An AI-based Internet of Things multi-source data power quality energy-saving operation monitoring method and device

Abstract

The present disclosure relates to a method and device for monitoring the energy-saving operation of power quality based on multi-source data of AI Internet of Things. The method includes: acquiring the transient electromagnetic signal of a permanent magnet operated circuit breaker and extracting the timing characteristic parameters of the transient electromagnetic signal; determining whether there is a harmonic problem caused by an inverter and whether there is a voltage sudden rise or sudden drop, and determining whether the timing characteristic parameters are related to power quality disturbances; obtaining the voltage mutation amplitude and the voltage sudden rise rate to obtain the voltage fluctuation degree, and outputting the discharge strategy of the energy storage system through a pre-established discharge optimization model; respectively calculating the voltage distortion rate and the three-phase voltage unbalance degree, and selecting the charging strategy of the energy storage system through a pre-established charging optimization model; predicting the sudden rise rate and sudden drop rate of the sample, obtaining a prediction result, and forming an energy-saving optimization scheme for the energy storage charge and discharge strategy according to the prediction result; The present invention automatically adjusts the charge and discharge power of the energy storage battery to form an energy-saving optimization scheme, effectively improving the stability of the power grid.

Description

Technical Field

[0001] The present disclosure relates to, and specifically to, a method and device for monitoring the energy-saving operation of power quality based on multi-source data of AIoT (Artificial Intelligence of Things). Background Art

[0002] In a smart city power plant, the permanent magnet actuator circuit breaker is a key device, and the timing characteristics of its transient electromagnetic signals directly reflect the changes in the grid operation state. When a large number of new energy sources are connected to the grid, due to the intermittency and volatility of new energy generation, it is easy to cause power quality disturbances such as sudden voltage rises and drops. These disturbances not only affect the stable operation of the grid but also cause potential damage to power equipment. Therefore, studying the correlation between the timing characteristics of the transient electromagnetic signals of the permanent magnet actuator circuit breaker and power quality disturbances is of great significance for improving the stability and security of the grid. In actual operation, when the voltage fluctuation reaches a specific type and degree, the AIoT monitoring system needs to quickly identify and analyze the characteristics of the transient electromagnetic signals. Based on these characteristics, the AIoT monitoring system needs to optimize the charge and discharge strategies of the energy storage system on the grid side to actively respond to power quality disturbances. However, there are technical contradictions in this process: on the one hand, the rapid response of the energy storage system requires high-precision identification of transient electromagnetic signals, but the signals themselves have complexity and uncertainty, increasing the difficulty of identification; on the other hand, the charge and discharge strategies of the energy storage system need to be highly matched with the real-time operation state of the grid, but the changes in the grid state are random and sudden, making it difficult to accurately predict. In addition, the impact of this active power quality optimization strategy on line losses, the action frequency of reactive power compensation equipment, and the overall energy-saving effect also needs to be analyzed in depth. Since the charge and discharge behavior of the energy storage system will change the power distribution of the grid, it may lead to an increase or decrease in line losses and also affect the action frequency of reactive power compensation equipment. How to find a balance among these mutually influencing factors is an important technical problem faced by smart city power plants when dealing with the large-scale connection of new energy sources to the grid. Summary of the Invention

[0003] In order to solve the problems existing in the above-mentioned prior art, the purpose of the present disclosure is to provide a method and device for monitoring the energy-saving operation of power quality based on multi-source data of AIoT.

[0004] A method for monitoring the energy-saving operation of power quality based on multi-source data of AIoT according to the present disclosure includes the following steps:

[0005] S1. Obtain the transient electromagnetic signals of the permanent magnet actuator circuit breaker and extract the timing characteristic parameters of the transient electromagnetic signals;

[0006] S2. Determine whether there is a harmonic problem caused by an inverter and whether there is a sudden voltage rise or drop, and determine whether the timing characteristic parameters are correlated with power quality disturbances;

[0007] S3. Obtain the voltage mutation amplitude and the voltage rise rate, obtain the voltage fluctuation degree according to the voltage mutation amplitude and the voltage rise rate, input the voltage fluctuation degree into the discharge optimization model, and output the discharge strategy of the energy storage system;

[0008] S4. Calculate the voltage distortion rate and the three-phase voltage unbalance degree, and select the charging strategy of the energy storage system through a pre-established charging optimization model;

[0009] S5. Evaluate the influence of the charging strategy and the discharge strategy on the harmonic current content of the transmission line and the energy loss corresponding to the change of the power factor, and determine the target energy-saving charging strategy and the target energy-saving discharge strategy;

[0010] S6. Real-time monitor the instantaneous power curve and the power spectral density corresponding to the transient electromagnetic signals of the target energy-saving charging strategy and the target energy-saving discharge strategy, and perform time series analysis to obtain the voltage value time series data; divide the time series data into samples of a set length, predict the rise rate and the fall rate of the samples, obtain the prediction results, and form an energy-saving optimization plan for the energy storage charging and discharging strategy according to the prediction results.

[0011] Preferably, the time series characteristic parameters include frequency components, amplitude changes, phase differences, and harmonic contents;

[0012] The step S1 includes:

[0013] Calculate the electromagnetic torque stability parameter according to the original waveform data of the electromagnetic signal collected by the circuit breaker sensor and the magnetic ring strength of the permanent magnetic material to obtain the first transient electromagnetic signal sequence;

[0014] Perform frequency domain decomposition on the first transient electromagnetic signal sequence through fast Fourier transform. If the spectral energy density is greater than the magnetic flux attenuation degree threshold, generate the second transient electromagnetic signal sequence;

[0015] Obtain the high-frequency coefficient and the low-frequency coefficient by performing wavelet decomposition on the second transient electromagnetic signal sequence, and extract the electromagnetic displacement change amount and the switch state persistence characteristic curve from the high-frequency coefficient and the low-frequency coefficient to obtain the third transient electromagnetic signal sequence;

[0016] Use the recursive least squares method to fit the third transient electromagnetic signal sequence to obtain the amplitude change characteristic curve, and correct the fundamental wave component and the harmonic component of the amplitude change characteristic curve through the phase compensation algorithm to obtain the frequency component data and the harmonic content data to construct the time series characteristic parameter matrix.

[0017] Preferably, the step S2 includes:

[0018] Obtain transient electromagnetic signals from a power grid sampling device, perform Fourier series decomposition on the transient electromagnetic signals, calculate the cumulative energy of frequency components within a preset frequency band, and obtain first spectral feature data by comparing the energy increment of the frequency band with a preset threshold;

[0019] Extract the amplitude of the transient electromagnetic signal according to the first spectral feature data, calculate the amplitude change rate using discrete Fourier transform. If the amplitude change rate is greater than a preset amplitude change threshold, generate first voltage step change feature data;

[0020] Perform spectral energy and transient response feature extraction on the first voltage step change feature data through wavelet packet transform to obtain second spectral feature data;

[0021] Analyze the second spectral feature data using correlation calculation, extract time series correlation features. If the matching degree of the time series correlation features exceeds a preset threshold, determine that the transient electromagnetic signal is associated with power quality disturbances caused by new energy grid connection.

[0022] Preferably, step S3 includes:

[0023] Obtain voltage mutation amplitude data and voltage step-up rate data from a power grid sampling device, locate mutation points of the voltage mutation amplitude data through wavelet edge detection to obtain voltage fluctuation degree data;

[0024] Perform data fitting on the voltage fluctuation degree data and the remaining capacity data of the energy storage device using the recursive least squares method to obtain first power response parameters;

[0025] Perform optimization calculation on the first power response parameters and the historical discharge data of the energy storage device through a pre-established discharge optimization model to obtain a discharge optimization curve and second power response parameters;

[0026] Calculate the discharge depth threshold of the energy storage device according to the second power response parameters, construct a response strategy matrix using the discharge depth threshold and the fluctuation response delay parameter to obtain the discharge strategy of the energy storage system; the discharge strategy includes determining the output power, discharge depth, and the speed of responding to voltage fluctuations of the energy storage system.

[0027] Preferably, step S3 further includes:

[0028] Obtain the current energy storage value, load value, and system operation parameters of the energy storage system, combine with the preset number of time periods and electricity price table to construct an objective function; set the target discharge amount and target energy storage value as constraint terms, use the linear programming algorithm to solve the objective function under the constraints to obtain a set of target discharge strategies; screen out the discharge strategies in the set of target strategies whose discharge amount exceeds the preset capacity threshold and adjust the discharge amount to obtain the target discharge strategy.

