Edge power distribution optimization method and system for power grid equipment

Abstract

The invention discloses an edge power distribution optimization method and system for power grid equipment, and relates to the technical field of power distribution, and the method comprises the steps: building a target power grid power transformation equipment set; constructing a first power transformation equipment model; rendering the first real-time operation data to the first power transformation equipment model to obtain a first visual model; judging whether the first power transformation equipment accords with a preset constraint or not; if yes, performing analogue simulation through a first simulation operation parameter generated based on the first real-time operation data to obtain a first simulation record; analyzing and judging whether the first simulation record conforms to a predetermined constraint, and if yes, acquiring first real-time fitness and first simulation fitness; and comparing the first real-time fitness with the first simulation fitness to determine a first edge power distribution decision, and forming a target power distribution decision. Therefore, the power distribution response speed is improved, the energy waste is reduced, and the stability and reliability of the system are improved.

Description

Technical Field

[0001] The present invention relates to the field of power distribution technology, and in particular to an edge power distribution optimization method and system for power grid equipment. Background Art

[0002] The power grid and its equipment are important infrastructure in social life. The power grid has the characteristics of wide coverage, many types of equipment, and complex and changing service requirements. Traditional power distribution systems may have fixed configurations and static optimization strategies, which fail to fully adapt to the dynamic changes and uncertainties of the power system. There are technical problems such as slow response, energy waste, and impact on the stability and reliability of the power system. Summary of the invention

[0003] The purpose of this application is to provide an edge power distribution optimization method and system for power grid equipment, so as to solve the technical problems in the prior art of slow response, energy waste, and influence on the stability and reliability of the power system.

[0004] In view of the above technical problems, the present application provides an edge power distribution optimization method and system for power grid equipment.

[0005] In a first aspect, the present application provides an edge power distribution optimization method for a power grid device, wherein the method comprises: Establishing a target power grid substation equipment set, wherein the target power grid substation equipment set refers to a collection of multiple substation equipment in the target power grid; Constructing a first substation equipment model, wherein the first substation equipment model is a physical model of a first substation equipment, and the first substation equipment is any one of the multiple substation equipments; Rendering first real-time operation data of the first power substation monitored based on a predetermined characteristic indicator to the first power substation model to obtain a first visualization model; determining whether the first power transformation equipment meets a predetermined constraint according to the first visualization model; If it is in compliance, simulating the first simulated operation parameter obtained based on the initial optimization item through the first substation equipment model to obtain a first simulation record, wherein the initial optimization item refers to the first real-time operation data; Analyze and determine whether the first simulation record meets the predetermined constraint, and if so, call a predetermined fitness function to sequentially obtain a first real-time fitness of the first real-time operation data and a first simulation fitness of the first simulation operation parameter; A first edge power distribution decision is determined by comparing the first real-time fitness and the first simulation fitness, and a target power distribution decision is formed, where the target power distribution decision is used to optimize edge power distribution for the target power grid.

[0006] In a second aspect, the present application also provides an edge power distribution optimization system for power grid equipment, wherein the system comprises: A target device acquisition module, the target device acquisition module is used to form a target power grid substation device set, the target power grid substation device set refers to a collection of multiple substation devices in the target power grid; A blank model building module, wherein the blank model building module is used to build a first substation model, wherein the first substation model is a physical model of the first substation, and the first substation is any one of the multiple substations; An initialization module, the initialization module is used to render first real-time operation data of the first power substation monitored based on a predetermined characteristic indicator to the first power substation model to obtain a first visualization model; A determination module, the determination module is used to determine whether the first power transformation equipment meets a predetermined constraint according to the first visualization model; A simulation operation module, wherein if the conditions are met, the simulation operation module is used to simulate the first simulation operation parameter obtained based on the initial optimization item through the first substation equipment model to obtain a first simulation record, wherein the initial optimization item refers to the first real-time operation data; an adaptability calculation module, the adaptability calculation module being used to analyze and determine whether the first simulation record meets the predetermined constraint, and if so, calling a predetermined fitness function to sequentially obtain a first real-time fitness of the first real-time operation data and a first simulation fitness of the first simulation operation parameter; A decision optimization module, wherein the decision optimization module is used to determine a first edge power distribution decision by comparing the first real-time fitness and the first simulation fitness, and to form a target power distribution decision, wherein the target power distribution decision is used to optimize the edge power distribution of the target power grid.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: By forming a target power grid substation set, the target power grid substation set refers to a collection of multiple substations in the target power grid; constructing a first substation model, the first substation model is a physical model of the first substation, and the first substation is any one of the multiple substations; rendering the first real-time operation data of the first substation monitored based on the predetermined characteristic index to the first substation model to obtain a first visualization model; judging whether the first substation meets the predetermined constraints according to the first visualization model; if so, simulating the first simulation operation parameters obtained based on the initial optimization item through the first substation model to obtain a first simulation record, wherein the initial optimization item refers to the first real-time operation data; analyzing and judging whether the first simulation record meets the predetermined constraints, if so, calling the predetermined fitness function to obtain the first real-time fitness of the first real-time operation data and the first simulation fitness of the first simulation operation parameter in turn; determining the first edge distribution decision by comparing the first real-time fitness and the first simulation fitness, and forming the target distribution decision, the target distribution decision is used to optimize the edge distribution of the target power grid. Thus, the technical effect of improving the distribution response speed, reducing energy waste, and thus improving the stability and reliability of the system is achieved.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly illustrate the technical means of the present application and to implement it in accordance with the contents of the specification, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The embodiments of the present invention and the following brief description are illustrated in conjunction with the accompanying drawings, which are described as follows: Figure 1 A schematic diagram of the flow chart of the edge power distribution optimization method for power grid equipment in this application; Figure 2 A schematic diagram of a process for determining whether the first substation equipment meets a predetermined constraint according to the first visualization model in the edge power distribution optimization method for power grid equipment in the present application; Figure 3 This is a schematic diagram of the structure of the edge power distribution optimization system used for power grid equipment in this application.

