Method and system for regulating and controlling autonomous controllable standardized power module of low-voltage power distribution network

Abstract

The invention provides an autonomous controllable standardized power module regulation and control method and system for a low-voltage power distribution network, and relates to the technical field of electric power. According to the specific scheme, data mining is conducted on operation data of the low-voltage power distribution network, and operation characteristics are obtained; clustering the operation characteristics to obtain operation characteristic requirements of the low-voltage power distribution network under various operation conditions; constructing a target function based on correlation among device characteristics, loss characteristics, switching frequencies, allowable ripples and voltage withstanding indexes of power modules in the low-voltage power distribution network by taking the operation characteristic requirements under each operation condition as a target; based on a power constraint condition, a heat dissipation constraint condition and a passive device constraint condition of each power module, solving an optimal solution for the target function to obtain a target operation parameter of each power module; and controlling the operation of each power module in the low-voltage power distribution network based on the target operation parameter of each power module. According to the invention, the power module can be adaptively controlled to work.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a method and system for regulating and controlling an autonomously controllable standardized power module of a low-voltage distribution network. Background Art

[0002] In application scenarios such as renewable energy power generation and grid connection, DC transmission, and microgrids, power electronic devices need to have the characteristics of high efficiency, high power density, high reliability, and multi-functions. However, existing power modules have the following technical contradictions: 1. In order to increase power density, the switching frequency needs to be increased, but this will increase switching losses and reduce efficiency; 2. In order to achieve high efficiency, the switching frequency needs to be reduced, but this will increase the size of passive components and reduce power density; 3. In order to improve reliability, a large margin design is required, but this will increase costs and reduce power density; 4. In order to achieve multi-functions, the complexity of the hardware circuit needs to be increased, but this will lead to reduced reliability.

[0003] In addition, when large-capacity power modules are connected in parallel, due to factors such as inconsistent device parameters and asymmetric wiring impedance, the power distribution of each module will be uneven, reducing system efficiency and reliability. Moreover, different application scenarios have different functional requirements for power modules, and traditional hardware design methods have poor flexibility and cannot meet the fast-changing market needs. Summary of the invention

[0004] The present invention provides a method, system, electronic device and storage medium for regulating an autonomously controllable standardized power module in a low-voltage distribution network, which can solve at least one of the above problems.

[0005] The present invention provides a method for regulating and controlling an autonomous and controllable standardized power module of a low-voltage distribution network, comprising: Conduct data mining on the operation data of the low-voltage distribution network to obtain the operation characteristics; Clustering the operating characteristics to obtain the operating characteristic requirements of the low-voltage distribution network under various operating conditions; Taking the operating characteristic requirements under each of the operating conditions as the target, and based on the correlation between the device characteristics, loss characteristics, switching frequency, allowable ripple and withstand voltage indicators of each power module in the low-voltage distribution network, constructing an objective function; Based on the power constraints, heat dissipation constraints and passive device constraints of each of the power modules, solving the objective function for the optimal solution to obtain the target operating parameters of each of the power modules; Based on the target operating parameters of each of the power modules, controlling the operation of each of the power modules in the low-voltage distribution network; While controlling each of the power modules in the low-voltage distribution network to operate according to the target operating parameters, the adaptive control parameters of each of the power modules are dynamically adjusted based on the actual operating data of each of the power modules, wherein the adaptive control parameters include the switching frequency and duty cycle of the power modules.

[0006] According to another aspect of the present invention, there is provided a low-voltage distribution network autonomously controllable standardized power module control system, comprising: A data mining module is used to perform data mining on the operation data of the low-voltage distribution network to obtain operation characteristics; A demand determination module, used to cluster the operation characteristics to obtain the operation characteristic requirements of the low-voltage distribution network under various operation conditions; An objective function determination module is used to construct an objective function based on the operating characteristic requirements under each of the operating conditions and the correlation between the device characteristics, loss characteristics, switching frequency, allowable ripple and withstand voltage indicators of each power module in the low-voltage distribution network; An objective function solving module, used to solve the objective function for an optimal solution based on power constraints, heat dissipation constraints and passive device constraints of each of the power modules, and obtain target operating parameters of each of the power modules; A parameter control module, used to control the operation of each of the power modules in the low-voltage distribution network based on the target operation parameters of each of the power modules; An adaptive adjustment module is used to dynamically adjust the adaptive control parameters of each power module based on the actual operating data of each power module while controlling each power module in the low-voltage distribution network to operate according to the target operating parameters, wherein the adaptive control parameters include the switching frequency and duty cycle of the power module.

[0007] According to another aspect of the present invention, there is provided an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any low-voltage distribution network autonomously controllable standardized power module control method in the embodiments of the present invention.

[0008] According to another aspect of the present invention, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute any low-voltage distribution network autonomously controllable standardized power module control method in the embodiments of the present invention.

