Photovoltaic power station fast frequency modulation response optimization control method, device, equipment and medium

Abstract

The present invention discloses a photovoltaic power station fast frequency modulation response optimization control method, device, equipment and medium, and relates to the field of photovoltaic power station fast frequency modulation response technology, including obtaining power grid frequency regulation data and energy storage system dependency data; and constructing a photovoltaic power station frequency modulation effect evaluation model based on machine learning, and constructing an evaluation vector according to the photovoltaic power station frequency modulation effect evaluation model and the corresponding inverter power regulation range; combining the output of the photovoltaic power station frequency modulation effect evaluation model with a rectangular coordinate system to establish a three-dimensional display model, and applying each evaluation vector to the three-dimensional display model and drawing a three-dimensional fluctuation curve; performing data analysis on the three-dimensional fluctuation curve to obtain the optimal inverter power regulation range, and applying it to the optimization control of the photovoltaic power station fast frequency modulation response system. The present application solves the problem that the inverter power regulation range has no standardized and reliable setting, resulting in fluctuations in the effect of the photovoltaic power station fast frequency modulation response.

Description

Technical Field

[0001] The present invention relates to the field of fast frequency modulation response technology, and more specifically, to a fast frequency modulation response optimization control method, device, equipment and medium for a photovoltaic power station. Background Art

[0002] The existing photovoltaic power station fast frequency response first uses phase-locked loop and filtering technology, so that the photovoltaic power station can monitor the changes in grid frequency in real time and quickly detect frequency deviations, thereby providing basic data support for frequency response; then the inverter control is combined with the energy storage system, which can quickly adjust the output power when the grid frequency fluctuates. At the same time, the model-based predictive control can optimize the power adjustment strategy to ensure system stability; then, using intelligent algorithms such as PID, fuzzy control and neural networks, the photovoltaic power station can respond to grid frequency changes more accurately and quickly, improving the flexibility and efficiency of frequency response; through virtual synchronous machines and virtual inertia algorithms, the photovoltaic power station simulates the inertial characteristics of traditional generators, thereby providing similar inertial responses when the frequency fluctuates and enhancing the frequency regulation capability; the Internet of Things and edge computing enable photovoltaic power stations to obtain and process grid status data in real time, reduce data transmission delays, and speed up the response speed of frequency regulation; finally, through multi-objective optimization, adaptive control and artificial intelligence strategies, the photovoltaic power station can dynamically adjust the control parameters according to the grid load, realize fast and intelligent frequency response control, and improve the stability and accuracy of the power station frequency response.

[0003] For example, the invention patent with announcement number: CN110783953B announces a fast frequency response communication method for a string inverter photovoltaic power station, including that after the frequency regulation system sends a power setting instruction to the secondary power control device, the secondary power control device calculates the active power target values ​​of all inverters, broadcasts and sends instructions containing the active power target values ​​of all inverters, and after the inverter receives the instruction, it does not need to reply to confirm, and parses the active power setting value corresponding to its own communication address and executes it. The transformer measurement and control device is connected to the secondary power control device through RS485, and the secondary power control device directly collects the active power on the transformer side and uploads it to the frequency regulation system. The frequency regulation system performs closed-loop regulation again according to this feedback value; the fast frequency response communication method of the present invention saves the time of collecting inverter operation data and the time of issuing instructions in sequence.

[0004] For example, the invention patent with announcement number CN111555308B discloses a method for photovoltaic power stations to participate in frequency regulation of regional power grids. By modifying the inverter control of photovoltaic arrays participating in rapid frequency regulation, it has a single-machine primary frequency regulation function based on rate of change and variable frequency regulation under different active powers, which can realize rapid frequency regulation and variable frequency regulation based on rate of change; modifying the inverter control of photovoltaic arrays that do not participate in rapid frequency regulation in photovoltaic power stations, it has a primary frequency regulation function based on variable frequency regulation, which can realize continuous frequency regulation; reasonably setting the photovoltaic arrays and frequency regulation parameters of rapid frequency regulation according to the needs of the power grid can realize the frequency support of photovoltaic power stations to the asynchronous sending-end power grid. This method only requires the modification and upgrade of the control software, and does not require the addition and transformation of hardware and communications. The transformation cost is low, and the single-machine frequency regulation response is shorter and faster than the station-level frequency regulation control response time, which can provide rapid frequency support to the asynchronous sending-end power grid.

[0005] The above disclosed technical solutions have at least the following technical problems: when the photovoltaic power station responds to rapid frequency regulation, the power regulation range of the inverter has a crucial impact on the rapid frequency regulation response of the photovoltaic power station. When the power regulation range of the inverter is too large, the inverter requires a higher power processing capability, resulting in an increase in equipment investment costs, and will cause excessive frequency adjustment, resulting in grid frequency oscillation, which affects the stability of the grid; when the power regulation range of the inverter is too small, the inverter may not be able to provide sufficient power adjustment when the frequency fluctuation is large, reducing the system's ability to respond to frequency deviations. The smaller regulation range requires the system to frequently call the energy storage system to compensate for the power gap when the frequency fluctuation is large, which accelerates the loss of the energy storage equipment. The prior art has no standardized and reliable setting for the power regulation range of the inverter, resulting in fluctuations in the effect of the rapid frequency response of the photovoltaic power station.

