Electric energy quality compensation method and equipment for new energy access power grid

Abstract

The invention relates to an electric energy quality compensation method and equipment for a new energy access power grid. The method comprises the following steps: acquiring voltage fluctuation data of a power grid and real-time state data of each power grid compensation node; quantizing the fluctuation condition of the power grid based on the voltage fluctuation data to obtain power grid cooperative compensation data; calculating a compensation weight of each power grid compensation node based on the power grid cooperative compensation data, a preset basic weight mapping rule and a preset power grid compensation node basic parameter; the basic parameters of the power grid compensation nodes comprise a capacity value, a response speed value and a reliable value of each power grid compensation node; the compensation weight is used for representing the priority of the power quality compensation of the power grid compensation node in the power grid; based on the compensation weight and the real-time state data, distributing the power grid cooperative compensation data to each power grid compensation node, and generating a compensation instruction of each power grid compensation node; the compensation instruction is used for indicating adjustment of working parameters of power grid compensation nodes. The method can improve the power quality compensation efficiency of the power grid.

Description

Technical Field

[0001] This invention belongs to the field of power quality compensation, and in particular relates to a power quality compensation method and equipment for new energy grid access. Background Technology

[0002] With the development of power quality compensation technology, centralized control power compensation technology has emerged. Existing centralized control power compensation technologies typically employ a central control system that centrally calculates and issues commands. Specifically, the system periodically collects operational data such as voltage and current at key nodes of the power grid through data acquisition and monitoring platforms such as SCADA, and uploads this data to the master station. The energy management system or dedicated power quality optimization algorithm in the master station calculates the required compensation amount based on the overall network status, and then issues specific reactive power output or filtering commands to various distributed compensation devices within the region. The entire process relies on the powerful computing power of the central node and a highly reliable communication network; each compensation device itself acts only as an execution unit, independently completing local commands.

[0003] However, current centralized power compensation technologies suffer from several drawbacks, including response speed limited by communication cycles and central computing power, insufficient system scalability and flexibility, and the potential for network-wide compensation failure due to central node failure. Particularly concerning is the significant differences in parameters and response characteristics between heterogeneous compensation systems. Traditional methods struggle to achieve coordinated optimization between devices, and mismatches between control commands and device dynamics can easily lead to offsetting compensation effects or even system oscillations, resulting in reduced power quality compensation efficiency. Summary of the Invention

[0004] Therefore, it is necessary to provide a power quality compensation method and equipment for new energy sources connected to the power grid that can improve the power quality compensation efficiency of the power grid, in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a power quality compensation method for new energy sources connected to the power grid, including:

[0006] Acquire voltage fluctuation data of the power grid and real-time status data of each power grid compensation node;

[0007] The fluctuation of the power grid is quantified based on voltage fluctuation data to obtain power grid collaborative compensation data; the power grid collaborative compensation data includes the priority level value of power quality compensation of the power grid and the compensation demand value of power quality compensation of the power grid.

[0008] Based on grid collaborative compensation data, preset basic weight mapping rules, and preset basic parameters of grid compensation nodes, the compensation weight of each grid compensation node is calculated. The basic parameters of the grid compensation nodes include the capacity value, response speed value, and reliability value of each grid compensation node. The compensation weight is used to characterize the priority of the grid compensation node in power quality compensation of the grid.

[0009] Based on compensation weights and real-time status data, grid collaborative compensation data is allocated to each grid compensation node, and compensation instructions are generated for each grid compensation node. The compensation instructions are used to instruct the adjustment of the operating parameters of the grid compensation node.

[0010] Furthermore, based on voltage fluctuation data, the fluctuation of the power grid is quantified to obtain power grid collaborative compensation data, including:

[0011] The voltage fluctuation data is filtered to eliminate outliers and obtain clean voltage fluctuation data.

[0012] Calculate the extreme values ​​of the clean voltage fluctuation data to obtain the voltage fluctuation amplitude;

[0013] Based on a preset time window, the rate of change of clean voltage fluctuation data within the time window is calculated to obtain the voltage fluctuation rate.

[0014] The priority level value is obtained by inputting the voltage fluctuation amplitude and voltage fluctuation rate into a preset power grid compensation priority level mapping model.

[0015] Based on the voltage fluctuation amplitude and the preset normal voltage threshold of the power grid, the total power quality compensation of the power grid is calculated to obtain the compensation demand value.

[0016] Based on priority level values ​​and compensation demand values, grid collaborative compensation data is obtained.

[0017] Furthermore, the power grid compensation priority mapping model is obtained through the following method:

[0018] Obtain the historical compensation database of the power grid; the historical compensation database of the power grid includes the voltage fluctuation amplitude, voltage fluctuation rate and corresponding priority level value of the historical compensation process;

[0019] The model training data is obtained by using the voltage fluctuation amplitude and voltage fluctuation rate of the historical compensation process as feature values ​​and the corresponding priority level value as feature attributes; and the model training data is divided into training samples and test samples according to the preset division ratio.

[0020] Based on the fuzzy C-means clustering algorithm and training samples, a preliminary power grid compensation priority mapping model is constructed.

[0021] A preliminary power grid compensation priority mapping model is trained using test samples until it meets the preset accuracy requirements, thus obtaining the power grid compensation priority mapping model.

[0022] Furthermore, based on grid collaborative compensation data, preset basic weight mapping rules, and preset basic parameters of grid compensation nodes, the compensation weight of each grid compensation node is calculated, including:

[0023] Based on the priority level value and the basic weight mapping rule, the basic compensation weight of each power grid compensation node is obtained;

[0024] For each power grid compensation node, the proportion of the basic parameters of the power grid compensation node in the total basic parameters of all power grid compensation nodes is calculated to obtain the basic parameter proportion data of each power grid compensation node.

[0025] For each power grid compensation node, the differences in the basic parameters of the power grid compensation node are quantified based on the weight data of the basic parameters of the power grid compensation node, and the difference coefficient of the basic parameters of each power grid compensation node is obtained.

[0026] For each power grid compensation node, the basic compensation weight is adjusted based on the difference coefficient to obtain the compensation weight of each power grid compensation node.

[0027] Furthermore, for each grid compensation node, the proportion of its basic parameters to the total basic parameters of all grid compensation nodes is calculated, yielding the basic parameter proportion data for each grid compensation node, including:

[0028] For each power grid compensation node, the capacity ratio of each compensation node is calculated using the following formula, based on its capacity value:

[0029]

[0030] Among them, P iv X is the capacity ratio value of power grid compensation node i. iv P is the capacity value of grid compensation node i, m is the total number of grid compensation nodes, and P is the capacity value of grid compensation node i. nv It is the capacity value of any power grid compensation node n;

[0031] For each power grid compensation node, the response speed ratio of each node is calculated using the following formula, based on its response speed value:

[0032]

[0033] Among them, P isX is the weight value of the response speed of grid compensation node i. is P is the response speed value of grid compensation node i, m is the total number of grid compensation nodes, and P is the response speed value of grid compensation node i. ns It is the response speed value of any power grid compensation node n;

[0034] For each power grid compensation node, the reliability weight value of each node is calculated using the following formula, based on its reliability value:

[0035]

[0036] Among them, P ik X is the reliability ratio of power grid compensation node i. ik P is the reliability value of power grid compensation node i, m is the total number of power grid compensation nodes, and P is the reliability value of power grid compensation node i. nk It is the reliable value of any power grid compensation node n;

[0037] For each power grid compensation node, the basic parameter weight data of each power grid compensation node are obtained based on the capacity weight value, response speed weight value, and reliability weight value.