[0010] Explanation of the reference numerals: target device acquisition module 11, blank model construction module 12, initialization module 13, determination module 14, simulation operation module 15, adaptation calculation module 16, decision optimization module 17. DETAILED DESCRIPTION

[0011] The present application solves the technical problems faced by the prior art of slow response, energy waste, and impact on the stability and reliability of the power system by providing an edge power distribution optimization method and system for power grid equipment.

[0012] The solution in the embodiment of the present technology, in order to solve the above problems, adopts the following overall ideas: First, a target power grid substation equipment set is formed, which refers to a collection of multiple substation equipment in the target power grid; a first substation equipment model is constructed, which is a physical model of any substation equipment in the target power grid; the first real-time operation data of the first substation equipment monitored based on the predetermined characteristic index is mapped to the first substation equipment model to form a first visualization model; whether the first substation equipment meets the predetermined constraints is judged according to the first visualization model; if it meets, the first simulation operation parameter obtained based on the initial optimization item is simulated using the first substation equipment model to obtain a first simulation record, wherein the initial optimization item refers to the first real-time operation data; whether the first simulation record meets the predetermined constraints is analyzed and judged, and if it meets, the predetermined fitness function is called in sequence to obtain the first real-time fitness of the first real-time operation data and the first simulation fitness of the first simulation operation parameter; the first edge distribution decision is determined by comparing the first real-time fitness and the first simulation fitness, a target distribution decision is formed, and the edge distribution optimization of the target power grid is performed. Thus, the technical effect of improving the distribution response speed, reducing energy waste, and improving the stability and reliability of the system is achieved.

[0013] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the drawings and specific implementation methods of the specification. It should be noted that the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should also be noted that for the sake of ease of description, only the parts related to the present invention are shown in the drawings, rather than all of them.

[0014] Embodiment 1

[0015] like Figure 1 As shown, the present application provides an edge power distribution optimization method for power grid equipment, the method comprising: S100: Establishing a target power grid substation equipment set, wherein the target power grid substation equipment set refers to a collection of multiple substation equipment in the target power grid; The target grid substation equipment set refers to a collection of multiple substation equipment in the target grid. This collection includes key equipment in the power system, such as substations, transformers, and switchgear. By forming such a target grid substation equipment set, the system can more comprehensively consider the status and performance of each key part of the grid.

[0016] Optionally, the target power grid substation equipment set includes multiple edge substation groups corresponding to multiple edge substation nodes of the target power grid, and includes key control equipment in the edge substation nodes.

[0017] S200: constructing a first substation model, where the first substation model is a physical model of the first substation, and the first substation is any one of the multiple substations; Optionally, the first substation equipment model is a twin digital model constructed based on the first substation equipment. The model is a physical model of the first substation equipment, describing various physical properties, structures and operating principles of the equipment. The construction of the first substation equipment model is based on the principle of the digital twin method and is created through engineering modeling software such as CAD, PSS / E, MATLAB or other simulation tools.

