Emergency control fault scene simplification method based on time sequence track feature mining
Through timing trajectory feature mining and cluster analysis, the fault scenarios of the power system are simplified, the problem that traditional methods are difficult to adapt to complex fault scenarios is solved, and the efficiency and reliability of emergency control strategies are improved.
Patent Information
- Application Number
- CN202411286134.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-13
- Publication Date
- 2024-12-06
AI Technical Summary
Traditional emergency control strategies are formulated to rely on traversal calculation and interpolation methods, which are difficult to adapt to complex and diverse fault scenarios, and existing fault scenario search methods lack interpretability and efficiency.
The method based on timing trajectory feature mining is adopted to obtain the fault voltage sequence of the power system, generate a classification sequence, calculate the sequence distance matrix, and use the condensed hierarchical clustering method to cluster the fault scenes into clusters to reduce the number of scenes that need to be analyzed.
It effectively simplifies the complexity of fault scenarios, improves the efficiency of emergency control strategies, enhances the classification effect of fault scenarios, reduces the number of analyzed scenarios, and improves the adaptability and reliability of emergency control strategies.
Smart Images

Figure CN119089223A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to a fault scenario simplification technology, and in particular to an emergency control fault scenario simplification method based on time series trajectory feature mining. Background Art
[0002] As the penetration rate of renewable energy continues to increase, the randomness and uncertainty of the power system have increased significantly, posing a huge challenge to the formulation of traditional emergency control strategies. Traditional stability analysis and strategy formulation rely on ergodic calculations. At the same time, existing stability setting control strategies mainly rely on interpolation calculations of typical operating conditions. However, with the increasing diversity and complexity of fault scenarios, the existing interpolation methods are no longer applicable in the pre-formulation of emergency control strategies. In addition, due to the increase in the proportion of new energy and power electronic equipment feed-in, the operating scenarios of the power system have become more complex, and the representativeness of typical scenarios has also been weakened. More and more complex fault scenarios need to be considered for safety analysis and corresponding emergency control strategy formulation.
[0003] In the aforementioned stability analysis and strategy formulation, reducing and concise the scenarios that need to be considered is of great significance for improving the efficiency of stability analysis and decision-making and improving the adaptability of the methods. There are two types of existing fault scenario search / screening methods: manual scenario screening methods based on domain experience, and scenario screening based on Monte Carlo sampling or other sampling methods. Of the two methods mentioned, the former relies on manual experience and lacks reliability guarantees in the face of complex scenarios; the latter requires a large number of samples, and the entire scenario simplification process does not have a clear physical meaning and lacks explainability. Summary of the invention
[0004] Based on this, the present invention aims to propose a method for simplifying emergency control fault scenarios based on timing trajectory feature mining, which effectively mines and clusters the key timing trajectory features of a large number of fault scenarios, simplifies the complexity of the fault scenarios, and thus reduces the number of fault scenarios that need to be analyzed, so that the system can more efficiently specify the emergency control strategy of the system.
[0005] In a first aspect, the present invention proposes a method for simplifying emergency control failure scenarios based on time series trajectory feature mining, comprising:
[0006] Obtain several fault voltage sequences of the power system;
[0007] generating a classification sequence based on a number of fault voltage sequences;
[0008] Calculate the distance between the classification sequence and each fault voltage sequence to obtain the sequence distance matrix;
[0009] Cluster analysis is performed using the sequence distance matrix, and the fault voltage sequences that meet the clustering conditions are clustered into a cluster to obtain several fault clusters.
[0010] Further, generating a classification sequence based on a number of fault voltage sequences includes:
[0011] The u-shapelet algorithm is used to generate classification sequences from several fault voltage sequences.
[0012] Furthermore, the u-shapelet algorithm is used to generate classification sequences from several fault voltage sequences including:
[0013] generating at least two sub-sequences based on the plurality of fault voltage sequences;
[0014] Calculate the distance between the subsequence and each fault voltage sequence, recorded as the first distance;
[0015] A subsequence satisfying a classification condition is selected from at least two subsequences according to the first distance as a classification sequence.