[0006] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0007] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a method, device, equipment and medium for optimizing the control of the fast frequency regulation response of a photovoltaic power station. By analyzing the power regulation range of different inverters, the problem that the power regulation range of the inverter is not standardized and reliably set is solved, resulting in fluctuations in the effect of the fast frequency regulation response of the photovoltaic power station.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] The photovoltaic power station fast frequency regulation response optimization control method includes the following steps: obtaining the power regulation range of several groups of inverters and applying them to the photovoltaic power station fast frequency regulation response system respectively; obtaining the grid frequency regulation data and energy storage system dependency data of each photovoltaic power station fast frequency regulation response system within the G time and P time interval; constructing a photovoltaic power station frequency regulation effect evaluation model based on machine learning according to the grid frequency regulation data and the energy storage system dependency data, and constructing an evaluation vector according to the photovoltaic power station frequency regulation effect evaluation model and the corresponding inverter power regulation range; taking the minimum and maximum values ​​of the power regulation range as the horizontal axis and vertical axis of the rectangular coordinate system respectively, combining the output of the photovoltaic power station frequency regulation effect evaluation model with the rectangular coordinate system to establish a three-dimensional display model, and applying each evaluation vector to the three-dimensional display model and drawing a three-dimensional fluctuation curve; performing data analysis on the three-dimensional fluctuation curve to obtain the optimal inverter power regulation range, and applying it to the optimization control of the photovoltaic power station fast frequency regulation response system.

[0010] In a preferred embodiment, the power grid frequency regulation data includes a frequency regulation capacity limitation coefficient and a frequency regulation compensation effect abnormality coefficient; the specific method for obtaining the frequency regulation capacity limitation coefficient is as follows: obtain the frequency regulation range size corresponding to the node in the time interval W within the time Q; perform Fourier transform on the frequency regulation range size, and convert the frequency regulation range size waveform to the frequency domain; in the frequency domain, calculate the peak frequency and valley frequency of the frequency regulation range size waveform, which respectively represent the peak and valley positions of the frequency regulation range size waveform in the frequency spectrum; calculate the frequency regulation capacity limitation coefficient by the square of the Euclidean distance between the peak frequency and the valley frequency.

[0011] In a preferred embodiment, the specific analysis method of the frequency compensation effect abnormality coefficient is as follows: the frequency compensation abnormality types are classified and labeled to form a frequency compensation set, and when the photovoltaic power station responds to rapid frequency regulation, the frequency of occurrence of each compensation effect abnormality in the historical system is obtained, and the sum of all compensation effect abnormality frequencies is calculated; for each compensation effect abnormality, the average value of its influence on other compensation effect abnormalities is calculated, and the average influence of each compensation effect abnormality is obtained by calculating the sum of the influence of each compensation effect abnormality and dividing it by the total number of frequency compensation abnormality types to obtain the average influence of each compensation effect abnormality as the frequency compensation effect abnormality coefficient.

[0012] In a preferred embodiment, the energy storage system dependency data includes an energy storage system dependency influence coefficient; the specific method for obtaining the energy storage system dependency influence coefficient is as follows: obtain the matching energy storage system capacity of each inverter power range, label and establish a matching energy storage system capacity set; obtain the average logarithm and logarithmic standard deviation of the device matching energy storage system capacity based on statistical analysis of historical matching energy storage system capacity data; make the matching energy storage system capacity of the inverter power range conform to the normal distribution, and obtain the probability density function of the matching energy storage system capacity; generate multiple random number samples that conform to the distribution based on the probability density function of the matching energy storage system capacity, label and establish a sample set; and perform analysis and calculation to obtain the device matching energy storage system capacity fluctuation coefficient, and compare and analyze with the preset device matching energy storage system capacity fluctuation expected value to obtain the energy storage system dependency influence coefficient.

[0013] In a preferred embodiment, the photovoltaic power station frequency regulation effect evaluation model is constructed based on machine learning according to the grid frequency regulation data and the energy storage system dependency data, specifically: the obtained frequency regulation capacity limitation coefficient, frequency regulation compensation effect abnormality coefficient and energy storage system dependency influence coefficient are used to construct the photovoltaic power station frequency regulation effect evaluation model to generate the photovoltaic power station frequency regulation effect evaluation coefficient; the evaluation vector is constructed according to the photovoltaic power station frequency regulation effect evaluation model and the corresponding inverter power regulation range, specifically: the evaluation vector includes the maximum value, the minimum value of the inverter power regulation range and the corresponding photovoltaic power station frequency regulation effect evaluation coefficient.

[0014] In a preferred embodiment, the output of the photovoltaic power station frequency modulation effect evaluation model is combined with a rectangular coordinate system to establish a three-dimensional display model, specifically: the maximum and minimum values ​​of each power adjustment range are marked on the rectangular coordinate system, the marked rectangular coordinate system is used as the base, and the output of the photovoltaic power station frequency modulation effect evaluation model corresponding to each power adjustment range mark is used as the z-axis of the three-dimensional display model; and each evaluation vector is used as a data point to update the marked three-dimensional display model; each data point of the three-dimensional display model is connected to draw a three-dimensional fluctuation curve.

[0015] In a preferred embodiment, the data analysis of the three-dimensional fluctuation curve is performed to obtain the optimal power adjustment range of the inverter, specifically: a corresponding mathematical model is established according to the three-dimensional fluctuation curve; each peak value in the three-dimensional fluctuation curve is obtained, and the secondary derivative of the corresponding peak value in the mathematical model is calculated, and the power adjustment range of the inverter corresponding to the peak value whose secondary derivative is closest to zero is taken as the optimal power adjustment range of the inverter, and it is applied to the optimization control of the fast frequency regulation response system of the photovoltaic power station.

