A dynamic stability online evaluation method and system for a transformer box control system

Abstract

This invention relates to a method and system for online dynamic stability assessment of a substation control system, belonging to the field of substations. The method includes: collecting raw data from the substation control system and constructing a joint state vector set; performing local neighborhood analysis based on the joint state vector set to obtain the local covariance matrix and metric matrix corresponding to each state point; estimating the tangent space curvature based on the local covariance matrix to obtain the curvature value corresponding to each state point; simulating geodesic deviation based on the metric matrix to obtain the local geodesic deviation index; and performing dynamic stability assessment based on the curvature value and the local geodesic deviation index, with online rolling updates and early warnings. This invention is a dynamic stability assessment method that integrates system command and response information, possesses online assessment capabilities, and can provide early warnings of instability trends.

Description

Technical Field

[0001] This invention belongs to the field of transformer box technology, specifically relating to an online method and system for evaluating the dynamic stability of a transformer box control system. Background Technology

[0002] Currently, with the deepening of smart grid construction, substations, as key nodes in the power system, directly affect the safe operation of the entire power grid due to the dynamic stability of their control systems. Traditional substation stability assessment methods largely rely on physical modeling and offline simulation, such as time-domain simulation based on electromechanical transient models and static stability criteria based on impedance matrices. While these methods can reflect the steady-state behavior of the system to some extent, they often fail to accurately capture the dynamic evolution trend of the system in the face of nonlinear, time-varying, and strongly coupled actual operating environments. In recent years, data-driven methods have gradually emerged, such as using time series analysis, neural networks, and support vector machines for fault prediction and state assessment. However, these methods often focus on trend prediction of single variables and lack the ability to model the overall dynamic structure of the system, making it difficult to reveal the nonlinear instability mechanism of the system under critical states. For example, while the traditional Lyapunov exponent can reflect the system's sensitivity to initial conditions, its calculation depends on the system's analytical model, making it difficult to apply to discrete data collected in practice. On the other hand, statistical characteristic-based methods, such as variance and spectral analysis, although computationally simple, cannot effectively distinguish between stable and unstable states of the system, easily leading to false alarms or missed alarms. Summary of the Invention

[0003] To address the aforementioned problems in the existing technology, this invention provides a method and system for online dynamic stability evaluation of a substation control system.

[0004] The objective of this invention can be achieved through the following technical solutions: A method for online dynamic stability assessment of a substation control system, comprising the following steps: Step S1: Collect raw data from the substation's control system and construct a joint state vector set. ; Step S2: Based on the joint state vector set Perform local neighborhood analysis to obtain the local covariance matrix corresponding to each state point. and metric matrix ; Step S3: Based on the local covariance matrix Perform tangent space curvature estimation to obtain the curvature value corresponding to each state point. ; Step S4: Based on the metric matrix By simulating geodesic deviation, the local geodesic deviation index is obtained. ; Step S5: Based on the curvature value and the local geodesic deviation index Dynamic stability assessments are conducted, and online rolling updates and early warnings are implemented.

[0005] Preferably, step S1 specifically includes: The raw data of the control system is acquired and preprocessed at the same sampling frequency. The raw data of the control system includes instruction sequences. and response sequence ; Choose the embedding dimension m and the delay time ; For the current time i, construct the joint state vector. Within the collection time window The joint state vector set N is the total number of points within the time window.

[0006] Preferably, the local neighborhood analysis in step S2 specifically includes: For each state point i, find the K nearest neighbors by Euclidean distance and form a local neighborhood; Calculate the local covariance matrix within the local neighborhood. Mathematically described ,in, For the weight function, Let j be the joint state vector of the neighborhood point j. This is the weighted average vector of the neighborhood points; Based on the local covariance matrix The metric matrix is ​​obtained. Mathematically described ,in, It is a very small positive number. It is an identity matrix.