[0038] Furthermore, based on compensation weights and real-time status data, the grid collaborative compensation data is allocated to each grid compensation node, generating compensation instructions for each grid compensation node, including:

[0039] Based on the compensation weights of each power grid compensation node, power grid collaborative compensation data, and real-time status data, the compensation demand value allocated to each power grid compensation node is calculated using the following formula, thus obtaining the contribution demand value of each power grid compensation node:

[0040]

[0041] Among them, Q i Q is the contribution demand value of power grid compensation node i. r It is the compensation demand value, w i Q is the compensation weight of power grid compensation node i. a,i This is the real-time status data of grid compensation node i, where m is the total number of grid compensation nodes, and Q is the real-time status data of grid compensation node i. a,n It is the real-time status data of any power grid compensation node n, w n It is the compensation weight of any power grid compensation node m;

[0042] Based on the contribution demand values ​​of each power grid compensation node and the preset working parameter database, compensation instructions for each power grid compensation node are generated.

[0043] Furthermore, the method also includes:

[0044] Obtain feedback voltage fluctuation data; the feedback voltage fluctuation data is used to characterize the fluctuation of the power grid after the compensation command is generated.

[0045] Calculate the standard deviation and steady-state deviation of the feedback voltage fluctuation data to obtain the feedback effect value of the compensation command;

[0046] When the feedback effect value is less than the preset feedback threshold, the gradient descent method is used to update the basic weight mapping rule, and the updated basic weight mapping rule is obtained.

[0047] Secondly, this application also provides a power quality compensation device for new energy grid connection, comprising:

[0048] The data acquisition module is used to acquire voltage fluctuation data of the power grid and real-time status data of each power grid compensation node;

[0049] The compensation calculation module is used to quantify the fluctuation of the power grid based on voltage fluctuation data to obtain power grid collaborative compensation data. The power grid collaborative compensation data includes the priority level value of power quality compensation and the compensation demand value of power quality compensation of the power grid.

[0050] The compensation allocation module is used to calculate the compensation weight of each power grid compensation node based on power grid collaborative compensation data, preset basic weight mapping rules, and preset basic parameters of power grid compensation nodes. The basic parameters of power grid compensation nodes include the capacity value, response speed value, and reliability value of each power grid compensation node. The compensation weight is used to characterize the priority of power grid compensation nodes in power grid power quality compensation.

[0051] The instruction generation module is used to allocate grid collaborative compensation data to each grid compensation node based on compensation weight and real-time status data, and generate compensation instructions for each grid compensation node; the compensation instructions are used to instruct the adjustment of the operating parameters of the grid compensation node.

[0052] 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 implement any of the power quality compensation methods for new energy grid access described in the first aspect of this application.

[0053] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any of the power quality compensation methods for new energy grid access described in the first aspect of this application.

[0054] The aforementioned power quality compensation method and equipment for new energy grid access acquires grid voltage fluctuation data and real-time status data of each grid compensation node; quantifies grid fluctuations based on voltage fluctuation data to obtain grid collaborative compensation data; the grid collaborative compensation data includes the priority level value and compensation demand value of power quality compensation; based on the grid collaborative compensation data, preset basic weight mapping rules, and preset basic parameters of grid compensation nodes, the compensation weight of each grid compensation node is calculated; the basic parameters of grid compensation nodes include the capacity value, response speed value, and reliability value of each grid compensation node; the compensation weight is used to characterize the priority of grid compensation nodes in grid power quality compensation; based on the compensation weight and real-time status data, the grid collaborative compensation data is allocated to each grid compensation node, generating compensation instructions for each grid compensation node; the compensation instructions are used to instruct the adjustment of the operating parameters of the grid compensation nodes, effectively avoiding conflicts, oscillations, or resource waste that may be caused by multiple device compensation actions, significantly improving the overall response speed, compensation accuracy, and operating efficiency of the grid compensation system, and improving the power quality compensation efficiency of the grid in environments with a high proportion of new energy access. Attached Figure Description

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

[0056] Figure 1 A schematic flowchart illustrating a power quality compensation method for new energy grid access, provided as an embodiment of this application;

[0057] Figure 2 A schematic diagram of the structure of a power quality compensation device for new energy grid access provided in one embodiment of this application;

[0058] Figure 3 This is a schematic diagram of a computer device for a power quality compensation method for new energy grid access, provided as an embodiment of this application. Detailed Implementation

[0059] 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.

[0060] In one embodiment, such as Figure 1As shown, a power quality compensation method for new energy grid connection is provided. This embodiment illustrates the method applied to a terminal. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps S101-S104, wherein:

[0061] S101, acquire voltage fluctuation data of the power grid and real-time status data of each power grid compensation node.

[0062] Specifically, the terminal acquires real-time voltage fluctuation data of the power grid and real-time status data of each power grid compensation node. The voltage fluctuation data represents the voltage value of the power grid's current operating state, which can be continuously collected in time series form using voltage sensors or synchronous phasor measurement devices deployed at key nodes of the power grid. The format can be {x} t x, t}, where t is the sampling timestamp, x t This is the voltage value at sampling timestamp t. Grid compensation nodes are callable intelligent power compensation devices, including but not limited to photovoltaic inverters, energy storage converters, and dedicated SVG / APF devices. Real-time status data is used to characterize the real-time operating status of the grid compensation nodes, including but not limited to the real-time reactive power compensation capacity of the grid compensation nodes.

[0063] S102, quantify the fluctuation of the power grid based on voltage fluctuation data to obtain power grid collaborative compensation data; the power grid collaborative compensation data includes the priority level value of power quality compensation of the power grid and the compensation demand value of power quality compensation of the power grid.

[0064] Specifically, the terminal filters and denoises the voltage fluctuation data. Then, by subtracting the filtered voltage fluctuation data from a preset normal grid voltage threshold, it obtains the voltage deviation between the real-time operating state and the normal state of the grid. Based on this voltage deviation and power calculation principles, it calculates the total reactive power compensation required for power quality compensation, thus obtaining the compensation demand value. It also calculates the voltage fluctuation rate and amplitude based on the voltage fluctuation data, and analyzes the urgency of power quality compensation in the grid using historical data to obtain a priority level value for power quality compensation. This priority level value characterizes the urgency of power quality compensation in the grid. For example, a mapping model can be constructed by learning the nonlinear relationship between the voltage fluctuation rate, voltage fluctuation amplitude, and power quality compensation priority value during historical power quality compensation processes using machine learning algorithms. This model allows for the input of real-time voltage fluctuation rate and amplitude to obtain the real-time priority value. Optionally, the priority value can be set according to the actual power quality compensation response requirements and the requirements for grid compensation nodes. For example, the priority value can be set as follows: when the grid voltage fluctuation is severe but slow, the priority value is 1; when the grid voltage fluctuation is gentle but rapid, the priority value is 0.