[0018] S300: Rendering first real-time operation data of the first power substation monitored based on a predetermined characteristic indicator to the first power substation model to obtain a first visualization model; Optionally, the first real-time operation data of the first substation equipment is collected through data acquisition paths such as sensors and power grid equipment monitoring platforms. Exemplary information includes current, voltage, temperature, frequency, power, insulation resistance, phase difference, etc. Then, the real-time collected data is integrated with the first substation equipment model, and the digital model is updated using the real-time data to ensure that the model is synchronized with the actual operation status.

[0019] Optionally, before rendering the first real-time operation data to the first substation equipment model, the acquired first real-time operation data is processed and converted to ensure the accuracy and consistency of the data, which may include data cleaning, calibration, unit conversion, etc.

[0020] Optionally, ensure real-time update of data to ensure the timeliness of the first real-time operation data obtained, thereby accurately reflecting the current state of the first substation. Real-time update of data is based on a preset data update frequency or based on a data update instruction, wherein the data update instruction is a manual update instruction issued by the control terminal or the control personnel.

[0021] Optionally, the real-time rendered data is combined with the physical model to generate a visual model of the first substation equipment. This model can be displayed in a monitoring center, an operation room, etc., to help operators intuitively understand the operating status of the equipment.

[0022] Furthermore, the steps include: Acquire an edge power distribution database, and extract a first historical power distribution record from the edge power distribution database, wherein the first historical power distribution record includes a first historical substation equipment operation data record and a first historical edge power distribution adaptability record; Performing a correlation analysis on the first historical substation equipment operation data record and the first historical edge distribution adaptability record to obtain a first correlation analysis result; The predetermined characteristic index is determined based on the first correlation analysis result.

[0023] Optionally, the edge power distribution database is a relational database containing historical power distribution data of multiple substations in the target power grid substation set. Access rights to the edge power distribution database are obtained through database query language, API calls, etc., and the first historical power distribution record is extracted. The first historical power distribution record includes the first historical substation operation data record and the first historical edge power distribution fitness record, and the first historical substation operation data record and the first historical edge power distribution fitness record have a corresponding relationship.

[0024] Optionally, a correlation analysis is performed on the first historical substation operation data record and the first historical edge distribution fitness record, and the degree of association between them is determined by statistical methods, machine learning algorithms or other correlation analysis tools. Then, the substation operation characteristics related to the distribution fitness are identified. Exemplarily, the CORR function is used in SQL to calculate the correlation coefficient between multiple characteristic indicator data columns in the first historical substation operation data record and the first historical edge distribution fitness record data column.

[0025] Optionally, based on the results of the correlation analysis, a predetermined characteristic index is determined. The predetermined characteristic index refers to the operating parameters of the substation equipment that have a greater impact on the adaptability of the edge power distribution, such as current overload, voltage fluctuation, etc. Through the above steps, it is ensured that the selected index is closely related to the operating status and performance of the system.

[0026] S400: judging whether the first power transformation equipment meets a predetermined constraint according to the first visualization model; Further, such as Figure 2 As shown, the predetermined constraint includes a predetermined single threshold constraint and a predetermined state constraint, and judging whether the first power transformation device meets the predetermined constraint according to the first visualization model includes the following steps: Extracting a first indicator from the predetermined characteristic indicators, and matching a first single threshold constraint of the first indicator in the predetermined single threshold constraint; Determining whether first real-time data of the first indicator in the first visualization model satisfies the first single threshold constraint; If the conditions are met, weighted calculation is performed on the first real-time data to obtain a first real-time status index; Determining whether the first real-time status index satisfies the predetermined status constraint; If so, the first power transformation equipment complies with the predetermined constraint.

[0027] Optionally, the predetermined constraint includes a predetermined single threshold constraint and a predetermined state constraint, wherein the predetermined single threshold constraint is used to perform a single constraint on multiple characteristic indicators in the first real-time data, and the predetermined state constraint is used to perform an overall constraint on the first real-time data. By performing constraint judgment on the first real-time operation data in the first visualization model based on the local constraint based on the predetermined single threshold constraint and the predetermined state constraint, a comprehensive judgment is achieved.

