Big Data-Based Smart Grid Fault Analysis Methods and Systems

Abstract

This invention relates to the field of smart grid fault analysis technology, specifically a smart grid fault analysis method and system based on big data. The method includes: constructing node admittance matrices by analyzing the power grid physical wiring diagram; extracting modal feature vectors through eigenvalue decomposition to generate a topological fingerprint database; synchronously acquiring wide-area phasor data streams, dynamically capturing data time windows and extracting resonant frequency band signals, and generating a fault feature dataset through feature enhancement; dynamically evaluating modal confidence factors, and activating redundant modes in the node-modal correlation graph when the confidence level of the dominant mode is below a threshold, fusing and reconstructing fault feature vectors; matching the reconstructed vectors with the fingerprint database for triple verification, and combining the confidence score to decide and output fault location coordinates or initiate safety protection commands. This invention improves the accuracy and fault tolerance of fault identification under new energy disturbance environments by introducing a dynamic confidence mechanism and a redundant mode compensation strategy.

Description

Technical Field

[0001] This invention relates to the field of smart grid fault analysis technology, specifically to a smart grid fault analysis method and system based on big data. Background Technology

[0002] In new power systems, the large-scale integration of renewable energy sources significantly enhances the dynamics of the power grid, and frequent power disturbances and topology changes complicate fault location. Although wide-area measurement systems provide high spatiotemporal resolution data support, extracting key modal response features highly correlated with faults remains a challenge. Currently used fault identification methods mostly rely on static modal features and lack dynamic assessment of modal stability and reliability. When the dominant mode degrades or energy disperses, there is a lack of effective alternative mechanisms, resulting in poor robustness and a high false positive rate in fault diagnosis.

[0003] Therefore, there is an urgent need for smart grid fault analysis methods and systems based on big data, which can dynamically identify key modal characteristics under multi-disturbance and multi-source input environments, thereby improving the accuracy of fault location and the overall robustness of the system. Summary of the Invention

[0004] (1) Technical problems to be solved

[0005] The purpose of this invention is to provide a smart grid fault analysis method and system based on big data, so as to solve the problem of unstable fault feature extraction caused by mode frequency drift and dominant mode failure under the conditions of high proportion of new energy access and frequent changes in grid topology.

[0006] (2) Technical solution

[0007] To achieve the above objectives, on the one hand, the present invention provides a smart grid fault analysis method based on big data, the method comprising:

[0008] Step S1: Obtain the power grid physical wiring diagram; parse the power grid physical wiring diagram to construct the node admittance matrix; extract the modal feature vector from the node admittance matrix through feature decomposition; generate dynamic fingerprint parameters based on the modal feature vector to construct a topological fingerprint database.

[0009] Step S2: Synchronously acquire phasor data streams from the wide-area measurement system and dynamically extract data time windows corresponding to scheduling command cycles; extract current and voltage signals from the inherent resonant frequency band of the power grid within the data time window; perform fault feature enhancement processing on the current and voltage signals to generate a fault feature dataset.

[0010] Step S3: Obtain the corresponding modal confidence factor through dynamic evaluation based on the modal feature vector; when the modal confidence factor of the dominant mode is lower than the preset activation threshold, activate the pre-constructed node-modal association graph and select the redundant modes in the node-modal association graph; fuse the feature components corresponding to the dominant mode in the fault feature dataset with the redundant modes to generate a fault feature vector.

[0011] Step S4: Match the fault feature vector with the topology fingerprint database, and sequentially perform Kirchhoff's law verification, topology connection consistency verification, and traveling wave reflection characteristic verification; calculate the confidence score based on the distribution results of the modal confidence factor; when the confidence score is greater than the preset score threshold and the verification is passed, output the fault location coordinates; otherwise, initiate the power grid safety protection command, which includes blocking automatic reclosing, initiating fault waveform recording, or sending a dispatch alarm signal.

[0012] Furthermore, the method for generating dynamic fingerprint parameters and constructing a topological fingerprint database based on the modal feature vector includes:

[0013] The modal feature vector is a low-energy modal vector with an eigenvalue less than a preset modal energy threshold. Based on the modal feature vector, the resonant frequency offset Δf = (f1-f0) / f0 and the impedance derivative norm ‖dZ / dt‖ are calculated to construct multidimensional dynamic fingerprint parameters. Among them, f1 is the real-time measurement value, f0 is the reference frequency, Z is the node impedance matrix element, and t is the time variable in which the reference is always synchronized with the wide-area measurement system.

[0014] A topological hash value is generated using a digital signature algorithm based on the dynamic fingerprint parameters; the topological hash value is then stored in a topological fingerprint database.