[0016] Further, selecting a subsequence satisfying a classification condition from at least two subsequences according to the first distance as a classification sequence includes:
[0017] Calculate the mean and variance of the first distance;
[0018] Selecting a subsequence satisfying a first candidate object condition from at least two subsequences as an intermediate sequence according to a mean and a variance of the first distance;
[0019] The separation coefficient corresponding to each intermediate sequence is calculated according to the first distance, and the subsequence satisfying the second candidate object condition is selected as the classification sequence according to the separation coefficient.
[0020] Furthermore, the sequence distance matrix is used for cluster analysis to cluster the fault voltage sequences that meet the clustering conditions into a cluster, and several fault clusters are obtained, including:
[0021] The row elements in the sequence distance matrix represent the distance between the fault voltage sequence of different nodes in the same fault scenario and the classification sequence. The agglomerative hierarchical clustering method is used to perform cluster analysis on the sequence distance matrix, and the fault voltage sequences corresponding to different fault scenarios are classified into several fault clusters.
[0022] Furthermore, the distance is expressed using Euclidean distance.
[0023] Furthermore, obtaining several fault voltage sequences of the power system includes:
[0024] For each fault scenario, a voltage sequence of at least one node in the power system within a preset time range after the fault is cleared is obtained.
[0025] In a second aspect, the present invention provides an emergency control fault scenario simplification device based on time series trajectory feature mining, comprising:
[0026] A voltage sequence acquisition module, used to acquire several fault voltage sequences of the power system;
[0027] A classification sequence generation module, used for generating a classification sequence based on a number of fault voltage sequences;
[0028] A matrix calculation module is used to calculate the distance between the classification sequence and each fault voltage sequence to obtain a sequence distance matrix;
[0029] The sequence clustering module is used to perform clustering analysis using a sequence distance matrix, clustering the fault voltage sequences that meet the clustering conditions into a cluster, and obtaining a number of fault clusters.
[0030] In a third aspect, the present invention provides an electronic device comprising a memory storing computer executable instructions and a processor. When the computer executable instructions are executed by the processor, the device executes the various steps of the emergency control fault scenario simplification method based on time series trajectory feature mining provided in the first aspect.
[0031] In a fourth aspect, the present invention provides a readable storage medium storing a computer executable program, which, when executed, can implement the various steps of the emergency control fault scenario simplification method based on time series trajectory feature mining provided in the first aspect.
[0032] It can be seen from the above technical solutions that the present invention has the following beneficial effects:
[0033] The present invention provides an emergency control fault scenario simplification method based on time series trajectory feature mining, which effectively extracts and utilizes key time series trajectory features in the voltage recovery process after a fault in the power system, performs cluster analysis on the trajectory features, and classifies fault scenarios with similar patterns into the same category. A further embodiment uses the u-shapelet algorithm to complete the links of sequence feature extraction and sequence distance matrix. The simplification method provided by the present invention realizes the simplification of a large number of complex fault scenarios, accurately identifies and distinguishes different fault recovery modes, and enhances the classification effect of fault scenarios. Compared with traditional fault scenario analysis methods, the number of scenarios that need to be analyzed is greatly reduced, and the efficiency of emergency control strategy formulation is improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.
[0035] Figure 1It is a flowchart of an implementation method of an emergency control fault scenario simplification method based on time series trajectory feature mining provided by an embodiment of the present invention;
[0036] Figure 2 It is a framework diagram for implementing an emergency control fault scenario simplification method based on time series trajectory feature mining provided by another embodiment of the present invention;
[0037] Figure 3 It is a schematic diagram of the structure of a simplified device for emergency control fault scenarios based on time series trajectory feature mining provided by an embodiment of the present invention;
[0038] Figure 4 This is a diagram of the electronic device architecture provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0040] See also Figure 1 An embodiment of the present invention provides a method for simplifying emergency control failure scenarios based on time series trajectory feature mining, comprising the following steps:
[0041] Step S110: Acquire several fault voltage sequences of the power system.
[0042] Specifically, in this step, for different fault scenarios, several system nodes are selected to obtain their corresponding fault voltage sequences. Usually, the voltage response characteristics of different nodes are different. The fault voltage sequences of different nodes can more completely present the dynamic behavior of the system's response to the fault.
