New energy station primary frequency modulation control method considering power grid fault characteristics

Abstract

The invention discloses a new energy station primary frequency modulation control method considering power grid fault characteristics, and relates to the technical field of smart power grids, comprising the following steps: collecting operation data of a power grid, and preprocessing the operation data; constructing a fault prediction model based on historical power grid operation data and fault data, inputting the preprocessed data into the fault prediction model, and generating a prediction result; adjusting the charge state of the energy storage equipment according to the prediction result; combining the adjusted charge state of the energy storage equipment with power grid operation data collected in real time, and analyzing the real-time monitoring data to extract fault feature information; based on the fault feature information and the adjusted charge state of the energy storage device, dynamically distributing the frequency modulation response priority of the energy storage device, and generating an instant frequency modulation power instruction of the energy storage device; and dynamically adjusting the power output of the energy storage equipment according to the instant frequency modulation power instruction. The instant frequency modulation power instruction is generated according to the calculated frequency modulation response priority of the energy storage equipment, and frequency modulation is accurately carried out.

Description

Technical Field

[0001] The present invention relates to the field of smart grid technology, and in particular to a primary frequency regulation control method for a new energy station taking into account grid fault characteristics. Background Art

[0002] With the rapid development of renewable energy power generation technology, the proportion of new energy stations in the power system is increasing. Due to the intermittent and random nature of wind and solar renewable energy, their large-scale access has brought new challenges to the stability of grid frequency. The traditional primary frequency regulation control method mainly relies on the mechanical inertia of the generator to respond to frequency deviations. This control method faces huge challenges when facing the high proportion of new energy penetration.

[0003] In the field of smart grids, existing frequency regulation control strategies often lack consideration of grid fault characteristics. The frequency regulation response of energy storage devices is not timely and cannot fully play their regulatory role. Current frequency regulation control methods usually use simple weight distribution or linear functions to calculate the frequency regulation power instructions of energy storage devices. This method is difficult to adapt to complex grid operation conditions and changeable fault characteristics. The management of the charge state of energy storage devices is also relatively extensive, and the information cannot be fully utilized to optimize the frequency regulation behavior of energy storage devices. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a new energy station primary frequency regulation control method taking into account grid fault characteristics to solve the problem of untimely and inaccurate frequency regulation response of energy storage equipment due to lack of consideration of grid fault characteristics.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a primary frequency regulation control method of a new energy station taking into account the fault characteristics of a power grid, which includes collecting the operation data of the power grid and preprocessing the data;

[0008] Building a fault prediction model based on historical power grid operation data and fault data, inputting the preprocessed data into the fault prediction model to generate prediction results;

[0009] Adjust the state of charge of the energy storage device according to the prediction results;

[0010] Combine the adjusted state of charge of the energy storage device with the real-time collected grid operation data, analyze the real-time monitoring data and extract fault feature information;

[0011] Based on the fault feature information and the charge state of the energy storage device after adjustment, the frequency modulation response priority of the energy storage device is dynamically allocated, and an instant frequency modulation power instruction of the energy storage device is generated;

[0012] According to the instant frequency modulation power instruction, the power output of the energy storage device is dynamically adjusted.

[0013] As a preferred solution of the primary frequency regulation control method of a new energy station taking into account the fault characteristics of the power grid as described in the present invention, the operation data of the power grid is collected and preprocessed, including the following steps:

[0014] The collected grid operation data include frequency deviation, frequency change rate and voltage fluctuation, and the collected grid operation data are filtered and outliers are eliminated.

[0015] As a preferred solution of the primary frequency regulation control method of a new energy station taking into account the grid fault characteristics of the present invention, wherein: constructing a fault prediction model based on historical grid operation data and fault data includes the following steps:

[0016] Align the time series of historical power grid operation data and fault data;

[0017] The preprocessed power grid operation data is segmented according to fixed time windows aligned with the time series, and feature vectors are extracted from the data in each time window;

[0018] A timing model based on long short-term memory network is selected to build a fault prediction model.