[0016] A device for optimizing the control method of fast frequency modulation response of photovoltaic power station, characterized in that it comprises a range random selection module, a data acquisition module, a model building module, a three-dimensional display module and a power adjustment range selection module of the inverter, and there is a connection between the modules; the range random selection module is used to obtain the power adjustment ranges of several groups of inverters, and respectively apply them to the fast frequency modulation response system of the photovoltaic power station; the data acquisition module is used to obtain the grid frequency regulation data and energy storage system dependency data of each photovoltaic power station fast frequency modulation response system within the G time interval and the P time interval; the model building module is used to build a model based on machine learning according to the grid frequency regulation data and the energy storage system dependency data The photovoltaic power station frequency regulation effect evaluation model constructs an evaluation vector according to the photovoltaic power station frequency regulation effect evaluation model and the corresponding inverter power regulation range; the three-dimensional display module is used to use the minimum and maximum values ​​of the power regulation range as the horizontal axis and vertical axis of the rectangular coordinate system, respectively, and combine the output of the photovoltaic power station frequency regulation effect evaluation model with the rectangular coordinate system to establish a three-dimensional display model, and apply each evaluation vector to the three-dimensional display model and draw a three-dimensional fluctuation curve; the inverter power regulation range selection module is used to perform data analysis on the three-dimensional fluctuation curve, obtain the optimal inverter power regulation range, and apply it to the optimization control of the photovoltaic power station fast frequency regulation response system.

[0017] An electronic device, characterized in that the electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute a photovoltaic power station fast frequency modulation response optimization control method.

[0018] A computer-readable storage medium stores a computer program, wherein the computer program is executed by a processor to implement a fast frequency modulation response optimization control method for a photovoltaic power station.

[0019] The technical effects and advantages of the photovoltaic power station fast frequency modulation response optimization control method, device, equipment and medium of the present invention are as follows:

[0020] 1. The present invention sets the power adjustment range of the inverter so that the system can quickly adjust the power output of the photovoltaic power station when the grid frequency fluctuates, thereby balancing the frequency deviation and improving the speed and accuracy of the frequency modulation response. The frequency modulation response process is finely managed and optimized using a variety of frequency modulation effect indicators such as the frequency modulation capacity limitation coefficient, the frequency modulation compensation effect abnormality coefficient, and the energy storage system dependency influence coefficient. In this way, while ensuring the rapid response of the system, it can reduce excessive reliance on the energy storage system, extend the service life of the equipment, and reduce maintenance costs. In addition, this method makes the frequency modulation effect of the photovoltaic power station more stable and reliable, helps to improve the stability of the grid frequency, and provides a dynamically adaptive frequency modulation strategy optimization scheme, which significantly improves the frequency modulation response capability and operating efficiency of the photovoltaic power station in a variable grid environment.

[0021] 2. The present invention introduces grid frequency regulation data and energy storage system dependency data, and constructs a photovoltaic power station frequency regulation effect evaluation model based on machine learning, which can accurately quantify and evaluate the frequency regulation performance of the photovoltaic power station. At the same time, the evaluation vector is constructed using the inverter power adjustment range, and the photovoltaic power station frequency regulation response system is further optimized through the three-dimensional display model and the visualization analysis of the three-dimensional fluctuation curve. This method not only improves the evaluation accuracy of the frequency regulation effect, but also obtains the optimal inverter power adjustment range by analyzing the peak value of the three-dimensional fluctuation curve through a mathematical model, thereby realizing the optimization control of the photovoltaic power station fast frequency regulation response system. Overall, this scheme effectively enhances the response speed and stability of the photovoltaic power station in grid frequency regulation, improves the frequency regulation capability of the photovoltaic power station, and optimizes the grid frequency regulation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a structural schematic diagram of the photovoltaic power station fast frequency modulation response optimization control method of the present invention.

[0023] Figure 2 It is a structural schematic diagram of the fast frequency modulation response optimization control device of the photovoltaic power station of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] Embodiment 1, Figure 1 The invention provides a photovoltaic power station fast frequency modulation response optimization control method, comprising the following step S1, obtaining power regulation ranges of several groups of inverters, and applying them to the photovoltaic power station fast frequency modulation response system respectively.

[0026] It should be noted that in the fast frequency response system of a photovoltaic power station, the power adjustment range of the inverter refers to the upper and lower limits of the power output that the inverter can adjust. This range determines the maximum and minimum power values ​​that the inverter can adjust when facing grid frequency fluctuations, which directly affects the frequency response capability of the photovoltaic power station. When the grid frequency deviates, the inverter will quickly increase or decrease the output power of the photovoltaic power station according to its power adjustment range in order to balance the frequency deviation in a short time. When the power adjustment range is large, the inverter can provide regulation under larger frequency fluctuations, but it may increase the equipment load and cost; on the contrary, when the adjustment range is small, the response capability of the inverter will be limited and may not be able to fully meet the regulation requirements of the grid frequency. Therefore, in order to achieve the best frequency regulation effect, it is necessary to comprehensively consider the size of the power adjustment range to balance the regulation capability and cost of the system.

[0027] S2, obtaining grid frequency regulation data and energy storage system dependency data of each photovoltaic power station's fast frequency regulation response system within a P time interval within a G time.

[0028] It should be noted that G and P are both arbitrarily set integers and are adjusted according to actual conditions.

[0029] The grid frequency regulation data includes the frequency regulation capacity limitation coefficient and the frequency regulation compensation effect abnormality coefficient, and the energy storage system dependency data includes the energy storage system dependency influence coefficient.

[0030] The frequency regulation capability limit coefficient is an indicator used to evaluate the power regulation capability of the inverter of the fast frequency regulation response system of a photovoltaic power station under the condition of grid frequency fluctuations. It reflects the impact of the inverter power regulation range on the overall frequency regulation response effect, especially whether the inverter can provide sufficient power compensation when the frequency deviation is large. This coefficient helps to measure the frequency regulation capability of the inverter and ensure that it can effectively respond and adjust power within a larger frequency deviation range. If the regulation range is small, the value of the frequency regulation capability limit coefficient will increase, indicating that the frequency regulation capability is insufficient and the frequency regulation response effect of the photovoltaic power station may be unstable. By setting an appropriate frequency regulation capability limit coefficient, the power regulation range of the inverter can be standardized and the fast frequency regulation response effect of the photovoltaic power station can be optimized.

