Power distribution system inter-phase imbalance correction device and correction method based on energy storage cooperation

Abstract

The invention discloses a power distribution system inter-phase imbalance correction device and method based on energy storage cooperation, and relates to the technical field of power conversion, and the method comprises the steps: collecting inter-phase historical operation data of a power distribution system, and predicting an inter-phase operation curve based on the historical operation data; acquiring an actual inter-phase operation curve of the power distribution system in real time, calculating an error coefficient based on the predicted inter-phase operation curve and the actual inter-phase operation curve, and generating a corrected inter-phase operation curve based on the error coefficient; and on the basis of the correction interphase operation curve, obtaining an interphase imbalance time point and a correction value at a future moment, wherein the imbalance time point and the correction value serve as correction parameters of the energy storage unit. An error coefficient of a predicted interphase operation curve and an actual interphase operation curve is analyzed, a corrected interphase operation curve is generated based on the error coefficient, and an interphase imbalance time point and a correction value at a future moment are extracted from the corrected interphase operation curve, so that the interphase of the power distribution system is corrected in advance, and the failure rate of interphase imbalance is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of power conversion, and particularly relates to an inter-phase imbalance correction device and a correction method for a distribution system based on energy storage cooperation. Background Art

[0002] The three-phase imbalance of a power system is caused by the imbalance of three-phase loads and the asymmetry of the three-phase parameters of system components. The condition of the three-phase voltage balance of a power system is one of the main indicators of power quality. Currently, corrections are made for inter-phase imbalances.

[0003] For example, the Chinese invention patent with the authorization announcement number CN105870944B discloses a method for controlling the inter-phase power balance of a power electronic transformer, including the following steps: calculating the d-axis component and q-axis component of the zero-sequence voltage by using the difference in active power under the action of the zero-sequence voltage required to be output by any two of the three phases of the transformer and the active power under the action of the zero-sequence voltage required to be output by the third phase of the three phases; calculating the zero-sequence voltage according to the d-axis component of the zero-sequence voltage, the q-axis component of the zero-sequence voltage, and the grid angular frequency; respectively superimposing the three-phase modulation waves output by the high-voltage stage of the transformer with the zero-sequence voltage to generate new three-phase modulation waves; generating corresponding trigger pulses according to the new three-phase modulation waves to control the high-voltage stage of the transformer, so as to achieve inter-phase power balance control. This patent intervenes in the correction after an imbalance fault occurs in the grid voltage, and it is impossible to perform pre-correction before the fault occurs to avoid the occurrence of inter-phase imbalance;

[0004] Therefore, the present invention proposes an inter-phase imbalance correction device and a correction method for a distribution system based on energy storage cooperation. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art. For this reason, the present invention proposes an inter-phase imbalance correction device and a correction method for a distribution system based on energy storage cooperation. The inter-phase imbalance correction device and correction method for the distribution system based on energy storage cooperation predict the inter-phase imbalance that will occur at a future moment based on historical power consumption data, and perform pre-correction based on the energy storage unit to reduce the failure rate of inter-phase imbalance.

[0006] To achieve the above object, an inter-phase imbalance correction device and a correction method for a distribution system based on energy storage cooperation are proposed, including:

[0007] Collecting the historical operation data of the inter-phase of the distribution system, and predicting the inter-phase operation curve based on the historical operation data;

[0008] Real-time collecting the actual inter-phase operation curve of the distribution system, calculating the error coefficient based on the predicted inter-phase operation curve and the actual inter-phase operation curve, and generating a corrected inter-phase operation curve based on the error coefficient;

[0009] Obtain the inter-phase unbalance time points and correction values at future moments based on the calibrated inter-phase operation curve, and use the unbalance time points and correction values as the correction parameters of the energy storage unit.