[0019] As a preferred solution of the primary frequency regulation control method of a new energy station taking into account the fault characteristics of the power grid as described in the present invention, the pre-processed data is input into the fault prediction model, and the generation of the prediction result includes the following steps:

[0020] The preprocessed feature vector is output to the fault prediction model to obtain the power grid fault prediction result, which is expressed as:

[0021]

[0022] Among them, Q f (t) is the predicted value of power grid fault at time t, σ is the output conversion value, X is the feature vector, H j (t) is the state of the jth unit in the output at time t, w j is the weight coefficient of the state of the jth unit, b is the bias term for adjusting the baseline level, α is the bias term for adjusting the baseline level, T k (t) is the value of the state of the kth unit after nonlinear transformation, z k is the weight coefficient of the kth unit state, v lis the weight coefficient of the lth feature in the feature vector X, j is the index of the output unit, l is the index of the nonlinear transformation parameter in the feature vector X, N is the dimension in the feature vector X, and F l (X) is the nonlinear transformation of the lth feature of the feature vector X, and K is the number of output units.

[0023] As a preferred solution of the primary frequency regulation control method of the new energy station taking into account the grid fault characteristics of the present invention, wherein: according to the prediction result, adjusting the charge state of the energy storage device includes the following steps: obtaining the current charge state of the energy storage device, calculating according to the current grid operation state and the fault prediction value

[0024] Head

[0025] The standard state of charge expression is:

[0026]

[0027] Among them, S t+1 is the target state of charge of the energy storage device at time t+1, S t is the current state of charge of the energy storage device at t, η is the adjustment coefficient, and t is the time point;

[0028] Adjusting the state of charge of the energy storage device according to the calculated target state of charge;

[0029] When S t+1 >S t When the charging process is started, the state of charge of the energy storage device is changed from S t Adjust to S t+1 , increase the charging power of the energy storage device until the state of charge reaches S t+1 ;

[0030] When S t+1 >S t When the discharge process is started, the state of charge of the energy storage device is changed from S t Adjust to S t+1 , increase the discharge power of the energy storage device until the state of charge reaches S t+1 ;

[0031] When S t+1 =S t The current state of charge remains unchanged.

[0032] As a preferred solution of the primary frequency regulation control method of the new energy station taking into account the grid fault characteristics of the present invention, wherein: combining the adjusted state of charge of the energy storage device with the real-time collected grid operation data, analyzing the real-time monitoring data to extract fault characteristic information includes the following steps:

[0033] The adjusted state of charge of the energy storage device is combined with the real-time collected grid operation frequency deviation, frequency change rate and voltage fluctuation data, and a comprehensive fault characteristic value is generated using nonlinear function fusion. The expression is:

[0034]

[0035] Among them, O fault (t) is the fault characteristic value at time point t, GΔ(t) is the frequency deviation at time point t,

[0036] U df (t) is the frequency change rate at time point t, R V (t) is the voltage fluctuation at time point t, and β1 is the adjustment coefficient.

[0037] As a preferred solution of the primary frequency regulation control method of the new energy station taking into account the grid fault characteristics of the present invention, wherein: based on the fault characteristic information and the charge state of the energy storage device after adjustment, the frequency regulation response priority of the energy storage device is dynamically allocated, and the instantaneous frequency regulation power instruction of the energy storage device is generated, including the following steps:

[0038] The frequency modulation response priority of the energy storage device is calculated based on the fault characteristic value and the charge state of the energy storage device after adjustment. The expression is:

[0039] Z priority (t) = (m1·O fault (t)+m2)·(γ1·S t+1 +γ2·S t+1 );

[0040] Among them, Z priority (t) is the frequency modulation response priority of the energy storage device at time point t, m1 is the influence of the control fault characteristic value on the frequency modulation response priority, m2 is the constant term, γ1 is the influence of the control state of charge on the frequency modulation response priority, and γ2 is the secondary influence of the control state of charge on the frequency modulation response priority;

[0041] According to the calculated frequency modulation response priority, the instant frequency modulation power instruction of the energy storage device is generated, and the expression is:

[0042] A freq (t) = C max ·Z priority (t);

[0043] Among them, A freq (t) is the instantaneous frequency modulation power instruction at time point t, C max is the maximum frequency modulation power of the energy storage device.