[0007] Preferably, the tangent space curvature estimation in step S3 specifically includes: For the local covariance matrix Perform eigenvalue decomposition to obtain eigenvalues. and the corresponding feature vector ; Obtain the eigendimensionality of the manifold at each state point. ; Obtain the orthogonal basis matrix of the tangent space Mathematically described ; Based on the orthogonal basis matrix Obtain the projection matrix , ; Based on the projection matrix The curvature value is obtained. Mathematically described ,in, Let j be the projection matrix of the neighboring point j. It is the Frobenius norm.

[0008] Preferably, the geodesic deviation simulation in step S4 specifically includes: Select the joint state vector of the nearest neighbor from the neighborhood points. The initial deviation vector is obtained. and its initial length Mathematically described , ; As the time series evolves through Q steps, the main trajectory from Starting from, the nearby trajectory is from Starting from the beginning, both move forward synchronously and calculate the deviation vector at each step q. and its deviation length ; Collect the deviation length of all valid steps Calculate its length relative to the initial length. The ratio of these values ​​is then averaged to obtain the local geodesic deviation index. .

[0009] Preferably, the dynamic stability assessment in step S5 specifically includes: Based on the curvature value and the local geodesic deviation index Calculate the average curvature of all points within the time window. and average deviation index Simultaneously calculate the standard deviation of curvature. ; Obtain the dynamic stability coefficient Mathematically described ,in, and These are normalization parameters; Based on the dynamic stability coefficient Provide online rolling updates and early warnings.

[0010] A dynamic stability online evaluation system for a transformer control system is used to execute the above-described dynamic stability online evaluation method for a transformer control system, including a preprocessing module, a local neighborhood analysis module, a curvature estimation module, a deviation simulation module, and a stability evaluation module. The preprocessing module is used to collect raw data from the substation's operating system and construct a joint state vector set. ; The local neighborhood analysis module is used to analyze the joint state vector set. Perform local neighborhood analysis to obtain the local covariance matrix corresponding to each state point. and metric matrix ; The curvature estimation module is used to estimate based on the local covariance matrix. Perform tangent space curvature estimation to obtain the curvature value corresponding to each state point. ; The deviation simulation module is used based on the metric matrix. By simulating geodesic deviation, the local geodesic deviation index is obtained. ; The stability assessment module is used to evaluate the curvature value. and the local geodesic deviation index Dynamic stability assessments are conducted, and online rolling updates and early warnings are implemented.

[0011] The beneficial effects of this invention are as follows: (1) By modeling the local geometry of the system manifold, the evolution characteristics of the system under nonlinear state can be effectively captured, avoiding the misjudgment of nonlinear behavior by traditional linear methods.

[0012] (2) By introducing the metric matrix and the curvature of the tangent space, the dynamic sensitivity of the system in different directions can be quantified, providing a more physically meaningful indicator for instability warning.

[0013] (3) The local deviation index based on geodesic deviation simulation can simulate the system response behavior under small disturbances.

[0014] (4) By constructing a dynamic stability coefficient and setting a graded early warning mechanism, it is possible to realize online rolling evaluation and real-time early warning of the system status, which greatly improves the safety and reliability of the substation operation. Attached Figure Description

[0015] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0016] Figure 1 This is a flowchart illustrating the steps of an online dynamic stability evaluation method for a transformer control system according to the present invention. Detailed Implementation

[0017] To better understand the invention, various aspects of the invention will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are merely illustrative of exemplary embodiments of the invention and are not intended to limit the scope of the invention in any way. Throughout the specification, the expression "and / or" includes any and all combinations of one or more of the associated listed items. As used herein, the terms "approximately," "about," and similar terms are used as expressions of approximation, not as expressions of degree, and are intended to describe inherent deviations in measured or calculated values ​​that will be recognized by those skilled in the art. Furthermore, the order in which the steps are described in this invention does not necessarily indicate the order in which these steps occur in actual operation, unless otherwise expressly defined or deduced from the context.