[0009] By adopting the technical solution of the present invention, data mining is performed on the operation data of the low-voltage distribution network to obtain the operation characteristics; the operation characteristics are clustered to obtain the operation characteristic requirements of the low-voltage distribution network under various operation conditions; taking the operation characteristic requirements under various operation conditions as the target, based on the device characteristics, loss characteristics, switching frequency, allowable ripple and the correlation between the withstand voltage index of each power module in the low-voltage distribution network, an objective function is constructed; based on the power constraints, heat dissipation constraints and passive device constraints of each power module, the optimal solution of the objective function is solved to obtain the target operation parameters of each power module; based on the target operation parameters of each power module, the operation of each power module in the low-voltage distribution network is controlled. In this way, the operation of the power modules in the low-voltage distribution network can meet the operation characteristic requirements of the low-voltage distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a flow chart of a method for regulating and controlling an autonomous and controllable standardized power module of a low-voltage distribution network according to an embodiment of the present invention; Figure 2 It is a structural block diagram of a low-voltage distribution network autonomously controllable standardized power module control system according to an embodiment of the present invention; Figure 3 is a block diagram of an electronic device for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0011] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0012] Figure 1 It is a flow chart of a method for regulating and controlling an autonomously controllable standardized power module of a low-voltage distribution network according to an embodiment of the present invention.

[0013] like Figure 1 As shown, the low-voltage distribution network autonomously controllable standardized power module control method may include: S110, performing data mining on the operation data of the low voltage distribution network to obtain operation characteristics; S120, clustering the operation characteristics to obtain the operation characteristic requirements of the low-voltage distribution network under various operation conditions; S130, taking the operating characteristic requirements under various operating conditions as the target, and constructing an objective function based on the correlation between the device characteristics, loss characteristics, switching frequency, allowable ripple and withstand voltage indicators of each power module in the low-voltage distribution network; S140, based on the power constraint conditions, heat dissipation constraint conditions and passive device constraint conditions of each power module, solving the optimal solution of the objective function to obtain the target operating parameters of each power module; S150, controlling the operation of each power module in the low-voltage distribution network based on the target operation parameters of each power module; S160, while controlling each power module in the low-voltage distribution network to operate according to the target operating parameters, dynamically adjust the adaptive control parameters of each power module based on the actual operating data of each power module, wherein the adaptive control parameters include the switching frequency and duty cycle of the power module.

[0014] By way of example, the operating data may include current, voltage, power, noise, etc. of each node.

[0015] For example, during the operation of the low-voltage distribution network, data acquisition devices such as smart meters and sensors are deployed, and communication protocols such as Modbus and IEC104 are used to realize automatic collection and transmission of multi-source heterogeneous data such as voltage, current, power, and temperature.

[0016] For example, the operation characteristics can be represented by some characteristics in the operation data, such as the mean value and the peak value. Alternatively, the operation data is subjected to a principal component analysis to obtain key characteristics, and the key characteristics are used as the above-mentioned operation characteristics.

[0017] Exemplarily, the principal component analysis (PCA) algorithm is used to extract features from high-dimensional data, and the first k principal components whose cumulative variance contribution rate reaches 95% are selected as key features to achieve data dimensionality reduction.

[0018] For example, the operation characteristics can be clustered by using methods such as K-Means clustering method, mean shift clustering algorithm or DBSCAN smiley face clustering, etc., to obtain various clusters, and then the types of each cluster are identified to confirm the operation conditions corresponding to each cluster. Thus, based on the clusters corresponding to each operation condition, the operation characteristic requirements of the low-voltage distribution network under each operation condition are determined.

[0019] Exemplarily, the extracted key features are clustered using the K-means clustering algorithm, and the key features are divided into categories to which the closest cluster center is located by calculating the Euclidean distance between each key feature and the cluster center.

[0020] Exemplarily, the operating conditions of the low-voltage distribution network can be divided into different modes such as normal operation, light-load operation, and heavy-load operation.

[0021] For example, for each typical operation mode, the rated power, heat dissipation conditions, and parameters of passive components such as capacitors and inductors of the power module are comprehensively considered to establish a multi-objective optimization model for the power module. With minimizing power loss and volume as the optimization goal, the current, voltage, switching frequency and other characteristics of the power device, as well as the heat dissipation coefficient, capacitor and inductor ripple coefficient, withstand voltage index, etc. are introduced into the model as constraints to form a mathematical model for the multi-objective optimization problem.

[0022] Exemplarily, the objective function may be a multi-objective function or a single-objective function.

[0023] Exemplarily, the power constraint may include an upper limit and a lower limit of power. The heat dissipation constraint may include an upper limit and a lower limit of heat generation. The passive component constraint may include optional passive components and prohibited passive components, or may also include power, voltage, and other constraints of the optional passive components.

[0024] Exemplarily, the target operating parameters may include the voltage drop of the switch tubes in the power module and the connection mode of the switch tubes, for example, which switch tubes are in the on state and which switch tubes are in the off state.