[0043] In a further embodiment, considering the importance of the fault location and the post-fault voltage recovery mode to the pre-formulation of the emergency control strategy, the voltage sequence within a preset time range after the system fault is cleared is selected as the analysis object. The preset time range can be 2s, 3s, 5s, etc. after the fault is cleared, which is used to reflect the most critical dynamic behavior of the system after the fault is cleared, and helps to capture the characteristics that have the greatest impact on system stability.
[0044] In a further embodiment, the initially acquired fault voltage sequence may be initially cleaned and preprocessed, such as missing value processing, data consistency check, abnormal value processing, etc., to ensure the quality and consistency of the data.
[0045] Step S120 : generating a classification sequence based on a number of fault voltage sequences.
[0046] Specifically, since the recovery process after a power system fault has obvious time domain characteristics, and the voltage response characteristics between different nodes vary according to the location of the fault, the u-shapelet algorithm is selected in this step to generate and screen the classification sequence.
[0047] The classification sequence is a subsequence generated from the fault voltage sequence. Specifically, the u-shapelet algorithm is used to analyze the fault voltage sequence to generate subsequences of different lengths as candidate sequences (i.e., shapelets) to ensure that the selected subsequences can accurately represent the key features of different fault scenarios and effectively distinguish different recovery modes of the same node after different fault scenarios. Subsequences similar to most fault voltage sequences may lack the necessary distinguishing ability, such as sequences with small changes. These sequences that do not have the distinguishing ability need to be eliminated from the initially generated subsequences, and subsequences that can significantly distinguish different fault recovery modes are screened out as classification sequences.
[0048] In a further embodiment, step S120 includes the following steps:
[0049] Step S121. Generate at least two sub-sequences based on a number of fault voltage sequences;
[0050] Step S122. Calculate the distance between the subsequence and each fault voltage sequence, recorded as the first distance;
[0051] Step S123: Select a subsequence that meets the classification condition from at least two subsequences according to the first distance as a classification sequence.
[0052] Specifically, this step includes the following steps:
[0053] Calculate the mean and variance of the first distance;
[0054] Selecting a subsequence satisfying a first candidate object condition from at least two subsequences as an intermediate sequence according to a mean and a variance of the first distance;
[0055] The separation coefficient corresponding to each intermediate sequence is calculated according to the first distance, and the subsequence satisfying the second candidate object condition is selected as the classification sequence according to the separation coefficient.
[0056] Step S130: Calculate the distance between the classification sequence and each fault voltage sequence to obtain a sequence distance matrix.
[0057] Specifically, this step converts the voltage sequence in the time domain into a sequence distance matrix through shapelet transformation. The previous step has screened out subsequences that can significantly distinguish different fault recovery modes. This step calculates the distance between the subsequence and the initially acquired fault voltage sequence to measure the similarity between the classification sequence and each fault voltage sequence. The calculation result is presented in a matrix. The row vector of the sequence distance matrix represents the distance between the voltage sequence corresponding to different nodes in the same fault scenario and the classification sequence.
[0058] Step S140: Perform cluster analysis using the sequence distance matrix to cluster the fault voltage sequences that meet the clustering conditions into a cluster, and obtain a number of fault clusters.
[0059] In this step, different fault scenarios with similar patterns are merged through cluster analysis to retain the local characteristics of the data. The clustering results are used to guide the formulation of emergency control strategies. Since similar scenarios are merged into one category, the number of fault scenarios that need to be considered is simplified and the reliability of the overall solution is enhanced.
[0060] Combine the following Figure 2 The emergency control fault scenario simplification method based on time series trajectory feature mining proposed in the present invention is further introduced.
[0061] See also Figure 2 An embodiment of the present invention provides an emergency control fault scenario simplification method based on time series trajectory feature mining, which specifically uses the u-shapelet algorithm to complete the feature mining of the sequence, and performs cluster analysis on different fault scenarios based on the mining results.
