Method and device for clustering and evaluating operation modes of power system

Abstract

The invention discloses a clustering and evaluation method and device for operation modes of a power system. The method comprises the following steps: carrying out dimensionality reduction feature extraction on actual power flow section operation data of a power system by adopting a principal component analysis method to obtain dimensionality reduction feature data; determining the optimal clustering number of the operation mode of the power system by adopting an elbow rule of a contour coefficient and an intra-cluster error sum of squares; performing clustering analysis on the dimension reduction feature data according to the optimal clustering number to obtain a clustering result of the operation mode of the power system, the clustering result being used for representing a typical operation mode of the power system; and evaluating the clustering result according to the contour coefficient distribution of each sample point in the dimension reduction feature data and the average contour coefficient, and determining an evaluation result of the clustering result.

Description

Technical Field

[0001] The present invention relates to the technical field of power system operation, and more specifically, to a method and device for clustering and evaluating power system operation modes. Background Art

[0002] The power system is experiencing a critical period of transformation from traditional energy to new energy. The uncertainty of power output and the diversification of load demand have increased the complexity of power system operation. The large-scale interconnection of power grids has made the geographical differences of new energy more prominent, and the natural characteristics of new energy such as wind power and photovoltaic power have led to obvious time differences in their power generation output. This difference has put forward higher requirements for the flexibility of power system dispatch and operation.

[0003] In the face of an increasingly complex operating environment, clustering research on the operation mode of power systems is particularly important. Cluster analysis helps to identify typical operation modes in power systems, thereby providing decision support for the planning and operation of power systems. However, existing clustering methods are often limited by the scale of generated data and are difficult to adapt to the complexity of actual power grid operation data. In addition, the determination of clustering categories often relies on experience and lacks clear regularity and scientificity. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a method and device for clustering and evaluating operation modes of an electric power system.

[0005] According to one aspect of the present invention, a method for clustering and evaluating power system operation modes is provided, comprising:

[0006] The principal component analysis method is used to extract the dimension reduction features of the actual power flow section operation data of the power system to obtain the dimension reduction feature data;

[0007] The optimal number of clusters for the operation mode of the power system is determined using the silhouette coefficient and the elbow rule of the sum of squared errors within clusters.

[0008] Performing cluster analysis on the dimension-reduced feature data according to the optimal cluster number to obtain cluster results of the operation mode of the power system, wherein the cluster results are used to characterize the typical operation mode of the power system;

[0009] The clustering results are evaluated according to the silhouette coefficient distribution and the average silhouette coefficient of each sample point in the dimensionality reduction feature data to determine the evaluation results of the clustering results.

[0010] Optionally, a principal component analysis method is used to extract dimension reduction features from the actual power flow section operation data of the power system to obtain dimension reduction feature data, including:

[0011] Standardize the actual flow section operation data to determine the standardized data;

[0012] Compute the covariance matrix of the standardized data;

[0013] The singular value decomposition method is used to calculate the eigenvalues ​​and eigenvectors of the covariance matrix;

[0014] Arrange the eigenvectors in descending order of eigenvalues, select a preset number of eigenvectors as main components, and determine the main component eigenvectors;

[0015] Based on the main component eigenvectors, the standardized data is projected into a new feature space to obtain the reduced dimension feature data.

[0016] Optionally, the actual flow section operation data is standardized to determine the standardized data, including:

[0017] Subtract the mean of the column from all the data in each dimension of the actual tidal section operation data to obtain the standardized data in each dimension data center.

[0018] Optionally, the calculation formula for each covariance of the covariance matrix is:

[0019]

[0020] In the formula, x i ,y i is the value of two dimensions of the i-th sample, is its mean, and N is the number of samples.

[0021] Optionally, the silhouette coefficient is calculated as:

[0022]

[0023] In the formula, a i is the average distance between the i-th sample point and other sample points in its category; b i It is the average distance between the i-th sample point and the sample points in the category to which the nearest category center belongs.

[0024] Optionally, the intra-cluster sum of squared errors is calculated as:

[0025]

[0026] In the formula, μ i is the category center of category i, C i is the i-th category, k is the number of categories, and x is C i The sample points within.