[0025] Exemplarily, after executing the above steps, during the operation of the low-voltage distribution network, the operation data is continuously collected, and the current operating conditions are judged by data analysis and pattern recognition technology to determine whether they have changed. For example, by monitoring the change trend of parameters such as voltage and current, the support vector machine (SVM) algorithm is used to classify the operating conditions in real time. When a change in the operating condition is detected, the optimization model is recalculated, and the operating parameters of the power module are dynamically updated to achieve adaptive optimization control of the distribution network.

[0026] Then, based on the optimization results and feedback information from real-time control, a comprehensive evaluation is conducted on the operating status of the low-voltage distribution network. Through data visualization technology, an operating indicator dashboard and performance report of the distribution network are generated. For example, a pie chart is used to show the proportion of different operating modes, a line chart is used to show the trend of key electrical parameters, and a radar chart is used to show the compliance of comprehensive performance indicators, etc., providing intuitive decision support for the safe, stable and efficient operation of the distribution network.

[0027] According to the above implementation, data mining is performed on the operation data of the low-voltage distribution network to obtain the operation characteristics; the operation characteristics are clustered to obtain the operation characteristic requirements of the low-voltage distribution network under various operation conditions; taking the operation characteristic requirements under various operation conditions as the target, based on the device characteristics, loss characteristics, switching frequency, allowable ripple and the correlation between the withstand voltage indicators of each power module in the low-voltage distribution network, an objective function is constructed; based on the power constraints, heat dissipation constraints and passive device constraints of each power module, the optimal solution of the objective function is solved to obtain the target operation parameters of each power module; based on the target operation parameters of each power module, the operation of each power module in the low-voltage distribution network is controlled. In this way, the operation of the power modules in the low-voltage distribution network can meet the operation characteristic requirements of the low-voltage distribution network.

[0028] In one embodiment, taking the operating characteristic requirements under various operating conditions as the target, based on the device characteristics, loss characteristics, switching frequency, noise characteristics and withstand voltage index of each power module in the low-voltage distribution network, an objective function is constructed, including: Obtaining the operating characteristic requirements under the operating conditions, wherein the operating characteristic requirements include total output power requirements, noise requirements, power conversion loss requirements, and withstand voltage requirements; Obtain the output characteristic curve of the switch tube of each power module in the low-voltage distribution network, the curve of the total output power and power conversion loss of each power module, the mapping relationship between the connection mode of the switch tube in each power module and the switching frequency, the curve of the noise change of each power module with the switching frequency, and the withstand voltage index of each power module; Based on the output characteristic curve of the switch tube of each power module and the curve of the total output power and electric energy conversion loss of each power module, a first function and a second function are constructed, wherein the independent variable of the first function is the voltage drop of the switch tube of each power module, and the dependent variable is the total output power of the low-voltage distribution network, and the independent variable of the second function is the voltage drop of the switch tube of each power module, and the dependent variable is the total electric energy conversion loss of the low-voltage distribution network; Determine the value range of the dependent variable of the first function based on the total output power requirement, determine the value range of the dependent variable of the second function based on the power conversion loss requirement, and determine the value range of the independent variables of the first function and the second function based on the withstand voltage requirement; Based on the curve of the noise of each power module changing with the switching frequency, and the mapping relationship between the connection mode of the switch tube in each power module and the switching frequency, a third function is determined, wherein the independent variable of the third function is the connection mode of the switch tube, and the dependent variable is the noise of the low-voltage distribution network; Based on the noise requirement, determine the value range of the dependent variable of the third function; Based on the first function, the second function and the third function, a target function is determined.

[0029] Exemplarily, the total output power requirement may include upper and lower limits of the output power, the noise requirement may include an upper noise limit, the power conversion loss requirement may include an upper power conversion loss limit, and the withstand voltage requirement may include upper and lower voltage limits.

[0030] Exemplarily, the output characteristic curve may be a corresponding relationship between the current Ic flowing through the switch tube and the voltage drop Vce. For example, if the test voltage is Imax, the voltage drop of the switch tube may be Vcep.

[0031] For example, for the curves of total output power and power conversion loss of each power module, the power conversion loss varies with the total number of power modules and the total output power.

[0032] Exemplarily, the connection mode of each switch tube in the power module can be the on or off state of each switch tube.

[0033] Exemplarily, as the switching frequency changes, the noise of the power module also changes accordingly.

[0034] It can be understood that the operating data of each power module can be used to fit it to obtain the above-mentioned curves.

[0035] Exemplarily, based on the first function, the second function and the third function, a piecewise function is constructed to obtain a multi-objective function.

[0036] Exemplarily, a weighted sum is performed on the first function, the second function, and the third function to obtain a single objective function.

[0037] According to the above implementation, the operating characteristic requirements under the operating conditions can be taken as the target, and an objective function corresponding to the operating condition can be constructed based on the device characteristics, loss characteristics, switching frequency, noise characteristics and withstand voltage indicators of each power module in the low-voltage distribution network.

