CN114123200B - Photovoltaic power station dynamic modeling method based on data driving and storage device - Google Patents

Photovoltaic power station dynamic modeling method based on data driving and storage device Download PDF

Info

Publication number
CN114123200B
CN114123200B CN202210080739.2A CN202210080739A CN114123200B CN 114123200 B CN114123200 B CN 114123200B CN 202210080739 A CN202210080739 A CN 202210080739A CN 114123200 B CN114123200 B CN 114123200B
Authority
CN
China
Prior art keywords
photovoltaic power
power station
voltage
neural network
convolution
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210080739.2A
Other languages
Chinese (zh)
Other versions
CN114123200A (en
Inventor
姬玉泽
陈文刚
宰洪涛
朱剑飞
王新瑞
张轲
原亚飞
刘贺龙
杨世宁
张玉娟
陈磊
姚泽龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jincheng Power Supply Co of State Grid Shanxi Electric Power Co Ltd
Original Assignee
Jincheng Power Supply Co of State Grid Shanxi Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jincheng Power Supply Co of State Grid Shanxi Electric Power Co Ltd filed Critical Jincheng Power Supply Co of State Grid Shanxi Electric Power Co Ltd
Priority to CN202210080739.2A priority Critical patent/CN114123200B/en
Publication of CN114123200A publication Critical patent/CN114123200A/en
Application granted granted Critical
Publication of CN114123200B publication Critical patent/CN114123200B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H02J3/381—Dispersed generators
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/04—Power grid distribution networks
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/20—The dispersed energy generation being of renewable origin
    • H02J2300/22—The renewable source being solar energy
    • H02J2300/24—The renewable source being solar energy of photovoltaic origin
    • H02J2300/26—The renewable source being solar energy of photovoltaic origin involving maximum power point tracking control for photovoltaic sources
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B10/00—Integration of renewable energy sources in buildings
    • Y02B10/10—Photovoltaic [PV]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E10/00—Energy generation through renewable energy sources
    • Y02E10/50—Photovoltaic [PV] energy
    • Y02E10/56—Power conversion systems, e.g. maximum power point trackers

Abstract

The invention provides a photovoltaic power station dynamic modeling method and storage equipment based on data driving, wherein the method comprises the following steps: s10, establishing a database of the photovoltaic power station in a normal grid-connected operation state based on the operation monitoring information of the photovoltaic power station; s20, establishing a relational equation of the input variable and the output variable of the photovoltaic power station; the input variables include: ambient light intensity and temperature, the output variables including: the output voltage and power of the grid-connected point when the photovoltaic power station normally operates; s30, dividing the data in the database into a training set and a test set; s40, training the convolutional neural network model through a training set, wherein the trained convolutional neural network model has a dynamic model of the operation characteristic of the photovoltaic power station; s50, inputting the test set into the dynamic model, and predicting voltage and power to obtain a prediction result; the photovoltaic power station control method has the beneficial effects of higher reliability and accuracy, and is suitable for the field of photovoltaic power stations.