[0018] It should also be understood that expressions such as "comprising," "including," "having," "containing," and / or "comprising" are open-ended rather than closed-ended expressions in this specification, indicating the presence of the stated features, elements, and / or components, but not excluding the presence of one or more other features, elements, components, and / or combinations thereof. Furthermore, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features, not just individual elements in the list. Additionally, when describing embodiments of the invention, the word "may" is used to mean "one or more embodiments of the invention." And the term "exemplary" is intended to refer to examples or illustrations.

[0019] Unless otherwise specified, all terms used herein (including engineering and technical terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that, unless expressly stated herein, terms defined in common dictionaries shall be interpreted as having the meaning consistent with their meaning in the context of the relevant art, and not in an idealized or overly formalized sense.

[0020] It should be noted that, unless otherwise specified, the embodiments and features described in this invention can be combined with each other. The invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0021] Example 1: Please see Figure 1 A method for online evaluation of the dynamic stability of a substation control system, comprising: Step S1: Collect raw data from the substation's control system and construct a joint state vector set. ; Step S2: Based on the joint state vector set Perform local neighborhood analysis to obtain the local covariance matrix corresponding to each state point. and metric matrix ; Step S3: Based on the local covariance matrix Perform tangent space curvature estimation to obtain the curvature value corresponding to each state point. ; Step S4: Based on the metric matrix By simulating geodesic deviation, the local geodesic deviation index is obtained. ; Step S5: Based on the curvature value and the local geodesic deviation index Dynamic stability assessments are conducted, and online rolling updates and early warnings are implemented.

[0022] In this embodiment, step S1 can be implemented through the following steps: S101: The dynamic characteristics of the substation's control system are reflected in how commands are converted into responses. If the system is stable, the response will smoothly follow the commands; if the system is about to become unstable, the response will exhibit abnormalities (such as oscillations, lag, or irregularities). Therefore, the raw data of the control system is collected and preprocessed at the same sampling frequency. The raw data of the control system includes command sequences. and response sequence The instruction sequence The commands issued by the control system, such as upshifting or downshifting commands for on-load tap changers, can be encoded as numerical values, where +1 indicates upshifting, -1 indicates downshifting, and 0 indicates no command. The response sequence... The preprocessing represents the actual response of the controlled object (such as a transformer tap), for example, the actual position of the tap (continuous value). The preprocessing includes noise reduction, normalization, etc. S102: Select the embedding dimension m and the delay time The embedding dimension m represents the number of historical moments used to describe the current state, which is usually determined using the spurious nearest neighbor method, or a fixed value can be used. The delay time... This indicates how many points are taken from a historical value; S103: For the current time i, construct the joint state vector. It consists of instruction values ​​and response values ​​from the current time and several past moments, and is a collection of values ​​within a time window. The joint state vector set N is the total number of points within the time window.

[0023] In this embodiment, the local neighborhood analysis specifically refers to: S201: For each state point i, use algorithms such as kd-tree to find the K nearest neighbors by Euclidean distance and form a local neighborhood (the neighbors are approximately located on local blocks of the system manifold). S202: Calculate the local covariance matrix within the local neighborhood. This is used to describe the degree of dispersion of these K points in various directions, mathematically described as follows: ,in, This is a weighting function that measures the influence of neighboring point j on center point i. Let j be the joint state vector of the neighborhood point j. This is the weighted average vector of the neighborhood points; S203: Based on the local covariance matrix The metric matrix is ​​obtained. Mathematically described ,in, It is a very small positive number, used to prevent matrix singularity and ensure invertibility. Let be the identity matrix. In differential geometry, the metric on a manifold determines the geometric properties. In directions where the system's behavior changes drastically, the metric value is small (i.e., the direction is stretched, making the actual distance shorter), while in directions where the behavior changes slowly, the metric value is large (i.e., the direction is compressed, making the actual distance longer). Depend on The inverse construction of the matrix shows that the inverse matrix has smaller elements in the direction with large covariance (drastic changes).