[0062] For different fault scenarios, select the voltage sequence within 2 seconds after the fault is cleared (denoted as V post ) as a data set, specifically to obtain the voltage response curve of node i 2s after the fault is cleared at different fault operating points, such as Figure 2 The upper left corner of the curve is shown in the figure. Using the u-shapelet algorithm, each sequence V post The mining analysis generates several subsequences as candidate sequences.
[0063] In order to quantify the similarity between each candidate sequence and each voltage sequence, we calculate each candidate sequence The distance from all voltage sequences, specifically the local Euclidean distance between the two is calculated as follows:
[0064]
[0065] in, Represents the candidate sequence The local Euclidean distance to the subsequence s, Represents the voltage sequence T and the candidate sequence A collection of subsequences of the same length.
[0066] In a further embodiment, in order to improve the efficiency of the u-shapelet algorithm search process, the u-shapelet search algorithm is parallelized so that the distance calculation between each candidate sequence and the voltage sequence is independent, which can significantly speed up the search. Especially when processing large-scale data sets, this improvement can greatly reduce the calculation time.
[0067] In addition, an early screening mechanism is introduced to exclude candidate sequences that do not have obvious distinguishing ability. Specifically, the distance between each candidate sequence and each voltage sequence is calculated. The candidate sequences are sorted according to the mean and variance, which can screen out candidate sequences with abnormally high or low means and small variances and eliminate them. The remaining candidate sequences are further sorted according to the separation coefficient to ensure that the selected classification sequences can significantly distinguish different post-fault recovery modes.
[0068] Specifically, a "good" classification sequence should be based on The two sample sets D divided A and D B There is a large separation factor (gap) between them. The definition of the separation factor is as follows:
[0069]
[0070] in, , Group D A and D B middle The mean of , Group D A and D B The larger the separation coefficient, the greater the difference between groups. The more significant, the quantitative index of the difference between samples in the group or The smaller it is, the more effectively the corresponding subsequence can distinguish different time series patterns.
[0071] Since the calculation process of the u-shapelet algorithm is unsupervised, it can be accelerated in many ways. Once the most informative classification sequence is identified, the multidimensional time series can be converted into a distance matrix. This process is called "shapelet transformation". Since the time series data of the power system is usually high-dimensional, the u-shapelet algorithm can effectively extract the key features of these high-dimensional data, extract explanatory local patterns from the high-dimensional data and perform similarity measurement, so as to understand the dynamic behavior of the power system in more detail, compress the complex multidimensional time series into an easy-to-handle two-dimensional matrix form, and simplify the complexity of cluster analysis.
[0072] like Figure 2 The matrix form shown in the upper right corner is the sequence distance matrix It can be expressed as follows:
[0073]
[0074] The row vectors in the matrix represent the system in the same fault scenario. The distance between the fault voltage sequence of nodes and the classification sequence is A failure scenario.
[0075] The sequence distance matrix is used as the input of cluster analysis, and the unsupervised agglomerative hierarchical clustering method is specifically selected for cluster analysis. This clustering method can effectively handle clusters of different shapes and sizes. By gradually merging similar clusters based on the connection criterion, it ensures that fault scenarios with similar patterns are classified into one category. The gradual merging method can retain the local characteristics of the data and adapt to complex voltage recovery characteristics, providing a more interpretable and reliable fault scenario classification for emergency control strategies. Figure 2 As shown in the clustering results in the lower right corner, by clustering the voltage sequences, fault scenarios with similar patterns can be clustered together, effectively reducing the number of scenarios to be analyzed and enabling more efficient formulation of emergency control strategies for the power system.
[0076] The above-mentioned embodiments provide a method for simplifying emergency control fault scenarios based on mining of timing trajectory features, which effectively extracts and utilizes key timing trajectory features in the process of voltage recovery after a fault in the power system, performs cluster analysis on the trajectory features, and classifies fault scenarios with similar patterns into the same category. A further embodiment uses the u-shapelet algorithm to complete the links of sequence feature extraction and sequence distance matrix. The simplification method provided by the present invention realizes the simplification of a large number of complex fault scenarios, accurately identifies and distinguishes different fault recovery modes, and enhances the classification effect of fault scenarios. Compared with traditional fault scenario analysis methods, it greatly reduces the number of scenarios that need to be analyzed and improves the efficiency of emergency control strategy formulation.