[0028] Optionally, the predetermined constraint is used to determine whether the first substation needs to be optimized for power distribution, and the predetermined single-threshold constraint and the predetermined state constraint in the predetermined constraint are expressed as a predetermined single-threshold constraint interval and a predetermined state constraint interval. Exemplarily, if the first real-time operating data of the first substation is within the above constraint interval, it is necessary to optimize the power distribution of the first substation; if the first real-time operating data of the first substation is greater than the upper limit of the above predetermined single-threshold constraint interval and the predetermined state constraint interval, it means that the first substation is in good operating condition; if the first real-time operating data of the first substation is less than the lower limit of the above predetermined single-threshold constraint interval and the predetermined state constraint interval, it means that there is an abnormality in the operation of the first substation, and emergency response or disposal is required.

[0029] Optionally, a weighted calculation is performed on the first real-time data to obtain a first real-time status index, wherein the weight of the first real-time data is determined based on the first correlation analysis result, and a feature index item with a large correlation coefficient in the correlation analysis result has a high weighted weight. Exemplarily, the method includes normalizing the correlation coefficient in the correlation analysis result to ensure that the sum of multiple weighted weights is equal to 1.

[0030] S500: If it is in compliance, simulating the first simulated operation parameter obtained based on the initial optimization item through the first substation equipment model to obtain a first simulation record, wherein the initial optimization item refers to the first real-time operation data; Further, simulating the first simulated operation parameter obtained based on the initial optimization item through the first substation equipment model to obtain a first simulation record includes the following steps: Acquire a first neighborhood of the first real-time data, where the first neighborhood includes a plurality of data; randomly acquiring first neighborhood data from the plurality of data in combination with the predetermined single threshold constraint; The first simulation operation parameters are composed based on the first neighborhood data.

[0031] Optionally, the first simulated operating parameters are operating parameters that are randomly changed based on the first real-time operating data, and are a set of operating parameters whose optimization effect is to be determined. Exemplarily, first, first neighborhood data related to the target substation equipment is obtained from the first real-time operating data. The first neighborhood includes multiple data points adjacent to or related to the equipment, such as operating parameters, environmental conditions, etc. of adjacent equipment. Exemplarily, the first neighborhood is determined based on the historical operating records of the first substation equipment or the equipment technical documents of the first substation equipment, and the first neighborhood reflects the adjustment range of the operating parameters of the first substation equipment. Then, randomly select from the first neighborhood data to obtain the first neighborhood data, the first neighborhood data is any data point in the first neighborhood, and satisfies the predetermined single threshold constraint. Finally, the selected first neighborhood data is combined into the first simulated operating parameters. The first simulated operating parameters will be used to simulate the operating conditions of the first substation equipment.

[0032] Optionally, a simulation is performed through the first simulation operation parameter, and the first simulation operation parameter is applied to the first substation model to set the initial state. This includes setting initial values ​​of current, voltage, power, etc. Then, the simulation is run to simulate the operation behavior of the first substation under the given parameters. The values ​​and changes of various parameters and performance indicators of the simulation operation are recorded to form a first simulation record.

[0033] S600: Analyze and determine whether the first simulation record meets the predetermined constraint. If yes, call a predetermined fitness function to sequentially obtain a first real-time fitness of the first real-time operation data and a first simulation fitness of the first simulation operation parameter. Optionally, the simulation record is analyzed to evaluate the performance, stability and other key indicators of the equipment, thereby understanding the behavior of the first substation equipment under the first simulation operation parameters. If the first simulation record meets the predetermined state constraint in the predetermined constraint, it means that the first substation equipment under the first simulation operation parameters is in a normal operation state.

[0034] Further, calling a predetermined fitness function to sequentially obtain a first real-time fitness of the first real-time operation data and a first simulation fitness of the first simulation operation parameter comprises: Acquire a first edge power distribution device, where the first edge power distribution device refers to a power distribution device in a distributed edge power distribution device group corresponding to the first power transformer; Monitoring and obtaining first real-time power distribution information of the first edge power distribution device under the first real-time operation data; Extracting first simulation power distribution information of the first edge power distribution device in the first simulation record; The predetermined fitness function is called to sequentially analyze the first real-time power distribution information to obtain the first real-time fitness and the first simulation fitness of the first simulation power distribution information.

[0035] Optionally, an interactive distributed edge power distribution management platform obtains a first edge power distribution device corresponding to the first substation. The first edge power distribution device is monitored in real time to obtain real-time power distribution information under the current real-time operating data. Then, simulated power distribution information related to the first edge power distribution device is extracted from the first simulation record. Exemplarily, it includes parameters such as current, voltage, power during the simulation, and the simulated state of the distribution equipment. Then, the first real-time power distribution information and the first simulated power distribution information are analyzed respectively using a predetermined fitness function to obtain a first real-time fitness and a first simulated fitness. The fitness function is based on the optimization target configuration of the target power grid, including power balance, efficiency, harmonic conditions, etc.