[0031] Analysis of the frequency regulation capability limit coefficient has the following advantages in solving the problem that the inverter power regulation range has no standardized and reliable setting, resulting in fluctuations in the effect of the photovoltaic power station's fast frequency regulation response: It cannot completely solve the standardization of the regulation range selection: Although the frequency regulation capability limit coefficient can quantify the inverter's ability in the frequency regulation process, it still lacks a unified standard to guide how to choose the optimal power regulation range. Due to the differences in system configuration, inverter model, local power grid environment and other factors of each photovoltaic power station, this coefficient may need to be personalized, so it is difficult to use as a universal standardized solution.

[0032] Insufficient sensitivity to changes in frequency regulation capability: The frequency regulation capability limit coefficient mainly focuses on the impact of the power regulation range, but in actual operation, the frequency regulation effect of photovoltaic power stations is also affected by other factors, such as the frequency and amplitude of grid fluctuations, dynamic changes in loads, etc. The existence of these complex factors may cause the frequency regulation capability limit coefficient to be insufficiently reflected in certain situations, thus failing to fully reflect the actual frequency regulation effect.

[0033] Limited real-time and adaptability: When the grid frequency fluctuates rapidly, the frequency regulation capacity limit coefficient may not be able to reflect the changes in frequency regulation demand in a timely manner. The system needs to dynamically adjust the power regulation range of the inverter according to different grid frequency changes, and the frequency regulation capacity limit coefficient may have a certain delay in the adjustment process, which will affect the rapid response capability of the photovoltaic power station.

[0034] Over-reliance on the durability of equipment: Too large a frequency regulation capacity limit coefficient will cause the inverter to bear a larger load in frequent power regulation, thereby increasing the wear of the equipment and the risk of abnormal compensation effect. Especially in the case of long-term system operation, the setting of the frequency regulation capacity limit coefficient must balance the durability of the equipment and the frequency regulation effect, otherwise it will lead to an increase in the cost of long-term maintenance and replacement of equipment.

[0035] Limitations of application scope: The grid conditions and load characteristics of photovoltaic power plants vary greatly in different regions, and the frequency regulation capacity limit coefficient may not be applicable in some scenarios, especially under special grid conditions or extreme weather. In order to ensure the frequency regulation effect, this coefficient may need to be adjusted frequently, but this will increase the complexity of the frequency regulation system and may also require further debugging and optimization.

[0036] The specific method for obtaining the frequency modulation capability limitation coefficient is as follows:

[0037] Get the frequency modulation range size of the node corresponding to the interval W time period within time Q;

[0038] Perform Fourier transform on the frequency modulation range size, and convert the frequency modulation range size waveform into the frequency domain;

[0039] In the frequency domain, the peak frequency and the valley frequency of the frequency modulation range waveform are calculated, which respectively represent the peak and valley positions of the frequency modulation range waveform in the frequency spectrum;

[0040] The frequency modulation capacity limitation coefficient is calculated by the square of the Euclidean distance between the peak frequency and the valley frequency;

[0041] The calculation formula of the frequency modulation capability limitation coefficient is as follows:

[0042] In the formula, Indicates the frequency corresponding to the maximum value of the waveform spectrum of the corresponding frequency modulation range. Indicates the frequency corresponding to the minimum value of the waveform spectrum of the corresponding frequency modulation range. Indicates the frequency of the waveform spectrum corresponding to the FM range size, Indicates a point in time, is the frequency modulation range of the node corresponding to the interval of P time period in time G, i is the time label of the interval of P time period in time G, is the frequency modulation capacity limitation coefficient.

[0043] The frequency regulation compensation effect abnormality coefficient is an indicator used to evaluate the effectiveness of grid frequency regulation in the frequency regulation process of a photovoltaic power station. This coefficient reflects whether the inverter's compensation effect on grid frequency deviations fluctuates abnormally within different power regulation ranges. The larger the power regulation range of the inverter, the more effectively the photovoltaic power station can adjust the power output when the grid frequency fluctuates, thereby quickly balancing the frequency deviation and shortening the amplitude and duration of the frequency fluctuation. However, if the power regulation range is set too small, the inverter cannot provide sufficient power support when the frequency fluctuates greatly, resulting in unsatisfactory frequency regulation effect. This coefficient can reveal the impact of the power regulation range on the frequency regulation compensation effect, help identify and improve abnormal phenomena in the frequency regulation process, and achieve a more stable and reliable frequency regulation response effect. Analyzing the frequency regulation compensation effect abnormality coefficient has the following advantages in solving the problem that the power regulation range of the inverter is not standardized and reliable, resulting in fluctuations in the effect of the photovoltaic power station's rapid frequency regulation response:

[0044] Provide clear feedback on the frequency modulation effect: This coefficient can quantify the abnormal compensation during the frequency modulation process, thereby providing direct feedback on the frequency modulation effect. By monitoring and analyzing the frequency modulation compensation effect abnormal coefficient, it is possible to quickly find out whether the inverter power adjustment range is sufficient to effectively cope with grid frequency fluctuations, and make timely adjustments for unsatisfactory frequency modulation effects.

[0045] Enhance the stability of frequency modulation response: The frequency modulation compensation effect abnormality coefficient can identify the compensation effect fluctuation caused by the unreasonable inverter power adjustment range, and help system managers to standardize the inverter power adjustment range. The setting of this coefficient makes the frequency modulation response more stable, reduces abnormal fluctuations in the frequency modulation process, and helps to optimize the photovoltaic power station's ability to respond quickly to grid frequency fluctuations.