[0015] Furthermore, the method for constructing the node-modal association graph includes:

[0016] The electrical connectivity D between nodes is calculated based on the magnitudes of the elements of the node impedance matrix. mm ;

[0017] The modal response similarity S is calculated based on the cosine of the angle between the modal feature vectors. ij ;

[0018] The correlation strength W = D is calculated based on the electrical connectivity and modal response similarity. mm ×S ij Generate triples [node, association strength, modality] and store them as a graph database structure.

[0019] Furthermore, the calculation process of the modal confidence factor includes:

[0020] Monitor the drift amplitude of the modal frequency and construct a historical memory term reflecting the recent perturbation state of the mode; perform time decay weighting based on the historical memory term and the initial confidence value; calculate the confidence level by combining the correlation between the mode and the power perturbation to obtain the modal confidence factor.

[0021] Furthermore, the method for obtaining the corresponding confidence factor based on the modal feature vector through dynamic evaluation includes:

[0022] The initial modal weighting factor is set according to the type of power grid line.

[0023] The power output volatility of the new energy access point is monitored in real time. When the power output volatility exceeds the preset disturbance threshold, the initial mode weighting factor is dynamically adjusted to obtain the mode weighting factor.

[0024] When the access area is a photovoltaic power station, the weight of frequency-related mode components is increased, and the weight of impedance derivative-related mode components is decreased.

[0025] When the access area is a wind farm, the weight of the impedance derivative-related mode components is increased, while the weight of the frequency-related mode components is decreased.

[0026] The modal weighting factor and the modal feature vector are weighted and fused to generate a fault feature vector.

[0027] Furthermore, the method also includes:

[0028] Calculate the Shannon information entropy of the modal response amplitude and the relative drift amplitude of the frequency; when the Shannon information entropy exceeds a preset information entropy threshold, or the relative drift amplitude exceeds a drift amplitude threshold, adjust the confidence factor of the corresponding mode according to a preset penalty coefficient; use the corrected confidence factor for weighted calculation of the fault feature vector.

[0029] Furthermore, the method also includes:

[0030] During the topological fingerprint matching process, the overall modal information entropy of the fault feature dataset is calculated.

[0031] When the overall modal information entropy is less than the information entropy partition threshold, a full modal matching strategy is adopted.

[0032] When the overall modal information entropy is greater than the information entropy partitioning threshold, a redundant modal weighted matching strategy is adopted, and the modal confidence factor is used as the matching constraint.

[0033] Furthermore, the method also includes:

[0034] The confidence score is obtained by weighted fusion calculation based on the distribution of modal confidence factors and feature matching similarity. When the confidence score is lower than the preset score threshold, the automatic output of fault location coordinates is rejected, and fault recording data is triggered to be transmitted back. The confidence score is used as the priority ranking of the fusion judgment result location in the scheduling system.

[0035] Based on the same inventive concept, this invention also provides a smart grid fault analysis system based on big data, the system comprising:

[0036] The topology fingerprint database construction module is used to obtain the physical wiring diagram of the power grid; parse the physical wiring diagram of the power grid to construct the node admittance matrix; extract the modal feature vectors from the node admittance matrix through feature decomposition; and generate dynamic fingerprint parameters based on the modal feature vectors to construct the topology fingerprint database.

[0037] The real-time data preprocessing module is used to synchronously acquire phasor data streams from the wide-area measurement system, dynamically extract data time windows corresponding to scheduling command cycles, extract current and voltage signals in the inherent resonant frequency band of the power grid within the data time window, and perform fault feature enhancement processing on the current and voltage signals to generate a fault feature dataset.

[0038] The fault feature reconstruction module is used to obtain the corresponding modal confidence factor through dynamic evaluation based on the modal feature vector; when the modal confidence factor of the dominant mode is lower than the preset activation threshold, the pre-constructed node-modal association graph is activated, and redundant modes in the node-modal association graph are selected; the feature components corresponding to the dominant mode in the fault feature dataset are fused with the redundant modes to generate a fault feature vector.

[0039] The multidimensional verification decision module is used to match the fault feature vector with the topology fingerprint database, and sequentially perform Kirchhoff's law verification, topology connection consistency verification, and traveling wave reflection characteristic verification; calculate the confidence score based on the distribution results of the modal confidence factor; when the confidence score is greater than the preset score threshold and the verification is passed, output the fault location coordinates; otherwise, initiate the power grid safety protection command, which includes blocking automatic reclosing, initiating fault waveform recording, or sending a dispatch alarm signal.

[0040] (3) Beneficial effects

[0041] Compared with the prior art, the beneficial effects of the present invention are:

[0042] 1. This invention introduces modal confidence factors and uncertainty measurement mechanisms to achieve quantitative modeling and online discrimination of modal response credibility, and can still stably extract effective features even when the dominant mode degenerates.