[0065] S103, based on grid collaborative compensation data, preset basic weight mapping rules and preset basic parameters of grid compensation nodes, calculate the compensation weight of each grid compensation node; the basic parameters of grid compensation nodes include the capacity value, response speed value and reliability value of each grid compensation node; the compensation weight is used to characterize the priority of grid compensation nodes in power quality compensation of the grid.

[0066] Specifically, for each grid compensation node, the terminal obtains the basic compensation weights corresponding to the capacity, response speed, and reliability values ​​in the basic parameters of the grid compensation node based on the priority level value in the grid collaborative compensation data and through a preset basic weight mapping rule. It then adjusts the basic compensation weights corresponding to the capacity, response speed, and reliability values ​​by quantifying the differences between the capacity, response speed, and reliability values ​​of each grid compensation node, and obtains the compensation weight of the grid compensation node through a weighted combination. The preset basic weight mapping rule is used to characterize the mapping relationship between the priority level value and the basic compensation weights of the capacity, response speed, and reliability values. The preset basic parameters of the grid compensation node characterize the inherent attribute parameters of each grid compensation node, including the capacity, response speed, and reliability values. The capacity value is the rated apparent power of the grid compensation node, with a value range of [0,1]. The response speed value characterizes the response time of the grid compensation node from receiving the instruction to achieving the target output, with a value range of [0,1]. The reliability value characterizes the reliability of the grid compensation node, which can be obtained by dividing the mean time between failures (MTBF) of the grid compensation node by the total operating time, with a value range of [0,1]. For example, the specific form of the preset basic weight mapping rule can be: {priority level value: 0 - basic compensation weight for capacity value, basic compensation weight for response speed value, basic compensation weight for reliability value: 0.1, 0.7, 0.2}.

[0067] S104, based on compensation weights and real-time status data, distributes grid collaborative compensation data to each grid compensation node and generates compensation instructions for each grid compensation node; the compensation instructions are used to instruct the adjustment of the operating parameters of the grid compensation node.

[0068] Specifically, for each grid compensation node, the terminal allocates the power quality compensation demand value from the grid collaborative compensation data according to the compensation weight of the grid compensation node and the real-time status data to obtain the contribution demand value of the grid compensation node. Based on a preset working parameter database, the terminal obtains the working parameters and magnitudes that the grid compensation node needs to adjust to fulfill this contribution demand value, thus forming the compensation instruction for the grid compensation node. Illustratively, the contribution demand value includes, but is not limited to, the reactive power compensation amount undertaken by the grid compensation node; optionally, the preset working parameter database is used to characterize the mapping relationship between the reactive power compensation amount completed by the grid compensation node and the set working parameters, and can be set according to actual work requirements.

[0069] This embodiment provides a power quality compensation method for renewable energy grid integration. By acquiring grid voltage fluctuation data and real-time data from each grid compensation node, and combining this data with the fixed attribute parameters of each compensation node, the method dynamically allocates the required grid quality compensation value to each compensation node based on the characteristics of grid disturbances and the real-time capabilities of the compensation nodes. This is done using intelligent weight calculation and a global optimization allocation mechanism, and generates coordinated control commands to obtain compensation instructions for each compensation node. This effectively avoids conflicts, oscillations, or resource waste that may be caused by multiple device compensation actions, significantly improving the overall response speed, compensation accuracy, and operating efficiency of grid power quality compensation, and enhancing the power quality compensation efficiency of the grid in environments with a high proportion of renewable energy integration.

[0070] In one embodiment, the fluctuation of the power grid is quantified based on voltage fluctuation data to obtain power grid collaborative compensation data, including:

[0071] S201 filters the voltage fluctuation data to eliminate outliers and obtain clean voltage fluctuation data.

[0072] Specifically, based on preset voltage maximum and minimum amplitude thresholds, the terminal selects sampling timestamp points in the voltage fluctuation data where the voltage value is greater than the voltage maximum threshold or less than the voltage minimum amplitude threshold as abnormal value points, and removes these abnormal value points. The remaining sampling timestamp value points constitute clean voltage fluctuation data. For example, the preset voltage maximum and minimum amplitude thresholds can be set according to the actual voltage change amplitude during operation. The voltage maximum threshold can be set to 1.5 times the rated voltage, and the voltage minimum amplitude threshold can be set to 0.5 times the rated voltage.

[0073] S202, calculate the extreme values ​​of the clean voltage fluctuation data to obtain the voltage fluctuation amplitude.

[0074] Specifically, the terminal identifies the maximum and minimum voltage values ​​in the clean voltage fluctuation data, and obtains the voltage fluctuation amplitude by subtracting the maximum and minimum voltage values.

[0075] S203, based on a preset time window, calculates the rate of change of clean voltage fluctuation data within the time window to obtain the voltage fluctuation rate.

[0076] Specifically, the terminal uses the formula: ΔV=(V s -V e The formula ΔV / Δt is used to calculate the rate of change of clean voltage fluctuation data within a preset time window, thus obtaining the voltage fluctuation rate. In the aforementioned calculation formula, ΔV is the voltage fluctuation rate, and V is the voltage fluctuation rate. s It is the real-time voltage value, Ve It is the voltage value separated from the real-time time by a time window, where Δt is the time window. For example, the time window is used to measure the duration of instantaneous changes in voltage fluctuations, and can be set according to actual operating conditions.

[0077] S204, based on the voltage fluctuation amplitude and voltage fluctuation rate input into the preset power grid compensation priority level mapping model, obtains the priority level value.

[0078] Specifically, the terminal inputs the voltage fluctuation amplitude and voltage fluctuation rate into a preset grid compensation priority mapping model to obtain the real-time power quality compensation priority value. For example, the preset grid compensation priority mapping model can be constructed by learning the nonlinear relationship between the voltage fluctuation rate, voltage fluctuation amplitude, and power quality compensation priority value during historical power quality compensation processes using machine learning and fuzzy logic algorithms. This allows for the input of real-time voltage fluctuation rate and amplitude to obtain the real-time priority value. The power quality compensation priority value can be set according to actual work requirements; a smaller priority value indicates a more urgent power quality compensation.

[0079] S205, based on the voltage fluctuation amplitude and the preset normal voltage threshold of the power grid, calculates the total power quality compensation of the power grid and obtains the compensation demand value.

[0080] Specifically, the terminal uses the formula Q based on the voltage fluctuation amplitude and the preset normal grid voltage threshold: a =k*(ΔV-ΔV) t ), calculate the total reactive power compensation demand of the power grid, and obtain the compensation demand value. In the aforementioned calculation formula, Q a Here, k is the compensation demand value, k is the compensation coefficient, and ΔV is the voltage fluctuation rate. t This is the normal voltage threshold of the power grid. For example, the compensation demand value is the total reactive power that all power grid compensation nodes need to provide to eliminate the current voltage fluctuation. A positive compensation demand value indicates that capacitive reactive power needs to be injected; a negative compensation demand value indicates that inductive reactive power needs to be injected. Optionally, the compensation coefficient is used for characterization and can be set according to the short-circuit capacity or equivalent impedance of the power grid in actual operation. Illustratively, the normal voltage threshold of the power grid is ΔV. t It represents the maximum allowable fluctuation threshold when the power grid is operating normally, and can be set according to actual operation.

[0081] S206, based on priority level values ​​and compensation demand values, obtains grid collaborative compensation data.