[0046] Improve the system's rapid response performance: By monitoring the frequency compensation effect abnormality coefficient, the inverter's compensation effect can be evaluated when the frequency fluctuation is large or lasts for a long time, and the power regulation range can be adjusted in time. This can effectively improve the system's rapid response performance and ensure that the inverter can quickly and appropriately provide power support to maintain frequency stability in the case of frequency fluctuations.

[0047] Achieve adaptive optimization of frequency modulation strategy: The frequency modulation compensation effect abnormality coefficient can provide a dynamic adjustment basis for the setting of the inverter power regulation range, so that the frequency modulation strategy of the photovoltaic power station can be adaptively optimized. By continuously monitoring the frequency modulation effect, the system can automatically optimize the power regulation range, thereby improving the frequency modulation response effect without affecting the life of the equipment.

[0048] Reduce the maintenance requirements of photovoltaic power station equipment: When the frequency regulation compensation effect abnormality coefficient reduces volatility, it can reduce the equipment load caused by the inverter's frequent power adjustment. This coefficient can help balance the relationship between frequency regulation performance and equipment durability, avoid equipment wear or abnormal compensation effect caused by excessive or insufficient power adjustment range, and thus reduce the system's maintenance cost.

[0049] In summary, the frequency compensation effect abnormal coefficient can effectively guide the standardized setting of the inverter power regulation range, improve the stability and efficiency of the photovoltaic power station during the rapid frequency regulation response process, and provide a scientific basis for the dynamic optimization of the frequency regulation strategy.

[0050] The specific analysis method of the abnormal coefficient of the frequency modulation compensation effect is as follows:

[0051] The frequency compensation abnormality types are classified and numbered to form a frequency compensation set. When the photovoltaic power station responds to the rapid frequency regulation, the frequency of each compensation effect abnormality in the historical system is obtained, and the sum of all compensation effect abnormality frequencies is calculated;

[0052] For each compensation effect abnormality, calculate the average value of its influence on other compensation effect abnormalities. By calculating the sum of the influence of each compensation effect abnormality and dividing it by the total number of frequency modulation compensation abnormality types, the average influence of each compensation effect abnormality is obtained as the frequency modulation compensation effect abnormality coefficient. The specific calculation formula is as follows:

[0053]

[0054] In the formula, is the abnormal coefficient of frequency modulation compensation effect, To compensate for the frequency of abnormal effects, To compensate for the abnormal labeling effect, , To compensate for the total number of abnormal effects, is the element in the compensation effect anomaly weight matrix, and is the degree of influence of the p-th compensation effect anomaly on the q-th class;

[0055] The energy storage system dependency impact coefficient is an indicator used to evaluate the collaborative work of a photovoltaic power station with an energy storage system in the frequency modulation response. It reflects the impact of the inverter power adjustment range on the degree of dependence on the energy storage system. The larger the power adjustment range, the more flexibly the inverter can combine the energy storage system in the frequency modulation process, which can not only assist the energy storage system in outputting power, but also adjust the output by itself, thereby achieving the joint frequency modulation effect of photovoltaics and energy storage. On the contrary, if the adjustment range is small, the inverter will rely more on the energy storage system to make up for its insufficient regulation, which not only increases the frequency of use of the energy storage system, accelerates equipment aging and loss, but also may lead to an increase in system maintenance costs. By using the energy storage system dependency impact coefficient, photovoltaic power stations can optimize the setting of the inverter power adjustment range, make photovoltaics and energy storage systems more coordinated and effective in the frequency modulation process, and reduce the fluctuation of the frequency modulation response effect.

[0056] Analyzing the dependence influence coefficient of the energy storage system has the following advantages in solving the problem that the power regulation range of the inverter is not standardized and reliable, resulting in fluctuations in the effect of the fast frequency regulation response of the photovoltaic power station:

[0057] Enhance the coordinated frequency regulation effect of photovoltaic and energy storage systems: By using the energy storage system dependency coefficient, the system can better evaluate the degree of dependence of the inverter adjustment range on the energy storage system. This helps to fully utilize the combined advantages of photovoltaic power stations and energy storage systems when setting the power adjustment range, and achieve a more efficient and smoother frequency regulation effect.

[0058] Reduce overuse of energy storage systems: A larger power regulation range means that the inverter can take on more frequency regulation responsibilities, reducing over-reliance on energy storage systems. The energy storage system dependency impact coefficient can effectively identify this, thereby preventing the energy storage system from frequently overloading, extending its service life, and reducing the overall maintenance and replacement costs of photovoltaic power plants.

[0059] Improve the flexibility of frequency regulation response: This coefficient can reveal the impact of the inverter power adjustment range on the flexibility of the frequency regulation strategy. A larger adjustment range can enable the system to respond flexibly to different frequency fluctuation scenarios, reduce the reliance on a single energy storage system, and enable the photovoltaic power station to adjust the output power under different frequency fluctuation conditions, thus improving the ability to respond quickly.

[0060] Reduce the aging rate of the energy storage system: By using the energy storage system dependency influence coefficient, the optimal power adjustment range can be found, so that the energy storage system does not need to frequently intervene in power compensation. This can reduce the number of charge and discharge times of the energy storage battery, delay its aging process, and ensure that the equipment operates in the best state for a long time.

[0061] Achieve higher system stability: When the inverter and energy storage system have a more stable coordinated frequency regulation effect, the photovoltaic power station can reduce abnormal fluctuations in the frequency regulation response process. By setting a reasonable power regulation range and evaluating the energy storage system dependency coefficient, the frequency regulation effect fluctuation caused by uneven energy storage system load can be greatly reduced, thereby improving the stability of the power grid.

