Equivalent modeling method and system for large-scale photovoltaic hydrogen production station

Abstract

The invention provides a large-scale photovoltaic hydrogen production station equivalent modeling method and system. The method comprises the following steps: constructing a basic structure of a large-scale photovoltaic hydrogen production station grid-connected system; establishing an electrolytic cell system model taking single electrolytic cell operation as a unit and a photovoltaic power generation system model taking single photovoltaic array operation as a unit; based on the working principle of an electrolytic cell system and a photovoltaic power generation system and the interaction mechanism of the electrolytic cell system and the photovoltaic power generation system and a power grid, key factors reflecting the dynamic characteristics of the photovoltaic hydrogen production station are analyzed, dimensionality reduction is conducted on the key factors through a sparse auto-encoder so as to remove redundant information, and electrolytic cell units and photovoltaic power generation units in the photovoltaic hydrogen production station are grouped through a clustering algorithm; a large-scale photovoltaic hydrogen production field station multi-machine equivalent model is established by adopting a capacity weighting method, an equal power loss method and the like. According to the method, the physical characteristics and data analysis of the grid-connected system of the large-scale photovoltaic hydrogen production station are effectively fused, the equivalent model can adapt to steady-state and transient-state variable working conditions, and the simulation calculation amount of the system is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of equivalent modeling of new energy stations, and in particular to an equivalent modeling method and system for large-scale photovoltaic hydrogen production stations. Background Art

[0002] Based on the reverse distribution of renewable resources such as wind and light and energy demand, the large-scale new energy station grid-connected system is an inevitable development trend of energy and power layout. The use of a high proportion of power electronic equipment in large-scale photovoltaic hydrogen production stations, the intermittent, random and volatile output of photovoltaic new energy, and the wide power range operation characteristics of water electrolysis hydrogen production devices will change the dynamic characteristics of the system. Detailed modeling of each unit in the station can reflect its operating characteristics, but it cannot meet the simulation needs under the development of large-scale new energy stations. How to construct a reasonable and accurate station equivalent model for system steady-state and transient analysis is one of the current research focuses.

[0003] Equivalence modeling of new energy stations often aggregates units with similar dynamic characteristics together for equivalence in order to reduce the amount of system simulation calculations. Most existing studies determine clustering indicators and construct equivalence models for a certain scenario or specific characteristics, which lacks comprehensiveness. Modeling based on the physical characteristics of new energy stations cannot fully reflect the dynamic characteristics of the system. Modeling based on its data analysis often requires a large amount of high-quality data to find the inherent laws hidden in it, and the model is not interpretable enough. Therefore, it is urgent to comprehensively consider the physical-data characteristics of the grid-connected system of large-scale photovoltaic hydrogen production stations to construct its multi-machine equivalence model that can adapt to variable working conditions and make the modeling more accurate. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes a method and system for equivalent modeling of large-scale photovoltaic hydrogen production stations. Starting from the interaction mechanism among the electrolyzer system, photovoltaic power generation system and power grid, the electrolyzer units and photovoltaic power generation units in the station are grouped based on physical characteristics-data analysis, and a multi-machine equivalent model of large-scale photovoltaic hydrogen production stations is constructed.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] A method for equivalent modeling of a large-scale photovoltaic hydrogen production station includes the following steps:

[0007] Step 1: Based on the capacity of the photovoltaic hydrogen production station and the actual application of the water electrolysis hydrogen production demonstration project, the basic structure of the grid-connected system of the large-scale photovoltaic hydrogen production station is constructed;

[0008] Step 2: According to the site structure and the working principles of the electrolyzer and photovoltaic array and the control method of their converters, an electrolyzer system model with a single electrolyzer as a unit and a photovoltaic power generation system model with a single photovoltaic array as a unit are established;

[0009] Step 3: Based on the working principles of the electrolyzer system and the photovoltaic power generation system and their interaction mechanism with the power grid, the key factors reflecting the dynamic characteristics of the photovoltaic hydrogen production station are analyzed, and the sparse autoencoder is used to reduce the dimension of the key factors to remove redundant information. The electrolyzer units and photovoltaic power generation units in the photovoltaic hydrogen production station are grouped by a clustering algorithm;

[0010] Step 4: Use the capacity-weighted and equal power loss method to construct an equivalent model for the equipment in the same cluster to form a multi-machine equivalent model for a large-scale photovoltaic hydrogen production station.

[0011] The present invention also provides a large-scale photovoltaic hydrogen production station equivalent modeling system, including the following modules:

[0012] The structural construction module considers the capacity of the photovoltaic hydrogen production station and determines the basic structure of the grid-connected system of the large-scale photovoltaic hydrogen production station;

[0013] The model building module builds an electrolyzer system model with a single electrolyzer as a unit and a photovoltaic power generation system model with a single photovoltaic array as a unit according to the site structure and the working principles of the electrolyzer and photovoltaic array and the control method of their converters;

[0014] The clustering module analyzes the key factors reflecting the dynamic characteristics of photovoltaic hydrogen production stations based on the working principles of the electrolyzer system and photovoltaic power generation system and their interaction mechanism with the power grid. It uses a sparse autoencoder to reduce the dimension of key factors to remove redundant information, and clusters the electrolyzer units and photovoltaic power generation units in the photovoltaic hydrogen production station through a clustering algorithm.

[0015] The multi-machine equivalent construction module uses capacity weighting and equal power loss method to construct an equivalent model for the equipment in the same cluster, forming a multi-machine equivalent model for large-scale photovoltaic hydrogen production stations.

[0016] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the above-mentioned method for equivalent modeling of a large-scale photovoltaic hydrogen production station are implemented.

[0017] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for equivalent modeling of a large-scale photovoltaic hydrogen production station.

[0018] Compared with the prior art, the present invention has the following beneficial effects:

[0019] 1. The present invention effectively integrates the physical characteristics and data analysis of the large-scale photovoltaic hydrogen production station grid-connected system, that is, the data is targetedly screened and processed based on a deep understanding of the physical characteristics of the system, which can reduce the redundancy of system information and improve the accuracy of the established model.

[0020] 2. The present invention is applicable to various transient and steady-state working conditions, reflects the dynamic characteristics of the system operation process, and effectively reduces the amount of simulation calculation while ensuring that the external characteristics of the equivalent model output remain unchanged. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A schematic diagram of a flow chart of a method for equivalent modeling of a large-scale photovoltaic hydrogen production station according to the present invention;

[0022] Figure 2 The topological structure and electric energy flow path diagram of the grid-connected power system of the large-scale photovoltaic hydrogen production station of the present invention;

[0023] Figure 3 is an equivalent circuit diagram of an alkaline electrolytic cell of the present invention;

[0024] Figure 4 This is a control block diagram of the Buck converter on the electrolytic cell side of the present invention;

[0025] Figure 5 It is a control block diagram of the electrolytic cell side rectifier of the present invention;

[0026] Figure 6 is an equivalent circuit diagram of a photovoltaic cell of the present invention;

[0027] Figure 7 This is a control block diagram of the photovoltaic side Boost converter of the present invention;

[0028] Figure 8 The photovoltaic side inverter control block diagram of the present invention;

[0029] Fig. 9 This is a schematic diagram of a set of factors characterizing the dynamic characteristics of a photovoltaic hydrogen production station according to the present invention. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0031] like Figure 1 As shown, a large-scale photovoltaic hydrogen production station equivalent modeling method of the present invention includes the following steps:

[0032] Step 1: Construct the basic structure of the grid-connected system for large-scale photovoltaic hydrogen production stations, including:

[0033] According to Figure 2 The topological structure and power flow path diagram of the large-scale photovoltaic hydrogen production station grid-connected system shown in the figure, the green electricity generated by the photovoltaic power generation system passes through the Boost circuit and inverter, and then through the step-up transformer through the collection line and then through the main step-up transformer to connect to the 220kV line for transmission to the hydrogen production plant; the electric energy consumed by the water electrolysis hydrogen production device is connected from the 220kV line through the main step-down transformer through multiple lines to the step-down transformer, and then through the rectifier and Buck circuit for supply and use; the path of the electricity generated by the photovoltaic system and the electricity consumed by the electrolyzer is basically opposite. When the grid is connected to the 220kV line, when the electricity generated by the 100-megawatt photovoltaic hydrogen production station is too much, the excess electricity is absorbed by the grid; when the electricity generated by the photovoltaic is not enough to support the electrolyzer to operate at the minimum power, the grid needs to supply energy to support the continuous operation of the electrolyzer;

[0034] Step 2: According to the site structure and the working principles of the electrolyzer and photovoltaic array and the control method of their converters, an electrolyzer system model with a single electrolyzer as a unit and a photovoltaic power generation system model with a single photovoltaic array as a unit are established, including:

[0035] 1) Establishing the electrolyzer system model

[0036] 1.1) Electrolyzer model

[0037] The electrolyzer is a key component of the hydrogen production system, which decomposes the electrolyte solution into hydrogen and oxygen through direct current. In order to accurately simulate the electrical characteristics of the electrolyzer, a dynamic model is established. Figure 3 As shown, the reversible voltage U rev It is the basic voltage required for the electrolysis of water. The voltage source U rev Indicates; Ohmic overvoltage U ohm It is caused by the resistance of the electrolytic cell components to the flow of charge and can be represented by an ohmic resistance R ohm Indicates; activation overvoltage U act It is the potential difference caused by the electron transfer process at the electrode, which can be controlled by a controlled current source I act With capacitor C act Parallel representation; reversible voltage U rev , Ohmic overvoltage U ohm , Activation overvoltage U act The sum of the above three connected in series is the electrolytic cell voltage U el , which can be expressed as:

[0038] (1)

[0039] Among them, U acta , Uactc They are the anode activation overvoltage and the cathode activation overvoltage respectively.

[0040] Each electrolytic cell stack consists of multiple electrolytic cells. The reversible voltage can be expressed as:

[0041] (2)

[0042] Among them, N el is the number of electrolysis chambers; ΔG is the Gibbs free energy; z is the number of electrons required to transfer to produce 1 mole of hydrogen; F is the Faraday constant; R is the ideal gas constant; T el is the working temperature of the electrolytic cell; P H2 , P O2 are the partial pressures of the reaction products hydrogen and oxygen respectively; α H2O is water activity; ln() is logarithmic function.

[0043] The ohmic overvoltage can be expressed as:

[0044] (3)

[0045] Among them, A el is the surface area of ​​the electrolytic cell; r 1 、r 2 、r 3 、r 4 I is the area specific resistivity of the electrolytic cell monomer; el is the electrolytic cell current.

[0046] According to the modified Tafel equation, the activation overvoltage is a nonlinear function of the activation current and can be expressed as:

[0047] (4)

[0048] (5)

[0049] Among them, I acta ,I actc are the anode activation current and cathode activation current respectively; a el , b el 、c el d el is the Tafel empirical coefficient, which can be expressed as:

[0050] (6)

[0051] (7)

[0052] (8)

[0053] (9)

[0054] Among them, a 1 、a 2 、a 3 , b 1 , b 2 , b 3 c is the empirical coefficient of the anode activation resistance of the electrolytic cell; 1 、c 2 、c 3 d 1 d 2 d 3 is the empirical coefficient of cathode activation resistance of electrolytic cell.

[0055] 1.2) DC / DC converter on the electrolyzer side and its control model:

[0056] The DC voltage amplitude required for the operation of the electrolyzer equipment is relatively low, and usually needs to pass through a DC / DC converter, that is, a Buck circuit to reduce the high voltage on the source side to the voltage required by the electrolyzer. The control block diagram of the DC / DC converter is shown in Figure 4 As shown, a dual-loop control method of power outer loop and current inner loop is adopted, that is, according to the system operating state and the operating range P of the electrolyzer eln Give the active power reference value P of the electrolytic cell elref , and the actual active power value P of the electrolytic cell el In comparison, the current reference value I is obtained through the PI regulator elref , through current closed-loop control, that is, with the electrolytic cell current value I el After comparison, the Buck circuit modulation information D is obtained through the PI regulator. eldc , adjusting the circuit duty cycle to achieve real-time control of the electrolytic cell power.

[0057] Since the electrolyzer can flexibly adjust the system unbalanced power within a wide power range, its minimum operating power can reach 5%~25% of the rated power, and the maximum operating power can reach 110%~130% of the rated power. When the photovoltaic output fluctuates greatly or the system is in a fault state, the response and adjustment characteristics of the electrolyzer can be fully utilized, and a voltage response link can be added to the outer loop control, that is, the electrolyzer DC bus voltage reference value U eldcref The actual voltage value U eldc In comparison, the value after passing through the PI regulator is used as the outer loop control parameter, which makes the electrolyzer operate outside the normal operating range (25%~100%) for a short time.

[0058] 1.3) Electrolyzer side rectifier and its control model:

[0059] The electrolyzer equipment requires direct current to operate. To meet the requirements of large-scale electrolyzer equipment grid connection, the source side AC power is usually converted into DC power through an AC / DC converter. The control block diagram of the electrolyzer side rectifier is shown in the figure. Figure 5 As shown in the figure, a dual-loop control method of voltage, power outer loop and current inner loop is adopted, that is, the DC bus voltage reference value U of the electrolyzer is given according to the electrolyzer operation status and system stability requirements. eldcref , Reference value of active power required by electrolyzer P elref , reactive power reference value Q elref , and the actual voltage value U of the electrolytic cell DC bus eldc , the actual active power value P of the electrolytic cell el , actual reactive power value Q el For comparison, the PI regulator generates the d-axis and q-axis current reference values ​​I eldref ,I elqref ; The current inner loop control is to set the current reference value I eldref ,I elqref With the actual value I eld ,I elq After comparison, it passes through the PI regulator and then compares with the actual voltage value of the d-axis and q-axis on the AC side. eld 、e elq and the equivalent inductance L flowing through the AC side els The voltages of the d-axis and q-axis modulation voltages u are superimposed. eld 、u elq , the rectifier modulation signal D is obtained through Park inverse transformation and pulse width modulation technology elac , achieving system power balance.

[0060] 2) Establishing a photovoltaic power generation system model

[0061] 2.1) Photovoltaic array model:

[0062] Photovoltaic cells convert light energy into electrical energy based on the "photovoltaic effect". Their output characteristics are easily affected by the external environment, such as ambient temperature, light intensity, etc. At present, the most widely used photovoltaic cell equivalent circuits are Figure 6 As shown, the photovoltaic cell generates a photocurrent I after being illuminated. sc , which can be represented by a constant current source; part of it is used to offset the junction current I of the PN junction d , that is, an ideal diode is used in parallel to shunt the current; since the battery edge leakage and the loss of the metal bridge will cause the current to short-circuit, a shunt resistor R sh Parallel connection is used to represent; since the battery material has a certain resistivity that will cause loss, a parasitic resistance R can be used s Based on this circuit, the model of the photovoltaic cell can be obtained as follows:

[0063] (10)

[0064] Among them, U pc ,I pc are the output voltage and output current of the photovoltaic cell respectively; I 0 is the reverse saturation current of the parallel diode; q is the electron Coulomb constant; n is the ideal quality factor of the diode; K is the Boltzmann constant; T pv is the photovoltaic cell temperature; exp() is the exponential function.

[0065] A photovoltaic array is usually composed of multiple photovoltaic cells connected in series and parallel. Its model can be expressed as:

[0066] (11)

[0067] Among them, U pv ,I pv are the output voltage and output current of the photovoltaic array respectively; N s 、N p are the number of photovoltaic cells connected in series and in parallel, respectively.

[0068] 2.2) Photovoltaic side DC / DC converter and its control model:

[0069] The output voltage of the photovoltaic array is low and usually needs to be boosted by a DC / DC converter, i.e., a Boost circuit. The output of the photovoltaic power generation system is affected by the ambient temperature and light intensity, and exhibits nonlinear characteristics. The control block diagram of the Boost converter is shown in the figure below. Figure 7 As shown in the figure, when the system is operating normally, the maximum power tracking technology is usually adopted, that is, the voltage value U at the maximum power output of the photovoltaic array pvref The actual output voltage value U pv In comparison, the modulation signal D is generated by the PI regulator pvdc , to achieve the maximum power output of the photovoltaic array; when the system fails, the Boost converter usually adopts a dual-loop control method of power outer loop and current inner loop, that is, the active power reference value P of the photovoltaic array is given according to the system operation status pvref , and the actual active power value P of the photovoltaic array pv By comparison, the current reference value I is generated by the regulator pvref and controlled by the inner current loop, that is, the actual output current value I of the photovoltaic array pv After comparison, the Boost circuit modulation signal D is obtained through the PI regulator. pvdc , achieving power balance of the entire system.

[0070] 2.3) Photovoltaic side inverter and its control model:

[0071] In order to meet the grid connection requirements of large-scale photovoltaic power generation systems, the DC power generated by the photovoltaic system is usually converted into AC power through a DC / AC converter, while keeping the amplitude, voltage, frequency and phase of the grid connection consistent. Figure 8 As shown in Figure 1, under normal operating conditions, the photovoltaic side inverter adopts a dual-loop control method with voltage and power outer loops and current inner loops. Its control process is similar to that of the electrolyzer, that is, the photovoltaic array DC bus voltage reference value U is given according to the system operating power and stability requirements. pvdcref , PV array active power reference value P pvref , reactive power reference value Q pvref , and the actual voltage value of the PV array DC busbar U pvdc , the actual active power value of the photovoltaic array P pv , actual reactive power value Q pv In comparison, the active and reactive current reference values ​​I of the photovoltaic array are generated by the PI regulator. pvdref ,I pvqref , and then generate the modulation signal D through the current inner loop control pvac , to achieve unity power factor operation of photovoltaic power generation system.

[0072] In the case of a system fault, that is, when the voltage at the photovoltaic side port drops or rises, the photovoltaic inverter will switch to the fault ride-through control mode. While ensuring that the photovoltaic inverter does not disconnect from the grid for a certain period of time, it absorbs and emits a certain amount of reactive power to support the recovery of the grid voltage. On the grid side, due to a short-circuit fault, the voltage will drop. The dynamic reactive current should track the voltage change of the grid connection point in real time. Its output current can be expressed as:

[0073] (12)

[0074] (13)

[0075] Among them, k 1 , k 2 is the reactive current coefficient; V pcc is the grid-connected point voltage on the photovoltaic side, which is a per-unit value; I pvN is the photovoltaic rated current; I pvd I is the active current of the photovoltaic system under normal operation; max It is the inverter current limit, which is generally 1.2~1.5 times of the rated current.

[0076] Step 3: Based on the working principle of the electrolyzer system and the photovoltaic power generation system and the interaction mechanism with the power grid, the key factors reflecting the dynamic characteristics of the photovoltaic hydrogen production station are analyzed. The key factors are longized by using a sparse autoencoder to remove redundant information. The electrolyzer units and photovoltaic power generation units in the photovoltaic hydrogen production station are grouped by a clustering algorithm, including:

[0077] 1) Key factors analysis:

[0078] For large-scale photovoltaic hydrogen production station grid-connected systems, it is often difficult to accurately characterize the dynamic characteristics of the overall system using physical characteristics at a certain time and space scale. When the system operating state changes, the dynamic characteristics of the photovoltaic array unit and the electrolyzer unit show many changes, such as changes in DC bus voltage, terminal voltage, active power, reactive power, and changes in converter control methods. Therefore, it is necessary to sort out the internal and external key influencing factors that can reflect the dynamic characteristics of photovoltaic power generation units, electrolyzer units, and photovoltaic hydrogen production stations from multiple time and space scales.

[0079] 1.1) Voltage change:

[0080] The photovoltaic array, electrolyzer and power grid exchange power information through two-stage converters. When a fault occurs on the grid side, such as a single-phase short circuit fault or a two-phase short circuit fault, the grid voltage will change and the active power absorbed by the grid will be reduced. Since the two-stage converter control system has a certain time delay, the power emitted and absorbed by the photovoltaic power generation unit and the electrolyzer unit cannot immediately track the power changes on the grid side. At this time, the active power on the grid side, photovoltaic side and electrolyzer side can be expressed as:

[0081] (14)

[0082] (15)

[0083] (16)

[0084] Among them, P g is the grid-side active power; e gd 、e gq are the d-axis and q-axis components of the grid-side voltage respectively; i gd 、i gq They are the d-axis and q-axis components of the grid-side current respectively.

[0085] According to the power balance principle, we get:

[0086] (17)

[0087] Among them, P g1 , P g2 are the interaction powers between the grid side, the photovoltaic side and the electrolyzer side respectively; ΔP 1 , ΔP 2 are the unbalanced power on the photovoltaic side and the electrolyzer side respectively; C pvdc , C eldc They are the DC bus capacitors on the photovoltaic side and the electrolyzer side respectively.

[0088] It can be seen that the unbalanced power between the photovoltaic side, the electrolyzer side and the grid side is absorbed by the DC bus capacitor, making the DC bus voltage U pvdc , U eldc Changes occur, which in turn causes changes in the control strategies of the converters in the photovoltaic power generation system and the electrolyzer system to eliminate the DC bus voltage changes. Therefore, the DC bus voltage U pvdc , U eldc To describe the dynamic behavior of the photovoltaic array, electrolyzer and its converter, the photovoltaic side terminal voltage U pvt , electrolytic cell side voltage U elt To describe the degree of system failure.

[0089] 1.2) Power variation:

[0090] One of the main external characteristics of the photovoltaic power generation system and the electrolyzer system is the photovoltaic output power and the electrolyzer absorption power, which is achieved through power control. When the system is operating normally, the power between the photovoltaic power generation system, the electrolyzer system, and the power grid is balanced; when the system fails, the photovoltaic side inverter and the electrolyzer side rectifier will respond to the power change on the grid side by changing their control strategy, so that the entire system is in a power balance state again. Therefore, the photovoltaic active power P can be selected. pv , Photovoltaic reactive power Q pv , electrolytic cell active power P el To describe the dynamic behavior of photovoltaic systems and electrolyzer systems.

[0091] The grid voltage is used as the directional vector for vector control, and the three-phase voltage and current are converted into a two-phase rotating dq coordinate system, so that the grid voltage vector e g coincides with the d axis, that is, e gd =E g 、e gq =0, the grid-side active power and reactive power can be expressed as:

[0092] (18)

[0093] Among them, Q g is the grid-side reactive power; E g is the grid side voltage.

[0094] From the above formula, we can know that the grid-side active power can be controlled by the d-axis current, and the grid-side reactive power can be controlled by the q-axis current. The photovoltaic side current I pvt 、Electrolytic cell side current I elt To characterize the power change on the grid side.

[0095] 1.3) Spatial information:

[0096] When the system is operating normally, the photovoltaic power generation system always maintains the maximum power output, the electrolyzer system always maintains the rated power operation, and the power grid absorbs and emits a certain amount of power to maintain the power balance of the entire system. When the system fails, the spatial distribution of large-scale photovoltaic hydrogen production sites is large, and the operating status of photovoltaic power generation systems and electrolyzer systems at different locations will change. The photovoltaic arrays and electrolyzers close to the fault point are more deeply affected by the fault, and their power fluctuations are larger; the photovoltaic arrays and electrolyzers far from the fault point are less affected by the fault or even unaffected. The photovoltaic power P can be selected pv , Q pv , electrolytic cell power P el The dynamic impact of spatial information on photovoltaic hydrogen production sites is quantified and characterized.

[0097] From the above analysis, we can see that U pvdc , U eldc , U pvt , U elt ,I pvt ,I elt , P pv , Q pv , P el The comprehensive consideration of factors such as can relatively comprehensively characterize the dynamic characteristics of the photovoltaic hydrogen production station. That is, according to the control process of the photovoltaic hydrogen production station in step 2, the key factors that can characterize the dynamic characteristics of the station are as follows: Fig. 9 As shown, the above factors are strongly coupled, nonlinear, and have dimensional differences. If all factors are considered together, low modeling efficiency, poor interpretability, and poor implementation possibility may occur. They need to be screened and refined to reduce the information redundancy of the input features and facilitate the subsequent clustering of photovoltaic hydrogen production sites.

[0098] 2) Perform data preprocessing:

[0099] In order to improve the accuracy and convergence speed of the model, it is necessary to pre-process the key factors of different attributes and physical characteristics. Since the data units of different factors are inconsistent and the numerical differences are large, the data of each factor is regularized before analyzing each factor, that is, the p-norm of the sample data is first calculated, and then all elements of the sample data are divided by the norm, which can reduce the equivalent error and avoid data overfitting.

[0100] For the vector x=[x 1 , x 2 , …, x n ] T (n is the number of samples), its p-norm can be expressed as:

[0101] (19)

[0102] The sample data is normalized and can be expressed as:

[0103] (20)

[0104] Among them, x ir is the result of regularization of each sample data, which is distributed between [0,1]; x i is the i-th original sample data.

[0105] 3) Construct data features:

[0106] Autoencoders are a neural network model that uses the back propagation algorithm for unsupervised learning and can be used for data dimensionality reduction and feature extraction. It mainly consists of two parts: encoding and decoding. The encoder compresses the input high-dimensional data into a low-dimensional data representation to extract the most informative features of the input data; the decoder reconstructs the original input data from the low-dimensional data representation. For sample data that has been normalized, the operations of the encoder and decoder can be expressed as:

[0107] (twenty one)

[0108] Among them, z en 、x de are low-dimensional data and reconstructed data respectively; f and g are activation functions of encoder and decoder respectively; W en , W de are the weight matrices of the encoder and decoder respectively; b en , b de are the bias items of the encoder and decoder respectively.

[0109] The weight matrix and bias term in the encoding and decoding process are updated using the stochastic gradient descent method to minimize the error between the reconstructed data and the original high-dimensional data. The objective function can be expressed as:

[0110] (twenty two)

[0111] Among them, R re is the reconstruction error; L lo is the loss function.

[0112] When using an autoencoder to reduce the dimensionality of key factors that characterize the dynamic characteristics of large-scale photovoltaic hydrogen production stations, the hidden layer in the autoencoder, that is, the result after data dimensionality reduction, is often the focus of attention. Due to the large amount of data and high complexity of key factors, overfitting problems are prone to occur. Sparse autoencoders introduce sparsity penalty terms to force sparse activation of hidden layer neurons so that they can better learn the characteristics and structure of input data. Compared with traditional autoencoders, sparse autoencoders have no restrictions on the amount of input data, can filter out noise and redundant information in the data, extract the most critical features for classification and recognition, and improve the robustness and generalization ability of the system. The control objective of the sparse autoencoder is to add a sparse penalty term on the basis of the loss error, which can be expressed as:

[0113] (twenty three)

[0114] Among them, R sa is the control target of the sparse autoencoder; Ω is the penalty term.

[0115] The penalty term is constructed using KL divergence, which can be expressed as:

[0116] (twenty four)

[0117] Among them, K l is the number of hidden layer nodes; ρ s is to set the activation value; ρ kav is the average activation value of the hidden layer.

[0118] Then the objective function of the sparse autoencoder can be expressed as:

[0119] (25)

[0120] Among them, β pf is the penalty factor.

[0121] In order to avoid losing too much information during the data dimensionality reduction process, the information retention rate is introduced to reduce redundant information while ensuring the amount of information, which can be expressed as:

[0122] (26)

[0123] Among them, η ir is the information retention rate; d en is the feature dimension after data dimensionality reduction; x ir,j 、x de,j are the j-th dimension features of the original data and the reconstructed data respectively; m is the feature dimension of the original data.

[0124] 4) Perform clustering:

[0125] After using the autoencoder to obtain the data features of the grid-connected system of large-scale photovoltaic hydrogen production stations, it can be used as a clustering indicator, and a clustering algorithm can be used to cluster photovoltaic systems and electrolyzer systems. The k-means algorithm has the characteristics of fast calculation speed and simple and easy to understand, and is widely used in cluster division. The k-means algorithm is an iterative clustering algorithm. Its core idea is to divide the data set into k groups so that each data point belongs to the group with the closest distance, that is, to divide the photovoltaic hydrogen production stations with the most similar characteristics into one group. There are many studies on the k-means algorithm, which will not be repeated here.

[0126] Step 4: Use capacity weighting, equal power loss method, etc. to construct an equivalent model for the equipment in the same cluster to form a multi-machine equivalent model for large-scale photovoltaic hydrogen production stations, including:

[0127] Based on the dynamic characteristics of large-scale photovoltaic hydrogen production stations, photovoltaic power generation units and electrolyzer units with similar characteristics are divided into a cluster. Several units can be used to perform equivalent evaluation on the entire photovoltaic hydrogen production station. This unit can accurately characterize the operating characteristics of a cluster. At the same time, the external characteristics of the photovoltaic hydrogen production station at the grid connection point before and after the equivalent evaluation are consistent. The construction of the equivalent unit model mainly includes the equivalent evaluation of the electrolyzer system, the equivalent evaluation of the photovoltaic system, and the equivalent evaluation of the transformer.

[0128] 1) Electrolyzer system equivalent:

[0129] The equivalent principle of the electrolyzer system is that the required power remains unchanged before and after the equivalent, that is, the required power of the electrolyzer sub-cluster is equal to the sum of the required power of all electrolyzer units in the cluster, which can be expressed as:

[0130] (27)

[0131] Among them, P tel,s is the equivalent power of the sth electrolytic cell sub-cluster; P el,as is the power required by the ath electrolyzer unit in the sth electrolyzer subcluster; is the number of electrolytic cell units in the sth electrolytic cell sub-cluster.