[0038] In one embodiment, based on the power constraints, heat dissipation constraints, and passive device constraints of each power module, an optimal solution is solved for the objective function to obtain target operating parameters of each power module, including: Determine an initial population, wherein the initial population includes a plurality of individuals, each individual having a corresponding voltage drop of a switch tube and a connection mode of the switch tube; Starting from the initial population, perform the following iterative operations: Based on the first function, the second function and the third function, the total output power, the total power conversion loss and the noise of the low-voltage distribution network corresponding to each individual in the current iteration population are calculated; Based on the total output power, total power conversion loss and noise of the low-voltage distribution network corresponding to each individual in this iteration population, the fitness value of each individual is determined respectively; When the fitness value does not meet the preset fitness value condition, the voltage drop and connection mode of the switch tube corresponding to each individual in the current iteration population are cross-mutated to obtain the next iteration population, under the premise of satisfying the power constraint conditions, heat dissipation constraint conditions and passive device constraint conditions of each power module; When the fitness value meets the preset fitness value condition, the target individual is determined in this iterative population based on the fitness value of each individual in this iterative population, and the voltage drop of the switching tube and the connection method of the switching tube corresponding to the target individual are determined.

[0039] Exemplarily, the fitness value of each individual can be one or more. For example, the total output power, total power conversion loss and noise of the low-voltage distribution network corresponding to the individual are weighted and summed to obtain the fitness value of the individual. For another example, the total output power, total power conversion loss and noise of the low-voltage distribution network corresponding to the individual are normalized to obtain the fitness value of the individual.

[0040] Exemplarily, the adaptation value condition may be that the total output power is greater than a preset threshold, the total power conversion loss is less than a preset threshold, and the noise is less than a preset threshold.

[0041] Exemplarily, the fitness value condition may be that the maximum fitness value among the fitness values ​​of each individual is less than a preset threshold.

[0042] According to the above implementation, the optimal solution of the objective function can be solved based on the power constraints, heat dissipation constraints and passive device constraints of each power module to obtain the target operating parameters of each power module.

[0043] In one embodiment, data mining is performed on the operation data of the low-voltage distribution network to obtain operation characteristics, including: preprocessing the operation data of the low-voltage distribution network to obtain normalized operation data, wherein the preprocessing includes removing outliers, supplementing missing values ​​and normalizing; and using a graph neural network to perform feature representation on the normalized operation data to obtain operation characteristics.

[0044] Exemplarily, the collected data is preprocessed by a data cleaning algorithm, outliers beyond the normal range are eliminated using the 3σ principle, and missing values ​​are interpolated and supplemented.

[0045] Exemplarily, the data is normalized using the maximum and minimum normalization method, and the original data is linearly mapped to the interval [0, 1] to obtain a preprocessed normalized data set.

[0046] According to the above embodiments, the operation data can be pre-processed and characterized.

[0047] In one embodiment, the normalized operating data includes operating data of each node in the low-voltage distribution network; the graph neural network is: in, It is +1 layer node feature matrix, It is The node feature matrix of the layer, It is The trainable weight matrix of the layer, is an adjacency matrix with self-loops, yes The degree matrix of is the activation function of ReLU; Among them, after passing through the L-layer graph neural network, the running characteristics are .

[0048] In one embodiment, operating characteristics are clustered to obtain operating characteristic requirements of the low-voltage distribution network under various operating conditions, including: clustering the operating characteristics to obtain multiple operating characteristic sets; classifying each operating characteristic set based on an operating condition classifier to obtain the operating conditions corresponding to each operating characteristic set; and determining the operating characteristic requirements corresponding to each operating condition based on the operating characteristic set corresponding to each operating condition.

[0049] For example, the K-means clustering algorithm is used to perform cluster analysis on the extracted key features, and the data points are divided into the category where the nearest cluster center is located by calculating the Euclidean distance between the sample point and the cluster center. By iteratively optimizing the position of the cluster center, the data is finally divided into m different categories, each category representing a typical operation mode.

[0050] Exemplarily, the operating condition classifier is a pre-trained classifier.

[0051] According to the above implementation, the operating characteristic requirements corresponding to each operating condition can be determined.

[0052] In one embodiment, dynamically adjusting the adaptive control parameters of each of the power modules based on actual operation data of each of the power modules includes: Acquire historical operation data and optimized control parameters of the power module, wherein the historical operation data includes power, temperature, current and voltage, and the optimized control parameters include switching frequency and duty cycle; Based on historical operation data and optimized control parameters, the network model of the support vector machine and random forest combination is trained to obtain the power module adaptive control model; The actual operation data of the power module is input into the power module adaptive control model to obtain the adaptive control parameters of the power module output by the power module adaptive control model, wherein the actual operation data includes power, temperature, current and voltage, and the adaptive control parameters include switching frequency and duty cycle.

[0053] Exemplarily, historical operating data and optimized control parameters need to be preprocessed to obtain corresponding data sets for training the model.