[0010] Preferably, the method for predicting the inter-phase operation curve based on historical operation data includes:

[0011] Train a voltage recognition model for predicting inter-phase voltage based on historical operation data;

[0012] Continuously collect the operation data of n distribution systems at a preset frequency, where n is an integer greater than 1. Input the n pieces of operation data into the voltage recognition model in sequence, and output n inter-phase voltages;

[0013] Map the n inter-phase voltages in the coordinate system with time as the abscissa and inter-phase voltage as the ordinate in the order of acquisition time, and connect the n inter-phase voltages in sequence to obtain the predicted inter-phase operation curve.

[0014] Preferably, the historical operation data includes H groups of condition data and the inter-phase voltages corresponding to the H groups of condition data;

[0015] Where H is the preset amount of training data, and H = 1, 2, 3... H.

[0016] Preferably, the training method of the voltage recognition model is:

[0017] Convert a group of condition data and the inter-phase voltage corresponding to the condition data into a group of first feature vectors, and use the first feature vectors as the input of the machine learning model A. The machine learning model A outputs the predicted inter-phase voltage for each group of condition data, and uses minimizing the sum of the prediction accuracies of all inter-phase voltages as the training objective; train the machine learning model A until the sum of the prediction accuracies reaches convergence and then stop training. The trained machine learning model A is used as the voltage recognition model, and the machine learning model A is a polynomial regression model or a support vector machine model.

[0018] Preferably, the predicted inter-phase operation curve is a curve of the inter-phase voltage changing with time predicted by the distribution system according to the current operation data and combined with the historical operation data;

[0019] The actual inter-phase operation curve is a curve drawn by the distribution system by collecting the inter-phase voltage in real time and changing with time.

[0020] Preferably, the method for calculating the error coefficient based on the predicted inter-phase operation curve and the actual inter-phase operation curve is:

[0021] Calculate the sub-error coefficients of the predicted inter-phase operation curve and the actual inter-phase operation curve. The calculation expression is:

[0022]

[0023] Among them, represents the sub-error coefficient at the t-th moment of the n-th running data; is the voltage value of the predicted inter-phase running curve at the t-th moment of the n-th running data; is the voltage value collected at the t-th moment of the actual inter-phase running curve;

[0024] Calculate the error coefficient based on n sub-error coefficients. The calculation expression of the error coefficient is:

[0025] , where is the error coefficient.

[0026] Preferably, the method for generating the corrected inter-phase running curve based on the error coefficient is:

[0027] Step 1, calculate the corrected voltage at the (t + L)-th moment based on the error coefficient, where L is an integer greater than 1. The calculation expression is:

[0028] , is the compensation coefficient, and D is the corrected voltage;

[0029] Step 2, repeat Step 1 and continuously update the value of L, and calculate the corrected voltage values of (t + L) after updating in sequence to obtain corrected voltage values, , and connect the corrected voltage values in chronological order to draw the corrected inter-phase running curve.

[0030] Preferably, the method for obtaining the inter-phase unbalance time point and the corrected value at a future moment based on the corrected inter-phase running curve is:

[0031] Compare the corrected voltage at a future moment with a preset voltage threshold. If the corrected voltage is greater than or less than the preset voltage threshold, it is determined as inter-phase unbalance, and the corresponding moment of this corrected voltage is marked; if the corrected voltage is equal to the preset voltage threshold, it is determined as inter-phase balance;

[0032] Collect multiple groups of historical correction data, where the historical correction data includes unbalanced data and the corrected values corresponding to the unbalanced data;

[0033] Train a correction recognition model for predicting the corrected value based on the historical correction data;

[0034] Obtain the real-time operation data of the distribution system, and input the real-time operation data into the correction recognition model to output the corrected value.

[0035] Preferably, the training method of the correction recognition model is:

[0036] Convert a set of unbalanced data and the correction values corresponding to the unbalanced data into a set of second feature vectors, and use the second feature vectors as the input of the machine learning model B. The machine learning model B outputs the predicted correction values for each set of unbalanced data, and uses minimizing the sum of the prediction accuracies of all correction values as the training objective; train the machine learning model B until the sum of the prediction accuracies reaches convergence and then stop training. The trained machine learning model B is used as the correction recognition model, and the machine learning model B is a polynomial regression model or a support vector machine model.

