Compressed air energy storage frequency regulation method based on neural network

Abstract

This application relates to the field of new energy technology, and in particular to a neural network-based frequency regulation method for compressed air energy storage. The method includes: acquiring the inlet mass flow rate of the compressor unit in the compressed air energy storage system, the frequency deviation of the power system, and the rate of change of the frequency deviation; determining whether the frequency deviation meets certain frequency regulation activation conditions of the compressed air energy storage system; when the frequency deviation meets the certain frequency regulation activation conditions, adjusting the output power of the compressed air energy storage system based on the inlet mass flow rate and a pre-trained neural network, and adjusting the frequency of the power system based on the adjusted output power until the frequency meets a preset frequency stability condition. This solves the technical problems in related technologies, such as the inability to fully utilize the intelligent processing capabilities of neural networks for multi-dimensional parameters, the inability to reflect the advantages of compressed air energy storage systems such as fast response speed and environmentally friendly high-quality transient frequency regulation power supply, and the low accuracy of active power control in compressed air energy storage systems.

Description

Technical Field

[0001] This application relates to the field of new energy technology, and in particular to a method for frequency regulation of compressed air energy storage based on neural networks. Background Technology

[0002] In recent years, with the increasing severity of environmental pollution and resource shortages, renewable energy has gradually gained attention, and traditional power systems are shifting towards sustainable development. However, with the large-scale integration of renewable energy into the grid, the randomness of its output will cause problems such as grid frequency imbalance, posing challenges to the economic operation of the grid and power quality. Compressed air energy storage, in the field of frequency regulation, has the advantages of large energy storage capacity, wide frequency regulation range, and inherent electromechanical transient and rotational inertia characteristics, thus allowing for good coupling with the power grid.

[0003] In related technologies, the acquired grid frequency deviation, energy storage and release operation data of air-source energy storage units, wind turbine operation data, and wind information of the area where the wind turbine is located can be input into a neural network model to adjust the energy storage power, energy release power, and electromagnetic power of the air-source energy storage unit and the wind turbine. Alternatively, by establishing a gas storage model for a gas storage tank and a thermal storage model for a thermal storage tank, the frequency regulation droop control coefficient of compressed air energy storage can be obtained, and then the adjustment command of the mass flow rate of the regulating valve can be adjusted.

[0004] However, research on compressed air energy storage mainly involves thermodynamic analysis of system structure and system efficiency, which cannot fully utilize the intelligent processing capabilities of neural networks for multi-dimensional parameters. It also fails to demonstrate the advantages of compressed air energy storage systems, such as fast response speed and environmentally friendly high-quality transient frequency modulation power supply. Furthermore, the active power control accuracy of compressed air energy storage systems is relatively low, which urgently needs improvement. Summary of the Invention

[0005] This application provides a neural network-based compressed air energy storage frequency regulation method to solve the problems in related technologies, such as the inability to fully utilize the intelligent processing capabilities of neural networks for multi-dimensional parameters, the inability to reflect the advantages of compressed air energy storage systems such as fast response speed, environmentally friendly high-quality transient frequency regulation power supply, and low accuracy of active power control in compressed air energy storage systems.

[0006] The first aspect of this application provides a neural network-based compressed air energy storage frequency regulation method, comprising the following steps: obtaining the intake mass flow rate of the compressor unit in the compressed air energy storage system, the frequency deviation of the power system, and the frequency deviation change rate; determining whether the frequency deviation meets the preset frequency regulation start condition of the compressed air energy storage system; if the frequency deviation meets the preset frequency regulation start condition, adjusting the output power of the compressed air energy storage system based on the intake mass flow rate and the pre-trained neural network, so as to regulate the frequency of the power system based on the adjusted output power, until the frequency meets the preset frequency stability condition.

[0007] Optionally, in one embodiment of this application, adjusting the output power of the compressed air energy storage system based on the intake mass flow rate and a pre-trained neural network, and adjusting the frequency of the power system based on the adjusted output power until the frequency meets a preset frequency stability condition, includes: inputting the intake mass flow rate, the frequency deviation, and the frequency deviation change rate into a pre-trained neural network to obtain target proportional parameters and target integral parameters of the compressed air energy storage system, and controlling the compressed air energy storage system to enter a short-term boost phase based on the target proportional parameters and the target integral parameters; when the compressed air energy storage system is in the short-term boost phase, determining the frequency deviation... The system determines whether the frequency deviation is greater than a first preset frequency deviation of the power system, or whether the frequency deviation is less than a second preset frequency deviation of the power system, wherein the first preset frequency deviation is greater than the second preset frequency deviation; if the frequency deviation is greater than the first preset frequency deviation, the target proportional parameter is the maximum value of the proportional parameter that the compressed air energy storage system can accept, and the output power is adjusted based on the maximum value and the target integral parameter; if the frequency deviation is less than the second preset frequency deviation, the target integral parameter is the minimum value of the integral parameter that the compressed air energy storage system can accept, and the output power is adjusted based on the target proportional parameter and the minimum value.

[0008] Optionally, in one embodiment of this application, adjusting the output power of the compressed air energy storage system based on the intake mass flow rate and a pre-trained neural network, and adjusting the frequency of the power system based on the adjusted output power until the frequency meets a preset frequency stability condition, further includes: determining a frequency in the power system that maintains frequency stability based on the output power, and controlling the compressed air energy storage system to enter a power transition phase based on the frequency; when the compressed air energy storage system is in the power transition phase, if the intake mass flow rate is less than or equal to the upper limit of the intake mass flow rate, determining whether the frequency meets the preset frequency stability condition; if the frequency meets the preset frequency stability condition, then prohibiting the use of the neural network to adjust the output power.

[0009] Optionally, in one embodiment of this application, before adjusting the output power of the compressed air energy storage system based on the intake mass flow rate and the pre-trained neural network, the method further includes: constructing an input layer of a preset neural network based on intake mass flow rate neurons, frequency deviation neurons, and frequency deviation change rate neurons; constructing an output layer of the preset neural network based on proportional parameter neurons and integral parameter neurons; and training the preset neural network using a target loss function to obtain a trained neural network.

[0010] Optionally, in one embodiment of this application, the formula for calculating the target loss function may be, but is not limited to, the following:

[0011]

[0012] Among them, K p With K i K′ represents the target scaling parameter and target integral parameter output by the neural network. p With K′ i Let m be the ideal scaling parameter and the ideal integral parameter for the output, m be the sample size, and L be the loss function.

[0013] Optionally, in one embodiment of this application, the calculation formulas for the target proportional parameter and the target integral parameter may be, but are not limited to, as follows:

[0014]

[0015] Among them, h j b j C jLet $\mathbf$ be the basis vector, $\mathbf$ function, and $\mathbf$ center point vector value of the $j$-th neuron, respectively. Let $\mathbf$ be the Euclidean norm, $\mathbf$ be the weight vector from the hidden layer to the output layer, and $X$ be a ternary vector. The ternary vector can be, but is not limited to, represented by $X = (β, Δf, Δf′)$, where $β$ is the intake mass flow rate of the compressor, $Δf$ is the frequency deviation of the power system, and $Δf′$ is the rate of change of the frequency deviation of the power system.

[0016] A second aspect of this application provides a neural network-based compressed air energy storage frequency regulation device, comprising: an acquisition module for acquiring the inlet mass flow rate of a compressor unit in a compressed air energy storage system, the frequency deviation of a power system, and the frequency deviation change rate; a judgment module for judging whether the frequency deviation meets a preset frequency regulation activation condition of the compressed air energy storage system; and a frequency regulation module for adjusting the output power of the compressed air energy storage system based on the inlet mass flow rate and a pre-trained neural network when the frequency deviation meets the preset frequency regulation activation condition, so as to regulate the frequency of the power system based on the adjusted output power until the frequency meets a preset frequency stability condition.

[0017] Optionally, in one embodiment of this application, the frequency modulation module includes: an input unit, configured to input the intake air mass flow rate, the frequency deviation, and the frequency deviation change rate into a pre-trained neural network to obtain a target proportional parameter and a target integral parameter of the compressed air energy storage system, and control the compressed air energy storage system to enter a short-term boost phase based on the target proportional parameter and the target integral parameter; a first judgment unit, configured to determine whether the frequency deviation is greater than a first preset frequency deviation of the power system, or whether the frequency deviation is less than a second preset frequency deviation of the power system, wherein the first preset frequency deviation is greater than the second preset frequency deviation, when the frequency deviation is greater than the first preset frequency deviation, the target proportional parameter is the maximum value of the proportional parameter acceptable to the compressed air energy storage system, and the output power is adjusted based on the maximum value and the target integral parameter; a second frequency modulation unit, configured to determine whether the target integral parameter is the minimum value of the integral parameter acceptable to the compressed air energy storage system when the frequency deviation is less than the second preset frequency deviation, and the output power is adjusted based on the target proportional parameter and the minimum value.

[0018] Optionally, in one embodiment of this application, the frequency modulation module further includes: a determining unit, configured to determine the frequency for maintaining frequency stability in the power system based on the output power, and control the compressed air energy storage system to enter a power transition phase based on the frequency; a second judging unit, configured to judge whether the frequency meets the preset frequency stability condition when the compressed air energy storage system is in the power transition phase, provided that the intake mass flow rate is less than or equal to the upper limit of the intake mass flow rate; and a third frequency modulation unit, configured to prohibit the use of the neural network to adjust the output power when the frequency meets the preset frequency stability condition.

[0019] Optionally, in one embodiment of this application, it further includes: a first construction module, used to construct an input layer of a preset neural network based on an intake mass flow rate neuron, a frequency deviation neuron, and a frequency deviation change rate neuron before adjusting the output power of the compressed air energy storage system based on the intake mass flow rate and the pre-trained neural network; a second construction module, used to construct an output layer of the preset neural network based on a proportional parameter neuron and an integral parameter neuron; and a training module, used to train the preset neural network using a target loss function to obtain a trained neural network.

[0020] Optionally, in one embodiment of this application, the formula for calculating the target loss function may be, but is not limited to, the following:

[0021]

[0022] Among them, K p With K i K′ represents the target scaling parameter and target integral parameter output by the neural network. p With K′ i Let m be the ideal scaling parameter and the ideal integral parameter for the output, m be the sample size, and L be the loss function.

[0023] Optionally, in one embodiment of this application, the calculation formulas for the target proportional parameter and the target integral parameter may be, but are not limited to, as follows:

[0024]

[0025] Among them, h j b j C jLet $\mathbf$ be the basis vector, $\mathbf$ function, and $\mathbf$ center point vector value of the $j$-th neuron, respectively. Let $\mathbf$ be the Euclidean norm, $\mathbf$ be the weight vector from the hidden layer to the output layer, and $X$ be a ternary vector. The ternary vector can be, but is not limited to, represented by $X = (β, Δf, Δf′)$, where $β$ is the intake mass flow rate of the compressor, $Δf$ is the frequency deviation of the power system, and $Δf′$ is the rate of change of the frequency deviation of the power system.

[0026] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the neural network-based compressed air energy storage frequency modulation method as described in the above embodiments.

[0027] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described neural network-based compressed air energy storage frequency modulation method.

[0028] A fifth aspect of this application provides a computer program product, including a computer program that, when executed, implements the above-described neural network-based compressed air energy storage frequency regulation method.

[0029] In this embodiment, when the frequency deviation meets the preset frequency regulation start-up conditions of the compressed air energy storage system, the obtained intake mass flow rate of the compressor unit, the frequency deviation of the power system, and the rate of change of frequency deviation are input into a pre-trained neural network to adjust the output power of the compressed air energy storage system until a certain frequency stability condition is met. This fully utilizes the intelligent processing capability of the neural network for multi-dimensional parameters, achieving optimal real-time adaptive tuning of the frequency regulation controller parameters in the power system. It maximizes the advantages of the compressed air energy storage system, such as fast response speed and environmentally friendly high-quality transient frequency regulation power supply, improving the accuracy of active power control and the frequency stability of the power system. Therefore, it solves the problems in related technologies, such as the inability to fully utilize the intelligent processing capability of the neural network for multi-dimensional parameters, the inability to fully demonstrate the advantages of the compressed air energy storage system, such as fast response speed and environmentally friendly high-quality transient frequency regulation power supply, and the low accuracy of active power control in the compressed air energy storage system.

[0030] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0031] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0032] Figure 1 This is a block diagram of a system for implementing a neural network-based compressed air energy storage frequency regulation method according to an embodiment of this application;

[0033] Figure 2 This is a flowchart of a neural network-based compressed air energy storage frequency regulation method provided according to an embodiment of this application;

[0034] Figure 3 This is a flowchart illustrating the working principle of a neural network-based compressed air energy storage frequency modulation method according to an embodiment of this application;

[0035] Figure 4 This is a block diagram of a neural network-based compressed air energy storage frequency modulation device according to an embodiment of this application;

[0036] Figure 5 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0037] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0038] The following describes a neural network-based frequency regulation method for compressed air energy storage according to embodiments of this application, with reference to the accompanying drawings. Addressing the issues mentioned in the background art, such as the inability to fully utilize the intelligent processing capabilities of neural networks for multi-dimensional parameters, the inability to fully leverage the advantages of compressed air energy storage systems (such as fast response speed and environmentally friendly transient frequency regulation power supply), and the low accuracy of active power control in compressed air energy storage systems, this application provides a neural network-based frequency regulation method for compressed air energy storage. In this method, when the frequency deviation meets the preset frequency regulation activation conditions of the compressed air energy storage system, the acquired intake mass flow rate of the compressor unit, the frequency deviation of the power system, and the rate of change of frequency deviation are input into a pre-trained neural network to adjust the output power of the compressed air energy storage system until a certain frequency stability condition is met. This fully utilizes the intelligent processing capabilities of neural networks for multi-dimensional parameters, achieving optimal real-time adaptive tuning of the frequency controller parameters in the power system. This maximizes the advantages of compressed air energy storage systems, such as fast response speed and environmentally friendly transient frequency regulation power supply, thereby improving the accuracy of active power control and the frequency stability of the power system. This solves the problems in related technologies, such as the inability to fully utilize the intelligent processing capabilities of neural networks for multi-dimensional parameters, the inability to demonstrate the advantages of compressed air energy storage systems, such as fast response speed and environmentally friendly high-quality transient frequency modulation power supplies, and the low accuracy of active power control in compressed air energy storage systems.

[0039] Before introducing the neural network-based compressed air energy storage frequency regulation method proposed in the embodiments of this application, we will first introduce a system that implements the neural network-based compressed air energy storage frequency regulation method in one embodiment of this application.

[0040] Specifically, Figure 1 This is a block diagram of a system for implementing a neural network-based compressed air energy storage frequency regulation method according to an embodiment of this application.

[0041] like Figure 1 As shown, 101 is the data acquisition device, 102 is the computing device, 103 is the control device, 104 is the frequency detector, 105 is the frequency differential detector, 106 is the air mass flow meter, 107 is the input layer, 108 is the hidden layer, 109 is the output layer, 110 is the proportional element, 111 is the integral element, and 112 is the compressor inlet valve.

[0042] The data acquisition device 101 may include, but is not limited to, a frequency detector 104, a frequency differential detector 105, and an air mass flow meter 106.

[0043] Furthermore, in this embodiment of the application, the frequency detector 104 can detect the real-time frequency of the power system at a sampling frequency of ten times per second, and the collected sample points are smoothed and noise-reduced by a five-point triple filtering algorithm.

[0044] The frequency differential detector 105 is responsible for approximating the frequency change rate by using finite difference to calculate the smoothed data from the frequency detector.

[0045] The air mass flow rate meter 106 detects the air mass flow rate at the compressor inlet valve at the same sampling frequency of ten times per second.

[0046] For example, in this embodiment of the application, the power system can select a reference frequency of 50Hz. If the frequency deviation of the power system meets certain frequency regulation start conditions of the compressed air energy storage system, such as the frequency deviation being greater than the maximum value Δf of the frequency regulation dead zone of the compressed air energy storage unit... gate And the duration is greater than the threshold time t gate Then all the information from the three will be sent to the computing device 102 for further processing.

[0047] The computing device 102 employs a neural network model, which includes a pre-trained neural network, and may include, but is not limited to, an input layer 107, a hidden layer 108, and an output layer 109.

[0048] Furthermore, in this embodiment, the input layer 107 includes three neurons, which respectively represent the intake mass flow rate neuron of the compressor, the frequency deviation neuron of the power system, and the frequency deviation rate of change neuron of the power system.

[0049] The output layer 109 contains two neurons, representing the proportional parameter neuron and the integral parameter neuron of the output, respectively.

[0050] Hidden layer 108 is a superposition of several layers of intermediate neurons. In this embodiment, the number of neurons, their connection method, and weight parameters are unknown. However, the parameters can be trained to more closely approximate the real power system. The training method employs a loss function approach, using historical operating data of the power plant as the training set. Each time, the intake mass flow rate of the β compressor, the frequency deviation of the power system (Δf), and the rate of change of the frequency deviation of the power system (Δf′) are input, and then the output K is compared. p Scale parameter and K i The difference between the integral parameter and the actual value is considered, and the loss function is defined as the Euclidean distance between the output value and the ideal value.

[0051] It is understood that the training objective of the neural network in this application embodiment is to minimize the value of the loss function, and the solution algorithm can adopt the radial basis function method.

[0052] The control device may include, but is not limited to, a proportional element 110 and an integral element 111, which are directly connected to the compressor inlet valve 112. By controlling the valve opening, the inlet mass flow rate of the compressor is controlled, thereby achieving the purpose of setting the power and regulating the frequency of the power system.

[0053] Furthermore, in the embodiments of this application, the main function of the proportional element 110 is to amplify the frequency deviation, generate a control signal proportional to the frequency deviation, and apply it to the controlled object to reduce the deviation, but at the same time, it will inevitably introduce hysteresis and overshoot.

[0054] The main function of the integrator 111 is to accumulate the frequency deviation history and generate a control signal to eliminate the frequency deviation, thus enabling error-free regulation of the power system.

[0055] It should be noted that, in order to achieve rapid frequency regulation and reduce the impact on the power system as much as possible, the control process in this embodiment can be divided into two stages:

[0056] The first stage is the short-term power generation stage, in which the compressor releases kinetic energy to support power. The start time of this stage is when the compressed air energy storage unit participates in frequency regulation, and the end time is when it enters the power tracking stage.

[0057] In this application embodiment, the frequency regulation in the first stage follows the following principles: when the frequency deviation is large, the largest proportional coefficient is adopted to accelerate the timely power response of the frequency-regulated power system; when the frequency deviation is small, the power system has already reached a stable state, and the smallest proportional coefficient is adopted to maintain the frequency stability of the power system.

[0058] The second stage is the power transition stage, which maintains the frequency of the power system at a constant value while ensuring that the intake mass flow rate does not exceed the limit. When the frequency of the power system meets certain frequency stability conditions, such as the frequency stabilizing at Δf... gate Within and the duration is greater than t gate When this occurs, the frequency regulation process can be considered complete, and the compressed air energy storage unit resumes maximum power point tracking operation.

[0059] Specifically, Figure 2 This is a flowchart of a neural network-based compressed air energy storage frequency regulation method provided according to an embodiment of this application.

[0060] like Figure 2 As shown, the neural network-based compressed air energy storage frequency regulation method includes the following steps:

[0061] In step S201, the intake mass flow rate of the compressor unit in the compressed air energy storage system, the frequency deviation of the power system, and the frequency deviation change rate are obtained.

[0062] As one possible implementation method, embodiments of this application can obtain the intake mass flow rate of the compressor unit in the compressed air energy storage system, the frequency deviation of the power system, and the frequency deviation change rate.

[0063] For example, such as Figure 1 As shown, in this embodiment of the application, a frequency detector can be used to detect the real-time frequency of the power system, and then a frequency differential detector can be used to calculate the frequency deviation and the frequency deviation change rate, while an air mass flow meter can detect the intake air mass flow rate at the compressor intake valve.

[0064] In step S202, it is determined whether the frequency deviation meets the preset frequency regulation start condition of the compressed air energy storage system.

[0065] In some embodiments, the present application can determine whether the compressed air energy storage system participates in the frequency regulation of the power system by judging whether the frequency deviation meets the preset frequency regulation start conditions of the compressed air energy storage system.

[0066] Among them, the certain frequency regulation start condition can be understood as whether the frequency deviation of the power system is greater than the maximum value of the frequency regulation dead zone of the compressed air energy storage unit and whether the duration is greater than the threshold time. The specific settings can be made by those skilled in the art according to the actual situation, and this application does not impose specific restrictions.

[0067] For example, in this application embodiment, the power system can select a reference frequency of 50Hz to determine whether the frequency deviation of the power system is greater than Δf. gate And whether the duration is greater than t gate .

[0068] Optionally, in one embodiment of this application, before adjusting the output power of the compressed air energy storage system based on the intake mass flow rate and a pre-trained neural network, the method further includes: constructing an input layer of a preset neural network based on intake mass flow rate neurons, frequency deviation neurons, and frequency deviation rate of change neurons; constructing an output layer of the preset neural network based on proportional parameter neurons and integral parameter neurons; and training the preset neural network using a target loss function to obtain a trained neural network. The calculation formula for the target loss function may be, but is not limited to, the following:

[0069]

[0070] Among them, K p With K i K′ represents the target scaling parameter and target integral parameter output by the neural network. p With K′ i Let m be the ideal scaling parameter and the ideal integral parameter for the output, m be the sample size, and L be the loss function.

[0071] The formulas for calculating the target proportional parameter and the target integral parameter can be, but are not limited to, as follows:

[0072]

[0073] Among them, hj b j C j Let $\mathbf$ be the basis vector, $\mathbf$ function, and $\mathbf$ center point vector value of the $j$-th neuron, respectively. Let $\mathbf$ be the Euclidean norm, $\mathbf$ be the weight vector from the hidden layer to the output layer, and $X$ be a ternary vector. The ternary vector can be, but is not limited to, represented by $X = (β, Δf, Δf′)$, where $β$ is the intake mass flow rate of the compressor, $Δf$ is the frequency deviation of the power system, and $Δf′$ is the rate of change of the frequency deviation of the power system.

[0074] It should be noted that, in the embodiments of this application, the neural network can be constructed and trained before adjusting the output power of the compressed air energy storage system using a pre-trained neural network.

[0075] For example, in this application embodiment, an input layer can be constructed based on intake mass flow rate neurons, frequency deviation neurons, and frequency deviation change rate neurons; an output layer can be constructed based on proportional parameter neurons and integral parameter neurons; and then a preset neural network can be trained using a target loss function to obtain a trained neural network. The calculation formula for the target loss function can be, but is not limited to, the following:

[0076]

[0077] Among them, K p With K i K′ represents the target scaling parameter and target integral parameter output by the neural network. p With K′ i Let m be the ideal scaling parameter and the ideal integral parameter for the output, m be the sample size, and L be the loss function.

[0078] Furthermore, in the embodiments of this application, the solution algorithm can employ the radial basis function method, and the solution process can be described as follows:

[0079]

[0080] Here, x is located in the input layer of the neural network and is represented by a ternary vector X = (β, Δf, Δf′), where β is the intake mass flow rate of the compressor, Δf is the frequency deviation of the power system, Δf′ is the rate of change of the frequency deviation of the power system, and h j b j C j Let be the basis vector, Gaussian function, and center point vector value of the j-th neuron, respectively; ||·|| is the Euclidean norm; and w is the weight vector from the hidden layer to the output layer.

[0081] Therefore, the embodiments of this application can use the objective loss function method and gradient descent algorithm to train the neural network.

[0082] In step S203, if the frequency deviation meets the preset frequency regulation start condition, the output power of the compressed air energy storage system is adjusted based on the intake air mass flow rate and the pre-trained neural network, so as to regulate the frequency of the power system based on the adjusted output power until the frequency meets the preset frequency stability condition.

[0083] As one possible implementation method, in the embodiments of this application, when the frequency deviation meets certain frequency modulation start conditions, the output power of the compressed air energy storage system can be adjusted based on the intake air mass flow rate and a pre-trained neural network, thereby obtaining a frequency that meets certain frequency stability conditions.

[0084] The certain frequency stability condition can be understood as the frequency being stable within the maximum value of the frequency regulation dead zone of the compressed air energy storage unit and the duration being greater than the threshold time. The specific setting can be made by those skilled in the art according to the actual situation, and this application does not impose specific restrictions.

[0085] It can be understood that the embodiments of this application mainly regulate the output power by adjusting the mass flow rate of the expander. The expressions for the outlet air temperature and pressure of the i-th stage expander can be, but are not limited to, expressed as:

[0086]

[0087]

[0088] in, p represents the temperature of the air entering the expander inlet. e i in This represents the inlet air pressure of the i-th stage expander. This represents the rated expansion ratio of the i-th stage expander. Let represent the rated isentropic efficiency of the i-th stage expander, and k be the air adiabatic index.

[0089] Furthermore, in the embodiments of this application, the output power of the i-th stage expander can be, but is not limited to, expressed as:

[0090]

[0091] The total output power of each stage of the expander can then be obtained, which can be expressed, but is not limited to, as:

[0092]

[0093] in, The mass flow rate of the expander. The specific heat capacity of air at constant pressure, N e The number of stages in the expander.

[0094] Therefore, the embodiments of this application can appropriately increase the mass flow rate of the expander, thereby increasing the output power of compressed air energy storage and thus achieving the purpose of stabilizing the frequency in the power system.

[0095] For example, in the embodiments of this application, the frequency deviation of the power system is greater than Δf gate And the duration is greater than t gate In this case, it can be determined that the compressed air energy storage system participates in the frequency regulation of the power system. Furthermore, the power system can control the output power of the compressed air energy storage system by adjusting the proportional and integral parameters based on the intake mass flow rate and a pre-trained neural network according to the load power command, until the frequency stabilizes at Δf. gate Within and the duration is greater than t gate The frequency of the power system is stable.

[0096] For example, such as Figure 1 As shown, in this embodiment of the application, the frequency deviation of the power system is greater than Δf. gate And the duration is greater than t gate In this case, the intake mass flow rate of the compressor unit, the frequency deviation of the power system, and the frequency deviation change rate are input into a pre-trained neural network. The neural network outputs target proportional parameters and target integral parameters to the control device. The control device is connected to the compressor intake valve and adjusts the opening of the compressor intake valve through the proportional and integral links, thereby adjusting the output power.

[0097] Optionally, in one embodiment of this application, adjusting the output power of the compressed air energy storage system based on the intake mass flow rate and a pre-trained neural network, and adjusting the frequency of the power system based on the adjusted output power until the frequency meets a preset frequency stability condition, includes: inputting the intake mass flow rate, frequency deviation, and frequency deviation change rate into the pre-trained neural network to obtain the target proportional parameter and target integral parameter of the compressed air energy storage system, and controlling the compressed air energy storage system to enter a short-term boost phase based on the target proportional parameter and target integral parameter; when the compressed air energy storage system is in the short-term boost phase, determining whether the frequency deviation is greater than a first preset frequency deviation of the power system, or determining whether the frequency deviation is less than a second preset frequency deviation of the power system, wherein the first preset frequency deviation is greater than the second preset frequency deviation; if the frequency deviation is greater than the first preset frequency deviation, the target proportional parameter is the maximum value of the proportional parameter that the compressed air energy storage system can accept, and the output power is adjusted based on the maximum value and the target integral parameter; if the frequency deviation is less than the second preset frequency deviation, the target integral parameter is the minimum value of the integral parameter that the compressed air energy storage system can accept, and the output power is adjusted based on the target proportional parameter and the minimum value.

[0098] Those skilled in the art will understand that, in the process of adjusting the output power of the compressed air energy storage system using a pre-trained neural network, the embodiments of this application can also determine whether the frequency deviation is greater than the preset frequency deviation of the power system in order to achieve the fastest possible frequency regulation and reduce the impact of the compressed air energy storage system on the power system.

[0099] For example, in this embodiment, the control process is divided into two stages, where Δf1 is the first certain frequency deviation of the power system, and Δf2 is the second certain frequency deviation of the power system, with the first certain frequency deviation being greater than the second certain frequency deviation. The specific settings can be configured by those skilled in the art according to actual conditions, and this application does not impose specific limitations. It should be noted that the specific content of the first stage in this embodiment is as follows:

[0100] In this embodiment, the first stage is a short-term power boosting stage, in which the compressor releases kinetic energy to provide power support. The start time is when the compressed air energy storage unit participates in frequency regulation, and the end time is when it enters the power tracking stage. The frequency regulation in this stage follows the following principles:

[0101] Principle 1: Determine if the frequency deviation is greater than the first preset frequency deviation of the power system. If the frequency deviation is greater than the first preset frequency deviation, the target proportional parameter is the maximum value of the proportional parameter that the compressed air energy storage system can accept, that is:

[0102] When Δf > Δf1, K p =K pmax ,

[0103] In other words, in this embodiment of the application, when the frequency deviation is large, the maximum scaling parameter K is adopted. p To accelerate the timely power response of frequency regulation power systems.

[0104] Principle Two: Determine if the frequency deviation is less than the second preset frequency deviation of the power system. If the frequency deviation is less than the second preset frequency deviation, the target integral parameter is the minimum value of the integral parameter acceptable to the compressed air energy storage system, i.e.:

[0105] When Δf < Δf2, K i =K imin ,

[0106] In other words, in the embodiments of this application, when the frequency deviation is small, the power system has already reached a stable state, and the minimum integral parameter K can be adopted. i This is to maintain the frequency stability of the power system.

[0107] Optionally, in one embodiment of this application, adjusting the output power of the compressed air energy storage system based on the intake mass flow rate and a pre-trained neural network, and adjusting the frequency of the power system based on the adjusted output power until the frequency meets a preset frequency stability condition, further includes: determining the frequency in the power system to maintain frequency stability based on the output power, and controlling the compressed air energy storage system to enter a power transition phase based on the frequency; when the compressed air energy storage system is in the power transition phase, if the intake mass flow rate is less than or equal to the upper limit of the intake mass flow rate, determining whether the frequency meets the preset frequency stability condition; if the frequency meets the preset frequency stability condition, then it is prohibited to use the neural network to adjust the output power.

[0108] As can be seen from the above analysis, in the first stage, the embodiment of this application can determine that the frequency of the power system has initially stabilized, and then enter the second stage, that is, when the intake mass flow rate is less than or equal to the upper limit of the intake mass flow rate, it is determined whether the frequency meets a certain frequency stability condition, and when the frequency meets the preset frequency stability condition, it is prohibited to use the neural network to adjust the output power.

[0109] For example, the second stage of this application embodiment specifically includes:

[0110] In this embodiment, the second stage is a power transition stage. While ensuring the intake mass flow rate is less than or equal to the upper limit of the intake mass flow rate, it is determined whether the frequency meets a certain frequency stability condition, i.e., the power system frequency is maintained at a constant value, for example, when the power system frequency stabilizes at Δf. gate Within and the duration is greater than t gate When the frequency regulation process is complete, the compressed air energy storage unit can be considered to have resumed maximum power point tracking operation, and the use of neural networks to adjust the output power is prohibited.

[0111] This application adopts a neural network architecture with three-dimensional system state input, which overcomes the shortcomings of previous frequency control controllers that only considered one input system state variable (frequency deviation) in parameter tuning or when the parameters were fixed. It can give full play to the intelligent processing capability of neural networks for multi-dimensional parameters, realize the optimal real-time adaptive tuning of power system frequency control controller parameters, give full play to the advantages of compressed air energy storage system as a high-quality transient frequency regulation power source with fast response speed and environmental friendliness, and improve the accuracy of active power control in compressed air energy storage system and the frequency stability of power system.

[0112] The following is combined Figure 1 and Figure 3 The working principle of the neural network-based compressed air energy storage frequency regulation method proposed in this application will be described in detail with a specific embodiment.

[0113] in, Figure 3This is a flowchart illustrating the working principle of a neural network-based compressed air energy storage frequency regulation method according to an embodiment of this application.

[0114] Step S301: The data acquisition device acquires the intake mass flow rate of the compressor unit, the frequency deviation of the power system, and the frequency deviation change rate, and then proceeds to step S302.

[0115] Step S302: If the frequency deviation of the power system is greater than the maximum value of the frequency regulation dead zone of the compressed air energy storage unit and the duration is greater than the threshold time, it is determined that the compressed air energy storage system participates in the frequency regulation of the power system, and step S303 is continued.

[0116] Step S303: Input the collected intake mass flow rate, frequency deviation, and frequency deviation change rate into the pre-trained neural network.

[0117] Step S304: Obtain the target proportional parameters and target integral parameters of the compressed air energy storage system.

[0118] Step S305: The control device controls the opening degree of the compressor inlet valve to adjust the output power of the compressed air energy storage system.

[0119] Step S306: Enter the short-term issuance phase.

[0120] Step S307: Determine whether the frequency duration of the power system is greater than the threshold time. If it is greater than the threshold time, proceed to step S308; otherwise, proceed to step S306.

[0121] Step S308: Enter the power transition stage.

[0122] According to the neural network-based frequency regulation method for compressed air energy storage proposed in this application, when the frequency deviation meets the preset frequency regulation start conditions of the compressed air energy storage system, the obtained intake mass flow rate of the compressor unit, the frequency deviation of the power system, and the rate of change of frequency deviation are input into a pre-trained neural network to adjust the output power of the compressed air energy storage system until a certain frequency stability condition is met. This fully utilizes the intelligent processing capability of the neural network for multi-dimensional parameters, realizing the optimal real-time adaptive tuning of the frequency controller parameters in the power system. It maximizes the advantages of the compressed air energy storage system, such as fast response speed and environmentally friendly high-quality transient frequency regulation power supply, and improves the accuracy of active power control and the frequency stability of the power system. Therefore, it solves the problems in related technologies, such as the inability to fully utilize the intelligent processing capability of the neural network for multi-dimensional parameters, the inability to fully demonstrate the advantages of the compressed air energy storage system, such as fast response speed and environmentally friendly high-quality transient frequency regulation power supply, and the low accuracy of active power control in the compressed air energy storage system.

[0123] Next, referring to the accompanying drawings, a neural network-based compressed air energy storage frequency modulation device according to an embodiment of this application is described.

[0124] Figure 4 This is a block diagram of a neural network-based compressed air energy storage frequency modulation device provided according to an embodiment of this application.

[0125] like Figure 4 As shown, the neural network-based compressed air energy storage frequency modulation device 10 includes: an acquisition module 100, a judgment module 200, and a frequency modulation module 300.

[0126] The acquisition module 100 is used to acquire the intake mass flow rate of the compressor unit in the compressed air energy storage system, the frequency deviation of the power system, and the frequency deviation change rate.

[0127] The judgment module 200 is used to determine whether the frequency deviation meets the preset frequency regulation start conditions of the compressed air energy storage system.

[0128] The frequency modulation module 300 is used to adjust the output power of the compressed air energy storage system based on the intake air mass flow rate and a pre-trained neural network when the frequency deviation meets the preset frequency modulation start conditions, so as to regulate the frequency of the power system based on the adjusted output power until the frequency meets the preset frequency stability conditions.

[0129] Optionally, in one embodiment of this application, the frequency modulation module 300 includes: an input unit, a first judgment unit, a first frequency modulation unit, and a second frequency modulation unit.

[0130] The input unit is used to input the intake air mass flow rate, frequency deviation, and frequency deviation change rate into a pre-trained neural network to obtain the target proportional parameters and target integral parameters of the compressed air energy storage system, and to control the compressed air energy storage system to enter the short-term boost phase based on the target proportional parameters and target integral parameters.

[0131] The first judgment unit is used to determine whether the frequency deviation is greater than the first preset frequency deviation of the power system or whether the frequency deviation is less than the second preset frequency deviation of the power system when the compressed air energy storage system is in a short-term power generation phase, wherein the first preset frequency deviation is greater than the second preset frequency deviation.

[0132] The first frequency modulation unit is used to adjust the output power based on the maximum value of the proportional parameter that the compressed air energy storage system can accept when the frequency deviation is greater than the first preset frequency deviation.

[0133] The second frequency modulation unit is used to adjust the output power based on the target integral parameter being the minimum value of the integral parameter that the compressed air energy storage system can accept when the frequency deviation is less than the second preset frequency deviation.

[0134] Optionally, in one embodiment of this application, the frequency modulation module 300 further includes: a determination unit, a second judgment unit, and a third frequency modulation unit.

[0135] The determining unit is used to determine the frequency that maintains frequency stability in the power system based on the output power, and to control the compressed air energy storage system to enter the power transition phase based on the frequency.

[0136] The second judgment unit is used to determine whether the frequency meets the preset frequency stability condition when the compressed air energy storage system is in the power transition stage and the intake mass flow rate is less than or equal to the upper limit of the intake mass flow rate.

[0137] The third frequency modulation unit is used to prevent the use of neural networks to adjust the output power when the frequency meets the preset frequency stability conditions.

[0138] Optionally, in one embodiment of this application, it further includes: a first building module, a second building module, and a training module.

[0139] The first construction module is used to construct the input layer of a preset neural network based on intake mass flow rate neurons, frequency deviation neurons, and frequency deviation change rate neurons before adjusting the output power of the compressed air energy storage system based on intake mass flow rate and pre-trained neural network.

[0140] The second building module is used to construct the output layer of a preset neural network based on proportional parameter neurons and integral parameter neurons.

[0141] The training module is used to train a preset neural network using a target loss function to obtain a trained neural network.

[0142] Optionally, in one embodiment of this application, the formula for calculating the target loss function may be, but is not limited to, the following:

[0143]

[0144] Among them, K p With K i K′ represents the target scaling parameter and target integral parameter output by the neural network. p With K′ i Let m be the ideal scaling parameter and the ideal integral parameter for the output, m be the sample size, and L be the loss function.

[0145] Optionally, in one embodiment of this application, the calculation formulas for the target scaling parameter and the target integral parameter may be, but are not limited to, as follows:

[0146]

[0147] Among them, h j b j C j Let $\mathbf$ be the basis vector, $\mathbf$ function, and $\mathbf$ center point vector value of the $j$-th neuron, respectively. Let $\mathbf$ be the Euclidean norm, $\mathbf$ be the weight vector from the hidden layer to the output layer, and $X$ be a ternary vector. The ternary vector can be, but is not limited to, represented by $X = (β, Δf, Δf′)$, where $β$ is the intake mass flow rate of the compressor, $Δf$ is the frequency deviation of the power system, and $Δf′$ is the rate of change of the frequency deviation of the power system.

[0148] It should be noted that the foregoing explanation of the embodiment of the compressed air energy storage frequency regulation method based on neural networks also applies to the compressed air energy storage frequency regulation device based on neural networks in this embodiment, and will not be repeated here.

[0149] According to the neural network-based compressed air energy storage frequency regulation device proposed in this application, when the frequency deviation meets the preset frequency regulation start conditions of the compressed air energy storage system, the acquired intake mass flow rate of the compressor unit, the frequency deviation of the power system, and the rate of change of frequency deviation are input into a pre-trained neural network to adjust the output power of the compressed air energy storage system until a certain frequency stability condition is met. This fully utilizes the intelligent processing capability of the neural network for multi-dimensional parameters, realizing the optimal real-time adaptive tuning of the frequency regulation controller parameters in the power system. It maximizes the advantages of the compressed air energy storage system, such as fast response speed and environmentally friendly high-quality transient frequency regulation power supply, and improves the accuracy of active power control and the frequency stability of the power system. Therefore, it solves the problems in related technologies, such as the inability to fully utilize the intelligent processing capability of the neural network for multi-dimensional parameters, the inability to fully demonstrate the advantages of the compressed air energy storage system, such as fast response speed and environmentally friendly high-quality transient frequency regulation power supply, and the low accuracy of active power control in the compressed air energy storage system.

[0150] Figure 5 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. The electronic device may include:

[0151] The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0152] When the processor 502 executes the program, it implements the neural network-based compressed air energy storage frequency regulation method provided in the above embodiments.

[0153] Furthermore, electronic devices also include:

[0154] Communication interface 503 is used for communication between memory 501 and processor 502.

[0155] The memory 501 is used to store computer programs that can run on the processor 502.

[0156] The memory 501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0157] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0158] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0159] Processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0160] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described neural network-based compressed air energy storage frequency modulation method.

[0161] This application also provides a computer program product, including a computer program that, when executed, implements the above-described neural network-based compressed air energy storage frequency regulation method.

[0162] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0163] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0164] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0165] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0166] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0167] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0168] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0169] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for frequency regulation of compressed air energy storage based on neural networks, characterized in that, Includes the following steps: Obtain the intake mass flow rate of the compressor unit in the compressed air energy storage system, the frequency deviation of the power system, and the rate of change of frequency deviation; Determine whether the frequency deviation meets the preset frequency regulation start condition of the compressed air energy storage system; If the frequency deviation meets the preset frequency modulation start condition, the output power of the compressed air energy storage system is adjusted based on the intake air mass flow rate and the pre-trained neural network, so as to adjust the frequency of the power system based on the adjusted output power until the frequency meets the preset frequency stability condition. The step of adjusting the output power of the compressed air energy storage system based on the intake air mass flow rate and a pre-trained neural network, and then adjusting the frequency of the power system based on the adjusted output power until the frequency meets a preset frequency stability condition, includes: The intake air mass flow rate, the frequency deviation, and the frequency deviation change rate are input into a pre-trained neural network to obtain the target proportional parameters and target integral parameters of the compressed air energy storage system, and the compressed air energy storage system is controlled to enter the short-term boost phase based on the target proportional parameters and the target integral parameters. When the compressed air energy storage system is in the short-term boost phase, it is determined whether the frequency deviation is greater than the first preset frequency deviation of the power system, or whether the frequency deviation is less than the second preset frequency deviation of the power system, wherein the first preset frequency deviation is greater than the second preset frequency deviation. If the frequency deviation is greater than the first preset frequency deviation, then the target proportional parameter is the maximum value of the proportional parameter that the compressed air energy storage system can accept, and the output power is adjusted based on the maximum value and the target integral parameter; If the frequency deviation is less than the second preset frequency deviation, then the target integral parameter is the minimum value of the integral parameter that the compressed air energy storage system can accept, and the output power is adjusted based on the target proportional parameter and the minimum value; The step of adjusting the output power of the compressed air energy storage system based on the intake air mass flow rate and a pre-trained neural network, and adjusting the frequency of the power system based on the adjusted output power until the frequency meets a preset frequency stability condition, further includes: The frequency for maintaining frequency stability in the power system is determined based on the output power, and the compressed air energy storage system is controlled to enter the power transition phase based on the frequency. When the compressed air energy storage system is in the power transition phase, if the intake mass flow rate is less than or equal to the upper limit of the intake mass flow rate, it is determined whether the frequency meets the preset frequency stability condition. If the frequency meets the preset frequency stability condition, then adjusting the output power using the neural network is prohibited.

2. The method according to claim 1, characterized in that, Before adjusting the output power of the compressed air energy storage system based on the intake air mass flow rate and a pre-trained neural network, the method further includes: An input layer of a pre-defined neural network is constructed based on intake mass flow rate neurons, frequency deviation neurons, and frequency deviation change rate neurons. The output layer of the preset neural network is constructed based on proportional parameter neurons and integral parameter neurons; The preset neural network is trained using the target loss function to obtain a trained neural network.

3. The method according to claim 2, characterized in that, The formula for calculating the target loss function is as follows: ， in, and The target scaling parameter and target integral parameter are the output of the neural network. and The ideal proportional parameters and ideal integral parameters are output. For sample size, This is the loss function.

4. The method according to claim 1, characterized in that, The calculation formulas for the target proportional parameter and the target integral parameter are as follows: ， in, , , The first The basis vectors, Gaussian function, and center point vector values ​​of each neuron. For the Euclidean norm, This is the weight vector from the hidden layer to the output layer. It is a ternary vector.

5. A compressed air energy storage frequency regulation device based on neural networks, characterized in that, The compressed air energy storage frequency regulation method based on neural networks as described in any one of claims 1-4 is adopted, wherein the device comprises: The acquisition module is used to acquire the intake mass flow rate of the compressor unit in the compressed air energy storage system, the frequency deviation of the power system, and the frequency deviation change rate. The judgment module is used to determine whether the frequency deviation meets the preset frequency regulation start condition of the compressed air energy storage system; The frequency modulation module is used to adjust the output power of the compressed air energy storage system based on the intake air mass flow rate and a pre-trained neural network when the frequency deviation meets the preset frequency modulation activation condition, so as to adjust the frequency of the power system based on the adjusted output power until the frequency meets the preset frequency stability condition.

6. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, the processor executing the program to implement the neural network-based compressed air energy storage frequency regulation method as described in any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the neural network-based compressed air energy storage frequency regulation method as described in any one of claims 1-4.

8. A computer program product, characterized in that, Includes a computer program, which, when executed, is used to implement the neural network-based compressed air energy storage frequency regulation method as described in any one of claims 1-4.

Images