Description

Photovoltaic power station dynamic modeling method based on data driving and storage device
Technical Field
The invention relates to the technical field of photovoltaic power stations, in particular to a dynamic modeling method and storage equipment of a photovoltaic power station based on data driving.
Background
In the process of constructing a novel power system mainly using new energy, the new energy brings many difficulties to planning and regulation of a power grid due to factors such as uncertain output, large power fluctuation and the like; in order to realize effective management of new energy power generation and improve the reliability and stability of operation of a novel power system, a large number of modeling methods and prediction models related to new energy power generation are provided in the field of electrical engineering.
Generally, in new energy power generation, the ratio of a photovoltaic power station gradually increases, photovoltaic power generation is a technology for directly converting light energy into electric energy by using the photovoltaic effect of a semiconductor interface, and the operation output of the photovoltaic power generation depends on the change of external illumination and the working state of a semiconductor; in addition, the novel power system still mainly operates in an alternating current synchronous mechanism, so that the photovoltaic power station comprises an inverter and a controller part except a photovoltaic battery component part, and the inverter and the controller part are used for boosting and inverting grid connection of photovoltaic power generation; therefore, the photovoltaic power station is modeled by considering not only the operating characteristics of the photovoltaic cells but also the operating characteristics of the controller and the inverter circuit.
At present, when modeling a photovoltaic power station, the following three modeling methods are generally adopted:
the equivalent modeling of the photovoltaic cell comprises the following steps: the method has the starting point that the photovoltaic cell is equivalent to a diode device according to the working principle of the photovoltaic cell, under the general test condition (the general temperature is 25 ℃, the illuminance is 1000W/square meter), a Norton equivalent circuit of the photovoltaic cell is established by using five parameters, namely short-circuit current, open-circuit voltage, maximum power point output power and voltage and current at the maximum power point, when the method is adopted to carry out equivalent modeling on the photovoltaic cell, the nonlinear working characteristic of the cell is subjected to linearization treatment, and a 'four-parameter' or 'three-parameter' model is established for expressing the working characteristic of the photovoltaic cell; when an inverter and a control system of a photovoltaic power plant are researched, a parametric model is further simplified, and a single current source is used for equivalent modeling expression of a photovoltaic cell.
Secondly, equivalent modeling of the photovoltaic power generation inverter: the method has the starting point that modeling is carried out aiming at the control and working conduction state of the inverter, the modeling is generally carried out by adopting a switching function modeling or parameter identification method, a relational equation of control loop control parameters (PI parameters) and an inverter working circuit is established, and the working characteristics of the inverter are expressed by using the switching function equation.
And thirdly, equivalent modeling of a control loop: the method is characterized in that the method is equivalent according to different operation control modes adopted by photovoltaic power generation, a control loop is the most complex part in the equivalent modeling process of a photovoltaic power station, the voltage and power stability of the photovoltaic power generation is influenced, and when the photovoltaic power generation is influenced by external environment changes, control parameters can influence the control and adjustment of the voltage and power. Generally, a control loop equation is adopted to express the change of a control mode, the adjustment and selection of control parameters have great difficulty, and the photovoltaic power generation can be adjusted to be stable only by adaptively changing the control parameters when the output power and the voltage of the photovoltaic are subjected to transient fluctuation.
In summary, a photovoltaic power generation system is a complex nonlinear system, and a traditional equivalent modeling method generally carries out linearization treatment on the system to obtain a modeling method and a model suitable for a specific research purpose; however, with the continuous development of new power systems, the demand of the power grid for new energy is gradually increased, and the influence of the new energy on the power grid is gradually enlarged and deepened, so that the traditional modeling method and model are no longer suitable for engineering research and application.
Therefore, it is necessary to establish a model capable of accurately reflecting photovoltaic dynamic changes in real time according to actual engineering requirements.
Disclosure of Invention
Aiming at the defects in the related technology, the technical problem to be solved by the invention is as follows: the photovoltaic power station dynamic modeling method and the storage device based on the data driving are high in accuracy and reliability.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
the photovoltaic power station dynamic modeling method based on data driving comprises the following steps:
s10, establishing a database of the photovoltaic power station in a normal grid-connected operation state based on the operation monitoring information of the photovoltaic power station;
s20, establishing a relational equation of the input variable and the output variable of the photovoltaic power station; the input variables include: ambient light intensity and temperature, the output variables including: the output voltage and power of the grid-connected point when the photovoltaic power station normally operates;
s30, dividing the data in the database into a training set and a test set;
s40, training the convolutional neural network model through a training set, wherein the trained convolutional neural network model has a dynamic model of the operation characteristic of the photovoltaic power station;
s50, inputting the test set into the dynamic model, and predicting voltage and power to obtain a prediction result;
wherein, the database comprises: temperature information, illuminance information, and power change information and voltage change information of the photovoltaic power station.
Preferably, the method further comprises the following steps:
and S60, verifying the accuracy of the dynamic model based on the test set and the prediction result.
Preferably, the expression of the relational equation of the input variables and the output variables is:
Figure 384408DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 582171DEST_PATH_IMAGE002
and
Figure 129827DEST_PATH_IMAGE003
representing the voltage and power of the grid-connected point at time t,
Figure 96646DEST_PATH_IMAGE004
and
Figure 851981DEST_PATH_IMAGE005
representing the outside temperature and the illuminance at the moment t;
Figure 271461DEST_PATH_IMAGE006
representing a non-linear functional relationship based on ambient light illumination and temperature.
Preferably, the training of the convolutional neural network model by the training set specifically includes:
s401, an input layer of the convolutional neural network model receives sample data in a training set;
s402, inputting sample data into a convolution layer of the convolution neural network model;
s403, after normalization processing is carried out on the sample data by the convolution layer of the convolution neural network model, convolution operation is carried out to obtain a convolution result;
s404, carrying out nonlinear processing on the convolution result through an activation function ReLU;
s405, extracting the features in the convolution result after the nonlinear processing, and integrating other features through a full connection layer of the convolution neural network model to form an integrated result;
s406, the output layer of the convolutional neural network model outputs a comprehensive result, wherein the comprehensive result comprises: the power, the voltage amplitude and the voltage phase angle matrix of the grid-connected point of the photovoltaic power station;
wherein: the sample data is as follows: an external illumination intensity and temperature matrix of the photovoltaic power station;
the rows of the external illumination intensity and temperature matrix represent state variables of temperature and illumination intensity in a certain time period, the rows represent different time sampling points, and the columns represent the number of the state variables.
Preferably, a loss function is used in the convolutional layer and the fully-connected layer to optimize the convolutional result and the comprehensive result.