[0024] In this embodiment, the tangent space curvature estimation specifically refers to: S301: For the local covariance matrix Perform eigenvalue decomposition to obtain eigenvalues. and the corresponding feature vector The magnitude of the eigenvalue represents the variance in that direction; S302: Obtain the eigendimensionality of the manifold at each state point. The first r principal components whose cumulative contribution rate reaches 95% are selected, and r is the intrinsic dimension. For example, if the sum of the first three eigenvalues ​​accounts for more than 95% of the total, then A value of 3 means that the local manifold is approximately three-dimensional; S303: Obtain the orthogonal basis matrix of the tangent space (spanned by the principal eigenvectors of the local covariance matrix). Mathematically described ; S304: Based on the orthogonal basis matrix Obtain the projection matrix , , representing the orthogonal projection onto the tangent space; S305: Based on the projection matrix The curvature value is obtained. Mathematically described ,in, Let j be the projection matrix of the neighboring point j. It is the Frobenius norm. It measures the rate at which the tangent space changes with position. If two points are very close but the tangent spaces are very different, it indicates that the manifold is severely curved and has a large curvature. If the two points are far apart but the tangent spaces are small, it indicates that the manifold is flat and has a small curvature.

[0025] In this embodiment, the geodesic deviation simulation specifically refers to: S401: Select the joint state vector of the nearest neighboring points from the neighboring points. The initial deviation vector is obtained. and its initial length Mathematically described , ; S402: Q-step evolution over time, i.e., tracking and Changes over time: The main trajectory from Starting from, the nearby trajectory is from Starting from the beginning, both move forward synchronously and calculate the deviation vector at each step q. and its deviation length ; S403: Collect the deviation lengths of all valid steps. Calculate its length relative to the initial length. The ratio of these values ​​is then averaged to obtain the local geodesic deviation index. Generally speaking, When the value is greater than 1, small deviations are amplified, and the system tends to be unstable near that point. When the value is less than 1, the deviations decrease, and the system tends to be stable.

[0026] In this embodiment, the dynamic stability assessment specifically includes: S501: Based on the curvature value and the local geodesic deviation index Calculate the average curvature of all points within the time window. and average deviation index Simultaneously calculate the standard deviation of curvature. This is used to reflect the fluctuation of curvature; an increase in curvature fluctuation is often a precursor to the system approaching its critical point. S502: Obtain the dynamic stability coefficient Mathematically described ,in, and The normalization parameter is calibrated using historical stable data; S503: Based on the aforementioned dynamic stability coefficient Online rolling updates and alerts are implemented. The alert logic is based on a set threshold, such as... The system is normal at this time. Furthermore, the price has been declining for three consecutive time windows, triggering a yellow alert, indicating a possible unstable trend. If a single drop exceeds 0.3, a red alert will be issued, indicating that the system is on the verge of instability and requires immediate inspection or intervention.

[0027] Example 2: An online dynamic stability evaluation system for a substation control system includes a preprocessing module, a local neighborhood analysis module, a curvature estimation module, a deviation simulation module, and a stability evaluation module. The preprocessing module is used to collect raw data from the substation's operating system and construct a joint state vector set. ; The local neighborhood analysis module is used to analyze the joint state vector set. Perform local neighborhood analysis to obtain the local covariance matrix corresponding to each state point. and metric matrix ; The curvature estimation module is used to estimate based on the local covariance matrix. Perform tangent space curvature estimation to obtain the curvature value corresponding to each state point. ; The deviation simulation module is used based on the metric matrix. By simulating geodesic deviation, the local geodesic deviation index is obtained. ; The stability assessment module is used to evaluate the curvature value. and the local geodesic deviation index Dynamic stability assessments are conducted, and online rolling updates and early warnings are implemented.

[0028] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for online evaluation of the dynamic stability of a substation control system, characterized in that, Includes the following steps: Step S1: Collect raw data from the substation's control system and construct a joint state vector set. ; Step S2: Based on the joint state vector set Perform local neighborhood analysis to obtain the local covariance matrix corresponding to each state point. and metric matrix ; Step S3: Based on the local covariance matrix Perform tangent space curvature estimation to obtain the curvature value corresponding to each state point. ; Step S4: Based on the metric matrix By simulating geodesic deviation, the local geodesic deviation index is obtained. ; Step S5: Based on the curvature value and the local geodesic deviation index Dynamic stability assessments are conducted, and online rolling updates and early warnings are implemented.

2. The method for online dynamic stability evaluation of a substation control system according to claim 1, characterized in that, Step S1 specifically includes: The raw data of the control system is acquired and preprocessed at the same sampling frequency. The raw data of the control system includes instruction sequences. and response sequence ; Choose the embedding dimension m and the delay time ; For the current time i, construct the joint state vector. Within the collection time window The joint state vector set constitutes N is the total number of points within the time window.

3. The method for online dynamic stability evaluation of a substation control system according to claim 2, characterized in that, The local neighborhood analysis in step S2 specifically refers to: For each state point i, find the K nearest neighbors by Euclidean distance and form a local neighborhood; Calculate the local covariance matrix within the local neighborhood. Mathematically described ,in, For the weight function, Let j be the joint state vector of the neighborhood point j. This is the weighted average vector of the neighborhood points; Based on the local covariance matrix The metric matrix is ​​obtained. Mathematically described ,in, It is a very small positive number. It is an identity matrix.

4. The method for online dynamic stability evaluation of a substation control system according to claim 3, characterized in that, The tangent space curvature estimation in step S3 specifically refers to: For the local covariance matrix Perform eigenvalue decomposition to obtain eigenvalues. and the corresponding feature vector ; Obtain the eigendimensionality of the manifold at each state point. ; Obtain the orthogonal basis matrix of the tangent space Mathematically described ; Based on the orthogonal basis matrix Obtain the projection matrix , ; Based on the projection matrix The curvature value is obtained Mathematically described ,in, Let J be the projection matrix of the neighboring point j. It is the Frobenius norm.

5. The method for online dynamic stability evaluation of a substation control system according to claim 4, characterized in that, The geodesic deviation simulation in step S4 specifically refers to: Select the joint state vector of the nearest neighbor from the neighborhood points. The initial deviation vector is obtained. and its initial length Mathematically described , ; As the time series evolves through Q steps, the main trajectory from Starting from, the nearby trajectory is from Starting from the beginning, both move forward synchronously and calculate the deviation vector at each step q. and its deviation length ; Collect the deviation length of all valid steps Calculate its length relative to the initial length. The ratio of these values ​​is then averaged to obtain the local geodesic deviation index. .

6. The method for online dynamic stability evaluation of a substation control system according to claim 1, characterized in that, The dynamic stability assessment in step S5 specifically involves: Based on the curvature value and the local geodesic deviation index Calculate the average curvature of all points within the time window. and average deviation index Simultaneously calculate the standard deviation of curvature. ; Obtain the dynamic stability coefficient Mathematically described ,in, and These are normalization parameters; Based on the dynamic stability coefficient Provide online rolling updates and early warnings.

7. An online dynamic stability evaluation system for a substation control system, characterized in that, The system is applied to the online dynamic stability evaluation method of the substation control system as described in any one of claims 1-6, and includes a preprocessing module, a local neighborhood analysis module, a curvature estimation module, a deviation simulation module, and a stability evaluation module. The preprocessing module is used to collect raw data from the substation's operating system and construct a joint state vector set. ; The local neighborhood analysis module is used to analyze the joint state vector set. Perform local neighborhood analysis to obtain the local covariance matrix corresponding to each state point. and metric matrix ; The curvature estimation module is used to estimate based on the local covariance matrix. Perform tangent space curvature estimation to obtain the curvature value corresponding to each state point. ; The deviation simulation module is used based on the metric matrix. By simulating geodesic deviation, the local geodesic deviation index is obtained. ; The stability assessment module is used to evaluate the curvature value. and the local geodesic deviation index Dynamic stability assessments are conducted, and online rolling updates and early warnings are implemented.

Images