[0054] Specifically, the historical operating data and optimized control parameters of the power module are obtained. The operating data include key indicators of power, temperature, and current. Through data cleaning methods, outliers are removed and missing values ​​are filled. Key features such as power, temperature, and current are extracted, and the features are standardized to obtain a preprocessed data set. Using the Scikit-learn library, two algorithms, support vector machine (SVM) and random forest (RF), are selected to train the models on the preprocessed data sets respectively to obtain two initial control models.

[0055] Then, the 5-fold cross validation method was used to evaluate the performance of the two initial control models using accuracy and recall as evaluation indicators to determine the optimal model. According to the evaluation results, the grid search (GridSearchCV) was used to tune the parameters of the optimal model to obtain the optimized power module adaptive control model.

[0056] The optimized power module adaptive control model is deployed to the power module control system, and the operation data is collected in real time. The control strategy is generated through model reasoning. The reasoning method uses model prediction combined with preset control rules. Monitor the model performance according to the real-time operation data and the model output results. The monitoring indicators include prediction accuracy and response time. If it is found that the model performance drops below the preset threshold, the model update mechanism is triggered to re-collect data, re-train the model and optimize. The dynamic response capability of the power module is evaluated through the dynamic response test module, and the specific test method is the step response test. If the dynamic response capability does not reach the preset threshold, adjust the model parameters, including increasing the model complexity or adjusting the learning rate, to further improve the dynamic response capability of the system.

[0057] According to the above implementation mode, data collection, preprocessing, model training, optimization, deployment, monitoring and dynamic response testing are closely linked to ensure the continuous optimization of the power module adaptive control strategy and the improvement of system performance.

[0058] Figure 2It is a structural block diagram of a low-voltage distribution network autonomously controllable standardized power module control system according to an embodiment of the present invention.

[0059] like Figure 2 As shown, the power module control system includes: The data mining module 210 is used to perform data mining on the operation data of the low voltage distribution network to obtain operation characteristics; A demand determination module 220, for clustering the operation characteristics to obtain the operation characteristic requirements of the low-voltage distribution network under various operation conditions; An objective function determination module 230 is used to construct an objective function based on the correlation between the device characteristics, loss characteristics, switching frequency, allowable ripple and withstand voltage index of each power module in the low-voltage distribution network, with the operating characteristic requirements under each of the operating conditions as the target; An objective function solving module 240 is used to solve the objective function for an optimal solution based on power constraints, heat dissipation constraints and passive device constraints of each power module to obtain target operating parameters of each power module; A parameter control module 250, configured to control the operation of each of the power modules in the low voltage distribution network based on the target operation parameters of each of the power modules; The adaptive adjustment module 260 is used to dynamically adjust the adaptive control parameters of each power module based on the actual operating data of each power module while controlling each power module in the low-voltage distribution network to operate according to the target operating parameters, wherein the adaptive control parameters include the switching frequency and duty cycle of the power module.

[0060] In one implementation, the objective function determination module 230 includes: A demand acquisition unit, which acquires the operation characteristic demand under the operation condition, wherein the operation characteristic demand includes total output power demand, noise demand, power conversion loss demand and withstand voltage demand; A module characteristic acquisition unit, used to acquire the output characteristic curve of the switch tube of each power module in the low-voltage distribution network, the curve of the total output power and the electric energy conversion loss of each power module, the mapping relationship between the connection mode of the switch tube in each power module and the switching frequency, the curve of the noise of each power module changing with the switching frequency, and the withstand voltage index of each power module; A first function construction unit is used to construct a first function and a second function based on the output characteristic curve of the switch tube of each power module and the curve of the total output power and the electric energy conversion loss of each power module, wherein the independent variable of the first function is the voltage drop of the switch tube of each power module, and the dependent variable is the total output power of the low-voltage distribution network, and the independent variable of the second function is the voltage drop of the switch tube of each power module, and the dependent variable is the total electric energy conversion loss of the low-voltage distribution network; a first value determination unit, configured to determine a value range of a dependent variable of the first function based on the total output power requirement, determine a value range of a dependent variable of the second function based on the electric energy conversion loss requirement, and determine a value range of independent variables of the first function and the second function based on the withstand voltage requirement; A second function construction unit is used to determine a third function based on a curve of a noise change of each power module with a switching frequency, and a mapping relationship between a connection mode of a switch tube in each of the power modules and the switching frequency, wherein the independent variable of the third function is the connection mode of the switch tube, and the dependent variable is the noise of the low-voltage distribution network; A second value determination unit, configured to determine a value range of a dependent variable of the third function based on the noise requirement; The third function construction unit is used to determine the target function based on the first function, the second function and the third function.