Accordingly, a data-driven based photovoltaic power plant predictive model, comprising: the photovoltaic battery module, the inverter and the control module are connected to the alternating current bus after the inverter and the control module carry out inversion processing on the voltage/current output by the photovoltaic battery module; further comprising:
and forming a data table/curve according to the output current of the photovoltaic cell module and the output voltage of the inverter and the control module corresponding to the external illumination intensity and the temperature.
Preferably, the photovoltaic cell module includes: a current output equation;
the current output equation is:
Figure 888387DEST_PATH_IMAGE007
；
wherein:
Figure 709713DEST_PATH_IMAGE008
representing the photo-generated current of the semiconductor under illumination,
Figure 386682DEST_PATH_IMAGE009
representing the total diffusion current formed during operation of the PN junction within the semiconductor,
Figure 559037DEST_PATH_IMAGE010
shows the loss current formed by various resistances such as the battery material and the surface,
Figure 694834DEST_PATH_IMAGE012
represents the output current;
the control strategy of the inverter and the control module adopts constant voltage control, the inverter and the control module comprise an inverter and a controller, wherein: the inverter equation is:
Figure 901824DEST_PATH_IMAGE013
Figure 484115DEST_PATH_IMAGE014
、
Figure 143766DEST_PATH_IMAGE015
、
Figure 836916DEST_PATH_IMAGE016
which represents the three-phase output current,
Figure 882101DEST_PATH_IMAGE017
representing the sum of the inductance resistance and the power device loss equivalent resistance,
Figure 900873DEST_PATH_IMAGE018
the inductance of each phase of the outgoing line reactor is shown,
Figure 782241DEST_PATH_IMAGE019
、
Figure 544661DEST_PATH_IMAGE020
、
Figure 195085DEST_PATH_IMAGE021
representing the switching functions of three bridge arms in the main circuit of the inverter;
the equations for the controller include: a voltage outer loop control function and a current inner loop control function, wherein:
the equation for the voltage outer loop control function is:
Figure 119179DEST_PATH_IMAGE022
the equation for the current inner loop control function is:
Figure DEST_PATH_IMAGE023
Figure 471531DEST_PATH_IMAGE024
、
Figure 772063DEST_PATH_IMAGE025
d-and q-axis output currents respectively representing currents,
Figure 542573DEST_PATH_IMAGE026
representing the voltage on the DC side
Figure 637568DEST_PATH_IMAGE027
A reference value of (d);
Figure 742796DEST_PATH_IMAGE028
and
Figure 847018DEST_PATH_IMAGE029
respectively representing the proportion and integral coefficients of the voltage outer ring active control;
Figure 472034DEST_PATH_IMAGE030
and
Figure 737931DEST_PATH_IMAGE032
respectively representing the proportion and integral coefficient of voltage outer loop reactive power control;
Figure 81187DEST_PATH_IMAGE033
a reference value representing the reactive power Q;
Figure 723521DEST_PATH_IMAGE034
and
Figure 720821DEST_PATH_IMAGE035
d-axis and q-axis output voltages respectively representing voltages;
Figure 157618DEST_PATH_IMAGE037
is a filter inductor;
Figure 988171DEST_PATH_IMAGE038
and
Figure 434196DEST_PATH_IMAGE039
respectively representing d-axis and q-axis components of the voltage;
Figure 768225DEST_PATH_IMAGE040
and
Figure 641503DEST_PATH_IMAGE042
respectively representing the proportion and the integral coefficient of an inner loop of the d-axis current;
Figure 208620DEST_PATH_IMAGE043
and
Figure 927177DEST_PATH_IMAGE044
respectively representing the proportion and the integral coefficient of an inner loop of the q-axis current;
Figure 646871DEST_PATH_IMAGE045
representing the current system frequency of the phase locked loop output.
Preferably, the method further comprises the following steps: and the maximum power tracking module judges the maximum power point by adopting an increment conductance method.
Accordingly, a storage device has stored therein a plurality of instructions adapted to be loaded by a processor and to perform the data-driven based photovoltaic power plant dynamic modeling method as described above.
The invention has the beneficial technical effects that:
1. according to the method, the database of the photovoltaic power station in the normal grid-connected operation state is established based on the operation monitoring information of the photovoltaic power station, so that the advantages of the large electric power data are fully exerted, and the method has a wider application prospect under the support of the large electric power data technology; meanwhile, the convolutional neural network model is trained through a training set, so that a dynamic model with the operating characteristics of the photovoltaic power station, which is established based on the convolutional neural network model, has higher reliability and accuracy.
2. According to the method, the nonlinear characteristic of the operation of the photovoltaic power station is fully considered, the actual operation characteristic of the photovoltaic power station is better met, and the method has more superiority in engineering application compared with the traditional ideal linear model.
Drawings
FIG. 1 is a circuit diagram of the operation of a solar cell;
FIG. 2 is an equivalent circuit diagram of a photovoltaic cell module of the present invention;
FIG. 3 is a schematic illustration of the effect of series resistance on the operation of a photovoltaic cell module;
FIG. 4 is a schematic illustration of the effect of parallel resistance on the operation of a photovoltaic cell module;
FIG. 5 is a schematic of a topology of an inverter and control module;
FIG. 6 is a schematic flow chart of the dynamic modeling method of the photovoltaic power plant based on data driving according to the invention;
FIG. 7 is a schematic flow chart of step S40 in the dynamic modeling method for a photovoltaic power plant based on data driving according to the present invention;
FIG. 8 is a schematic diagram of a simulation model based on MATLAB/Simulink pair invention;
FIG. 9 is a graph showing the results of a first condition of simulation using the simulation model of FIG. 8;
FIG. 10 is a graph showing the results of a second condition in simulation using the simulation model of FIG. 8;
FIG. 11 is a graph showing the results of a third condition of simulation using the simulation model of FIG. 8;
FIG. 12 is a schematic diagram of power prediction error in simulation using the simulation model of FIG. 8;
FIG. 13 is a schematic diagram of voltage prediction error in simulation using the simulation model of FIG. 8.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments, but not all embodiments, of the present invention; all other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Next, the present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially according to the general scale for convenience of illustration when describing the embodiments of the present invention, and the drawings are only examples, which should not limit the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
An embodiment of the present invention is described in detail below with reference to the accompanying drawings.
Example one
In this embodiment, the photovoltaic power plant prediction model based on data driving includes: the photovoltaic battery module comprises a photovoltaic battery module, an inverter and a control module, wherein the inverter and the control module are connected to an alternating current bus after the voltage/current output by the photovoltaic battery module is subjected to inversion processing, and a data table/curve is formed according to the output current of the photovoltaic battery module and the output voltage of the inverter and the control module corresponding to the external illumination intensity and the external temperature.
Specifically, as shown in fig. 1, the basic principle of photovoltaic power generation is to generate photovoltaic current by using the photovoltaic effect of semiconductors, so that a photovoltaic cell module is extremely sensitive to changes in light and temperature, and small changes of the photovoltaic cell module cause large fluctuations in voltage and current, and the photovoltaic cell module belongs to a typical unstable power supply.
Fig. 2 is an equivalent circuit of fig. 1, and as shown in fig. 2, the equation of the photovoltaic cell module is:
Figure 425471DEST_PATH_IMAGE046
；
wherein:
Figure 230616DEST_PATH_IMAGE008
representing the photo-generated current of the semiconductor under illumination,
Figure 18444DEST_PATH_IMAGE009
representing the total diffusion current formed during operation of the PN junction within the semiconductor,
Figure 576333DEST_PATH_IMAGE010
shows the loss current formed by various resistances such as the battery material and the surface,
Figure 791414DEST_PATH_IMAGE047
represents the output current of the power supply module;
Figure 818276DEST_PATH_IMAGE048
a series resistance representing the internal losses of the battery,
Figure 144215DEST_PATH_IMAGE050
which represents the sum of various resistances of the battery material and the surface.
In particular, the total diffusion current
Figure 572922DEST_PATH_IMAGE051
The calculation formula of (A) is as follows:
Figure 942592DEST_PATH_IMAGE052
(ii) a Wherein:
Figure 722329DEST_PATH_IMAGE053
represents the saturation current of the solar cell in the absence of illumination, q represents the charge of the mobile electrons, and generally takes the value of
Figure 851959DEST_PATH_IMAGE054
K represents Boltzmann constant, and generally takes the value
Figure 869594DEST_PATH_IMAGE055
T denotes the thermodynamic temperature, a denotes a constant factor, 1 for full diffusion and 2 for most recombination of holes and electrons in the depletion region.
Further, internal resistance of the photovoltaic cell module
Figure 692057DEST_PATH_IMAGE048
And
Figure 427931DEST_PATH_IMAGE050
as the operating state of the battery changes, as shown in fig. 3 and 4, the influence curves of the series and parallel resistors on the voltage and the current of the battery are nonlinear, so that the nonlinear influence of the resistors can be ignored when the traditional linear equation is adopted for modeling; therefore, in this embodiment, the photovoltaic cell module further includes a non-linear relationship curve established between the output current and the output voltage and between the external illumination intensity and the temperature; namely: the relational equation of the input variables and the output variables is: corresponding output current of photovoltaic cell module according to external illumination intensity and temperature
Figure 607590DEST_PATH_IMAGE057
Output voltage, formed data table/curve.
Generally, a photovoltaic power plant generally adopts a centralized inverter for grid connection, and three points are required for controlling the inverter: the voltage between the front and rear DC/AC stages is stable; 2. controlling the photovoltaic grid-connected current; 3. and scheduling the network side reactive power when necessary.
The photovoltaic power station generally adopts a grid connection method of a voltage type grid-connected inverter, mainly because an energy storage element in the voltage type inverter is a capacitor, the energy storage efficiency and the volume, price and other aspects of the energy storage element have obvious advantages.
The topological structure mechanism of the voltage type inverter circuit is easy to analyze, and an accurate mathematical model can be established according to the mechanism; however, the inversion process of the voltage-type inverter circuit depends on a corresponding control strategy, and the control strategy determines the operation mode of photovoltaic power generation.
As shown in fig. 5, in the present embodiment, the mathematical model of the circuit topology of the inverter is:
Figure 479731DEST_PATH_IMAGE058
wherein the content of the first and second substances,
Figure 473095DEST_PATH_IMAGE014
、
Figure 696266DEST_PATH_IMAGE015
、
Figure 167699DEST_PATH_IMAGE059
which represents the three-phase output current,
Figure 425505DEST_PATH_IMAGE060
representing the sum of the inductance resistance and the power device loss equivalent resistance,
Figure 573458DEST_PATH_IMAGE061
the inductance of each phase of the outgoing line reactor is shown,
Figure 283925DEST_PATH_IMAGE062
、
Figure 293469DEST_PATH_IMAGE063
、
Figure 671361DEST_PATH_IMAGE021
the switching function of three bridge arms in the main circuit of the inverter is represented, and a switching driving signal of the grid-connected inverter can be generated through the control of the control module and the conversion of SVPWM;
Figure 740948DEST_PATH_IMAGE064
、
Figure 187979DEST_PATH_IMAGE065
、
Figure 1214DEST_PATH_IMAGE066
representing the three-phase voltage at the output side of the inverter.
The inverter for photovoltaic power generation generally comprises a voltage outer ring and a current inner ring, wherein the voltage outer ring realizes the static-error-free control of direct-current voltage by utilizing PI regulation and voltage feedback regulation, and the current inner ring is arranged
Figure 968033DEST_PATH_IMAGE067
Implemented in a coordinate system, using
Figure 208522DEST_PATH_IMAGE068
、
Figure 893581DEST_PATH_IMAGE069
Converting two coordinate systems, namely converting the coordinate system of the three-phase current and carrying out PI regulation to realize d-axis and q-axis components of the current
Figure 510507DEST_PATH_IMAGE070
And
Figure 581100DEST_PATH_IMAGE071
and then, generating a driving control signal through SVPWM conversion to control the on-off of each IGBT.
In this embodiment, the equation of the voltage outer loop control function is:
Figure 258069DEST_PATH_IMAGE072
the equation for the current inner loop control function is:
Figure DEST_PATH_IMAGE073
Figure 899266DEST_PATH_IMAGE024
、
Figure 54304DEST_PATH_IMAGE074
d-and q-axis output currents respectively representing currents,
Figure 247912DEST_PATH_IMAGE026
representing the voltage on the DC side
Figure 830203DEST_PATH_IMAGE027
A reference value of (d);
Figure 224276DEST_PATH_IMAGE075
and
Figure 183004DEST_PATH_IMAGE076
respectively representing the proportion and integral coefficients of the voltage outer ring active control;
Figure 244501DEST_PATH_IMAGE030
and
Figure 997694DEST_PATH_IMAGE032
respectively representing the proportion and integral coefficient of voltage outer loop reactive power control;
Figure 393909DEST_PATH_IMAGE077
a reference value representing the reactive power Q;
in the above equation
Figure 625170DEST_PATH_IMAGE078
Is a spatial variable, namely: the expression of the control function is generally expressed in the complex frequency domain, and the spatial function (generally, the time function f (t)) in the time domain is subjected to laplace transform to obtain the complex frequencyFunction expression in the domain), the parameter rule and the control performance of the space control variable can be more intuitively reflected and analyzed.
In this embodiment, the
Figure 541173DEST_PATH_IMAGE079
And
Figure 465267DEST_PATH_IMAGE076
the values of (a) may be: 7 and 800;
Figure 99511DEST_PATH_IMAGE080
and
Figure 400042DEST_PATH_IMAGE082
can be between 0.3 and 20.
Still further, still include: and the maximum power tracking module judges the maximum power point by adopting an increment conductance method.
The basic principle of the incremental conductance method is as follows:
formula of output power, voltage and current:
Figure 154240DEST_PATH_IMAGE083
at the maximum power point:
Figure 514814DEST_PATH_IMAGE084
thus, the algorithmic criteria for the incremental conductance method are:
Figure 370775DEST_PATH_IMAGE085
in this embodiment, the rated voltage may be U =0.26kV, and in a standard environment (a temperature of 25 ℃, an illuminance of 1000W per square meter), the MPPT control output active power P of the photovoltaic device is P =100kW, and the power factor cos Φ = 1.
The invention also provides a photovoltaic power station dynamic modeling method based on data driving.
As shown in fig. 6, the photovoltaic power plant dynamic modeling method based on data driving includes the following steps:
s10, establishing a database of the photovoltaic power station in a normal grid-connected operation state based on the operation monitoring information of the photovoltaic power station;
s20, establishing a relational equation of the input variable and the output variable of the photovoltaic power station; the input variables include: ambient light intensity and temperature, the output variables including: the output voltage and power of the grid-connected point when the photovoltaic power station normally operates;
s30, dividing the data in the database into a training set and a test set;
s40, training the convolutional neural network model through a training set, wherein the trained convolutional neural network model has a dynamic model of the operation characteristic of the photovoltaic power station, and the dynamic model is the dynamic model;
s50, inputting the test set into the dynamic model, and predicting voltage and power to obtain a prediction result;
wherein, the database comprises: temperature information, illuminance information, and power change information and voltage change information of the photovoltaic power station.
Specifically, the method further comprises the following steps: s60, verifying the accuracy of the dynamic model based on the test set and the prediction result; the method specifically comprises the following steps: and comparing and analyzing the power and voltage predicted values of the dynamic model with the power and voltage values of the actual operation of the photovoltaic power station, and evaluating the prediction accuracy of the dynamic model.
Further, the expression of the relational equation of the input variables and the output variables is:
Figure 209418DEST_PATH_IMAGE086
wherein the content of the first and second substances,
Figure 834434DEST_PATH_IMAGE002
and
Figure 615178DEST_PATH_IMAGE087
representing the voltage and power of the grid-connected point at time t,
Figure 958434DEST_PATH_IMAGE004
and
Figure 600768DEST_PATH_IMAGE005
representing the outside temperature and the illuminance at the moment t;
Figure 345870DEST_PATH_IMAGE088
representing a non-linear functional relationship based on ambient light illumination and temperature.
As shown in fig. 7, the training of the convolutional neural network model by the training set specifically includes:
s401, an input layer of the convolutional neural network model receives sample data in a training set;
s402, inputting sample data into a convolution layer of the convolution neural network model;
s403, after normalization processing is carried out on the sample data by the convolution layer of the convolution neural network model, convolution operation is carried out to obtain a convolution result;
s404, carrying out nonlinear processing on the convolution result through an activation function ReLU;
s405, extracting the features in the convolution result after the nonlinear processing, and integrating other features through a full connection layer of the convolution neural network model to form an integrated result;
s406, the output layer of the convolutional neural network model outputs a comprehensive result, wherein the comprehensive result comprises: the power, the voltage amplitude and the voltage phase angle matrix of the grid-connected point of the photovoltaic power station;
wherein: the sample data is as follows: an external illumination intensity and temperature matrix of the photovoltaic power station;
the rows of the external illumination intensity and temperature matrix represent state variables of temperature and illumination intensity in a certain time period, the rows represent different time sampling points, and the columns represent the number of the state variables.
Specifically, the normalization process includes: the data distribution of each layer is transformed into the distribution with the mean value of 0 and the variance of 1, the consistency of the data distribution in the training process can be ensured, the mutual influence of different data distribution characteristics in the training process of each layer is effectively avoided, particularly, the linearization result after the convolutional layer operation is easy to collapse into linear transformation, and a nonlinear processing method for normalization is necessary for accurately extracting the nonlinear characteristics of the data by the convolutional layer and improving the nonlinear mapping capability of the convolutional neural network.
Further, the convolution operation includes: carrying out convolution operation on each matrix block of the illumination intensity and temperature matrix of the input layer from left to right in sequence to obtain a convolution result; in order to weaken the interdependence relation among input parameters and relieve the overfitting problem, after each convolution, nonlinear processing is carried out through a ReLU function, and nonlinear results are sequentially arranged to form vectors of convolution layers so as to obtain variable characteristics of different nodes.
Further, the calculation method of the full connection layer is as follows:
Figure 782668DEST_PATH_IMAGE089
in the formula:
Figure 613221DEST_PATH_IMAGE090
a bias matrix is represented that is,
Figure DEST_PATH_IMAGE092
representing a weight matrix, two matrices being used for the feature quantity
Figure DEST_PATH_IMAGE093
And performing output transformation, wherein the corresponding parameters in the matrix represent the contribution degree of the characteristic quantity to an output result.
In addition, in the calculation process of the convolution and the full-connected layer, the fitting degree of the model needs to be reflected by a loss function, and a mean square error function is generally adopted as the loss function to participate in the operation of the convolution neural network, and the mean square error function expression is as follows:
Figure DEST_PATH_IMAGE094
in the formula, the compound is shown in the specification,
Figure DEST_PATH_IMAGE095
is the number of data points in the data set,
Figure DEST_PATH_IMAGE096
for the data points at the actual run-time,
Figure DEST_PATH_IMAGE097
are predicted data points of the dynamic model.
Specifically, a loss function is used in the convolutional layer and the fully-connected layer to optimize the convolutional result and the comprehensive result.
The trained convolutional neural network establishes a complex nonlinear function relationship between the external illumination intensity and temperature change and the output voltage and power change of the photovoltaic power station, and the convolutional neural network model has dynamic operation characteristics for describing the output power and voltage change of the photovoltaic power station when the external conditions change, so that the trained convolutional neural network model is a dynamic model of the photovoltaic power station with the operation characteristics of the photovoltaic power station; the model is used for predicting power, the illumination intensity and temperature change information in a certain time period are input into the model, and the dynamic model outputs predicted values of power and voltage.
According to the method, the operational data of the photovoltaic power station is learned and trained based on the convolutional neural network, the functional relation between the illuminance and the temperature and the voltage and the power of the photovoltaic power station can be obtained, and the functional relation is included in the mechanism after the convolutional neural network is learned and trained, so that the dynamic model becomes a dynamic model with the operational characteristics of the photovoltaic power station, the equivalent output of the photovoltaic power station can be realized under the driving of big data, and meanwhile, the method can be well applied to the prediction of the voltage and the power change of the photovoltaic power station.
The invention also provides a storage device.
A storage device having stored therein a plurality of instructions adapted to be loaded by a processor and to perform the data-driven based photovoltaic power plant dynamic modeling method as described above.
The storage device may be a computer-readable storage medium, and may include: ROM, RAM, magnetic or optical disks, and the like.
The present invention also provides a terminal, which may include:
a processor adapted to implement instructions; and
a storage device adapted to store a plurality of instructions adapted to be loaded by a processor and to perform the photovoltaic plant dynamic modeling method as described above.
The terminal can be any device capable of realizing dynamic modeling of the photovoltaic power station, and the device can be various terminal devices, such as: desktop computers, portable computers, etc., may be implemented in software and/or hardware.
As shown in FIG. 8, the present invention verifies and explains the technical effect of the present invention by establishing a simulation model.
The method comprises the steps of obtaining a corresponding change curve of power and voltage of a grid-connected point of the photovoltaic power station by changing the temperature and illumination intensity of a photovoltaic cell, so as to construct a database for operation of the photovoltaic power station, sampling illumination and temperature change in the database within 6 hours a day, uniformly sampling 10 points, and containing 1200 groups of data in total.
Under the condition that the illuminance is constant, namely the temperature T =25 ℃ and the illuminance Ir = 1000W/square meter, the power and voltage curves of the grid-connected points of the photovoltaic power station are shown in fig. 9:
the power and voltage curves at temperature T =0 ℃, Ir =2000 and 1000 and 200W/square meter change are shown in fig. 10.
The power and voltage curves at temperature T =15 ℃, Ir =200 and 1000-square meter changes are shown in fig. 11.
The dynamic model is used to predict power and voltage, and 200 sets of data are used to verify and analyze prediction accuracy, which is shown in fig. 12 and 13.
In summary, in the photovoltaic power station dynamic model and the modeling method provided by the invention, the output of the photovoltaic power station is reliably predicted by using the dynamic model which is more combined with the actual engineering, so that the overall controllability of the operation of the photovoltaic power station is realized, and the practicability is strong.
In the description of the present invention, it should be understood that the terms "mounted," "connected," "fixed," and the like are used in a broad sense, and for example, may be fixedly connected, detachably connected, or integrated; can be mechanically or electrically connected; they may be directly connected or indirectly connected through intervening media, or they may be connected internally or in any other suitable relationship, unless expressly stated otherwise. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
It will be appreciated that the relevant features of the method, apparatus and system described above are referred to one another. In addition, "first", "second", and the like in the above embodiments are for distinguishing the embodiments, and do not represent merits of the embodiments.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the module described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a device will be apparent from the description above. In addition, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims (5)

