A smart microgrid optimization method and system

By obtaining and standardizing the power parameters of the smart microgrid, using the K-means clustering method to find the cluster with the best operating efficiency, extracting and applying the optimal power parameter value, the problem of low operating efficiency of the smart microgrid is solved, and the The system is stable, reliable and efficient.

CN118761519BActive Publication Date: 2024-11-29CHENGDU TEXTILE COLLEGE
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411250543.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-06
Publication Date
2024-11-29
Estimated Expiration
2044-09-06

AI Technical Summary

Technical Problem

The operation control technology of smart microgrids is not yet mature, resulting in insufficient system stability and reliability, and the operation efficiency needs to be further improved.

Method used

By obtaining the power parameters that affect the operation efficiency of the smart microgrid, performing standardization processing, and using the K-means clustering method to find the cluster with the best operating efficiency, extracting the average value or median of the power parameters as the optimal operating efficiency correspondence The parameter values ​​of the smart microgrid are applied to the smart microgrid to optimize operational efficiency.

Benefits of technology

It has achieved stable, reliable and maximum improvement in the operation efficiency of smart microgrids, and improved the overall performance of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118761519B_ABST
    Figure CN118761519B_ABST
Patent Text Reader

Abstract

The present invention provides an optimization method and system for a smart microgrid, belonging to the technical field of smart microgrids, and the method includes: obtaining power parameters that affect the operating efficiency of the smart microgrid; standardizing or normalizing the power parameters and the operating efficiency to obtain multiple data points; randomly selecting K data points as initial cluster centers; calculating the distance from each data point to all cluster centers, and assigning the data points to the clusters where the nearest cluster centers are located, recalculating the positions of the cluster centers according to the data points in the clusters, and repeating the steps until the positions of the cluster centers no longer change or reach a preset number of iterations, to obtain clustering results; analyzing the clustering results, finding the cluster with the best operating efficiency, and extracting the average value or median of the power parameters in the cluster as the parameter value corresponding to the best operating efficiency; applying the parameter value corresponding to the best operating efficiency to the smart microgrid. The present invention can effectively improve the operating efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of smart microgrids, and in particular to an optimization method and system for a smart microgrid. Background Art

[0002] A smart microgrid refers to a small power generation and distribution system composed of distributed power sources (such as photovoltaic cells, fuel cells, wind power generation, biomass energy, micro gas turbines, etc.), energy storage devices, energy conversion devices, loads, monitoring and protection devices, etc. It adopts advanced Internet and information technology to achieve flexible and efficient application of distributed power sources and has certain energy management functions.

[0003] However, the operation and control technology of smart microgrids is still immature, and the stability and reliability of the system need to be further improved, especially its operation efficiency needs to be improved. Summary of the invention

[0004] The present invention provides an optimization method and system for a smart microgrid to improve operation efficiency.

[0005] This specification discloses a method for optimizing a smart microgrid, including:

[0006] Obtaining power parameters that affect the operating efficiency of the smart microgrid, the power parameters including voltage fluctuation amplitude, frequency fluctuation amplitude, power loss, load factor, load fluctuation amplitude, line impedance, line capacitance, harmonic current, harmonic voltage, harmonic impedance, and harmonic frequency;

[0007] Standardizing or normalizing the power parameters and operating efficiency to obtain multiple data points;

[0008] Randomly select K data points as the initial cluster centers, K = 1, 2, ... n; n is the total number of data points;

[0009] Calculate the distance from each data point to all cluster centers, and assign the data point to the cluster with the closest cluster center. Recalculate the location of the cluster center based on the data points in the cluster, and repeat this step until the location of the cluster center no longer changes or reaches the preset number of iterations to obtain the clustering result.

[0010] Analyze the clustering results to find the cluster with the best operating efficiency. The data points in the cluster represent the power parameters under the optimal operating efficiency. The average value or median of the power parameters in the cluster is extracted as the parameter value corresponding to the optimal operating efficiency.

[0011] The parameter values ​​corresponding to the optimal operating efficiency are applied to the smart microgrid to optimize the operating efficiency.

[0012] In this manual, K-means clustering is performed on different K values, the sum of squared errors within the cluster corresponding to each K value is calculated, a relationship graph between the K value and the sum of squared errors within the cluster is drawn, the elbow point is found in the relationship graph, and the K value corresponding to the elbow point is selected as the optimal number of clusters.

[0013] In this specification, K-means clustering is performed for different K values, the silhouette coefficient of the clustering result under each K value is calculated, the silhouette coefficients under different K values ​​are compared, and the K value with the largest silhouette coefficient is selected as the optimal number of clusters.

[0014] In this specification, multiple random data sets with the same sample size as an original data set composed of multiple data points are generated, each random data set is clustered with different K values, and the corresponding log-likelihood ratio is calculated, the log-likelihood ratio of the original data set at different K values ​​is calculated, and compared with the corresponding values ​​of the random data sets to obtain the gap statistic, and the K value with the largest gap statistic is selected as the optimal number of clusters.

[0015] In this specification, K-means clustering is performed for different K values, the Calinski-Harabasz index is calculated for the clustering results under each K value, the Calinski-Harabasz index under different K values ​​is compared, and the K value with the largest Calinski-Harabasz index is selected as the optimal number of clusters.

[0016] In this specification, K-means clustering is performed on different K values, and the silhouette coefficient of the clustering result under each K value is calculated to obtain a reference silhouette coefficient; the Calinski-Harabasz index is calculated for the clustering result under each K value to obtain a reference Calinski-Harabasz index; multiple random data sets with the same sample size as the original data set composed of multiple data points are generated, and different K values ​​are clustered for each random data set, and the corresponding log-likelihood ratio is calculated, and the log-likelihood ratio of the original data set under different K values ​​is calculated, and compared with the corresponding values ​​of the random data sets to obtain a reference gap statistic;

[0017] The reference contour coefficient is used as a row vector, the reference Calinski-Harabasz index is used as a column vector, a matrix is ​​constructed, and then the K value is imported to perform surface fitting to obtain the first reference fitting surface;

[0018] The reference contour coefficient is used as a row vector, the reference gap statistic is used as a column vector, a matrix is ​​constructed, and then the K value is introduced to perform surface fitting to obtain a second reference fitting surface;

[0019] The reference Calinski-Harabasz index is used as a row vector, the reference gap statistic is used as a column vector, a matrix is ​​constructed, and then the K value is introduced to perform surface fitting to obtain a third reference fitting surface;

[0020] Based on the first reference fitting surface, the second reference fitting surface and the third reference fitting surface, the first reference Calinski-Harabasz index, the first reference gap statistic and the first K value corresponding to the maximum reference contour coefficient are obtained, the first reference contour coefficient, the second reference gap statistic and the second K value corresponding to the maximum reference Calinski-Harabasz index are obtained, and the second reference contour coefficient, the second reference Calinski-Harabasz index and the third K value corresponding to the maximum reference gap statistic are obtained; and the fourth K value corresponding to the average of the first reference contour coefficient and the second reference contour coefficient is obtained, the fifth K value corresponding to the average of the first reference Calinski-Harabasz index and the second reference Calinski-Harabasz index is obtained, and the sixth K value corresponding to the average of the first reference gap statistic and the second reference gap statistic is obtained, and the average among the first K value, the second K value, the third K value, the fourth K value, the fifth K value and the sixth K value is taken as the optimal number of clusters.

[0021] In this manual, K-means clustering is performed on different K values, the sum of squared errors within the cluster corresponding to each K value is calculated, a relationship graph between the K value and the sum of squared errors within the cluster is drawn, the elbow point is found in the relationship graph, the seventh K value corresponding to the elbow point is selected, and the average of the first K value, the second K value, the third K value, the fourth K value, the fifth K value, the sixth K value and the seventh K value is taken as the optimal number of clusters.

[0022] This specification also discloses an optimization system for a smart microgrid, which is used to implement the optimization method for the smart microgrid described in any one of the above. The optimization system for the smart microgrid includes:

[0023] An acquisition module is used to acquire power parameters that affect the operating efficiency of the smart microgrid, wherein the power parameters include voltage fluctuation amplitude, frequency fluctuation amplitude, power loss, load factor, load fluctuation amplitude, line impedance, line capacitance, harmonic current, harmonic voltage, harmonic impedance and harmonic frequency;

[0024] A processing module, used for standardizing or normalizing the power parameters and operating efficiency to obtain multiple data points;

[0025] Clustering module for:

[0026] Randomly select K data points as initial cluster centers;

[0027] Calculate the distance from each data point to all cluster centers, and assign the data point to the cluster with the closest cluster center. Recalculate the location of the cluster center based on the data points in the cluster, and repeat this step until the location of the cluster center no longer changes or reaches the preset number of iterations to obtain the clustering result.

[0028] Analyze the clustering results to find the cluster with the best operating efficiency. The data points in the cluster represent the power parameters under the optimal operating efficiency. The average value or median of the power parameters in the cluster is extracted as the parameter value corresponding to the optimal operating efficiency.

[0029] The optimization module is used to apply the parameter values ​​corresponding to the optimal operating efficiency to the smart microgrid to optimize the operating efficiency.

[0030] This manual can at least achieve the following beneficial effects:

[0031] By obtaining the power parameters that affect the operating efficiency of the smart microgrid and performing cluster analysis, the power parameters corresponding to the optimal operating efficiency are obtained, and the power parameters corresponding to the optimal operating efficiency are applied to the smart microgrid to optimize the operating efficiency. This solution can make the operating efficiency stable and reliable and improve it to the greatest extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0033] Figure 1 It is a schematic diagram of the optimization method of the smart microgrid involved in the present invention. DETAILED DESCRIPTION

[0034] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the embodiments of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0035] The disclosure below provides many different embodiments or examples to implement different structures of the embodiments of the present invention. In order to simplify the disclosure of the embodiments of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the embodiments of the present invention. In addition, the embodiments of the present invention can repeat reference numbers and / or reference letters in different examples, and this repetition is for the purpose of simplification and clarity, which itself does not indicate the relationship between the various embodiments and / or settings discussed.

[0036] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0037] like Figure 1 As shown, the embodiment of this specification discloses a method for optimizing a smart microgrid, including:

[0038] Obtaining power parameters that affect the operating efficiency of the smart microgrid, the power parameters including voltage fluctuation amplitude, frequency fluctuation amplitude, power loss, load factor, load fluctuation amplitude, line impedance, line capacitance, harmonic current, harmonic voltage, harmonic impedance, and harmonic frequency;

[0039] Standardizing or normalizing the power parameters and operating efficiency to obtain multiple data points;

[0040] Randomly select K data points as the initial cluster centers, K = 1, 2, ... n; n is the total number of data points;

[0041] Calculate the distance from each data point to all cluster centers, and assign the data point to the cluster with the closest cluster center. Recalculate the location of the cluster center based on the data points in the cluster, and repeat this step until the location of the cluster center no longer changes or reaches the preset number of iterations to obtain the clustering result.

[0042] Analyze the clustering results to find the cluster with the best operating efficiency. The data points in the cluster represent the power parameters under the optimal operating efficiency. The average value or median of the power parameters in the cluster is extracted as the parameter value corresponding to the optimal operating efficiency.

[0043] The parameter values ​​corresponding to the optimal operating efficiency are applied to the smart microgrid to optimize the operating efficiency.

[0044] In some embodiments of the present specification, K-means clustering is performed on different K values, the sum of squared errors within the cluster corresponding to each K value is calculated, a relationship graph between the K value and the sum of squared errors within the cluster is plotted, the elbow point is found in the relationship graph, and the K value corresponding to the elbow point is selected as the optimal number of clusters.

[0045] In some embodiments of the present specification, K-means clustering is performed on different K values, the silhouette coefficient of the clustering result at each K value is calculated, the silhouette coefficients at different K values ​​are compared, and the K value with the largest silhouette coefficient is selected as the optimal number of clusters.

[0046] In some embodiments of the present specification, multiple random data sets are generated with the same sample size as an original data set consisting of multiple data points, each random data set is clustered with different K values, and the corresponding log-likelihood ratio is calculated, the log-likelihood ratio of the original data set at different K values ​​is calculated and compared with the corresponding values ​​of the random data sets to obtain a gap statistic, and the K value with the largest gap statistic is selected as the optimal number of clusters.

[0047] In some embodiments of the present specification, K-means clustering is performed for different K values, the Calinski-Harabasz index is calculated for the clustering results at each K value, the Calinski-Harabasz index at different K values ​​is compared, and the K value with the largest Calinski-Harabasz index is selected as the optimal number of clusters.

[0048] In some embodiments of the present specification, K-means clustering is performed on different K values, and the silhouette coefficient of the clustering result under each K value is calculated to obtain a reference silhouette coefficient; the Calinski-Harabasz index is calculated for the clustering result under each K value to obtain a reference Calinski-Harabasz index; multiple random data sets having the same sample size as an original data set composed of multiple data points are generated, and different K values ​​are clustered for each random data set, and the corresponding log-likelihood ratio is calculated, and the log-likelihood ratio of the original data set under different K values ​​is calculated, and compared with the corresponding values ​​of the random data set to obtain a reference gap statistic;

[0049] The reference contour coefficient is used as a row vector, the reference Calinski-Harabasz index is used as a column vector, a matrix is ​​constructed, and then the K value is imported to perform surface fitting to obtain the first reference fitting surface;

[0050] The reference contour coefficient is used as a row vector, the reference gap statistic is used as a column vector, a matrix is ​​constructed, and then the K value is introduced to perform surface fitting to obtain a second reference fitting surface;

[0051] The reference Calinski-Harabasz index is used as a row vector, the reference gap statistic is used as a column vector, a matrix is ​​constructed, and then the K value is introduced to perform surface fitting to obtain a third reference fitting surface;

[0052] Based on the first reference fitting surface, the second reference fitting surface and the third reference fitting surface, the first reference Calinski-Harabasz index, the first reference gap statistic and the first K value corresponding to the maximum reference contour coefficient are obtained, the first reference contour coefficient, the second reference gap statistic and the second K value corresponding to the maximum reference Calinski-Harabasz index are obtained, and the second reference contour coefficient, the second reference Calinski-Harabasz index and the third K value corresponding to the maximum reference gap statistic are obtained; and the fourth K value corresponding to the average of the first reference contour coefficient and the second reference contour coefficient is obtained, the fifth K value corresponding to the average of the first reference Calinski-Harabasz index and the second reference Calinski-Harabasz index is obtained, and the sixth K value corresponding to the average of the first reference gap statistic and the second reference gap statistic is obtained, and the average among the first K value, the second K value, the third K value, the fourth K value, the fifth K value and the sixth K value is taken as the optimal number of clusters.

[0053] In some embodiments of the present specification, K-means clustering is performed on different K values, the sum of squared errors within the cluster corresponding to each K value is calculated, a relationship graph between the K value and the sum of squared errors within the cluster is drawn, the elbow point is found in the relationship graph, the seventh K value corresponding to the elbow point is selected, and the average of the first K value, the second K value, the third K value, the fourth K value, the fifth K value, the sixth K value and the seventh K value is taken as the optimal number of clusters.

[0054] It can be understood that applying the parameter value corresponding to the optimal operating efficiency to the smart microgrid means adjusting the power parameters in the smart microgrid to the parameter value corresponding to the optimal operating efficiency, so as to optimize the operating efficiency. The adjustment of the power parameters is a prior art and will not be repeated here.

[0055] The present invention obtains the parameter value corresponding to the optimal operating efficiency through a clustering method, and adopts surface fitting to obtain the K value corresponding to the case where the silhouette coefficient, the Calinski-Harabasz index and the gap statistic are as large as possible at the same time, and takes the average of the K value and the K value obtained by the elbow point as the optimal clustering number, so that the clustering effect is better, and thus the parameter value corresponding to the optimal operating efficiency is accurate, reliable and effective.

[0056] The embodiment of this specification also discloses an optimization system for a smart microgrid, which is used to implement the optimization method for the smart microgrid described in any one of the above. The optimization system for the smart microgrid includes:

[0057] An acquisition module is used to acquire power parameters that affect the operating efficiency of the smart microgrid, wherein the power parameters include voltage fluctuation amplitude, frequency fluctuation amplitude, power loss, load factor, load fluctuation amplitude, line impedance, line capacitance, harmonic current, harmonic voltage, harmonic impedance and harmonic frequency;

[0058] A processing module, used for standardizing or normalizing the power parameters and operating efficiency to obtain multiple data points;

[0059] Clustering module for:

[0060] Randomly select K data points as initial cluster centers;

[0061] Calculate the distance from each data point to all cluster centers, and assign the data point to the cluster with the closest cluster center. Recalculate the location of the cluster center based on the data points in the cluster, and repeat this step until the location of the cluster center no longer changes or reaches the preset number of iterations to obtain the clustering result.

[0062] Analyze the clustering results to find the cluster with the best operating efficiency. The data points in the cluster represent the power parameters under the optimal operating efficiency. The average value or median of the power parameters in the cluster is extracted as the parameter value corresponding to the optimal operating efficiency.

[0063] The optimization module is used to apply the parameter values ​​corresponding to the optimal operating efficiency to the smart microgrid to optimize the operating efficiency.

[0064] In summary, when the system implements the above-mentioned embodiment method, it only needs to add corresponding functional modules.

[0065] It should be understood that the above surface fitting operation can use existing software tools, such as the CurveFitting tool in Matlab. Through existing data detection / measurement devices / sensors or data reading modules of the smart microgrid system (transmission and distribution substations, etc.), data in the smart microgrid system can be directly obtained.

[0066] It is clear that by obtaining the power parameters of the smart microgrid system in advance through existing equipment, a large amount of test data can be obtained. These test data can be simulation test data in the laboratory or actual measured or operating data of the smart microgrid system in practice.

[0067] The above-described embodiments are used to illustrate the present invention, not to limit the present invention, so changes in the exemplified values ​​or replacement of equivalent elements should still fall within the scope of the present invention.

[0068] From the above detailed description, it can be understood by those skilled in the art that the present invention can indeed achieve the aforementioned objectives and is in compliance with the provisions of the Patent Law.

[0069] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they are aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention. The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. It should be pointed out that any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0070] It should be noted that the above description of the relevant process is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0071] The basic concepts have been described above. Obviously, for those of ordinary skill in the art who have read this application, the above invention disclosure is only for example and does not constitute a limitation of this application. Although not explicitly stated here, those of ordinary skill in the art may make various modifications, improvements and amendments to this application. Such modifications, improvements and amendments are suggested in this application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary embodiments of this application.

[0072] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0073] In addition, it will be understood by those skilled in the art that various aspects of the present application may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvement thereof. Therefore, various aspects of the present application may be implemented entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as a "unit", "module" or "system". In addition, various aspects of the present application may take the form of a computer program product embodied in one or more computer-readable media, wherein computer-readable program code is contained therein.

[0074] The computer program code required for the operation of each part of the present application can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C programming language, VisualBasic, Fortran2103, Perl, COBOL2102, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages. The program code can be run entirely on the user's computer, or run on the user's computer as an independent software package, or run partially on the user's computer and partially on the remote computer, or run entirely on the remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0075] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this application, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this application. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this application. For example, although the implementation of the various components described above can be embodied in a hardware device, it can also be implemented as a pure software solution, for example, installation on an existing server or mobile device.

[0076] Similarly, it should be noted that in order to simplify the description disclosed in this application and thus help understand one or more embodiments of the invention, in the above description of the embodiments of the application, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this method of the application should not be interpreted as reflecting the intention that the claimed object requires more features than those explicitly stated in each claim. On the contrary, the subject of the invention should have fewer features than the above single embodiment.

Claims

1. A method for optimizing a smart microgrid, characterized in that: include: Obtaining power parameters that affect the operating efficiency of the smart microgrid, the power parameters including voltage fluctuation amplitude, frequency fluctuation amplitude, power loss, load factor, load fluctuation amplitude, line impedance, line capacitance, harmonic current, harmonic voltage, harmonic impedance, and harmonic frequency; Standardizing or normalizing the power parameters and operating efficiency to obtain multiple data points; Randomly select K data points as the initial cluster centers, K = 1, 2, ... n; n is the total number of data points; Calculate the distance from each data point to all cluster centers, and assign the data point to the cluster with the closest cluster center. Recalculate the location of the cluster center based on the data points in the cluster, and repeat this step until the location of the cluster center no longer changes or reaches the preset number of iterations to obtain the clustering result. Analyze the clustering results to find the cluster with the best operating efficiency. The data points in the cluster represent the power parameters under the optimal operating efficiency. The average value or median of the power parameters in the cluster is extracted as the parameter value corresponding to the optimal operating efficiency. Apply the parameter values ​​corresponding to the optimal operating efficiency to the smart microgrid to optimize the operating efficiency; Perform K-means clustering for different K values, calculate the silhouette coefficient of the clustering results under each K value, and obtain the reference silhouette coefficient; calculate the Calinski-Harabasz index for the clustering results under each K value, and obtain the reference Calinski-Harabasz index; generate multiple random data sets with the same sample size as the original data set composed of multiple data points, perform clustering for each random data set with different K values, and calculate the corresponding log-likelihood ratio, calculate the log-likelihood ratio of the original data set under different K values, and compare it with the corresponding value of the random data set to obtain the reference gap statistic; The reference contour coefficient is used as a row vector, the reference Calinski-Harabasz index is used as a column vector, a matrix is ​​constructed, and then the K value is imported to perform surface fitting to obtain the first reference fitting surface; The reference contour coefficient is used as a row vector, the reference gap statistic is used as a column vector, a matrix is ​​constructed, and then the K value is introduced to perform surface fitting to obtain a second reference fitting surface; The reference Calinski-Harabasz index is used as a row vector, the reference gap statistic is used as a column vector, a matrix is ​​constructed, and then the K value is introduced to perform surface fitting to obtain a third reference fitting surface; Based on the first reference fitting surface, the second reference fitting surface and the third reference fitting surface, the first reference Calinski-Harabasz index, the first reference gap statistic and the first K value corresponding to the maximum reference contour coefficient are obtained, the first reference contour coefficient, the second reference gap statistic and the second K value corresponding to the maximum reference Calinski-Harabasz index are obtained, and the second reference contour coefficient, the second reference Calinski-Harabasz index and the third K value corresponding to the maximum reference gap statistic are obtained; and the fourth K value corresponding to the average of the first reference contour coefficient and the second reference contour coefficient is obtained, the fifth K value corresponding to the average of the first reference Calinski-Harabasz index and the second reference Calinski-Harabasz index is obtained, and the sixth K value corresponding to the average of the first reference gap statistic and the second reference gap statistic is obtained, and the average among the first K value, the second K value, the third K value, the fourth K value, the fifth K value and the sixth K value is taken as the optimal number of clusters.

2. The optimization method of the smart microgrid according to claim 1, characterized in that: Perform K-means clustering on different K values, calculate the intra-cluster sum of squared errors corresponding to each K value, draw a relationship graph between the K value and the intra-cluster sum of squared errors, find the elbow point in the relationship graph, select the seventh K value corresponding to the elbow point, and take the average of the first K value, the second K value, the third K value, the fourth K value, the fifth K value, the sixth K value and the seventh K value as the optimal number of clusters.

3. An optimization system for a smart microgrid, characterized in that: The optimization method for the smart microgrid according to any one of claims 1 to 2 is implemented, wherein the optimization system for the smart microgrid comprises: An acquisition module is used to acquire power parameters that affect the operating efficiency of the smart microgrid, wherein the power parameters include voltage fluctuation amplitude, frequency fluctuation amplitude, power loss, load factor, load fluctuation amplitude, line impedance, line capacitance, harmonic current, harmonic voltage, harmonic impedance and harmonic frequency; A processing module, used for standardizing or normalizing the power parameters and operating efficiency to obtain multiple data points; Clustering module for: Randomly select K data points as initial cluster centers; Calculate the distance from each data point to all cluster centers, and assign the data point to the cluster with the closest cluster center. Recalculate the location of the cluster center based on the data points in the cluster, and repeat this step until the location of the cluster center no longer changes or reaches the preset number of iterations to obtain the clustering result. Analyze the clustering results to find the cluster with the best operating efficiency. The data points in the cluster represent the power parameters under the optimal operating efficiency. The average value or median of the power parameters in the cluster is extracted as the parameter value corresponding to the optimal operating efficiency. The optimization module is used to apply the parameter values ​​corresponding to the optimal operating efficiency to the smart microgrid to optimize the operating efficiency.

Citation Information

Patent Citations

  • Micro-grid group optimization method based on conditional value-at-risk

    CN113364043A

  • Power grid user data analysis method based on improved k-means clustering algorithm

    CN116894744A

  • Intelligent county power distribution network grid optimization method and system

    CN118133062A