[0037] An inter-phase imbalance correction device for a distribution system based on energy storage collaboration, which is used to implement the above-mentioned inter-phase imbalance correction method for a distribution system based on energy storage collaboration, and includes a historical data collection module, a collection module, an operating curve prediction module, a correction parameter generation module, a correction module and an energy storage unit; among them, each module is connected by wired and / or wireless means;

[0038] The historical data collection module is used to collect the historical operating data of the inter-phase.

[0039] The collection module is used to collect the actual inter-phase operating curve.

[0040] The operating curve prediction module is used to predict the inter-phase operating curve based on the historical operating data.

[0041] The correction parameter generation module calculates the error coefficient based on the predicted inter-phase operating curve and the actual inter-phase operating curve, generates a corrected inter-phase operating curve based on the error coefficient, and obtains the future inter-phase imbalance time points and correction values based on the corrected inter-phase operating curve.

[0042] The correction module controls the collaboration of the energy storage unit based on the imbalance time points and correction values, and adjusts the inter-phase in the way of injecting or absorbing energy.

[0043] Compared with the prior art, the beneficial effects of the present invention are:

[0044] The present invention collects the historical operating data of the distribution system, predicts the inter-phase operating curve based on the historical operating data, analyzes the error coefficient between the predicted inter-phase operating curve and the actual inter-phase operating curve, generates a corrected inter-phase operating curve based on the error coefficient, extracts the future inter-phase imbalance time points and correction values from the corrected inter-phase operating curve, so as to perform advance correction on the inter-phase of the distribution system and reduce the failure rate of inter-phase imbalance. Description of the Drawings

[0045] Figure 1 It is the flowchart of the inter-phase imbalance correction method for a distribution system based on energy storage collaboration in Embodiment 1 of the present invention;

[0046] Figure 2This is an example diagram of the predicted and actual inter-phase operating curves in Embodiment 1 of the present invention;

[0047] Figure 3 This is a module connection diagram of the inter-phase imbalance correction device for a distribution system based on energy storage cooperation in Embodiment 2 of the present invention;

[0048] Figure 4 This is a relationship diagram of the inter-phase imbalance correction device for a distribution system based on energy storage cooperation applied to the distribution system in Embodiment 2 of the present invention. Detailed implementation manners

[0049] Next, the technical solutions of the present invention will be clearly and completely described in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0050] Embodiment 1

[0051] As Figure 1 and Figure 2 shown, the inter-phase imbalance correction method for a distribution system based on energy storage cooperation includes:

[0052] Collect the historical operating data of the inter-phase of the distribution system. The historical operating data includes H groups of condition data and the inter-phase voltage corresponding to the H groups of condition data. Among them, H is a preset amount of training data, H = 1, 2, 3... H. The condition data in this embodiment covers different time periods, different load conditions, and various factors that may affect the inter-phase voltage, specifically including but not limited to information such as inter-phase voltage values, current values, load sizes, power factors, etc. Preprocess the collected historical operating data, including operations such as data cleaning, removing outliers, and data normalization, to ensure the accuracy and reliability of the data. Predict the inter-phase operating curve based on the historical operating data. The specific method for predicting the inter-phase operating curve based on the historical operating data is to first train a voltage identification model for predicting the inter-phase voltage based on the historical operating data;

[0053] Continuously collect n pieces of operating data of the distribution system at a preset frequency. The operating data of the distribution system includes the same features as the historical operating data, so as to be input into the trained voltage identification model for prediction. The preset frequency in this embodiment is determined by those skilled in the art according to actual needs. For example, the alternating current frequency of each phase of the three-phase electricity is used as the preset frequency. n is an integer greater than 1. Input the n pieces of operating data into the voltage identification model in sequence, and output n predicted inter-phase voltage values;