1. The photovoltaic power station dynamic modeling method based on data driving is characterized by comprising the following steps: the method comprises the following steps:
s10, establishing a database of the photovoltaic power station in a normal grid-connected operation state based on the operation monitoring information of the photovoltaic power station;
s20, establishing a relational equation of the input variable and the output variable of the photovoltaic power station; the input variables include: ambient light intensity and temperature, the output variables including: the output voltage and power of the grid-connected point when the photovoltaic power station normally operates;
s30, dividing the data in the database into a training set and a test set;
s40, training the convolutional neural network model through a training set, wherein the trained convolutional neural network model has a dynamic model of the operation characteristic of the photovoltaic power station;
s50, inputting the test set into the dynamic model, and predicting voltage and power to obtain a prediction result;
wherein, the database comprises: temperature information, illuminance information, and power change information and voltage change information of the photovoltaic power station;
the expression of the relational equation of the input variables and the output variables is as follows:
Figure 478085DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 988701DEST_PATH_IMAGE002
and
Figure 237279DEST_PATH_IMAGE003
representing the voltage and power of the grid-connected point at time t,
Figure 711117DEST_PATH_IMAGE004
and
Figure 994331DEST_PATH_IMAGE005
representing the outside temperature and the illuminance at the moment t;
Figure 410269DEST_PATH_IMAGE006
representing a non-linear functional relationship based on ambient light illumination and temperature.
2. The data-driven-based photovoltaic power plant dynamic modeling method of claim 1, characterized in that: further comprising:
and S60, verifying the accuracy of the dynamic model based on the test set and the prediction result.
3. The data-driven-based photovoltaic power plant dynamic modeling method of claim 1, characterized in that: training the convolutional neural network model through a training set specifically comprises:
s401, an input layer of the convolutional neural network model receives sample data in a training set;
s402, inputting sample data into a convolution layer of the convolution neural network model;
s403, after normalization processing is carried out on the sample data by the convolution layer of the convolution neural network model, convolution operation is carried out to obtain a convolution result;
s404, carrying out nonlinear processing on the convolution result through an activation function ReLU;
s405, extracting the features in the convolution result after the nonlinear processing, and integrating other features through a full connection layer of the convolution neural network model to form an integrated result;
s406, the output layer of the convolutional neural network model outputs a comprehensive result, wherein the comprehensive result comprises: the power, the voltage amplitude and the voltage phase angle matrix of the grid-connected point of the photovoltaic power station;
wherein: the sample data is as follows: an external illumination intensity and temperature matrix of the photovoltaic power station;
the rows of the external illumination intensity and temperature matrix represent state variables of temperature and illumination intensity in a certain time period, the rows represent different time sampling points, and the columns represent the number of the state variables.
4. The data-driven-based photovoltaic power plant dynamic modeling method of claim 3, characterized in that: and optimizing convolution results and comprehensive results by adopting a loss function in the convolution layer and the full-connection layer.
5. A storage device having a plurality of instructions stored therein, characterized in that: the instructions are adapted to be loaded by a processor and to perform the data-driven-based photovoltaic power plant dynamic modeling method of any of claims 1 to 4.
CN202210080739.2A 2022-01-24 2022-01-24 Photovoltaic power station dynamic modeling method based on data driving and storage device Active CN114123200B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210080739.2A CN114123200B (en) 2022-01-24 2022-01-24 Photovoltaic power station dynamic modeling method based on data driving and storage device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210080739.2A CN114123200B (en) 2022-01-24 2022-01-24 Photovoltaic power station dynamic modeling method based on data driving and storage device

