Networking type new energy power generation cluster dynamic characteristic analysis method, equipment, medium and product

Abstract

The invention discloses a dynamic characteristic analysis method, device, medium and product for a network-forming type new energy power generation cluster, and relates to the field of new energy power generation analysis, and the method comprises the steps: carrying out the hierarchical classification of the network-forming type new energy power generation cluster, and obtaining a plurality of subsystems; carrying out modeling on each subsystem to obtain a corresponding subsystem model; according to the historical oscillation signal data of the network construction type new energy power generation cluster and the output result of the corresponding subsystem model, a convolutional neural network algorithm is adopted to obtain an oscillation model; the oscillation model is used for outputting the output power of the photovoltaic power generation system, the output power of the wind power generation system and the performance and health condition of the energy storage system; and analyzing the oscillation signal data acquired in real time by using the oscillation model to obtain an analysis result of multi-dimensional quantification of the dynamic characteristic value of the network-forming type new energy power generation cluster heterogeneous unit.

Description

Technical Field

[0001] The present application relates to the field of new energy power generation analysis, and in particular to a method, equipment, medium and product for analyzing the dynamic characteristics of a grid-type new energy power generation cluster. Background Art

[0002] With the global emphasis on renewable energy and the rapid development of science and technology, new energy power generation clusters, especially grid-type new energy power generation clusters, have become an important part of the power system. Grid-type new energy power generation clusters integrate multiple new energy technologies on a large scale to form a stable and efficient power supply system, which is of great significance to the realization of green and low-carbon transformation of energy.

[0003] New energy power generation clusters usually contain multiple types of new energy power generation units, such as photovoltaic power generation units, hydroelectric generators, wind turbines, energy storage devices, etc. These units have obvious differences in dynamic characteristics, power generation principles, and response speeds, that is, they are heterogeneous. At the same time, new energy power generation clusters will be disturbed by many factors, such as geographical location, grid structure, climate factors, etc. Due to the interference of these factors, the complexity and diversity of new energy power generation clusters are further increased.

[0004] Due to the volatility and intermittency of renewable energy power generation, its output power will change over time, which will put higher requirements on the operation and scheduling of the power grid. Therefore, it is necessary to accurately analyze and quantify the dynamic characteristics of renewable energy power generation clusters, which is of great significance for formulating scientific scheduling strategies, optimizing power grid operation, and improving the ability to absorb new energy. How to accurately analyze and quantify the dynamic characteristics of renewable energy power generation clusters is an urgent problem to be solved. Summary of the invention

[0005] The purpose of this application is to provide a method, equipment, medium and product for analyzing the dynamic characteristics of a grid-type new energy power generation cluster, which can accurately analyze and quantify the dynamic characteristics of a new energy power generation cluster.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a method for analyzing dynamic characteristics of a grid-type new energy power generation cluster, and the method for analyzing dynamic characteristics of a grid-type new energy power generation cluster includes:

[0008] The grid-building new energy power generation cluster is hierarchically classified to obtain multiple subsystems; the subsystems include: photovoltaic power generation system, wind power generation system and energy storage system;

[0009] Model each subsystem to obtain the corresponding subsystem model;

[0010] According to the historical oscillation signal data of the grid-type new energy power generation cluster and the output results of the corresponding subsystem model, a convolutional neural network algorithm is used to obtain an oscillation model; the oscillation model is used to output the output power of the photovoltaic power generation system, the output power of the wind power generation system, and the performance and health status of the energy storage system; the oscillation signal data includes: power, voltage, wind speed and temperature;

[0011] The oscillation model is used to analyze the oscillation signal data obtained in real time, and the multi-dimensional quantitative analysis results of the dynamic characteristic values ​​of the heterogeneous units of the grid-connected new energy power generation cluster are obtained.

[0012] Optionally, modeling each subsystem to obtain a corresponding subsystem model specifically includes:

[0013] Using the formula Determine the output power model of the photovoltaic power generation system;

[0014] Using the formula P wind-out =0.5C P ρS wind v 3 Determine the output power model of the wind power generation system;

[0015] Using the formula Determine the mathematical model of the energy storage system;

[0016] Among them, P c is the final output power of photovoltaic power generation, W a and W b Corresponding to light intensity and standard light intensity, P z is the maximum power value obtained under standard environmental conditions, k is the power temperature coefficient, T e is the ambient temperature, T g is the panel operating temperature, P wind-out is the output power of the wind turbine, C P is the utilization factor of the wind turbine, ρ is the air density, S wind is the area swept by the fan blades, v is the wind speed, E is the electromotive force of the battery pack, E0 is the initial electromotive force, K is the polarization voltage constant, A and B are the voltage coefficient and capacity coefficient, Q n is the rated capacity, i (t) is the charge and discharge current, SOC is the remaining charge, is the number of battery components connected in series and parallel, t is time, exp() is a mathematical function, and C represents the charge and discharge rate of the battery.