[0082] Specifically, the terminal integrates the priority level value and the compensation demand value to obtain grid collaborative compensation data.

[0083] This embodiment provides a power quality compensation method for new energy grid integration. It cleans and filters voltage fluctuation data to obtain clean voltage fluctuation data, extracts the voltage fluctuation amplitude (characterizing the severity of fluctuations) and the voltage fluctuation rate (characterizing the urgency of fluctuations), and inputs these two features into a preset mapping model for intelligent matching, outputting a priority value that determines the resource allocation strategy. Furthermore, it calculates the total reactive power compensation requirement needed to eliminate fluctuations based on the voltage amplitude and grid parameters, obtaining the compensation requirement value. Finally, it combines the priority value and the compensation requirement value to form grid collaborative compensation data. This method achieves deep perception and feature extraction of grid fluctuation states, transforming voltage signals into grid collaborative compensation data that combines strategic guidance and physical accuracy. It provides reliable input data for subsequent reactive power resource allocation at each grid compensation node, significantly improving the overall efficiency of the compensation system.

[0084] In one embodiment, the power grid compensation priority mapping model is obtained through the following method:

[0085] S301, Obtain the historical compensation database of the power grid; the historical compensation database of the power grid includes the voltage fluctuation amplitude, voltage fluctuation rate and corresponding priority level value of the historical compensation process.

[0086] Specifically, the terminal acquires the historical compensation database of the power grid, which includes voltage fluctuation values, voltage fluctuation rates, and priority levels corresponding to the compensation processes during historical power quality compensation. The priority level value characterizes the urgency of power quality compensation for the power grid. Optionally, the priority level value can be set according to the actual response requirements of power quality compensation and the requirements for power grid compensation nodes. For example, a priority level of 1 can be used when the grid voltage fluctuation is severe but slow, and a priority level of 0 can be used when the grid voltage fluctuation is gentle but rapid.

[0087] S302, using the voltage fluctuation amplitude and voltage fluctuation rate of the historical compensation process as feature values, and the corresponding priority level as feature attributes, to obtain model training data; and according to the preset division ratio, divide the model training data into training samples and test samples.

[0088] Specifically, the terminal formats and organizes the data in the historical compensation database, using the voltage fluctuation amplitude and rate of change in each compensation process as feature values, and the priority level of the compensation process as a feature attribute, to form a model training sample. The model training samples from all compensation processes in the historical compensation database constitute the model training data. The terminal also divides the model training data into training samples and test samples according to a preset ratio. The training samples are used to train the model to learn the nonlinear relationship between the voltage fluctuation amplitude, rate of change, and the corresponding priority level value. The test samples are used to evaluate the model's performance on new data, preventing overfitting and verifying its generalization performance. Illustratively, the preset ratio can be dynamically adjusted according to the model's recognition accuracy in actual work; the default setting is training samples:test samples = 7:3.

[0089] S303, based on the fuzzy C-means clustering algorithm and training samples, constructs a preliminary power grid compensation priority mapping model.

[0090] Specifically, the terminal uses the fuzzy C-means algorithm to perform fuzzy clustering on the feature values ​​and corresponding feature attributes in the training samples, calculating the typical feature value of each feature attribute. This learns the nonlinear relationship between the priority level value most likely corresponding to different voltage fluctuation amplitudes and voltage fluctuation rates, thus obtaining a preliminary power grid compensation priority level mapping model. The fuzzy C-means clustering algorithm is a soft partitioning clustering algorithm based on objective function optimization. Its principle is to divide the training sample set into fuzzy clusters with the same number of feature attributes as the number of feature attributes, so that each feature value belongs to all clusters with different membership degrees. Through iterative optimization, the algorithm minimizes the weighted sum of squared distances from the feature values ​​corresponding to all feature attributes to each cluster center, thereby finding the optimal cluster center position and membership matrix. The optimal cluster center position for each feature attribute is the typical feature value of that feature attribute.

[0091] S304. The preliminary power grid compensation priority level mapping model is trained using test samples until the preliminary power grid compensation priority level mapping model meets the preset accuracy requirements, thus obtaining the power grid compensation priority level mapping model.

[0092] Specifically, the terminal uses a test sample set to test the trained preliminary power grid compensation priority mapping model. When the preliminary power grid compensation priority mapping model satisfies the requirements, a trained power grid compensation priority mapping model is obtained, which outputs the priority value with the highest probability based on the input voltage fluctuation amplitude and voltage fluctuation rate. Illustratively, the preset accuracy requirement is 85%, but this can be adjusted according to actual work requirements.

[0093] This embodiment provides a power quality compensation method for renewable energy grid integration. It collects a historical compensation database including voltage fluctuation amplitude, voltage fluctuation rate, and corresponding priority level values ​​from historical compensation processes. The data is formatted and partitioned to obtain a training sample set and a wiped sample set. Fuzzy C-means clustering is used on the training sample set to mine implicit classification rules from data features to construct a preliminary grid compensation priority level mapping model. The model is repeatedly verified and optimized using test samples until it reaches the preset accuracy requirements, resulting in the final grid compensation priority level mapping model. This successfully transforms the decision-making experience of human experts into a mathematical model, enabling real-time intelligent identification and classification of grid fluctuations and outputting the optimal priority level value, thus improving the power quality compensation efficiency of the grid in environments with a high proportion of renewable energy integration.

[0094] In one embodiment, based on grid collaborative compensation data, preset basic weight mapping rules, and preset basic parameters of grid compensation nodes, the compensation weight of each grid compensation node is calculated, including:

[0095] S401, based on priority level values ​​and basic weight mapping rules, obtains the basic compensation weights of each power grid compensation node.

[0096] Specifically, the terminal determines the basic weights of the basic parameters of the grid compensation nodes corresponding to the priority level values ​​based on the priority level values ​​and the basic weight mapping rules, thus obtaining the basic compensation weights of each grid compensation node. The preset basic weight mapping rules characterize the mapping relationship between the basic compensation weights of the priority level values ​​and capacity values, and response speed values ​​and reliability values. For example, the preset basic weight mapping rules can be set according to the priority level values ​​and the grid fluctuations they represent. For instance, if a priority level value of 1 indicates that the grid voltage fluctuations are severe but slow, the capacity value of the grid compensation node should be given priority. In this case, the specific form of the basic weight mapping rule can be: {Priority level value: 1 - basic compensation weight of capacity value, basic compensation weight of response speed value, basic compensation weight of reliability value: 0.7, 0.2, 0.1}.

[0097] S402, for each power grid compensation node, calculate the proportion of the basic parameters of the power grid compensation node in the total basic parameters of all power grid compensation nodes, and obtain the basic parameter proportion data of each power grid compensation node.

[0098] Specifically, for each grid compensation node, the terminal calculates the proportion of its capacity value to the total capacity value of all grid compensation nodes, obtaining the capacity proportion value of that node; the terminal also calculates the proportion of its response speed value to the total response speed value of all grid compensation nodes, obtaining the response speed proportion value of that node; the terminal further calculates the proportion of its reliability value to the total reliability value of all grid compensation nodes, obtaining the reliability proportion value of that node; the terminal integrates the capacity proportion value, response speed proportion value, and reliability proportion value of that node to obtain the basic parameter proportion data of that grid compensation node. For example, the basic parameter proportion data is used to characterize the processing capacity of a single grid compensation node relative to all grid compensation nodes.