[0043] 2. A collaborative control strategy of redundant modal compensation and matching score is proposed to support rapid modal switching and feature reconstruction when the main mode is unavailable, which significantly improves the fault identification accuracy and fault tolerance robustness of the system under multi-source disturbance environment. Attached Figure Description

[0044] Figure 1 This is a block diagram of the smart grid fault analysis method based on big data according to Embodiment 1 of the present invention;

[0045] Figure 2 This is a block diagram of the smart grid fault analysis system based on big data according to Embodiment 2 of the present invention. Detailed Implementation

[0046] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0047] Before providing examples, it is necessary to describe the application scenarios of this invention. This invention is applicable to complex power grid environments with a wide-area power system, particularly those with a high proportion of renewable energy integration. In such grids, the volatility and intermittency of renewable energy sources (such as wind power and photovoltaics) significantly increase the instability of the grid's modal response, causing methods based on static topology, fixed modal features, or rule bases to exhibit low confidence and increased false positive rates in fault location. Furthermore, the frequent adjustments to current power grid operation and scheduling result in a dynamically changing line topology, making traditional solutions relying on static models or fixed path propagation features difficult to adapt to. In scenarios with frequent renewable energy disturbances, the modal energy distribution reflected in time-series signals such as current and voltage is prone to drift or even failure of the dominant mode, leading to the failure of conventional matching strategies and the inability to effectively locate fault areas. Therefore, this invention focuses on addressing the following issues: high renewable energy integration ratio and modal response instability; frequent topology adjustments and failure of traditional fingerprint features; fault signals being masked or weakened by disturbances, resulting in decreased confidence; and the need for the system to possess online adaptive identification and fault-tolerant matching capabilities. Based on the above-mentioned practical needs, this invention constructs a dynamic modal fingerprint matching mechanism, introduces modal confidence factors and uncertainty measurement system, and realizes dynamic and reliable extraction and fault-tolerant location of fault features. It is particularly suitable for typical complex power grid scenarios with significant new energy disturbances, flexible power grid structure and strong state uncertainty.

[0048] Example 1: As Figure 1 As shown, this embodiment provides a smart grid fault analysis method based on big data, the method including:

[0049] Step S1: Obtain the power grid physical wiring diagram; parse the power grid physical wiring diagram to construct the node admittance matrix; extract the modal feature vector from the node admittance matrix through feature decomposition; generate dynamic fingerprint parameters based on the modal feature vector to construct a topological fingerprint database.

[0050] Step S2: Synchronously acquire phasor data streams from the wide-area measurement system and dynamically extract data time windows corresponding to scheduling command cycles; extract current and voltage signals from the inherent resonant frequency band of the power grid within the data time window; perform fault feature enhancement processing on the current and voltage signals to generate a fault feature dataset.

[0051] Step S3: Obtain the corresponding modal confidence factor through dynamic evaluation based on the modal feature vector; when the modal confidence factor of the dominant mode is lower than the preset activation threshold, activate the pre-constructed node-modal association graph and select the redundant modes in the node-modal association graph; fuse the feature components corresponding to the dominant mode in the fault feature dataset with the redundant modes to generate a fault feature vector.

[0052] Step S4: Match the fault feature vector with the topology fingerprint database, and sequentially perform Kirchhoff's law verification, topology connection consistency verification, and traveling wave reflection characteristic verification; calculate the confidence score based on the distribution results of the modal confidence factor; when the confidence score is greater than the preset score threshold and the verification is passed, output the fault location coordinates; otherwise, initiate the power grid safety protection command, which includes blocking automatic reclosing, initiating fault waveform recording, or sending a dispatch alarm signal.

[0053] For example, this embodiment scenario involves a single-phase ground fault in a wind farm's collector line, accompanied by power fluctuations caused by turbulence.

[0054] Specifically, the dominant mode refers to the mode component with an energy share greater than 30% or the highest weight; dynamic evaluation includes monitoring frequency drift amplitude, constructing disturbance history memory terms, and calculating power disturbance correlation; the characteristic component is a sub-element of the modal characteristic vector, representing the electrical parameters of a single mode.

[0055] Furthermore, the method for generating dynamic fingerprint parameters and constructing a topological fingerprint database based on the modal feature vector includes:

[0056] The modal feature vector is a low-energy modal vector with an eigenvalue less than a preset modal energy threshold. Based on the modal feature vector, the resonant frequency offset Δf = (f1-f0) / f0 and the impedance derivative norm ‖dZ / dt‖ are calculated to construct multidimensional dynamic fingerprint parameters. Among them, f1 is the real-time measurement value, f0 is the reference frequency, Z is the node impedance matrix element, and t is the time variable in which the reference is always synchronized with the wide-area measurement system.