[0044] As a preferred solution of the primary frequency regulation control method of a new energy station taking into account the grid fault characteristics of the present invention, wherein: dynamically adjusting the power output of the energy storage device according to the instant frequency regulation power instruction includes the following steps:

[0045] According to the instant frequency modulation power instruction and the current power output, the power adjustment amount of the energy storage device is calculated. The expression is:

[0046] Δd(t)=A freq (t)-Y current (t);

[0047] Where ΔD(t) is the power adjustment at time point t, Y current (t) is the current power output at time point t;

[0048] When ΔD(t)>0, it means that the power output of the energy storage device needs to be increased;

[0049] When ΔD(t)<0, it means that the power output of the energy storage device needs to be reduced;

[0050] When ΔD(t)=0, it means that the current power output has met the frequency modulation requirement and no adjustment is required.

[0051] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the primary frequency regulation control method of a new energy station taking into account grid fault characteristics as described in the first aspect of the present invention is implemented.

[0052] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the primary frequency regulation control method of a new energy station taking into account grid fault characteristics as described in the first aspect of the present invention.

[0053] The beneficial effects of the present invention are as follows: by collecting grid operation data, filtering and eliminating abnormal values ​​of the collected grid operation data, the reliability and consistency of the data are improved, the preprocessed feature vector is output to the fault prediction model to obtain the grid fault prediction result, which provides a reliable basis for frequency modulation control, and the calculated grid fault prediction value is used to calculate the target charge state according to the current grid operation state and the fault prediction value to ensure timely provision of frequency modulation support in the event of a fault, and the adjusted energy storage device state and voltage fluctuation data are combined to generate a comprehensive fault feature value, and the comprehensiveness and accuracy of the fault characteristics are improved through multi-parameter fusion, and an instant frequency modulation power instruction is generated according to the calculated frequency modulation response priority of the energy storage device to ensure fast and accurate frequency modulation in the event of a fault, and the power output of the energy storage device is dynamically adjusted according to the instant frequency modulation power instruction to ensure that the frequency modulation demand is met. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0055] Figure 1 This is a flow chart of the primary frequency regulation control method for a new energy station taking into account the characteristics of power grid faults in Example 1.

[0056] Figure 2 It is a schematic diagram of a flow chart of the instantaneous frequency regulation power instruction of the primary frequency regulation control method of the new energy station in Example 1 and the grid fault characteristics. DETAILED DESCRIPTION

[0057] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0058] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0059] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0060] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a primary frequency regulation control method for a new energy station taking into account the fault characteristics of a power grid, comprising the following steps:

[0061] S1. Collecting the operation data of the power grid and preprocessing it includes the following steps:

[0062] Collect grid operation data including frequency deviation, frequency change rate and voltage fluctuation, filter the collected grid operation data and remove abnormal values;

[0063] Furthermore, high-frequency noise is removed through filtering, making the data smoother and more stable, reducing the impact of noise on subsequent analysis, and outlier removal eliminates abnormal data caused by equipment failure, improving data reliability and consistency.

[0064] S2. Building a fault prediction model based on historical power grid operation data and fault data includes the following steps:

[0065] Align the time series of historical power grid operation data and fault data;

[0066] The preprocessed power grid operation data is segmented according to fixed time windows aligned with the time series, and feature vectors are extracted from the data in each time window;

[0067] A time series model based on long short-term memory network is selected to build a fault prediction model;

[0068] Furthermore, through time series alignment, the timestamps of all data are ensured to be consistent, avoiding errors caused by time misalignment. Through fixed time window segmentation and feature extraction, key features are extracted from each time window, improving the representativeness and information density of the data.