[0099] S403, for each power grid compensation node, quantify the differences in the basic parameters of the power grid compensation node based on the weight data of the basic parameters of the power grid compensation node, and obtain the difference coefficient of the basic parameters of the power grid compensation node for each power grid compensation node.

[0100] Specifically, for each grid compensation node, the terminal uses the following formula based on the capacity ratio, response speed ratio, and reliability ratio values ​​in the basic parameter weighting data of the grid compensation node: and g j =1-e j The differences in the basic parameters of the power grid compensation nodes are quantified to obtain the corresponding capacity difference coefficient, response speed difference coefficient, and reliability difference coefficient. The terminal then integrates these coefficients to obtain the difference coefficient of the basic parameters of each power grid compensation node. In the aforementioned formula, e... j is the distribution entropy of any parameter j among the basic parameters of the power grid compensation node, where j can be a capacity value, response speed value, or reliability value. m is the total number of power grid compensation nodes. p nj It is the proportion data of any parameter j of any power grid compensation node n, p nj It can be a capacity weighting value, a response speed weighting value, or a reliability weighting value. j It is the difference coefficient of any parameter j in the basic parameters of the power grid compensation node. The larger the difference coefficient, the greater the difference of the parameter among different nodes. The more information it can provide when distinguishing node capabilities and making weight decisions, the more important it should be in subsequent weight calculations.

[0101] S404: For each power grid compensation node, the basic compensation weight is adjusted based on the difference coefficient to obtain the compensation weight of each power grid compensation node.

[0102] Specifically, for each grid compensation node, the terminal uses the following formula based on the capacity difference coefficient, response speed difference coefficient, reliability difference coefficient, and basic compensation weight within the difference coefficient of the grid compensation node: and The compensation weights of the power grid compensation nodes are calculated. In the aforementioned formula, w j It is the comprehensive weight of any parameter j in the basic parameters of the power grid compensation node, where j can be the capacity value, response speed value, and reliability value. j,s It is the basic compensation weight of any parameter j in the basic parameters of the power grid compensation node, g j It is the difference coefficient of any parameter j in the basic parameters of the power grid compensation node. This is used to calculate the sum of the products of the basic compensation weights and difference coefficients of all parameters in the basic parameters of the power grid compensation node. i It is the comprehensive score of any power grid compensation node i, x ij It is the value of any parameter j in the basic parameters of any power grid compensation node i. This is used to calculate the sum of the combined weights and corresponding parameter values ​​of all parameters in the basic parameters of any power grid compensation node i. i is the compensation weight of any power grid compensation node i. m is the total number of power grid compensation nodes, which can be set according to the actual number of power grid compensation nodes. s n It is the comprehensive score of any power grid compensation node n.

[0103] This embodiment provides a power quality compensation method for new energy grid access. It obtains the basic weights of each parameter in the basic parameters of the grid compensation node based on priority level values ​​and basic weight mapping rules. Then, it calculates the proportion of each node's basic parameters in the entire network to obtain standardized proportion data. Based on information entropy theory, it calculates the difference coefficients of each parameter in the basic parameters of the grid compensation node according to the uniformity of the proportion data distribution. These difference coefficients are used to adjust and integrate the basic weights. Through weighted summation and normalization, the compensation weight of each grid compensation node is obtained. This method balances the global compensation target with the actual capabilities of individual grid compensation nodes, scientifically allocating weights to generate efficient compensation commands, and significantly improving the operational efficiency of power quality compensation.

[0104] In one embodiment, for each grid compensation node, the proportion of the grid compensation node's basic parameters to the total basic parameters of all grid compensation nodes is calculated to obtain the basic parameter proportion data for each grid compensation node, including:

[0105] S501, for each power grid compensation node, the capacity ratio of each power grid compensation node is calculated using the following formula based on the capacity value of each node:

[0106]

[0107] Among them, P iv X is the capacity ratio value of power grid compensation node i. iv P is the capacity value of grid compensation node i, m is the total number of grid compensation nodes, and P is the capacity value of grid compensation node i. nv It is the capacity value of any power grid compensation node n.

[0108] Specifically, for each grid compensation node, the terminal calculates the capacity proportion value of each grid compensation node using a formula based on the node's capacity value. Illustratively, the capacity proportion value P of grid compensation node i... iv The capacity value of a single grid compensation node is used to characterize the proportion of the total compensation capacity of all available grid compensation nodes, and its value ranges from [0,1]. Optionally, the capacity value X of grid compensation node i... iv The rated apparent power of the equipment at a power grid compensation node can be obtained based on preset basic parameters of the power grid compensation node. For example, the total number of power grid compensation nodes, m, is the total number of power grid compensation nodes and can be set according to the actual number of power grid compensation nodes. Optionally, the capacity value P of any power grid compensation node n... nv Used to calculate the sum of the capacity values ​​of all grid compensation nodes.

[0109] S502, for each power grid compensation node, the response speed ratio of each power grid compensation node is calculated using the following formula based on the response speed value of each power grid compensation node:

[0110]

[0111] Among them, P is X is the weight value of the response speed of grid compensation node i. is P is the response speed value of grid compensation node i, m is the total number of grid compensation nodes, and P is the response speed value of grid compensation node i. ns It is the response speed value of any power grid compensation node n.

[0112] Specifically, for each grid compensation node, the terminal calculates the response speed weight value of each grid compensation node using a formula based on the response speed value of each node. Illustratively, the response speed weight value P of grid compensation node i... is The response speed value of a single grid compensation node is used to characterize the proportion of the total response speed values ​​of all available grid compensation nodes, and its value ranges from [0,1]. Optionally, the response speed value X of grid compensation node i...is This can be obtained from preset basic parameters of the power grid compensation nodes, representing the time required for the equipment of the power grid compensation node to reach the target value from receiving the command. For example, the total number of power grid compensation nodes, m, is the total number of power grid compensation nodes, which can be set according to the actual number of power grid compensation nodes. Optionally, the capacity value P of any power grid compensation node n... ns Used to calculate the sum of the response speed values ​​of all grid compensation nodes.

[0113] S503, for each power grid compensation node, the reliability weight value of each power grid compensation node is calculated using the following formula based on the reliability value of each power grid compensation node:

[0114]

[0115] Among them, P ik X is the reliability ratio of power grid compensation node i. ik P is the reliability value of power grid compensation node i, m is the total number of power grid compensation nodes, and P is the reliability value of power grid compensation node i. nk It is the reliable value of any power grid compensation node n.

[0116] Specifically, for each grid compensation node, the terminal calculates the reliability weight value of each grid compensation node using a formula based on the reliability value of each node. Illustratively, the reliability weight value P of grid compensation node i... ik The reliability proportion is used to characterize the ratio of the reliability value of a single grid compensation node to the total reliability value of all available grid compensation nodes. Its value ranges from [0,1]. A higher reliability proportion indicates that the grid compensation node is better in terms of reliability compared to other grid compensation nodes. Optionally, the reliability value X of grid compensation node i... ik The capacity can be obtained based on preset basic parameters of the power grid compensation nodes, and can be calculated by dividing the mean time between failures (MTBF) of the power grid compensation nodes by the total operating time. For example, the total number of power grid compensation nodes, m, is the total number of power grid compensation nodes, which can be set according to the actual number of power grid compensation nodes. Optionally, the capacity value P of any power grid compensation node n... nk Used to calculate the sum of reliability values ​​for all power grid compensation nodes.

