A Fault Identification and Network Efficiency Improvement Method for Smart Microgrids

Abstract

The present invention discloses a method for fault identification and network efficiency improvement in an intelligent microgrid, specifically relating to the technical field of cross-domain collaborative avoidance, and is used to solve the resonance frequency band problem caused by the coupling of the existing SDN flow table update strategy and the power fluctuation of the microgrid. By collecting the power fluctuation data of the microgrid and the SDN flow table update parameters in real time and performing timestamp calibration; extracting the frequency domain characteristics of the power fluctuation and the time domain correlation coefficient of the flow table update; generating a dynamic resonance risk index through cross-domain coupling model to fuse frequency domain integration and time domain convolution; predicting the future main fluctuation frequency band based on the phase change and generating constraint conditions in combination with the historical avoidance frequency band; dynamically generating frequency avoidance weights according to the real-time network load and frequency band effectiveness; triggering the asymmetric flow table period adjustment to achieve the frequency domain avoidance of the update frequency and the main fluctuation frequency band; realizing the resonance risk identification and active avoidance of cross-domain data fusion of power and communication, and significantly improving the transient stability of the microgrid and the utilization rate of network resources.

Description

Technical Field

[0001] The present invention relates to the technical field of cross - domain collaborative avoidance, and more specifically, to a method for fault identification and network efficiency improvement for an intelligent microgrid. Background Art

[0002] With the expansion of the scale of intelligent microgrids, software - defined network (SDN) technology has been widely introduced to achieve dynamic scheduling and centralized control of communication resources. In the prior art, SDN controllers usually adjust flow - table rules according to network traffic status or device load changes, using fixed - period or simple adaptive algorithms to optimize communication bandwidth allocation and transmission delay. For example, by real - time monitoring the packet loss rate or link utilization, the flow - table update period is dynamically shortened or extended to improve network resource utilization. Such methods have achieved certain effects in general industrial networks, and their core logic is to focus on the state feedback of the communication network itself.

[0003] However, in the intelligent microgrid scenario, there will be a cross - domain coupling effect between the SDN flow - table update strategy and the power fluctuation of the power system: when the power fluctuation frequency of the microgrid (such as the second - level fluctuation caused by the randomness of the output of wind - solar - storage) is close to or coincides with the flow - table update period, the two form a resonance band, resulting in the periodic preemption of the communication channel bandwidth, leading to group - delay jitter and timing misalignment of key control instructions (such as energy storage charge - discharge instructions, fault isolation signals). This hidden resonance effect not only exacerbates network congestion but also may cause asynchronous execution of multi - node control instructions, seriously threatening the transient stability of the microgrid. Summary of the Invention

[0004] In order to overcome the above - mentioned defects of the prior art, an embodiment of the present invention provides a method for fault identification and network efficiency improvement for an intelligent microgrid to solve the problems raised in the above - mentioned background art.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for fault identification and network efficiency improvement for an intelligent microgrid, comprising the following steps:

[0007] S1. Real - time collect the power fluctuation data of the microgrid and the flow - table update parameters of the software - defined network, and perform timestamp calibration;

[0008] S2. Perform short - time Fourier transform on the calibrated power fluctuation data to extract the power fluctuation frequency - domain features, and calculate the time - domain correlation coefficient based on the period distribution of the flow - table update parameters;

[0009] S3. Input the power fluctuation frequency - domain features and the time - domain correlation coefficient into a cross - domain coupling model, and generate a dynamic resonance risk index through the product operation of frequency - domain amplitude integration and time - domain sliding - window convolution;

[0010] S4. When the dynamic resonance risk index exceeds the preset threshold, predict the future main fluctuation frequency band based on the phase change of the power fluctuation frequency domain characteristics, and generate a constraint condition by superimposing it with the historical avoidance frequency band;

[0011] S5. Based on the constraint condition and the real-time network bandwidth occupancy rate, use a sliding window to statistically analyze the effectiveness of the historical avoidance frequency band, and generate a frequency avoidance weight by combining the frequency band priority ranking;

[0012] S6. Asymmetrically adjust the flow table update period according to the frequency avoidance weight, so that the frequency domain distribution of the update frequency has no overlapping interval with the main fluctuation frequency band.

[0013] In a preferred embodiment, the power fluctuation data of the microgrid and the flow table update parameters of the software-defined network are collected in real time and timestamp calibration is performed, including:

[0014] Real-time collect the voltage fluctuation data at the output end of the inverter in the microgrid and the state of charge change data of the energy storage system as power fluctuation data, and collect the update time interval of each node flow table entry recorded in the software-defined network controller as the flow table update parameter;

[0015] Receive the timestamps of the power fluctuation data from the inverter and the energy storage system through the microgrid communication gateway, and synchronize and calibrate with the system clock of the software-defined network controller;

[0016] Store the calibrated power fluctuation data and flow table update parameters in the cache queue according to a unified time reference.

[0017] In a preferred embodiment, perform a short-time Fourier transform on the calibrated power fluctuation data to extract the power fluctuation frequency domain characteristics, and calculate the time domain correlation coefficient based on the period distribution of the flow table update parameters, including:

[0018] Perform a short-time Fourier transform on the calibrated power fluctuation data using a predefined window function to extract the power fluctuation frequency domain characteristics, and the power fluctuation frequency domain characteristics include the amplitude spectral density within the selected frequency band range;

[0019] Calculate the time domain correlation coefficient between the flow table update period and the power fluctuation time domain sequence based on the period distribution of the flow table update parameters;

[0020] Align the power fluctuation frequency domain characteristics and the time domain correlation coefficient according to the timestamp to generate a joint feature dataset.

[0021] In a preferred embodiment, integrate the amplitude spectral density within the selected frequency band, and the formula is: ; where represents the integration result of the selected frequency band amplitude spectral density in the power fluctuation frequency domain characteristics, represents the complex amplitude corresponding to the th frequency domain index after short-time Fourier transform, represents the minimum frequency domain index corresponding to the selected frequency band, represents the maximum frequency domain index corresponding to the selected frequency band, represents the frequency resolution, represents the discrete frequency domain index after short-time Fourier transform.

[0022] In a preferred embodiment, the power fluctuation frequency domain feature and the time domain correlation coefficient are input into the cross-domain coupling model, and a dynamic resonance risk index is generated through the product operation of frequency domain amplitude integration and time domain sliding window convolution, including:

[0023] Normalize the integration result of the amplitude spectral density of each selected frequency band in the power fluctuation frequency domain feature to obtain the normalized frequency domain amplitude weight;

[0024] Perform a sliding window convolution operation on the time domain correlation coefficient sequence, where the window width is consistent with the statistical interval of the flow table update period, and output the time domain dynamic correlation strength;

[0025] Align the normalized frequency domain amplitude weight and the time domain dynamic correlation strength according to the time stamp and multiply them point by point to generate the dynamic resonance risk index;

[0026] Among them, the convolution kernel coefficient of the sliding window convolution operation is dynamically adjusted according to the historical distribution of the dynamic resonance risk index, and the convolution kernel length is positively correlated with the mean value of the flow table update period.

[0027] In a preferred embodiment, when the dynamic resonance risk index exceeds the preset threshold, predict the future main fluctuation frequency band based on the phase change of the power fluctuation frequency domain feature, and superimpose it with the historical avoidance frequency band to generate constraint conditions, including:

[0028] When the dynamic resonance risk index exceeds the preset threshold, extract the target frequency band with the fastest phase change rate in the power fluctuation frequency domain feature, and calculate the frequency offset of the target frequency band within the future time window through the second-order difference of the phase change;

[0029] Calculate the center frequency and bandwidth of the future main fluctuation frequency band according to the frequency offset. The center frequency is the algebraic sum of the current target frequency band center frequency and the frequency offset, and the bandwidth is a linear combination of the current target frequency band bandwidth and the absolute value of the frequency offset, where the linear combination coefficient is dynamically adjusted according to the effectiveness of the historical avoidance frequency band;

[0030] Perform frequency domain superposition of the future fluctuation main frequency band and the pre-stored historical avoidance frequency band. If there is an overlapping area between the two, take the upper and lower limits of the overlapping area as the frequency band boundaries of the constraint conditions. If there is no overlap, merge the future fluctuation main frequency band and the historical avoidance frequency band into a discrete constraint interval;

[0031] Dynamically correct the constraint conditions based on the current network load status. If the real-time bandwidth occupancy rate exceeds the load threshold, compress the bandwidth of the constraint frequency band proportionally to the bandwidth occupancy rate.

[0032] In a preferred embodiment, based on the constraint conditions and the real-time network bandwidth occupancy rate, use a sliding window to statistically analyze the effectiveness of the historical avoidance frequency band, and generate a frequency avoidance weight by combining the frequency band priority ranking, including:

[0033] Extract the avoidance success rate and average avoidance duration of each frequency band within a predefined time window from the pre-stored historical avoidance frequency band as effectiveness indicators;

[0034] According to the real-time network bandwidth occupancy rate and the effectiveness indicators, perform weighted calculation on each frequency band through the dynamic allocation of the bandwidth occupancy rate weight coefficient and the average avoidance duration weight coefficient to obtain a priority score, where the allocation ratio of the bandwidth occupancy rate weight coefficient and the duration weight coefficient changes with the current network load status;

[0035] Arrange the priority scores of each frequency band in descending order, and select the top preset number of high-frequency bands as candidate avoidance frequency bands;

[0036] Normalize the priority scores of the candidate avoidance frequency bands to generate a frequency avoidance weight.

[0037] In a preferred embodiment, perform an asymmetric adjustment on the flow table update period according to the frequency avoidance weight, so that the frequency domain distribution of the update frequency has no overlapping interval with the fluctuation main frequency band, including:

[0038] Determine the benchmark adjustment amount of the flow table update period based on the frequency avoidance weight, and the benchmark adjustment amount is non-linearly negatively correlated with the frequency avoidance weight;

[0039] Dynamically correct the benchmark adjustment amount according to the real-time network bandwidth occupancy rate. When the bandwidth occupancy rate is higher than the preset load threshold, reduce the adjustment amount additionally according to the occupancy rate overrun ratio;

[0040] Trigger the software-defined network controller to perform an asymmetric adjustment on the flow table update period of the target node. The adjustment direction is: extend the update period of the candidate avoidance frequency band node with a high frequency avoidance weight, and shorten the update period of the frequency band node with a low frequency avoidance weight;

[0041] Verify whether the updated frequency of the flow table after adjustment overlaps with the main frequency band of fluctuations through frequency domain distribution histogram matching. If there is residual overlap, the update period offset is adjusted quadratically based on the bandwidth of the overlapping region.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] 1. The present invention constructs a cross-domain coupling model by collecting power fluctuations and flow table update parameters in real time, fuses the power frequency domain characteristics and flow table time domain parameters to calculate the dynamic resonance risk index, breaks through the limitations of traditional single-domain optimization, and realizes the accurate identification of power-communication coupling risks. Further, based on the phase change, the future main frequency band of fluctuations is predicted, and dynamic constraint conditions are generated in combination with historical avoidance frequency bands. The resonance frequency band is actively avoided through frequency domain weight and asymmetric period adjustment, eliminating the timing misalignment and network congestion caused by cross-domain coupling from the root cause.

[0044] 2. The present invention dynamically generates frequency avoidance weights by sliding window statistics of the effectiveness of historical avoidance frequency bands and combining with the real-time network load status, realizing the multi-objective balance of bandwidth occupancy rate, avoidance success rate and timing accuracy. Further, through the asymmetric flow table period adjustment mechanism, the update period is differentially extended or shortened for different weight frequency bands, making the communication resource scheduling closely match the power fluctuation characteristics, maximizing the network utilization while avoiding channel preemption. In addition, a frequency domain distribution verification and quadratic adjustment mechanism is introduced to ensure the global optimality of the avoidance strategy, significantly improving the reliability of microgrid operation and the execution synchronization rate of control commands. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flowchart of a method for fault identification and network efficiency improvement in an intelligent microgrid according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0047] Embodiment: Figure 1 A method for fault identification and network efficiency improvement in an intelligent microgrid according to the present invention is given, which includes the following steps:

[0048] S1. Collect the power fluctuation data of the microgrid and the flow table update parameters of the software-defined network in real time, and perform timestamp calibration;

[0049] S2. Perform short-time Fourier transform on the calibrated power fluctuation data to extract the power fluctuation frequency domain features, and calculate the time domain correlation coefficient based on the periodic distribution of the flow table update parameters;

[0050] S3. Input the power fluctuation frequency domain features and the time domain correlation coefficient into the cross-domain coupling model, and generate a dynamic resonance risk index through the product operation of the frequency domain amplitude integration and the time domain sliding window convolution;

[0051] S4. When the dynamic resonance risk index exceeds the preset threshold, predict the future main fluctuation frequency band based on the phase change of the power fluctuation frequency domain features, and superimpose it with the historical avoidance frequency band to generate a constraint condition;

[0052] S5. Based on the constraint condition and the real-time network bandwidth occupancy rate, use a sliding window to statistically analyze the effectiveness of the historical avoidance frequency band, and generate a frequency avoidance weight by combining the frequency band priority ranking;

[0053] S6. Asymmetrically adjust the flow table update period according to the frequency avoidance weight, so that the frequency domain distribution of the update frequency has no overlapping interval with the main fluctuation frequency band.

[0054] S1. Real-time collect the power fluctuation data of the microgrid and the flow table update parameters of the software-defined network, and perform timestamp calibration, including:

[0055] Real-time collect the voltage fluctuation data at the output end of the inverter in the microgrid. For example, the voltage fluctuation data is obtained through a three-phase voltage sensor connected to the AC side of the inverter at a sampling frequency of 100 times per second; at the same time, collect the change data of the state of charge of the energy storage system. The state of charge data is obtained through the built-in battery management system of the energy storage system at a sampling frequency of 10 times per second.

[0056] The flow table update parameters of the software-defined network controller are obtained by reading the time intervals of the flow table entries recorded in the controller. The time interval data includes, but is not limited to, the time of adding, deleting, and modifying the flow table entries, and the time interval accuracy is at the millisecond level.

[0057] Perform timestamp calibration on the power fluctuation data and the flow table update parameters. The specific method is as follows: Receive the timestamp of the power fluctuation data from the three-phase voltage sensor and the battery management system through the microgrid communication gateway. The timestamp format is Unix millisecond timestamp; at the same time, obtain the system clock of the software-defined network controller. The system clock is synchronized to the Beidou satellite time through the network time protocol; Compare the timestamp of the power fluctuation data with the system clock of the software-defined network controller. If the time deviation exceeds 1 millisecond, discard the data and trigger re-collection. If the time deviation is within 1 millisecond, correct the timestamp of the power fluctuation data to the system clock time of the software-defined network controller.

[0058] The calibrated power fluctuation data and the flow table update parameters are stored in the cache queue according to a unified time reference. The cache queue adopts a first-in-first-out storage structure.

[0059] S2. Perform a short-time Fourier transform on the calibrated power fluctuation data to extract the power fluctuation frequency-domain characteristics, and calculate the time-domain correlation coefficient based on the periodic distribution of the flow table update parameters, including:

[0060] When performing a short-time Fourier transform on the calibrated power fluctuation data, a predefined window function is used to window the power fluctuation time-domain sequence. The predefined window function includes but is not limited to the Hanning window or the rectangular window, and the window length is dynamically adjusted according to the power fluctuation characteristics. The extraction range of the power fluctuation frequency-domain characteristics is the selected frequency band, and the selected frequency band is determined according to the typical fluctuation frequencies of distributed power sources in the microgrid. For example, for photovoltaic output fluctuations, the selected frequency band is 0.5 Hz to 5 Hz; for wind power generation fluctuations, the selected frequency band is 0.2 Hz to 2 Hz; for energy storage charge and discharge fluctuations, the selected frequency band is 0.1 Hz to 1 Hz. The calculation of the frequency-domain characteristics includes integrating the amplitude spectral density within the selected frequency band, and the integration formula is: ; where represents the integration result of the amplitude spectral density of the selected frequency band in the power fluctuation frequency-domain characteristics; represents the complex amplitude corresponding to the th frequency-domain index after the short-time Fourier transform, which is calculated by the discrete Fourier transform; represents the minimum frequency-domain index corresponding to the selected frequency band; represents the maximum frequency-domain index corresponding to the selected frequency band; represents the frequency resolution, which is determined by the window length and the sampling interval; represents the discrete frequency-domain index after the short-time Fourier transform, and the value range is an integer.

[0061] When calculating the time-domain correlation coefficient based on the periodic distribution of the flow table update parameters, first, the time series of the flow table update period is statistically analyzed, and the statistical interval of the time series is consistent with the sampling interval of the power fluctuation data.

[0062] The time-domain correlation coefficient is obtained by calculating the ratio of the covariance of the flow table update period sequence and the power fluctuation time-domain sequence to the standard deviations of both, and the calculation formula is: ; where represents the time-domain correlation coefficient between the flow table update period and the power fluctuation time-domain sequence; represents the flow table update period sequence, which is the set of the update time intervals of each node's flow table entries, in seconds; represents the power fluctuation time-domain sequence, which is the set of the time-domain sampling values of the power fluctuation data, in kilowatts; represents the sequence and Covariance; Indicates the standard deviation of the flow table update period sequence; Indicates the standard deviation of the power fluctuation time domain sequence.

[0063] When generating a joint feature dataset by aligning the power fluctuation frequency domain features and the time domain correlation coefficients according to the timestamp, the alignment rule is as follows: If there are multiple power fluctuation frequency domain feature values at the same timestamp (for example, data from multiple inverters), the average value is taken as the feature value at that timestamp; If the timestamps of the flow table update period sequence do not exactly match the timestamps of the power fluctuation data, linear interpolation is used to complete the missing values. The storage format of the joint feature dataset is a two-dimensional matrix, where the rows of the matrix correspond to timestamps, and the columns correspond to the integrated results of the amplitude spectral density of different frequency bands and the time domain correlation coefficients respectively.

[0064] S3. Input the power fluctuation frequency domain features and the time domain correlation coefficients into the cross-domain coupling model, and generate a dynamic resonance risk index through the product operation of the frequency domain amplitude integration and the time domain sliding window convolution, including:

[0065] When normalizing the integrated results of the amplitude spectral density of each selected frequency band in the power fluctuation frequency domain features, the normalization method is as follows: For the integrated results of each frequency band at each timestamp, calculate the maximum and minimum values in the historical data of that frequency band respectively, and map the current integrated value to the interval from 0 to 1 according to the formula "(current value - minimum value) / (maximum value - minimum value)" to obtain the normalized frequency domain amplitude weight.

[0066] For example, if the historical integrated value range of a certain frequency band is from 100 to 500 and the current integrated value is 300, the normalization result is (300 - 100) / (500 - 100) = 0.5.

[0067] For new frequency bands with insufficient historical data, interpolation substitution is performed using the normalization parameters of adjacent frequency bands, and the interpolation methods include but are not limited to linear interpolation or nearest neighbor interpolation.

[0068] When performing a sliding window convolution operation on the time domain correlation coefficient sequence, the window width is set to an integer multiple of the statistical interval of the flow table update period. For example, if the statistical interval of the flow table update period is 1 second, the window width can be set to 5 seconds or 10 seconds.

[0069] The convolution kernel coefficients are dynamically adjusted according to the distribution of the historical resonance risk index. The specific method is as follows: Statistically analyze the distribution of the time domain correlation coefficients corresponding to the moments when the dynamic resonance risk index in the historical data exceeds the preset threshold, and extract its mean and variance as the adjustment basis for the convolution kernel coefficients.

[0070] For example, if the mean value of the time-domain correlation coefficient corresponding to the historical high-risk period is 0.8 and the variance is 0.1, the convolution kernel coefficients are generated according to the Gaussian distribution, the central coefficient is 0.8, and the edge coefficients decay according to the variance of 0.1. The length of the convolution kernel is positively correlated with the mean value of the flow table update period. For example, when the mean value of the flow table update period is 2 seconds, the length of the convolution kernel is set to 5 sampling points; when the mean value is 5 seconds, the length is set to 10 sampling points, and the positive correlation ratio coefficient is determined by fitting historical data.

[0071] When multiplying the normalized frequency-domain amplitude weight and the time-domain dynamic correlation strength point by point after aligning them according to the timestamp, the alignment rules include: if there is only a single piece of data in the frequency-domain weight or the time-domain strength at a certain timestamp, the data at that timestamp is discarded; if there are normalized frequency-domain amplitude weights for multiple frequency bands at the same timestamp, the sum of the weights of each frequency band is taken as the comprehensive frequency-domain weight at that timestamp.

[0072] The calculation method of point-by-point multiplication is: dynamic resonance risk index = normalized frequency-domain amplitude weight × time-domain dynamic correlation strength. For example, if the comprehensive frequency-domain weight at a certain timestamp is 0.6 and the time-domain dynamic correlation strength is 0.9, then the dynamic resonance risk index is 0.6 × 0.9 = 0.54. For data with timestamp deviations (such as the timestamp of the frequency-domain data is t1, the timestamp of the time-domain data is t2, and |t1 - t2| ≤ 10 milliseconds), time tolerance matching is allowed and the two are treated as the same timestamp.

[0073] After generating the dynamic resonance risk index, the specific implementation method of dynamically adjusting the convolution kernel coefficients according to the historical resonance risk index distribution includes: regularly (such as every hour) counting the frequency and duration of the dynamic resonance risk index exceeding the preset threshold. If the frequency exceeds 20% of the historical mean or the single duration exceeds the historical maximum value, the convolution kernel coefficient update is triggered. The update logic is: extract the statistical features (such as mean value, variance, extreme value) of the time-domain correlation coefficient sequence in the current period, regenerate the convolution kernel coefficients, and smoothly transition to the new coefficients through the moving average algorithm to avoid oscillations caused by mutations. For example, if the original convolution kernel coefficients are [0.5, 0.3, 0.2] and the new coefficients are [0.6, 0.25, 0.15], then they are gradually replaced at a rate of 10% per day during the transition period.

[0074] The implementation method of the positive correlation between the convolution kernel length and the mean value of the flow table update period further includes: determining the convolution kernel length using a piecewise function according to the dynamic change of the mean value of the flow table update period. For example, when the mean value of the flow table update period is less than 3 seconds, the convolution kernel length = mean value × 2.5; when the mean value is between 3 seconds and 6 seconds, the length = mean value × 2; when the mean value is greater than 6 seconds, the length = mean value × 1.5.

[0075] Among them, the proportionality coefficient is determined by regression analysis of historical data. For example, the least squares method is used to fit the relationship curve between the mean value and the optimal convolution kernel length. If the mean value of the flow table update period mutates (such as the mean value changes by more than 3 times the standard deviation of the historical fluctuation range), the adjustment of the convolution kernel length is temporarily frozen until the mean value stabilizes and then the dynamic adaptation is resumed.

[0076] S4. When the dynamic resonance risk index exceeds the preset threshold, predict the future main fluctuation frequency band based on the phase change of the power fluctuation frequency domain characteristics, and superimpose it with the historical avoidance frequency band to generate constraint conditions, including:

[0077] When the dynamic resonance risk index exceeds the preset threshold, first extract the target frequency band with the fastest phase change rate from the power fluctuation frequency domain characteristics. The calculation method of the phase change rate is as follows: perform a first-order difference on the phase sequence of the target frequency band to obtain the instantaneous phase change amount, and then perform a second-order difference operation on the result of the first-order difference. The calculation process of the second-order difference is: subtract the phase first-order difference value of the previous moment from the phase first-order difference value of the current moment to obtain the acceleration of the phase change.

[0078] The frequency offset is calculated by multiplying the acceleration of the phase change by the frequency domain resolution and dividing by twice the pi, where the frequency domain resolution is determined by the window length and sampling interval of the short-time Fourier transform.

[0079] When calculating the center frequency and bandwidth of the future main fluctuation frequency band according to the frequency offset, the calculation method of the center frequency is: directly add the center frequency of the current target frequency band and the frequency offset. The sign of the frequency offset is determined by the direction of the acceleration of the phase change. When the acceleration is positive, the frequency offset is positive, and vice versa. The calculation method of the bandwidth is: add the bandwidth of the current target frequency band and the absolute value of the frequency offset multiplied by the linear combination coefficient. The value range of the linear combination coefficient is from 0.1 to 0.5, and the specific value is dynamically adjusted according to the effectiveness of the historical avoidance frequency band.

[0080] The effectiveness of the historical avoidance frequency band is defined as: within a preset time window (such as 24 hours), the proportion of the number of times the frequency band is successfully avoided to the total number of avoidance attempts. For example, if a certain frequency band is attempted to be avoided 10 times and successfully avoided 8 times in the recent 24 hours, the effectiveness is 80%. At this time, the linear combination coefficient is taken as 0.2 (the coefficient is 0.2 when the effectiveness ≥ 80%, 0.3 when 60% ≤ effectiveness < 80%, and 0.5 when the effectiveness < 60%).

[0081] When performing frequency-domain superposition of the future main fluctuation frequency band and the pre-stored historical avoidance frequency band, the superposition rules are as follows: If there is an overlapping area between the future main fluctuation frequency band and any historical avoidance frequency band (that is, there is an intersection in their frequency-domain ranges), the frequency band boundaries of the constraint conditions are the minimum frequency lower limit and the maximum frequency upper limit of the overlapping area; if there is no overlap, the future main fluctuation frequency band and all historical avoidance frequency bands are combined into discrete constraint intervals.

[0082] For example, if the future main fluctuation frequency band is from 1.5 Hz to 3 Hz and the historical avoidance frequency band is from 2 Hz to 4 Hz, the overlapping area is from 2 Hz to 3 Hz, and the frequency band boundaries of the constraint conditions are 2 Hz (lower limit) and 3 Hz (upper limit); if the future main fluctuation frequency band is from 1 Hz to 2 Hz and the historical avoidance frequency band is from 3 Hz to 5 Hz, the constraint conditions are the discrete intervals [1 Hz, 2 Hz] and [3 Hz, 5 Hz].

[0083] When dynamically correcting the constraint conditions based on the current network load status, if the real-time bandwidth occupancy rate exceeds the load threshold (such as 80%), the bandwidth of the constraint frequency band is compressed proportionally according to the bandwidth occupancy rate. The compression logic is: the original bandwidth is multiplied by the compression factor, and the compression factor is equal to 1 minus (the real-time bandwidth occupancy rate minus the load threshold) divided by (100 minus the load threshold). For example, when the original bandwidth is 2 Hz, the real-time bandwidth occupancy rate is 90%, and the load threshold is 80%, the compression factor is 1 - (90 - 80) / (100 - 80) = 0.5, and the compressed bandwidth is 2 Hz × 0.5 = 1 Hz.

[0084] It should be noted that the preset threshold corresponding to the dynamic resonance risk index is jointly determined through statistical analysis of historical operation data and experimental calibration: an initial threshold range is generated by removing outliers based on the distribution characteristics of the index values in the historical data, and then the effectiveness of the threshold is verified by artificially injecting typical power disturbance scenarios; the threshold is dynamically adjusted according to the effectiveness of the historical avoidance frequency band during operation. When the effectiveness is high, the threshold is increased proportionally to reduce the false alarm rate; when the effectiveness is low, the threshold is decreased proportionally to enhance the sensitivity; at the same time, the threshold is regularly calibrated in combination with the microgrid operation cycle to ensure adaptation to the frequency band fluctuation characteristics of different seasons or load scenarios.

[0085] S5. Based on the constraint conditions and the real-time network bandwidth occupancy rate, use a sliding window to statistically analyze the effectiveness of the historical avoidance frequency band, and generate a frequency avoidance weight in combination with the frequency band priority ranking, including:

[0086] When extracting the avoidance success rate and average avoidance duration of each frequency band within a predefined time window from the pre-stored historical avoidance frequency bands as validity indicators, the predefined time window is set to the most recent 24 hours. The calculation method of the avoidance success rate is: the percentage of the number of times a certain frequency band is successfully avoided within the time window to the total number of times the frequency band is attempted to be avoided; the average avoidance duration is the average value of the durations of all successful avoidance events of the frequency band. For example, if a certain frequency band is attempted to be avoided 20 times within 24 hours and is successfully avoided 15 times, the avoidance success rate is 75%; the durations of the 15 successful avoidance events are 5 seconds, 8 seconds, 6 seconds, etc., and the average avoidance duration is (5 + 8 + 6 +...) / 15. If there are multiple time windows in the historical data (such as stored in hourly segments), the overall validity indicator is calculated by time weighting, and the data closer to the current time has a higher weight.

[0087] When calculating the priority score for each frequency band through the dynamic allocation of the bandwidth occupancy rate weight coefficient and the average avoidance duration weight coefficient based on the real-time network bandwidth occupancy rate and the validity indicator, the dynamic allocation rule is: if the real-time bandwidth occupancy rate is higher than the preset load threshold (e.g., 80%), the bandwidth occupancy rate weight coefficient is set to 0.7, and the average avoidance duration weight coefficient is set to 0.3; if it is lower than the load threshold, the bandwidth occupancy rate weight coefficient is set to 0.3, and the average avoidance duration weight coefficient is set to 0.7.

[0088] After the dimensionless processing of the avoidance success rate and the average avoidance duration, the calculation of the priority score is as follows: ; where represents the priority score, is the avoidance success rate, is the average avoidance duration, is the bandwidth occupancy rate weight coefficient, is the average avoidance duration weight coefficient.

[0089] For example, if the avoidance success rate of a certain frequency band is 80% and the average avoidance duration is 6 seconds, when the real-time bandwidth occupancy rate is 85% (higher than the threshold), , , then the priority score = 80×0.7 + 6×0.3 = 56 + 1.8 = 57.8.

[0090] Among them, the setting of the bandwidth occupancy rate weight coefficient and the average avoidance duration weight coefficient is based on the real-time network load status: when the real-time bandwidth occupancy rate exceeds the preset load threshold, the bandwidth occupancy rate weight coefficient is assigned as the main proportion, and the average avoidance duration weight coefficient is the secondary proportion to prioritize the efficient release of bandwidth resources; when the bandwidth occupancy rate is below the threshold, the two proportions are inversely assigned, the average avoidance duration weight coefficient is increased to the main proportion, and the bandwidth occupancy rate weight coefficient is decreased to the secondary proportion to optimize the timing accuracy of control commands. The sum of the two types of weight coefficients remains constant to ensure the coordinated calculation ratio of the priority score, and at the same time, it adapts to the core requirements of different load scenarios through dynamic allocation.

[0091] It should be noted that multiplying the avoidance success rate by the bandwidth occupancy rate weight coefficient conforms to the logic of microgrid dynamic scheduling: when the network bandwidth occupancy rate is high (such as >80%), the calculation weight of the avoidance success rate is increased, and the frequency band with good historical avoidance effect is preferentially selected to quickly release bandwidth resources; when the bandwidth occupancy rate is low, its weight is reduced to take into account other factors (such as avoidance duration). This design dynamically adjusts the influence of historical data through the real-time network state, realizes the linkage adaptation between network load and avoidance strategy, solves the problems of over-avoidance or insufficient avoidance caused by fixed weights in traditional methods, and ensures the efficiency and stability of resource scheduling.

[0092] When arranging the priority scores of each frequency band in descending order and selecting the top preset number of high-frequency bands as candidate avoidance frequency bands, the preset number is dynamically adjusted according to the total number of historical avoidance frequency bands. The adjustment rule is: if the total number of historical avoidance frequency bands is less than or equal to 10, the preset number = total number × 50%; if it is greater than 10, the preset number = 5 + (total number - 10) × 20%. For example, if the total number of historical avoidance frequency bands is 8, the preset number = 8 × 50% = 4; if the total number is 15, the preset number = 5 + (15 - 10) × 20% = 6.

[0093] When normalizing the priority scores of candidate avoidance frequency bands to generate frequency avoidance weights, the normalization method is: divide the priority score of each candidate frequency band by the sum of the priority scores of all candidate frequency bands, so that the sum of all weights is 1. For example, if the priority scores of three candidate frequency bands are 60, 40, and 20 respectively, the normalized weights are 60 / (60 + 40 + 20) = 0.5, 40 / 120 ≈ 0.33, and 20 / 120 ≈ 0.17 respectively.

[0094] S6. Asymmetrically adjust the flow table update period according to the frequency avoidance weight to make the frequency domain distribution of the update frequency have no overlapping interval with the main frequency band of fluctuations, including:

[0095] When determining the benchmark adjustment amount of the flow table update period based on the frequency avoidance weight, the non-linear negative correlation between the benchmark adjustment amount and the frequency avoidance weight is achieved through an exponential function. The specific rule is as follows: the higher the frequency avoidance weight, the greater the reduction amplitude of the benchmark adjustment amount, but the reduction rate gradually slows down as the weight increases. For example, when the frequency avoidance weight is 0.8, the benchmark adjustment amount is reduced to 30% of the original period; when the weight is 0.5, it is reduced to 50%; when the weight is 0.2, it is reduced to 80%. The parameters of the non-linear relationship are determined by fitting historical data to ensure that the avoidance priority of high-weight frequency bands is significantly higher than that of low-weight frequency bands.

[0096] When dynamically correcting the benchmark adjustment amount according to the real-time network bandwidth occupancy rate, if the bandwidth occupancy rate is higher than the preset load threshold (e.g., 80%), the adjustment amount is additionally reduced according to the over-limit ratio of the occupancy rate. The calculation method of the over-limit ratio is: (real-time bandwidth occupancy rate - load threshold) / (100 - load threshold). For example, the preset load threshold is 80% and the real-time bandwidth occupancy rate is 90%, then the over-limit ratio is (90 - 80) / (100 - 80) = 0.5, and the additional reduction amount = benchmark adjustment amount × 0.5. If the bandwidth occupancy rate is lower than the threshold, the benchmark adjustment amount remains unchanged.

[0097] When triggering the software-defined network controller to perform asymmetric adjustment on the flow table update period of the target node, the specific rule of the adjustment direction is as follows: for the network nodes corresponding to the candidate avoidance frequency bands with high frequency avoidance weights, their flow table update periods are extended according to the adjustment amount; for the nodes corresponding to the frequency bands with low weights, the periods are shortened according to the adjustment amount. For example, a certain node has a frequency avoidance weight of 0.8 and a benchmark adjustment amount of a 30% reduction, and the over-limit ratio of the bandwidth occupancy rate is 0.5, then the final adjustment amount = 30% × (1 + 0.5) = 45%, and the update period is extended from the original 1 second to 1 second / (1% - 45%) = 1.82 seconds; another node has a weight of 0.2 and an adjustment amount of a 20% reduction, without additional reduction, then the period is shortened from 1 second to 1 second × (1% - 20%) = 0.8 seconds.

[0098] When verifying whether the adjusted flow table update frequency has no overlapping interval with the main fluctuation frequency band through the frequency domain distribution histogram matching, the generation method of the frequency domain distribution histogram is as follows: count the flow table update frequencies of all nodes after adjustment, divide the frequency bands according to the preset resolution (e.g., 0.1 Hz) and calculate the occurrence frequencies of each frequency band; compare the histogram with the range of the main fluctuation frequency band. If there is a frequency band overlap, it is determined as a residual overlap. For example, the main fluctuation frequency band is from 1.5 Hz to 2.5 Hz, and the adjusted flow table update frequency is distributed between 2 Hz and 3 Hz, then the overlapping area is from 2 Hz to 2.5 Hz.

[0099] If there is residual overlap, the update cycle offset is adjusted based on the bandwidth of the overlapping area for the second time. The adjustment rule is as follows: According to the proportion of the bandwidth of the overlapping area in the total bandwidth of the main fluctuating frequency band, the update cycle is further reduced or extended. For example, if the bandwidth of the overlapping area is 0.5 Hz and the total bandwidth of the main fluctuating frequency band is 1 Hz, then the adjustment amount = the original adjustment amount × (1 + 0.5 / 1) = 1.5 times the original adjustment amount, and the update cycle is additionally adjusted by 50%.

[0100] The above formulas are all calculated by taking the numerical value without dimension. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.

[0101] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that includes one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0102] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices, and modules described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0103] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the devices or modules can be in electrical, mechanical, or other forms.

[0104] The modules described as separate components may or may not be physically separated. The components displayed as modules may or may not be physical modules. They can be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0105] In addition, in each embodiment of the present application, the functional modules can be integrated in a processing module, or each module can exist physically alone, or two or more modules can be integrated in one module.

[0106] If the above functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0107] As described above, this is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0108] Finally, the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for fault identification and network performance improvement for a smart microgrid, characterized in that: The steps include: S1, real-time collection of microgrid power fluctuation data and software-defined network flow table update parameters, and timestamp calibration; S2. Perform short-time Fourier transform on the calibrated power fluctuation data to extract the power fluctuation frequency domain characteristics, and calculate the time domain correlation coefficient based on the periodic distribution of the flow table update parameters; The time domain correlation coefficient is obtained by calculating the ratio of the covariance of the flow table update cycle sequence and the power fluctuation time domain sequence to the standard deviation of the two. The calculation formula is: ;in, Represents the time domain correlation coefficient between the flow table update period and the power fluctuation time domain series; Represents the flow table update cycle sequence, which represents the set of update time intervals of flow table entries of each node; represents a power fluctuation time domain sequence, and represents a set of time domain sampling values ​​of power fluctuation data; Representation sequence and The covariance of Indicates the standard deviation of the flow table update cycle sequence; Represents the standard deviation of the power fluctuation time domain series; S3, inputting the power fluctuation frequency domain characteristics and time domain correlation coefficient into the cross-domain coupling model, and generating a dynamic resonance risk index by multiplying the frequency domain amplitude integral and the time domain sliding window convolution; S4. When the dynamic resonance risk index exceeds the preset threshold, the future main frequency band of fluctuation is predicted based on the phase change of the power fluctuation frequency domain characteristics, and the constraint condition is generated by superimposing it with the historical avoidance frequency band; S5. Based on the constraints and the real-time network bandwidth occupancy rate, a sliding window is used to count the effectiveness of the historical avoidance frequency bands, and the frequency avoidance weights are generated in combination with the frequency band priority sorting; S6. Asymmetrically adjust the flow table update period according to the frequency avoidance weight so that the frequency domain distribution of the update frequency has no overlapping interval with the main frequency band of the fluctuation.

2. A method for fault identification and network performance improvement for a smart microgrid according to claim 1, characterized in that: Real-time collection of microgrid power fluctuation data and software-defined network flow table update parameters, and timestamp calibration, including: The voltage fluctuation data at the inverter output end in the microgrid and the charge state change data of the energy storage system are collected in real time as power fluctuation data, and the update time interval of the flow table items of each node recorded in the software-defined network controller is collected as the flow table update parameter; Receive the timestamp of power fluctuation data from the inverter and energy storage system through the microgrid communication gateway, and synchronize and calibrate it with the system clock of the software-defined network controller; The calibrated power fluctuation data and flow table update parameters are stored in the cache queue according to a unified time base.

3. The method for fault identification and network performance improvement for a smart microgrid according to claim 1, characterized in that: Perform short-time Fourier transform on the calibrated power fluctuation data to extract the power fluctuation frequency domain features, and calculate the time domain correlation coefficient based on the periodic distribution of the flow table update parameters, including: The calibrated power fluctuation data is subjected to short-time Fourier transform using a predefined window function to extract the power fluctuation frequency domain features, where the power fluctuation frequency domain features include the amplitude spectral density within the selected frequency band; Based on the periodic distribution of flow table update parameters, the time domain correlation coefficient between the flow table update period and the power fluctuation time domain sequence is calculated; The power fluctuation frequency domain features and time domain correlation coefficients are aligned by timestamps to generate a joint feature dataset.

4. A method for fault identification and network performance improvement for a smart microgrid according to claim 3, characterized in that: The amplitude spectral density within the selected frequency band is integrated, and the formula is: ;in, It represents the integral result of the amplitude spectrum density of the selected frequency band in the frequency domain characteristics of power fluctuation. It represents the short-time Fourier transform The complex amplitude corresponding to the frequency domain index, Indicates the minimum frequency domain index corresponding to the selected frequency band, Indicates the maximum frequency domain index corresponding to the selected frequency band, represents the frequency resolution, Represents the discrete frequency domain index after short-time Fourier transform.

5. The method for fault identification and network performance improvement for a smart microgrid according to claim 1, characterized in that: The power fluctuation frequency domain characteristics and time domain correlation coefficients are input into the cross-domain coupling model, and the dynamic resonance risk index is generated by the product operation of the frequency domain amplitude integral and the time domain sliding window convolution, including: Normalizing the integral results of the amplitude spectrum density of each selected frequency band in the power fluctuation frequency domain characteristics to obtain the normalized frequency domain amplitude weight; Perform sliding window convolution operation on the time domain correlation coefficient sequence, with the window width consistent with the statistical interval of the flow table update cycle, and output the time domain dynamic correlation strength; The normalized frequency domain amplitude weight and the time domain dynamic correlation strength are aligned with the timestamp and multiplied point by point to generate a dynamic resonance risk index; Among them, the convolution kernel coefficient of the sliding window convolution operation is dynamically adjusted according to the historical distribution of dynamic resonance risk indicators, and the convolution kernel length is positively correlated with the mean of the flow table update cycle.

6. A method for fault identification and network performance improvement for a smart microgrid according to claim 1, characterized in that: When the dynamic resonance risk index exceeds the preset threshold, the future main frequency band of fluctuation is predicted based on the phase change of the power fluctuation frequency domain characteristics, and the constraints are superimposed with the historical avoidance frequency band to generate the following conditions: When the dynamic resonance risk index exceeds the preset threshold, the target frequency band with the fastest phase change rate in the power fluctuation frequency domain characteristics is extracted, and the frequency offset of the target frequency band in the future time window is predicted by calculating the second-order difference of the phase change; The center frequency and bandwidth of the future fluctuation main frequency band are calculated based on the frequency offset. The center frequency is the algebraic sum of the center frequency of the current target frequency band and the frequency offset. The bandwidth is the linear combination of the bandwidth of the current target frequency band and the absolute value of the frequency offset. The linear combination coefficient is dynamically adjusted based on the effectiveness of the historical avoidance frequency band. The future fluctuation main frequency band and the pre-stored historical avoidance frequency band are superimposed in the frequency domain. If there is an overlapping area between the two, the upper and lower limits of the overlapping area are taken as the frequency band boundaries of the constraint conditions. If there is no overlap, the future fluctuation main frequency band and the historical avoidance frequency band are merged into a discrete constraint interval. The constraints are dynamically modified based on the current network load status. If the real-time bandwidth occupancy rate exceeds the load threshold, the bandwidth of the constrained frequency band is compressed year-on-year according to the bandwidth occupancy rate.

7. A method for fault identification and network performance improvement for a smart microgrid according to claim 1, characterized in that: Based on the constraints and real-time network bandwidth occupancy, a sliding window is used to count the effectiveness of historical avoidance frequency bands, and frequency avoidance weights are generated in combination with frequency band priority sorting, including: Extract the avoidance success rate and average avoidance duration of each frequency band within a predefined time window from the pre-stored historical avoidance frequency bands as effectiveness indicators; According to the real-time network bandwidth occupancy rate and effectiveness indicators, the priority score is obtained by weighted calculation of each frequency band through the dynamic allocation of bandwidth occupancy rate weight coefficient and average avoidance time weight coefficient. The allocation ratio of bandwidth occupancy rate weight coefficient and time weight coefficient changes with the current network load status. The priority scores of each frequency band are arranged in descending order, and a preset number of high frequency bands are selected as candidate avoidance frequency bands; The priority scores of the candidate avoidance frequency bands are normalized to generate frequency avoidance weights.

8. The method for fault identification and network performance improvement for a smart microgrid according to claim 1, characterized in that: The flow table update period is adjusted asymmetrically according to the frequency avoidance weight so that the frequency domain distribution of the update frequency has no overlap with the main frequency band of the fluctuation, including: The base adjustment amount of the flow table update period is determined based on the frequency avoidance weight, and the base adjustment amount is nonlinearly negatively correlated with the frequency avoidance weight; The baseline adjustment amount is dynamically modified according to the real-time network bandwidth utilization rate. When the bandwidth utilization rate is higher than the preset load threshold, the adjustment amount is additionally reduced according to the excess utilization rate ratio. The software-defined network controller is triggered to perform asymmetric adjustment on the flow table update period of the target node. The adjustment direction is: the update period of the node corresponding to the candidate avoidance frequency band with high frequency avoidance weight is extended, and the update period of the node corresponding to the frequency band with low frequency avoidance weight is shortened; The frequency domain distribution histogram matching is used to verify whether the adjusted flow table update frequency has no overlapping interval with the main frequency band of the fluctuation. If there is residual overlap, the update cycle offset is adjusted secondary based on the bandwidth of the overlapping area.

Images