[0061] In one implementation, the objective function solving module 240 includes: An initial population determination unit, used to determine an initial population, wherein the initial population includes a plurality of individuals, each of which has a corresponding voltage drop of a switch tube and a connection mode of the switch tube; A population iteration unit is used to perform the following iterative operations starting from the initial population: Based on the first function, the second function and the third function, the total output power, the total power conversion loss and the noise of the low-voltage distribution network corresponding to each individual in the current iteration population are calculated; Based on the total output power, total power conversion loss and noise of the low-voltage distribution network corresponding to each individual in the iterative population, determine the fitness value of each individual respectively; When the fitness value does not meet the preset fitness value condition, on the premise of satisfying the power constraint condition, the heat dissipation constraint condition and the passive device constraint condition of each power module, the voltage drop of the switch tube and the connection mode of the switch tube corresponding to each individual in the current iteration population are cross-mutated to obtain the next iteration population; When the fitness value meets the preset fitness value condition, the target individual is determined in the current iterative population based on the fitness value of each individual in the current iterative population, and the voltage drop of the switching tube and the connection method of the switching tube corresponding to the target individual are determined.

[0062] In one embodiment, the data mining module 210 includes: A preprocessing unit, used for preprocessing the operation data of the low-voltage distribution network to obtain normalized operation data, wherein the preprocessing includes removing abnormal values, supplementing missing values ​​and normalization; The feature representation unit is used to use a graph neural network to perform feature representation on the normalized operation data to obtain the operation feature.

[0063] In one embodiment, the normalized operating data includes operating data of each node in the low-voltage distribution network; The graph neural network is: in, It is +1 layer node feature matrix, It is The node feature matrix of the layer, It is The trainable weight matrix of the layer, is an adjacency matrix with self-loops, yes The degree matrix of is the activation function of ReLU; Among them, after passing through the L-layer graph neural network, the running characteristics are .

[0064] In one implementation, the demand determination module 220 includes: A clustering unit, used for clustering the operation characteristics to obtain a plurality of operation characteristic sets; A classification unit, configured to classify each of the operating feature sets based on an operating condition classifier to obtain an operating condition corresponding to each of the operating feature sets; The demand determination unit is used to determine the operation characteristic demand corresponding to each of the operating conditions based on the operation feature set corresponding to each of the operating conditions.

[0065] In one implementation, the adaptive control module 260 includes: A historical data acquisition unit, used to acquire historical operation data and optimized control parameters of the power module, wherein the historical operation data includes power, temperature, current and voltage, and the optimized control parameters include switching frequency and duty cycle; A model training unit, used for training a network model of a combination of a support vector machine and a random forest based on the historical operation data and the optimized control parameters to obtain a power module adaptive control model; A model application unit is used to input the actual operation data of the power module into the power module adaptive control model to obtain the adaptive control parameters of the power module output by the power module adaptive control model, wherein the actual operation data includes power, temperature, current and voltage, and the adaptive control parameters include switching frequency and duty cycle.

[0066] For the description of specific functions and examples of each module and submodule of the system in the embodiment of the present invention, reference can be made to the relevant description of the corresponding steps in the above method embodiment, which will not be repeated here.

[0067] According to an embodiment of the present invention, the above method of the present invention can be applied to an electronic device and a readable storage medium.

[0068] Figure 3 A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0069] like Figure 3 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0070] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0071] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as a method for regulating and controlling a low-voltage distribution network autonomously controllable standardized power module. For example, in some embodiments, a method for regulating and controlling a low-voltage distribution network autonomously controllable standardized power module may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the method for regulating and controlling a low-voltage distribution network autonomously controllable standardized power module described above may be executed. Alternatively, in other embodiments, the computing unit 601 may be configured to execute a method for regulating and controlling an autonomously controllable standardized power module in a low-voltage distribution network in any other appropriate manner (for example, by means of firmware).

[0072] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0073] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0074] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0075] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0076] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0077] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0078] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present invention can be achieved, and this document does not limit this.

[0079] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for regulating and controlling an autonomous and controllable standardized power module of a low-voltage distribution network, characterized in that: include: Conduct data mining on the operation data of the low-voltage distribution network to obtain the operation characteristics; Clustering the operating characteristics to obtain the operating characteristic requirements of the low-voltage distribution network under various operating conditions; Taking the operating characteristic requirements under each of the operating conditions as the target, and based on the correlation between the device characteristics, loss characteristics, switching frequency, allowable ripple and withstand voltage indicators of each power module in the low-voltage distribution network, constructing an objective function; Based on the power constraints, heat dissipation constraints and passive device constraints of each of the power modules, solving the objective function for the optimal solution to obtain the target operating parameters of each of the power modules; Based on the target operating parameters of each of the power modules, controlling the operation of each of the power modules in the low-voltage distribution network; While controlling each of the power modules in the low-voltage distribution network to operate according to the target operating parameters, the adaptive control parameters of each of the power modules are dynamically adjusted based on the actual operating data of each of the power modules, wherein the adaptive control parameters include the switching frequency and duty cycle of the power modules.