[0117] S504, for each power grid compensation node, obtains the basic parameter weight data of each power grid compensation node based on the capacity weight value, response speed weight value, and reliability weight value.

[0118] Specifically, the terminal integrates the capacity ratio, response speed ratio, and reliability ratio of the same power grid compensation node to obtain the basic parameter ratio data of each power grid compensation node.

[0119] This embodiment provides a power quality compensation method for new energy grid access. By standardizing the capacity, response speed, and reliability values ​​of the basic parameters of each grid compensation node to generate weight data, the basic parameter weight data of each grid compensation node is obtained. This eliminates the incomparability between different types of parameters, provides reliable parameter weight data for generating scientific and reasonable compensation weights, and significantly improves the operating efficiency of power quality compensation.

[0120] In one embodiment, based on compensation weights and real-time status data, grid collaborative compensation data is allocated to each grid compensation node, and compensation instructions are generated for each grid compensation node, including:

[0121] S601, based on the compensation weights of each power grid compensation node, power grid collaborative compensation data, and real-time status data, the compensation demand value allocated to each power grid compensation node is calculated using the following formula, thus obtaining the contribution demand value of each power grid compensation node:

[0122]

[0123] Among them, Q i Q is the contribution demand value of power grid compensation node i. r It is the compensation demand value, w i Q is the compensation weight of power grid compensation node i. a,i This is the real-time status data of grid compensation node i, where m is the total number of grid compensation nodes, and Q is the real-time status data of grid compensation node i. a,n It is the real-time status data of any power grid compensation node n, w n It is the compensation weight of any power grid compensation node m.

[0124] Specifically, the terminal allocates the total reactive power compensation to each grid compensation node using a formula based on the compensation weight of each grid compensation node, the compensation demand value in the grid collaborative compensation data, and real-time status data, thus obtaining the contribution demand value of each grid compensation node. Illustratively, the contribution demand value Q of grid compensation node i... i This is used to characterize the reactive power that grid compensation node i needs to contribute. Optionally, the compensation demand value Q r This refers to the compensation demand value included in the aforementioned grid collaborative compensation data, which is the total reactive power required to stabilize the grid voltage. Schematic, the compensation weight w of grid compensation node i... i This refers to the compensation weight calculated above. Optionally, the real-time status data Q of grid compensation node i... a,iThe aforementioned real-time status data represents the real-time reactive power compensation capacity of grid compensation node i. Illustratively, the total number of grid compensation nodes m is the total number of grid compensation nodes, which can be set according to the actual number of grid compensation nodes. Optionally, the real-time status data Q of any grid compensation node n... a,n It represents the real-time reactive power compensation capacity of any power grid compensation node n. Schematically, it represents the compensation weight w of any power grid compensation node m. n It is the compensation weight of each power grid compensation node obtained from the aforementioned calculation.

[0125] S602 generates compensation instructions for each power grid compensation node based on the contribution demand value of each power grid compensation node and the preset working parameter database.

[0126] Specifically, the terminal obtains the adjusted operating parameters and magnitudes required for each power grid compensation node to contribute reactive power according to a preset operating parameter database, and forms the compensation instructions for each power grid compensation node. Optionally, the preset operating parameter database is used to characterize the mapping relationship between the reactive power contributed by the power grid compensation node and the operating parameters set on the equipment of the power grid compensation node, and can be set according to actual operation.

[0127] This embodiment provides a power quality compensation method for renewable energy grid integration. It accurately decomposes the total global reactive power demand into the contribution demand value of each grid compensation node, and combines this with the inherent operating parameters of the equipment. The contribution demand value is then converted using a protocol to generate compensation commands that can directly drive the equipment. This method balances the optimal compensation strategy with the objective energy of each grid compensation node, and imposes real-time operational constraints on each node. This significantly enhances the reliability and security of power quality compensation, effectively preventing execution failures or equipment damage due to commands exceeding equipment capabilities. It significantly improves the overall response speed, compensation accuracy, and operating efficiency of the grid compensation system, thereby increasing the power quality compensation efficiency of the grid in environments with a high proportion of renewable energy integration.

[0128] In one embodiment, the method further includes:

[0129] S701, acquire feedback voltage fluctuation data; feedback voltage fluctuation data is used to characterize the fluctuation of the power grid after the compensation command is generated.

[0130] Specifically, the terminal obtains the voltage fluctuation data of the power grid after executing the compensation command and gets the feedback voltage fluctuation data.

[0131] S702 calculates the standard deviation and steady-state deviation of the feedback voltage fluctuation data to obtain the feedback effect value of the compensation command.

[0132] Specifically, the terminal performs statistical analysis on the feedback voltage fluctuation data, calculates the difference between the average value of the feedback voltage fluctuation data and the preset voltage fluctuation value, and obtains the steady-state deviation of the feedback voltage fluctuation data; it also calculates the standard deviation of the feedback voltage fluctuation data using the formula: J=|ΔV r |+k*σ r The feedback effect value of the compensation command is calculated. In the aforementioned formula, J is the feedback effect value of the compensation command; the smaller the value, the better the power quality after compensation and the better the compensation effect. ΔV r This is the steady-state deviation. k is a preset penalty coefficient used to characterize the impact of steady-state deviation and volatility. σ r This refers to the standard deviation. Indicatively, the preset voltage fluctuation value can be set according to the actual requirements for voltage fluctuation after power compensation in practical work. Optionally, the penalty coefficient can be set according to actual work conditions.

[0133] S703: When the feedback effect value is less than the preset feedback threshold, the gradient descent method is used to update the basic weight mapping rule and obtain the updated basic weight mapping rule.

[0134] Specifically, when the feedback effect value is less than a preset feedback threshold, the terminal employs gradient descent. This involves calculating the partial derivatives of the feedback effect value with respect to the base compensation weights for capacity, response speed, and reliability corresponding to the real-time priority value in the preset base weight mapping rules. The goal is to find the optimal solution that minimizes the feedback effect value, thereby adjusting these base compensation weights to form an updated base weight mapping rule. Gradient descent is an iterative optimization algorithm based on the first derivative. Its core principle is to progressively adjust the variable values ​​along the negative gradient direction of the objective function with respect to the decision variables to find the optimal solution that minimizes the objective function.

[0135] This embodiment provides a power quality compensation method for renewable energy grid integration. It collects actual grid response data as feedback to obtain feedback voltage fluctuation data. The comprehensive effect of the compensation is quantitatively evaluated by calculating steady-state deviation and standard deviation, yielding a feedback effect value. Based on this feedback effect value, a gradient descent optimization algorithm is used to fine-tune the weights in the basic weight mapping rule to seek better performance, resulting in an updated basic weight mapping rule. This method adjusts the basic weights of each parameter according to actual feedback, continuously adapting to changes in grid operation modes and equipment characteristics, thus improving the power quality compensation efficiency of the grid in environments with a high proportion of renewable energy integration.