[0057] A topological hash value is generated using a digital signature algorithm based on the dynamic fingerprint parameters; the topological hash value is then stored in a topological fingerprint database.

[0058] For example, the physical wiring diagram of the power grid is analyzed, including nodes #201-#210 of the wind farm, generating a 582-dimensional node admittance matrix; the node admittance matrix is ​​constructed according to the IEEE 39-node standard model, with elements Y ij =G ij +jB ij The results are calculated from the impedance parameters of each branch. Simultaneously, wind farm category labels are written into the topology library for subsequent modal matching and scenario association.

[0059] Perform eigenvalue decomposition to extract low-energy mode vectors with eigenvalues ​​λ < 0.15. max =3.07. The preset modal energy threshold is dynamically set according to the grid scale. In this embodiment, the number of wind farm nodes is 10, and the threshold is set to λ = 0.05λ. max ≈0.15. Due to the increased resonant mode density caused by the increased node size, the threshold needs to be lowered to avoid mode aliasing. Therefore, if the number of nodes in the region is greater than 500, the threshold is adjusted to 0.03λ. max .

[0060] Based on the selected modal components, the resonant frequency offset Δf = (52.3-50) / 50 = 0.046 is calculated, and the impedance derivative norm ‖dZ / dt‖ = 22.1 is the per-unit value, which is used to combine and construct dynamic fingerprint parameters.

[0061] In this embodiment, Z in the impedance derivative norm ‖dZ / dt‖ is defined as an element of the nodal impedance matrix, obtained by inverting the nodal admittance matrix. Its real-time value is calculated and updated based on the voltage and current data of the wide-area measurement system. The impedance derivative norm is normalized to a 100MVA standard capacity for the IEEE 39-bus system, in units of pu / s.

[0062] The time variable t is based on the clock of the scheduling master station. The time window length dt for derivative calculation is consistent with the scheduling period T. In this embodiment, T = dt = 200ms to ensure synchronization with the time scale of the phasor data stream.

[0063] After the dynamic fingerprint parameters are serialized, they are input into the SHA-256 algorithm to generate hash values ​​d4e5f6...a9b1 and stored in the topological fingerprint database to support subsequent fault feature comparison.

[0064] Furthermore, the method for constructing the node-modal association graph includes:

[0065] The electrical connectivity D between nodes is calculated based on the magnitudes of the elements of the node impedance matrix. mn ;

[0066] The modal response similarity S is calculated based on the cosine of the angle between the modal feature vectors. ij；

[0067] The correlation strength W = D is calculated based on the electrical connectivity and modal response similarity. mn ×S ij Generate triples [node, association strength, modality] and store them as a graph database structure.

[0068] For example, when the system detects that the dominant mode confidence factor of 0.65 is less than the activation threshold of 0.7, it triggers the redundant mode compensation mechanism.

[0069] The system calls a predefined node-modal correlation graph; it selects the k most relevant redundant modal components to the current fault target area from the graph as compensation candidates. k is dynamically set according to the number of nodes in the power grid area.

[0070] For example, when the target node #201 fails, select the three redundant modes with the highest correlation strength in the graph, such as #205, #209, and #210.

[0071] Subsequently, these redundant modes are introduced into the current fault feature reconstruction process and fused with the dominant mode features to generate a more stable and perturbation-robust reconstructed feature vector. This process ensures that the ability to identify fault features and the continuity of system judgment are maintained even in the event of degradation or failure of the dominant mode.

[0072] Furthermore, the calculation process of the modal confidence factor includes:

[0073] Monitor the drift amplitude of the modal frequency and construct a historical memory term reflecting the recent perturbation state of the mode; perform time decay weighting based on the historical memory term and the initial confidence value; calculate the confidence level by combining the correlation between the mode and the power perturbation to obtain the modal confidence factor.

[0074] For example, the confidence levels for the past three periods are [0.85, 0.76, 0.68], and the time decay factor η = 0.8.

[0075] The dynamic modal confidence factor is used to quantify the stability and reliability of each modal component under the current power grid conditions, guiding the weighting of fault feature vectors and the triggering mechanism of redundant modes. To calculate the modal confidence factor, the relative drift amplitude of the current modal frequency compared to the reference frequency is first monitored. If the frequency fluctuation is severe, it indicates that the mode is significantly affected by disturbances, resulting in decreased stability and reduced confidence. The system extracts the activation records of this mode from the previous n scheduling cycles to construct a historical memory entry. Applying a time decay factor η enables dynamic evaluation of recent activation levels; where h i(k) represents the activation state of this mode in the k-th period, with 1 for activation and 0 for inactivation. The number of historical periods n = min(5, fault characteristic time window length / scheduling period) ensures that the memory terms cover the typical disturbance decay time.