[0062] In general, the energy storage system dependency influence coefficient provides a quantitative basis for setting the regulation range, ensuring that the photovoltaic power station can efficiently cooperate with the energy storage system during frequency regulation response, achieving a dual improvement in flexibility and stability, while extending equipment life and reducing long-term costs.

[0063] The specific method for obtaining the energy storage system dependency influence coefficient is as follows:

[0064] Obtain the matching energy storage system capacity of each inverter power range, label and establish a matching energy storage system capacity set;

[0065] The average logarithm and logarithmic standard deviation of the equipment matching energy storage system capacity are obtained based on the statistical analysis of the historical matching energy storage system capacity data;

[0066] The capacity of the energy storage system matching the inverter power range is made to conform to the normal distribution, and the probability density function of the capacity of the energy storage system matching is obtained;

[0067] Generate multiple random number samples that conform to the distribution according to the probability density function matching the capacity of the energy storage system, label them and establish a sample set;

[0068] And analyze and calculate to obtain the capacity fluctuation coefficient of the equipment matching energy storage system, and compare and analyze it with the preset expected value of the capacity fluctuation of the equipment matching energy storage system to obtain the dependence influence coefficient of the energy storage system;

[0069] The specific formula of the probability density function of matching the energy storage system capacity is as follows:

[0070]

[0071] The calculation formula of the energy storage system dependence influence coefficient is as follows:

[0072]

[0073] In the formula, To match the energy storage system capacity to the equipment, is the average logarithm of the capacity of the energy storage system matched with the equipment, is the logarithmic standard deviation, A sample of random numbers, is the total number of samples, is the random number sample label, is the random number sample mean, To match the expected value of energy storage system capacity fluctuation to the equipment, is the energy storage system dependency coefficient.

[0074] This embodiment sets the power adjustment range of the inverter so that the system can quickly adjust the power output of the photovoltaic power station when the grid frequency fluctuates, thereby balancing the frequency deviation and improving the speed and accuracy of the frequency modulation response. The frequency modulation response process is finely managed and optimized using a variety of frequency modulation effect indicators such as the frequency modulation capacity limit coefficient, the frequency modulation compensation effect abnormality coefficient, and the energy storage system dependency influence coefficient. In this way, while ensuring the rapid response of the system, it can reduce excessive reliance on the energy storage system, extend the service life of the equipment, and reduce maintenance costs. In addition, this method makes the frequency modulation effect of the photovoltaic power station more stable and reliable, helps to improve the stability of the grid frequency, and provides a dynamically adaptive frequency modulation strategy optimization solution, which significantly improves the frequency modulation response capability and operating efficiency of the photovoltaic power station in a variable grid environment.

[0075] Embodiment 2, S3, constructs a photovoltaic power station frequency regulation effect evaluation model based on machine learning according to the grid frequency regulation data and the energy storage system dependency data, and constructs an evaluation vector according to the photovoltaic power station frequency regulation effect evaluation model and the corresponding inverter power regulation range.

[0076] The photovoltaic power station frequency regulation effect evaluation model is constructed based on machine learning according to the grid frequency regulation data and the energy storage system dependency data, specifically: the obtained frequency regulation capacity limitation coefficient, frequency regulation compensation effect abnormality coefficient and energy storage system dependency influence coefficient are used to construct the photovoltaic power station frequency regulation effect evaluation model, and generate the photovoltaic power station frequency regulation effect evaluation coefficient;

[0077] The specific calculation formula of the photovoltaic power station frequency modulation effect evaluation coefficient is as follows:

[0078]

[0079] In the formula, is the evaluation coefficient of the frequency regulation effect of the photovoltaic power station, is the preset proportional coefficient of the frequency modulation capacity limitation coefficient, It is the preset proportional coefficient of the abnormal coefficient of the frequency modulation compensation effect. is the preset proportional coefficient of the energy storage system dependence influence coefficient, is the frequency modulation capacity limitation coefficient, is the abnormal coefficient of frequency modulation compensation effect, is the energy storage system dependency coefficient.

[0080] The evaluation vector is constructed according to the photovoltaic power station frequency regulation effect evaluation model and the corresponding inverter power regulation range. Specifically, the evaluation vector includes the maximum value, the minimum value of the inverter power regulation range and the corresponding photovoltaic power station frequency regulation effect evaluation coefficient.

[0081] S4, taking the minimum and maximum values ​​of the power regulation range as the horizontal and vertical axes of the rectangular coordinate system respectively, combining the output of the photovoltaic power station frequency regulation effect evaluation model with the rectangular coordinate system to establish a three-dimensional display model, and applying each evaluation vector to the three-dimensional display model and drawing a three-dimensional fluctuation curve.

[0082] The output of the photovoltaic power station frequency modulation effect evaluation model is combined with the rectangular coordinate system to establish a three-dimensional display model, specifically:

[0083] The maximum and minimum values ​​of each power regulation range are marked on the rectangular coordinate system, the marked rectangular coordinate system is used as the base, and the output of the photovoltaic power station frequency regulation effect evaluation model corresponding to each power regulation range mark is used as the z-axis of the three-dimensional display model;

[0084] Each evaluation vector is used as a data point to update the marked three-dimensional display model;

[0085] Connect the data points of the three-dimensional display model and draw a three-dimensional fluctuation curve.

[0086] S5, performs data analysis on the three-dimensional fluctuation curve to obtain the best power adjustment range of the inverter, and applies it to the optimization control of the fast frequency modulation response system of the photovoltaic power station.

[0087] The data analysis of the three-dimensional fluctuation curve is performed to obtain the optimal power adjustment range of the inverter, specifically:

[0088] Establish a corresponding mathematical model based on the three-dimensional fluctuation curve;

[0089] The peak values ​​in the three-dimensional fluctuation curve are obtained, and the secondary derivatives of the corresponding peak values ​​in the mathematical model are calculated. The power regulation range of the inverter corresponding to the peak value whose secondary derivative is closest to zero is taken as the optimal power regulation range of the inverter, and it is applied to the optimization control of the fast frequency regulation response system of the photovoltaic power station.