2. The method according to claim 1, characterized in that The objective function is constructed based on the operating characteristic requirements under each of the operating conditions and the device characteristics, loss characteristics, switching frequency, noise characteristics and withstand voltage index of each power module in the low-voltage distribution network, including: Obtaining the operating characteristic requirements under the operating conditions, wherein the operating characteristic requirements include total output power requirements, noise requirements, power conversion loss requirements, and withstand voltage requirements; Obtaining the output characteristic curve of the switch tube of each power module in the low-voltage distribution network, the curve of the total output power and the power conversion loss of each power module, the mapping relationship between the connection mode of the switch tube in each power module and the switching frequency, the curve of the noise change of each power module with the switching frequency, and the withstand voltage index of each power module; Based on the output characteristic curves of the switch tubes of each of the power modules and the curves of the total output power and the electric energy conversion loss of each of the power modules, a first function and a second function are constructed, wherein the independent variable of the first function is the voltage drop of the switch tubes of each power module, and the dependent variable is the total output power of the low-voltage distribution network, and the independent variable of the second function is the voltage drop of the switch tubes of each power module, and the dependent variable is the total electric energy conversion loss of the low-voltage distribution network; Determine the value range of the dependent variable of the first function based on the total output power requirement, determine the value range of the dependent variable of the second function based on the power conversion loss requirement, and determine the value range of the independent variables of the first function and the second function based on the withstand voltage requirement; Based on the curve of the noise of each power module changing with the switching frequency, and the mapping relationship between the connection mode of the switch tube in each power module and the switching frequency, a third function is determined, wherein the independent variable of the third function is the connection mode of the switch tube, and the dependent variable is the noise of the low-voltage distribution network; Based on the noise requirement, determining a value range of a dependent variable of the third function; The objective function is determined based on the first function, the second function and the third function.

3. The method according to claim 2, characterized in that The step of solving the objective function for the optimal solution based on the power constraint conditions, heat dissipation constraint conditions and passive device constraint conditions of each power module to obtain the target operating parameters of each power module includes: Determine an initial population, wherein the initial population includes a plurality of individuals, each individual having a corresponding voltage drop of a switch tube and a connection mode of the switch tube; Starting from the initial population, the following iterative operations are performed: Based on the first function, the second function and the third function, the total output power, the total power conversion loss and the noise of the low-voltage distribution network corresponding to each individual in the current iteration population are calculated; Based on the total output power, total power conversion loss and noise of the low-voltage distribution network corresponding to each individual in the iterative population, determine the fitness value of each individual respectively; When the fitness value does not meet the preset fitness value condition, on the premise of satisfying the power constraint condition, the heat dissipation constraint condition and the passive device constraint condition of each power module, the voltage drop of the switch tube and the connection mode of the switch tube corresponding to each individual in the current iteration population are cross-mutated to obtain the next iteration population; When the fitness value meets the preset fitness value condition, the target individual is determined in the current iterative population based on the fitness value of each individual in the current iterative population, and the voltage drop of the switching tube and the connection method of the switching tube corresponding to the target individual are determined.

4. The method according to claim 1, characterized in that: The data mining of the operation data of the low voltage distribution network is performed to obtain the operation characteristics, including: Preprocessing the operation data of the low-voltage distribution network to obtain standardized operation data, wherein the preprocessing includes removing abnormal values, supplementing missing values ​​and normalizing; A graph neural network is used to perform feature representation on the normalized operation data to obtain the operation features.

5. The method according to claim 4, characterized in that The standardized operation data includes the operation data of each node in the low-voltage distribution network; The graph neural network is: in, It is +1 layer node feature matrix, It is The node feature matrix of the layer, It is The trainable weight matrix of the layer, is an adjacency matrix with self-loops, yes The degree matrix of is the activation function of ReLU; Among them, after passing through the L-layer graph neural network, the running characteristics are .

6. The method according to any one of claims 1 to 5, characterized in that The clustering of the operating characteristics to obtain the operating characteristic requirements of the low-voltage distribution network under various operating conditions includes: Clustering the operation characteristics to obtain multiple operation characteristic sets; Based on the operating condition classifier, classify each of the operating feature sets to obtain the operating conditions corresponding to each of the operating feature sets; Based on the operating feature sets corresponding to the various operating conditions, the operating characteristic requirements corresponding to the various operating conditions are determined respectively.

7. The method according to claim 1, characterized in that The dynamically adjusting the adaptive control parameters of each of the power modules based on the actual operation data of each of the power modules includes: Acquire historical operation data and optimized control parameters of the power module, wherein the historical operation data includes power, temperature, current and voltage, and the optimized control parameters include switching frequency and duty cycle; Based on the historical operation data and the optimized control parameters, a network model of a combination of a support vector machine and a random forest is trained to obtain a power module adaptive control model; The actual operation data of the power module is input into the power module adaptive control model to obtain the adaptive control parameters of the power module output by the power module adaptive control model, wherein the actual operation data includes power, temperature, current and voltage, and the adaptive control parameters include switching frequency and duty cycle.