[0054] Map the n phase voltages in the order of acquisition time in a coordinate system with time as the abscissa and phase voltage as the ordinate, and connect the n phase voltages in sequence to obtain the predicted phase operation curve. In this way, the change trend of the phase voltage over time can be intuitively observed. Refer to Figure 2 the curve marked as Y in

[0055] Specifically, the training method of the voltage recognition model is as follows:

[0056] Collect historical operation data in the experimental environment. The historical operation data includes H groups of condition data and the phase voltages corresponding to the H groups of condition data. That is, in the experimental environment, simulate multiple groups of condition data, run the distribution system with this condition data and record the phase voltage at this time as the phase voltage corresponding to this condition data. In this way, by simulating H groups of different condition data, the phase voltages corresponding to the H groups of condition data can be obtained;

[0057] Convert a group of condition data and the phase voltage corresponding to the condition data into a group of first feature vectors, and use the first feature vectors as the input of the machine learning model A. The machine learning model A outputs the predicted phase voltage for each group of condition data, and takes minimizing the sum of the prediction accuracies of all phase voltages as the training objective; where the calculation formula for the prediction accuracy is: , where is the number of the first feature vector, is the prediction accuracy, is the predicted phase voltage corresponding to the th group of first feature vectors, is the actual phase voltage corresponding to the

[0058] It should be noted that the predicted phase - to - phase operation curve is a curve showing the variation of the phase - to - phase voltage over time predicted by the distribution system based on the current operating data and combined with historical operating data. Specifically, when generating the predicted phase - to - phase operation curve, first, the current operating data of the distribution system is analyzed. These operating data may include the current load conditions, power factor, system topology, etc. At the same time, combined with a large amount of historical operating data, advanced data processing and analysis techniques, such as machine learning algorithms, statistical models, etc., are used to predict the change trend of the future phase - to - phase voltage. The predicted phase - to - phase operation curve generated in this way can provide forward - looking guidance for the operation and management of the system, helping to detect potential problems in advance and take corresponding measures.

[0059] The actual phase - to - phase operation curve is a curve drawn by the distribution system by collecting the phase - to - phase voltage in real - time over time. During the operation of the distribution system, the phase - to - phase voltage data is collected in real - time at a certain frequency through sensors and monitoring devices installed at different positions. These data are recorded in chronological order and a curve with the phase - to - phase voltage as the vertical axis and time as the horizontal axis is drawn. The actual phase - to - phase operation curve reflects the real state of the distribution system during actual operation and is an important basis for evaluating the system performance and stability. By comparing the predicted phase - to - phase operation curve and the actual phase - to - phase operation curve, the differences between the two can be found in a timely manner, thereby determining whether the system operation meets the expectations. If a large difference is found, it may mean that there are abnormal conditions in the system, and it is necessary to further analyze the reasons and take corresponding adjustment measures to ensure the safe, stable and efficient operation of the distribution system.

[0060] Refer to Figure 2 As shown, the actual phase - to - phase operation curve of the distribution system is collected in real - time. Figure 2 In the figure, the curve marked as S is the actual phase - to - phase operation curve. Calculate the error coefficient based on the predicted phase - to - phase operation curve and the actual phase - to - phase operation curve, and generate a corrected phase - to - phase operation curve based on the error coefficient. Specifically, the method for calculating the error coefficient based on the predicted phase - to - phase operation curve and the actual phase - to - phase operation curve is as follows:

[0061] Calculate the sub - error coefficient of the predicted phase - to - phase operation curve and the actual phase - to - phase operation curve. The calculation expression is:

[0062]

[0063] Wherein, represents the sub - error coefficient at the t - th moment of the n - th piece of operating data; is the voltage value of the predicted phase - to - phase operation curve at the t - th moment of the n - th piece of operating data; is the voltage value collected at the t-th moment for the actual phase-to-phase operation curve; the purpose is that through this formula, the sub-error coefficient corresponding to each moment and each piece of operation data can be calculated, reflecting the deviation degree between the predicted value and the actual value;

[0064] Calculate the error coefficient based on n sub-error coefficients, and the calculation expression of the error coefficient is:

[0065] , the purpose is that by averaging all the sub-error coefficients, a comprehensive error coefficient is obtained, representing the prediction error situation of the entire distribution system at a specific moment.