[0076] The confidence level is comprehensively assessed by combining the correlation factors between the modal amplitude and the renewable energy power disturbance rate. Finally, the system outputs the fused drift characteristics. Historical stability and the correlation of disturbance ρ i Modal confidence factor This is used to guide the weighted processing of fault feature vectors and the redundant mode triggering mechanism. Here, γ is an empirically set sensitivity factor, typically ranging from [3,7], adjusted according to the scene disturbance intensity; here, γ = 5; Δf i For the real-time frequency offset of mode i, The confidence level is the same as the previous period. in, The normalized standard deviation of the power fluctuation rate of new energy sources is given by κ = 0.5 for wind farms and κ = 0.3 for photovoltaic farms.

[0077] Furthermore, the method for obtaining the corresponding confidence factor based on the modal feature vector through dynamic evaluation includes:

[0078] The initial modal weighting factor is set according to the type of power grid line.

[0079] The power output volatility of the new energy access point is monitored in real time. When the power output volatility exceeds the preset disturbance threshold, the initial mode weighting factor is dynamically adjusted to obtain the mode weighting factor.

[0080] When the access area is a photovoltaic power station, the weight of frequency-related mode components is increased, and the weight of impedance derivative-related mode components is decreased.

[0081] When the access area is a wind farm, the weight of the impedance derivative-related mode components is increased, while the weight of the frequency-related mode components is decreased.

[0082] The modal weighting factor and the modal feature vector are weighted and fused to generate a fault feature vector.

[0083] For example, a vector data stream of a wide-area measurement system is acquired synchronously, wherein the sampling rate of 4 kHz conforms to the IEEE C37.118.2 standard.

[0084] Data windows are extracted according to a scheduling period of T = 200ms; the duration is dynamically adjusted based on the real-time load of the scheduling system.

[0085] The current and voltage signals in the 55-60Hz frequency band are extracted, and the inherent resonant frequency band is determined through historical fault statistics, covering 90% of the power grid resonant points.

[0086] Wavelet packet decomposition was used to extract resonant frequency band features, and the data dimension was compressed by a sparse autoencoder, which improved the signal-to-noise ratio from 15dB to 23dB, exceeding the target of 20dB improvement.

[0087] To achieve dynamic evaluation of modal confidence factors, in a wind farm access area, the system first sets initial modal weighting factors based on the grid line type. By default, the weights of frequency-dependent modal components and impedance derivative-dependent modal components are both 0.5.

[0088] Due to the monitoring of wind farm power fluctuation rate When the disturbance level exceeds the preset disturbance threshold of 25% by 32%, a dynamic correction mechanism is triggered. Since wind farm connection disturbances are more likely to cause changes in impedance response, the impedance derivative mode weight is increased from 0.5 to 0.7, and the frequency mode weight is decreased from 0.5 to 0.3. The frequency component Z and impedance derivative f are extracted from the modal feature vector and weighted together with the dynamically generated corrected mode weight vector W′=[0.3,0.7] to generate the corrected fault feature vector V. f =W′·[Z,f]. The fused fault feature vector V f It can better highlight the impedance derivative-related modes, and improve the stability and positioning accuracy of feature extraction in environments where wind power disturbances are dominant.

[0089] Specifically, the disturbance threshold is set according to the anti-interference capability classification of new energy power plants, and the dynamic correction mechanism is only applicable to the defined wind power and photovoltaic scenarios.

[0090] Furthermore, the method also includes:

[0091] Calculate the Shannon information entropy of the modal response amplitude and the relative drift amplitude of the frequency; when the Shannon information entropy exceeds a preset information entropy threshold, or the relative drift amplitude exceeds a drift amplitude threshold, adjust the confidence factor of the corresponding mode according to a preset penalty coefficient; use the corrected confidence factor for weighted calculation of the fault feature vector.

[0092] For example, in a single-phase ground fault scenario of a wind power collector line, the system first extracts the response amplitude and frequency fluctuation information of each mode from the current fault feature dataset. For each mode component, the system calculates its amplitude Shannon information entropy H. i and relative frequency drift amplitude Δf i / f0. In this embodiment, the amplitude Shannon information entropy of mode #207 is 0.41, which is greater than the preset information entropy threshold of 0.3; at the same time, the relative frequency drift amplitude of this mode is 0.12, which is greater than the drift amplitude threshold of 0.05.

[0093] Meeting any one of these conditions is considered modal instability, triggering a downregulation of the confidence factor; modes with a weight ratio greater than 30% are selected as dominant modes, and the confidence level of the dominant mode is... The revised confidence factor is 0.8 × C. t ≈0.61, where 0.8 is the penalty coefficient determined based on training with historical fault data. Subsequently, all modal confidence factors are normalized to ensure consistency when participating in the weighting process of the fault feature vector; where k is the number of historical cycles.

[0094] This correction mechanism is based on historical fault statistics, ensuring that the system can identify modal instability in real time and improve the credibility of the final matching score by dynamically adjusting the confidence level.

[0095] Specifically, the preset information entropy threshold and drift amplitude threshold were obtained through training on historical fault data, with the training set containing 327 fault records.

[0096] Furthermore, the method also includes:

[0097] During the topological fingerprint matching process, the overall modal information entropy of the fault feature dataset is calculated.

[0098] When the overall modal information entropy is less than the information entropy partition threshold, a full modal matching strategy is adopted.

[0099] When the overall modal information entropy is greater than the information entropy partitioning threshold, a redundant modal weighted matching strategy is adopted, and the modal confidence factor is used as the matching constraint.

[0100] For example, during topological fingerprint matching, the system first calculates the overall modal information entropy of the current fault feature dataset to assess the concentration or dispersion of modal energy distribution. When the overall modal information entropy is less than the information entropy partitioning threshold of 0.5, it indicates that the modal energy distribution is relatively concentrated. In this case, the full modal matching strategy is executed first to match all valid modal information to improve accuracy.

[0101] If the overall modal information entropy is higher than the information entropy partition threshold, it indicates that the modal features are showing a dispersion trend, and there may be abnormal situations such as dominant mode degradation and enhanced signal perturbation. At this time, the system automatically switches to a redundant mode weighted matching strategy. This strategy prioritizes modal components with high confidence factors and uses them as matching constraints to suppress the interference of unstable modes on the matching results.

[0102] The strategy switching mechanism ensures that the system can still perform stable and robust fault matching and location judgment under different disturbance environments.

[0103] Specifically, the information entropy partitioning threshold is set to 0.5 based on the power grid size.

[0104] Furthermore, the method also includes:

[0105] The confidence score is obtained by weighted fusion calculation based on the distribution of modal confidence factors and feature matching similarity. When the confidence score is lower than the preset score threshold, the automatic output of fault location coordinates is rejected, and fault waveform data is triggered for back transmission and expert diagnosis system intervention. The confidence score is used as the priority ranking of the fusion judgment result in the scheduling system.

[0106] For example, the similarity of fault feature matching is 0.88 obtained by using the cosine similarity algorithm.

[0107] Perform triple verification:

[0108] Kirchhoff's laws verification: The deviation of 4.2% is less than the 5% threshold, thus passing the verification; the 5% threshold standard is based on IEEE 1159 §4.3.

[0109] Topology connectivity consistency: SCADA matching rate of 98% is greater than the 95% threshold, which has been verified; the 95% threshold standard is based on DL / T 1230-2021.

[0110] Traveling wave reflection characteristics: Δt = 45.6 μs, within the standard range of 28.8-53.6 μs, which has been verified; the threshold standard is a new fixed threshold adapted to the high fluctuation scenario of new energy short-line circuits.

[0111] The confidence score S is obtained by weighted fusion of modal confidence factor distribution and feature matching similarity. Among them, w i The above-mentioned modified modal weights are ξ, where ξ is the modal confidence weight and ζ is the feature matching similarity weight. The weights ξ and ζ are dynamically adjusted based on the overall modal information entropy H. Based on the analysis of 327 historical fault data, when H > 0.3, the modal instability probability is > 80%. Therefore, when H < 0.3, values ​​of ξ = 0.4 and ζ = 0.6 are used to make feature matching more reliable; when H ≥ 0.3, values ​​of ξ = 0.7 and ζ = 0.3 are used to give priority to modal confidence.

[0112] Because S = 0.67 is less than the scoring threshold of 0.7 set according to the dispatching procedure, automatic output of location coordinates is rejected. A power grid safety protection command is initiated, the wind farm's grid-connected circuit breaker is locked, fault recording data is triggered for transmission, and a dispatching alarm signal is sent to the regional monitoring center. S is used as the fusion judgment value; this fault is marked as Class-B priority, requiring manual verification, and the wind farm's #201-#210 collector lines are disconnected.

[0113] Example 2: Based on the same inventive concept, such as Figure 2 As shown, this embodiment also provides a smart grid fault analysis system based on big data, the system comprising:

[0114] The topology fingerprint database construction module is used to obtain the physical wiring diagram of the power grid; parse the physical wiring diagram of the power grid to construct the node admittance matrix; extract the modal feature vectors from the node admittance matrix through feature decomposition; and generate dynamic fingerprint parameters based on the modal feature vectors to construct the topology fingerprint database.

[0115] The real-time data preprocessing module is used to synchronously acquire phasor data streams from the wide-area measurement system, dynamically extract data time windows corresponding to scheduling command cycles, extract current and voltage signals in the inherent resonant frequency band of the power grid within the data time window, and perform fault feature enhancement processing on the current and voltage signals to generate a fault feature dataset.

[0116] The fault feature reconstruction module is used to obtain the corresponding modal confidence factor through dynamic evaluation based on the modal feature vector; when the modal confidence factor of the dominant mode is lower than the preset activation threshold, the pre-constructed node-modal association graph is activated, and redundant modes in the node-modal association graph are selected; the feature components corresponding to the dominant mode in the fault feature dataset are fused with the redundant modes to generate a fault feature vector.

[0117] The multidimensional verification decision module is used to match the fault feature vector with the topology fingerprint database, and sequentially perform Kirchhoff's law verification, topology connection consistency verification, and traveling wave reflection characteristic verification; calculate the confidence score based on the distribution results of the modal confidence factor; when the confidence score is greater than the preset score threshold and the verification is passed, output the fault location coordinates; otherwise, initiate the power grid safety protection command, which includes blocking automatic reclosing, initiating fault waveform recording, or sending a dispatch alarm signal.

[0118] It should be noted that the specific methods by which each module performs operations in the system described in the above embodiments have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0119] Finally, it should be noted that although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A smart grid fault analysis method based on big data, characterized in that, The method includes: Obtain the physical wiring diagram of the power grid; parse the physical wiring diagram of the power grid to construct the node admittance matrix; extract the modal feature vectors from the node admittance matrix through eigenvalue decomposition; generate dynamic fingerprint parameters based on the modal feature vectors to construct a topological fingerprint database; The system synchronously acquires phasor data streams from a wide-area measurement system and dynamically extracts data time windows corresponding to scheduling command cycles; it extracts current and voltage signals from the inherent resonant frequency band of the power grid within the data time window; and it performs fault feature enhancement processing on the current and voltage signals to generate a fault feature dataset. Based on the modal feature vector, the corresponding modal confidence factor is obtained through dynamic evaluation; when the modal confidence factor of the dominant mode is lower than the preset activation threshold, the pre-constructed node-modal association graph is activated, and the redundant modes in the node-modal association graph are selected; the feature components corresponding to the dominant mode in the fault feature dataset are fused with the redundant modes to generate a fault feature vector; The fault feature vector is matched with the topology fingerprint database, and Kirchhoff's laws, topology connectivity consistency, and traveling wave reflection characteristics are verified sequentially. A confidence score is calculated based on the distribution of modal confidence factors. When the confidence score is greater than a preset score threshold and the verification is passed, the fault location coordinates are output. Otherwise, a power grid safety protection command is initiated, which includes blocking automatic reclosing, initiating fault waveform recording, or sending a dispatch alarm signal. The method for generating dynamic fingerprint parameters and constructing a topological fingerprint database based on the modality feature vector includes: The modal eigenvectors are low-energy modal vectors with eigenvalues ​​less than a preset modal energy threshold; the resonant frequency offset is calculated based on the modal eigenvectors. and impedance derivative norm Construct multi-dimensional dynamic fingerprint parameters; among which, For real-time measurements, As the reference frequency, For the elements of the nodal impedance matrix, The time variable is always synchronized with the wide-area measurement system as a reference. A topological hash value is generated using a digital signature algorithm based on the dynamic fingerprint parameters; the topological hash value is then stored in a topological fingerprint database. The method for constructing the node-modal association graph includes: Calculate the electrical connectivity between nodes based on the magnitudes of the elements of the node impedance matrix. ; Modal response similarity is calculated based on the cosine of the angle between modal feature vectors. ; The correlation strength is calculated based on the electrical connectivity and modal response similarity. Generate triples [node, association strength, mode] and store them as a graph database structure; The calculation process of the modal confidence factor includes: Monitor the drift amplitude of the modal frequency and construct a historical memory term reflecting the recent perturbation state of the mode; perform time decay weighting based on the historical memory term and the initial confidence value; calculate the confidence level by combining the correlation between the mode and the power perturbation to obtain the modal confidence factor; The method for obtaining the corresponding confidence factor based on the modality feature vector through dynamic evaluation includes: The initial modal weighting factor is set according to the type of power grid line; Real-time monitoring of the power output volatility of the new energy access point; when the power output volatility exceeds a preset disturbance threshold, the initial mode weighting factor is dynamically adjusted to obtain the mode weighting factor. When the access area is a photovoltaic power station, the weight of frequency-related mode components is increased and the weight of impedance derivative-related mode components is decreased. When the access area is a wind farm, increase the weight of impedance derivative-related mode components and decrease the weight of frequency-related mode components; The modal weighting factor and the modal feature vector are weighted and fused to generate a fault feature vector.

2. The smart grid fault analysis method based on big data according to claim 1, characterized in that, The method further includes: Calculate the Shannon information entropy of the modal response amplitude and the relative drift amplitude of the frequency; when the Shannon information entropy exceeds a preset information entropy threshold, or the relative drift amplitude exceeds a drift amplitude threshold, adjust the confidence factor of the corresponding mode according to a preset penalty coefficient; use the corrected confidence factor for weighted calculation of the fault feature vector.

3. The smart grid fault analysis method based on big data according to claim 2, characterized in that, The method further includes: During the topological fingerprint matching process, the overall modal information entropy of the fault feature dataset is calculated; When the overall modal information entropy is less than the information entropy partition threshold, a full modal matching strategy is adopted. When the overall modal information entropy is greater than the information entropy partitioning threshold, a redundant modal weighted matching strategy is adopted, and the modal confidence factor is used as the matching constraint.

4. The smart grid fault analysis method based on big data according to claim 3, characterized in that, The method further includes: The confidence score is obtained by weighted fusion calculation based on the distribution of modal confidence factors and feature matching similarity. When the confidence score is lower than the preset score threshold, the automatic output of fault location coordinates is rejected, and fault recording data is triggered to be transmitted back. The confidence score is used as the priority ranking of the fusion judgment result location in the scheduling system.

5. A smart grid fault analysis system based on big data, characterized in that, The system includes: A topology fingerprint database construction module is used to obtain the physical wiring diagram of the power grid; parse the physical wiring diagram of the power grid to construct a node admittance matrix; extract modal feature vectors from the node admittance matrix through feature decomposition; and generate dynamic fingerprint parameters based on the modal feature vectors to construct a topology fingerprint database. The real-time data preprocessing module is used to synchronously acquire phasor data streams from the wide-area measurement system, dynamically extract data time windows corresponding to scheduling command cycles, extract current and voltage signals within the inherent resonant frequency band of the power grid within the data time window, and perform fault feature enhancement processing on the current and voltage signals to generate a fault feature dataset. The fault feature reconstruction module is used to obtain the corresponding modal confidence factor through dynamic evaluation based on the modal feature vector; when the modal confidence factor of the dominant mode is lower than the preset activation threshold, the pre-constructed node-modal association graph is activated, and redundant modes in the node-modal association graph are selected; the feature components corresponding to the dominant mode in the fault feature dataset are fused with the redundant modes to generate a fault feature vector; The multidimensional verification decision module is used to match the fault feature vector with the topology fingerprint database, and sequentially perform Kirchhoff's law verification, topology connection consistency verification, and traveling wave reflection characteristic verification; calculate the confidence score based on the distribution results of the modal confidence factor; when the confidence score is greater than the preset score threshold and the verification is passed, output the fault location coordinates; otherwise, initiate the power grid safety protection command, which includes blocking automatic reclosing, initiating fault waveform recording, or sending a dispatch alarm signal; The method for generating dynamic fingerprint parameters and constructing a topological fingerprint database based on the modality feature vector includes: The modal eigenvectors are low-energy modal vectors with eigenvalues ​​less than a preset modal energy threshold; the resonant frequency offset is calculated based on the modal eigenvectors. and impedance derivative norm Construct multi-dimensional dynamic fingerprint parameters; among which, For real-time measurements, As the reference frequency, For the elements of the nodal impedance matrix, The time variable is always synchronized with the wide-area measurement system as a reference. A topological hash value is generated using a digital signature algorithm based on the dynamic fingerprint parameters; the topological hash value is then stored in a topological fingerprint database. The method for constructing the node-modal association graph includes: Calculate the electrical connectivity between nodes based on the magnitudes of the elements of the node impedance matrix. ; Modal response similarity is calculated based on the cosine of the angle between modal feature vectors. ; The correlation strength is calculated based on the electrical connectivity and modal response similarity. Generate triples [node, association strength, mode] and store them as a graph database structure; The calculation process of the modal confidence factor includes: Monitor the drift amplitude of the modal frequency and construct a historical memory term reflecting the recent perturbation state of the mode; perform time decay weighting based on the historical memory term and the initial confidence value; calculate the confidence level by combining the correlation between the mode and the power perturbation to obtain the modal confidence factor; The method for obtaining the corresponding confidence factor based on the modality feature vector through dynamic evaluation includes: The initial modal weighting factor is set according to the type of power grid line; Real-time monitoring of the power output volatility of the new energy access point; when the power output volatility exceeds a preset disturbance threshold, the initial mode weighting factor is dynamically adjusted to obtain the mode weighting factor. When the access area is a photovoltaic power station, the weight of frequency-related mode components is increased and the weight of impedance derivative-related mode components is decreased. When the access area is a wind farm, increase the weight of impedance derivative-related mode components and decrease the weight of frequency-related mode components; The modal weighting factor and the modal feature vector are weighted and fused to generate a fault feature vector.

Images