[0136] The aforementioned power quality compensation method and equipment for new energy grid access acquires grid voltage fluctuation data and real-time status data of each grid compensation node; quantifies grid fluctuations based on voltage fluctuation data to obtain grid collaborative compensation data; the grid collaborative compensation data includes the priority level value and compensation demand value of power quality compensation; based on the grid collaborative compensation data, preset basic weight mapping rules, and preset basic parameters of grid compensation nodes, the compensation weight of each grid compensation node is calculated; the basic parameters of grid compensation nodes include the capacity value, response speed value, and reliability value of each grid compensation node; the compensation weight is used to characterize the priority of grid compensation nodes in grid power quality compensation; based on the compensation weight and real-time status data, the grid collaborative compensation data is allocated to each grid compensation node, generating compensation instructions for each grid compensation node; the compensation instructions are used to instruct the adjustment of the operating parameters of the grid compensation nodes, effectively avoiding conflicts, oscillations, or resource waste that may be caused by multiple device compensation actions, significantly improving the overall response speed, compensation accuracy, and operating efficiency of the grid compensation system, and improving the power quality compensation efficiency of the grid in environments with a high proportion of new energy access.

[0137] 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 of other steps.

[0138] Based on the same inventive concept, this application also provides a power quality compensation device for new energy grid access, which implements the power quality compensation method for new energy grid access described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the power quality compensation device for new energy grid access provided below can be found in the limitations of the power quality compensation method for new energy grid access described above, and will not be repeated here.

[0139] In one exemplary embodiment, such as Figure 2 As shown, a power quality compensation device 200 for new energy grid connection is provided, comprising:

[0140] The data acquisition module 201 is used to acquire voltage fluctuation data of the power grid and real-time status data of each power grid compensation node;

[0141] The compensation calculation module 202 is used to quantify the fluctuation of the power grid based on voltage fluctuation data to obtain power grid collaborative compensation data; the power grid collaborative compensation data includes the priority level value of power quality compensation of the power grid and the compensation demand value of power quality compensation of the power grid.

[0142] The compensation allocation module 203 is used to calculate the compensation weight of each power grid compensation node based on power grid collaborative compensation data, preset basic weight mapping rules, and preset basic parameters of power grid compensation nodes. The basic parameters of power grid compensation nodes include the capacity value, response speed value, and reliability value of each power grid compensation node. The compensation weight is used to characterize the priority of power grid compensation nodes in power grid power quality compensation.

[0143] The instruction generation module 204 is used to allocate grid collaborative compensation data to each grid compensation node based on compensation weight and real-time status data, and generate compensation instructions for each grid compensation node; the compensation instructions are used to instruct the adjustment of the working parameters of the grid compensation node.

[0144] Furthermore, the compensation calculation module is also used for:

[0145] The voltage fluctuation data is filtered to eliminate outliers and obtain clean voltage fluctuation data.

[0146] Calculate the extreme values ​​of the clean voltage fluctuation data to obtain the voltage fluctuation amplitude;

[0147] Based on a preset time window, the rate of change of clean voltage fluctuation data within the time window is calculated to obtain the voltage fluctuation rate.

[0148] The priority level value is obtained by inputting the voltage fluctuation amplitude and voltage fluctuation rate into a preset power grid compensation priority level mapping model.

[0149] Based on the voltage fluctuation amplitude and the preset normal voltage threshold of the power grid, the total power quality compensation of the power grid is calculated to obtain the compensation demand value.

[0150] Based on priority level values ​​and compensation demand values, grid collaborative compensation data is obtained.

[0151] Furthermore, the power grid compensation priority mapping model is obtained through the following method:

[0152] Obtain the historical compensation database of the power grid; the historical compensation database of the power grid includes the voltage fluctuation amplitude, voltage fluctuation rate and corresponding priority level value of the historical compensation process;

[0153] The model training data is obtained by using the voltage fluctuation amplitude and voltage fluctuation rate of the historical compensation process as feature values ​​and the corresponding priority level value as feature attributes; and the model training data is divided into training samples and test samples according to the preset division ratio.

[0154] Based on the fuzzy C-means clustering algorithm and training samples, a preliminary power grid compensation priority mapping model is constructed.

[0155] A preliminary power grid compensation priority mapping model is trained using test samples until it meets the preset accuracy requirements, thus obtaining the power grid compensation priority mapping model.

[0156] Furthermore, the compensation allocation module includes:

[0157] The basic weight determination unit is used to obtain the basic compensation weight of each power grid compensation node based on the priority level value and the basic weight mapping rule.

[0158] The basic ratio determination unit is used to calculate the proportion of the basic parameters of each power grid compensation node to the basic parameters of all power grid compensation nodes for each power grid compensation node, and obtain the basic parameter proportion data of each power grid compensation node.

[0159] The difference coefficient determination unit is used to quantify the differences in the basic parameters of each power grid compensation node based on the weight data of the basic parameters of the power grid compensation node, and obtain the difference coefficient of the basic parameters of each power grid compensation node.

[0160] The compensation weight determination unit is used to adjust the basic compensation weight based on the difference coefficient for each power grid compensation node to obtain the compensation weight of each power grid compensation node.

[0161] Furthermore, the basic ratio determination unit is also used for:

[0162] For each power grid compensation node, the capacity ratio of each compensation node is calculated using the following formula, based on its capacity value:

[0163]

[0164] Among them, P iv X is the capacity ratio value of power grid compensation node i. iv P is the capacity value of grid compensation node i, m is the total number of grid compensation nodes, and P is the capacity value of grid compensation node i. nv It is the capacity value of any power grid compensation node n;

[0165] For each power grid compensation node, the response speed ratio of each node is calculated using the following formula, based on its response speed value:

[0166]

[0167] Among them, P is X is the weight value of the response speed of grid compensation node i. is P is the response speed value of grid compensation node i, m is the total number of grid compensation nodes, and P is the response speed value of grid compensation node i. ns It is the response speed value of any power grid compensation node n;

[0168] For each power grid compensation node, the reliability weight value of each node is calculated using the following formula, based on its reliability value:

[0169]

[0170] Among them, P ik X is the reliability ratio of power grid compensation node i. ik P is the reliability value of power grid compensation node i, m is the total number of power grid compensation nodes, and P is the reliability value of power grid compensation node i. nk It is the reliable value of any power grid compensation node n;

[0171] For each power grid compensation node, the basic parameter weight data of each power grid compensation node are obtained based on the capacity weight value, response speed weight value, and reliability weight value.

[0172] Furthermore, the instruction generation module is also used for:

[0173] Based on the compensation weights of each power grid compensation node, power grid collaborative compensation data, and real-time status data, the compensation demand value allocated to each power grid compensation node is calculated using the following formula, thus obtaining the contribution demand value of each power grid compensation node:

[0174]

[0175] Among them, Q i Q is the contribution demand value of power grid compensation node i. r It is the compensation demand value, w i Q is the compensation weight of power grid compensation node i. a,i This is the real-time status data of grid compensation node i, where m is the total number of grid compensation nodes, and Q is the real-time status data of grid compensation node i. a,n It is the real-time status data of any power grid compensation node n, w n It is the compensation weight of any power grid compensation node m;

[0176] Based on the contribution demand values ​​of each power grid compensation node and the preset working parameter database, compensation instructions for each power grid compensation node are generated.