[0077] The above-disclosed method can be implemented using various forms of equipment, so the present invention also discloses an emergency control fault scenario simplification device based on time series trajectory feature mining corresponding to the above-disclosed method, and a specific embodiment is given below for detailed description.
[0078] like Figure 3 As shown, an embodiment of the present invention provides an emergency control fault scenario simplification device based on time series trajectory feature mining, comprising:
[0079] A voltage sequence acquisition module 302 is used to acquire several fault voltage sequences of the power system;
[0080] A classification sequence generating module 304, configured to generate a classification sequence based on a number of fault voltage sequences;
[0081] A matrix calculation module 306 is used to calculate the distance between the classification sequence and each fault voltage sequence to obtain a sequence distance matrix;
[0082] The sequence clustering module 308 is used to perform clustering analysis using a sequence distance matrix, clustering the fault voltage sequences that meet the clustering conditions into a cluster, and obtaining a plurality of fault clusters.
[0083] The implementation principle and technical effects of the device provided in the embodiments of the present application are the same as those of the aforementioned method embodiments. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiments.
[0084] The methods and related devices mentioned in the above embodiments are described with reference to the method flow charts and / or structural diagrams provided in the embodiments of the present application. Specifically, each process and / or block in the method flow charts and / or structural diagrams, as well as the combination of processes and / or blocks in the flow charts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the process. Figure 1 Schematic diagram of one or more processes and / or structures Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 Schematic diagram of one or more processes and / or structures Figure 1These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A flow or multiple flows and / or structures illustrate the steps of the functions specified in one block or multiple blocks.
[0085] The following embodiments are described by taking the method applied to a computer device as an example. It can be understood that the computer device can be any device with computing and processing functions, and can be but not limited to a server or a personal laptop computer, etc. In one embodiment, the computer device can be an application server, and the application server can be a server for running an application to be tested.
[0086] See also Figure 4 , which shows a hardware block diagram of an electronic device, the electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.
[0087] like Figure 4 As shown, the electronic device includes: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;
[0088] In the embodiment of the present application, the number of the processor 1, the communication interface 2, the memory 3, and the communication bus 4 is at least one, and the processor 1, the communication interface 2, and the memory 3 communicate with each other through the communication bus 4;
[0089] The processor 1 may be a central processing unit CPU, or an application-specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention, etc.;
[0090] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), etc., such as at least one disk memory;
[0091] Among them, the memory stores a program, and the processor can call the program stored in the memory, and the program is used to: implement each processing flow of the aforementioned emergency control fault scenario simplification solution based on time series trajectory feature mining.
[0092] An embodiment of the present invention also provides a readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the various processing flows of the emergency control fault scenario simplification solution based on time series trajectory feature mining provided in the above embodiment and / or any possible implementation method in combination with the embodiment are implemented.
[0093] The above-mentioned embodiments have described the present invention in particular detail with respect to possible scenarios, and those skilled in the art will recognize that the present invention can be practiced through other embodiments. The specific naming of components, the capitalization of terms, attributes, data structures, or any other programming or structural aspects are not mandatory or important, and the mechanisms or features of the present invention may have different names, forms, or procedures. The system may be implemented by a combination of hardware and software (as described), entirely by hardware elements, or entirely by software elements. The specific division of functions between the various system components described herein is exemplary only and not mandatory; on the contrary, the functions performed by a single system component may be performed by multiple components, or the functions performed by multiple components may be performed by a single component.
[0094] Those skilled in the art should understand that the various steps of the above disclosed method can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented with program codes executable by the computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the embodiments of the present invention are not limited to any specific combination of hardware and software.
[0095] These computing device executable programs (also referred to as programs, software, software applications, or code) include machine instructions for programmable processors, and these computing programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.
[0096] Certain aspects of the present invention include process steps and instructions described herein in the form of algorithms. It should be noted that the process steps and instructions of the present invention can be implemented in software, firmware and / or hardware, and when implemented by software, it can be downloaded, stored on different platforms used by various operating systems and operated from the platforms.