[0069] S3, inputting the preprocessed data into the fault prediction model, generating the prediction results includes the following steps:

[0070] The preprocessed feature vector is output to the fault prediction model to obtain the power grid fault prediction result, which is expressed as:

[0071]

[0072] Among them, Q f (t) is the predicted value of power grid fault at time t, σ is the output conversion value, X is the feature vector, H j (t) is the state of the jth unit in the output at time t, w jis the weight coefficient of the state of the jth unit, b is the bias term for adjusting the baseline level, α is the bias term for adjusting the baseline level, T k (t) is the value of the state of the kth unit after nonlinear transformation, z k is the weight coefficient of the kth unit state, v l is the weight coefficient of the lth feature in the feature vector X, j is the index of the output unit, l is the index of the nonlinear transformation parameter in the feature vector X, N is the dimension in the feature vector X, and F l (X) is the nonlinear transformation of the lth feature of the feature vector X, and K is the number of output units;

[0073] Furthermore, the feature vector X in each time window is arranged in chronological order, and the feature vector X is input into the LSTM model;

[0074] The output of the LSTM layer is weighted and summed, and the bias term b is added. The formula is:

[0075]

[0076] The nonlinear transformation results of the eigenvectors are weighted summed, and the formula is:

[0077] The nonlinear transformation results output by the LSTM layer are weighted and summed, and the bias term a is added. The formula is:

[0078] The denominator is in the form of an exponential function, which is used to adjust the strength of the nonlinear transformation. The expression is:

[0079] Through complex nonlinear transformations and weighted summations, the prediction results are made more accurate and the prediction ability of the model is improved. The introduction of multiple nonlinear transformations and weight coefficients enhances the model's expressiveness and generalization capabilities. High-quality fault prediction models can quickly generate prediction results, enabling energy storage devices to respond in a timely manner. Accurate fault prediction can provide early warning of potential faults, allowing energy storage devices to be prepared in advance, thereby enhancing the reliability and stability of energy storage devices.

[0080] S4. According to the prediction results, adjusting the state of charge of the energy storage device includes the following steps:

[0081] Obtain the current state of charge of the energy storage device and calculate it based on the current grid operation status and fault prediction value

[0082] Head

[0083] The standard state of charge expression is:

[0084]

[0085] Among them, S t+1 is the target state of charge of the energy storage device at time t+1, S t is the current state of charge of the energy storage device at t, η is the adjustment coefficient, and t is the time point;

[0086] Adjusting the state of charge of the energy storage device according to the calculated target state of charge;

[0087] When S t+1 >S t When the charging process is started, the state of charge of the energy storage device is changed from S t Adjust to S t+1 , increase the charging power of the energy storage device until the state of charge reaches S t+1 ;

[0088] When S t+1 t When the discharge process is started, the state of charge of the energy storage device is changed from S t Adjust to S t+1 , increase the discharge power of the energy storage device until the state of charge reaches S t+1 ;

[0089] When S t+1 =S t The current state of charge remains unchanged.

[0090] Furthermore, after using the calculated power grid fault prediction value, the prediction value has a value range of [0, 1];

[0091] When Q f When (t) is close to 0, the probability of grid failure is low and the target state of charge S t+1 Will be close to the current state of charge S t , the state of charge of the energy storage device does not change much;

[0092] When Q f When (t) is close to 0, the probability of grid failure is high, and the target state of charge S t+1 Will increase significantly, and the state of charge of energy storage devices will be adjusted to a higher level to provide more backup energy in the event of a fault;

[0093] When S t+1 >S t When the amount of electricity required is calculated, the expression is ΔE charge =(S t+1 -S t )×total capacity;

[0094] Where, ΔE charge For the increased amount of electricity; ​

[0095] According to the charging efficiency and maximum charging power, determine the charging time, set the charging controller, start the charging process, and monitor the charging status until the state of charge reaches S t+1 ;

[0096] When S t+1 t When the amount of electricity required to be reduced is calculated, the expression is, ΔE discharge =(S t -S t+1 )×total capacity;

[0097] Where, ΔE discharge To reduce the amount of electricity;

[0098] Set the discharge controller, start the discharge process, and monitor the discharge status until the state of charge reaches S t+1 ;

[0099] When S t+1 =S t When the battery is in the state of charge, the current state of charge remains unchanged and no charging or discharging operations are performed.