Publications (2)

Publication Number Publication Date
CN114123200A CN114123200A (en) 2022-03-01
CN114123200B true CN114123200B (en) 2022-04-12

Family

ID=80361210

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210080739.2A Active CN114123200B (en) 2022-01-24 2022-01-24 Photovoltaic power station dynamic modeling method based on data driving and storage device

Country Status (1)

Country Link
CN (1) CN114123200B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115809545A (en) * 2022-11-15 2023-03-17 西安电子科技大学 Photovoltaic cell array configuration design method based on omega space solar power station
CN116667369B (en) * 2023-08-01 2023-10-31 国网山西省电力公司晋城供电公司 Distributed photovoltaic voltage control method based on graph convolution neural network
CN116937696B (en) * 2023-09-18 2023-12-05 四川大学 Self-adaptive equivalent modeling method based on photovoltaic power generation system

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2017200360A (en) * 2016-04-28 2017-11-02 清水建設株式会社 Photovoltaic power generation amount prediction system, photovoltaic power generation amount prediction method, and program
CN109934423A (en) * 2019-04-25 2019-06-25 山东大学 Predicting power of photovoltaic plant method and system based on gird-connected inverter operation data
CN112600244A (en) * 2020-12-10 2021-04-02 江苏派尔高智能科技有限公司 Photovoltaic power station voltage control method based on neural network
CN112906987A (en) * 2021-03-29 2021-06-04 福州大学 Photovoltaic power prediction method based on convolutional neural network and two-dimensional meteorological matrix
CN113469427A (en) * 2021-06-24 2021-10-01 国网山东省电力公司东营供电公司 Convolution LSTM-based photovoltaic power station day-ahead power generation amount prediction method and system
CN113705876A (en) * 2021-08-19 2021-11-26 广西电网有限责任公司电力科学研究院 Method and device for constructing photovoltaic power prediction model based on meteorological big data
CN113705887A (en) * 2021-08-27 2021-11-26 浙江工业大学 Data-driven photovoltaic power generation power prediction method and system
CN113962162A (en) * 2021-11-19 2022-01-21 国网重庆市电力公司电力科学研究院 Simulation modeling method for alternating current-direct current hybrid system containing high-proportion new energy