[0036] Furthermore, the above steps also include: The first real-time power distribution information includes first real-time public grid interharmonics, first real-time three-phase imbalance, first real-time voltage transient event information, first real-time voltage transient event information, and first real-time frequency quality index; Sequentially encoding the first real-time voltage transient event information and the first real-time voltage transient event information to obtain first encoded data and second encoded data, respectively; The predetermined fitness function is called to analyze the first real-time public grid interharmonic, the first real-time three-phase imbalance, the first coded data, the second coded data, and the first real-time frequency quality index to obtain the first real-time fitness, wherein the expression of the predetermined fitness function is as follows: ,in, characterizing the first real-time fitness of the first real-time operation data, and and and and are respectively normalized results of the first real-time public grid interharmonics, the first real-time three-phase unbalance, the first coded data, the second coded data, and the first real-time frequency quality index, and and and and are the first weight coefficient, the second weight coefficient, the third weight coefficient, the fourth weight coefficient, and the fifth weight coefficient respectively, and .

[0037] Among them, interharmonics of the power grid are an important factor affecting the quality of power distribution. Poor interharmonic performance of the power grid will reduce the efficiency of power generation, transmission and consumption, cause overheating of electrical equipment, cause vibration and noise, make equipment age, shorten service life, and even cause failure or burns. Monitor current and voltage waveforms to identify and extract interharmonic components of the public power grid. This is achieved through harmonic analysis technology, including the use of digital power quality analyzers or other harmonic analysis equipment.

[0038] Optionally, the first real-time three-phase imbalance is obtained by monitoring the current and voltage of each phase, calculating the imbalance of the current and voltage. This includes calculating the imbalance of the positive sequence, negative sequence and zero sequence components. The instantaneous change of the voltage, such as a sudden voltage jump, is detected and recorded by a high-speed sampling voltage recording device, and the recorded waveform is subjected to event detection and classification to generate the first real-time voltage transient event information.

[0039] Optionally, the first real-time voltage transient event information and the first real-time voltage transient event information are processed by one-hot encoding to obtain first encoded data and second encoded data. Exemplarily, the severity level of the first real-time voltage transient event information and the severity level of the first real-time voltage transient event information are converted from the original event information into binary encoded data based on one-hot encoding, so as to facilitate subsequent calculation based on a predetermined fitness function.

[0040] Furthermore, the above steps also include: Acquire a first frequency curve of a first frequency time series in the first real-time power distribution information; Analyze the first frequency curve to obtain a first average frequency deviation and a first frequency flicker number; The first average frequency deviation and the first frequency flicker times are weighted by using the variation coefficient principle to obtain the first real-time frequency quality index.

[0041] Optionally, extract the data of the first frequency time series from the first real-time power distribution information. And draw a curve chart of the first frequency time series based on the extracted data to generate a first frequency curve. The first frequency curve reflects the change of the power frequency of the power distribution equipment over time. Then, analyze the first frequency curve, calculate the first average frequency deviation and count the number of first frequency flickers, where the first average frequency deviation refers to the standard deviation of the power frequency and at each time point in the first frequency curve. Then, use the coefficient of variation principle to weight the first average frequency deviation and the number of first frequency flickers, respectively calculate the coefficient of variation of the first average frequency deviation and the coefficient of variation of the first frequency flicker, and obtain the weight of the first average frequency deviation and the weight of the first frequency flicker. The weight of the first average frequency deviation and the weight of the first frequency flicker reflect the discrete degree and risk level of the first average frequency deviation and the first frequency flicker. Finally, according to the weight, the first average frequency deviation and the first frequency flicker are weighted and calculated to obtain the first real-time frequency quality index.

[0042] Through the above steps, various fluctuation factors affecting frequency quality are comprehensively considered, and the coefficient of variation principle is adopted. In combination with the discrete and risk characteristics of various fluctuation factors, the frequency quality evaluation of the first real-time power distribution information is realized.

[0043] S700: Determine a first edge power distribution decision by comparing the first real-time fitness and the first simulation fitness, and form a target power distribution decision, where the target power distribution decision is used to optimize edge power distribution of the target power grid.

[0044] Optionally, the first real-time fitness is compared with the first simulation. According to the fitness comparison result, the one with better fitness is determined as the first edge power distribution decision. The first edge power distribution decisions are combined into a target power distribution decision. It involves traversing the target power grid and integrating the decisions of multiple substations to form an overall power distribution optimization strategy.