[0027] Optionally, the clustering result is evaluated according to the silhouette coefficient distribution and the average silhouette coefficient of each sample point in the dimension reduction feature data to determine the evaluation result of the clustering result, including:

[0028] In the clustering results, the silhouette coefficient of the sample points of each cluster is greater than 0, which means that the classification of the sample points of each cluster in the clustering results is reasonable;

[0029] When the average value of the silhouette coefficients of all sample points in the clustering result is greater than a preset threshold, the clustering result is determined to be qualified.

[0030] According to another aspect of the present invention, there is provided a device for clustering and evaluating an operation mode of a power system, comprising:

[0031] An extraction module is used to extract dimension reduction features from actual power flow section operation data of the power system using a principal component analysis method to obtain dimension reduction feature data;

[0032] A determination module for determining an optimal number of clusters for an operation mode of a power system using an elbow rule of a silhouette coefficient and a sum of squared errors within a cluster;

[0033] A clustering module is used to perform cluster analysis on the dimension reduction feature data according to the optimal cluster number to obtain the clustering results of the operation mode of the power system, wherein the clustering results are used to characterize the typical operation mode of the power system;

[0034] The evaluation module is used to evaluate the clustering results according to the silhouette coefficient distribution and the average silhouette coefficient of each sample point in the dimension reduction feature data, and determine the evaluation result of the clustering results.

[0035] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute the method described in any one of the above aspects of the present invention.

[0036] According to another aspect of the present invention, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of the above aspects of the present invention.

[0037] Therefore, the present invention can achieve optimal clustering of operating modes and clustering effect evaluation by reducing the dimension of operating mode data, extracting its key features for clustering, and determining the optimal number of clusters by comprehensively considering clustering evaluation indicators, thereby providing a reference basis for accurately analyzing and studying the changing characteristics of operating modes. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] A more complete understanding of exemplary embodiments of the present invention may be obtained by referring to the following drawings:

[0039] Figure 1 It is a flow chart of a clustering and evaluation method of power system operation modes provided by an exemplary embodiment of the present invention;

[0040] Figure 2 is another flow chart of a method for clustering and evaluating power system operation modes provided by an exemplary embodiment of the present invention;

[0041] Figure 3 is a schematic diagram of selecting the optimal number of clusters provided by an exemplary embodiment of the present invention;

[0042] Figure 4 is a schematic diagram of an optimal clustering result provided by an exemplary embodiment of the present invention;

[0043] Figure 5 is a schematic diagram of evaluation results of clustering results provided by an exemplary embodiment of the present invention;

[0044] Figure 6 It is a structural schematic diagram of a device for clustering and evaluating power system operation modes provided by an exemplary embodiment of the present invention;

[0045] Figure 7 This is a structure of an electronic device provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0046] Below, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described here.

[0047] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0048] Those skilled in the art can understand that the terms "first" and "second" in the embodiments of the present invention are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate the necessary logical order between them.

[0049] It should also be understood that, in the embodiments of the present invention, “plurality” may refer to two or more than two, and “at least one” may refer to one, two or more than two.

[0050] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0051] In addition, the term "and / or" in the present invention is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects before and after are in an "or" relationship.

[0052] It should also be understood that the description of the various embodiments of the present invention focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced to each other, and for the sake of brevity, they will not be described one by one.

[0053] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0054] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0055] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0056] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0057] Embodiments of the present invention can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate with many other general or special computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, servers, etc. include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, small computer systems, large computer systems, and distributed cloud computing technology environments including any of the above systems, etc.

[0058] Electronic devices such as terminal devices, computer systems, servers, etc. can be described in the general context of computer system executable instructions (such as program modules) executed by computer systems. Generally, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in a distributed cloud computing environment, where tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0059] Exemplary Methods

[0060] Figure 1 FIG. 1 is a flow chart of a clustering and evaluation method for power system operation modes provided by an exemplary embodiment of the present invention. This embodiment can be applied to electronic devices, such as Figure 1 As shown, the clustering and evaluation method 100 of the power system operation mode includes the following steps:

[0061] Step 101, using principal component analysis to extract dimension reduction features from actual power flow section operation data of the power system to obtain dimension reduction feature data;

[0062] Step 102, determining the optimal number of clusters of the operation mode of the power system by using the elbow rule of the silhouette coefficient and the sum of squares of the intra-cluster errors;

[0063] Step 103, performing cluster analysis on the dimension reduction feature data according to the optimal cluster number to obtain a clustering result of the operation mode of the power system, wherein the clustering result is used to characterize a typical operation mode of the power system;

[0064] Step 104, evaluating the clustering result according to the silhouette coefficient distribution and the average silhouette coefficient of each sample point in the dimension reduction feature data, and determining the evaluation result of the clustering result.