[0090] This embodiment introduces grid frequency regulation data and energy storage system dependency data, and constructs a photovoltaic power station frequency regulation effect evaluation model based on machine learning, which can accurately quantify and evaluate the frequency regulation performance of the photovoltaic power station. At the same time, the evaluation vector is constructed using the inverter power adjustment range, and the photovoltaic power station frequency regulation response system is further optimized through the three-dimensional display model and the visualization analysis of the three-dimensional fluctuation curve. This method not only improves the evaluation accuracy of the frequency regulation effect, but also obtains the optimal inverter power adjustment range by analyzing the peak value of the three-dimensional fluctuation curve through a mathematical model, thereby realizing the optimization control of the photovoltaic power station fast frequency regulation response system. Overall, this solution effectively enhances the response speed and stability of the photovoltaic power station in grid frequency regulation, improves the frequency regulation capability of the photovoltaic power station, and optimizes the grid frequency regulation process.

[0091] Embodiment 3, Figure 2 A schematic diagram of a device for a photovoltaic power station fast frequency modulation response optimization control method, characterized in that it includes a range random selection module, a data acquisition module, a model building module, a three-dimensional display module and an inverter power adjustment range selection module, and there are connections between the modules;

[0092] A range random selection module is used to obtain the power adjustment ranges of several groups of inverters and apply them to the fast frequency response system of the photovoltaic power station respectively;

[0093] A data acquisition module is used to obtain the grid frequency regulation data and energy storage system dependency data of each photovoltaic power station's fast frequency response system within the G time interval and the P time interval;

[0094] A model building module is used to build a photovoltaic power station frequency regulation effect evaluation model based on machine learning according to the grid frequency regulation data and energy storage system dependency data, and to build an evaluation vector according to the photovoltaic power station frequency regulation effect evaluation model and the corresponding inverter power regulation range;

[0095] A three-dimensional display module is used to use the minimum and maximum values ​​of the power regulation range as the horizontal axis and vertical axis of the rectangular coordinate system, respectively, combine the output of the photovoltaic power station frequency regulation effect evaluation model with the rectangular coordinate system to establish a three-dimensional display model, and apply each evaluation vector to the three-dimensional display model and draw a three-dimensional fluctuation curve;

[0096] The power regulation range selection module of the inverter is used to perform data analysis on the three-dimensional fluctuation curve, obtain the best power regulation range of the inverter, and apply it to the optimization control of the fast frequency regulation response system of the photovoltaic power station.

[0097] The present application also includes an electronic device, characterized in that the electronic device includes:

[0098] at least one processor; and,

[0099] a memory communicatively connected to the at least one processor; wherein,

[0100] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the photovoltaic power station fast frequency regulation response optimization control method.

[0101] The present application also includes a computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement a fast frequency modulation response optimization control method for a photovoltaic power station.

[0102] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0103] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0104] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

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

[0106] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0107] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A photovoltaic power station fast frequency modulation response optimization control method, characterized in that: The steps include: Obtain the power regulation ranges of several groups of inverters and apply them to the fast frequency response system of photovoltaic power stations respectively; Obtain grid frequency regulation data and energy storage system dependency data of each photovoltaic power station’s fast frequency response system within G time interval and P time interval; According to the grid frequency regulation data and energy storage system dependency data, a photovoltaic power station frequency regulation effect evaluation model is built based on machine learning, and an evaluation vector is built based on the photovoltaic power station frequency regulation effect evaluation model and the corresponding inverter power regulation range; The photovoltaic power station frequency regulation effect evaluation model is constructed based on machine learning according to the grid frequency regulation data and the energy storage system dependency data, specifically: the obtained frequency regulation capacity limitation coefficient, frequency regulation compensation effect abnormality coefficient and energy storage system dependency influence coefficient are used to construct the photovoltaic power station frequency regulation effect evaluation model, and generate the photovoltaic power station frequency regulation effect evaluation coefficient; The specific calculation formula of the photovoltaic power station frequency modulation effect evaluation coefficient is as follows: In the formula, is the evaluation coefficient of the frequency regulation effect of the photovoltaic power station, is the preset proportional coefficient of the frequency modulation capacity limitation coefficient, It is the preset proportional coefficient of the abnormal coefficient of the frequency modulation compensation effect. is the preset proportional coefficient of the energy storage system dependence influence coefficient, is the frequency modulation capacity limitation coefficient, is the abnormal coefficient of frequency modulation compensation effect, is the energy storage system dependency impact coefficient; The minimum and maximum values ​​of the power regulation range are used as the horizontal and vertical axes of the rectangular coordinate system respectively, and the output of the photovoltaic power station frequency regulation effect evaluation model is combined with the rectangular coordinate system to establish a three-dimensional display model, and each evaluation vector is applied to the three-dimensional display model and a three-dimensional fluctuation curve is drawn; Perform data analysis on the three-dimensional fluctuation curve to obtain the best power regulation range of the inverter, and apply it to the optimization control of the fast frequency response system of the photovoltaic power station; The data analysis of the three-dimensional fluctuation curve is performed to obtain the optimal power adjustment range of the inverter, specifically: Establish a corresponding mathematical model based on the three-dimensional fluctuation curve; The peak values ​​in the three-dimensional fluctuation curve are obtained, and the secondary derivatives of the corresponding peak values ​​in the mathematical model are calculated. The power regulation range of the inverter corresponding to the peak value whose secondary derivative is closest to zero is taken as the optimal power regulation range of the inverter, and it is applied to the optimization control of the fast frequency regulation response system of the photovoltaic power station.

2. The photovoltaic power station fast frequency modulation response optimization control method according to claim 1 is characterized in that: The grid frequency regulation data includes a frequency regulation capacity limitation coefficient and a frequency regulation compensation effect abnormality coefficient; the specific method for obtaining the frequency regulation capacity limitation coefficient is as follows: Get the frequency modulation range size of the node corresponding to the interval W time period within time Q; Perform Fourier transform on the frequency modulation range size, and convert the frequency modulation range size waveform into the frequency domain; In the frequency domain, the peak frequency and the valley frequency of the frequency modulation range waveform are calculated, which respectively represent the peak and valley positions of the frequency modulation range waveform in the frequency spectrum; The frequency modulation capacity limitation coefficient is calculated by the square of the Euclidean distance between the peak frequency and the valley frequency.

3. The photovoltaic power station fast frequency modulation response optimization control method according to claim 2 is characterized in that: The specific analysis method of the abnormal coefficient of the frequency modulation compensation effect is as follows: The frequency compensation abnormality types are classified and numbered to form a frequency compensation set. When the photovoltaic power station responds to the rapid frequency regulation, the frequency of each compensation effect abnormality in the historical system is obtained, and the sum of all compensation effect abnormality frequencies is calculated; For each compensation effect anomaly, calculate the average value of its influence on other compensation effect anomalies. By calculating the sum of the influence of each compensation effect anomaly and dividing it by the total number of frequency modulation compensation anomaly types, the average influence of each compensation effect anomaly is obtained as the frequency modulation compensation effect anomaly coefficient.

4. The photovoltaic power station fast frequency modulation response optimization control method according to claim 3 is characterized in that: The energy storage system dependency data includes an energy storage system dependency influence coefficient; the specific method for obtaining the energy storage system dependency influence coefficient is as follows: Obtain the matching energy storage system capacity of each inverter power range, label and establish a matching energy storage system capacity set; The average logarithm and logarithmic standard deviation of the equipment matching energy storage system capacity are obtained based on the statistical analysis of the historical matching energy storage system capacity data; The capacity of the energy storage system matching the inverter power range is made to conform to the normal distribution, and the probability density function of the capacity of the energy storage system matching is obtained; Generate multiple random number samples that conform to the distribution according to the probability density function matching the capacity of the energy storage system, label them and establish a sample set; And analyze and calculate to obtain the capacity fluctuation coefficient of the equipment matching energy storage system, and compare and analyze it with the preset expected value of the capacity fluctuation of the equipment matching energy storage system to obtain the energy storage system dependence influence coefficient.

5. The photovoltaic power station fast frequency modulation response optimization control method according to claim 4 is characterized in that: The photovoltaic power station frequency regulation effect evaluation model is constructed based on machine learning according to the grid frequency regulation data and the energy storage system dependency data, specifically: the obtained frequency regulation capacity limitation coefficient, frequency regulation compensation effect abnormality coefficient and energy storage system dependency influence coefficient are used to construct the photovoltaic power station frequency regulation effect evaluation model, and generate the photovoltaic power station frequency regulation effect evaluation coefficient; The evaluation vector is constructed according to the photovoltaic power station frequency regulation effect evaluation model and the corresponding inverter power regulation range. Specifically, the evaluation vector includes the maximum value, the minimum value of the inverter power regulation range and the corresponding photovoltaic power station frequency regulation effect evaluation coefficient.

6. The photovoltaic power station fast frequency modulation response optimization control method according to claim 5 is characterized in that: The output of the photovoltaic power station frequency modulation effect evaluation model is combined with the rectangular coordinate system to establish a three-dimensional display model, specifically: The maximum and minimum values ​​of each power regulation range are marked on the rectangular coordinate system, the marked rectangular coordinate system is used as the base, and the output of the photovoltaic power station frequency regulation effect evaluation model corresponding to each power regulation range mark is used as the z-axis of the three-dimensional display model; Each evaluation vector is used as a data point to update the marked three-dimensional display model; Connect the data points of the three-dimensional display model and draw a three-dimensional fluctuation curve.

7. A device using the photovoltaic power station fast frequency modulation response optimization control method according to any one of claims 1 to 6, characterized in that: It includes a range random selection module, a data acquisition module, a model building module, a three-dimensional display module and an inverter power adjustment range selection module, and there are connections between the modules; A range random selection module is used to obtain the power adjustment ranges of several groups of inverters and apply them to the fast frequency response system of the photovoltaic power station respectively; A data acquisition module is used to obtain the grid frequency regulation data and energy storage system dependency data of each photovoltaic power station's fast frequency response system within the G time interval and the P time interval; A model building module is used to build a photovoltaic power station frequency regulation effect evaluation model based on machine learning according to the grid frequency regulation data and energy storage system dependency data, and to build an evaluation vector according to the photovoltaic power station frequency regulation effect evaluation model and the corresponding inverter power regulation range; A three-dimensional display module is used to use the minimum and maximum values ​​of the power regulation range as the horizontal axis and vertical axis of the rectangular coordinate system, respectively, combine the output of the photovoltaic power station frequency regulation effect evaluation model with the rectangular coordinate system to establish a three-dimensional display model, and apply each evaluation vector to the three-dimensional display model and draw a three-dimensional fluctuation curve; The power regulation range selection module of the inverter is used to perform data analysis on the three-dimensional fluctuation curve, obtain the best power regulation range of the inverter, and apply it to the optimization control of the fast frequency regulation response system of the photovoltaic power station.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the photovoltaic power station fast frequency regulation response optimization control method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the photovoltaic power station fast frequency regulation response optimization control method according to any one of claims 1 to 6.

Images