[0097] Those skilled in the art will understand that the structures shown in the accompanying drawings are merely block diagrams of partial structures related to the scheme of the present application, and do not constitute a limitation on the terminal device to which the scheme of the present application is applied. The specific terminal device may include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.
[0098] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "possible design" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.
[0099] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0100] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for simplifying emergency control failure scenarios based on time series trajectory feature mining, characterized in that: include: Obtain several fault voltage sequences of the power system; generating a classification sequence based on the plurality of fault voltage sequences; Calculating the distance between the classification sequence and each fault voltage sequence to obtain a sequence distance matrix; The sequence distance matrix is used to perform cluster analysis, and the fault voltage sequences that meet the clustering conditions are clustered into a cluster to obtain a plurality of fault clusters.
2. The method according to claim 1, characterized in that The generating a classification sequence based on the plurality of fault voltage sequences comprises: A classification sequence is generated from the plurality of fault voltage sequences using a u-shapelet algorithm.
3. The method according to claim 2, characterized in that The step of generating a classification sequence from the plurality of fault voltage sequences using a u-shapelet algorithm comprises: generating at least two sub-sequences based on the plurality of fault voltage sequences; Calculating the distance between the subsequence and each fault voltage sequence, recorded as a first distance; A subsequence satisfying a classification condition is selected from the at least two subsequences according to the first distance as a classification sequence.
4. The method according to claim 3, characterized in that The selecting a subsequence satisfying a classification condition from the at least two subsequences according to the first distance as a classification sequence comprises: Calculating the mean and variance of the first distance; selecting a subsequence satisfying a first candidate object condition from the at least two subsequences as an intermediate sequence according to the mean and variance of the first distance; The separation coefficient corresponding to each intermediate sequence is calculated according to the first distance, and the subsequence satisfying the second candidate object condition is selected as the classification sequence according to the separation coefficient.
5. The method according to claim 1, characterized in that The cluster analysis is performed using the sequence distance matrix to cluster the fault voltage sequences that meet the clustering conditions into a cluster, and several fault clusters are obtained, including: The row elements in the sequence distance matrix represent the distance between the fault voltage sequence of different nodes in the same fault scenario and the classification sequence. The agglomerative hierarchical clustering method is used to perform cluster analysis on the sequence distance matrix, and the fault voltage sequences corresponding to different fault scenarios are classified into several fault clusters.
6. The method according to claim 1, characterized in that The distance is expressed using Euclidean distance.
7. The method according to claim 1, characterized in that The acquisition of several fault voltage sequences of the power system includes: For each fault scenario, a voltage sequence of at least one node in the power system within a preset time range after the fault is cleared is obtained.
8. An emergency control fault scenario simplification device based on time series trajectory feature mining, characterized in that: include: A voltage sequence acquisition module, used to acquire several fault voltage sequences of the power system; A classification sequence generation module, used for generating a classification sequence based on a number of fault voltage sequences; A matrix calculation module is used to calculate the distance between the classification sequence and each fault voltage sequence to obtain a sequence distance matrix; The sequence clustering module is used to perform clustering analysis using a sequence distance matrix, clustering the fault voltage sequences that meet the clustering conditions into a cluster, and obtaining a number of fault clusters.
9. An electronic device, characterized in that: The device comprises a memory storing computer executable instructions and a processor. When the computer executable instructions are executed by the processor, the device executes the emergency control fault scenario simplification method based on time series trajectory feature mining as described in any one of claims 1 to 7.
10. A readable storage medium, characterized in that: A computer executable program is stored, and when the program is executed, the emergency control fault scenario simplification method based on time series trajectory feature mining as described in any one of claims 1 to 7 can be implemented.
Citation Information
Patent Citations
Power system transient voltage stability serious fault screening method
CN111244937A
Power distribution network arc grounding identification method based on waveform subsequence segmentation-clustering
CN115828150A
Automatic labeling method and system for industrial field time series data
CN117113237A
Time sequence clustering method based on u-Shape
CN118940061A