[0065] Specifically, the present invention proposes a clustering and evaluation method for the operation mode of a power system, and formulates corresponding judgment and evaluation criteria to scientifically evaluate the complexity and clustering effect of the operation mode of the power system. The present invention analyzes and processes the actual flow section operation data of the power system, extracts the main features through a dimensionality reduction method, and realizes the clustering division of the operation mode of the power system. At the same time, combined with the clustering effect evaluation index, the optimal number of clusters is selected, and a clustering effect evaluation method suitable for clustering the operation mode of the power system is proposed, which is beneficial for the power system operator to extract typical operation modes and evaluate the division results of the operation modes.

[0066] The present invention proposes a power system operation mode clustering and evaluation method, which includes four steps: Figure 2 As shown:

[0067] Step 1: Use principal component analysis (PCA) to reduce the dimension of the actual power system flow section operation data to extract the main features. For different flow sections, the operation data constitutes a set of multidimensional data points, and the data dimension is the number of flow sections. Using principal component analysis to reduce the data dimension mainly includes five steps:

[0068] The first step is to standardize the data. Each dimension data is a column. Subtract the mean of the column from all the data in this dimension to centralize the data in each dimension.

[0069] The second step is to calculate the covariance matrix of the processed data set. For variables x and y in each dimension of the data set, the covariance calculation formula is:

[0070]

[0071] Among them, x i ,y i is the value of two dimensions of the i-th sample, is its mean, and N is the number of samples.

[0072] The third step is to calculate the eigenvalues ​​and eigenvectors. The eigenvalues ​​and corresponding eigenvectors of the covariance matrix are calculated using the singular value decomposition (SVD) method. The eigenvalue represents the variance or degree of variation of each principal component, and the eigenvector represents the spatial direction of the principal component. The eigenvector with the largest eigenvalue has the largest variance in the data set and is identified as the main component.

[0073] The calculation process of the singular value decomposition method is as follows. For any matrix A, it can be decomposed into the following form:

[0074] A=UΣV T

[0075] Among them, U and V are the left and right singular vectors respectively, satisfying UU T =1, VV T =1, Σ is all 0 except the elements on the main diagonal. The elements on the main diagonal are called singular values.

[0076] The eigenvalue matrix is ​​equal to the square of the singular value matrix. The eigenvalues ​​and singular values ​​satisfy the following relationship:

[0077]

[0078] Among them, σ i is a singular value, λi is the characteristic value.

[0079] The fourth step is to sort in descending order of eigenvalues ​​and select the first m eigenvectors as the main components after dimensionality reduction, where m is the dimension of the low-dimensional data after dimensionality reduction.

[0080] Finally, in the fifth step, the original data is projected into the new feature space using the selected eigenvector as the basis to obtain the reduced-dimensional data.

[0081] Step 2: Determine the maximum number of clusters and select the optimal number of clusters by comprehensively considering the clustering evaluation indicators. The optimal number of clusters is selected by the elbow rule of the silhouette coefficient and the sum of squared errors within the cluster, providing a method for selecting the number of clusters for the next step of clustering.

[0082] The silhouette coefficient calculation method is:

[0083]

[0084] Among them, a i is the average distance between the i-th sample point and other sample points in its category, reflecting the compactness within the cluster; b i It is the average distance between the i-th sample point and the sample points in the category to which the closest category center belongs, reflecting the separation degree between clusters. i The closer it is to 1, the closer the sample point is to the data in its category and well separated from other categories; when it is close to 0, it means that the sample point is at the boundary of the category, or the distance within the category is equivalent to the distance between categories; when it is close to -1, it means that the sample point may be assigned to the wrong category.