[0066] Furthermore, the method for generating the corrected phase-to-phase operation curve based on the error coefficient is as follows:

[0067] Step 1, calculate the corrected voltage at the (t + L)-th moment based on the error coefficient, that is, predict the corrected voltage at a future moment at the current moment. The corrected voltage is to predict the voltage of the phase-to-phase operation of the distribution system at the future moment, that is, the (t + L)-th moment, after calculating the error based on the predicted phase-to-phase operation curve and the actual phase-to-phase operation curve. L is an integer greater than 1, and the calculation expression is:

[0068] , where is the error coefficient, is the compensation coefficient, which is obtained by those skilled in the art based on a large amount of experimental data and is not specifically limited here. D is the corrected voltage; the purpose is to adjust the voltage value at the current moment by considering the error coefficient and the compensation coefficient to obtain the corrected voltage at the (t + L)-th moment;

[0069] Step 2, repeat Step 1 and continuously update the value of L, and calculate the corrected voltage values of (t + L) after updating in turn to obtain corrected voltage values, , and Connect the corrected voltage values in chronological order, and the corrected phase-to-phase operation curve can be drawn. This curve reflects the predicted situation of the phase-to-phase voltage of the distribution system after correction. By continuously predicting the voltage values at future moments, the operation state of the distribution system can be grasped more accurately, providing a strong basis for subsequent phase-to-phase imbalance correction; obtain the phase-to-phase imbalance time points and correction values at future moments based on the corrected phase-to-phase operation curve, and the imbalance time points and correction values are used as the correction parameters of the energy storage unit.

[0070] Specifically, the method for obtaining the phase-to-phase imbalance time points and correction values at future moments based on the corrected phase-to-phase operation curve is as follows:

[0071] Compare the future moment correction voltage with the preset voltage threshold. If the correction voltage is greater than or less than the preset voltage threshold, it is determined as phase - to - phase imbalance, and mark the corresponding moment of this correction voltage; if the correction voltage is equal to the preset voltage threshold, it is determined as phase - to - phase balance;

[0072] Collect multiple sets of historical correction data. The historical correction data includes imbalance data and the corresponding correction values for the imbalance data. That is, in the experimental environment, simulate multiple sets of imbalance data. The imbalance data includes, but is not limited to, the phase - to - phase voltage values, current values, load magnitudes, power factors, etc. monitored from the power distribution system when phase - electricity imbalance occurs. By simulating imbalance data under different time periods and different load conditions, and then using different correction values to correct the phases, those skilled in the art detect the corrected phases and select the correction value with the best correction effect corresponding to this imbalance data. In this way, by simulating multiple sets of different imbalance data, multiple sets of historical correction data can be obtained;

[0073] Train a correction recognition model for predicting correction values based on the historical correction data;

[0074] Obtain the real - time operation data of the power distribution system, and input the real - time operation data into the correction recognition model to output the correction value.

[0075] More specifically, the training method of the correction recognition model is as follows:

[0076] Convert a set of imbalance data and the corresponding correction value for the imbalance data into a set of second feature vectors;

[0077] Use the second feature vector as the input of the machine learning model B. The machine learning model B outputs the predicted correction value for each set of imbalance data, and takes minimizing the sum of the prediction accuracies of all correction values as the training objective; among them, the calculation formula for the prediction accuracy is: , where g is the number of the second feature vector, is the prediction accuracy, is the predicted correction value corresponding to the g - th group of second feature vectors, is the actual correction value corresponding to the g - th group of second feature vectors; Train the machine learning model B until the sum of the prediction accuracies reaches convergence and then stop training. The trained machine learning model B is used as the correction recognition model;

[0078] It should be noted that the machine learning model A and the machine learning model B are polynomial regression models or support vector machine models.