[0017] Optionally, the convolutional neural network algorithm includes: a convolution layer, a pooling layer, a fully connected layer and an activation function layer.

[0018] Optionally, the oscillation signal data acquired in real time is analyzed by using the oscillation model to obtain the multi-dimensional quantitative analysis results of the dynamic characteristic values ​​of the heterogeneous units of the grid-forming new energy power generation cluster, which also includes:

[0019] The oscillation signal data acquired in real time is preprocessed; the preprocessing includes: cleaning, labeling, tiling and zero filling processing.

[0020] Optionally, the training process of the oscillation model specifically includes:

[0021] Group the historical oscillation signal data by characteristic values ​​under the same oscillation mode;

[0022] Determine the key characteristic value according to the preset damping ratio;

[0023] Normalize the key eigenvalues ​​under different oscillation modes and the output results of the corresponding subsystem models;

[0024] According to the normalized key eigenvalues ​​and the output results of the corresponding subsystem model, the oscillation model is trained using the regularization method.

[0025] Optionally, the trained oscillatory model is evaluated based on the mean error of the key eigenvalue results.

[0026] In a second aspect, the present application provides a network-based new energy power generation cluster dynamic characteristics analysis device, the network-based new energy power generation cluster dynamic characteristics analysis device comprising:

[0027] A hierarchical classification module is used to hierarchically classify the grid-building new energy power generation cluster to obtain multiple subsystems; the subsystems include: photovoltaic power generation system, wind power generation system and energy storage system;

[0028] The subsystem modeling module is used to model each subsystem and obtain the corresponding subsystem model;

[0029] The oscillation model determination module is used to obtain the oscillation model by using the convolutional neural network algorithm according to the historical oscillation signal data of the grid-type new energy power generation cluster and the output results of the corresponding subsystem model; the oscillation model is used to output the output power of the photovoltaic power generation system, the output power of the wind power generation system and the performance and health status of the energy storage system; the oscillation signal data includes: power, voltage, wind speed and temperature;

[0030] The analysis result determination module is used to analyze the oscillation signal data acquired in real time using the oscillation model to obtain the multi-dimensional quantitative analysis results of the dynamic characteristic values ​​of the heterogeneous units of the grid-forming new energy power generation cluster.

[0031] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for analyzing the dynamic characteristics of a grid-connected new energy power generation cluster.

[0032] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for analyzing the dynamic characteristics of a grid-connected new energy power generation cluster.

[0033] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method for analyzing the dynamic characteristics of a grid-connected new energy power generation cluster.

[0034] According to the specific embodiments provided in this application, this application has the following technical effects:

[0035] The present application provides a method, equipment, medium and product for analyzing the dynamic characteristics of a grid-type new energy power generation cluster, which hierarchically classifies the grid-type new energy power generation cluster, and models the three subsystems of the photovoltaic power generation system, the wind power generation system and the energy storage system respectively; then, according to the historical oscillation signal data of the grid-type new energy power generation cluster and the output results of the corresponding subsystem model, a convolutional neural network algorithm is used to obtain an oscillation model; that is, based on the oscillation model, the different manifestations of different characteristic values ​​of the grid-type new energy power generation cluster are divided, and based on the differentiated characteristic values ​​and manifestations of the grid-type new energy power generation cluster, the characteristic values ​​of the diversified heterogeneous units of the grid-type new energy power generation cluster are multi-dimensionally quantitatively analyzed qualitatively / quantitatively, and then the influencing factors and influencing laws of the inertia, damping and synchronization characteristics of the new energy power generation cluster system are revealed according to the analysis results. In different dimensions, the present application uses different manifestations of different characteristic values ​​of the new energy power generation cluster, considers the time-varying characteristics of the characteristic value attributes of the diversified heterogeneous units of the cluster, and conducts multi-dimensional quantitative analysis of the dynamic characteristics of the diversified heterogeneous units of the grid-type new energy power generation cluster, and can accurately analyze and quantify the dynamic characteristics of the new energy power generation cluster, which is of great significance for formulating scientific scheduling strategies, optimizing power grid operation, and improving the new energy absorption capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1This is a schematic diagram of a flow chart of a method for analyzing dynamic characteristics of a grid-type new energy power generation cluster in one embodiment of the present application;