[0177] Furthermore, the device also includes a feedback module, which is used for:

[0178] Obtain feedback voltage fluctuation data; the feedback voltage fluctuation data is used to characterize the fluctuation of the power grid after the compensation command is generated.

[0179] Calculate the standard deviation and steady-state deviation of the feedback voltage fluctuation data to obtain the feedback effect value of the compensation command;

[0180] When the feedback effect value is less than the preset feedback threshold, the gradient descent method is used to update the basic weight mapping rule, and the updated basic weight mapping rule is obtained.

[0181] In one embodiment, such as Figure 3 A computer device is provided, comprising:

[0182] At least one processor 301, and a memory 302 communicatively connected to at least one of the processors 301: the memory stores application code executable by at least one of the processors, the application code being executed by at least one of the processors to enable at least one of the processors to perform the power quality compensation method for new energy grid access as described above.

[0183] Computer equipment may also include: sensor 303.

[0184] The processor 301, memory 302 and sensor 303 can be connected via a bus or other means, with the bus being an example in the figure.

[0185] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0186] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The components described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0187] The above-described embodiments are merely illustrative of several implementation methods of the embodiments of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the embodiments of this application, and these modifications and improvements all fall within the protection scope of the embodiments of this application.

Claims

1. A power quality compensation method for new energy access to power grid, characterized in that, The method comprises: acquiring voltage fluctuation data of a power grid and real-time state data of each power grid compensation node; quantifying fluctuation conditions of the power grid based on the voltage fluctuation data to obtain power grid collaborative compensation data; the power grid collaborative compensation data comprises a priority level value of power quality compensation of the power grid and a compensation demand value of the power quality compensation of the power grid; calculating compensation weights of each power grid compensation node based on the power grid collaborative compensation data, a preset basic weight mapping rule and preset power grid compensation node basic parameters; the power grid compensation node basic parameters comprise capacity values, response speed values and reliability values of each power grid compensation node; the compensation weights are used to represent priorities of power grid compensation nodes in the power quality compensation of the power grid; distributing the power grid collaborative compensation data to each power grid compensation node based on the compensation weights and the real-time state data to generate compensation instructions of each power grid compensation node; the compensation instructions are used to instruct adjustment of working parameters of the power grid compensation nodes.

2. The method of claim 1, wherein, The method comprises: performing filtering processing on the voltage fluctuation data to eliminate abnormal values of the voltage fluctuation data to obtain clean voltage fluctuation data; calculating change extreme values of the clean voltage fluctuation data to obtain voltage fluctuation change amplitudes; calculating change rates of the clean voltage fluctuation data within a preset time window to obtain voltage fluctuation change rates based on the time window; inputting the voltage fluctuation change amplitudes and the voltage fluctuation change rates into a preset power grid compensation priority level mapping model to obtain the priority level value; calculating a total amount of power quality compensation of the power grid based on the voltage fluctuation change amplitudes and a preset normal voltage threshold of the power grid to obtain the compensation demand value; obtaining the power grid collaborative compensation data based on the priority level value and the compensation demand value.

3. The method of claim 2, wherein, The power grid compensation priority level mapping model is obtained by the following method: acquiring a historical compensation database of the power grid; the historical compensation database of the power grid comprises the voltage fluctuation change amplitudes, the voltage fluctuation change rates and corresponding priority level values of a historical compensation process; obtaining model training data by taking the voltage fluctuation change amplitudes and the voltage fluctuation change rates of the historical compensation process as characteristic values and taking the corresponding priority level values as characteristic attributes; and dividing the model training data into training samples and test samples according to a preset division ratio; constructing a preliminary power grid compensation priority level mapping model based on a fuzzy C-means clustering algorithm and the training samples; training the preliminary power grid compensation priority level mapping model by using the test samples until the preliminary power grid compensation priority level mapping model meets a preset accuracy requirement to obtain the power grid compensation priority level mapping model.

4. The method of claim 1, wherein, The method comprises: obtaining a basic compensation weight of each power grid compensation node based on the priority level value and the basic weight mapping rule; for each of the power grid compensation nodes, calculating a proportion of the power grid compensation node basic parameter of the power grid compensation node in all power grid compensation node basic parameters to obtain basic parameter proportion data of each of the power grid compensation nodes; for each of the power grid compensation nodes, quantifying a difference in the power grid compensation node basic parameter of the power grid compensation node based on the basic parameter proportion data of the power grid compensation node to obtain a difference coefficient of the power grid compensation node basic parameter of each of the power grid compensation nodes; for each of the power grid compensation nodes, adjusting the basic compensation weight based on the difference coefficient to obtain the compensation weight of each of the power grid compensation nodes.

5. The method of claim 4, wherein, The method further comprises: obtaining feedback voltage fluctuation data; the feedback voltage fluctuation data is used to represent the fluctuation of the power grid after the compensation instruction is generated; where P iv is the capacity proportion value of grid compensation node i, X i v is the capacity value of grid compensation node i, m is the total number of grid compensation nodes, P nv is the capacity value of any grid compensation node n; calculating the standard deviation and steady-state deviation of the feedback voltage fluctuation data to obtain a feedback effect value of the compensation instruction; where P is is the response speed proportion value of the grid compensation node i, X is is the response speed value of the grid compensation node i, m is the total number of the grid compensation nodes, P ns is the response speed value of any grid compensation node n; when the feedback effect value is less than a preset feedback threshold, using a gradient descent method to update the basic weight mapping rule to obtain an updated basic weight mapping rule. where P ik is the reliable proportion value of the grid compensation node i, X ik is the reliable value of the grid compensation node i, m is the total number of grid compensation nodes, P nk is the reliable value of any grid compensation node n; The device comprises:

6. The method of claim 1, wherein, a data acquisition module for acquiring voltage fluctuation data of a power grid and real-time state data of each power grid compensation node; ​ wherein Q i is the contribution demand value of grid compensation node i, Q r is the compensation demand value, w i is the compensation weight of grid compensation node i, Q a,i is the real-time state data of grid compensation node i, m is the total number of grid compensation nodes, Q a,n is the real-time state data of any grid compensation node n, w n is the compensation weight of any grid compensation node m; ​ 7. The method of claim 1, wherein, ​ ​ ​ ​ 8. A power quality compensation device for new energy access to power grid, characterized in that, ​ ​ The compensation calculation module is configured to quantify fluctuation conditions of the power grid based on the voltage fluctuation data, and obtain power grid collaborative compensation data; the power grid collaborative compensation data comprises a priority level value of power quality compensation of the power grid and a compensation demand value of the power quality compensation of the power grid. The compensation distribution module is configured to calculate compensation weights of the power grid compensation nodes based on the power grid collaborative compensation data, a preset basic weight mapping rule and preset power grid compensation node basic parameters; the power grid compensation node basic parameters comprise capacity values, response speed values and reliability values of the power grid compensation nodes; the compensation weights are used to represent priorities of the power grid compensation nodes in the power quality compensation of the power grid. The instruction generation module is configured to distribute the power grid collaborative compensation data to the power grid compensation nodes based on the compensation weights and the real-time state data, and generate compensation instructions of the power grid compensation nodes; the compensation instructions are used to instruct to adjust working parameters of the power grid compensation nodes. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8. The processor executes the computer program to implement the steps of the method in any one of claims 1 to 7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 7.

Images