[0079] Specifically, in this embodiment, the unbalanced time points and correction values that will occur at future times are obtained, and then, based on the response capabilities of the selected energy storage units and load forecasting, compensation operations for the energy storage units are initiated in advance for the unbalanced time points; the aim is that the energy storage units can inject or absorb energy in advance according to the predicted voltage fluctuation trend to avoid the impact when actual imbalances occur.

[0080] Embodiment 2

[0081] Based on the above embodiment, referring to Figure 3 and Figure 4 As shown, the inter-phase imbalance correction device for a distribution system based on energy storage collaboration includes a historical data collection module, a collection module, an operating curve prediction module, a correction parameter generation module, a correction module, and an energy storage unit; among them, each module is connected by wired and / or wireless means;

[0082] The historical data collection module is used to collect historical inter-phase operating data. In this embodiment, the historical operating data includes, but is not limited to, information such as inter-phase voltage values, current values, load sizes, power factors, etc. The historical data collection module includes multiple units, and sensors with the function of collecting information such as inter-phase voltage values, current values, load sizes, power factors, etc. are used. The sensors are deployed on the distribution system, and the specific deployment locations and sensor models are not specifically defined here;

[0083] The collection module is used to collect the actual inter-phase operating curve. The collection module includes a sensor for collecting inter-phase voltage values. The sensor is deployed on the distribution system, and the specific deployment location and sensor model are not specifically defined here. Referring to Figure 2 As shown, the actual inter-phase operating curve can be obtained by plotting a curve as shown in Figure 2 using the collected inter-phase voltage values and the time stamps at the time of collection;

[0084] The operating curve prediction module is used to predict the inter-phase operating curve based on the historical operating data. The specific method is: calculate the sub-error coefficient between the predicted inter-phase operating curve and the actual inter-phase operating curve. The calculation expression is:

[0085]

[0086] where represents the sub-error coefficient at the t-th moment of the n-th piece of operating data; is the voltage value at the t-th moment of the n-th piece of operating data of the predicted inter-phase operating curve; is the voltage value collected at the t-th moment of the actual inter-phase operating curve. The aim is that through this formula, the sub-error coefficient corresponding to each moment and each piece of operating data can be calculated, reflecting the deviation degree between the predicted value and the actual value;

[0087] Calculate the error coefficient based on n sub-error coefficients. The calculation expression of the error coefficient is as follows:

[0088] , aiming to obtain a comprehensive error coefficient by averaging all sub-error coefficients, which represents the prediction error situation of the entire distribution system at a specific moment;

[0089] The correction parameter generation module calculates the error coefficient based on the predicted phase-interphase operation curve and the actual phase-interphase operation curve, generates a corrected phase-interphase operation curve based on the error coefficient, and obtains the interphase imbalance time point and correction value at the future moment based on the corrected phase-interphase operation curve. The specific method is as follows: Step 1, calculate the corrected voltage at time t+L based on the error coefficient, that is, predict the corrected voltage at the future moment at the current moment. The corrected voltage is the voltage of the phase-interphase operation of the distribution system at the future moment, that is, time t+L, after calculating the error based on the predicted phase-interphase operation curve and the actual phase-interphase operation curve. L is an integer greater than 1. The calculation expression is:

[0090] , where is the error coefficient, is the compensation coefficient, which is obtained by those skilled in the art based on a large amount of experimental data and is not specifically limited here. D is the corrected voltage; the aim is to adjust the voltage value at the current moment by considering the error coefficient and the compensation coefficient to obtain the corrected voltage at time t+L;

