the active power loss index and voltage deviation index in the comprehensive objective function are set with equal weights. The upper and lower limits of the node selection probability parameter are respectively taken as follows: , To avoid premature convergence during the search process, probability parameters are selected to update the coefficients. A value of 0.7 is used to balance historical probability information with the current iteration result. In the calculation of candidate site selection weights, the parameter... , To enhance the suppression effect on schemes that violate operational constraints. Each iteration generates 50 candidate location schemes, and the top 20 candidate location schemes are selected as intermediate location schemes for updating the probability parameters.

[0186] Without the integration of distributed power sources, hourly power flow calculations were performed on a typical 96-hour day across four seasons. The results showed that the total active power loss of the 32 branches of the distribution network within 96 hours was 4094.72 kW, and the total voltage deviation of the 33 nodes within 96 hours was 66.67 pu. Simultaneously, distributed photovoltaic (PV) integration constraints were set: the installed capacity of a single PV power source should not exceed 300 kW, the total installed capacity should not exceed 1.5 MW, and the power factor was set to 0.9.

[0187] When integrating distributed power sources, a set of candidate nodes is first selected based on the annual comprehensive evaluation indicators of the nodes. The top 7 nodes are then selected to form a candidate set (i.e., the candidate set size is 7). The selected nodes, from highest to lowest, are 25, 24, 30, 17, 7, 20, and 8. Subsequently, the installed capacity of each node is determined only within this candidate set, and hourly power flow verification and target indicator evaluation are performed under a typical 96-hour scenario in all four seasons. This yields a set of location and capacity determination schemes that meet the constraints: the installed capacity of nodes 7, 8, 24, and 30 is 300kW, the installed capacity of node 17 is 190.783kW, the installed capacity of node 25 is 97.733kW, and the installed capacity of node 20 is 0, for a total installed capacity of 1488.516kW. Therefore, the cumulative total active power loss of the distribution network within 96 hours is 2994.19kW, and the cumulative total voltage deviation is 48.42pu. Furthermore, in practical applications, the calculated installed capacity is rounded up to match the actual installed capacity of distributed power sources.

[0188] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0189] Based on the same inventive concept, this application also provides a distributed power source addressing and capacity grading device for implementing the above-described distributed power source addressing and capacity grading method. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more distributed power source addressing and capacity grading device embodiments provided below can be found in the limitations of the distributed power source addressing and capacity grading method described above, and will not be repeated here.

[0190] In one exemplary embodiment, such as Figure 5 As shown, a distributed power source addressing and capacity determination device 500 is provided, including: a conversion module 502, a construction module 504, a configuration module 506, a filtering module 508, an update module 510, and an acquisition module 512, wherein:

[0191] The conversion module 502 is used to convert the distribution network into a network structure that includes nodes and branches;

[0192] Module 504 is used to construct an optimization objective function based on the deviation between the power loss of each branch when it is not connected to the distributed power source and the power loss when it is connected to the distributed power source under a preset time period, as well as the deviation between the actual voltage of each node when it is not connected to the distributed power source and the actual voltage when it is connected to the distributed power source.

[0193] Configuration module 506 is used to configure the selection probability for each node. The selection probability is used to characterize the probability that the corresponding node will be selected as the access node of the distributed power source in the current iteration.

[0194] The screening module 508 is used to select a preset number of different nodes from all nodes based on the selection probability of each node to form a candidate site selection scheme; based on the optimization objective function and power flow algorithm, it obtains the installed capacity matched by each node in the candidate site selection scheme and the objective function value used to characterize the merits of the candidate site selection scheme; based on the installed capacity matched by each node in the candidate site selection scheme, it evaluates the candidate site selection scheme through a feasible region boundary learning model to obtain the minimum operating margin used to characterize the feasibility of the candidate site selection scheme; based on the corresponding minimum operating margin and objective function value of each candidate site selection scheme, it screens multiple candidate site selection schemes to obtain a first intermediate site selection scheme;

[0195] The update module 510 is used to update the selection probability of the node based on the minimum operating margin and objective function value of the first intermediate location scheme, return the selection probability of each node, select a preset number of different nodes from all nodes to form a candidate location scheme, and continue to execute the steps until the preset conditions are met to obtain the second intermediate location scheme.

[0196] The acquisition module 512 is used to obtain the final location scheme based on the obtained second intermediate location scheme, and to perform location and capacity determination based on the final location scheme and the installed capacity matched by each node in the final location scheme.

[0197] In one embodiment, the filtering module 508 is further configured to select a preset number of different nodes from all nodes based on the selection probability of each node to form a candidate location scheme, including: normalizing the selection probability of all nodes to obtain the corresponding sampling weight of each node; selecting a preset number of different nodes from all nodes in sequence based on the corresponding sampling weight of each node to form a candidate location scheme; replacing the selected nodes and selecting a preset number of different nodes from all nodes again in sequence to form a new candidate location scheme, repeating the selection process until multiple candidate location schemes are obtained.

[0198] In one embodiment, before updating the selection probability of a node based on the minimum operating margin and objective function value of the first intermediate location scheme, the update module 510 further includes: for candidate location schemes not selected as intermediate location schemes, if the minimum operating margin of the candidate location scheme is less than 0 and the difference between it and 0 is less than a preset value, performing a repair process on the candidate location scheme; wherein, it is determined whether there are nodes in the candidate location scheme whose actual voltage exceeds the upper limit or is lower than the lower limit, and if there are nodes whose actual voltage exceeds the upper limit or is lower than the lower limit, the installed capacity matched to the corresponding node is adjusted; it is determined whether there are branches in the candidate location scheme whose effective value of actual current exceeds the maximum current carrying capacity, and if there are branches whose effective value of actual current exceeds the maximum current carrying capacity, the reactive power output of the upstream and downstream nodes of the corresponding branch is adjusted to reduce the effective value of the actual current of the branch; after the candidate location scheme is repaired through the above repair process, if the candidate location scheme passes the screening, the candidate location scheme is used as an intermediate location scheme.

[0199] In one embodiment, the update module 510 is further configured to update the selection probability of a node based on the minimum operating margin and objective function value of the first intermediate location scheme, including: determining the scheme weight of the first intermediate location scheme based on the minimum operating margin and objective function value of the first intermediate location scheme; the magnitude of the scheme weight is negatively correlated with the objective function value and positively correlated with the minimum operating margin; obtaining the weighted occurrence count of a node based on the number of times a node is selected in the first intermediate location scheme and the scheme weight of the first intermediate location scheme; and updating the selection probability of a node according to the weighted occurrence count of the node in accordance with the cross-entropy update rule.

[0200] In one embodiment, the update module 510 is further configured to update the selection probability of a node according to the weighted occurrence count of the node in accordance with the cross-entropy update rule, including: recalculating the selection probability of the node according to the weighted occurrence count of the node in accordance with the cross-entropy update rule; and integrating the recalculated selection probability of the node with the selection probability of the node in the previous iteration based on the update coefficient to obtain the selection probability of the node.

[0201] In one embodiment, the update module 510 is further configured to preset conditions including that the change in the comprehensive objective function value of a consecutive preset number of rounds does not exceed a preset change or the total number of iterations reaches a preset number of rounds; the comprehensive objective function value of each round is obtained by integrating the objective function values ​​of the intermediate location schemes under each round.

[0202] Each module in the aforementioned distributed power source addressing and calibrating device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0203] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a distributed power supply addressing and sizing method.

[0204] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0205] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0206] Transform the distribution network into a network structure that includes nodes and branches;

[0207] Based on the deviation between the power loss of each branch when it is not connected to the distributed power source and the power loss when it is connected to the distributed power source during a preset time period, as well as the deviation between the actual voltage of each node when it is not connected to the distributed power source and the actual voltage when it is connected to the distributed power source, an optimization objective function is constructed.

[0208] Each node is configured with a selection probability, which characterizes the likelihood that the corresponding node will be selected as the access node of the distributed power source in the current iteration.

[0209] Based on the selection probability of each node, a predetermined number of different nodes are selected from all nodes to form candidate site selection schemes. Based on the optimization objective function and power flow algorithm, the installed capacity matched by each node in the candidate site selection scheme and the objective function value used to characterize the merits of the candidate site selection scheme are obtained. Based on the installed capacity matched by each node in the candidate site selection scheme, the candidate site selection scheme is evaluated through a feasible region boundary learning model to obtain the minimum operating margin used to characterize the feasibility of the candidate site selection scheme. Based on the corresponding minimum operating margin and objective function value of each candidate site selection scheme, multiple candidate site selection schemes are screened to obtain the first intermediate site selection scheme.

[0210] Based on the minimum operating margin and objective function value of the first intermediate location scheme, update the selection probability of the node, return the selection probability of each node, select a preset number of different nodes from all nodes to form a candidate location scheme, and continue to execute until the preset conditions are met to obtain the second intermediate location scheme.

[0211] Based on the intermediate location scheme obtained in the second step, the final location scheme is obtained, and the location and capacity are determined based on the final location scheme and the installed capacity matched by each node in the final location scheme.

[0212] In one embodiment, when the processor executes the computer program, it further implements the following steps: selecting a preset number of different nodes from all nodes based on the selection probability of each node to form a candidate addressing scheme, including: normalizing the selection probabilities of all nodes to obtain the corresponding sampling weight of each node; selecting a preset number of different nodes from all nodes sequentially based on the corresponding sampling weight of each node to form a candidate addressing scheme; replacing the selected nodes and reselecting a preset number of different nodes from all nodes sequentially to form a new candidate addressing scheme, repeating the selection process until multiple candidate addressing schemes are obtained.

[0213] In one embodiment, when the processor executes the computer program, it further implements the following steps: before updating the selection probability of the node based on the minimum operating margin and objective function value corresponding to the first intermediate addressing scheme, the process further includes: for candidate addressing schemes that are not selected as intermediate addressing schemes, if the minimum operating margin of the candidate addressing scheme is less than 0 and the difference between it and 0 is less than a preset value, performing a repair process on the candidate addressing scheme; wherein, it is determined whether there are any nodes in the candidate addressing scheme whose actual voltage exceeds the upper limit or is lower than the lower limit, and if there are any nodes whose actual voltage exceeds the upper limit or is lower than the lower limit, the installed capacity matched to the corresponding node is adjusted; it is determined whether there are any branches in the candidate addressing scheme whose actual current effective value exceeds the maximum current carrying capacity, and if there are any branches whose actual current effective value exceeds the maximum current carrying capacity, the reactive power output of the upstream and downstream nodes of the corresponding branch is adjusted to reduce the actual current effective value of the branch; after the candidate addressing scheme is repaired through the above repair process, if the candidate addressing scheme passes the screening, the candidate addressing scheme is used as an intermediate addressing scheme.

[0214] In one embodiment, when the processor executes the computer program, it further implements the following steps: updating the selection probability of a node based on the minimum operating margin and objective function value corresponding to the first intermediate addressing scheme, including: determining the scheme weight corresponding to the first intermediate addressing scheme based on the minimum operating margin and objective function value corresponding to the first intermediate addressing scheme; the magnitude of the scheme weight is negatively correlated with the objective function value and positively correlated with the minimum operating margin; obtaining the weighted occurrence count of a node based on the number of times a node is selected in the first intermediate addressing scheme and the scheme weight corresponding to the first intermediate addressing scheme; and updating the selection probability of a node according to the weighted occurrence count of the node in accordance with the cross-entropy update rule.

[0215] In one embodiment, when the processor executes the computer program, it further implements the following steps: according to the cross-entropy update rule, update the selection probability of the node according to the weighted occurrence count of the node, including: according to the cross-entropy update rule, recalculate the selection probability of the node according to the weighted occurrence count of the node; and based on the update coefficient, integrate the recalculated selection probability of the node with the selection probability of the node in the previous iteration to obtain the selection probability of the node.

[0216] In one embodiment, when the processor executes the computer program, it further implements the following steps: the preset conditions include the change in the comprehensive objective function value of a consecutive preset number of rounds not exceeding a preset change or the total number of iterations reaching a preset number of rounds; the comprehensive objective function value of each round is obtained by integrating the objective function values ​​of the intermediate addressing schemes under each round.

[0217] The implementation principle and technical effects of the above embodiments are similar to those of the above method embodiments, and will not be repeated here.

[0218] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0219] Transform the distribution network into a network structure that includes nodes and branches;

[0220] Based on the deviation between the power loss of each branch when it is not connected to the distributed power source and the power loss when it is connected to the distributed power source during a preset time period, as well as the deviation between the actual voltage of each node when it is not connected to the distributed power source and the actual voltage when it is connected to the distributed power source, an optimization objective function is constructed.

[0221] Each node is configured with a selection probability, which characterizes the likelihood that the corresponding node will be selected as the access node of the distributed power source in the current iteration.

[0222] Based on the selection probability of each node, a predetermined number of different nodes are selected from all nodes to form candidate site selection schemes. Based on the optimization objective function and power flow algorithm, the installed capacity matched by each node in the candidate site selection scheme and the objective function value used to characterize the merits of the candidate site selection scheme are obtained. Based on the installed capacity matched by each node in the candidate site selection scheme, the candidate site selection scheme is evaluated through a feasible region boundary learning model to obtain the minimum operating margin used to characterize the feasibility of the candidate site selection scheme. Based on the corresponding minimum operating margin and objective function value of each candidate site selection scheme, multiple candidate site selection schemes are screened to obtain the first intermediate site selection scheme.

[0223] Based on the minimum operating margin and objective function value of the first intermediate location scheme, update the selection probability of the node, return the selection probability of each node, select a preset number of different nodes from all nodes to form a candidate location scheme, and continue to execute until the preset conditions are met to obtain the second intermediate location scheme.

[0224] Based on the obtained second intermediate site selection scheme, the final site selection scheme is obtained, and the site selection and capacity determination are performed based on the final site selection scheme and the installed capacity matched by each node in the final site selection scheme.

[0225] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: selecting a preset number of different nodes from all nodes based on the selection probability of each node to form a candidate addressing scheme, including: normalizing the selection probabilities of all nodes to obtain the corresponding sampling weight of each node; selecting a preset number of different nodes from all nodes sequentially based on the corresponding sampling weight of each node to form a candidate addressing scheme; replacing the selected nodes and reselecting a preset number of different nodes from all nodes sequentially to form a new candidate addressing scheme, repeating the selection process until multiple candidate addressing schemes are obtained.

[0226] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: before updating the selection probability of the node based on the minimum operating margin and objective function value corresponding to the first intermediate addressing scheme, it further includes: for candidate addressing schemes that are not selected as intermediate addressing schemes, if the minimum operating margin of the candidate addressing scheme is less than 0 and the difference between it and 0 is less than a preset value, performing a repair process on the candidate addressing scheme; wherein, it is determined whether there are any nodes in the candidate addressing scheme whose actual voltage exceeds the upper limit or is lower than the lower limit, and if there are any nodes whose actual voltage exceeds the upper limit or is lower than the lower limit, the installed capacity matched to the corresponding node is adjusted; it is determined whether there are any branches in the candidate addressing scheme whose actual current effective value exceeds the maximum current carrying capacity, and if there are any branches whose actual current effective value exceeds the maximum current carrying capacity, the reactive power output of the upstream and downstream nodes of the corresponding branch is adjusted to reduce the actual current effective value of the branch; after the candidate addressing scheme is repaired through the above repair process, if the candidate addressing scheme passes the screening, the candidate addressing scheme is used as an intermediate addressing scheme.

[0227] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: updating the selection probability of a node based on the minimum operating margin and objective function value corresponding to the first intermediate addressing scheme, including: determining the scheme weight corresponding to the first intermediate addressing scheme based on the minimum operating margin and objective function value corresponding to the first intermediate addressing scheme; the magnitude of the scheme weight is negatively correlated with the objective function value and positively correlated with the minimum operating margin; obtaining the weighted occurrence count of a node based on the number of times a node is selected in the first intermediate addressing scheme and the scheme weight corresponding to the first intermediate addressing scheme; and updating the selection probability of a node according to the weighted occurrence count of the node in accordance with the cross-entropy update rule.

[0228] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: according to the cross-entropy update rule, update the selection probability of the node according to the weighted occurrence count of the node, including: according to the cross-entropy update rule, recalculate the selection probability of the node according to the weighted occurrence count of the node; based on the update coefficient, integrate the recalculated selection probability of the node with the selection probability of the node in the previous iteration to obtain the selection probability of the node.

[0229] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: the preset conditions include the change in the comprehensive objective function value of a consecutive preset number of rounds not exceeding a preset change or the total number of iterations reaching a preset number of rounds; the comprehensive objective function value of each round is obtained by integrating the objective function values ​​of the intermediate location schemes under each round.

[0230] The implementation principle and technical effects of the above embodiments are similar to those of the above method embodiments, and will not be repeated here.

[0231] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0232] Transform the distribution network into a network structure that includes nodes and branches;

[0233] Based on the deviation between the power loss of each branch when it is not connected to the distributed power source and the power loss when it is connected to the distributed power source during a preset time period, as well as the deviation between the actual voltage of each node when it is not connected to the distributed power source and the actual voltage when it is connected to the distributed power source, an optimization objective function is constructed.

[0234] Each node is configured with a selection probability, which characterizes the likelihood that the corresponding node will be selected as the access node of the distributed power source in the current iteration.

[0235] Based on the selection probability of each node, a predetermined number of different nodes are selected from all nodes to form candidate site selection schemes. Based on the optimization objective function and power flow algorithm, the installed capacity matched by each node in the candidate site selection scheme and the objective function value used to characterize the merits of the candidate site selection scheme are obtained. Based on the installed capacity matched by each node in the candidate site selection scheme, the candidate site selection scheme is evaluated through a feasible region boundary learning model to obtain the minimum operating margin used to characterize the feasibility of the candidate site selection scheme. Based on the corresponding minimum operating margin and objective function value of each candidate site selection scheme, multiple candidate site selection schemes are screened to obtain the first intermediate site selection scheme.

[0236] Based on the minimum operating margin and objective function value of the first intermediate location scheme, update the selection probability of the node, return the selection probability of each node, select a preset number of different nodes from all nodes to form a candidate location scheme, and continue to execute until the preset conditions are met to obtain the second intermediate location scheme.

[0237] Based on the obtained second intermediate site selection scheme, the final site selection scheme is obtained, and the site selection and capacity determination are performed based on the final site selection scheme and the installed capacity matched by each node in the final site selection scheme.

[0238] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: selecting a preset number of different nodes from all nodes based on the selection probability of each node to form a candidate addressing scheme, including: normalizing the selection probabilities of all nodes to obtain the corresponding sampling weight of each node; selecting a preset number of different nodes from all nodes sequentially based on the corresponding sampling weight of each node to form a candidate addressing scheme; replacing the selected nodes and reselecting a preset number of different nodes from all nodes sequentially to form a new candidate addressing scheme, repeating the selection process until multiple candidate addressing schemes are obtained.

[0239] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: before updating the selection probability of the node based on the minimum operating margin and objective function value corresponding to the first intermediate addressing scheme, it further includes: for candidate addressing schemes that are not selected as intermediate addressing schemes, if the minimum operating margin of the candidate addressing scheme is less than 0 and the difference between it and 0 is less than a preset value, performing a repair process on the candidate addressing scheme; wherein, it is determined whether there are any nodes in the candidate addressing scheme whose actual voltage exceeds the upper limit or is lower than the lower limit, and if there are any nodes whose actual voltage exceeds the upper limit or is lower than the lower limit, the installed capacity matched to the corresponding node is adjusted; it is determined whether there are any branches in the candidate addressing scheme whose actual current effective value exceeds the maximum current carrying capacity, and if there are any branches whose actual current effective value exceeds the maximum current carrying capacity, the reactive power output of the upstream and downstream nodes of the corresponding branch is adjusted to reduce the actual current effective value of the branch; after the candidate addressing scheme is repaired through the above repair process, if the candidate addressing scheme passes the screening, the candidate addressing scheme is used as an intermediate addressing scheme.

[0240] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: updating the selection probability of a node based on the minimum operating margin and objective function value corresponding to the first intermediate addressing scheme, including: determining the scheme weight corresponding to the first intermediate addressing scheme based on the minimum operating margin and objective function value corresponding to the first intermediate addressing scheme; the magnitude of the scheme weight is negatively correlated with the objective function value and positively correlated with the minimum operating margin; obtaining the weighted occurrence count of a node based on the number of times a node is selected in the first intermediate addressing scheme and the scheme weight corresponding to the first intermediate addressing scheme; and updating the selection probability of a node according to the weighted occurrence count of the node in accordance with the cross-entropy update rule.

[0241] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: according to the cross-entropy update rule, update the selection probability of the node according to the weighted occurrence count of the node, including: according to the cross-entropy update rule, recalculate the selection probability of the node according to the weighted occurrence count of the node; based on the update coefficient, integrate the recalculated selection probability of the node with the selection probability of the node in the previous iteration to obtain the selection probability of the node.

[0242] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: the preset conditions include the change in the comprehensive objective function value of a consecutive preset number of rounds not exceeding a preset change or the total number of iterations reaching a preset number of rounds; the comprehensive objective function value of each round is obtained by integrating the objective function values ​​of the intermediate location schemes under each round.

[0243] The implementation principle and technical effects of the above embodiments are similar to those of the above method embodiments, and will not be repeated here.

[0244] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0245] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0246] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0247] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for addressing and sizing a distributed power source, characterized in that, The method includes: Transform the distribution network into a network structure that includes nodes and branches; Based on the deviation between the power loss of each branch when it is not connected to the distributed power source and the power loss when it is connected to the distributed power source during a preset time period, as well as the deviation between the actual voltage of each node when it is not connected to the distributed power source and the actual voltage when it is connected to the distributed power source, an optimization objective function is constructed. Each node is configured with a selection probability, which is used to characterize the probability that the corresponding node will be selected as the access node of the distributed power source in the current iteration. Based on the selection probability of each node, a predetermined number of different nodes are selected from all nodes to form candidate site selection schemes. Based on the optimization objective function and the power flow algorithm, the installed capacity matched by each node in the candidate site selection scheme and the objective function value used to characterize the merits of the candidate site selection scheme are obtained. Based on the installed capacity matched by each node in the candidate site selection scheme, the candidate site selection scheme is evaluated through a feasible region boundary learning model to obtain the minimum operating margin used to characterize the feasibility of the candidate site selection scheme. Based on the corresponding minimum operating margin and objective function value of each candidate site selection scheme, multiple candidate site selection schemes are screened to obtain a first intermediate site selection scheme. Based on the minimum operational margin and objective function value of the first intermediate location scheme, update the selection probability of the node, return the selection probability of each node, select a preset number of different nodes from all nodes to form a candidate location scheme, and continue to execute until the preset condition is met to obtain the second intermediate location scheme. Based on the obtained second intermediate site selection scheme, the final site selection scheme is obtained, and the site selection and capacity determination are performed based on the final site selection scheme and the installed capacity matched by each node in the final site selection scheme.

2. The method according to claim 1, characterized in that, The step of selecting a preset number of different nodes from all nodes based on the selection probability of each node to form a candidate location scheme includes: Normalize the selection probability of all nodes to obtain the corresponding sampling weight for each node; Based on the corresponding sampling weight of each node, a preset number of different nodes are selected sequentially from all nodes to form a candidate location scheme; the selected nodes are put back, and a preset number of different nodes are selected sequentially from all nodes to form a new candidate location scheme. The selection process is repeated until multiple candidate location schemes are obtained.

3. The method according to claim 1, characterized in that, Before updating the node's selection probability based on the minimum operational margin and objective function value corresponding to the first intermediate location scheme, the method further includes: For candidate site selection schemes that were not selected as intermediate site selection schemes, if the minimum operating margin of the candidate site selection scheme is less than 0 and the difference between it and 0 is less than a preset value, a repair process is performed on the candidate site selection scheme. Specifically, it is determined whether the actual voltage of any node in the candidate site selection scheme exceeds the upper limit or falls below the lower limit. If the actual voltage of any node exceeds the upper limit or falls below the lower limit, the installed capacity matched to the corresponding node is adjusted. It is also determined whether the effective value of the actual current of any branch in the candidate site selection scheme exceeds the maximum current carrying capacity. If the effective value of the actual current of any branch exceeds the maximum current carrying capacity, the reactive power output of the upstream and downstream nodes of the corresponding branch is adjusted to reduce the effective value of the actual current of the branch. After the candidate site selection schemes are repaired through the above repair process, if the candidate site selection schemes pass the screening, the candidate site selection schemes will be used as intermediate site selection schemes.

4. The method according to claim 1, characterized in that, The step of updating the selection probability of a node based on the minimum operational margin and objective function value corresponding to the first intermediate location scheme includes: Based on the minimum operational margin and objective function value of the first intermediate location scheme, the corresponding scheme weight of the first intermediate location scheme is determined; the magnitude of the scheme weight is negatively correlated with the objective function value and positively correlated with the minimum operational margin; Based on the number of times a node is selected in the first intermediate location scheme and the corresponding scheme weight of the first intermediate location scheme, obtain the weighted occurrence count of the node; according to the cross-entropy update rule, update the selection probability of the node according to the weighted occurrence count of the node.

5. The method according to claim 4, characterized in that, The step of updating the selection probability of a node according to the cross-entropy update rule, based on the weighted occurrence count of the node, includes: According to the cross-entropy update rule, the selection probability of a node is recalculated based on its weighted occurrence count. Based on the update coefficients, the recalculated selection probability of the node and the selection probability of the node in the previous iteration are integrated to obtain the corresponding selection probability of the node.

6. The method according to claim 1, characterized in that, The preset conditions include that the change in the comprehensive objective function value of a consecutive preset number of rounds does not exceed a preset change or the total number of iterations reaches a preset number of rounds; the comprehensive objective function value of each round is obtained by integrating the objective function values ​​of the intermediate location schemes under each round.

7. A distributed power source addressing and calibrating device, characterized in that, The device includes: The conversion module is used to convert the distribution network into a network structure that includes nodes and branches; The module is used to construct an optimization objective function based on the deviation between the power loss of each branch when it is not connected to the distributed power source and the power loss when it is connected to the distributed power source under a preset time period, as well as the deviation between the actual voltage of each node when it is not connected to the distributed power source and the actual voltage when it is connected to the distributed power source. A configuration module is used to configure a selection probability for each node, wherein the selection probability is used to characterize the probability that the corresponding node will be selected as the access node of the distributed power source in the current iteration. A filtering module is used to select a preset number of different nodes from all nodes based on the selection probability of each node to form a candidate site selection scheme; based on the optimization objective function and the power flow algorithm, obtain the installed capacity matched by each node in the candidate site selection scheme and the objective function value used to characterize the merits of the candidate site selection scheme; based on the installed capacity matched by each node in the candidate site selection scheme, evaluate the candidate site selection scheme through a feasible region boundary learning model to obtain the minimum operating margin used to characterize the feasibility of the candidate site selection scheme; based on the corresponding minimum operating margin and objective function value of each candidate site selection scheme, filter multiple candidate site selection schemes to obtain a first intermediate site selection scheme; The update module is used to update the selection probability of the node based on the minimum operating margin and objective function value of the first intermediate location scheme, return the selection probability of each node, select a preset number of different nodes from all nodes to form a candidate location scheme, and continue to execute the steps until the preset conditions are met to obtain the second intermediate location scheme. The acquisition module is used to obtain the final location scheme based on the obtained second intermediate location scheme, and to perform location and capacity determination based on the final location scheme and the installed capacity matched by each node in the final location scheme.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images