8. A low-voltage distribution network autonomous controllable standardized power module control system, characterized in that: include: A data mining module is used to perform data mining on the operation data of the low-voltage distribution network to obtain operation characteristics; A demand determination module, used to cluster the operation characteristics to obtain the operation characteristic requirements of the low-voltage distribution network under various operation conditions; An objective function determination module is used to construct an objective function based on the operating characteristic requirements under each of the operating conditions and the correlation between the device characteristics, loss characteristics, switching frequency, allowable ripple and withstand voltage indicators of each power module in the low-voltage distribution network; An objective function solving module, used to solve the objective function for an optimal solution based on power constraints, heat dissipation constraints and passive device constraints of each of the power modules, and obtain target operating parameters of each of the power modules; A parameter control module, used to control the operation of each of the power modules in the low-voltage distribution network based on the target operation parameters of each of the power modules; An adaptive adjustment module is used to dynamically adjust the adaptive control parameters of each power module based on the actual operating data of each power module while controlling each power module in the low-voltage distribution network to operate according to the target operating parameters, wherein the adaptive control parameters include the switching frequency and duty cycle of the power module.

9. The system according to claim 8, characterized in that The objective function determination module comprises: A demand acquisition unit, which acquires the operation characteristic demand under the operation condition, wherein the operation characteristic demand includes total output power demand, noise demand, power conversion loss demand and withstand voltage demand; A module characteristic acquisition unit, used to acquire the output characteristic curve of the switch tube of each power module in the low-voltage distribution network, the curve of the total output power and the electric energy conversion loss of each power module, the mapping relationship between the connection mode of the switch tube in each power module and the switching frequency, the curve of the noise of each power module changing with the switching frequency, and the withstand voltage index of each power module; A first function construction unit is used to construct a first function and a second function based on the output characteristic curve of the switch tube of each power module and the curve of the total output power and the electric energy conversion loss of each power module, wherein the independent variable of the first function is the voltage drop of the switch tube of each power module, and the dependent variable is the total output power of the low-voltage distribution network, and the independent variable of the second function is the voltage drop of the switch tube of each power module, and the dependent variable is the total electric energy conversion loss of the low-voltage distribution network; a first value determination unit, configured to determine a value range of a dependent variable of the first function based on the total output power requirement, determine a value range of a dependent variable of the second function based on the electric energy conversion loss requirement, and determine a value range of independent variables of the first function and the second function based on the withstand voltage requirement; A second function construction unit is used to determine a third function based on a curve of a noise change of each power module with a switching frequency, and a mapping relationship between a connection mode of a switch tube in each of the power modules and the switching frequency, wherein the independent variable of the third function is the connection mode of the switch tube, and the dependent variable is the noise of the low-voltage distribution network; A second value determination unit, configured to determine a value range of a dependent variable of the third function based on the noise requirement; The third function construction unit is used to determine the target function based on the first function, the second function and the third function.

10. The system according to claim 9, characterized in that The objective function solving module comprises: An initial population determination unit, used to determine an initial population, wherein the initial population includes a plurality of individuals, each of which has a corresponding voltage drop of a switch tube and a connection mode of the switch tube; A population iteration unit is used to perform the following iterative operations starting from the initial population: Based on the first function, the second function and the third function, the total output power, the total power conversion loss and the noise of the low-voltage distribution network corresponding to each individual in the current iteration population are calculated; Based on the total output power, total power conversion loss and noise of the low-voltage distribution network corresponding to each individual in the iterative population, determine the fitness value of each individual respectively; When the fitness value does not meet the preset fitness value condition, on the premise of satisfying the power constraint condition, the heat dissipation constraint condition and the passive device constraint condition of each power module, the voltage drop of the switch tube and the connection mode of the switch tube corresponding to each individual in the current iteration population are cross-mutated to obtain the next iteration population; When the fitness value meets the preset fitness value condition, the target individual is determined in the current iterative population based on the fitness value of each individual in the current iterative population, and the voltage drop of the switching tube and the connection method of the switching tube corresponding to the target individual are determined.

11. The system according to claim 8, characterized in that The data mining module comprises: A preprocessing unit, used for preprocessing the operation data of the low-voltage distribution network to obtain normalized operation data, wherein the preprocessing includes removing abnormal values, supplementing missing values ​​and normalization; The feature representation unit is used to use a graph neural network to perform feature representation on the normalized operation data to obtain the operation feature.

12. The system according to claim 11, characterized in that The standardized operation data includes the operation data of each node in the low-voltage distribution network; The graph neural network is: in, It is +1 layer node feature matrix, It is The node feature matrix of the layer, It is The trainable weight matrix of the layer, is an adjacency matrix with self-loops, yes The degree matrix of is the activation function of ReLU; Among them, after passing through the L-layer graph neural network, the running characteristics are .

13. The system according to any one of claims 8 to 12, characterized in that: The demand determination module includes: A clustering unit, used for clustering the operation characteristics to obtain a plurality of operation characteristic sets; A classification unit, configured to classify each of the operating feature sets based on an operating condition classifier to obtain an operating condition corresponding to each of the operating feature sets; The demand determination unit is used to determine the operation characteristic demand corresponding to each of the operating conditions based on the operation feature set corresponding to each of the operating conditions.

14. An electronic device comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any one of claims 1 to 8.

15. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-8.

Images