[0085] The intra-cluster error sum of squares is calculated as follows:

[0086]

[0087] Among them, μ i is the category center of category i, C i is the i-th category, and k is the number of categories. This indicator is the clustering error of all samples, reflecting the quality of the clustering effect. The smaller the value, the better.

[0088] The elbow rule means that as the number of clusters k increases, the E value gradually decreases. When k is less than the optimal number of clusters, the E value decreases greatly as k increases, and when k is close to the optimal number of clusters, the E value decreases sharply as k increases, and then tends to be flat as the k value continues to increase. The relationship diagram is similar to the shape of an elbow, and the k value corresponding to the elbow is the optimal number of clusters for the data.

[0089] Step 3: Cluster the reduced dimension running data according to the optimal number of clusters determined in step 2. The clustering is implemented by k-means clustering. First, the category center is initialized using the k-means++ algorithm, and the sample points are assigned to the category to which the nearest category center belongs according to the distance between each sample point and the category center; then, after all sample points are assigned to categories, the average value of the sample points in each category is used as the category center, and the category is reallocated. This is iterated continuously until the category center no longer changes or the maximum number of iterations is reached, which is the final classification result.

[0090] Step 4: Evaluate the clustering effect based on the classification results. Evaluate the clustering results based on the distribution diagram of the silhouette coefficient of each sample point. A silhouette coefficient greater than 0 indicates that the classification of the corresponding sample point is reasonable. At the same time, define the average silhouette coefficient S as the average of the silhouette coefficients of all sample points. A value above 0.5 indicates that the clustering result is good.

[0091]

[0092] A specific implementation example is the actual power system flow section operation data of a certain region in 2024. The flow sections include six flow sections: HXWS flow section, XJWS flow section, DY flow section, GY flow section, QY flow section, and HY flow section. The active power value of the flow section at a time interval of 5 minutes constitutes a six-dimensional data sample point.

[0093] Step 1: Use principal component analysis to reduce the dimension of the actual power flow section operation data of the power system to extract the main features. The dimension of the power flow data in this embodiment is 6 dimensions.

[0094] The data is standardized, its covariance matrix is ​​calculated, and its eigenvalues ​​and corresponding eigenvectors are calculated by singular value decomposition method, and arranged in descending order by eigenvalue. In this embodiment, the first two eigenvectors are selected as the main components after dimensionality reduction, and the dimension of the low-dimensional data after dimensionality reduction is 2. Finally, the original data is projected into the new feature space with the selected eigenvector as the basis to obtain the data after dimensionality reduction.

[0095] Step 2: Determine the maximum number of clusters and select the optimal number of clusters by comprehensively considering the clustering evaluation indicators.

[0096] This embodiment selects the optimal number of clusters by comprehensively considering the two indicators of silhouette coefficient and intra-cluster error sum of squares. Figure 3 , it is determined that the optimal number of clusters is 12, under which the silhouette coefficient is high and the sum of squared errors within the cluster has reached the elbow position.

[0097] Step 3: Cluster the reduced dimension operation data. The results of this embodiment using k-means clustering into 12 categories are as follows: Figure 4 shown.

[0098] Step 4: Evaluate the clustering effect based on the classification results.

[0099] In this embodiment, after clustering is completed according to the optimal number of clusters, a distribution histogram of the silhouette coefficients of all sample points in the sample data set is drawn as follows: Figure 5 , the negative values ​​of the silhouette coefficient only account for a small proportion, indicating that most sample points are reasonably assigned to the corresponding categories; the average silhouette coefficient is 0.53, and the clustering effect is relatively good.

[0100] Therefore, the present invention can achieve optimal clustering of operating modes and clustering effect evaluation by reducing the dimension of operating mode data, extracting its key features for clustering, and determining the optimal number of clusters by comprehensively considering clustering evaluation indicators, thereby providing a reference basis for accurately analyzing and studying the changing characteristics of operating modes.

[0101] Exemplary Devices

[0102] Figure 6 FIG. 1 is a schematic diagram of a clustering and evaluation device for power system operation modes provided by an exemplary embodiment of the present invention. Figure 6 As shown, the device 600 includes:

[0103] The extraction module 610 is used to extract dimension reduction features from the actual power flow section operation data of the power system by using the principal component analysis method to obtain dimension reduction feature data;

[0104] A determination module 620 is used to determine the optimal number of clusters of the operation mode of the power system using the elbow rule of the silhouette coefficient and the sum of squared errors within the cluster;

[0105] A clustering module 630 is used to perform cluster analysis on the dimension reduction feature data according to the optimal cluster number to obtain a clustering result of the operation mode of the power system, wherein the clustering result is used to characterize a typical operation mode of the power system;

[0106] The evaluation module 640 is used to evaluate the clustering result according to the silhouette coefficient distribution and the average silhouette coefficient of each sample point in the dimension reduction feature data, and determine the evaluation result of the clustering result.

[0107] Optionally, the extraction module 610 includes:

[0108] The processing submodule is used to standardize the actual flow section operation data and determine the standardized data;

[0109] A first calculation submodule, used for calculating the covariance matrix of the standardized data;

[0110] The second calculation submodule is used to calculate the eigenvalues ​​and eigenvectors of the covariance matrix using a singular value decomposition method;

[0111] A selection submodule is used to arrange the eigenvectors in descending order of eigenvalues, select a preset number of eigenvectors as main components, and determine the main component eigenvectors;

[0112] The projection submodule is used to project the standardized data into a new feature space based on the main component eigenvectors to obtain the reduced dimension feature data.

[0113] Optionally, the processing submodule includes:

[0114] The acquisition unit is used to subtract the mean value of the column from all the data in each dimension of the actual flow section operation data to obtain the standardized data in each dimension data center.

[0115] Optionally, the calculation formula for each covariance of the covariance matrix is:

[0116]

[0117] In the formula, x i ,y i is the value of two dimensions of the i-th sample, is its mean, and N is the number of samples.

[0118] Optionally, the silhouette coefficient is calculated as:

[0119]

[0120] In the formula, a i is the average distance between the i-th sample point and other sample points in its category; b i It is the average distance between the i-th sample point and the sample points in the category to which the nearest category center belongs.

[0121] Optionally, the intra-cluster sum of squared errors is calculated as:

[0122]

[0123] In the formula, μ i is the category center of category i, C i is the i-th category, k is the number of categories, and x is C i Sample points within.

[0124] Optionally, the evaluation module 640 includes:

[0125] The first determination submodule is used to determine that the classification of the sample points of each cluster in the clustering result is reasonable when the silhouette coefficient of the sample points of each cluster in the clustering result is greater than 0;

[0126] The second determination submodule is used to determine that the clustering result is qualified when the average value of the silhouette coefficients of all sample points in the clustering result is greater than a preset threshold.

[0127] Exemplary Electronic Devices

[0128] Figure 7 This is a structure of an electronic device provided by an exemplary embodiment of the present invention. Figure 7 As shown, the electronic device 70 includes one or more processors 71 and a memory 72 .

[0129] The processor 71 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0130] The memory 72 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 71 may run the program instructions to implement the methods of the software programs of the various embodiments of the present invention described above and / or other desired functions. In one example, the electronic device may also include: an input device 73 and an output device 74, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0131] In addition, the input device 73 may also include, for example, a keyboard, a mouse, and the like.

[0132] The output device 74 can output various information to the outside, and can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto.

[0133] Of course, to simplify, Figure 7 Only some of the components related to the present invention in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application conditions, the electronic device may also include any other appropriate components.

[0134] Exemplary computer program products and computer-readable storage media

[0135] In addition to the above-mentioned methods and devices, an embodiment of the present invention may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present invention described in the above-mentioned "Exemplary Method" section of this specification.

[0136] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the embodiments of the present invention, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0137] In addition, an embodiment of the present invention may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present invention described in the above “Exemplary Method” section of this specification.

[0138] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, system or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0139] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details disclosed above are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0140] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0141] The block diagrams of the devices, systems, equipment, and systems involved in the present invention are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, systems, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The word "such as" used here refers to the phrase "such as but not limited to", and can be used interchangeably with it.

[0142] The method and system of the present invention may be implemented in many ways. For example, the method and system of the present invention may be implemented by software, hardware, firmware or any combination of software, hardware, firmware. The above order of steps for the method is only for illustration, and the steps of the method of the present invention are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present invention may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present invention. Thus, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

[0143] It should also be noted that in the system, device and method of the present invention, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. The above description of the disclosed aspects is provided to enable any technician in the field to make or use the present invention. Various modifications to these aspects are very obvious to those skilled in the art, and the general principles defined here can be applied to other aspects without departing from the scope of the present invention. Therefore, the present invention is not intended to be limited to the aspects shown here, but in accordance with the widest range consistent with the principles and novel features disclosed here.

[0144] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present invention to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A clustering and evaluation method for power system operation modes, characterized in that: include: The principal component analysis method is used to extract the dimension reduction features of the actual power flow section operation data of the power system to obtain the dimension reduction feature data; Determining the optimal number of clusters for the operation mode of the power system using the silhouette coefficient and the elbow rule of the sum of squared errors within the cluster; Performing cluster analysis on the dimension reduction feature data according to the optimal cluster number to obtain a clustering result of the operation mode of the power system, wherein the clustering result is used to characterize a typical operation mode of the power system; The clustering result is evaluated according to the silhouette coefficient distribution and the average silhouette coefficient of each sample point in the dimension reduction feature data to determine the evaluation result of the clustering result.

2. The method according to claim 1, characterized in that The principal component analysis method is used to extract the dimension reduction features of the actual power flow section operation data of the power system to obtain the dimension reduction feature data, including: Standardizing the actual flow section operation data to determine standardized data; Calculating a covariance matrix of the standardized data; Calculating the eigenvalues ​​and eigenvectors of the covariance matrix using a singular value decomposition method; Arrange the eigenvectors in descending order of the eigenvalues, select a preset number of the eigenvectors as main components, and determine the main component eigenvectors; The standardized data is projected onto a new feature space based on the main component feature vector to obtain the dimension-reduced feature data.

3. The method according to claim 2, characterized in that The actual flow section operation data is subjected to standardization processing to determine the standardized data, including: Subtract the mean of the column from all the data in each dimension of the actual tidal section operation data to obtain the standardized data in each dimensional data center.

4. The method according to claim 2, characterized in that: The calculation formula for each covariance of the covariance matrix is: In the formula, x i ,y i is the value of two dimensions of the i-th sample, is its mean, and N is the number of samples.

5. The method according to claim 1, characterized in that The calculation method of the silhouette coefficient is: In the formula, a i is the average distance between the i-th sample point and other sample points in its category; b i It is the average distance between the i-th sample point and the sample points in the category to which the nearest category center belongs.

6. The method according to claim 1, characterized in that The intra-cluster error sum of squares is calculated as follows: In the formula, μ i is the category center of category i, C i is the i-th category, k is the number of categories, and x is C i Sample points within.

7. The method according to claim 1, characterized in that The clustering result is evaluated according to the silhouette coefficient distribution and the average silhouette coefficient of each sample point in the dimension reduction feature data to determine the evaluation result of the clustering result, including: If the silhouette coefficient of the sample points of each cluster in the clustering result is greater than 0, it is determined that the classification of the sample points of each cluster in the clustering result is reasonable; When the average value of the silhouette coefficients of all sample points in the clustering result is greater than a preset threshold, the clustering result is determined to be qualified.

8. A device for clustering and evaluating power system operation modes, characterized in that: include: An extraction module is used to extract dimension reduction features from actual power flow section operation data of the power system using a principal component analysis method to obtain dimension reduction feature data; A determination module, for determining an optimal number of clusters of the operation mode of the power system by using a silhouette coefficient and an elbow rule of the sum of squared errors within a cluster; A clustering module, used for performing cluster analysis on the dimension reduction feature data according to the optimal cluster number, and obtaining a clustering result of the operation mode of the power system, wherein the clustering result is used to characterize a typical operation mode of the power system; An evaluation module is used to evaluate the clustering result according to the silhouette coefficient distribution and the average silhouette coefficient of each sample point in the dimension reduction feature data, and determine the evaluation result of the clustering result.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1 to 7.

Images