[0045] Optionally, the target distribution decision is applied to the target power grid for edge distribution optimization. This includes the transmission of the target distribution decision, integrity verification, analysis, updating of the configuration of the power grid equipment, and adjustment of the current distribution to meet specific performance goals and optimization criteria. This ensures that the performance and benefit requirements can be better met in actual power grid operation.

[0046] In summary, the edge power distribution optimization method for power grid equipment provided by the present invention has the following technical effects: By forming a target power grid substation set, the target power grid substation set refers to a collection of multiple substations in the target power grid; constructing a first substation model, the first substation model is a physical model of the first substation, and the first substation is any one of the multiple substations; rendering the first real-time operation data of the first substation monitored based on the predetermined characteristic index to the first substation model to obtain a first visualization model; judging whether the first substation meets the predetermined constraints according to the first visualization model; if so, simulating the first simulation operation parameters obtained based on the initial optimization item through the first substation model to obtain a first simulation record, wherein the initial optimization item refers to the first real-time operation data; analyzing and judging whether the first simulation record meets the predetermined constraints, if so, calling the predetermined fitness function to obtain the first real-time fitness of the first real-time operation data and the first simulation fitness of the first simulation operation parameter in turn; determining the first edge distribution decision by comparing the first real-time fitness and the first simulation fitness, and forming the target distribution decision, the target distribution decision is used to optimize the edge distribution of the target power grid. Thus, the technical effect of improving the distribution response speed, reducing energy waste, and thus improving the stability and reliability of the system is achieved.

[0047] Embodiment 2 Based on the same concept as the edge power distribution optimization method for power grid equipment in the above embodiment, Figure 3 As shown, the present application also provides an edge power distribution optimization system for power grid equipment, the system comprising: A target device acquisition module 11 is used to form a target power grid substation device set, wherein the target power grid substation device set refers to a collection of multiple substation devices in the target power grid; A blank model building module 12, used to build a first substation model, wherein the first substation model is a physical model of the first substation, and the first substation is any one of the multiple substations; An initialization module 13, configured to render first real-time operation data of the first substation equipment monitored based on a predetermined characteristic indicator to the first substation equipment model to obtain a first visualization model; A determination module 14, configured to determine whether the first power transformation equipment meets a predetermined constraint according to the first visualization model; The simulation operation module 15 is used for simulating the first simulation operation parameter obtained based on the initial optimization item through the first substation equipment model to obtain a first simulation record if the condition meets the requirements, wherein the initial optimization item refers to the first real-time operation data; The fitness calculation module 16 is used to analyze and determine whether the first simulation record meets the predetermined constraint, and if so, call a predetermined fitness function to sequentially obtain a first real-time fitness of the first real-time operation data and a first simulation fitness of the first simulation operation parameter; The decision optimization module 17 determines a first edge power distribution decision by comparing the first real-time fitness and the first simulation fitness, and forms a target power distribution decision, wherein the target power distribution decision is used to optimize edge power distribution of the target power grid.

[0048] Furthermore, the initialization module 13 also includes: A power distribution record unit, used to obtain an edge power distribution database, and extract a first historical power distribution record from the edge power distribution database, wherein the first historical power distribution record includes a first historical substation operation data record and a first historical edge power distribution adaptability record; A correlation analysis unit, configured to perform a correlation analysis on the first historical substation operation data record and the first historical marginal distribution adaptability record to obtain a first correlation analysis result; A feature indicator selection unit is used to determine the predetermined feature indicator based on the first correlation analysis result.

[0049] Furthermore, the determination module 14 also includes: a constraint matching unit, configured to extract a first indicator from the predetermined feature indicators and match a first single threshold constraint of the first indicator in the predetermined single threshold constraint; a single threshold constraint unit, configured to determine whether the first real-time data of the first indicator in the first visualization model satisfies the first single threshold constraint; A state index calculation unit, configured to, if the condition is satisfied, perform weighted calculation on the first real-time data to obtain a first real-time state index; The state constraint unit is used to determine whether the first real-time state index satisfies the predetermined state constraint. If so, the first power transformation device complies with the predetermined constraint.

[0050] Furthermore, the simulation operation module 15 also includes: A first neighborhood acquisition unit, configured to acquire a first neighborhood of the first real-time data, wherein the first neighborhood includes a plurality of data; A neighborhood data selection unit, configured to randomly obtain first neighborhood data from the plurality of data in combination with the predetermined single threshold constraint; A simulation operation parameter generating unit is used to compose the first simulation operation parameter based on the first neighborhood data.