[0038] Figure 2 It is a schematic diagram of the topological structure of the photovoltaic power generation system;

[0039] Figure 3 is a schematic diagram of the equivalent circuit of a photovoltaic module;

[0040] Figure 4 Schematic diagram of the topological structure of a wind power generation system. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0042] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0043] In an exemplary embodiment, Figure 1 As shown, a method for analyzing dynamic characteristics of a grid-type new energy power generation cluster is provided, and the method includes the following S101 to S104. Among them:

[0044] S101, hierarchically classify the grid-building new energy power generation cluster to obtain multiple subsystems; the subsystems include: a photovoltaic power generation system, a wind power generation system, and an energy storage system;

[0045] S102, modeling each subsystem to obtain a corresponding subsystem model;

[0046] like Figure 2 As shown in the figure, the photovoltaic power generation system mainly includes photovoltaic arrays, photovoltaic inverters and their control systems, step-up transformers, etc. Among them, Figure 3 is the equivalent circuit of the photovoltaic module, Figure 3 The PV module equivalent circuit in represents the nonlinear characteristics of an ideal solar PV cell based on solar irradiance (G) and temperature (T).

[0047] The output power of photovoltaic cells is affected by many factors, the most important of which are changes in solar radiation intensity and ambient temperature. Due to these factors, the current output of photovoltaic cells shows obvious nonlinear characteristics. Photovoltaic cells have a negative temperature coefficient, that is, when the surface temperature of the cell rises, its output power will decrease accordingly. In order to calculate the operating temperature of the solar panel, it can be estimated by the following formula:

[0048]

[0049] Among them, T e is the ambient temperature; T r represents the actual temperature of the battery surface; W is the solar radiation value. Then the output power model of the photovoltaic power generation system is:

[0050]

[0051] Where P c is the final output power of photovoltaic power generation; W a and W b Corresponding to light intensity and standard light intensity, P z is the maximum power value obtained under standard environmental conditions; k is the power temperature coefficient, usually -0.0047 / ℃; T e is the ambient temperature; T g is the working temperature of the solar panel. e The change makes the working temperature T of the solar panel r Also changes with the ambient temperature T e The impact of photovoltaic power generation eventually makes the output power P c Also affected.

[0052] like Figure 4 As shown in Figure 1, the basic principle of wind power generation is to use wind power to drive the rotor of a wind turbine to rotate, and then convert mechanical energy into electrical energy through the generator. The power absorbed by a wind turbine depends on the product of wind force and wind speed. Since wind force is proportional to the square of wind speed, the power absorbed by a wind turbine is proportional to the cube of wind speed. The absorbed power of a wind turbine is expressed by the following formula:

[0053] P wind-in =0.5ρS wind v 3 ;

[0054] Where P wind-in is the input power of the wind turbine; ρ is the air density, usually 1.25kg / m3, S wind is the area swept by the fan blades, and v is the wind speed.

[0055] In the actual operation of wind turbines, due to the wear of mechanical components and the loss in the energy conversion process, it is impossible to completely convert the captured wind energy into electrical energy. Therefore, when calculating the output power of wind turbines, it is necessary to introduce an efficiency coefficient, which is usually less than 1, to reflect the actual conversion efficiency. The output power model of the wind turbine can be expressed as:

[0056] P wind-out =0.5C P ρS wind v 3 ;

[0057] Where P wind-Out is the output power of the wind turbine, C P is the utilization factor of the wind turbine.

[0058] An energy storage system is a device or system used to store electrical energy. It can store energy when electricity demand is low and release energy when demand is high. In renewable energy power generation systems, batteries play a key role in regulating power. Since batteries can undergo multiple charge and discharge cycles, they can store excess electricity when solar photovoltaic and wind power generation generate excess electricity. When the overall power generation of the system is insufficient to meet demand due to weather changes, the batteries can release the stored energy to supplement the system's energy and ensure that the system can continuously and stably provide the required power to the load, thereby maintaining the power balance of the power system. Therefore, the mathematical model of the energy storage system is:

[0059]

[0060] Where, E is the electromotive force of the battery pack (V); E0 is the initial electromotive force (V); K is the polarization voltage constant; A and B are the voltage coefficient and capacity coefficient; Q n is the rated capacity (Ah); i (t) is the charge and discharge current (A); SOC is the remaining charge (remaining charge ratio); Represents the number of battery components connected in series and parallel, t is time, exp() is a mathematical function, and C represents the charge and discharge rate of the battery.

[0061] S103, according to the historical oscillation signal data of the grid-type new energy power generation cluster and the output results of the corresponding subsystem model, a convolutional neural network (CNN) algorithm is used to obtain an oscillation model; the oscillation model is used to output the output power of the photovoltaic power generation system, the output power of the wind power generation system, and the performance and health status of the energy storage system; the oscillation signal data includes: power, voltage, wind speed and temperature; the convolutional neural network algorithm includes: convolution layer, pooling layer, full connection layer and activation function layer. The input of the convolutional neural network algorithm is input in the form of a two-dimensional matrix. After a series of eigenvalue extraction and abstract learning links, the output power of the photovoltaic power generation system, the output power of the wind power generation system, and the performance and health status of the energy storage system are obtained, and the dynamic eigenvalue multi-dimensional quantitative qualitative / quantitative analysis of the diversified heterogeneous units of the grid-type new energy power generation cluster is realized to obtain the analysis results.

[0062] The training process of the oscillating model specifically includes:

[0063] S1, grouping the historical oscillation signal data by characteristic values ​​under the same oscillation mode;

[0064] S2, determining the key characteristic value according to the preset damping ratio;

[0065] S3, normalizing the key eigenvalues ​​under different oscillation modes and the output results of the corresponding subsystem models;

[0066] S4, according to the normalized key eigenvalues ​​and the output results of the corresponding subsystem model, the oscillation model is trained using a regularization method.

[0067] After training is completed, the trained oscillation model is evaluated based on the mean error of the key eigenvalue results.

[0068] The following is an explanation through a specific embodiment. Six sets of data are recorded starting from a certain time point and continuing for a period of time: t, t-t0, t-2t0, t-3t0, t-4t0, t-5t0, t is selected as the time interval, and the features of the input data are automatically extracted through the convolution layer of CNN. Considering that the input of CNN is two-dimensional data, the power mode of each node and branch in each subsystem needs to be arranged in a matrix form:

[0069]

[0070] In the formula, X represents the power variable, x nn is the power of the nth row and nth column, x ij is the power of the i-th row and j-th column, P ij is the active power of the i-th row and j-th column, Q ij is the reactive power of the i-th row and j-th column.

[0071] Arrange the power variables of the time periods t, t-t0, t-2t0, t-3t0, t-4t0, and t-5t0 into a matrix form according to the above formula, and we get:

[0072]

[0073] In order to calculate the results accurately, two aspects are considered: for the spatial flow, Xt is used as the input variable to obtain the topological structure and characteristic information of the system at different powers at time t; in terms of the time flow, the power differences at six time points are used as input variables to avoid the mutual influence between different time points and different faults.

[0074]

[0075] The set consisting of power variable X and power variable M is:

[0076] I=[X 1 , X 2 , ..., X n ];

[0077] J=[M 1 , M 2 , ..., M n ];

[0078] The set of key power eigenvalues ​​obtained from the training set is Y:

[0079]

[0080] At time t, the motion trend vector of the power key characteristic value is set to the difference between the power key value at time t+t0 and the power key value at time t. In this way, the motion trend vector set Z of each power key characteristic value can be obtained:

[0081]

[0082] Where n represents the amount of data, m represents the number of key oscillation modes, and z i (i=1, 2, ..., m) is the eigenvalue corresponding to the i-th key oscillation mode;

[0083] Normalize sets I and J to obtain:

[0084]

[0085] In the formula, x and t are the original values ​​of the power matrix, x′ and m′ are the values ​​of the power matrix after the change, and μ and σ are the mean and standard deviation of each element in the power matrix, respectively. Then, the Dropout (regularization) method is used to regularize the oscillation model, so that it becomes:

[0086]

[0087] In the formula, α is the regularization parameter and ω is the set of connection weights of the fully connected layer of the convolutional neural network (CNN). After training, the loss function of the oscillating network reaches the minimum value.

[0088] Finally, calculate the average error E of the learning results E :

[0089]

[0090] In the formula, R is the number of test sets, z′ i is the motion trend vector of the learning eigenvalue, z i is the actual motion trend vector.

[0091] By comparing the actual and predicted values, the category of the unit involved in the oscillation mode can be determined. Then, by comparing the oscillation decay results, the dynamic stability of the power system can be evaluated.

[0092] S104, using the oscillation model to analyze the oscillation signal data acquired in real time, and obtain the multi-dimensional quantitative analysis results of the dynamic characteristic values ​​of the heterogeneous units of the grid-forming new energy power generation cluster.

[0093] Before S104, it also included:

[0094] The oscillation signal data acquired in real time is preprocessed; the preprocessing includes: cleaning, labeling, tiling and zero filling processing.

[0095] In this application, based on the output of the oscillation model, the inertial characteristics of the power generation cluster under different operating conditions can be extracted, and the influencing factors and laws of the inertial characteristics can be clarified; the oscillation model is used to identify the oscillation signal in the power generation cluster, and the characteristics of the oscillation signal and the output of the oscillation model are combined to reveal the influencing factors and laws of the system damping characteristics; the oscillation model is used to monitor the synchronization state of the power generation cluster to reveal the influencing factors and laws of the synchronization characteristics of the new energy power generation cluster.

[0096] Through the oscillation model, it is found that different types of generators (such as wind power and solar energy) have different inertial responses. The change in speed directly affects the inertia of the system. The instantaneous change of the load will affect the speed of the generator and its inertial response. Increasing the number of generators usually increases the overall inertia of the system. Slowly changing loads can provide better inertial support, while rapidly changing loads may cause system instability.

[0097] Different control strategies can affect the damping performance of the system through the oscillation model. Different interconnection methods (such as grid connection methods) can affect the damping characteristics of the power system. The topology of the system affects the distribution and characteristics of the damping. Better control strategies can improve the damping performance of the system and enhance stability. Appropriate interconnection methods can reduce the oscillation amplitude of the system and improve synchronization stability.

[0098] A small deviation in the frequency obtained through the oscillation model will lead to a decrease in the synchronization between the generators, and the overall inertia affects the synchronization stability of the system. The smaller the phase difference between the generators, the better the synchronization performance of the system. Increasing the overall inertia of the system can improve the synchronization stability, while too high inertia may cause the system to respond more slowly.

[0099] Based on the same inventive concept, the embodiment of the present application also provides a network-type new energy power generation cluster dynamic characteristics analysis device for implementing the above-mentioned network-type new energy power generation cluster dynamic characteristics analysis method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more network-type new energy power generation cluster dynamic characteristics analysis device embodiments provided below can refer to the above limitations on the network-type new energy power generation cluster dynamic characteristics analysis method, which will not be repeated here.

[0100] In an exemplary embodiment, a network-based new energy power generation cluster dynamic characteristics analysis device is provided, comprising:

[0101] A hierarchical classification module is used to hierarchically classify the grid-building new energy power generation cluster to obtain multiple subsystems; the subsystems include: photovoltaic power generation system, wind power generation system and energy storage system;

[0102] The subsystem modeling module is used to model each subsystem and obtain the corresponding subsystem model;

[0103] The oscillation model determination module is used to obtain the oscillation model by using the convolutional neural network algorithm according to the historical oscillation signal data of the grid-type new energy power generation cluster and the output results of the corresponding subsystem model; the oscillation model is used to output the output power of the photovoltaic power generation system, the output power of the wind power generation system and the performance and health status of the energy storage system; the oscillation signal data includes: power, voltage, wind speed and temperature;

[0104] The analysis result determination module is used to analyze the oscillation signal data acquired in real time using the oscillation model to obtain the multi-dimensional quantitative analysis results of the dynamic characteristic values ​​of the heterogeneous units of the grid-forming new energy power generation cluster.

[0105] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, 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, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for analyzing the dynamic characteristics of a network-based new energy power generation cluster is implemented.

[0106] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0107] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0108] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0109] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0110] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0111] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0112] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for analyzing the dynamic characteristics of a grid-connected new energy power generation cluster, characterized in that: The dynamic characteristics analysis method of the grid-type new energy power generation cluster includes: The grid-building new energy power generation cluster is hierarchically classified to obtain multiple subsystems; the subsystems include: photovoltaic power generation system, wind power generation system and energy storage system; Model each subsystem to obtain the corresponding subsystem model; According to the historical oscillation signal data of the grid-type new energy power generation cluster and the output results of the corresponding subsystem model, a convolutional neural network algorithm is used to obtain an oscillation model; the oscillation model is used to output the output power of the photovoltaic power generation system, the output power of the wind power generation system, and the performance and health status of the energy storage system; the oscillation signal data includes: power, voltage, wind speed and temperature; The oscillation model is used to analyze the oscillation signal data obtained in real time, and the multi-dimensional quantitative analysis results of the dynamic characteristic values ​​of the heterogeneous units of the grid-connected new energy power generation cluster are obtained.

2. The method for analyzing dynamic characteristics of a grid-type new energy power generation cluster according to claim 1 is characterized in that: The modeling of each subsystem to obtain a corresponding subsystem model specifically includes: Using the formula Determine the output power model of the photovoltaic power generation system; Using the formula P wind-out =0.5C P ρS wind v 3 Determine the output power model of the wind power generation system; Using the formula Determine the mathematical model of the energy storage system; Among them, P c is the final output power of photovoltaic power generation, W a and W b Corresponding to light intensity and standard light intensity, P z is the maximum power value obtained under standard environmental conditions, k is the power temperature coefficient, T e is the ambient temperature, T g is the panel operating temperature, P wind-out is the output power of the wind turbine, C P is the utilization factor of the wind turbine, ρ is the air density, S wind is the area swept by the fan blades, v is the wind speed, E is the electromotive force of the battery pack, E0 is the initial electromotive force, K is the polarization voltage constant, A and B are the voltage coefficient and capacity coefficient, Q n is the rated capacity, i (t) is the charge and discharge current, SOC is the remaining charge, is the number of battery components connected in series and parallel, t is time, exp() is a mathematical function, and C represents the charge and discharge rate of the battery.

3. The method for analyzing dynamic characteristics of a grid-type new energy power generation cluster according to claim 1 is characterized in that: The convolutional neural network algorithm includes: a convolution layer, a pooling layer, a fully connected layer and an activation function layer.

4. The method for analyzing dynamic characteristics of a grid-type new energy power generation cluster according to claim 1 is characterized in that: The oscillation signal data acquired in real time is analyzed by using the oscillation model to obtain the multi-dimensional quantitative analysis results of the dynamic characteristic values ​​of the heterogeneous units of the grid-type new energy power generation cluster, which also includes: The oscillation signal data acquired in real time is preprocessed; the preprocessing includes: cleaning, labeling, tiling and zero filling processing.

5. The method for analyzing dynamic characteristics of a grid-type new energy power generation cluster according to claim 1 is characterized in that: The training process of the oscillating model specifically includes: Group the historical oscillation signal data by characteristic values ​​under the same oscillation mode; Determine the key characteristic value according to the preset damping ratio; Normalize the key eigenvalues ​​under different oscillation modes and the output results of the corresponding subsystem models; According to the normalized key eigenvalues ​​and the output results of the corresponding subsystem model, the oscillation model is trained using the regularization method.

6. The method for analyzing dynamic characteristics of a grid-type new energy power generation cluster according to claim 5 is characterized in that: The trained oscillatory models are evaluated based on the mean error of the key eigenvalue results.

7. A network-building new energy power generation cluster dynamic characteristics analysis device, characterized in that: The network-building new energy power generation cluster dynamic characteristics analysis device includes: A hierarchical classification module is used to hierarchically classify the grid-building new energy power generation cluster to obtain multiple subsystems; the subsystems include: photovoltaic power generation system, wind power generation system and energy storage system; The subsystem modeling module is used to model each subsystem and obtain the corresponding subsystem model; The oscillation model determination module is used to obtain the oscillation model by using the convolutional neural network algorithm according to the historical oscillation signal data of the grid-type new energy power generation cluster and the output results of the corresponding subsystem model; the oscillation model is used to output the output power of the photovoltaic power generation system, the output power of the wind power generation system and the performance and health status of the energy storage system; the oscillation signal data includes: power, voltage, wind speed and temperature; The analysis result determination module is used to analyze the oscillation signal data acquired in real time using the oscillation model to obtain the multi-dimensional quantitative analysis results of the dynamic characteristic values ​​of the heterogeneous units of the grid-forming new energy power generation cluster.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for analyzing dynamic characteristics of a grid-connected new energy power generation cluster as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for analyzing dynamic characteristics of a grid-connected new energy power generation cluster described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for analyzing dynamic characteristics of a grid-connected new energy power generation cluster described in any one of claims 1 to 6 is implemented.

Images