[0091] Step 2, repeat Step 1 and continuously update the value of L, calculate the corrected voltage values of t+L after updating in sequence, obtain a series of corrected voltage data points, and connect these data points in chronological order to draw the corrected phase-interphase operation curve;

[0092] The correction module controls the cooperation of the energy storage unit based on the imbalance time point and the correction value to adjust the phase-interphase in the way of injecting or absorbing energy; specifically, obtain the imbalance time point and the correction value that appear at the future moment, and then, according to the response ability of the selected energy storage unit and the load prediction, start the compensation operation of the energy storage unit in advance for the imbalance time point; the aim is that the energy storage unit can inject or absorb energy in advance according to the predicted voltage fluctuation trend to avoid the impact when the actual imbalance occurs; in this embodiment, the energy storage unit adopts a device with the function of storing and releasing electric energy such as a battery energy storage system or a supercapacitor, which is not specifically limited here.

[0093] In the above technical solutions provided in the embodiments of the present application, the parts that are the same as the corresponding technical solutions in the prior art in terms of implementation principles are not described in detail to avoid excessive elaboration.

[0094] The specific embodiments described above further elaborate on the object, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only the specific embodiments of the present invention and is 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.

[0095] The above preset parameters or preset thresholds are set by those skilled in the art according to the actual situation or obtained through a large amount of data simulation.

[0096] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for correcting phase imbalance in a power distribution system based on energy storage coordination, characterized in that: include: Collect the historical operation data between phases of the distribution system and predict the phase operation curve based on the historical operation data; Collect the actual phase-to-phase operation curve of the distribution system in real time, calculate the error coefficient based on the predicted phase-to-phase operation curve and the actual phase-to-phase operation curve, and generate the corrected phase-to-phase operation curve based on the error coefficient; Based on the corrected interphase operation curve, the interphase unbalance time point and the correction value at a future moment are obtained, and the unbalance time point and the correction value are used as correction parameters of the energy storage unit.

2. The method for correcting phase imbalance in a power distribution system based on energy storage synergy according to claim 1, characterized in that: Methods for predicting phase-to-phase operating curves based on historical operating data include: A voltage identification model that predicts phase-to-phase voltage based on historical operating data training; Continuously collect n pieces of operation data of the power distribution system at a preset frequency, where n is an integer greater than 1, input the n pieces of operation data into the voltage identification model in sequence, and output n phase-to-phase voltages; The n phase-to-phase voltages are mapped in a coordinate system with time as the horizontal coordinate and the phase-to-phase voltage as the vertical coordinate according to the order of collection time, and the n phase-to-phase voltages are connected in sequence to obtain the predicted phase-to-phase operation curve.

3. The method for correcting phase imbalance in a power distribution system based on energy storage synergy according to claim 2, characterized in that: The historical operation data includes H groups of condition data and phase-to-phase voltages corresponding to the H groups of condition data; wherein H is a preset amount of training data, H=1, 2, 3...H.

4. The method for correcting phase imbalance in a power distribution system based on energy storage coordination according to claim 3 is characterized in that: The training method of the voltage recognition model is: Converting a set of conditional data and the phase-to-phase voltage corresponding to the conditional data into a set of first eigenvectors, and using the first eigenvectors as inputs of a machine learning model A, wherein the machine learning model A uses the predicted phase-to-phase voltage for each set of conditional data as output and uses minimizing the sum of the prediction accuracies of all phase-to-phase voltages as a training objective; The machine learning model A is trained until the sum of the prediction accuracies reaches convergence, and the training is stopped. The machine learning model A obtained by training is used as a voltage recognition model. The machine learning model A is a polynomial regression model or a support vector machine model.

5. The method for correcting phase imbalance in a power distribution system based on energy storage coordination according to claim 1, characterized in that: The predicted phase-to-phase operation curve is a curve of the phase-to-phase voltage change over time predicted by the power distribution system according to the current operation data and combined with the historical operation data; The actual phase-to-phase operation curve is a curve drawn by collecting the phase-to-phase voltage changes over time in real time by the power distribution system.