[0100] S5, combining the adjusted state of charge of the energy storage device with the real-time collected grid operation data, analyzing the real-time monitoring data to extract fault feature information includes the following steps:

[0101] The adjusted state of charge of the energy storage device is combined with the real-time collected grid operation frequency deviation, frequency change rate and voltage fluctuation data, and a comprehensive fault characteristic value is generated using nonlinear function fusion. The expression is:

[0102]

[0103] Among them, O fault (t) is the fault characteristic value at time point t, GΔ(t) is the frequency deviation at time point t, U df (t) is the frequency change rate at time point t, R V (t) is the voltage fluctuation at time point t, β1 is the adjustment coefficient;

[0104] Further, Part I Taking into account the influence of frequency deviation and frequency change rate, the larger the frequency deviation, the larger the numerator, the larger the frequency change rate, the smaller the denominator, and the larger the overall value;

[0105] Part 2 The influence of voltage fluctuation and the state of charge of the energy storage device is taken into account. The greater the voltage fluctuation, the larger the numerator; the higher the state of charge of the energy storage device, the larger the denominator, and the smaller the overall value.

[0106] ​S6, based on the fault feature information and the state of charge of the energy storage device after adjustment, dynamically allocating the frequency modulation response priority of the energy storage device, and generating the instant frequency modulation power instruction of the energy storage device includes the following steps:

[0107] The frequency modulation response priority of the energy storage device is calculated based on the fault characteristic value and the charge state of the energy storage device after adjustment. The expression is:

[0108] Z priority (t) = (m1·O fault (t)+m2)·(γ1·S t+1 +γ2·S t+1 );

[0109] Among them, Z priority (t) is the frequency modulation response priority of the energy storage device at time point t, m1 is the influence of the control fault characteristic value on the frequency modulation response priority, m2 is the constant term, γ1 is the influence of the control state of charge on the frequency modulation response priority, and γ2 is the secondary influence of the control state of charge on the frequency modulation response priority;

[0110] According to the calculated frequency modulation response priority, the instant frequency modulation power instruction of the energy storage device is generated, and the expression is:

[0111] A freq (t) = C max ·Z priority (t);

[0112] Among them, A freq (t) is the instantaneous frequency modulation power instruction at time point t, C max is the maximum frequency modulation power of the energy storage device;

[0113] Furthermore, when the fault characteristic value P priority (t), when it is larger, it means that the power grid has a higher risk of failure. fault The value of (t)+m2 will be larger, thus increasing the priority of the FM response;

[0114] One-time impact γ1·S t+1 : When the state of charge of the energy storage device is high, it indicates that the energy storage device has sufficient energy reserves and can provide more frequency modulation support, so the frequency modulation response priority is higher;

[0115] Secondary impact γ2·S t+1 : By introducing the quadratic term, the influence of the state of charge can be further enhanced or weakened. When γ2 is positive, the growth rate of the frequency modulation response priority increases with the increase of the state of charge. When γ2 is negative, the growth rate of the frequency modulation response priority slows down with the increase of the state of charge.

[0116] S7, dynamically adjusting the power output of the energy storage device according to the instant frequency modulation power instruction includes the following steps:

[0117] According to the instant frequency modulation power instruction and the current power output, the power adjustment amount of the energy storage device is calculated. The expression is:

[0118] Δd(t)=A freq (t)-Y current (t);

[0119] Where ΔD(t) is the power adjustment at time point t, Y current (t) is the current power output at time point t;

[0120] When ΔD(t)>0, it means that the power output of the energy storage device needs to be increased;

[0121] When ΔD(t)<0, it means that the power output of the energy storage device needs to be reduced;

[0122] When ΔD(t) = 0, it means that the current power output has met the frequency regulation requirements and no adjustment is required;

[0123] Furthermore, when ΔP(t)>0, the power ΔP(t) that needs to be increased is calculated, and the time and method of power adjustment are determined according to the maximum charge and discharge rate of the energy storage device and the current state of charge. The power controller is set to start the power adjustment process to monitor the power output until P is reached. freq (t);

[0124] When ΔP(t)<0, calculate the power that needs to be reduced ΔP(t), determine the time and method of power adjustment according to the maximum charge and discharge rate of the energy storage device and the current state of charge, and set the power controller to start the power adjustment process to monitor the power output until P is reached. freq (t);

[0125] When ΔP(t)=0, it means that the current power output has met the frequency modulation requirement and no adjustment is required to keep the current power output unchanged.