[0132] 2) Photovoltaic system equivalent:

[0133] The equivalence principle of the photovoltaic system is that the output power remains unchanged before and after the equivalence, that is, the output power of the photovoltaic sub-cluster is equal to the sum of the output powers of all photovoltaic power generation units in the cluster, which can be expressed as:

[0134] (28)

[0135] Among them, P tpv,t , Q tpv,t are the equivalent active and reactive power of the t-th PV sub-cluster respectively; P pv,bt, Q pv,bt are the active and reactive power of the b-th photovoltaic power generation unit in the t-th photovoltaic sub-cluster, respectively; is the number of photovoltaic power generation units in the tth photovoltaic sub-cluster.

[0136] 3) Transformer equivalent:

[0137] The transformer equivalent principle is that the power loss before and after the equivalent remains unchanged. The total power loss of the transformers in a cluster is equal to the sum of the power losses of each transformer, which can be expressed as:

[0138] (29)

[0139] Among them, P ttr,w、 S ttr,w are the equivalent active power loss and rated capacity of the transformer in the wth sub-cluster respectively; P tr,cw , S tr,cw are the active power loss and rated capacity of the cth transformer in the wth sub-cluster, respectively; is the number of transformers in the wth sub-cluster.

[0140] In addition, the present invention also provides a large-scale photovoltaic hydrogen production station equivalent modeling system, including the following modules:

[0141] The structural construction module considers the capacity of the photovoltaic hydrogen production station and determines the basic structure of the grid-connected system of the large-scale photovoltaic hydrogen production station;

[0142] The model building module builds an electrolyzer system model with a single electrolyzer as a unit and a photovoltaic power generation system model with a single photovoltaic array as a unit according to the site structure and the working principles of the electrolyzer and photovoltaic array and the control method of their converters;

[0143] The clustering module analyzes the key factors reflecting the dynamic characteristics of photovoltaic hydrogen production stations based on the working principles of the electrolyzer system and photovoltaic power generation system and their interaction mechanism with the power grid. It uses a sparse autoencoder to reduce the dimension of key factors to remove redundant information, and clusters the electrolyzer units and photovoltaic power generation units in the photovoltaic hydrogen production station through a clustering algorithm.

[0144] The multi-machine equivalent construction module uses capacity weighting and equal power loss method to construct an equivalent model for the equipment in the same cluster, forming a multi-machine equivalent model for large-scale photovoltaic hydrogen production stations.

[0145] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the above-mentioned method for equivalent modeling of a large-scale photovoltaic hydrogen production station are implemented.

[0146] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for equivalent modeling of a large-scale photovoltaic hydrogen production station.

[0147] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The solutions in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and interpreted scripting language JavaScript, etc.

[0148] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0149] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0150] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0151] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0152] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for equivalent modeling of large-scale photovoltaic hydrogen production stations, characterized in that: The steps include: Step 1: Based on the capacity of the photovoltaic hydrogen production station and the actual application of the water electrolysis hydrogen production demonstration project, the basic structure of the grid-connected system of the large-scale photovoltaic hydrogen production station is constructed; Step 2: According to the site structure and the working principles of the electrolyzer and photovoltaic array and the control method of their converters, an electrolyzer system model with a single electrolyzer as a unit and a photovoltaic power generation system model with a single photovoltaic array as a unit are established; Step 3: Based on the working principles of the electrolyzer system and the photovoltaic power generation system and their interaction mechanism with the power grid, the key factors reflecting the dynamic characteristics of the photovoltaic hydrogen production station are analyzed, and the sparse autoencoder is used to reduce the dimension of the key factors to remove redundant information. The electrolyzer units and photovoltaic power generation units in the photovoltaic hydrogen production station are grouped by a clustering algorithm; Step 4: Use the capacity-weighted and equal power loss method to construct an equivalent model for the equipment in the same cluster to form a multi-machine equivalent model for a large-scale photovoltaic hydrogen production station.

2. A method for equivalent modeling of a large-scale photovoltaic hydrogen production station according to claim 1, characterized in that In step 1, the basic structure of a large-scale photovoltaic hydrogen production station grid-connected system is constructed, including: The green electricity generated by the photovoltaic power generation system passes through the Boost circuit and inverter, and then through the step-up transformer through the collection line and then through the main step-up transformer to connect to the 220kV line for transmission to the hydrogen production plant; the electric energy consumed by the water electrolysis hydrogen production device is connected from the 220kV line through the main step-down transformer through multiple lines to the step-down transformer, and then through the rectifier and Buck circuit for supply and use; the path of the electricity generated by the photovoltaic system and the electricity consumed by the electrolyzer is basically opposite; the power grid is connected to the 220kV line. When the electricity generated by the 100-megawatt photovoltaic hydrogen production station is too much, the excess electricity is consumed by the power grid; when the electricity generated by the photovoltaic is not enough to support the minimum power operation of the electrolyzer, the power grid supplies energy to support the continuous operation of the electrolyzer.

3. The equivalent modeling method for a large-scale photovoltaic hydrogen production station according to claim 1 is characterized in that: In the step 2, an electrolytic cell system model with a single electrolytic cell as a unit is established, including: 1) Construct the electrolytic cell model as follows: （1） Among them, U el is the cell voltage; U rev is the reversible voltage; U ohm is the ohmic overvoltage; U acta , U actc They are the anode activation overvoltage and the cathode activation overvoltage respectively; Each electrolyzer stack consists of multiple electrolysis cells; The reversible voltage is expressed as: （2） Among them, N el is the number of electrolysis chambers; ΔG is the Gibbs free energy; z is the number of electrons required to transfer to produce 1 mole of hydrogen; F is the Faraday constant; R is the ideal gas constant; T el is the working temperature of the electrolytic cell; P H2 , P O2 are the partial pressures of hydrogen and oxygen, the reaction products; α H2O is water activity; ln() is logarithmic function; The ohmic overvoltage is expressed as: （3） Among them, A el is the surface area of ​​the electrolytic cell; r1, r2, r3, r4 are the area specific resistivity of the electrolytic cell monomer; I el is the electrolytic cell current; The activation overvoltage is expressed as: （4） （5） Among them, I acta ,I actc are the anode activation current and cathode activation current respectively; a el , b el 、c el ,d el is the Tafel empirical coefficient, expressed as: （6） （7） （8） （9） Among them, a1, a2, a3, b1, b2, b3 are the empirical coefficients of the anode activation resistance of the electrolytic cell; c1, c2, c3, d1, d2, d3 are the empirical coefficients of the cathode activation resistance of the electrolytic cell; 2) Construct the converter on the electrolyzer side and its control model. The electrolyzer adopts two-stage control of rectifier and Buck converter, that is, the rectifier is used to convert the source side AC power into DC power, and the Buck converter reduces the voltage to the voltage required by the electrolyzer. When the system is operating normally, according to the operating status of the system and the operating range of the electrolyzer, the two-stage controllers both adopt a dual-loop control method of power and voltage outer loop and current inner loop to achieve real-time control of the electrolyzer reference power and DC voltage. When the photovoltaic output fluctuates greatly or the system is in a fault state, a voltage response link is added to the outer loop control to give full play to the response and regulation characteristics of the electrolyzer.

4. A method for equivalent modeling of a large-scale photovoltaic hydrogen production station according to claim 1, characterized in that In step 2, a photovoltaic power generation system model with a single photovoltaic array operation as a unit is established, including: 1) Construct a photovoltaic array model, including: The photovoltaic cell model is expressed as: （10） Among them, U pc ,I pc are the output voltage and output current of the photovoltaic cell respectively; I sc is the photocurrent; I0 ​​is the reverse saturation current of the parallel diode; q is the electron coulomb constant; R sh , R s are shunt resistance and parasitic resistance respectively; n is the ideal quality factor of the diode; K is the Boltzmann constant; T pv is the photovoltaic cell temperature; exp() is the exponential function; The photovoltaic array is composed of multiple photovoltaic cells connected in series and parallel, and its model is expressed as: （11） Among them, U pv ,I pv are the output voltage and output current of the photovoltaic array respectively; N s 、N p are the number of photovoltaic cells connected in series and in parallel, respectively; 2) Construct the photovoltaic side converter and its control model. The photovoltaic array adopts two-level control of Boost converter and inverter, that is, the Boost converter is used to increase the voltage on the photovoltaic array side to the voltage required on the grid side, and the inverter converts DC power into AC power. When the system is operating normally, the Boost circuit often adopts the maximum power point tracking technology to achieve the maximum power output of the photovoltaic array. The inverter adopts the dual-loop control method of voltage, power outer loop and current inner loop to keep the amplitude, voltage, frequency and phase of the grid connected consistent, and the photovoltaic power generation system achieves unity power factor operation. When the system is in a fault state, that is, when the voltage at the photovoltaic side port drops or rises, the photovoltaic inverter will switch to the fault ride-through control mode to absorb and emit a certain amount of reactive power to support the recovery of the grid voltage. The Boost converter will switch to the dual-loop control method of power outer loop and current inner loop to achieve power balance of the overall system.

5. The equivalent modeling method for a large-scale photovoltaic hydrogen production station according to claim 1 is characterized in that: In step 3, the electrolyzer units and photovoltaic power generation units in the photovoltaic hydrogen production station are grouped, including key factor analysis, including: 1) The photovoltaic array, electrolyzer and grid exchange power information through two-stage converters. When a fault occurs on the grid side, the power emitted and absorbed by the photovoltaic side and the electrolyzer side cannot immediately track the power changes on the grid side. The active power on the grid side, photovoltaic side and electrolyzer side is expressed as: （12） （13） （14） Among them, P g is the grid-side active power; e gd 、e gq are the d-axis and q-axis components of the grid-side voltage respectively; i gd 、i gq are the d-axis and q-axis components of the grid-side current respectively; P pv is the photovoltaic active power; P el is the active power of the electrolyzer; According to the power balance principle, we get: （15） Among them, P g1 , P g2 are the interactive power between the grid side, the photovoltaic side and the electrolyzer side; ΔP1 and ΔP2 are the unbalanced power between the photovoltaic side and the electrolyzer side; C pvdc , C eldc are the DC bus capacitors on the photovoltaic side and the electrolyzer side respectively; U pvdc , U eldc is the DC bus voltage on the photovoltaic side and the electrolyzer side; The unbalanced power on the photovoltaic side, electrolyzer side and grid side is absorbed by the DC bus capacitor. The DC bus voltage U pvdc , DC bus voltage U on the electrolytic cell side eldc To describe the dynamic behavior of the photovoltaic array, electrolyzer and its converter, the photovoltaic side terminal voltage U pvt , electrolytic cell side voltage U elt To describe the degree of system failure; 2) When the system is operating normally, the power among the photovoltaic power generation system, the electrolyzer system and the power grid is balanced; when the system fails, the photovoltaic hydrogen production station will change the control strategy to respond to the power change on the grid side, so that the system power reaches a new balance state, and the photovoltaic active power P is selected. pv , Photovoltaic reactive power Q pv 、Electrolyzer active power P el To describe the dynamic behavior of photovoltaic systems and electrolyzer systems; The grid voltage is used as the directional vector for vector control, and the three-phase voltage and current are converted into a two-phase rotating dq coordinate system, so that the grid voltage vector e g coincides with the d axis, that is, e gd =E g 、e gq =0, the grid-side active power and reactive power are expressed as: （16） Among them, Q g is the grid-side reactive power; E g is the grid-side voltage; From the above formula, the grid-side active power is controlled by the d-axis current, and the grid-side reactive power is controlled by the q-axis current. The photovoltaic side terminal current I is selected pvt 、Electrolytic cell side current I elt To characterize the power change on the grid side; 3) The light intensity and fault degree at different spatial locations are different, so the photovoltaic power P is selected pv , Q pv , electrolytic cell power P el Quantify the impact of spatial information on the dynamics of photovoltaic hydrogen production sites; In summary, U pvdc , U eldc , U pvt , U elt ,I pvt ,I elt , P pv , Q pv , P el The comprehensive consideration relatively comprehensively characterizes the dynamic characteristics of photovoltaic hydrogen production stations.

6. The equivalent modeling method for a large-scale photovoltaic hydrogen production station according to claim 5 is characterized in that: In step 3, the electrolyzer units and photovoltaic power generation units in the photovoltaic hydrogen production station are grouped, including dimensionality reduction of key factors, including: 1) Regularize the data of each factor, first find the p-norm of the sample data, and then divide all elements of the sample data by the norm; For a vector x=[x1, x2, …, x n ] T , n is the number of samples, and its p-norm is expressed as: （17） Each sample data is normalized and expressed as: （18） Among them, x ir is the result of regularization of each sample data, which is distributed between [0,1]; x i is the i-th original sample data; 2) For the sample data that has been normalized, the autoencoder is used to reduce the dimension of the data and extract features. The operations of the encoder and decoder are expressed as follows: （19） Among them, z en 、x de are low-dimensional data and reconstructed data respectively; f and g are activation functions of encoder and decoder respectively; W en , W de are the weight matrices of the encoder and decoder respectively; b en , b de are the bias items of the encoder and decoder respectively; The weight matrix and bias term in the encoding and decoding process are updated using the stochastic gradient descent method to minimize the error between the reconstructed data and the original high-dimensional data. The objective function is expressed as: （20） Among them, R re is the reconstruction error; L lo is the loss function; A sparse autoencoder is used to introduce a sparsity penalty term. By forcing the sparse activation of hidden layer neurons, it can better learn the characteristics and structure of the input data. The control goal of the sparse autoencoder is to add a sparse penalty term on the basis of the loss error, which is expressed as: （21） Among them, R sa is the control target of the sparse autoencoder; Ω is the penalty term; The penalty term is constructed using KL divergence, expressed as: （22） Among them, K l is the number of hidden layer nodes; ρ s is to set the activation value; ρ kav is the average activation value of the hidden layer; Then the objective function of the sparse autoencoder is expressed as: （23） Among them, β pf is the penalty factor; In order to avoid losing too much information during the data dimensionality reduction process, the information retention rate is introduced to reduce redundant information while ensuring the amount of information, which is expressed as: （24） Among them, η ir is the information retention rate; d en is the feature dimension after data dimensionality reduction; x ir,j 、x de,j are the j-th dimension features of the original data and the reconstructed data respectively; m is the feature dimension of the original data; 3) After using the autoencoder to obtain the data characteristics of the grid-connected system of large-scale photovoltaic hydrogen production stations, it is used as a clustering indicator, and a clustering algorithm is used to cluster the photovoltaic system and the electrolyzer system, and the photovoltaic hydrogen production stations with the most similar characteristics are divided into the same cluster.

7. The equivalent modeling method of a large-scale photovoltaic hydrogen production station according to claim 1 is characterized in that In step 4, a multi-machine equivalent model of a large-scale photovoltaic hydrogen production station is formed, including: 1) The principle of equalization of electrolyzer system is that the required power remains unchanged before and after equalization, that is, the required power of the electrolyzer sub-cluster is equal to the sum of the required power of all electrolyzer units in the cluster, expressed as: （25） Among them, P tel,s is the equivalent power of the sth electrolytic cell sub-cluster; P el,as is the power required by the ath electrolyzer unit in the sth electrolyzer subcluster; is the number of electrolytic cell units in the sth electrolytic cell sub-cluster; 2) The equivalence principle of the photovoltaic system is that the output power remains unchanged before and after the equivalence, that is, the output power of the photovoltaic sub-cluster is equal to the sum of the output powers of all photovoltaic power generation units in the cluster, expressed as: （26） Among them, P tpv,t , Q tpv,t are the equivalent active and reactive power of the t-th PV sub-cluster respectively; P pv,bt , Q pv,bt are the active and reactive power of the b-th photovoltaic power generation unit in the t-th photovoltaic sub-cluster, respectively; is the number of photovoltaic power generation units in the t-th photovoltaic sub-cluster; 3) The transformer equivalent principle is that the power loss before and after the equivalent remains unchanged. The total power loss of the transformers in a cluster is equal to the sum of the power losses of each transformer, expressed as: （27） Among them, P ttr,w、 S ttr,w are the equivalent active power loss and rated capacity of the transformer in the wth sub-cluster respectively; P tr,cw , S tr,cw are the active power loss and rated capacity of the cth transformer in the wth sub-cluster, respectively; is the number of transformers in the wth sub-cluster.

8. A large-scale photovoltaic hydrogen production station equivalent modeling system, characterized in that: Includes the following modules: The structural construction module considers the capacity of the photovoltaic hydrogen production station and determines the basic structure of the grid-connected system of the large-scale photovoltaic hydrogen production station; The model building module builds an electrolyzer system model with a single electrolyzer as a unit and a photovoltaic power generation system model with a single photovoltaic array as a unit according to the site structure and the working principles of the electrolyzer and photovoltaic array and the control method of their converters; The clustering module analyzes the key factors reflecting the dynamic characteristics of photovoltaic hydrogen production stations based on the working principles of the electrolyzer system and photovoltaic power generation system and their interaction mechanism with the power grid. It uses a sparse autoencoder to reduce the dimension of key factors to remove redundant information, and clusters the electrolyzer units and photovoltaic power generation units in the photovoltaic hydrogen production station through a clustering algorithm. The multi-machine equivalent construction module uses capacity weighting and equal power loss method to construct an equivalent model for the equipment in the same cluster, forming a multi-machine equivalent model for large-scale photovoltaic hydrogen production stations.

9. Provide an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of a method for equivalent modeling of a large-scale photovoltaic hydrogen production station as described in any one of claims 1 to 7 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for equivalent modeling of a large-scale photovoltaic hydrogen production station as described in any one of claims 1 to 7 are implemented.

Images