[0029] Preferably, step S4 includes:

[0030] Obtain three-phase voltage waveform data from the power grid monitoring device, and through Fourier transform analysis of the three-phase voltage waveform data, obtain first voltage distortion data;

[0031] Perform symmetrical component decomposition on the three-phase voltage waveform data, and use the least squares method to calculate the phase deviation value and voltage amplitude to obtain first unbalance data;

[0032] Perform compensation calculation based on the first voltage distortion data and the first unbalance data, determine the compensation voltage amplitude and phase through the symmetrical component method, and obtain first harmonic compensation data and first phase sequence compensation data;

[0033] Perform charging capacity optimization calculation on the first harmonic compensation data and the first phase sequence compensation data, and verify the constraint of the compensation parameters through a preset compensation model to screen out the charging strategy of the energy storage system.

[0034] Preferably, step S4 further includes:

[0035] Calculate harmonic content data from the harmonic content data in the transient electromagnetic signal, and calculate the voltage distortion rate based on the harmonic content data; by measuring the instantaneous values of the three-phase voltages, determine the difference between the first target phase voltage and the second target phase voltage in the three-phase voltages, as well as the average value of the three-phase voltages, and calculate the three-phase voltage unbalance.

[0036] Preferably, step S5 includes:

[0037] Obtain the harmonic current content and power factor reference data before the implementation of the charge and discharge strategy in the line monitoring device, and perform spectral analysis on the reference data through Fourier transform to obtain first evaluation data;

[0038] Collect the line operation data after the implementation of the charge and discharge strategy according to the first evaluation data, and calculate the change value of the harmonic current content through Fourier transform to obtain second evaluation data;

[0039] Calculate the change value of the power factor according to the second evaluation data, and obtain third evaluation data through reactive power compensation calculation;

[0040] Use a line loss calculator to comprehensively calculate the second evaluation data and the third evaluation data, and perform integral operation on the unit length energy loss value according to the line resistance parameter to obtain the total line energy loss data;

[0041] If the harmonic current content in the total line energy loss data is lower than the reference value and the power factor is higher than the reference value, determine the current charge-discharge strategy as the target energy-saving charge-discharge strategy.

[0042] Preferably, step S6 described above includes:

[0043] Decompose the electromagnetic signal through fast Fourier transform, and calculate the first power spectral density data according to the spectrum distribution;

[0044] Perform instantaneous power calculation on the first power spectral density data, and use a sliding window to segment the instantaneous power curve to obtain the first time series data;

[0045] Perform sample division according to the first time series data, extract voltage values from the divided sample segments to obtain the second time series data;

[0046] Perform long short-term memory network training on the second time series data, extract voltage change characteristics from historical data to obtain the first prediction parameter;

[0047] Calculate the voltage rise rate and fall rate using the first prediction parameter, and judge through a threshold comparator to obtain the second prediction parameter;

[0048] If the rise rate or fall rate exceeds the preset threshold, record the current voltage change data, generate a power adjustment amount according to the change amplitude, and obtain the energy storage optimization parameter.

[0049] The present disclosure also provides an AI Internet of Things multi-source data power quality energy-saving operation monitoring device, including:

[0050] A transient electromagnetic signal acquisition module, which is used to acquire the transient electromagnetic signal of the permanent magnet actuator circuit breaker;

[0051] A timing feature parameter extraction module, which is used to extract the timing feature parameters of the transient electromagnetic signal;

[0052] A power quality disturbance correlation module, which is used to judge whether there is a harmonic problem caused by an inverter and a voltage rise or fall occurs, and determine whether the timing feature parameter is correlated with the power quality disturbance;

[0053] A discharge strategy optimization module, which is used to obtain the voltage mutation amplitude and the voltage rise rate, obtain the voltage fluctuation degree according to the voltage mutation amplitude and the voltage rise rate, input the voltage fluctuation degree into the discharge optimization model, and output the discharge strategy of the energy storage system;

[0054] A charging strategy optimization module, which is used to calculate the voltage distortion rate and the three-phase voltage unbalance degree, and select the charging strategy of the energy storage system through a pre-established charging optimization model;

[0055] An energy-saving strategy evaluation module, which is used to evaluate the influence of the charging strategy and the discharging strategy on the harmonic current content of the transmission line and the energy loss corresponding to the change of the power factor, and determine the target energy-saving charging strategy and the target energy-saving discharging strategy;

[0056] An adjustment module, which is used to monitor in real time the instantaneous power curve and the power spectral density corresponding to the transient electromagnetic signals of the target energy-saving charging strategy and the target energy-saving discharging strategy, and perform time series analysis to obtain voltage value time series data; divide the time series data into samples of a set length, predict the sudden rise rate and the sudden drop rate of the samples, obtain the prediction results, and form an energy-saving optimization plan for the energy storage charging and discharging strategy according to the prediction results.

[0057] The advantages of a method and device for monitoring the energy-saving operation of power quality based on AI Internet of Things multi-source data according to the present disclosure are as follows:

[0058] By acquiring the transient electromagnetic signals of the permanent magnet actuator circuit breaker, extracting the time series characteristic parameters, and identifying the power quality disturbances caused by large-scale new energy grid connection. According to the voltage fluctuation degree, the present invention outputs the discharging strategy of the energy storage system, including the output power, the discharging depth and the response speed. At the same time, by analyzing the voltage distortion rate and the three-phase voltage unbalance degree, a suitable charging strategy is selected to achieve harmonic suppression, unbalance compensation and power factor correction. The present invention also evaluates the influence of the charging and discharging strategies on the energy loss of the transmission line, and monitors the instantaneous power curve and the power spectral density in real time to predict the voltage sudden change risk. When the power grid is detected to be unstable, the present invention automatically adjusts the charging and discharging power of the energy storage battery to form an energy-saving optimization plan, effectively improving the power grid stability and the energy utilization efficiency. Description of the Drawings

[0059] Figure 1 is a flowchart of a method and device for monitoring the energy-saving operation of power quality based on AI Internet of Things multi-source data according to the present disclosure. Detailed Embodiments

[0060] As Figure 1 shown, a method for monitoring the energy-saving operation of power quality based on AI Internet of Things multi-source data according to the present disclosure includes the following steps:

[0061] S1. Acquire the transient electromagnetic signals of the permanent magnet actuator circuit breaker, and extract the time series characteristic parameters of the transient electromagnetic signals;

[0062] S2. Determine whether there are harmonic problems caused by the inverter and voltage surges or sags occur, and determine whether the timing characteristic parameters are related to the power quality disturbance;

[0063] S3. Obtain the voltage mutation amplitude and the voltage rise rate, obtain the voltage fluctuation degree according to the voltage mutation amplitude and the voltage rise rate, input the voltage fluctuation degree into the discharge optimization model, and output the discharge strategy of the energy storage system;

[0064] S4. Calculate the voltage distortion rate and the three-phase voltage unbalance degree, and select the charging strategy of the energy storage system through a pre-established charging optimization model;

[0065] S5. Evaluate the influence of the charging strategy and the discharge strategy on the harmonic current content of the transmission line and the energy loss corresponding to the change of the power factor, and determine the target energy-saving charging strategy and the target energy-saving discharge strategy;

[0066] S6. Real-time monitor the instantaneous power curve and the power spectral density corresponding to the transient electromagnetic signals of the target energy-saving charging strategy and the target energy-saving discharge strategy, and perform time series analysis to obtain the voltage value time series data; divide the time series data into samples of a set length, predict the rise rate and the fall rate of the samples, obtain the prediction results, and form an energy-saving optimization plan for the energy storage charging and discharging strategy according to the prediction results.

[0067] Further, the timing characteristic parameters in step S1 may include frequency components, amplitude changes, phase differences, and harmonic contents;

[0068] More specifically, step S1 may specifically include:

[0069] Calculate the electromagnetic torque stability parameter according to the original waveform data of the electromagnetic signal collected by the circuit breaker sensor and the magnetic ring strength of the permanent magnet material to obtain the first transient electromagnetic signal sequence;

[0070] Perform frequency domain decomposition on the first transient electromagnetic signal sequence through fast Fourier transform. If the spectral energy density is greater than the magnetic flux attenuation degree threshold, generate the second transient electromagnetic signal sequence;

[0071] Perform wavelet decomposition on the second transient electromagnetic signal sequence to obtain high-frequency coefficients and low-frequency coefficients, and extract the electromagnetic displacement change amount and the switch state persistence characteristic curve from the high-frequency coefficients and the low-frequency coefficients to obtain the third transient electromagnetic signal sequence;

[0072] Use the recursive least squares method to fit the third transient electromagnetic signal sequence to obtain the amplitude change characteristic curve, and correct the fundamental wave component and the harmonic component of the amplitude change characteristic curve through the phase compensation algorithm to obtain the frequency component data and the harmonic content data to construct the timing characteristic parameter matrix.