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8942959B2 (en) * 2012-03-29 2015-01-27 Mitsubishi Electric Research Laboratories, Inc. Method for predicting outputs of photovoltaic devices based on two-dimensional fourier analysis and seasonal auto-regression
CN104680424B (en) * 2015-01-30 2018-09-14 国家电网公司 The voltage power situation predictor method in large-sized photovoltaic power station
CN107947244B (en) * 2017-09-12 2021-03-16 国电南瑞科技股份有限公司 New energy power station grid-connected power advanced control method
US20200057175A1 (en) * 2018-08-17 2020-02-20 Nec Laboratories America, Inc. Weather dependent energy output forecasting
CN112541633A (en) * 2020-12-15 2021-03-23 浙江浙能嘉兴发电有限公司 Ultrahigh-precision photovoltaic power generation power prediction method and system based on neural network
CN113642255A (en) * 2021-09-01 2021-11-12 中国人民解放军国防科技大学 Photovoltaic power generation power prediction method based on multi-scale convolution cyclic neural network

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2017200360A (en) * 2016-04-28 2017-11-02 清水建設株式会社 Photovoltaic power generation amount prediction system, photovoltaic power generation amount prediction method, and program
CN109934423A (en) * 2019-04-25 2019-06-25 山东大学 Predicting power of photovoltaic plant method and system based on gird-connected inverter operation data
CN112600244A (en) * 2020-12-10 2021-04-02 江苏派尔高智能科技有限公司 Photovoltaic power station voltage control method based on neural network
CN112906987A (en) * 2021-03-29 2021-06-04 福州大学 Photovoltaic power prediction method based on convolutional neural network and two-dimensional meteorological matrix
CN113469427A (en) * 2021-06-24 2021-10-01 国网山东省电力公司东营供电公司 Convolution LSTM-based photovoltaic power station day-ahead power generation amount prediction method and system
CN113705876A (en) * 2021-08-19 2021-11-26 广西电网有限责任公司电力科学研究院 Method and device for constructing photovoltaic power prediction model based on meteorological big data
CN113705887A (en) * 2021-08-27 2021-11-26 浙江工业大学 Data-driven photovoltaic power generation power prediction method and system
CN113962162A (en) * 2021-11-19 2022-01-21 国网重庆市电力公司电力科学研究院 Simulation modeling method for alternating current-direct current hybrid system containing high-proportion new energy

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
"A New Data Driven Long-Term Solar Yield Analysis Model of Photovoltaic Power Plants";BIPLOB RAY 等;《IEEE POWER & ENERGY SOCIETY SECTION》;20200727;第8卷;第136223-136233页 *
"Accurate modeling of photovoltaic modules using a 1-D deep residual network based on I-V characteristics";Zhicong Chen 等;《Energy Conversion and Management》;20190302(第186期);第168–187页 *
"基于深度学习的高比例分布式光伏配电网电压预测研究";杨镇宁;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20220115;摘要，正文第7-29页第2-3章、第41-57页第5章 *
"基于混合神经网络的光伏组件输出特性数据驱动建模方法";张国宾 等;《智能科学与技术学报》;20200630;第2卷(第2期);第169-178页 *

Also Published As

Publication number Publication date
CN114123200A (en) 2022-03-01

Similar Documents

Publication Publication Date Title
CN114123200B (en) Photovoltaic power station dynamic modeling method based on data driving and storage device
Yilmaz et al. Improved MPPT method to increase accuracy and speed in photovoltaic systems under variable atmospheric conditions
Thangamuthu et al. Design and development of extract maximum power from single-double diode PV model for different environmental condition using BAT optimization algorithm
Boumaaraf et al. A three-phase NPC grid-connected inverter for photovoltaic applications using neural network MPPT
Soon et al. A fast-converging MPPT technique for photovoltaic system under fast-varying solar irradiation and load resistance
OLiveira da Silva et al. Feed‐forward DC‐bus control loop applied to a single‐phase grid‐connected PV system operating with PSO‐based MPPT technique and active power‐line conditioning
Ibrahim et al. Optimizing step-size of perturb & observe and incremental conductance MPPT techniques using PSO for grid-tied PV system
Purba et al. Dynamic aggregation of grid-tied three-phase inverters
CN110556871B (en) Aggregation equivalence method for large-scale photovoltaic power generation system based on structure keeping method
Shukl et al. Recursive digital filter based control for power quality improvement of grid tied solar PV system
Riquelme-Dominguez et al. Systematic evaluation of photovoltaic MPPT algorithms using state-space models under different dynamic test procedures
said Adouairi et al. Application of fuzzy sliding mode control on a single-stage grid-connected PV system based on the voltage-oriented control strategy
CN109830987B (en) Active power distribution network probability stability analysis method considering distributed photovoltaic randomness
Dagal et al. A novel hybrid series salp particle Swarm optimization (SSPSO) for standalone battery charging applications
Wu et al. Equivalent modeling of photovoltaic power station based on canopy-FCM clustering algorithm
Yahiaoui et al. An experimental testing of optimized fuzzy logic-based MPPT for a standalone PV system using genetic algorithms
Saraswathi et al. An artificial neural network-based comprehensive solar photovoltaic emulator
Çelik et al. Analytical investigation of PV panel operated at maximum power point on DC microgrid
Kelesidis et al. Investigation of a control scheme based on modified pq theory for single phase single stage grid connected PV system
Cho et al. A variable step size incremental conductance MPPT of a photovoltaic system using DC-DC converter with direct control scheme
Assia et al. Detailed modeling of two diode photovoltaic module using MATLAB simulik
Debnath et al. Step-size optimization of new straight line approximation-based mppt algorithm for photovoltaic systems
Liu et al. Equivalent modeling of distributed photovoltaic power station clusters based on deep belief network
Cuzco et al. Comparative analysis of the performance of maximum power point tracking algorithms in photovoltaic systems
CN113138620A (en) Photovoltaic maximum power point tracking method and system based on hybrid BSO-FLC

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant