A low voltage flexible interconnection equipment access node preferred method, system, device, and medium

Abstract

The application discloses a low-voltage flexible interconnected equipment access node optimization method, system, device and medium, and the method comprises the following steps: obtaining the topology structure and equipment operation data of a low-voltage distribution network, and preprocessing the data to obtain preprocessed data; establishing a multi-type equipment operation boundary constraint model according to the preprocessed data, and dividing the feasible region of node optimization; based on the multi-type equipment operation boundary constraint model, constructing a node optimization comprehensive evaluation index system, and converting the access node optimization problem into a multi-objective quantitative evaluation problem; taking the node optimization comprehensive evaluation index system as a target function, and taking the multi-type equipment operation boundary constraint model as a constraint condition, constructing an access node solving model, and obtaining a candidate node scheme set; and selecting the candidate node scheme set by using an access node optimization decision method, obtaining a final recommended access node, and realizing the optimization of the low-voltage flexible interconnected equipment access node, which has a significant engineering application prospect.

Description

Technical Field

[0001] This invention relates to the field of power distribution network planning and operation optimization technology, and in particular to a method, system, equipment and medium for optimizing access nodes of low-voltage flexible interconnection equipment. Background Technology

[0002] With the large-scale integration of distributed energy resources and the diversification of loads, the operational complexity of low-voltage distribution networks has increased significantly. Low-voltage flexible interconnection equipment, as a key component for improving the flexibility and reliability of distribution networks, directly impacts system operating efficiency and economy through its connection location. Currently, the selection of connection nodes largely relies on manual experience or single-indicator judgment, lacking systematic multi-constraint modeling and multi-objective optimization methods, making it difficult to achieve scientific decision-making under complex operational boundaries. Furthermore, existing methods are highly sensitive to data quality, lack comprehensive constraint considerations, and often result in optimization results that are out of sync with actual operation.

[0003] To address this, the present invention proposes a systematic strategy for optimizing access nodes of low-voltage flexible interconnection equipment. Through multi-step modeling and optimization, it achieves data-driven scientific selection of nodes. Summary of the Invention

[0004] In view of the above-mentioned existing problems, the present invention provides a method, system, device and medium for the selection of access nodes for low-voltage flexible interconnection equipment, so as to solve the problem that there is a lack of systematic multi-constraint modeling and multi-objective optimization methods for the selection of access nodes for flexible interconnection equipment in low-voltage distribution networks.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a method for selecting the optimal access node for low-voltage flexible interconnection equipment, comprising: The topology and equipment operation data of the low-voltage distribution network are acquired, and the topology and equipment operation data are preprocessed to obtain preprocessed data. Based on the preprocessed data, a multi-type equipment operation boundary constraint model is established, and the feasible region for node optimization is divided. Based on the multi-type equipment operation boundary constraint model, a comprehensive evaluation index system for node selection is constructed, transforming the access node selection problem into a multi-objective quantitative evaluation problem; Using the node optimization comprehensive evaluation index system as the objective function and the multi-type equipment operation boundary constraint model as the constraint condition, an access node solution model is constructed to obtain a set of candidate node schemes; The candidate node scheme set is selected using the access node optimization decision method to obtain the final recommended access node, thereby realizing the optimization of access nodes for low-voltage flexible interconnection equipment.

[0006] As a preferred embodiment of the method for selecting access nodes for low-voltage flexible interconnection equipment according to the present invention, the preprocessing of the topology and equipment operation data includes: Calculate data integrity assessment indicators based on the topology of the low-voltage distribution network and equipment operation data; If the data integrity assessment index is less than the first threshold, the data cleaning process is triggered until the data integrity assessment index is greater than or equal to the first threshold. If the data integrity assessment index is greater than or equal to the first threshold, the correction process is triggered to obtain the corrected data; The data with missing values ​​is estimated using the imputation method to obtain the preprocessed data.

[0007] As a preferred embodiment of the low-voltage flexible interconnection equipment access node selection method described in this invention, the establishment of a multi-type equipment operation boundary constraint model includes: Line capacity constraints include ensuring that the current flowing through the line at any given time is less than or equal to the maximum safe current; The transformer load rate constraint includes the condition that the transformer load rate is less than or equal to the maximum allowable load rate at any given time. Node voltage constraints include ensuring that the voltage amplitude of each node is within the allowable upper and lower limits; The power constraints on interconnected equipment include limiting the active power injected or absorbed by flexible interconnected equipment to be between the lower and upper limits of the active power adjustment range.

[0008] The beneficial effects of this preferred technical solution are that it can define a precise feasible domain and ensure the safety of equipment and the stable operation of the system.

[0009] As a preferred embodiment of the low-voltage flexible interconnection equipment access node selection method described in this invention, the method includes: constructing a comprehensive evaluation index system for node selection, which includes: The comprehensive evaluation index system for node optimization includes voltage stability improvement index, line load balancing index, transformer load balancing index, and access economic cost index. The values ​​of the evaluation indicators in the baseline scenario without interconnected equipment are used as the normalization benchmark. Each evaluation indicator is normalized, and the weighted sum is performed using the weight coefficients corresponding to each evaluation indicator to construct an auxiliary scalar objective function.

[0010] The beneficial effect of this preferred technical solution is that it quantifies and normalizes the weighted multi-dimensional objectives, realizes a unified evaluation of multiple objectives, and provides a clear guide for optimization solutions.

[0011] As a preferred embodiment of the low-voltage flexible interconnection equipment access node selection method described in this invention, the following is included: Constructing an access node solution model to obtain a candidate node scheme set: A mathematical model for a multi-objective optimization problem is constructed by minimizing multiple indicators in the comprehensive evaluation index system as the objective function vector, taking the access node location of interconnected equipment and the power plan in each time period as decision variables, and using the boundary constraint model of multi-type equipment operation as the constraint condition. The mathematical model of the multi-objective optimization problem is solved using a solution algorithm to obtain a set of non-dominated solutions, which serves as a set of candidate node schemes.

[0012] As a preferred embodiment of the low-voltage flexible interconnection equipment access node selection method described in this invention, the method includes: solving the mathematical model of the multi-objective optimization problem using a solution algorithm, which includes: Initialize the population; The fitness of each individual in the population is evaluated to obtain the values ​​of each evaluation index and the total constraint violation for each individual. The population is stratified and sorted to determine the non-dominated level of each individual, and the crowding distance of individuals within the same level is calculated. The enhanced ranking value is obtained by weighting the non-dominated ranking level of an individual with the normalized auxiliary scalar target value. The enhanced ranking value is used as the basis for comparison to select parent individuals from the current population; For continuous decision variables, simulated binary crossover operator and polynomial mutation operator are used; for discrete decision variables, multi-point crossover operator and uniform mutation operator are used. The parent population is merged with the offspring population generated by crossover mutation. Non-dominated ranking and crowding calculation are performed. Based on the enhanced ranking value, the same number of individuals as the initial population size are selected from the merged population to form a new generation population. If the current generation reaches the preset maximum generation, or if the non-dominant frontier of the population does not change significantly over multiple generations, the iteration is terminated, and the set of non-dominant individuals in the current population is output as the set of candidate node schemes. Otherwise, return to fitness assessment and continue evolution.

[0013] The beneficial effects of this preferred technical solution are that it can quickly generate high-quality non-dominated solutions, taking into account both constraints and multi-objective optimization efficiency.

[0014] As a preferred embodiment of the method for selecting access nodes for low-voltage flexible interconnection equipment according to the present invention, the selection of the candidate node scheme set includes: Using each indicator in the comprehensive evaluation index system as an evaluation factor, several evaluation levels are set as a set of comments, and a membership function is defined for each evaluation indicator under each comment level. Based on the index values ​​of each scheme in the candidate node scheme set, the membership degree to each comment is calculated through the membership function to form the fuzzy evaluation vector of the corresponding scheme, and combined into the single-factor evaluation matrix of the corresponding scheme. Based on the weight coefficient vector, the single-factor evaluation matrix of each scheme is fuzzy synthesized to obtain the comprehensive evaluation membership vector of each scheme. Assign corresponding scores to each evaluation level, and perform a dot product operation between the comprehensive evaluation membership vector and the evaluation level score vector of each scheme to obtain the comprehensive score of the corresponding scheme. Compare the overall scores of each candidate solution, and select the solution with the highest overall score as the final recommended access node and corresponding operating strategy.

[0015] Secondly, the present invention provides a low-voltage flexible interconnection equipment access node optimization system, comprising: The preprocessing module is used to acquire the topology and equipment operation data of the low-voltage distribution network, and to preprocess the topology and equipment operation data to obtain preprocessed data. The multi-type equipment operation boundary constraint model construction module is used to establish a multi-type equipment operation boundary constraint model based on the preprocessed data and divide the feasible region for node optimization. The evaluation index system construction module is used to construct a comprehensive evaluation index system for node optimization based on the multi-type equipment operation boundary constraint model, and to transform the access node optimization problem into a multi-objective quantitative evaluation problem. The node solution model construction module is used to construct an access node solution model with the node optimization comprehensive evaluation index system as the objective function and the multi-type equipment operation boundary constraint model as the constraint condition, so as to obtain a set of candidate node schemes. The scheme selection module is used to select the candidate node scheme set using the access node optimization decision method to obtain the final recommended access node, thereby realizing the optimization of access nodes for low-voltage flexible interconnection equipment.

[0016] Thirdly, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, characterized in that the processor executes the computer program to implement the steps of the method for selecting access nodes of a low-voltage flexible interconnection equipment.

[0017] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that the computer program, when executed by a processor, implements the steps of the method for selecting access nodes of a low-voltage flexible interconnection equipment.

[0018] Compared with existing technologies, the beneficial effects of this invention are as follows: First, this invention establishes a boundary constraint model for the operation of multiple types of equipment, comprehensively considering practical engineering constraints such as line capacity, transformer load rate, voltage level, and equipment capabilities, to define a precise feasible region for node optimization. Second, it constructs a comprehensive evaluation index system integrating voltage stability, load balancing, and economy to achieve quantitative evaluation of multi-dimensional performance. Finally, it employs an improved multi-objective optimization algorithm and fuzzy decision-making method to select the optimal access scheme from the Pareto front. Compared with traditional methods that rely on experience or single indicators, this invention achieves scientific quantitative decision-making under multiple constraints, resulting in a more comprehensive and reliable scheme. This invention incorporates innovative designs in the optimization solution and decision-making stages, enhancing the practicality and robustness of the method. In the optimization phase, an improved Non-Dominated Sorting Genetic Algorithm II (NSGA-II) is employed. By introducing an enhanced sorting mechanism based on aggregation functions and a feasible solution-first constraint processing strategy, it effectively balances search speed and global optimization capability, enabling the rapid generation of high-quality Pareto solution sets. In the decision-making phase, a fuzzy comprehensive evaluation method is used to combine quantitative multi-objective optimization results with qualitative expert experience, achieving refined sorting and selection of candidate solutions. This method can adapt to the optimization needs of distribution networks of different scales and structures, and has stronger adaptability and engineering practicality compared to traditional fixed-parameter optimization methods. The strategy proposed in this invention fully considers the data conditions and operational requirements in actual engineering, and has good operability and promotion value. By establishing a data quality assessment and preprocessing model, it effectively addresses issues such as missing and anomalies in actual data, improving the reliability of basic data. The entire method flow is clear, and the model parameters can be flexibly adjusted according to the specific power grid operation procedures and planning objectives, making it easy to integrate into existing distribution network planning auxiliary decision-making systems. This invention provides a systematic technical solution for the precise deployment of low-voltage flexible interconnection equipment, which helps to improve the distribution network's ability to absorb distributed energy, its operational economy, and its power supply reliability, and has significant engineering application prospects. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of the overall process logic of a method for selecting access nodes for low-voltage flexible interconnection equipment according to an embodiment of the present invention; Figure 2 This is an overall flowchart of a method for selecting access nodes for low-voltage flexible interconnection equipment according to an embodiment of the present invention; Figure 3 The flowchart of the NSGA-II algorithm for a method of selecting access nodes for low-voltage flexible interconnection equipment is provided in one embodiment of the present invention. Detailed Implementation

[0021] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0022] Example 1, referring to Figures 1-3 As an embodiment of the present invention, a method for selecting a low-voltage flexible interconnection equipment access node is provided, comprising: S100: Acquire the topology and equipment operation data of the low-voltage distribution network, preprocess the topology and equipment operation data, and obtain the preprocessed data; In this embodiment of the invention, the distribution network topology data, including node numbers, line connection relationships, line types and lengths, is used to construct a network model; transformer parameter data, including rated capacity and historical load rate data, is used to evaluate the transformer operating status; line parameter data, including rated current, resistance, and reactance, is used to calculate line power flow and losses; load data, including historical and predicted active and reactive power curves for each node, is used to simulate system operating scenarios; and low-voltage flexible interconnection equipment parameters, including rated power, adjustment range, and response time, are used to model the equipment's adjustment capabilities.

[0023] S200: Based on the preprocessed data, establish a boundary constraint model for the operation of multiple types of equipment and divide the feasible region for node optimization; S300: Based on the boundary constraint model of multi-type equipment operation, a comprehensive evaluation index system for node selection is constructed, which transforms the access node selection problem into a multi-objective quantitative evaluation problem; S400: Using the node optimization comprehensive evaluation index system as the objective function and the multi-type equipment operation boundary constraint model as the constraint condition, a solution model for access nodes is constructed to obtain a set of candidate node schemes; S500: The access node optimization decision method is used to select from the set of candidate node schemes to obtain the final recommended access node, thereby realizing the optimization of access nodes for low-voltage flexible interconnection equipment.

[0024] In one optional embodiment, the access node optimization decision method can be the superior-inferior solution distance method, which performs homogenization and normalization processing on the four indicators of each scheme in the Pareto solution set; constructs a standardized decision matrix to determine the optimal ideal solution and the worst ideal solution; calculates the Euclidean distance of each scheme to the optimal and worst solutions; calculates the proximity of each scheme, with the scheme being better if the proximity is higher; sorts the schemes by proximity and selects the one with the highest score as the final access node scheme. In another optional embodiment, the access node optimization decision method can also be the analytic hierarchy process (AHP) – entropy weight method, which uses the AHP to determine subjective weights and the entropy weight method to calculate objective weights; the subjective and objective weights are linearly combined to obtain a comprehensive weight; the indicators of each candidate scheme are weighted and summed to obtain a comprehensive score; the schemes are sorted from high to low according to the comprehensive scores; and the scheme with the highest score is selected as the optimal access node and operating strategy. In this embodiment of the invention, the access node optimization decision method includes fuzzy comprehensive evaluation; Specifically, using the Pareto optimal solution set output by multi-objective optimization as input, the evaluation index and comment set are determined, the membership function and single-factor evaluation matrix are constructed, fuzzy comprehensive evaluation is performed in combination with weights, the comprehensive score of the scheme is calculated and ranked, and the optimal access node is selected.

[0025] like Figure 2 As shown, this invention collects and cleans the topology and equipment operation data of low-voltage distribution networks. If the data integrity does not meet the requirements, a data cleaning and correction process is triggered, and the data acquisition and preprocessing are repeated until the data integrity meets the standards. If the data integrity meets the standards, subsequent steps are executed. A multi-type equipment operation boundary constraint model is established, including line capacity constraints, transformer load rate constraints, node voltage constraints, and interconnection equipment power constraints, to divide the feasible region for node optimization. A comprehensive evaluation index system for node optimization is constructed, incorporating voltage stability improvement indicators, line load balancing indicators, transformer load balancing indicators, and access economic cost indicators into a unified evaluation framework. Based on this framework, a multi-objective optimization model for access nodes is constructed and solved. The comprehensive evaluation index is used as the objective function, and the operation boundary constraints are used as constraints. An improved NSGA-II algorithm is used to solve the model, determining whether the termination condition has been met. If the termination condition has not been met, the optimization process continues; if the termination condition has been met, a set of candidate node schemes is output. The fuzzy comprehensive evaluation method is used to select the solution. The comprehensive score is calculated for each solution in the candidate node solution set, and the solution with the highest score is selected as the final recommended access node and the corresponding operation strategy.

[0026] It should be noted that this invention solves the problems of traditional methods relying on experience and ignoring multiple operational boundaries by systematically preprocessing data, multi-dimensional constraint modeling, and multi-objective optimization decision-making processes. It achieves scientific quantitative optimization of low-voltage flexible interconnection equipment access nodes while meeting actual engineering constraints such as lines, transformers, and voltage, effectively improving the reliability, economy, and capacity for distributed energy absorption in distribution network operations.

[0027] In this embodiment of the invention, step S100 includes the following sub-steps A1-A4; In A1: Calculate data integrity assessment indicators based on the topology of the low-voltage distribution network and equipment operation data; In A2: In response to the data integrity assessment index being less than the first threshold, the data cleaning process is triggered until the data integrity assessment index is greater than or equal to the first threshold. In A3: When the data integrity assessment index is greater than or equal to the first threshold, the correction process is triggered to obtain the corrected data; In A4: The data with missing values ​​is estimated using the imputation method to obtain the preprocessed data.

[0028] In one optional embodiment, the data integrity assessment metric can be the data missing rate. The missing rate is obtained by calculating the theoretical total number of data entries and the number of missing data entries, and the ratio of the theoretical total number of data entries to the number of missing data entries. If the missing rate is higher than a preset threshold, the data cleaning and completion process is initiated. In another optional embodiment, the data integrity assessment index can also be the effective field coverage rate. The total number of fields that should be collected for a single data record is determined, the number of effective fields for a single data record is counted, the field coverage rate of a single data record is calculated by the ratio of the total number of fields that should be collected for a single data record to the number of effective fields for a single data record, the field coverage rates of the single data records are summed and divided by the overall dataset to obtain the overall coverage rate. If the overall coverage rate is lower than a preset threshold, the data integrity is determined to be substandard. In this embodiment of the invention, the data integrity assessment index includes the data integrity rate; Specifically, the data integrity assessment index is calculated, and the degree of missing data is represented as follows: in, For data integrity rate, The number of valid data entries, i.e., the number of data entries that are complete and correctly formatted. This represents the total theoretical number of data entries.

[0029] The first threshold can be 95%. If the data integrity assessment index is less than 95%, the data cleaning process is triggered until the data integrity assessment index is greater than or equal to 95%. If the data integrity assessment index is greater than or equal to 95%, then an integrity check will be performed and a correction process will be initiated.

[0030] Data sequences that pass integrity checks To perform consistency correction, significant outliers are removed or corrected as follows: in, For the first One set of raw data, For this data sequence The mean, The standard deviation of the sequence is . This is the corrected data.

[0031] For missing values ​​that still exist in the corrected sequence, imputation methods are used to estimate them to ensure data continuity.

[0032] In one alternative embodiment, the interpolation method can be sliding window mean interpolation, to determine the missing time point. Select with A fixed-length window is defined before and after the center; all existing valid data within the window are extracted; the arithmetic mean of these valid data is calculated; and this mean is used as the missing time step. The estimated values ​​are filled into the sequence; In another alternative embodiment, the interpolation method can also be linear interpolation to find the missing moments. Previous known time and the next known time ; obtain Corresponding data value , Corresponding data value ;according to , The time ratio between them, calculate the missing moments. The estimated value; the calculation result is used as the missing value to fill the sequence; In this embodiment of the invention, the interpolation method includes a timing interpolation model; Specifically, the estimation using the time-series interpolation model is expressed as follows: in, For the first Imputed values ​​for data that is constantly missing. For the first Known data at time, For the first trend-based forecast Time-based data estimates This is the attenuation coefficient, used to balance the weights of historical data and future trend estimates. A recommended value range is 0.6 to 0.8.

[0033] It should be noted that through data quality assessment and preprocessing, anomalies are effectively eliminated, missing data is filled in, and data reliability is improved, providing high-quality input for subsequent modeling and ensuring that the constraints and optimization results are accurate and reliable.

[0034] In this embodiment of the invention, step S200 includes the following sub-steps B1-B4; In B1: Line capacity constraints include that the current flowing through the line at any given time is less than or equal to the maximum safe current; In B2: The transformer load rate constraint includes the condition that the transformer load rate is less than or equal to the maximum allowable load rate at any given time; In B3: Node voltage constraints include ensuring that the voltage amplitude of each node is within the allowable upper and lower limits; In B4: Interconnected equipment power constraints include limiting the active power injected or absorbed by flexible interconnected equipment to between the lower and upper limits of the active power adjustment range.

[0035] In this embodiment of the invention, the line capacity constraint includes ensuring that the current flowing through the line at any given time does not exceed its maximum safe current, expressed as: in, The route calculated based on power flow At any moment The current amplitude, This refers to the upper limit of the rated current of the line. It is the collection of all lines in the distribution network. For all time periods, For all lines.

[0036] Transformer load factor constraints include measures to prevent transformer overload operation. The load factor is determined by the apparent power flowing through it and is expressed as: in, For the transformer at time load rate, This represents the apparent power of the transformer at that moment. These represent the total active power and total reactive power flowing through the transformer, respectively. For the collected transformer rated capacity, The maximum allowable load rate is recommended to be between 0.7 and 0.9 according to the operating procedures.

[0037] Node voltage constraints include ensuring that the voltage of each node in the system is within the allowable range, satisfying power quality requirements, expressed as: in, For nodes obtained through power flow calculation At any moment The voltage amplitude is expressed in per-unit value pu; These are the upper and lower limits of the allowable voltage, typically taken as 0.93 pu and 1.07 pu. The set of all nodes in the system. For all nodes.

[0038] Power constraints on interconnected equipment include limiting the active power injected or absorbed by flexible interconnected equipment within its physical capabilities, expressed as: in, Let be the variable to be optimized, representing the time of the flexible interconnected equipment. Active power injected into the network is positive (injection) and negative (absorption). This refers to the lower and upper limits of the active power adjustment range of the equipment.

[0039] It should be noted that by constructing hard constraints on the operating boundaries of four types of equipment, the range of current, load, voltage and equipment power is precisely defined, the feasible domain is delineated, and the safe and stable operation of the distribution network and the compliant usability of the optimization results are ensured.

[0040] In this embodiment of the invention, step S300 includes the following sub-steps C1-C2; In C1: The comprehensive evaluation index system for node optimization includes voltage stability improvement index, line load balancing index, transformer load balancing index, and access economic cost index; In C2: The values ​​of the evaluation indicators in the baseline scenario without interconnected equipment are used as the normalization benchmark. Each evaluation indicator is normalized and then weighted and summed using the weight coefficients corresponding to each evaluation indicator to construct an auxiliary scalar objective function.

[0041] In this embodiment of the invention, the voltage stability improvement index This includes calculating the time average of the sum of squares of the voltage deviations of all system nodes relative to the rated voltage after the candidate node is connected to the equipment: in, This is an indicator of voltage stability improvement; the smaller the value, the more stable the overall system voltage. As a reference voltage, we take 1.0 (pu). The total number of time periods examined. For nodes At any moment The voltage, its calculation is affected by the equipment connection location and power. Influence, It is a set of nodes.

[0042] Line load balancing metrics include calculating the time average of the sum of squares of the load rates of all lines, aiming to achieve a more even distribution of line loads. in, This is a load balancing index for power lines; the smaller the value, the more balanced the load on the power lines. For the set of routes The number of elements in the middle, i.e., the total number of lines; For the line At any moment The current, This is the upper limit of the rated current of the line.

[0043] Transformer load balancing index, calculated as the time average of the sum of squares of the load rates of all transformers, aims to balance transformer utilization. in, This is a transformer load balancing index; the smaller the value, the more balanced the transformer load. This represents the total number of transformers. For the first The transformer at time The load rate.

[0044] Access the economic cost indicator, which is the one-time investment cost and is directly related to the candidate node's location: in, To incorporate the economic cost indicator, a smaller value indicates better economic efficiency. The fixed installation cost of the flexible interconnect equipment itself, The construction cost per unit length of cable or channel. From the power source or planned access point to the candidate node The data on the distance of the line laying is derived from topology and geographic information.

[0045] Define the weighted sum of the normalized indicators as one of the auxiliary scalar objectives, with its weights reflecting the relative importance of different objectives: in, The auxiliary scalar objective function after aggregation. These are the values ​​of each indicator in a baseline scenario without interconnected equipment, used for normalization. The weighting coefficients for each indicator satisfy the following conditions: Based on the guidelines for safe and economical operation of distribution networks, the recommended value is [value to be filled in]. (Voltage stable) (Line balancing) (Transformer balancing) (Economic costs).

[0046] It should be noted that a four-dimensional indicator system of voltage stability, line balancing, transformer balancing, and economic cost is constructed to achieve quantitative evaluation of technical and economic efficiency. By normalizing and weighting the benchmark scenario, the multi-objective dimensions are unified, the optimization direction is clearly guided, and the safety of the power grid, load balancing and investment benefits are taken into account, thereby improving the scientific nature and engineering practicality of node selection.

[0047] In this embodiment of the invention, step S400 includes the following sub-steps D1-D11; In D1: The objective function vector is to minimize multiple indicators in the comprehensive evaluation index system, the access node location of the interconnected equipment and the power plan in each time period are the decision variables, and the boundary constraint model of multi-type equipment operation is used as the constraint condition to construct a mathematical model of multi-objective optimization problem. In D2: The mathematical model of the multi-objective optimization problem is solved using a solution algorithm to obtain a set of non-dominated solutions, which serves as a set of candidate node schemes.

[0048] In D3: Initialize the population; In D4: Fitness is evaluated for each individual in the population to obtain the values ​​of each evaluation index and the total constraint violation for each individual; In D5: Individuals in the population are stratified and ordered to determine the non-dominated level of each individual, and the crowding distance of individuals within the same level is calculated; In D6: The non-dominated ranking level of an individual is weighted and combined with the normalized auxiliary scalar target value to obtain the enhanced ranking value; In D7: The enhanced sort value is used as the comparison basis to select parent individuals from the current population; In D8: For continuous decision variables, simulated binary crossover operator and polynomial mutation operator are used; for discrete decision variables, multi-point crossover operator and uniform mutation operator are used. In D9: The parent population is merged with the offspring population generated by crossover mutation. Non-dominated ordination and crowding calculation are performed. Based on the enhanced ordination value, the same number of individuals as the initial population size are selected from the merged population to form a new generation population. In D10: If the current generation reaches the preset maximum generation, or if the non-dominant frontier of the population does not change significantly over multiple generations, the iteration is terminated, and the set of non-dominant individuals in the current population is output as the set of candidate node schemes. In D11: Otherwise, return to fitness assessment and continue evolution.

[0049] In this embodiment of the invention, the mathematical model for constructing a multi-objective optimization problem is expressed as follows: in, Let the objective function vector be... The decision variable vector contains discrete access node locations. and continuous power planning sequence , This represents the set of inequality constraints that integrate the constraints in the boundary constraint model for the operation of multiple types of equipment.

[0050] In one optional embodiment, the solution algorithm can be an improved multi-objective particle swarm optimization algorithm, which initializes a particle population, with each particle containing decision variables such as access node and power; calculates the four objective function values ​​of each particle to determine whether the running boundary constraints are satisfied; updates the individual optimal and global optimal positions of the particles, and constructs an external archive to store Pareto solutions; adjusts the particle velocity and position according to the constraint dominance principle to guide the population to converge toward the feasible region; iterates to the maximum number of iterations and outputs a set of non-dominated candidate solutions. In another alternative embodiment, the solution algorithm can also be a multi-objective artificial bee colony algorithm, which initializes the nectar source location, corresponding to different access nodes and power adjustment schemes; performs neighborhood search, calculates the objective and retains better feasible solutions; selects nectar sources according to fitness, continues to search and updates the Pareto file; abandons poor solutions, randomly generates new nectar sources to avoid local optima, and outputs the Pareto optimal solution set for decision-making after the stopping condition is met. In this embodiment of the invention, the solution algorithm includes the NSGA-II algorithm; Specifically, such as Figure 3 As shown, in the NSGA-II algorithm, to process multiple targets simultaneously, a ranking based on Pareto dominance and crowding calculation is used to select superior individuals. To enhance search guidance, an aggregation function is introduced as an auxiliary selection pressure, expressed as: in, The smaller the ranking value of the enhanced individual, the better. For individuals The primary level is obtained based on the non-dominated sorting, with 1 being the optimal frontier, and the levels increasing sequentially. In the current population The maximum value; A small positive coefficient used to introduce within the same Pareto level. For a more precise comparison, a value of 0.1 to 0.2 is recommended.

[0051] The constraint dominance principle of prioritizing feasible solutions is adopted, and the total constraint violation degree of an individual is defined. : in, For individuals Total constraint violation For the first The amount of violation of a constraint condition, if the constraint is satisfied. , The set of all constraints. Represents an individual Completely feasible; In crossover and mutation operations, for continuous variables and discrete variables Design different operators for simulated binary crossover (SBX) of continuous variables: in, For offspring individuals at any time The power variable, Based on the distribution index Randomly generated cross factors for discrete variables It employs a multi-point intersection method.

[0052] The algorithm ultimately outputs a non-dominated solution set. Each of them For a Pareto-optimal access node and power regulation scheme, the solution set is used for the final decision. Among these, This represents the number of Pareto optimal solutions.

[0053] It should be noted that an improved multi-objective optimization algorithm is used to construct the access node solution model, taking into account the operational constraints of multiple devices. The optimization accuracy is improved by non-dominated sorting and congestion calculation, auxiliary objectives are introduced to enhance the search guidance, and the feasible solution priority principle is adopted to ensure the compliance of the scheme. The Pareto optimal solution set is output quickly, providing scientific, efficient and reliable solution support for node optimization.

[0054] In this embodiment of the invention, step S500 includes the following sub-steps E1-E5; In E1: Each indicator in the comprehensive evaluation index system is used as an evaluation factor, several evaluation levels are set as a set of comments, and a membership function is defined for each evaluation indicator under each comment level. In E2: Based on the index values ​​of each scheme in the candidate node scheme set, the membership degree to each comment is calculated through the membership function to form the fuzzy evaluation vector of the corresponding scheme, and combined into the single-factor evaluation matrix of the corresponding scheme. In E3: Based on the weight coefficient vector, the single-factor evaluation matrix of each scheme is fuzzy synthesized to obtain the comprehensive evaluation membership vector of each scheme; In E4: Assign corresponding scores to each rating level, and perform a dot product operation between the comprehensive rating membership vector and the rating level score vector of each scheme to obtain the comprehensive score of the corresponding scheme. In E5: Compare the overall scores of each candidate solution, and select the solution with the highest overall score as the final recommended access node and corresponding operating strategy.

[0055] In this embodiment of the invention, the evaluation factor set is determined. and a collection of comments For each indicator Define its in comments Membership function under Represented as: in, For the indicator The actual value is At that time, it belonged to the category of comments. To what extent, To define the first The first indicator corresponds to the first The parameters of the trapezoidal membership function shape for each comment are determined based on historical data or expert experience, so that the smaller the index value, the higher the membership degree of the corresponding excellent comment.

[0056] For Pareto solution set Each of the schemes According to its various indicator values By calculating its membership degree to each comment, a fuzzy evaluation vector for the scheme is constructed. This leads to the formation of a single-factor evaluation matrix for the scheme. Represented as: Apply a defined weight vector For each scheme Perform fuzzy comprehensive evaluation to obtain the membership vector of the comprehensive evaluation. : in, For fuzzy synthesis operators, a weighted average operator is used, i.e. , For the plan Belongs to the comments The degree of integration.

[0057] To rank the solutions, the membership vector of the comprehensive evaluation criteria is used. Convert to a scalar score To emphasize the importance of the "Excellent" feedback, a weighted scoring method was used, assigning scores to each feedback level. Represented as: in, For the plan The overall score indicates that the solution performs better overall.

[0058] The solution with the highest overall score is selected as the optimal access node and operating strategy: in, The final optimal decision-making solution is selected. To obtain the objective function The independent variable that reaches its maximum value This completes the process of determining a single final decision from a multi-objective optimization solution set.

[0059] It should be noted that by using fuzzy comprehensive evaluation to perform a secondary sorting of the multi-objective optimization solution set, the technical and economic indicators are quantified and scored, and the optimal node is accurately selected, thereby improving the scientific nature of decision-making and the practicality of engineering.

[0060] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

[0061] Example 2: The above is an illustrative scheme of a method for selecting access nodes for low-voltage flexible interconnection equipment according to this embodiment. It should be noted that the technical solution of this low-voltage flexible interconnection equipment access node selection system and the technical solution of the aforementioned method for selecting access nodes for low-voltage flexible interconnection equipment belong to the same concept. Details not described in detail in the technical solution of the low-voltage flexible interconnection equipment access node selection system in this embodiment can be found in the description of the aforementioned method for selecting access nodes for low-voltage flexible interconnection equipment.

[0062] This embodiment provides a low-voltage flexible interconnection equipment access node optimization system, comprising: The preprocessing module is used to acquire the topology and equipment operation data of the low-voltage distribution network, and to preprocess the topology and equipment operation data to obtain preprocessed data. The multi-type equipment operation boundary constraint model construction module is used to establish a multi-type equipment operation boundary constraint model based on the preprocessed data and divide the feasible region for node optimization. The evaluation index system construction module is used to construct a comprehensive evaluation index system for node optimization based on the multi-type equipment operation boundary constraint model, and to transform the access node optimization problem into a multi-objective quantitative evaluation problem. The node solution model construction module is used to construct an access node solution model with the node optimization comprehensive evaluation index system as the objective function and the multi-type equipment operation boundary constraint model as the constraint condition, so as to obtain a set of candidate node schemes. The scheme selection module is used to select the candidate node scheme set using the access node optimization decision method to obtain the final recommended access node, thereby realizing the optimization of access nodes for low-voltage flexible interconnection equipment.

[0063] This embodiment also provides a computer device applicable to a method for selecting the access node of a low-voltage flexible interconnection equipment, including: The system includes a memory and a processor. The memory stores computer-executable instructions, and the processor executes these instructions to implement a method for selecting a low-voltage flexible interconnection equipment access node as described in the above embodiments.

[0064] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements a method for selecting access nodes for low-voltage flexible interconnection equipment as proposed in the above embodiments.

[0065] The storage medium proposed in this embodiment and the preferred method for implementing a low-voltage flexible interconnection equipment access node proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0066] Based on the above description of the implementation methods, those skilled in the art will clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computing device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

Claims

1. A method for selecting the optimal access node for low-voltage flexible interconnection equipment, characterized in that, include: The topology and equipment operation data of the low-voltage distribution network are acquired, and the topology and equipment operation data are preprocessed to obtain preprocessed data. Based on the preprocessed data, a multi-type equipment operation boundary constraint model is established, and the feasible region for node optimization is divided. Based on the multi-type equipment operation boundary constraint model, a comprehensive evaluation index system for node selection is constructed, transforming the access node selection problem into a multi-objective quantitative evaluation problem; Using the node optimization comprehensive evaluation index system as the objective function and the multi-type equipment operation boundary constraint model as the constraint condition, an access node solution model is constructed to obtain a set of candidate node schemes; The candidate node scheme set is selected using the access node optimization decision method to obtain the final recommended access node, thereby realizing the optimization of access nodes for low-voltage flexible interconnection equipment.

2. The preferred method for access nodes of low-voltage flexible interconnection equipment as described in claim 1, characterized in that, Preprocessing of the topology and equipment operation data includes: Calculate data integrity assessment indicators based on the topology of the low-voltage distribution network and equipment operation data; If the data integrity assessment index is less than the first threshold, the data cleaning process is triggered until the data integrity assessment index is greater than or equal to the first threshold. If the data integrity assessment index is greater than or equal to the first threshold, the correction process is triggered to obtain the corrected data; The data with missing values ​​is estimated using the imputation method to obtain the preprocessed data.

3. The preferred method for access nodes of low-voltage flexible interconnection equipment as described in claim 2, characterized in that, Establishing boundary constraint models for the operation of multiple types of equipment includes: Line capacity constraints include ensuring that the current flowing through the line at any given time is less than or equal to the maximum safe current; The transformer load rate constraint includes the condition that the transformer load rate is less than or equal to the maximum allowable load rate at any given time. Node voltage constraints include ensuring that the voltage amplitude of each node is within the allowable upper and lower limits; The power constraints on interconnected equipment include limiting the active power injected or absorbed by flexible interconnected equipment to be between the lower and upper limits of the active power adjustment range.

4. The preferred method for access nodes of low-voltage flexible interconnection equipment as described in claim 3, characterized in that, The construction of a comprehensive evaluation index system for node optimization includes: The comprehensive evaluation index system for node optimization includes voltage stability improvement index, line load balancing index, transformer load balancing index, and access economic cost index. The values ​​of the evaluation indicators in the baseline scenario without interconnected equipment are used as the normalization benchmark. Each evaluation indicator is normalized, and the weighted sum is performed using the weight coefficients corresponding to each evaluation indicator to construct an auxiliary scalar objective function.

5. The preferred method for access nodes of low-voltage flexible interconnection equipment as described in claim 1, characterized in that, The access node solution model is constructed, and the candidate node scheme set is obtained, including: A mathematical model for a multi-objective optimization problem is constructed by minimizing multiple indicators in the comprehensive evaluation index system as the objective function vector, taking the access node location of interconnected equipment and the power plan in each time period as decision variables, and using the boundary constraint model of multi-type equipment operation as the constraint condition. The mathematical model of the multi-objective optimization problem is solved using a solution algorithm to obtain a set of non-dominated solutions, which serves as a set of candidate node schemes.

6. The preferred method for access nodes of low-voltage flexible interconnection equipment as described in claim 5, characterized in that, Solving mathematical models of multi-objective optimization problems using algorithmic methods includes: Initialize the population; The fitness of each individual in the population is evaluated to obtain the values ​​of each evaluation index and the total constraint violation for each individual. The population is stratified and sorted to determine the non-dominated level of each individual, and the crowding distance of individuals within the same level is calculated. The enhanced ranking value is obtained by weighting the non-dominated ranking level of an individual with the normalized auxiliary scalar target value. The enhanced ranking value is used as the basis for comparison to select parent individuals from the current population; For continuous decision variables, simulated binary crossover operator and polynomial mutation operator are used; for discrete decision variables, multi-point crossover operator and uniform mutation operator are used. The parent population is merged with the offspring population generated by crossover mutation. Non-dominated ranking and crowding calculation are performed. Based on the enhanced ranking value, the same number of individuals as the initial population size are selected from the merged population to form a new generation population. If the current generation reaches the preset maximum generation, or if the non-dominant frontier of the population does not change significantly over multiple generations, the iteration is terminated, and the set of non-dominant individuals in the current population is output as the set of candidate node schemes. Otherwise, return to fitness assessment and continue evolution.

7. The preferred method for access nodes of low-voltage flexible interconnection equipment as described in claim 6, characterized in that, The selection of the candidate node scheme set includes: Using each indicator in the comprehensive evaluation index system as an evaluation factor, several evaluation levels are set as a set of comments, and a membership function is defined for each evaluation indicator under each comment level. Based on the index values ​​of each scheme in the candidate node scheme set, the membership degree to each comment is calculated through the membership function to form the fuzzy evaluation vector of the corresponding scheme, and combined into the single-factor evaluation matrix of the corresponding scheme. Based on the weight coefficient vector, the single-factor evaluation matrix of each scheme is fuzzy synthesized to obtain the comprehensive evaluation membership vector of each scheme. Assign corresponding scores to each evaluation level, and perform a dot product operation between the comprehensive evaluation membership vector and the evaluation level score vector of each scheme to obtain the comprehensive score of the corresponding scheme. Compare the overall scores of each candidate solution, and select the solution with the highest overall score as the final recommended access node and corresponding operating strategy.

8. A low-voltage flexible interconnection equipment access node selection system, employing the low-voltage flexible interconnection equipment access node selection method as described in any one of claims 1-7, characterized in that, include: The preprocessing module is used to acquire the topology and equipment operation data of the low-voltage distribution network, and to preprocess the topology and equipment operation data to obtain preprocessed data. The multi-type equipment operation boundary constraint model construction module is used to establish a multi-type equipment operation boundary constraint model based on the preprocessed data and divide the feasible region for node optimization. The evaluation index system construction module is used to construct a comprehensive evaluation index system for node optimization based on the multi-type equipment operation boundary constraint model, and to transform the access node optimization problem into a multi-objective quantitative evaluation problem. The node solution model construction module is used to construct an access node solution model with the node optimization comprehensive evaluation index system as the objective function and the multi-type equipment operation boundary constraint model as the constraint condition, so as to obtain a set of candidate node schemes. The scheme selection module is used to select the candidate node scheme set using the access node optimization decision method to obtain the final recommended access node, thereby realizing the optimization of access nodes for low-voltage flexible interconnection equipment.

9. A computer device, characterized in that, include: A memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the preferred method for a low-voltage flexible interconnection equipment access node according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed by a processor, implements the steps of a preferred method for a low-voltage flexible interconnection equipment access node according to any one of claims 1 to 7.

Images