[0126] This embodiment also provides a computer device, which is suitable for the case of a primary frequency regulation control method for a new energy station taking into account the characteristics of a power grid fault, comprising: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the primary frequency regulation control method for a new energy station taking into account the characteristics of a power grid fault as proposed in the above embodiment.

[0127] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0128] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the primary frequency regulation control method of a new energy station taking into account the fault characteristics of the power grid as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0129] In summary, the present invention collects grid operation data, filters the collected grid operation data and removes outliers, thereby improving the reliability and consistency of the data, outputs the preprocessed feature vector to the fault prediction model to obtain a grid fault prediction result, and provides a reliable basis for frequency modulation control. The calculated grid fault prediction value is used to calculate the target charge state according to the current grid operation state and the fault prediction value to ensure timely provision of frequency modulation support in the event of a fault. The adjusted energy storage device state and voltage fluctuation data are combined to generate a comprehensive fault feature value, and the comprehensiveness and accuracy of the fault characteristics are improved through multi-parameter fusion. An instant frequency modulation power instruction is generated according to the calculated frequency modulation response priority of the energy storage device to ensure fast and accurate frequency modulation in the event of a fault. The power output of the energy storage device is dynamically adjusted according to the instant frequency modulation power instruction to ensure that the frequency modulation demand is met.

[0130] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A primary frequency modulation control method for a new energy station taking into account the characteristics of power grid faults, characterized in that: include, Collect the operation data of the power grid and pre-process it; Building a fault prediction model based on historical power grid operation data and fault data, inputting the preprocessed data into the fault prediction model to generate prediction results; Adjust the state of charge of the energy storage device according to the prediction results; Combine the adjusted state of charge of the energy storage device with the real-time collected grid operation data, analyze the real-time monitoring data and extract fault feature information; Based on the fault feature information and the charge state of the energy storage device after adjustment, the frequency modulation response priority of the energy storage device is dynamically allocated, and an instant frequency modulation power instruction of the energy storage device is generated; Dynamically adjust the power output of the energy storage device according to the instant frequency modulation power instruction.

2. The primary frequency modulation control method of a new energy station taking into account the fault characteristics of the power grid as claimed in claim 1, characterized in that: Collecting the operation data of the power grid and preprocessing it includes the following steps: The collected grid operation data include frequency deviation, frequency change rate and voltage fluctuation, and the collected grid operation data are filtered and outliers are eliminated.

3. The primary frequency modulation control method of a new energy station taking into account the fault characteristics of the power grid as claimed in claim 1, characterized in that: Building a fault prediction model based on historical power grid operation data and fault data includes the following steps: Align the time series of historical power grid operation data and fault data; The preprocessed power grid operation data is segmented according to fixed time windows aligned with the time series, and feature vectors are extracted from the data in each time window; A timing model based on long short-term memory network is selected to build a fault prediction model.

4. The primary frequency modulation control method of a new energy station taking into account the fault characteristics of the power grid as claimed in claim 1, characterized in that: Inputting the preprocessed data into the fault prediction model and generating the prediction results includes the following steps: The preprocessed feature vector is output to the fault prediction model to obtain the power grid fault prediction result, which is expressed as: Among them, Q f (t) is the predicted value of power grid fault at time t, σ is the output conversion value, X is the feature vector, H j (t) is the state of the jth unit in the output at time t, w j is the weight coefficient of the state of the jth unit, b is the bias term for adjusting the baseline level, α is the bias term for adjusting the baseline level, T k (t) is the value of the state of the kth unit after nonlinear transformation, z k is the weight coefficient of the kth unit state, v l is the weight coefficient of the lth feature in the feature vector X, j is the index of the output unit, l is the index of the nonlinear transformation parameter in the feature vector X, N is the dimension in the feature vector X, and F l (X) is the nonlinear transformation of the lth feature of the feature vector X, and k is the number of output units.