[0073] More specifically, the original waveform data of the electromagnetic signal is obtained from the circuit breaker sensor at a sampling frequency of at least 800 times per second. The stability parameter of the electromagnetic torque is calculated according to the magnetic ring strength of the permanent magnet material and the voltage fluctuation amplitude to obtain the first transient electromagnetic signal sequence. For the first transient electromagnetic signal sequence, the signal is decomposed in the frequency domain by fast Fourier transform. The transient response duration of the circuit breaker is judged according to the spectral energy density and the magnitude of the current peak. If it is greater than the magnetic flux attenuation degree threshold of 0.3, the second transient electromagnetic signal sequence is generated. The second transient electromagnetic signal sequence is decomposed by five-layer wavelet decomposition to obtain high-frequency coefficients and low-frequency coefficients. The electromagnetic displacement change amount and the switching state persistence characteristic curve are extracted from the coefficients to obtain the third transient electromagnetic signal sequence. The permanent magnet force loop parameters are calculated according to the third transient electromagnetic signal sequence, and the characteristic curve is fitted by the recursive least squares method to obtain the amplitude change characteristic curve. On the basis of the amplitude change characteristic curve, the electromagnetic signal is expanded by Fourier series according to the proportion of harmonic components to obtain the fundamental wave component and harmonic components. The phase compensation algorithm is used to correct the phase of the fundamental wave component and harmonic components to obtain the frequency component data, phase difference data and harmonic content data. The time series characteristic parameter matrix is constructed according to the frequency component data, phase difference data and harmonic content data to complete the extraction of the time series characteristic parameters of the transient electromagnetic signal.

[0074] Exemplarily, a permanent magnet operated circuit breaker adopts a high-precision sensor array in the electromagnetic signal acquisition stage, with a configured sampling frequency of 800 times per second. At the sampling moment, the transient electromagnetic signal is calculated through the ratio of the electromagnetic torque stability parameter to the voltage fluctuation amplitude. During actual operation, the magnetic ring strength of the circuit breaker fluctuates within a range of 12 millimeters. Higher than this value will have an adverse impact on the permanent magnet force circuit. After obtaining the electromagnetic signal waveform, the waveform is transformed into the frequency domain through Fourier transform. At this time, it will be found that the spectral energy density is mainly concentrated in the range of 20 Hz to 60 Hz, and the current peak value decays as the number of circuit breaker operations increases. When the decay degree exceeds the threshold of 0.3, it indicates that the performance of the permanent magnet material has declined. At this time, the original signal is resampled to improve the analysis accuracy. Five-layer wavelet decomposition of the sampled electromagnetic signal can obtain coefficients in different frequency bands. Among them, the high-frequency coefficients reflect the transient characteristics of the switch, and the low-frequency coefficients contain steady-state operation information. By extracting the electromagnetic displacement change amount in the coefficients, it is found that the displacement fluctuates between 0.8 mm and 1.2 mm when the switch state changes, and the duration is about 15 ms to 25 ms. The parameters of the permanent magnet force circuit include key indicators such as magnetic flux density and magnetic field strength. When fitting the characteristic curve using the recursive least squares method, the initial magnetic flux density is set to 1.2 Tesla, and the magnetic field strength is 950 amperes per meter. The amplitude change characteristic curve is obtained through iterative calculation, and the slope of the curve reflects the change trend of the performance of the permanent magnet material. During harmonic analysis, the fundamental frequency is 50 Hz. The contents of the 2nd to 7th harmonics can be obtained through Fourier series expansion. During normal operation, the content of each harmonic does not exceed 10% of the fundamental wave. Among them, the 3rd harmonic and the 5th harmonic account for relatively large proportions, about 8% and 6% respectively. During the phase correction process, it is found that there is a phase difference between the fundamental wave and each harmonic. The phase compensation algorithm is used to control the phase difference within 5 degrees. The compensated frequency component data more accurately reflects the operating state of the circuit breaker. At the same time, the phase difference data and the harmonic content data also provide important bases for fault diagnosis. The constructed time series characteristic parameter matrix includes four dimensions: frequency component, amplitude change, phase difference, and harmonic content. Each element in the matrix has a clear physical meaning. By analyzing the change law of the parameter matrix, the operating state of the permanent magnet operated circuit breaker can be effectively monitored.

[0075] Further, step S2 may specifically include:

[0076] Obtain the transient electromagnetic signal from the power grid sampling device. Through Fourier series decomposition of the transient electromagnetic signal, calculate the cumulative energy of the frequency components within a preset frequency band, and obtain the first spectral characteristic data according to the comparison between the frequency band energy increment and the preset threshold;

[0077] Extract the amplitude of the transient electromagnetic signal according to the first spectral characteristic data, calculate the amplitude change rate using the discrete Fourier transform. If the amplitude change rate is greater than the preset amplitude change threshold, generate the first voltage sudden change characteristic data;

[0078] The first voltage mutation characteristic data is subjected to spectrum energy and transient response feature extraction through wavelet packet transform to obtain second spectrum feature data;

[0079] Correlation calculation is used to analyze the second spectrum feature data to extract time-series correlation features. If the matching degree of the time-series correlation features exceeds a preset threshold, it is determined that the transient electromagnetic signal is associated with the power quality disturbance caused by new energy grid connection.

[0080] More specifically, a first transient electromagnetic signal is obtained from a power grid sampling device. The cumulative energy of the frequency components within a preset frequency band is calculated through Fourier series decomposition. The first spectrum feature data is obtained by comparing the frequency band energy increment with a preset threshold. The amplitude of the transient electromagnetic signal is extracted based on the first spectrum feature data, and the amplitude change rate is calculated using discrete Fourier transform. The first voltage change characteristic data is obtained by comparing the amplitude change rate with a preset amplitude change threshold. According to the first spectrum feature data, if the frequency band energy increment is greater than the preset threshold, it is determined that there are inverter harmonics, and the first harmonic feature data is generated. According to the first voltage change characteristic data, if the amplitude change rate is greater than the preset threshold, it is determined that a voltage mutation has occurred, and the first voltage mutation characteristic data is generated. For the first harmonic feature data and the first voltage mutation characteristic data, their spectrum energy and transient response features are extracted through wavelet packet transform to obtain second spectrum feature data. Correlation calculation is used to analyze the second spectrum feature data to extract time-series correlation features, and power quality disturbance feature data is obtained. The power quality disturbance feature data is analyzed through matching degree calculation. If the matching degree exceeds the preset threshold, it is determined that the transient electromagnetic signal is associated with the power quality disturbance caused by new energy grid connection.

[0081] Exemplarily, when the power grid sampling device obtains the transient electromagnetic signal from the circuit breaker, the sampling frequency is set to 10 kHz, the sampling duration is 200 ms, and the waveform of the complete transient process is recorded. The amplitude range of the original signal obtained by sampling fluctuates between -100 V and +100 V, and the signal contains fundamental wave and harmonic components of each order. The frequency-domain analysis of the signal is performed by Fourier series decomposition, and the energy distribution is statistically analyzed in the preset frequency band of 50 Hz to 2000 Hz. When the power ratio in this frequency band exceeds 25% during normal operation, it indicates that the harmonic content of the inverter output increases, and at this time, the first spectrum feature data shows an abnormality. In the amplitude analysis, the amplitude is calculated every 1 ms for a 200-ms sampling window, and an amplitude sequence of 200 sampling points is obtained. The amplitude change rate is calculated by discrete Fourier transform. When the change rate exceeds 0.2, it is often accompanied by a sudden voltage rise or drop, and this voltage change feature reflects the transient disturbance in the power grid. The inverter harmonics are mainly manifested as the switching frequency and its multiples. The common switching frequencies are 2 kHz to 20 kHz. After frequency-down modulation, harmonic components are generated in the low-frequency band, and the most significant ones are the sidebands near 100 Hz and 150 Hz. These features are recorded in the first harmonic feature data. The voltage sudden change phenomenon usually lasts for 3 to 5 power frequency cycles, manifested as a rapid change in the voltage amplitude, and the change amplitude exceeds 20% of the rated value. The start time, duration, and amplitude change amount of the sudden change are recorded in the first voltage sudden change feature data. Wavelet packet transform can provide both time-domain and frequency-domain resolutions. After 6-layer decomposition of the signal, 64 frequency bands are obtained, and the energy change of each frequency band reflects the time-varying characteristics of different frequency components. The second spectrum feature data is obtained by calculating the energy ratio of each frequency band. In the correlation analysis, the correlation coefficient between the feature sequences is calculated using a sliding time window. The window length is selected as 100 ms, and the sliding step is 10 ms. When the correlation coefficient is greater than 0.8, a significant correlation is considered to exist, and this correlation is reflected in the power quality disturbance feature data. The association degree between the transient electromagnetic signal and the new energy grid connection disturbance is determined by matching degree calculation. The matching degree calculation considers three dimensions: spectrum feature, amplitude feature, and time sequence feature. When the comprehensive matching degree exceeds the preset threshold of 0.75, it indicates that this transient process is indeed caused by the new energy grid connection.

[0082] Further, step S3 may specifically include:

[0083] Obtain the voltage mutation amplitude data and the voltage sudden rise rate data from the power grid sampling device, and perform mutation point positioning on the voltage mutation amplitude data through wavelet edge detection to obtain the voltage fluctuation degree data;

[0084] According to the voltage fluctuation degree data and the remaining capacity data of the energy storage device, use the recursive least squares method for data fitting to obtain the first power response parameter;

[0085] Optimization calculations are performed on the first power response parameter and the historical discharge data of the energy storage device through a pre-established discharge optimization model to obtain a discharge optimization curve and a second power response parameter;

[0086] Calculate the discharge depth threshold of the energy storage device according to the second power response parameter, and construct a response strategy matrix using the discharge depth threshold and the fluctuation response delay parameter to obtain the discharge strategy of the energy storage system; the discharge strategy includes determining the output power, discharge depth, and the speed of responding to voltage fluctuations of the energy storage system.

[0087] More specifically, obtain the voltage mutation amplitude and voltage ramp rate data from the grid sampling device, locate the mutation points of the voltage fluctuation sequence through wavelet edge detection, and calculate the voltage fluctuation degree data based on the voltage change amount before and after the mutation points. Obtain the remaining capacity data of the energy storage device from the energy storage management unit, fit the voltage fluctuation degree data using the recursive least squares method, and calculate the first power response parameter based on the fitted curve. Calculate the first power response parameter according to the pre-established discharge optimization model, and obtain the discharge optimization curve through training with the historical discharge data of the energy storage device. Perform segmented calculations on the power regulation accuracy using the discharge optimization curve to obtain the second power response parameter. Calculate the discharge depth threshold of the energy storage device according to the second power response parameter to obtain the discharge depth parameter. Construct a response strategy matrix based on the discharge depth parameter and the fluctuation response delay parameter to obtain the response speed parameter. Calculate the output power parameter, discharge depth parameter, and response speed parameter of the energy storage device through the response strategy matrix to form the discharge strategy data.

[0088] Exemplarily, the power grid sampling device collects voltage data every 20 milliseconds, and identifies voltage mutation points through wavelet edge detection. When the voltage changes by more than 10% of the nominal value within 5 milliseconds, it is determined as a mutation point, and the mutation amplitude and the sudden rise rate are recorded. Analyses are conducted on 100 sampling points before and after the mutation to calculate the voltage fluctuation degree. The energy storage management unit monitors the remaining capacity of the battery pack in real time. Taking the lithium battery energy storage system as an example, with a capacity of 10 megawatt-hours and a current remaining capacity of 80%, the recursive least squares method is used to fit the recent 100 groups of voltage fluctuation data to obtain the correlation curve between voltage fluctuation and energy storage response. This curve reflects the magnitude of the power response required under different fluctuation degrees. The discharge optimization model is constructed based on historical operation data, including 1000 groups of records of voltage fluctuation and energy storage response. Each group of records includes the voltage fluctuation degree, the power output value, the discharge depth, and the response time. Through these data, the discharge optimization curve is trained, and this curve reflects the best response characteristics of the energy storage system. The power regulation accuracy is divided into three intervals: the low-power interval from 0 to 2 megawatts, with an adjustment step of 0.1 megawatt; the medium-power interval from 2 to 5 megawatts, with an adjustment step of 0.2 megawatt; the high-power interval from 5 to 10 megawatts, with an adjustment step of 0.5 megawatt. The corresponding power interval is selected according to the voltage fluctuation degree. The discharge depth parameter is closely related to the battery life. During normal operation, the discharge depth is controlled between 20% and 80%. For severe voltage fluctuations, the upper limit of the discharge depth can be increased to 90%. At the same time, considering the remaining battery life, when the number of cycles exceeds 3000 times, the upper limit of the discharge depth is reduced to 70%. The response speed parameter reflects the following ability of the energy storage system to voltage fluctuations. By calculating the response delay time, for low-power regulation, the response time is controlled within 50 milliseconds; for medium-power regulation, it is controlled within 100 milliseconds; for high-power regulation, it is controlled within 200 milliseconds. The response strategy matrix includes three dimensions: output power, discharge depth, and response speed. Each element in the matrix corresponds to a set of specific response parameters. For example, when a voltage sudden drop of 15% and a rate of 3% per millisecond are detected, a response strategy with an output power of 4 megawatts, a discharge depth of 60%, and a response time of 80 milliseconds is selected. This strategy not only ensures a fast response to voltage fluctuations but also avoids over-discharging of the energy storage system.

[0089] Further, step S3 may further include:

[0090] Obtain the current energy storage value, load value, and system operation parameters of the energy storage system, combine with the preset number of time periods and the electricity price table to construct an objective function; set the target discharge amount and the target energy storage value as constraint terms, and use the linear programming algorithm to solve the objective function under the constraints to obtain the target discharge strategy set; screen out the discharge strategies in the target strategy set whose discharge amounts exceed the preset capacity threshold, adjust the discharge amounts, and obtain the target discharge strategy.

[0091] Specifically, obtain the current energy storage value and the real-time load value from the energy storage management device, read the operation parameter values of the energy storage device through the data collector, and segment the electricity price data values according to the preset time period division number to obtain the electricity price data for the first time period; construct a minimum cost objective function according to the electricity price data for the first time period, and use the target discharge amount and the target energy storage value to calculate the constraint conditions to obtain the first optimization constraint condition; use the first optimization constraint condition to perform linear programming solution on the minimum cost objective function to obtain the first discharge strategy data; compare the discharge amount in the first discharge strategy data with the preset capacity threshold, and if the discharge amount exceeds the threshold, record the excess part to obtain the first discharge deviation data; calculate the discharge adjustment coefficient according to the first discharge deviation data, and use the discharge adjustment coefficient to perform linear interpolation calculation on the discharge amount to generate the target discharge strategy.

[0092] More specifically, obtain the current energy storage value and the real-time load value from the energy storage management device, read the operation parameter values of the energy storage device through the data collector, and segment the electricity price data values according to the preset time period division number to obtain the electricity price data for the first time period. Construct a minimum cost objective function according to the electricity price data for the first time period, obtain the constraint conditions from the target discharge amount and the target energy storage value, and obtain the first optimization constraint condition. Use the first optimization constraint condition to perform linear programming solution on the minimum cost objective function to obtain the first discharge strategy data. Compare the discharge amount in the first discharge strategy data with the preset capacity threshold, and if the discharge amount exceeds the threshold, record the excess part to obtain the first discharge deviation data. Calculate the discharge adjustment coefficient based on the first discharge deviation data, and perform linear interpolation calculation on the discharge amount to obtain the second discharge strategy data. Perform constraint verification on the second discharge strategy data. If the target energy storage value constraint is not satisfied, repeat the discharge amount adjustment until the constraint conditions are met. Generate the target discharge strategy data according to the discharge strategy that meets the constraint conditions.

[0093] Exemplarily, the energy storage management device monitors the operating status of the energy storage unit in real time. The current energy storage value is 8 megawatt-hours, and the real-time load value is 12 megawatts. The operating parameters include key indicators such as a charge-discharge efficiency of 95%, a maximum discharge power of 10 megawatts, and a minimum remaining power of 20%. According to the requirements of grid dispatching, 24 hours are divided into 6 time periods, and the electricity price data for each time period is 0.8 yuan, 1.2 yuan, 0.6 yuan, 0.9 yuan, 1.5 yuan, and 0.7 yuan per kilowatt-hour respectively. In the process of constructing the objective function, the principle of maximizing the energy storage benefit is considered. Discharging is prioritized during high electricity price periods, and discharging is avoided during low electricity price periods. At the same time, the constraint conditions are set as the target discharge amount not exceeding 6 megawatt-hours and the target energy storage value not being lower than 1.6 megawatt-hours. Through the linear programming solver, a preliminary discharge strategy is calculated. During the time period with an electricity price of 1.5 yuan, 4 megawatt-hours are discharged, and during the time period with an electricity price of 1.2 yuan, 2 megawatt-hours are discharged. The capacity threshold test is carried out on the discharge strategy. The preset capacity threshold is the maximum discharge amount of 3 megawatt-hours in a single time period. It is found that the discharge amount during the time period with an electricity price of 1.5 yuan exceeds the threshold by 1 megawatt-hour, and this deviation data is recorded for subsequent adjustment. According to the deviation data, the discharge adjustment coefficient of 0.75 is calculated, and the excess part is proportionally allocated to adjacent time periods. The adjusted discharge strategy is to discharge 3 megawatt-hours during the time period with an electricity price of 1.5 yuan, 2.5 megawatt-hours during the time period with an electricity price of 1.2 yuan, and 0.5 megawatt-hours during the time period with an electricity price of 0.9 yuan. The constraint verification is carried out on the adjusted strategy. The verification result shows that the requirement of the target energy storage value not being lower than 1.6 megawatt-hours is met. The remaining power of the energy storage device after executing the discharge strategy is 2 megawatt-hours. By using the linear programming method to find the optimal solution under various constraint conditions, the generation of the discharge strategy not only considers economy but also ensures the safe operation of the energy storage device. The multi-time period joint optimization avoids excessive discharging in a single time period, and the refined adjustment of the discharge amount ensures the reasonable utilization of the energy storage capacity. The implementation effect of the discharge strategy is reflected in multiple aspects. The discharge amount of the energy storage device is positively correlated with the electricity price level, and the discharge amount is larger during high electricity price periods; the discharge amount in each time period does not exceed the rated power and capacity threshold of the equipment; after executing the entire discharge strategy, the remaining power of the energy storage device can still meet the minimum remaining power requirement; through the adjustment of the discharge amount in adjacent time periods, a smooth transition of the discharge plan is achieved.

[0094] Further, step S4 may specifically include:

[0095] Obtain three-phase voltage waveform data from the grid monitoring device, and through Fourier transform analysis of the three-phase voltage waveform data, obtain the first voltage distortion data;

[0096] Perform symmetrical component decomposition on the three-phase voltage waveform data, and use the least squares method to calculate the phase deviation value and voltage amplitude to obtain the first unbalance data;

[0097] Perform compensation calculations based on the first voltage distortion data and the first unbalance data, determine the amplitude and phase of the compensation voltage through the symmetrical component method, and obtain the first harmonic compensation data and the first phase sequence compensation data;

[0098] Perform charging capacity optimization calculations for the first harmonic compensation data and the first phase sequence compensation data, verify the constraint of the compensation parameters through a preset compensation model, and screen out the charging strategy of the energy storage system.

[0099] More specifically, obtain the three-phase voltage waveform data from the power grid monitoring device, perform harmonic analysis on the waveform through Fourier transform, and calculate the first voltage distortion data based on the fundamental voltage value and each harmonic voltage. Perform symmetrical component decomposition on the three-phase voltage data, calculate the phase deviation value and voltage amplitude using the least squares method, and obtain the first unbalance data. Calculate the harmonic compensation target value based on the first voltage distortion data, optimize and sort the harmonic contents of each order to obtain the first harmonic compensation data. Calculate the three-phase compensation target value based on the first unbalance data, determine the amplitude and phase of the compensation voltage through the symmetrical component method, and obtain the first phase sequence compensation data. Calculate the power factor for the first harmonic compensation data and the first phase sequence compensation data, calculate the charging capacity using a preset compensation optimization model to obtain the first charging compensation data. Generate harmonic suppression instructions, unbalance compensation instructions, and power factor correction instructions based on the first charging compensation data to obtain the second charging compensation data. Perform constraint verification on the second charging compensation data, adjust the compensation parameters until the charging limit requirements of the energy storage device are met, and obtain the target charging strategy data.

[0100] Exemplarily, in the three-phase voltage waveforms collected by the power grid monitoring device, the fundamental voltage of phase A is 220 volts, containing 3% of the 3rd harmonic, 4% of the 5th harmonic, and 2% of the 7th harmonic. Each harmonic component is obtained by Fourier transform decomposition, and the total voltage distortion rate is calculated to be 5.4%, exceeding the national standard limit of 5%. During the symmetrical component decomposition process, it is found that there is an unbalance in the three-phase voltage. The voltage of phase A is 220 volts, the voltage of phase B is 208 volts, and the voltage of phase C is 215 volts. The phase deviation values are 2 degrees, -3 degrees, and 1 degree respectively. The unbalance degree calculated by the least squares method is 6.2%, higher than the 2% limit required by the power quality standard. For the harmonic problem, the compensation optimization first deals with the 5th harmonic with a higher content, setting the compensation target to reduce it to less than 2%, then the 3rd harmonic to less than 1.5%, and finally the 7th harmonic to less than 1%. Through this hierarchical compensation method, the voltage waveform quality is gradually improved. The three-phase unbalance compensation uses the symmetrical component method. It is calculated that the voltage of phase B needs to be increased by 12 volts to reach 220 volts, and the phase is adjusted to 120 degrees at the same time. The voltage of phase C is increased by 5 volts to 220 volts, and the phase is adjusted to 240 degrees. Through this compensation method, the three-phase voltage reaches a symmetrical state. When determining the charging capacity, considering that 2 MW of capacity is required for harmonic compensation, 1.5 MW of capacity is required for unbalance compensation, and 1 MW of capacity is required to improve the power factor from 0.92 to 0.98, the energy storage device is comprehensively calculated to provide a charging power of 4.5 MW. During the generation process of the compensation instruction, the harmonic suppression instruction includes the compensation amplitude and phase of each harmonic, the unbalance compensation instruction includes the compensation voltage and phase adjustment amount of each phase, and the power factor correction instruction includes the reactive power compensation value. The constraint verification link focuses on the charging limit of the energy storage device, including that the maximum charging power does not exceed 5 MW, the battery terminal voltage does not exceed 850 volts during the charging process, the charging current does not exceed 600 amperes, and considering the limit that the state of charge of the battery does not exceed 90%, the compensation parameters are appropriately adjusted. The formed charging strategy realizes the comprehensive management of power quality on the premise of ensuring the safe operation of the energy storage device. By coordinating the control of harmonic suppression, unbalance compensation, and power factor correction in three aspects, the power grid operation indicators meet the relevant standard requirements.

[0101] Furthermore, step S4 may further include:

[0102] The harmonic content data is calculated from the harmonic content data in the transient electromagnetic signal, and the voltage distortion rate is calculated from the harmonic content data; by measuring the instantaneous values of the three-phase voltages, the difference between the first target phase voltage and the second target phase voltage in the three-phase voltages, and the average value of the three-phase voltages are determined, and the three-phase voltage unbalance degree is calculated.

[0103] Specifically, obtain the harmonic content data from the transient electromagnetic signal acquisition device, decompose the harmonic content data through fast Fourier transform, and calculate the harmonic component data according to the fundamental wave voltage value and the harmonic order value; perform amplitude statistics on the harmonic component data, calculate the ratio of each harmonic voltage to the fundamental wave voltage, and then perform cumulative summation to obtain the voltage distortion rate; obtain the instantaneous values of the three-phase voltages from the three-phase voltage sampling device, calculate the effective values of the three-phase voltages, and select the maximum value as the first target phase voltage and the minimum value as the second target phase voltage; calculate the voltage difference according to the first target phase voltage and the second target phase voltage to obtain the first inter-phase voltage deviation data, and calculate the three-phase voltage unbalance degree by dividing the first inter-phase voltage deviation data by the average value of the three-phase voltages.

[0104] More specifically, obtain the harmonic content data from the transient electromagnetic signal acquisition device, decompose the signal through fast Fourier transform, and calculate the first harmonic component data according to the fundamental wave voltage value and the harmonic order value. Perform amplitude statistics on the first harmonic component data, and calculate the first voltage distortion data according to the ratio of each harmonic voltage to the fundamental wave voltage. Perform cumulative summation on the first voltage distortion data, and calculate the voltage distortion rate according to the ratio of the total harmonic voltage to the fundamental wave voltage. Obtain the instantaneous values of the three-phase voltages from the three-phase voltage sampling device, and calculate the effective value sequence of the three-phase voltages. Sort the effective value sequence of the three-phase voltages according to the amplitude size, select the maximum value as the first target phase voltage and the minimum value as the second target phase voltage. Calculate the voltage difference according to the first target phase voltage and the second target phase voltage to obtain the first inter-phase voltage deviation data. Calculate the three-phase voltage unbalance degree by dividing the first inter-phase voltage deviation data by the average value of the three-phase voltages.

[0105] Exemplarily, the transient electromagnetic signal contains rich harmonic information. The sampling device collects the signal at a frequency of 10 kHz, records a data window of 200 ms, and can accurately extract each harmonic component through fast Fourier transform. The measured data of a substation shows that the fundamental voltage is 220 V, the 3rd harmonic voltage is 6.6 V, the 5th harmonic voltage is 11 V, and the 7th harmonic voltage is 4.4 V. When performing harmonic component statistics, the harmonic content percentage is obtained by dividing each harmonic voltage by the fundamental voltage. After the above data conversion, the 3rd harmonic content is 3%, the 5th harmonic content is 5%, and the 7th harmonic content is 2%. These values reflect the relative intensities of each harmonic in the power grid, among which the 5th harmonic content is the highest. This phenomenon is relatively common in industrial areas with a large number of variable-frequency devices. The calculation of the voltage distortion rate comprehensively considers the influence of all harmonics. After summing the squares of each harmonic voltage and taking the square root, and then dividing by the fundamental voltage, the total harmonic distortion rate is 6.2%. This value exceeds the 5% limit specified by the national standard, indicating that the power grid harmonic pollution is relatively serious. In the three-phase voltage sampling, 1000 sampling points are collected for each phase voltage to calculate the effective value. The effective value of phase A voltage is 225 V, the effective value of phase B voltage is 210 V, and the effective value of phase C voltage is 218 V. Through sorting and comparison, it is found that the maximum value appears in phase A and the minimum value appears in phase B. These two phases are selected as the target phases for calculating the unbalance degree. The voltage difference between the two target phases is 15 V, and at the same time, the average value of the three-phase voltage is calculated to be 217.7 V. Dividing the voltage difference by the average value, the three-phase voltage unbalance degree is 6.9%, which greatly exceeds the 2% limit specified by the power quality standard. This unbalance phenomenon is often related to the unreasonable distribution of single-phase large-power loads. This unbalance situation is particularly prominent in industrial areas. If there are single-phase loads such as large arc furnaces and electrified railways, it will often lead to more serious three-phase unbalance. In the power supply system of a steel plant, when the arc furnace starts to work, the three-phase voltage unbalance degree will quickly rise above 8%, accompanied by obvious harmonic distortion, and the total harmonic distortion rate can reach 7.5%. The comprehensive evaluation of voltage distortion and three-phase unbalance has important guiding significance for improving power quality. By accurately calculating these two indicators, it can not only reflect the operating state of the power supply system but also provide a basis for subsequent compensation measures. The actual operation data shows that through reasonable compensation means, the voltage distortion rate can be controlled within 4%, and the three-phase unbalance degree can be reduced to below 1.5%.

[0106] Further, step S5 can specifically include:

[0107] Obtain the harmonic current content and power factor reference data before the implementation of the charge and discharge strategy in the line monitoring device, and perform spectrum analysis on the reference data through Fourier transform to obtain the first evaluation data;

[0108] Collect the line operation data after the charge and discharge strategy is implemented according to the first evaluation data, and calculate the change value of the harmonic current content by using Fourier transform to obtain the second evaluation data;

[0109] Calculate the change value of the power factor according to the second evaluation data, and calculate the third evaluation data through reactive power compensation;

[0110] Use a line loss calculator to comprehensively calculate the second evaluation data and the third evaluation data, and perform an integral operation on the energy loss value per unit length according to the line resistance parameter to obtain the total line energy loss data;

[0111] If the harmonic current content in the total line energy loss data is lower than the reference value and the power factor is higher than the reference value, determine the current charge and discharge strategy as the target energy-saving charge and discharge strategy.

[0112] More specifically, obtain the harmonic current content and power factor reference data before the charge and discharge strategy is implemented from the line monitoring device, and perform spectral analysis on the reference data by using Fourier transform to obtain the first evaluation data. Collect the line operation data after the charge and discharge strategy is implemented, and calculate the change value of the harmonic current content by using Fourier transform to obtain the second evaluation data. Calculate the change value of the power factor according to the second evaluation data, and calculate the third evaluation data through reactive power compensation. Use a line loss calculator to comprehensively calculate the second evaluation data and the third evaluation data, and obtain the energy loss value per unit length according to the line resistance parameter. Perform an integral operation on the energy loss value per unit length to obtain the total line energy loss data. Determine the total line energy loss data according to the preset energy-saving reference. If the harmonic current content is lower than the reference value and the power factor is higher than the reference value, record the current charge and discharge strategy parameters. Mark the charge and discharge strategy parameters that meet the energy-saving reference as the target energy-saving charge and discharge strategy data.

[0113] Exemplarily, the line monitoring device collects the operation data of a 10 kV transmission line. Before the implementation of the charge-discharge strategy, there is obvious harmonic pollution in the line. Among them, the content of the 3rd harmonic current is 4.5%, the content of the 5th harmonic current is 6.2%, the content of the 7th harmonic current is 3.8%, and the power factor is 0.85. These data constitute the benchmark values for evaluation. By analyzing the data after the implementation of the strategy through Fourier transform, it is found that the content of the 3rd harmonic current is reduced to 2.8%, the content of the 5th harmonic current is reduced to 3.5%, the content of the 7th harmonic current is reduced to 2.2%, and the total harmonic current content is reduced from 8.5% to 5.0%, indicating that the charge-discharge strategy has a significant effect on harmonic suppression. The improvement of the power factor is reflected in the compensation of reactive power. Through the charge-discharge process of the energy storage device, the power factor of the line is increased to 0.95, and the reactive power is compensated from the original 750 kvar to 320 kvar. This improvement directly affects the energy loss of the line. When calculating the line loss, considering that the line resistance is 0.25 ohms per kilometer, for a 5-kilometer-long line segment, through the improvement of harmonic current and power factor, the energy loss per unit length is reduced from the original 2.8 kW per kilometer to 1.5 kW per kilometer. The calculation result of the total line energy loss shows that the total loss before the implementation of the strategy is 14 kW, and it is reduced to 7.5 kW after the implementation, and the loss reduction rate reaches 46%. The preset energy-saving benchmark requires that the harmonic current content be reduced by 30% and the power factor be increased by more than 0.08. The implementation effect of the current strategy has exceeded this benchmark. The specific parameters of the energy-saving charge-discharge strategy include the operation instructions of the energy storage device. When the harmonic content is high, the charging power is increased to 2 MW, and at the same time, the charging current waveform is adjusted through an intelligent control algorithm to make it opposite to the phase of the harmonic current, so as to achieve harmonic suppression. In terms of power factor correction, the energy storage device dynamically adjusts the charge-discharge power according to the load characteristics. The discharge power during peak hours is controlled at 1.5 MW, and the charging power during low valley hours is maintained at 1 MW, which not only ensures the improvement effect of power quality but also avoids overcharging and over-discharging of the energy storage device. The determined target energy-saving charge-discharge strategy not only meets the preset energy-saving benchmark but also shows good adaptability in actual operation. Even under the condition of large load fluctuations, it can still maintain stable harmonic suppression and power factor improvement effects, and the line energy loss always remains at a low level.

[0114] Further, step S6 may specifically include:

[0115] Decompose the electromagnetic signal through fast Fourier transform, and calculate the first power spectral density data according to the spectrum distribution;

[0116] Perform instantaneous power calculation on the first power spectral density data, and segment the instantaneous power curve by using a sliding window to obtain the first time series data;

[0117] Perform sample division based on the first time series data, extract voltage values from the divided sample segments to obtain second time series data;

[0118] Perform long short-term memory network training on the second time series data, extract voltage change features from historical data to obtain the first prediction parameter;

[0119] Calculate the voltage rise rate and fall rate using the first prediction parameter, and make a judgment through a threshold comparator to obtain the second prediction parameter;

[0120] If the rise rate or fall rate exceeds the preset threshold, record the current voltage change data, generate a power adjustment amount according to the change amplitude to obtain the energy storage optimization parameter.

[0121] More specifically, obtain transient electromagnetic signal data from the power grid monitoring device, decompose the signal through fast Fourier transform, and calculate the first power spectral density data according to the spectrum distribution. Calculate the instantaneous power of the first power spectral density data, segment the instantaneous power curve using a sliding window to obtain the first time series data. Perform sample division based on the first time series data, extract voltage values for each sample segment to obtain the second time series data. Perform long short-term memory network training on the second time series data, extract voltage change features from historical data to obtain the first prediction parameter. Calculate the voltage rise rate and fall rate using the first prediction parameter, and make a judgment through a threshold comparator to obtain the second prediction parameter. Judge the power grid stability state according to the second prediction parameter. If the rise rate or fall rate exceeds the preset threshold, record the current voltage change data. Calculate the charge and discharge power of the recorded voltage change data, generate a power adjustment amount according to the change amplitude to obtain the energy storage optimization parameter. Adjust the charge and discharge power using the energy storage optimization parameter to generate new energy storage charge and discharge strategy parameters.

[0122] Exemplarily, the transient electromagnetic signals collected by the power grid monitoring device are recorded at a sampling frequency of 10 kHz. After fast Fourier transform, the frequency spectrum distribution is obtained. The power spectral density has an obvious main peak at the 50 Hz fundamental frequency, with an amplitude of 100 kW / Hz. There are secondary peaks at 100 Hz and 150 Hz, with amplitudes of 15 kW / Hz and 8 kW / Hz respectively. The instantaneous power curve is calculated using a 200 ms sliding window with a 50% window overlap rate. 2000 sampling points are recorded in each window. This segmentation method not only ensures the continuity of the data but also can capture rapid power changes. The analysis of a certain period shows that the instantaneous power fluctuates between 5 MW and 7 MW, with obvious periodic changes. The time series samples are divided in a fixed-length manner. Each sample contains 10 consecutive sliding window data, which is equivalent to an observation duration of 2 s. This division method enables each sample to contain a complete power fluctuation cycle. The extracted voltage values show that during normal operation, the voltage fluctuates between 95% and 105% of the rated value of 220 V. The long short-term memory network adopts a three-layer structure with 128 hidden layer neurons. Through training, it masters the voltage change law and predicts the voltage change trend in the next 100 ms. The root mean square error of the prediction result is controlled within 2%. The change features extracted from the prediction results include the voltage change rate and duration. The calculation result of the voltage ramp rate shows that under normal conditions, the voltage change rate does not exceed 1% of the nominal value per millisecond, while it can reach 5% per millisecond during disturbances. The preset warning threshold is 3% per millisecond. Once the predicted value exceeds this threshold, it means that a power grid instability state may occur. The energy storage response strategy is calculated based on the voltage change data. When a voltage ramp is predicted, the energy storage device increases the charging power from the original 1 MW to 2 MW, and the charging duration is dynamically adjusted according to the voltage change duration. On the contrary, when a voltage dip is predicted, the discharging power is increased to 2.5 MW. The optimized charge and discharge strategy shows good adaptability in actual operation. For voltage fluctuations with a duration less than 50 ms, the energy storage device can complete the power adjustment within 20 ms, effectively suppressing the voltage fluctuations. For larger disturbances, the adjustment of the charge and discharge power is divided into multiple steps, with each step adjustment amplitude controlled within 0.5 MW, avoiding excessive response of the energy storage device. The measured data shows that the optimized control strategy reduces the voltage fluctuation amplitude by 40% and effectively suppresses the power fluctuations.

[0123] The present disclosure also provides an AIoT multi-source data-based power quality energy-saving operation monitoring device, including:

[0124] A transient electromagnetic signal acquisition module for acquiring the transient electromagnetic signals of the permanent magnet operated circuit breaker;

[0125] A timing feature parameter extraction module for extracting the timing feature parameters of the transient electromagnetic signals;

[0126] The power quality disturbance correlation module is used to determine whether there is a harmonic problem caused by an inverter and a voltage swell or sag occurs, and determine whether the timing characteristic parameters are correlated with the power quality disturbance;

[0127] The discharge strategy optimization module is used to obtain the voltage mutation amplitude and the voltage swell rate, obtain the voltage fluctuation degree according to the voltage mutation amplitude and the voltage swell rate, input the voltage fluctuation degree into the discharge optimization model, and output the discharge strategy of the energy storage system;

[0128] The charge strategy optimization module is used to calculate the voltage distortion rate and the three-phase voltage unbalance degree, and select the charge strategy of the energy storage system through a pre-established charge optimization model;

[0129] The energy-saving strategy evaluation module is used to evaluate the influence of the charge strategy and the discharge strategy on the harmonic current content of the transmission line and the energy loss corresponding to the change of the power factor, and determine the target energy-saving charge strategy and the target energy-saving discharge strategy;

[0130] The adjustment module is used to monitor in real time the instantaneous power curve and the power spectral density corresponding to the transient electromagnetic signals of the target energy-saving charge strategy and the target energy-saving discharge strategy, and perform time series analysis to obtain voltage value time series data; divide the time series data into samples of a set length, predict the swell rate and the sag rate of the samples, obtain the prediction results, and form an energy-saving optimization plan for the energy storage charge and discharge strategy according to the prediction results.

[0131] In the description of the present disclosure, it should be understood that the orientation or positional relationship indicated by orientation words such as "front, back, up, down, left, right", "horizontal, vertical, horizontal" and "top, bottom" is usually based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present disclosure and simplifying the description. Without contrary description, these orientation words do not indicate and imply that the device or element referred to must have a specific orientation or be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the protection scope of the present disclosure.

[0132] For those skilled in the art, various corresponding changes and deformations can be made according to the technical solutions and concepts described above, and all these changes and deformations should fall within the protection scope of the claims of the present disclosure.

Claims

1. A method for monitoring power quality and energy-saving operation based on AI IoT multi-source data, characterized in that: The following steps are involved: S1. Acquire a transient electromagnetic signal of a permanent magnetic operating mechanism circuit breaker and extract a time sequence characteristic parameter of the transient electromagnetic signal; S2, judging whether there is a harmonic problem caused by the inverter and whether a voltage surge or a voltage drop occurs, and determining whether the timing characteristic parameter is associated with the power quality disturbance; S3, obtaining a voltage mutation amplitude and a voltage surge rate, obtaining a voltage fluctuation degree according to the voltage mutation amplitude and the voltage surge rate, inputting the voltage fluctuation degree into a discharge optimization model, and outputting a discharge strategy for the energy storage system; S4. Calculate the voltage distortion rate and the three-phase voltage imbalance, and select the charging strategy of the energy storage system through the pre-established charging optimization model; S5. Evaluate the impact of charging strategy and discharging strategy on the harmonic current content of the transmission line and the energy loss corresponding to the power factor change, and determine the target energy-saving charging strategy and the target energy-saving discharging strategy; S6. Real-time monitoring of the instantaneous power curve and power spectrum density corresponding to the transient electromagnetic signals of the target energy-saving charging strategy and the target energy-saving discharging strategy, and performing time series analysis to obtain voltage value time series data; dividing the time series data into samples of a set length, predicting the sudden rise rate and sudden fall rate of the samples, obtaining prediction results, and forming an energy-saving optimization plan for the energy storage charging and discharging strategy according to the prediction results.

2. According to claim 1, the method for monitoring power quality and energy-saving operation based on AI Internet of Things multi-source data is characterized in that: The timing characteristic parameters include frequency components, amplitude changes, phase differences and harmonic content; The step S1 comprises: The electromagnetic torque stability parameter is calculated based on the original waveform data of the electromagnetic signal collected by the circuit breaker sensor and the magnetic ring strength of the permanent magnetic material to obtain a first transient electromagnetic signal sequence; Decomposing the first transient electromagnetic signal sequence in the frequency domain by fast Fourier transform, and generating a second transient electromagnetic signal sequence if the spectrum energy density is greater than the magnetic flux attenuation degree threshold; The third transient electromagnetic signal sequence is obtained by performing wavelet decomposition on the second transient electromagnetic signal sequence to obtain high-frequency coefficients and low-frequency coefficients, and extracting the electromagnetic displacement change and the switching state continuity characteristic curve from the high-frequency coefficients and the low-frequency coefficients. The recursive least squares method is used to fit the third transient electromagnetic signal sequence to obtain an amplitude change characteristic curve, and the fundamental component and harmonic component of the amplitude change characteristic curve are corrected by a phase compensation algorithm to obtain frequency component data and harmonic content data to construct a time series characteristic parameter matrix.

3. According to claim 1, the method for monitoring power quality and energy-saving operation based on AI Internet of Things multi-source data is characterized in that: The step S2 comprises: Acquire a transient electromagnetic signal from a power grid sampling device, perform Fourier series decomposition on the transient electromagnetic signal, calculate the cumulative energy of the frequency component within a preset frequency band, and obtain first frequency spectrum feature data based on the comparison of the frequency band energy increment with a preset threshold; Extracting the amplitude of the transient electromagnetic signal according to the first frequency spectrum characteristic data, calculating the amplitude change rate by discrete Fourier transform, and generating first voltage sudden change characteristic data if the amplitude change rate is greater than a preset amplitude change threshold; Extracting spectrum energy and transient response characteristics of the first voltage sudden change characteristic data by wavelet packet transformation to obtain second spectrum characteristic data; The second frequency spectrum feature data is analyzed by correlation calculation to extract time series correlation features. If the matching degree of the time series correlation features exceeds a preset threshold, it is determined that the transient electromagnetic signal is associated with the power quality disturbance caused by the new energy grid connection.

4. According to claim 1, the method for monitoring power quality and energy-saving operation based on AI Internet of Things multi-source data is characterized in that: The step S3 comprises: Acquire voltage mutation amplitude data and voltage surge rate data from the power grid sampling device, locate the mutation point of the voltage mutation amplitude data by wavelet edge detection, and obtain voltage fluctuation degree data; According to the voltage fluctuation degree data and the remaining capacity data of the energy storage device, a recursive least square method is used to perform data fitting to obtain a first power response parameter; The first power response parameter and the historical discharge data of the energy storage device are optimized and calculated by a pre-established discharge optimization model to obtain a discharge optimization curve and a second power response parameter; The discharge depth threshold of the energy storage device is calculated according to the second power response parameter, and the response strategy matrix is ​​constructed using the discharge depth threshold and the fluctuation response delay parameter to obtain the discharge strategy of the energy storage system; the discharge strategy includes determining the output power, discharge depth and speed of responding to voltage fluctuations of the energy storage system.

5. According to claim 4, the method for monitoring power quality and energy-saving operation based on AI Internet of Things multi-source data is characterized in that: The step S3 further comprises: The current energy storage value, load value and system operating parameters of the energy storage system are obtained, and the objective function is constructed in combination with the preset number of time periods and electricity price table; the target discharge capacity and target energy storage value are set as constraints, and a linear programming algorithm is used to solve the objective function under the constraints to obtain the target discharge strategy set; the discharge strategies whose discharge capacity exceeds the preset capacity threshold in the target strategy set are screened out, the discharge capacity is adjusted, and the target discharge strategy is obtained.

6. According to claim 1, the method for monitoring power quality and energy-saving operation based on AI Internet of Things multi-source data is characterized in that: The step S4 comprises: Acquire three-phase voltage waveform data from a power grid monitoring device, and obtain first voltage distortion data by performing Fourier transform analysis on the three-phase voltage waveform data; Decomposing the three-phase voltage waveform data into symmetrical components, calculating the phase deviation value and the voltage amplitude using the least square method, and obtaining first imbalance data; Perform compensation calculation according to the first voltage distortion data and the first imbalance data, determine the compensation voltage amplitude and phase by a symmetrical component method, and obtain first harmonic compensation data and first phase sequence compensation data; An optimization calculation of charging capacity is performed on the first harmonic compensation data and the first phase sequence compensation data, and constraint verification is performed on compensation parameters through a preset compensation model to screen out a charging strategy for the energy storage system.

7. According to claim 6, the method for monitoring power quality and energy-saving operation based on AI Internet of Things multi-source data is characterized in that: The step S4 further comprises: The harmonic content data is calculated from the harmonic content data in the transient electromagnetic signal, and the voltage distortion rate is calculated based on the harmonic content data; by measuring the instantaneous value of the three-phase voltage, the difference between the first target phase voltage and the second target phase voltage in the three-phase voltage, as well as the average value of the three-phase voltage are determined, and the three-phase voltage imbalance is calculated.

8. According to claim 1, the method for monitoring power quality and energy-saving operation based on AI Internet of Things multi-source data is characterized in that: The step S5 comprises: Obtaining harmonic current content and power factor benchmark data before the implementation of the charging and discharging strategy in the line monitoring device, and performing spectrum analysis on the benchmark data through Fourier transform to obtain first evaluation data; According to the first evaluation data, the line operation data after the implementation of the charging and discharging strategy is collected, and the harmonic current content change value is calculated by Fourier transform to obtain the second evaluation data; Calculating a power factor change value according to the second evaluation data, and obtaining third evaluation data through reactive power compensation calculation; A line loss calculator is used to comprehensively calculate the second evaluation data and the third evaluation data, and the energy loss value per unit length is integrated according to the line resistance parameter to obtain the total line energy loss data; If the harmonic current content in the total line energy loss data is lower than the reference value and the power factor is higher than the reference value, the current charging and discharging strategy is determined as the target energy-saving charging and discharging strategy.

9. According to claim 1, the method for monitoring power quality and energy-saving operation based on AI Internet of Things multi-source data is characterized in that: The step S6 comprises: Decomposing the electromagnetic signal by fast Fourier transform, and obtaining first power spectrum density data according to spectrum distribution calculation; Performing instantaneous power calculation on the first power spectrum density data, and performing segmented processing on the instantaneous power curve using a sliding window to obtain first time series data; Performing sample division according to the first time series data, extracting voltage values ​​from the divided sample segments, and obtaining second time series data; Performing long short-term memory network training on the second time series data, extracting voltage change characteristics from historical data, and obtaining a first prediction parameter; The voltage swell rate and the voltage sag rate are calculated by using the first prediction parameter, and a threshold comparator is used to make a judgment to obtain a second prediction parameter; If the surge rate or the sag rate exceeds the preset threshold, the current voltage change data is recorded, and the power adjustment amount is generated according to the change amplitude to obtain the energy storage optimization parameters.

10. A power quality energy-saving operation monitoring device based on AI Internet of Things multi-source data, characterized in that: include: A transient electromagnetic signal acquisition module, which is used to acquire a transient electromagnetic signal of a permanent magnetic operating mechanism circuit breaker; A time series characteristic parameter extraction module, wherein the time series characteristic parameter extraction module is used to extract the time series characteristic parameters of the transient electromagnetic signal; A power quality disturbance association module, which is used to determine whether there is a harmonic problem caused by the inverter and whether a voltage surge or a voltage drop occurs, and to determine whether the timing characteristic parameter is associated with the power quality disturbance; A discharge strategy optimization module, wherein the discharge strategy optimization module is used to obtain a voltage mutation amplitude and a voltage surge rate, obtain a voltage fluctuation degree according to the voltage mutation amplitude and the voltage surge rate, input the voltage fluctuation degree into a discharge optimization model, and output a discharge strategy for the energy storage system; A charging strategy optimization module, which is used to calculate the voltage distortion rate and the three-phase voltage imbalance, and select a charging strategy for the energy storage system through a pre-established charging optimization model; An energy-saving strategy evaluation module, which is used to evaluate the impact of charging strategy and discharging strategy on the harmonic current content of the transmission line and the energy loss corresponding to the power factor change, and determine the target energy-saving charging strategy and the target energy-saving discharging strategy; An adjustment module, the adjustment module is used to monitor in real time the instantaneous power curve and power spectrum density corresponding to the transient electromagnetic signals of the target energy-saving charging strategy and the target energy-saving discharging strategy, and perform time series analysis to obtain voltage value time series data; divide the time series data into samples of a set length, predict the sudden rise rate and sudden fall rate of the samples, obtain the prediction results, and form an energy-saving optimization plan for the energy storage charging and discharging strategy according to the prediction results.

Images