6. The method for correcting phase imbalance in a power distribution system based on energy storage synergy according to claim 2, characterized in that: The method for calculating the error coefficient based on the predicted phase-to-phase operation curve and the actual phase-to-phase operation curve is: Calculate the sub-error coefficients of the predicted phase-to-phase operation curve and the actual phase-to-phase operation curve. The calculation expression is: ； in, It represents the sub-error coefficient at the tth time of the nth running data; It is the voltage value of the predicted phase-to-phase operation curve at the nth operation data and the tth time; is the voltage value collected at the tth moment by the actual phase-to-phase operation curve; The error coefficient is calculated based on n sub-error coefficients. The error coefficient calculation expression is: ,in is the error coefficient.

7. The method for correcting phase imbalance in a power distribution system based on energy storage coordination according to claim 6, characterized in that: The method for generating the corrected phase-to-phase operation curve based on the error coefficient is: Step 1: Calculate the correction voltage at time t+L based on the error coefficient, where L is an integer greater than 1, and the calculation expression is: , is the compensation coefficient, D is the correction voltage; Step 2: Repeat step 1 and continue to update the value of L, and calculate the corrected voltage value of t+L after the update to obtain A correction voltage value, , and By connecting the correction voltage values ​​in chronological order, the correction phase-to-phase operation curve can be drawn.

8. The method for correcting phase imbalance in a power distribution system based on energy storage synergy according to claim 7, characterized in that: The method for obtaining the future phase imbalance time point and correction value based on the corrected phase operation curve is as follows: Compare the corrected voltage at a future moment with the preset voltage threshold. If the corrected voltage is greater than or less than the preset voltage threshold, it is determined to be phase unbalanced, and the corresponding moment of the corrected voltage is marked; if the corrected voltage is equal to the preset voltage threshold, it is determined to be phase balanced; Collect multiple sets of historical correction data, the historical correction data including imbalance data and correction values ​​corresponding to the imbalance data; A correction recognition model for predicting correction values ​​is trained based on historical correction data; Obtain the real-time operation data of the power distribution system, input the real-time operation data into the correction identification model to output the correction value.

9. The method for correcting phase imbalance in a power distribution system based on energy storage synergy according to claim 8, characterized in that: The training method of the correction recognition model is: Converting a set of unbalanced data and correction values ​​corresponding to the unbalanced data into a set of second eigenvectors; The second eigenvector is used as an input of a machine learning model B, wherein the machine learning model B outputs a predicted correction value for each group of imbalanced data, and minimizes the sum of the prediction accuracies of all correction values ​​as a training objective; The machine learning model B is trained until the sum of the prediction accuracies reaches convergence, and the training is stopped. The trained machine learning model B is used as a correction recognition model. The machine learning model B is a polynomial regression model or a support vector machine model.

10. A distribution system interphase imbalance correction device based on energy storage synergy, which is used to implement the distribution system interphase imbalance correction method based on energy storage synergy as described in any one of claims 8-9, characterized in that: It includes a historical data collection module, an acquisition module, an operation curve prediction module, a correction parameter generation module, a correction module and an energy storage unit; wherein each module is connected by wire and / or wireless means; Historical data collection module, used to collect historical operation data between phases; A collection module is used to collect actual phase-to-phase operation curves; An operation curve prediction module is used to predict the phase operation curve based on historical operation data; A correction parameter generation module calculates an error coefficient based on the predicted interphase operation curve and the actual interphase operation curve, generates a correction interphase operation curve based on the error coefficient, and obtains the interphase imbalance time point and correction value at a future moment based on the correction interphase operation curve; The correction module controls the coordination of the energy storage units based on the unbalanced time point and the correction value, and adjusts the phases by injecting or absorbing energy.

Images