CN-122026489-A - Flywheel energy storage active phase modulation control method, system, equipment and medium

Abstract

The invention discloses a flywheel energy storage active phase modulation control method, a system, equipment and a medium, wherein the method comprises the following steps of collecting multi-source power data of a power grid to obtain preprocessed phasor data; the method comprises the steps of inputting the preprocessed phasor data into a first network model, predicting a voltage phasor track, a power angle track and a frequency track in a preset time window in the future, respectively carrying out corresponding evaluation analysis, outputting corresponding evaluation analysis results, respectively calculating an active power injection instruction in a power angle supporting mode, a reactive power injection instruction in a voltage phase correction mode or an anti-phase power injection instruction in an oscillation suppression mode according to the evaluation analysis results, and controlling a flywheel body to carry out power output. By predicting the phasor track of the power grid, the risk can be predicted before instability occurs, and control measures can be actively taken, so that the disadvantage of traditional post-event response is changed into the disadvantage of being passive to active, and the timeliness and effectiveness of control are improved.

Inventors

• WEN XIANKUI
• HUANG ZHENG
• SHI ZHENGJUN
• WU WEI
• FAN LEI
• ZENG RONG
• YANG TAO
• WU JIANRONG
• CHEN JUNWEI
• GU TINGBIN
• ZHANG HOUYI
• FAN QIANG
• LI YUXIN
• WU YINGHAO
• Ai Bojun
• PANG LINGRONG
• CHEN YUANYUAN
• YE HUAYANG
• LI BOWEN
• LIU SHI
• YANG YI

Assignees

• 贵州电网有限责任公司

Dates

Publication Date

20260512

Application Date

20251226

Claims (10)

1. 1. The flywheel energy storage active phase modulation control method is characterized by comprising the following steps of: Collecting multi-source power data of a power grid, and preprocessing the collected multi-source power data to obtain preprocessed phasor data; inputting the preprocessed phasor data into a first network model, and predicting a voltage phasor track, a power angle track and a frequency track in a future preset time window; respectively carrying out corresponding evaluation analysis by predicting the obtained voltage phasor track, the power angle track and the frequency track, and outputting a corresponding evaluation analysis result; according to the evaluation analysis result, respectively calculating an active power injection instruction in a power angle supporting mode, a reactive power injection instruction in a voltage phase correction mode or an anti-phase power injection instruction in an oscillation suppression mode, and controlling the flywheel body to output power; The method comprises the steps of monitoring the rotating speed, the temperature and the actual output power of a flywheel body, comparing the actual output power with a predicted voltage phasor track, a power angle track and a frequency track, calculating a prediction error, and feeding the prediction error back to a first network model for parameter updating.
2. 2. The flywheel energy storage active phase modulation control method of claim 1, wherein the multi-source power data comprises grid voltage phasor, current phasor, and power phasor data; the preprocessing comprises filtering denoising, missing data interpolation and outlier rejection; The filtering denoising adopts a Kalman filtering algorithm to eliminate measurement noise; the missing data interpolation adopts a cubic spline interpolation method to fill in missing data caused by communication delay or data packet loss; And the outlier rejection is identified by adopting a 3 sigma criterion of sliding window statistics, and abnormal data points are rejected.
3. 3. The flywheel energy storage active phase modulation control method of claim 2, wherein the evaluation analysis comprises power angle stability evaluation, voltage phase analysis and subsynchronous oscillation detection; The method for evaluating the power angle stability comprises the following steps: calculating the power angle difference and the power angle difference change rate between adjacent generator sets according to the predicted power angle track; outputting a power angle instability risk signal when the absolute value of the power angle difference is larger than a power angle difference threshold value or the absolute value of the power angle difference change rate is larger than a power angle difference change rate threshold value; the method for analyzing the voltage phase comprises the following steps: monitoring the offset and the change rate of the voltage phase of each node according to the predicted voltage phasor track; outputting a voltage fluctuation risk signal when the voltage phase offset exceeds a voltage phase offset threshold or the voltage phase change rate exceeds a voltage phase change rate threshold; the subsynchronous oscillation detection method comprises the following steps: performing short-time Fourier transform on the predicted power angle track and the predicted frequency track, and identifying an oscillation component; And outputting a subsynchronous oscillation risk signal when the amplitude of the oscillation component exceeds an oscillation amplitude threshold and the duration exceeds an oscillation duration threshold.
4. 4. The flywheel energy storage active phase modulation control method according to claim 3, wherein when the evaluation analysis result is a power angle instability risk signal, a power angle support mode is started, and an active power injection instruction is calculated; When the evaluation analysis result is a voltage fluctuation risk signal, starting a voltage phase correction mode, and calculating a reactive power injection instruction; And when the evaluation analysis result is a subsynchronous oscillation risk signal, starting an oscillation suppression mode, extracting an oscillation dominant frequency and an oscillation phase, and calculating an anti-phase power injection instruction.
5. 5. The flywheel energy storage active phase modulation control method of claim 4, wherein the loss function of the first network model Expressed as: ; Wherein, the The loss is fitted to the data and, As a residual of the physical equation, Is a balance coefficient; The physical equation residual errors comprise generator swing equation residual errors and node power balance equation residual errors; The generator roll equation is expressed as: ; ; Wherein, the Is the power angle of the power point, In order to be able to achieve an angular velocity, In order to synchronize the angular velocity of the beam, Is the time constant of inertia, which is the time constant of inertia, For the mechanical power to be applied, For the purpose of electromagnetic power, Is a damping coefficient; The node power balance equation is that And 。
6. 6. The flywheel energy storage active phase modulation control method of claim 5, wherein the prediction error The calculation method of (1) is expressed as follows: ; Wherein, the For the grid phasor measurement corresponding to the actual output power, And the voltage phasor track, the power angle track and the frequency track corresponding values are predicted for the first network model.
7. 7. The flywheel energy storage active phase modulation control method of claim 6, wherein the parameter update employs a random gradient descent algorithm, and the update formula is expressed as: ; Wherein, the To update the first network model parameters before they are updated, For the updated first network model parameters, η is the learning rate, Gradient of prediction error for the loss function.
8. 8. A flywheel energy storage active phase modulation control system employing the method of any of claims 1-7, comprising: The synchronous phasor measurement unit is used for collecting multi-source power data, preprocessing the multi-source power data and outputting preprocessed phasor data; the phasor track prediction unit is used for predicting a voltage phasor track, a power angle track and a frequency track according to the preprocessed phasor data; The instability risk assessment unit is used for carrying out assessment analysis according to the voltage phasor track, the power angle track and the frequency track and outputting an assessment analysis result; The phase modulation control law calculation unit is used for calculating an active power injection instruction, a reactive power injection instruction or an anti-phase power injection instruction according to the evaluation analysis result and controlling the flywheel body to output power; The state monitoring and feedback unit is used for calculating a prediction error and feeding back the prediction error to the phasor track prediction unit for updating parameters of the first network model.
9. 9. An electronic device, comprising: A memory and a processor; The memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions, which when executed by the processor, implement the steps of the flywheel energy storage active phase modulation control method according to any one of claims 1 to 7.
10. 10. A computer readable storage medium storing computer executable instructions which when executed by a processor implement the steps of the flywheel energy storage active phase modulation control method of any of claims 1 to 7.