5. The primary frequency modulation control method of a new energy station taking into account the fault characteristics of the power grid as claimed in claim 1, characterized in that: According to the prediction results, adjusting the state of charge of the energy storage device includes the following steps: Get the current state of charge of the energy storage device, and calculate the target state of charge expression according to the current grid operation status and fault prediction value: Among them, S t+1 is the target state of charge of the energy storage device at time t+1, S t is the current state of charge of the energy storage device at t, η is the adjustment coefficient, and t is the time point; Adjusting the state of charge of the energy storage device according to the calculated target state of charge; When S t+1 >S t When the charging process is started, the state of charge of the energy storage device is changed from S t Adjust to S t+1 , increase the charging power of the energy storage device until the state of charge reaches S t+1 ; When S t+1 >S t When the discharge process is started, the state of charge of the energy storage device is changed from S t Adjust to S t+1 , increase the discharge power of the energy storage device until the state of charge reaches S t+1 ; When S t+1 =S t The current state of charge remains unchanged.

6. The primary frequency modulation control method of a new energy station taking into account the fault characteristics of the power grid as claimed in claim 1, characterized in that: Combine the adjusted state of charge of the energy storage device with the real-time collected grid operation data to analyze the real-time monitoring data and extract fault feature information The following steps are included: The adjusted state of charge of the energy storage device is combined with the real-time collected grid operation frequency deviation, frequency change rate and voltage fluctuation data, and a comprehensive fault characteristic value is generated using nonlinear function fusion. The expression is: Among them, O fault (t) is the fault characteristic value at time point t, GΔ(t) is the frequency deviation at time point t, U df (t) is the frequency change rate at time point t, R V (t) is the voltage fluctuation at time point t, and β1 is the adjustment coefficient.

7. The primary frequency modulation control method of a new energy station taking into account the fault characteristics of the power grid as claimed in claim 1, characterized in that: Based on the fault characteristic information and the charge state of the energy storage device after adjustment, the frequency modulation response priority of the energy storage device is dynamically allocated, and the instantaneous frequency modulation power instruction of the energy storage device is generated, which includes the following steps: The frequency modulation response priority of the energy storage device is calculated based on the fault characteristic value and the charge state of the energy storage device after adjustment. The expression is: Z priority (t)=(m1·O fault (t)+m2)·(γ1·S t+1 +γ2·S t+1 ); Among them, Z priority (t) is the frequency modulation response priority of the energy storage device at time point t, m1 is the influence of the control fault characteristic value on the frequency modulation response priority, m2 is the constant term, γ1 is the influence of the control state of charge on the frequency modulation response priority, and γ2 is the secondary influence of the control state of charge on the frequency modulation response priority; According to the calculated frequency modulation response priority, the instant frequency modulation power instruction of the energy storage device is generated, and the expression is: A freq (t)=C max ·Z priority (t); Among them, A freq (t) is the instantaneous frequency modulation power instruction at time point t, C max is the maximum frequency modulation power of the energy storage device.

8. The primary frequency regulation control method of a new energy station taking into account the fault characteristics of the power grid as claimed in claim 1, characterized in that: According to the instant frequency modulation power instruction, dynamically adjusting the power output of the energy storage device includes the following steps: According to the instantaneous frequency modulation power instruction and the current power output, the power adjustment amount of the energy storage device is calculated. The expression is: ΔD(t)=A freq (t)-Y current (t); Where ΔD(t) is the power adjustment at time point t, Y current (t) is the current power output at time point t; When ΔD(t)>0, it means that the power output of the energy storage device needs to be increased; When ΔD(t)<0, it means that the power output of the energy storage device needs to be reduced; When ΔD(t)=0, it means that the current power output has met the frequency modulation requirement and no adjustment is required.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the primary frequency regulation control method for a new energy station taking into account grid fault characteristics as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the primary frequency regulation control method for a new energy station taking into account grid fault characteristics as described in any one of claims 1 to 7 are implemented.

Images