CN112818592A - Photovoltaic cell parameter and power generation capacity prediction method and system based on data mining - Google Patents

Photovoltaic cell parameter and power generation capacity prediction method and system based on data mining Download PDF

Info

Publication number
CN112818592A
CN112818592A CN202110088612.0A CN202110088612A CN112818592A CN 112818592 A CN112818592 A CN 112818592A CN 202110088612 A CN202110088612 A CN 202110088612A CN 112818592 A CN112818592 A CN 112818592A
Authority
CN
China
Prior art keywords
photovoltaic
power generation
photovoltaic cell
parameters
data
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.)
Pending
Application number
CN202110088612.0A
Other languages
Chinese (zh)
Inventor
吴艳娟
王云亮
韩小明
刘爽
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.)
Tianjin University of Technology
Original Assignee
Tianjin University of Technology
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 Tianjin University of Technology filed Critical Tianjin University of Technology
Priority to CN202110088612.0A priority Critical patent/CN112818592A/en
Publication of CN112818592A publication Critical patent/CN112818592A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • 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
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Artificial Intelligence (AREA)
  • Medical Informatics (AREA)
  • Health & Medical Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computer Hardware Design (AREA)
  • Public Health (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Geometry (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The invention provides a photovoltaic cell parameter and generating capacity prediction method and system based on data mining, which relate to the technical field of photovoltaic power generation and comprise the following steps: acquiring photovoltaic parameters, wherein the photovoltaic parameters comprise actual operation physical quantity, operation environment parameters and operation duration of the photovoltaic cell; sending a data information processing instruction to enable the photovoltaic parameters to establish an access database; sending an information preprocessing instruction to preprocess the access database to obtain a photovoltaic data sample library; and constructing a photovoltaic power generation model, estimating parameters of the photovoltaic cell by using a photovoltaic data sample library, and predicting the electric quantity through a generated energy prediction system. The method and the system provided by the invention can be used for accurately calculating and predicting the photovoltaic power generation amount, and have important significance for promoting the practical engineering application of a photovoltaic power generation prediction system, accelerating the photovoltaic network access process, saving energy, improving the solar energy utilization rate, improving the operation stability of a power grid and the like.

Description

Photovoltaic cell parameter and power generation capacity prediction method and system based on data mining
Technical Field
The invention relates to the technical field of power generation system monitoring, in particular to a photovoltaic cell parameter and power generation amount calculation and prediction method and system based on data mining.
Background
With the increasing exhaustion of fossil energy on the earth, new energy power generation has a greater and greater proportion in the energy field, and solar power generation as a clean and sustainable new energy is one of the most important new energy power generation forms and occupies an increasingly important position in the energy field. With the increasing maturity of the photovoltaic power generation grid-connected technology and the increasing proportion of the generated energy occupied by the photovoltaic power generation grid-connected technology in the power grid, the accurate calculation and prediction of the photovoltaic generated energy become key technologies for further saving energy and improving the safe reliability of the power grid operation. The method has important significance for characteristic research of the solar cell, digital simulation modeling and optimization design of the photovoltaic power generation system, power grid planning including photovoltaic power generation, power grid dispatching, electricity price accounting and the like. Considering that the photovoltaic cell mostly adopts semiconductor materials such as silicon and germanium, and is very sensitive to temperature and illumination intensity, the output electric quantity of the photovoltaic cell can change along with environmental parameters and the use corrosion condition of a photovoltaic cell panel, and if the standard parameters when leaving the factory are adopted all the time or a method for scaling the standard parameters according to a certain proportional relation can influence the accurate calculation and prediction of the output power of the photovoltaic cell. Therefore, the following five main problems need to be solved in order to accurately calculate and predict the photovoltaic power generation amount: (1) the accuracy and the real-time performance of the collection of the actual operation physical quantity and the operation environment parameters of the photovoltaic power generation are improved; (2) the accuracy of the photovoltaic cell real-time mathematical simulation calculation model is established; (3) the accuracy of the nonlinear parameter identification of the photovoltaic cell simulation mathematical model is improved; (4) the accuracy of the photovoltaic cell simulation calculation method; (5) error checking of the calculation result and the actual operation result; (6) and the output generating capacity of the photovoltaic cell is predicted accurately.
Disclosure of Invention
In view of the above, the present invention aims to provide a photovoltaic cell parameter and power generation amount prediction method and system based on data mining, so as to accurately calculate and predict the output power of a photovoltaic cell, and have important meanings for promoting the practical engineering application of a photovoltaic power generation prediction system, accelerating the photovoltaic network access process, saving energy, improving the solar energy utilization rate, improving the power grid operation stability, and the like, and also provide a beneficial reference function for other new energy power generation related technologies.
In a first aspect, an embodiment of the present invention provides a photovoltaic cell parameter and power generation amount prediction method based on data mining, including:
acquiring the photovoltaic parameters, wherein the photovoltaic parameters comprise actual operation physical quantity of the photovoltaic cell, operation environment parameters and operation duration of the photovoltaic cell;
sending a data information processing instruction to enable the photovoltaic parameters to establish an access database;
sending an information preprocessing instruction to preprocess the access database to obtain a photovoltaic data sample library;
and constructing a photovoltaic power generation model, estimating photovoltaic cell parameters by using the photovoltaic data sample library, and predicting the power generation through a power generation prediction system.
Preferably, the step of sending information preprocessing instructions to preprocess the access database to obtain the photovoltaic data sample library includes:
and carrying out normalization processing on the photovoltaic parameters so as to carry out data filtration, data supplementation and data fusion on the photovoltaic parameters and establish a database.
Preferably, the step of constructing a photovoltaic power generation model, estimating photovoltaic cell parameters by using the photovoltaic data sample library, and predicting a power generation amount prediction system includes:
modeling a photovoltaic cell single diode equivalent model by adopting the following formula:
Figure BDA0002911890380000021
i-output current;
u-output voltage;
Iph-generating an electrical current;
io-diode reverse saturation current;
Rs-a series resistance;
Rsh-a parallel resistance;
q-electronic charge (1.6X 10-9C);
a-diode factor;
K-Boltzmann constant (1.38X 10-23J/K);
t-current ambient Fahrenheit absolute temperature;
modeling a photovoltaic cell double-diode equivalent model by adopting the following formula:
Figure BDA0002911890380000031
the BOOST converter is modeled using the following equation:
Figure BDA0002911890380000032
Figure BDA0002911890380000033
Pi＝P0；
Ui-an input voltage;
Uo-an output voltage;
Ii-an input current;
Io-an input current;
d is the duty cycle;
Piand PoInput power and output power, respectively;
furthermore, in the embodiment provided by the present invention, the maximum power tracking is used for modeling, but the present invention is not limited to indirect control methods (constant voltage tracking, open-circuit voltage proportionality coefficient, short-circuit current proportionality coefficient method, curve fitting method and table look-up method), direct control methods (disturbance observation method, conductance increment method and parasitic capacitance method) and artificial intelligence control methods (fuzzy logic control valve and artificial neural network method);
the accuracy of the photovoltaic cell nonlinear parameter identification determines the accuracy of a photovoltaic cell simulation model, the photovoltaic cell nonlinear parameter identification method currently adopts an analytic method, a simplified method, a heuristic method, an artificial intelligence method and a hybrid algorithm, and the number of photovoltaic cell nonlinear parameters is considered to be greatly increased along with the increase of the number of medium-value diodes in a photovoltaic cell equivalent model, the number of equation equations which can be obtained is less than the number of parameters, and moreover, the difference among the parameters is large, so that the accurate parameter solution is difficult to obtain by adopting a single analytic method. The invention provides a nonlinear parameter grouping and mixing analysis method with actual power verification based on the technology of the Internet of things, which is used for accurately identifying nonlinear parameters of a photovoltaic cell in real time and specifically comprises the following steps:
the photovoltaic cell single-diode equivalent model and the double-diode equivalent model meet the following constraint conditions:
f1(U＝Uoc,I＝0)＝0；
f2(U＝0,I＝Isc)＝0；
f3(I＝Im,U＝Um)＝0；
Figure BDA0002911890380000041
Figure BDA0002911890380000042
Uoc-photovoltaic cell open circuit voltage;
Isc-short circuit current of the photovoltaic cell;
Um-output voltage at maximum output power of the photovoltaic cell;
Im-output current at maximum output power of the photovoltaic cell.
Preferably, in the step of constructing the photovoltaic power generation model, estimating the photovoltaic cell parameters by using the photovoltaic data sample library, and predicting the power generation amount by using the power generation amount prediction system, a vector machine is used to predict the power generation amount: (ii) a
For a single diode model, there are 5 nonlinear unknown parameters (photo-generated current I)phDiode reverse current IoDiode factor A, series resistance RsParallel resistor Rsh) An accurate solution of 5 parameters can be obtained by solving the above 5 equations, but since Rsh is much different from other parameters and the parameter R issIn the power term of the index, the solving difficulty is very high, the requirement on the initial value of the parameter is very high when the iterative method is adopted for solving, and a convergence solution is difficult to obtain if the initial value is improperly selected. And the unknown number of the double-diode model is 7 (I)ph,Io1,A1,Io2,A2,Rs,Rsh) The above 5 equations can not be used to obtain a unique solution;
in order to improve the solving precision of the photovoltaic cell parameters, the invention provides an example of a grouping analysis solving method, and the method is explained as follows:
(1) grouping and alternately solving the parameter groups into an inner ring group and an outer ring group, substituting the parameters of the outer ring group as known quantities when the parameters of the inner ring group are solved, substituting the parameters of the inner ring group as known quantities in the solving process of the outer ring group, and simultaneously iterating, so that the problem that an unknown number is more than an equation number and a unique solution cannot be obtained can be solved, and the problem that a convergence solution cannot be obtained by an iteration method with large parameter difference is also solved;
(2) in order to ensure the accuracy of the solution, the parameters of the inner ring group are solved by adopting an accurate analysis method, and the initial values of the parameters are obtained by adopting a simplified analysis solving method; and solving the outer ring group parameters by adopting a gradient method, and taking the minimum difference value of the actual operating power and the calculated power as an objective function of the outer ring group parameter solution. Because the minimum deviation between the actual operating power and the calculated value is adopted as the objective function in the outer ring group, compared with the existing method, the method has higher accuracy and is closer to the practical engineering application.
The prediction model function based on the linear optimal decision is shown as follows:
f(x)＝wφ(x)+b
where φ (x) represents a characteristic attribute of the input data; w and b represent the weight vector and the bias value, respectively, and are coefficients estimated when the risk function is minimum. The risk function is given by the following formula
Figure BDA0002911890380000061
Wherein | | w | | non-conducting phosphor2Expressing the model complexity, gamma is a normalized parameter used for balancing the empirical risk Re and the model complexity, and in order to obtain the empirical risk, the following loss function is introduced:
L[x,y,f(x)]＝|y-f(x)|ε＝max[0,|y-f(x)|-ε]
where ε represents the accuracy and the empirical risk Re is formulated as follows:
Figure BDA0002911890380000062
in another aspect, the present invention provides a photovoltaic cell parameter and power generation amount prediction system based on data mining, preferably, including:
an information acquisition module: the photovoltaic parameters are used for acquiring the photovoltaic parameters, and the photovoltaic parameters comprise actual operation physical quantity of the photovoltaic cell, operation environment parameters and operation duration of the photovoltaic cell;
a database establishment module: the photovoltaic parameter management system is used for sending data information processing instructions to enable the photovoltaic parameters to establish an access database;
a sample library establishing module: the system comprises a data storage module, a data processing module and a data processing module, wherein the data storage module is used for storing an access database;
building a photovoltaic power generation model: and the photovoltaic cell parameter estimation system is used for estimating photovoltaic cell parameters by utilizing the photovoltaic data sample library and predicting the power generation capacity prediction system.
The embodiment of the invention has the following beneficial effects: the invention provides a photovoltaic cell parameter and power generation amount prediction method and system based on data mining, which comprises the following steps: acquiring photovoltaic parameters, wherein the photovoltaic parameters comprise actual operation physical quantity, operation environment parameters and operation duration of the photovoltaic cell; sending a data information processing instruction to enable the photovoltaic parameters to establish an access database; sending an information preprocessing instruction to preprocess the access database to obtain a photovoltaic data sample library; and (3) constructing a photovoltaic power generation model, estimating photovoltaic cell parameters by using a photovoltaic data sample library, and predicting a power generation amount prediction system. The method and the system provided by the invention can accurately predict the photovoltaic power generation amount, and have important significance for promoting the practical engineering application of a photovoltaic power generation prediction system, accelerating the photovoltaic network access process, saving energy, improving the solar energy utilization rate, improving the operation stability of a power grid and the like.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a photovoltaic cell parameter and power generation amount prediction method based on data mining according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a circuit for collecting illumination intensity or temperature according to a photovoltaic cell parameter and power generation amount prediction method based on data mining according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a humidity acquisition circuit provided by a photovoltaic cell parameter and power generation amount prediction method based on data mining according to an embodiment of the present invention;
fig. 4 is a schematic diagram of light ray inclination acquisition provided by a photovoltaic cell parameter and power generation amount prediction method based on data mining according to an embodiment of the present invention;
fig. 5 is an equivalent circuit diagram of a single-diode photovoltaic cell provided by a photovoltaic cell parameter and power generation amount prediction method based on data mining according to an embodiment of the present invention;
fig. 6 is an equivalent circuit diagram of a dual-diode photovoltaic cell provided by a photovoltaic cell parameter and power generation amount prediction method based on data mining according to an embodiment of the present invention;
fig. 7 is an equivalent circuit diagram of a multi-diode photovoltaic cell provided by a photovoltaic cell parameter and power generation amount prediction method based on data mining according to an embodiment of the present invention;
fig. 8 is a multi-cell equivalent circuit diagram provided by a photovoltaic cell parameter and power generation amount prediction method based on data mining according to an embodiment of the present invention;
fig. 9 is a schematic diagram of a photovoltaic power generation BOOST circuit provided by a photovoltaic cell parameter and power generation amount prediction method based on data mining according to an embodiment of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, 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.
At present, the following six main problems need to be solved for accurately calculating and predicting the photovoltaic power generation capacity: (1) the accuracy and the real-time performance of the collection of the actual operation physical quantity and the operation environment parameters of the photovoltaic power generation are improved; (2) the accuracy of the photovoltaic cell real-time mathematical simulation calculation model is established; (3) the accuracy of the nonlinear parameter identification of the photovoltaic cell simulation mathematical model is improved; (4) the accuracy of the photovoltaic cell simulation calculation method; (5) error checking of the calculation result and the actual operation result; (6) based on the accuracy of the photovoltaic cell output power generation prediction, the photovoltaic cell parameter and power generation amount prediction method and system based on data mining provided by the embodiment of the invention can accurately calculate and predict the output power of the photovoltaic cell, have important meanings for promoting the practical engineering application of a photovoltaic power generation prediction system, accelerating the photovoltaic network access process, saving energy, improving the solar energy utilization rate, improving the power grid operation stability and the like, and also provide beneficial reference functions for other new energy power generation related technologies.
In order to facilitate understanding of the embodiment, a method for predicting photovoltaic cell parameters and power generation based on data mining disclosed in the embodiment of the invention is first described in detail.
The first embodiment is as follows:
with reference to fig. 1 to 9, an embodiment of the present invention provides a photovoltaic cell parameter and power generation amount prediction method based on data mining, including:
acquiring the photovoltaic parameters, wherein the photovoltaic parameters comprise actual operation physical quantity of the photovoltaic cell, operation environment parameters and operation duration of the photovoltaic cell;
the data samples in the present invention include: the photovoltaic power generation system comprises photovoltaic power generation actual operation physical quantities (voltage, current and actual output power), operation environment parameters (temperature, illumination intensity, humidity, light inclination and shading degree), photovoltaic cell operation duration, a nonlinear parameter real-time calculation value and a simulation operation maximum output power value of the photovoltaic cell in an actual operation environment and the like;
sending a data information processing instruction to enable the photovoltaic parameters to establish an access database;
sending an information preprocessing instruction to preprocess the access database to obtain a photovoltaic data sample library;
and constructing a photovoltaic power generation model, estimating photovoltaic cell parameters by using the photovoltaic data sample library, and predicting a power generation amount prediction system.
Preferably, the step of sending information preprocessing instructions to preprocess the access database to obtain the photovoltaic data sample library includes:
and carrying out normalization processing on the photovoltaic parameters so as to carry out data filtration, data supplementation and data fusion on the photovoltaic parameters and establish a database.
Preferably, the step of constructing a photovoltaic power generation model, estimating photovoltaic cell parameters by using the photovoltaic data sample library, and predicting a power generation amount prediction system includes:
modeling a photovoltaic cell single diode equivalent model by adopting the following formula:
Figure BDA0002911890380000091
i-output current;
u-output voltage;
Iph-generating an electrical current;
io-diode reverse saturation current;
Rs-a series resistance;
Rsh-a parallel resistance;
q-electronic charge (1.6X 10)-9C)；
A-diode factor;
K-Boltzmann constant (1.38X 10-23J/K);
t-current ambient Fahrenheit absolute temperature;
modeling a photovoltaic cell single diode equivalent model by adopting the following formula:
Figure BDA0002911890380000101
the BOOST converter is modeled using the following equation:
Figure BDA0002911890380000102
Figure BDA0002911890380000103
Pi＝P0；
Ui-an input voltage;
Uo-an output voltage;
Ii-an input current;
Io-an input current;
d is the duty cycle;
Piand PoInput power and output power, respectively;
the single diode model and the double diode model satisfy the following constraint conditions:
f1(U＝Uoc,I＝0)＝0；
f2(U＝0,I＝Isc)＝0；
f3(I＝Im,U＝Um)＝0；
Figure BDA0002911890380000111
Figure BDA0002911890380000112
Uoc-photovoltaic cell open circuit voltage;
Isc-short circuit current of the photovoltaic cell;
Um-output voltage at maximum output power of the photovoltaic cell;
Im-output current at maximum output power of the photovoltaic cell.
It should be noted that there are many methods for establishing the prediction model, such as ARIMA model, gray prediction model, polynomial fitting model, etc., and the methods can be used to establish the prediction model of the photovoltaic power generation nonlinear parameter and the photovoltaic power generation amount without being limited to these methods.
Preferably, in the step of constructing a photovoltaic power generation model, estimating photovoltaic cell parameters by using the photovoltaic data sample library, and predicting the power generation amount prediction system, a vector machine is used to predict the power generation amount:
the prediction model function based on the linear optimal decision is shown as follows:
f(x)＝wφ(x)+b
where φ (x) represents a characteristic attribute of the input data; w and b represent the weight vector and the bias value, respectively, and are coefficients estimated when the risk function is minimum. The risk function is given by the following formula
Figure BDA0002911890380000113
Wherein | | w | | non-conducting phosphor2Expressing the model complexity, gamma is a normalized parameter used for balancing the empirical risk Re and the model complexity, and in order to obtain the empirical risk, the following loss function is introduced:
L[x,y,f(x)]＝|y-f(x)|ε＝max[0,|y-f(x)|-ε]
where ε represents the accuracy and the empirical risk Re is formulated as follows:
Figure BDA0002911890380000121
it should be noted that, in order to ensure the accuracy of the established photovoltaic power generation nonlinear parameter and photovoltaic power generation amount prediction model, the model needs to be evaluated, and the evaluation method includes a confusion matrix, an operation characteristic curve, a statistical test, and the like, and the confusion matrix is taken as an example and is described as follows:
the accuracy is as follows: the ratio between the number of correct prediction samples and the total number of samples.
Figure BDA0002911890380000122
The precision ratio is as follows: the ratio of the number of true positive samples to the number of true positive samples plus the number of false positive samples.
Figure BDA0002911890380000123
The recall ratio is as follows: is the ratio between the number of true positive samples and the number of true positive samples plus the number of false negative samples.
Figure BDA0002911890380000124
F1-fraction: harmonic averaging of precision and recall.
Figure BDA0002911890380000125
Wherein, when the true value is true, the predicted value is also true, and the result is marked as TP (true positive); the true value is true, but the predicted value is false, and is marked as FN (false negative); the true value is false, but the predicted value is true, and is marked as FP (false positive); true values are false, predicted values are also false, and are designated as TN (true negatives).
Example two:
the embodiment of the invention provides a photovoltaic cell parameter and power generation capacity prediction system based on data mining, which comprises:
an information acquisition module: the photovoltaic parameters are used for acquiring the photovoltaic parameters, and the photovoltaic parameters comprise actual operation physical quantity of the photovoltaic cell, operation environment parameters and operation duration of the photovoltaic cell;
a database establishment module: the photovoltaic parameter management system is used for sending data information processing instructions to enable the photovoltaic parameters to establish an access database;
a sample library establishing module: the system comprises a data storage module, a data processing module and a data processing module, wherein the data storage module is used for storing an access database;
building a photovoltaic power generation model: and the photovoltaic cell parameter estimation system is used for estimating photovoltaic cell parameters by utilizing the photovoltaic data sample library and predicting the power generation through a power generation prediction system.
The invention has the following technical effects:
(1) according to the method, the influence of the change of the environmental parameters of the photovoltaic cell is considered by adopting the technology of the Internet of things, the influence of corrosion caused by service duration of the photovoltaic cell on the photovoltaic power generation performance is also considered, and the real-time performance and the accuracy of prediction are further improved.
(2) According to the method, actual engineering operation data are collected through the Internet of things technology, the actual engineering operation data are used as parameters and check standards, photovoltaic cell parameters and power generation amount are calculated in real time, accuracy of photovoltaic power generation simulation operation modeling is improved, the adopted calculation method is a real-time grouping analysis calculation method, and checking is carried out through actual operation power, so that reliability and stability of analysis of a grid-connected photovoltaic power grid can be improved, accuracy of grid dispatching is improved, energy is saved, and energy waste is prevented.
(3) The photovoltaic power generation prediction model provided by the invention takes actual engineering operation data and calculation data verified by actual operation power as training samples of the model, and the accuracy of the prediction model is higher.
Unless specifically stated otherwise, the relative steps, numerical expressions, and values of the components and steps set forth in these embodiments do not limit the scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In addition, in the description of the embodiments of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (5)

1. A photovoltaic cell parameter and power generation capacity prediction method based on data mining is characterized by comprising the following steps:
acquiring the photovoltaic parameters, wherein the photovoltaic parameters comprise actual operation physical quantity of the photovoltaic cell, operation environment parameters and operation duration of the photovoltaic cell;
sending a data information processing instruction to enable the photovoltaic parameters to establish an access database;
sending an information preprocessing instruction to preprocess the access database to obtain a photovoltaic data sample library;
and constructing a photovoltaic power generation model, estimating photovoltaic cell parameters by using the photovoltaic data sample library, and predicting the power generation through a power generation prediction system.
2. The method of claim 1, wherein the step of sending information preprocessing instructions to preprocess the access database to obtain a photovoltaic data sample library comprises:
and carrying out normalization processing on the photovoltaic parameters so as to carry out data filtration, data supplementation and data fusion on the photovoltaic parameters and establish a database.
3. The method of claim 1, wherein the steps of constructing a photovoltaic power generation model, estimating photovoltaic cell parameters using the photovoltaic data sample library, and predicting a power generation prediction system comprise:
modeling a single-diode equivalent model of the photovoltaic cell by adopting the following formula:
Figure FDA0002911890370000011
i-output current;
u-output voltage;
Iph-generating an electrical current;
io-diode reverse saturation current;
Rs-a series resistance;
Rsh-a parallel resistance;
q-electronic charge (1.6X 10-9C);
a-diode factor;
K-Boltzmann constant (1.38X 10-23J/K);
t-current ambient Fahrenheit absolute temperature;
modeling a photovoltaic cell double-diode equivalent model by adopting the following formula:
Figure FDA0002911890370000021
the BOOST converter is modeled using the following equation:
Figure FDA0002911890370000022
Figure FDA0002911890370000023
Pi＝P0；
Ui-an input voltage;
Uo-an output voltage;
Ii-an input current;
Io-an input current;
d is the duty cycle;
Piand PoInput power and output power, respectively;
the photovoltaic cell single-diode equivalent model and the double-diode equivalent model meet the following constraint conditions:
f1(U＝Uoc,I＝0)＝0；
f2(U＝0,I＝Isc)＝0；
f3(I＝Im,U＝Um)＝0；
Figure FDA0002911890370000031
Figure FDA0002911890370000032
Uoc-photovoltaic cell open circuit voltage;
Isc-short circuit current of the photovoltaic cell;
Um-output voltage at maximum output power of the photovoltaic cell;
Im-output current at maximum output power of the photovoltaic cell.
4. The method according to claim 1, wherein in the step of constructing a photovoltaic power generation model, estimating photovoltaic cell parameters by using the photovoltaic data sample library, and predicting power generation amount by a power generation amount prediction system, a vector machine is used to predict power generation amount:
the prediction model function based on the linear optimal decision is shown as follows:
f(x)＝wφ(x)+b
where φ (x) represents a characteristic attribute of the input data; w and b represent the weight vector and the bias value, respectively, and are coefficients estimated when the risk function is minimum. The risk function is given by the following formula
Figure FDA0002911890370000033
Wherein | | w | | non-conducting phosphor2Expressing the model complexity, gamma is a normalized parameter used for balancing the empirical risk Re and the model complexity, and in order to obtain the empirical risk, the following loss function is introduced:
L[x,y,f(x)]＝|y-f(x)|ε＝max[0,|y-f(x)|-ε]
where ε represents the accuracy and the empirical risk Re is formulated as follows:
Figure FDA0002911890370000041
5. a photovoltaic cell parameter and power generation capacity prediction system based on data mining is characterized by comprising:
an information acquisition module: the photovoltaic parameters are used for acquiring the photovoltaic parameters, and the photovoltaic parameters comprise actual operation physical quantity of the photovoltaic cell, operation environment parameters and operation duration of the photovoltaic cell;
a database establishment module: the photovoltaic parameter management system is used for sending data information processing instructions to enable the photovoltaic parameters to establish an access database;
a sample library establishing module: the system comprises a data storage module, a data processing module and a data processing module, wherein the data storage module is used for storing an access database;
building a photovoltaic power generation model: and the photovoltaic cell parameter estimation system is used for estimating photovoltaic cell parameters by utilizing the photovoltaic data sample library and predicting the power generation capacity prediction system.
CN202110088612.0A 2021-01-22 2021-01-22 Photovoltaic cell parameter and power generation capacity prediction method and system based on data mining Pending CN112818592A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110088612.0A CN112818592A (en) 2021-01-22 2021-01-22 Photovoltaic cell parameter and power generation capacity prediction method and system based on data mining

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110088612.0A CN112818592A (en) 2021-01-22 2021-01-22 Photovoltaic cell parameter and power generation capacity prediction method and system based on data mining

Publications (1)

Publication Number Publication Date
CN112818592A true CN112818592A (en) 2021-05-18

Family

ID=75858820

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110088612.0A Pending CN112818592A (en) 2021-01-22 2021-01-22 Photovoltaic cell parameter and power generation capacity prediction method and system based on data mining

Country Status (1)

Country Link
CN (1) CN112818592A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI781872B (en) * 2022-01-18 2022-10-21 崑山科技大學 Method for predicting solar power generation with shading effect

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107341319A (en) * 2017-07-24 2017-11-10 山东大学 A kind of method that solar cell physical parameter is solved using mathematics dominant models
US20180046924A1 (en) * 2015-08-31 2018-02-15 Guangzhou Institute Of Energy Conversion, Chinese Academy Of Sciences Whole-life-cycle power output classification prediction system for photovoltaic systems
CN109120003A (en) * 2018-09-07 2019-01-01 中国南方电网有限责任公司 Distributed photovoltaic energy storage system optimization control method based on MPC algorithm
CN109347434A (en) * 2018-11-06 2019-02-15 王浩 A kind of method of photovoltaic generation power when meter and aging
CN110009098A (en) * 2019-04-19 2019-07-12 上海交通大学 A kind of photovoltaic cell operating temperature and generated output combined estimation method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180046924A1 (en) * 2015-08-31 2018-02-15 Guangzhou Institute Of Energy Conversion, Chinese Academy Of Sciences Whole-life-cycle power output classification prediction system for photovoltaic systems
CN107341319A (en) * 2017-07-24 2017-11-10 山东大学 A kind of method that solar cell physical parameter is solved using mathematics dominant models
CN109120003A (en) * 2018-09-07 2019-01-01 中国南方电网有限责任公司 Distributed photovoltaic energy storage system optimization control method based on MPC algorithm
CN109347434A (en) * 2018-11-06 2019-02-15 王浩 A kind of method of photovoltaic generation power when meter and aging
CN110009098A (en) * 2019-04-19 2019-07-12 上海交通大学 A kind of photovoltaic cell operating temperature and generated output combined estimation method

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
杨立成: "基于最小二乘支持向量机的短期电力负荷预测方法研究", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 *
苏虎成: "分布式发电仿真", 《万方数据知识服务平台》 *
陈海斌: "改进MPPT功能型三相光伏并网系统研究", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI781872B (en) * 2022-01-18 2022-10-21 崑山科技大學 Method for predicting solar power generation with shading effect

Similar Documents

Publication Publication Date Title
Boulmrharj et al. Online battery state-of-charge estimation methods in micro-grid systems
CN106532688B (en) It is a kind of for assessing the method and system of micro-capacitance sensor operational reliability
CN113064093A (en) Energy storage battery state of charge and state of health joint estimation method and system
Pei et al. An Equivalent Circuit Model for Lithium Battery of Electric Vehicle considering Self‐Healing Characteristic
Wang et al. Health diagnosis for lithium-ion battery by combining partial incremental capacity and deep belief network during insufficient discharge profile
Binelo et al. Mathematical modeling and parameter estimation of battery lifetime using a combined electrical model and a genetic algorithm
CN117878979B (en) Power balance and dynamic compensation system based on electric energy storage
CN112949207A (en) Short-term load prediction method based on improved least square support vector machine
CN110968703B (en) Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm
Lv et al. Short-term power load forecasting based on balanced KNN
CN115270640A (en) Configuration optimization method for distributed photovoltaic power generation system of microgrid and terminal equipment
Alharbi et al. Short-term wind speed and temperature forecasting model based on gated recurrent unit neural networks
CN113093014B (en) Online collaborative estimation method and system for SOH and SOC based on impedance parameters
CN112818592A (en) Photovoltaic cell parameter and power generation capacity prediction method and system based on data mining
CN112446175A (en) Distributed power supply site selection optimization method based on power distribution network probability load flow calculation
CN111814399A (en) Model parameter optimization extraction method and measurement data prediction method for solar photovoltaic cell system
CN115329487A (en) Parameter setting method for photovoltaic power generation system and terminal equipment
CN115267586A (en) Lithium battery SOH evaluation method
Huang et al. Long-Term Health State Estimation of Energy Storage Lithium-Ion Battery Packs
Uddin et al. State of health estimation of lithium-ion batteries in vehicle-to-grid applications using recurrent neural networks for learning the impact of degradation stress factors
Cho et al. Application of Parallel ANN-PSO to Hourly Solar PV Estimation
Basia et al. Comparison of data driven algorithms for SoH estimation of Lithium-ion batteries
CN117610314B (en) Photovoltaic module modeling method, device, equipment and storage medium
CN118011223B (en) Fault diagnosis method and system for electric power energy storage system
Jha et al. Advancing State of Charge Estimation for LTO Battery Storage: Experimental Data-Based Techniques for Digital Twin Development

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