Description

Flywheel energy storage active phase modulation control method, system, equipment and medium Technical Field The invention relates to the technical field of control of power systems, in particular to a flywheel energy storage active phase modulation control method, a system, equipment and a medium. Background With the large-scale grid connection of new energy and the wide application of power electronic equipment, dynamic stability challenges faced by a power system are increasingly serious. The problems of power angle instability, voltage fluctuation, subsynchronous oscillation and the like seriously threaten the safe operation of a power grid, and become a key bottleneck for restricting the high-quality development of a power system. The existing power grid stability control method mainly adopts a passive response strategy, namely, corresponding control measures are started after system abnormality is detected. The method has the defects of lag response, limited control effect and the like, and is difficult to meet the requirements of a novel power system on quick response and active defense. The flywheel energy storage system has become an important means for frequency modulation, voltage regulation and stable control of the power grid due to the advantages of high response speed, high power density, long cycle life and the like. However, most of the existing flywheel energy storage control strategies are post-response control, the quick response characteristic of the flywheel energy storage control strategies cannot be fully exerted, and the advanced prevention of dynamic instability of the power grid is not apprehended. The synchronous phasor measurement unit can provide high-precision and time-synchronous power grid phasor data, and provides a technical basis for dynamic monitoring of the power grid. By combining an advanced machine learning method, particularly a physical information neural network, accurate prediction of the phasor evolution track of the power grid can be realized. How to organically combine phasor track prediction with flywheel energy storage control to realize advanced sensing and active modulation of the risk of power grid instability, no mature technical scheme exists at present. Disclosure of Invention The present invention has been made in view of the above-described problems occurring in the prior art. Therefore, the invention provides a flywheel energy storage active phase modulation control method, a system, equipment and a medium, which solve the problems that the existing power grid stability control mode has response lag and mostly has passive post-response, and the problems of dynamic instability such as power angle instability, voltage fluctuation, subsynchronous oscillation and the like are difficult to predict in advance and actively inhibit. In order to solve the technical problems, the invention provides the following technical scheme: The invention provides a flywheel energy storage active phase modulation control method, which comprises the following steps of collecting multi-source power data of a power grid, preprocessing the collected multi-source power data to obtain preprocessed phasor data, inputting the preprocessed phasor data into a first network model, predicting a voltage phasor track, a power angle track and a frequency track in a preset time window in the future, respectively carrying out corresponding evaluation analysis through the predicted voltage phasor track, the power angle track and the frequency track, outputting corresponding evaluation analysis results, respectively calculating an active power injection command in a power angle support mode, a reactive power injection command in a voltage phase correction mode or an anti-phase power injection command in an oscillation suppression mode according to the evaluation analysis results, controlling a flywheel body to carry out power output, monitoring the rotating speed, the temperature and the actual output power of the flywheel body, comparing the actual output power with the predicted voltage phasor track, the power angle track and the frequency track, calculating a prediction error, and feeding back the prediction error to the first network model to carry out parameter updating. The flywheel energy storage active phase modulation control method is characterized in that the multisource power data comprises power grid voltage phasor, current phasor and power phasor data, the preprocessing comprises filtering denoising, missing data interpolation and outlier rejection, the filtering denoising adopts a Kalman filtering algorithm to eliminate measurement noise, the missing data interpolation adopts a cubic spline interpolation method to fill in missing data caused by communication delay or data packet loss, and the outlier rejection adopts 3 sigma criterion recognition of sliding window statistics and rejects abnormal data points. As a preferable scheme of the flywheel energy storage active phase