[0051] Furthermore, the adaptation calculation module 16 also includes: A power distribution equipment acquisition unit, configured to acquire a first edge power distribution equipment, where the first edge power distribution equipment refers to a power distribution equipment in a distributed edge power distribution equipment group corresponding to the first power transformer; A power distribution monitoring unit, configured to monitor and obtain first real-time power distribution information of the first edge power distribution device under the first real-time operation data; an information extraction unit, configured to extract first simulated power distribution information of the first edge power distribution device in the first simulated record; A function calling unit is used to call the predetermined fitness function to analyze the first real-time power distribution information in sequence to obtain the first real-time fitness and the first simulation fitness of the first simulation power distribution information.

[0052] Furthermore, the function calling unit also includes: The first real-time power distribution information includes first real-time public grid interharmonics, first real-time three-phase imbalance, first real-time voltage transient event information, first real-time voltage transient event information, and first real-time frequency quality index; an encoding unit, configured to sequentially encode the first real-time voltage transient event information and the second real-time voltage transient event information to obtain first encoded data and second encoded data, respectively; A calculation unit is used to call the predetermined fitness function to analyze the first real-time public grid interharmonic, the first real-time three-phase imbalance, the first coded data, the second coded data, and the first real-time frequency quality index to obtain the first real-time fitness, wherein the expression of the predetermined fitness function is as follows: ,in, characterizing the first real-time fitness of the first real-time operation data, and and and and are respectively normalized results of the first real-time public grid interharmonics, the first real-time three-phase unbalance, the first coded data, the second coded data, and the first real-time frequency quality index, and and and and are the first weight coefficient, the second weight coefficient, the third weight coefficient, the fourth weight coefficient, and the fifth weight coefficient respectively, and .

[0053] Furthermore, the system also includes a frequency quality index unit, which is used to: Acquire a first frequency curve of a first frequency time series in the first real-time power distribution information; Analyze the first frequency curve to obtain a first average frequency deviation and a first frequency flicker number; The first average frequency deviation and the first frequency flicker times are weighted by using the variation coefficient principle to obtain the first real-time frequency quality index.

[0054] It should be understood that the embodiments mentioned in this specification focus on their differences from other embodiments. The specific embodiments in the aforementioned embodiment one are also applicable to the edge power distribution optimization system for power grid equipment described in embodiment two. For the sake of brevity of the specification, they will not be further elaborated here.

[0055] It should be understood that the embodiments disclosed in this application and the above description can enable those skilled in the art to use this application to implement this application. At the same time, this application is not limited to the above-mentioned embodiments, and obvious modifications, combinations and substitutions of the embodiments mentioned in this application also fall within the scope of protection of this application.

Claims

1. A method for optimizing edge power distribution for power grid equipment, characterized in that: include: Establishing a target power grid substation equipment set, wherein the target power grid substation equipment set refers to a collection of multiple substation equipment in the target power grid; Constructing a first substation equipment model, wherein the first substation equipment model is a physical model of a first substation equipment, and the first substation equipment is any one of the multiple substation equipments; Rendering first real-time operation data of the first power substation monitored based on a predetermined characteristic indicator to the first power substation model to obtain a first visualization model; determining whether the first power transformation equipment meets a predetermined constraint according to the first visualization model; If it is in compliance, simulating the first simulated operation parameter obtained based on the initial optimization item through the first substation equipment model to obtain a first simulation record, wherein the initial optimization item refers to the first real-time operation data; Analyze and determine whether the first simulation record meets the predetermined constraint, and if so, call a predetermined fitness function to sequentially obtain a first real-time fitness of the first real-time operation data and a first simulation fitness of the first simulation operation parameter; A first edge power distribution decision is determined by comparing the first real-time fitness and the first simulation fitness, and a target power distribution decision is formed, where the target power distribution decision is used to optimize edge power distribution for the target power grid.

2. The method according to claim 1, characterized in that: include: Acquire an edge power distribution database, and extract a first historical power distribution record from the edge power distribution database, wherein the first historical power distribution record includes a first historical substation equipment operation data record and a first historical edge power distribution adaptability record; Performing a correlation analysis on the first historical substation equipment operation data record and the first historical edge distribution adaptability record to obtain a first correlation analysis result; The predetermined characteristic index is determined based on the first correlation analysis result.

3. The method according to claim 2, characterized in that: The predetermined constraint includes a predetermined single threshold constraint and a predetermined state constraint, and judging whether the first power transformation device meets the predetermined constraint according to the first visualization model includes: Extracting a first indicator from the predetermined characteristic indicators, and matching a first single threshold constraint of the first indicator in the predetermined single threshold constraint; Determining whether first real-time data of the first indicator in the first visualization model satisfies the first single threshold constraint; If the conditions are met, weighted calculation is performed on the first real-time data to obtain a first real-time status index; Determining whether the first real-time status index satisfies the predetermined status constraint; If so, the first power transformation equipment complies with the predetermined constraint.

4. The method according to claim 3, characterized in that: The first simulation operation parameter obtained based on the initial optimization item is simulated by the first substation equipment model to obtain a first simulation record, including: Acquire a first neighborhood of the first real-time data, where the first neighborhood includes a plurality of data; randomly acquiring first neighborhood data from the plurality of data in combination with the predetermined single threshold constraint; The first simulation operation parameters are composed based on the first neighborhood data.

5. The method according to claim 1, characterized in that: Calling a predetermined fitness function to sequentially obtain a first real-time fitness of the first real-time operation data and a first simulation fitness of the first simulation operation parameter includes: Acquire a first edge power distribution device, where the first edge power distribution device refers to a power distribution device in a distributed edge power distribution device group corresponding to the first power transformer; Monitoring and obtaining first real-time power distribution information of the first edge power distribution device under the first real-time operation data; Extracting first simulation power distribution information of the first edge power distribution device in the first simulation record; The predetermined fitness function is called to sequentially analyze the first real-time power distribution information to obtain the first real-time fitness and the first simulation fitness of the first simulation power distribution information.

6. The method according to claim 5, characterized in that: include: The first real-time power distribution information includes first real-time public grid interharmonics, first real-time three-phase imbalance, first real-time voltage transient event information, first real-time voltage transient event information, and first real-time frequency quality index; Sequentially encoding the first real-time voltage transient event information and the first real-time voltage transient event information to obtain first encoded data and second encoded data, respectively; The predetermined fitness function is called to analyze the first real-time public grid interharmonic, the first real-time three-phase imbalance, the first coded data, the second coded data, and the first real-time frequency quality index to obtain the first real-time fitness, wherein the expression of the predetermined fitness function is as follows: ,in, characterizing the first real-time fitness of the first real-time operation data, and and and and are respectively normalized results of the first real-time public grid interharmonics, the first real-time three-phase unbalance, the first coded data, the second coded data, and the first real-time frequency quality index, and and and and are the first weight coefficient, the second weight coefficient, the third weight coefficient, the fourth weight coefficient, and the fifth weight coefficient respectively, and .

7. The method according to claim 6, characterized in that: The method also includes: Acquire a first frequency curve of a first frequency time series in the first real-time power distribution information; Analyze the first frequency curve to obtain a first average frequency deviation and a first frequency flicker number; The first average frequency deviation and the first frequency flicker times are weighted by using the variation coefficient principle to obtain the first real-time frequency quality index.

8. An edge power distribution optimization system for power grid equipment, characterized in that: include: A target device acquisition module, the target device acquisition module is used to form a target power grid substation device set, the target power grid substation device set refers to a collection of multiple substation devices in the target power grid; A blank model building module, wherein the blank model building module is used to build a first substation model, wherein the first substation model is a physical model of the first substation, and the first substation is any one of the multiple substations; An initialization module, the initialization module is used to render first real-time operation data of the first power substation monitored based on a predetermined characteristic indicator to the first power substation model to obtain a first visualization model; A determination module, the determination module is used to determine whether the first power transformation equipment meets a predetermined constraint according to the first visualization model; A simulation operation module, wherein if the conditions are met, the simulation operation module is used to simulate the first simulation operation parameter obtained based on the initial optimization item through the first substation equipment model to obtain a first simulation record, wherein the initial optimization item refers to the first real-time operation data; an adaptability calculation module, the adaptability calculation module being used to analyze and determine whether the first simulation record meets the predetermined constraint, and if so, calling a predetermined fitness function to sequentially obtain a first real-time fitness of the first real-time operation data and a first simulation fitness of the first simulation operation parameter; A decision optimization module, wherein the decision optimization module is used to determine a first edge power distribution decision by comparing the first real-time fitness and the first simulation fitness, and to form a target power distribution decision, wherein the target power distribution decision is used to optimize the edge power distribution of the target power grid.

Images