CN117540859A - Method and system for estimating generated energy of photovoltaic power station based on neural network - Google Patents
Method and system for estimating generated energy of photovoltaic power station based on neural network Download PDFInfo
- Publication number
- CN117540859A CN117540859A CN202311519348.7A CN202311519348A CN117540859A CN 117540859 A CN117540859 A CN 117540859A CN 202311519348 A CN202311519348 A CN 202311519348A CN 117540859 A CN117540859 A CN 117540859A
- Authority
- CN
- China
- Prior art keywords
- photovoltaic
- power generation
- data
- power station
- module
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 25
- 238000010248 power generation Methods 0.000 claims abstract description 73
- 238000012937 correction Methods 0.000 claims abstract description 21
- 230000000875 corresponding effect Effects 0.000 claims description 15
- 238000003062 neural network model Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000005315 distribution function Methods 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 11
- 230000001186 cumulative effect Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 230000002596 correlated effect Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000010219 correlation analysis Methods 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 4
- BTCSSZJGUNDROE-UHFFFAOYSA-N gamma-aminobutyric acid Chemical compound NCCCC(O)=O BTCSSZJGUNDROE-UHFFFAOYSA-N 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 6
- 238000012360 testing method Methods 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 229910052710 silicon Inorganic materials 0.000 description 1
- 239000010703 silicon Substances 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Classifications
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0499—Feedforward networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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
-
- 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
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Power Engineering (AREA)
- Water Supply & Treatment (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Photovoltaic Devices (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a method and a system for predicting the generated energy of a photovoltaic power station based on a neural network, and relates to the technical field of prediction of the generated energy of the photovoltaic power station. The method comprises the steps of collecting operation parameter data of a photovoltaic module in a photovoltaic power station, comprehensively considering the operation state of the photovoltaic power station when the photovoltaic module fails, constructing a Weibull distribution model of the service life of the photovoltaic module in the use process, predicting the failure probability of the photovoltaic module in the use process in an future time interval through the model, collecting historical data of the photovoltaic power station as input to construct a prediction model, outputting a power generation quantity predicted value of the photovoltaic module of the photovoltaic power station in the time interval through the prediction model, calculating a total power generation quantity correction value according to the predicted result of the failure probability of the photovoltaic module and the total power generation quantity predicted value, and taking the power generation quantity predicted expected value as a final output power generation quantity predicted result, so that the method is more in line with the actual operation situation of the photovoltaic power station, and improving the accuracy of the predicted result.
Description
Technical Field
The invention relates to the technical field of photovoltaic power station generating capacity prediction, in particular to a method and a system for predicting the photovoltaic power station generating capacity based on a neural network.
Background
The photovoltaic power station is a power generation system which utilizes solar energy and is composed of electronic elements such as a crystal silicon plate, an inverter and the like made of special materials, and is connected with a power grid and used for transmitting power to the power grid. In recent years, with the shortage of fossil energy and the increasing severity of environmental problems, the scale of clean energy power generation is rapidly expanding. Photovoltaic power generation has become one of the most important renewable energy power generation modes due to the advantages of clean, economical and sustainable development.
At present, photovoltaic power generation amount prediction in the prior art is mostly realized through methods such as intelligent algorithm, deep learning and the like, the method trains a photovoltaic power generation power model by using a large number of historical samples, and then predicts the power generation amount by using a trained model.
However, the input of the existing deep learning algorithm prediction model is mostly environmental factor variable data influencing the generated energy, such as historical data of weather conditions, radiation quantity, temperature and humidity, dust collection quantity and the like, the problems of the operation efficiency and reliability of the photovoltaic module equipment are not considered, and along with the increase of the operation time of a photovoltaic power station, the problem of unstable operation of parts among the photovoltaic equipment which are networked can occur due to aging, corrosion and the like, the generated energy is influenced, and the prediction precision is reduced. Therefore, we propose a method and a system for estimating the generated energy of a photovoltaic power station based on a neural network.
Disclosure of Invention
The invention mainly aims to provide a method and a system for predicting the generated energy of a photovoltaic power station based on a neural network, which are based on Weibull distribution of service life and failure probability of a photovoltaic module in the use process, comprehensively consider the running state of a power station when the photovoltaic module fails to predict the generated energy, correct a predicted value output through a neural network model, output a predicted expected value of the generated energy, better accord with the actual running condition of the photovoltaic power station, improve the accuracy of a predicted result and effectively solve the problems in the background art.
In order to achieve the above purpose, the invention adopts the technical proposal that,
a method for estimating the generating capacity of a photovoltaic power station based on a neural network comprises the following steps,
step one, collecting operation parameter data of a photovoltaic module in a photovoltaic power station, wherein the operation parameter data comprise operation time and fault probability values;
fitting the operation parameter data by using a cumulative distribution function and a probability density function of the double-parameter Weibull distribution to obtain estimated values of the shape parameters and the scaling factors, and calculating estimated values of the position parameters according to the estimated values of the shape parameters and the scaling factors;
step three, the obtained shape parameters and scale parameters are brought into a Weibull distribution model, the expression of the model is,
wherein F (x) is a distribution function; x is a random variable; η is a scaling factor; β is a shape parameter; γ is a location parameter; predicting failure probability F (x) of ith group of photovoltaic modules through model i Wherein i=1, 2., n, n is the total number of photovoltaic modules;
step four, collecting history of the photovoltaic power stationData are used as input to construct a prediction model, and the generated energy predicted value P of the ith group of photovoltaic modules of the photovoltaic power station in the time interval t is output through the model i ；
Step five, calculating a total power generation amount correction value P according to the prediction result of the failure probability of the photovoltaic module and the total power generation amount prediction value c Correction value P of total power generation c The calculation formula of (a) is as follows,
wherein F (t) e ) i Denoted as the ith group of photovoltaic modules at the end time t of time interval t e Is a failure probability of (1); f (t) b ) i Denoted as the ith group of photovoltaic modules at an initial instant t of time interval t b Is a failure probability of (1); f (t) e ) i -F(t b ) i Expressed as the probability of failure of the ith group of photovoltaic modules within the time interval t.
A neural network-based photovoltaic power plant power generation capacity estimation system, comprising:
the photovoltaic module monitoring module is used for monitoring the operation state of the photovoltaic module in real time and collecting the operation parameter data of the photovoltaic module in the photovoltaic power station, including the operation time and the fault probability value;
the fault analysis module is connected with the photovoltaic module monitoring module and is used for calculating the failure probability of the photovoltaic module according to the Weibull distribution model and the operation parameter data of the photovoltaic module;
the data acquisition module is used for acquiring historical data of the photovoltaic power station;
the data analysis module is connected with the data acquisition module and is used for preprocessing the acquired data, carrying out correlation analysis on the data of each influence factor and the corresponding generated energy data, and acquiring the influence factors positively correlated with the generated energy;
the power generation amount prediction module takes collected historical data of the photovoltaic power station as input to construct a prediction model, and the model is used for the predictionOutput of the predicted value P of the power generation amount of the ith group of photovoltaic modules of the photovoltaic power station within the time interval t i ；
The correction prediction module calculates a total power generation amount correction value P according to a prediction result of the failure probability of the photovoltaic module and a total power generation amount prediction value c Wherein the total power generation amount correction value P c The calculation formula of (a) is as follows,
wherein F (t) e ) i Denoted as the ith group of photovoltaic modules at the end time t of time interval t e Is a failure probability of (1); f (t) b ) i Denoted as the ith group of photovoltaic modules at an initial instant t of time interval t b Is a failure probability of (1); f (t) e ) i -F(t b ) i Expressed as the probability of failure of the ith group of photovoltaic modules within the time interval t.
The system also includes a memory, a processor, and an electronic program stored in the memory and capable of running on the processor.
The invention has the following advantages that,
compared with the prior art, the technical scheme of the invention has the advantages that the operation parameter data of the photovoltaic module in the photovoltaic power station are collected, the operation state of the photovoltaic power station when the failure occurs to the photovoltaic module is comprehensively considered, the Weibull distribution model of the service life of the photovoltaic module in the use process is constructed, the failure probability of the photovoltaic module in the use process in the future time interval is predicted through the model, the historical data of the photovoltaic power station is collected as input to construct a prediction model, the power generation predicted value of the photovoltaic module of the photovoltaic power station in the time interval is output through the prediction model, the total power generation correction value is calculated according to the predicted result of the failure probability of the photovoltaic module and the total power generation predicted value, and the power generation predicted expected value is used as the final output power generation predicted result, so that the method is more in line with the actual operation situation of the photovoltaic power station, and the accuracy of the predicted result is improved.
Drawings
FIG. 1 is a flow chart of a method for estimating the power generation capacity of a photovoltaic power station based on a neural network;
fig. 2 is a block diagram of a system for estimating the power generation capacity of a photovoltaic power station based on a neural network.
Detailed Description
The present invention will be further described with reference to the following detailed description, wherein the drawings are for illustrative purposes only and are presented as schematic drawings, rather than physical drawings, and are not to be construed as limiting the invention, and wherein certain components of the drawings are omitted, enlarged or reduced in order to better illustrate the detailed description of the present invention, and are not representative of the actual product dimensions.
Example 1
The flow chart of the method for estimating the generated energy of the photovoltaic power station based on the neural network and the overall structure block diagram of the system for estimating the generated energy of the photovoltaic power station based on the neural network, which are provided by the technical scheme of the invention and are shown in the figure 1.
The technical proposal adopted by the invention is that,
a method for estimating the generating capacity of a photovoltaic power station based on a neural network comprises the following steps,
step one, collecting operation parameter data of a photovoltaic module in a photovoltaic power station, wherein the operation parameter data comprise operation time and fault probability values;
fitting the operation parameter data by using a cumulative distribution function and a probability density function of the double-parameter Weibull distribution to obtain estimated values of the shape parameters and the scaling factors, and calculating estimated values of the position parameters according to the estimated values of the shape parameters and the scaling factors;
step three, the obtained shape parameters and scale parameters are brought into a Weibull distribution model, the expression of the model is,
wherein F (x) is a distribution function; x is a random variable; η is a scaling factor; β is in the shape ofParameters; γ is a location parameter; predicting failure probability F (x) of ith group of photovoltaic modules through model i Wherein i=1, 2., n, n is the total number of photovoltaic modules;
step four, collecting historical data of the photovoltaic power station as input to construct a prediction model, and outputting a power generation quantity predicted value P of an ith group of photovoltaic modules of the photovoltaic power station within a time interval t through the model i ；
Step five, calculating a total power generation amount correction value P according to the prediction result of the failure probability of the photovoltaic module and the total power generation amount prediction value c Correction value P of total power generation c The calculation formula of (a) is as follows,
wherein F (t) e ) i Denoted as the ith group of photovoltaic modules at the end time t of time interval t e Is a failure probability of (1); f (t) b ) i Denoted as the ith group of photovoltaic modules at an initial instant t of time interval t b Is a failure probability of (1); f (t) e ) i -F(t b ) i Expressed as the probability of failure of the ith group of photovoltaic modules within the time interval t.
A neural network-based photovoltaic power plant power generation capacity estimation system, comprising:
the photovoltaic module monitoring module is used for monitoring the operation state of the photovoltaic module in real time and collecting the operation parameter data of the photovoltaic module in the photovoltaic power station, including the operation time and the fault probability value;
the fault analysis module is connected with the photovoltaic module monitoring module and is used for calculating the failure probability of the photovoltaic module according to the Weibull distribution model and the operation parameter data of the photovoltaic module;
the data acquisition module is used for acquiring historical data of the photovoltaic power station;
the data analysis module is connected with the data acquisition module and is used for preprocessing the acquired data, carrying out correlation analysis on the data of each influence factor and the corresponding generated energy data and acquiring the influence factors positively correlated with the generated energy;
the power generation amount prediction module takes collected historical data of the photovoltaic power station as input to construct a prediction model, and outputs a power generation amount predicted value P of an ith group of photovoltaic modules of the photovoltaic power station within a time interval t through the model i ；
The correction prediction module calculates a total power generation amount correction value P according to a prediction result of the failure probability of the photovoltaic module and a total power generation amount prediction value c Wherein the total power generation amount correction value P c The calculation formula of (a) is as follows,
wherein F (t) e ) i Denoted as the ith group of photovoltaic modules at the end time t of time interval t e Is a failure probability of (1); f (t) b ) i Denoted as the ith group of photovoltaic modules at an initial instant t of time interval t b Is a failure probability of (1); f (t) e ) i -F(t b ) i Expressed as the probability of failure of the ith group of photovoltaic modules within the time interval t.
The system also includes a memory, a processor, and an electronic program stored in the memory and capable of running on the processor.
The specific implementation flow of the technical scheme of the invention comprises the following steps:
step 1), monitoring the operation state of a photovoltaic module in real time through a photovoltaic module monitoring module, and collecting operation parameter data of the photovoltaic module in a photovoltaic power station, wherein the operation parameter data comprises operation time and a fault probability value;
step 2), fitting operation parameter data by using a cumulative distribution function and a probability density function of double-parameter Weibull distribution through a fault analysis module to obtain estimated values of shape parameters and scaling factors, and calculating estimated values of position parameters according to the estimated values of the shape parameters and the scaling factors, wherein the cumulative distribution function and the probability density function of Weibull distribution are expressed as follows:
CDF:
PDF:
wherein CDF is a cumulative distribution function expression; PDF is a probability density function expression; t is a time variable;
the calculation formula of the scale parameter formula of Weibull distribution is as follows:
step 3), the obtained shape parameters and scale parameters are brought into a Weibull distribution model, the expression of the model is,
wherein F (x) is a distribution function; x is a random variable; η is a scaling factor; beta is a shape parameter; gamma is a position parameter; predicting failure probability F (x) of ith group of photovoltaic modules through model i The method comprises the steps that i=1, 2, n and n are the total number of photovoltaic modules, and it is required to be noted that at present, most of detection certification authorities utilize an acceleration test method to analyze weather resistance and reliability of outdoor operation of the photovoltaic modules, and failure modes of the photovoltaic modules are analyzed through wet-freeze acceleration tests of the photovoltaic modules, and test results show that service lives and failure probabilities of the photovoltaic modules accord with Weibull distribution, so that the failure probabilities of the photovoltaic modules in a photovoltaic power station can be predicted by adopting a Weibull distribution model;
step 4), acquiring historical data of the photovoltaic power station as input through a power generation amount prediction module to construct a prediction model, and outputting a power generation amount predicted value P of an ith group of photovoltaic modules of the photovoltaic power station within a time interval t through the model i The method comprises the following specific steps of:
step 41, obtaining historical power generation data with the length of c, and preprocessing the obtained data to obtain the historical power generation numberThe data set X, expressed as: x= [ X ] 1 ,...,x t-1 ,x t ,...,x n ] T ；
Step 42, training the historical wind power data set X as input to construct a first neural network model, and extracting and outputting influence factor characteristics positively related to the generated energy in the historical wind power data set X through the constructed model;
step 43, training and constructing a second neural network model by taking the influence factor characteristics output by the first neural network model as input, learning the influence factor characteristic output rule by the second neural network model, and outputting a power generation quantity prediction result;
in actual operation, the model construction can be performed through a BP neural network tool in MATLAB, and the steps are as follows:
a, collecting historical power generation data of a photovoltaic power generation system, wherein the historical power generation data comprises month, day length, weather, time, radiation quantity, real-time temperature, humidity, wind power, wind direction, illumination intensity, current, voltage of a photovoltaic cell array and the like, and corresponding photovoltaic power output data, and the fact that the calculation quantity of a model is overlarge due to various types in the historical power generation data is required to be screened, the acquired data are preprocessed through a data analysis module, correlation analysis is carried out on the data of all the influence factors and corresponding generated energy data, and the influence factors positively correlated with generated energy are obtained, and the method comprises the following specific steps:
step a1, collecting data of all possible influencing factors and corresponding generating capacity data;
step a2, preprocessing the acquired data to acquire a data set X of each influencing factor i Corresponding generated energy data set Y i Wherein, the method comprises the steps of, wherein,x ij a j-th value expressed as an i-th influencing factor;y ij represented as the ith shadowGenerating capacity data corresponding to the j-th value of the response factor;
step a3, calculating correlation coefficients r of data of each influencing factor and corresponding generating capacity data respectively i Wherein r is i Is the first i The correlation coefficient of the term influence factors and the generated energy is calculated as follows:
wherein,is the first i The mean value of the term impact factor data; />Is the first i The average value of the generated energy corresponding to the item influence factors, j is the number of samples;
step a4, screening influence factors larger than 0 in the calculation result of the correlation coefficient as influence factors positively correlated with the generated energy;
b, preprocessing the collected data, including data cleaning, normalization processing and the like;
c, establishing a neural network model of photovoltaic power prediction by using a BP neural network tool box in MATLAB;
d, determining input layer variables and output layer variables of the neural network;
e, designing hidden layers of the neural network, wherein the hidden layers comprise the number of the hidden layers and the number of nodes;
f, selecting a proper training algorithm and training parameters;
g, training a neural network model by using the preprocessed historical data;
h, testing and verifying the trained neural network model by using the test data set;
the first neural network model can be a CNN model, has two characteristics of parameter sharing and sparse connection, can effectively capture the characteristics of original data, and the second neural network model can be a BiLSTM model, predicts subsequent information by utilizing forward information, and combines forward and backward information of an input sequence on the basis of LSTM to improve prediction accuracy;
step 5), calculating a total power generation amount correction value P according to the prediction result of the failure probability of the photovoltaic module and the total power generation amount prediction value through a correction prediction module c Correction value P of total power generation c The calculation formula of (a) is as follows,
wherein F (t) e ) i Denoted as the ith group of photovoltaic modules at the end time t of time interval t e Is a failure probability of (1); f (t) b ) i Denoted as the ith group of photovoltaic modules at an initial instant t of time interval t b Is a failure probability of (1); f (t) e ) i -F(t b ) i The failure probability of the photovoltaic module of the ith group in the time interval t is expressed, and it is required to be stated that, because the service life and the failure probability of the photovoltaic module conform to Weibull distribution in the use process, when the power generation amount of a future period is predicted, the situation when the photovoltaic module fails also needs to be considered, and therefore, the total power generation amount correction value P is calculated c The predicted value output by the neural network model is corrected, the predicted expected value of the generated energy in the future time interval t is output, the predicted value is more in line with the actual running condition of the photovoltaic power station, and the prediction accuracy of the predicted result is correspondingly improved.
The foregoing has shown and described the basic principles and main features of the present invention and the advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (7)
1. A method for estimating the power generation capacity of a photovoltaic power station based on a neural network is characterized by comprising the following steps of,
step one, collecting operation parameter data of a photovoltaic module in a photovoltaic power station, wherein the operation parameter data comprise operation time and fault probability values;
fitting the operation parameter data by using a cumulative distribution function and a probability density function of the double-parameter Weibull distribution to obtain estimated values of the shape parameters and the scaling factors, and calculating estimated values of the position parameters according to the estimated values of the shape parameters and the scaling factors;
step three, the obtained shape parameters and scale parameters are brought into a Weibull distribution model, the expression of the model is,
wherein F (x) is a distribution function; x is a random variable; η is a scaling factor; beta is a shape parameter; gamma is a position parameter; predicting failure probability F (x) of ith group of photovoltaic modules through model i Wherein i=1, 2., n, n is the total number of photovoltaic modules;
step four, collecting historical data of the photovoltaic power station as input to construct a prediction model, and outputting a power generation quantity predicted value P of an ith group of photovoltaic modules of the photovoltaic power station within a time interval t through the model i ；
Step five, calculating a total power generation amount correction value P according to the prediction result of the failure probability of the photovoltaic module and the total power generation amount prediction value c Correction value P of total power generation c The calculation formula of (a) is as follows,
wherein F (t) e ) i Denoted as the ith group of photovoltaic modules at the end time t of time interval t e Is a failure probability of (1); f (t) b ) i Denoted as ithThe group photovoltaic module is at the time interval t initial time t b Is a failure probability of (1); f (t) e ) i -F(t b ) i Expressed as the probability of failure of the ith group of photovoltaic modules within the time interval t.
2. The method for estimating the power generation capacity of a photovoltaic power station based on a neural network according to claim 1, wherein the expression of the cumulative distribution function and the probability density function of Weibull distribution is:
CDF:
PDF:
wherein CDF is a cumulative distribution function expression; PDF is a probability density function expression; t is a time variable.
3. The method for estimating the power generation capacity of a photovoltaic power station based on a neural network according to claim 1, wherein the calculation formula of the scale parameter formula of Weibull distribution is:
4. the method for estimating the power generation capacity of a photovoltaic power station based on a neural network according to claim 1, wherein the specific steps of the fourth step are as follows:
step s41, obtaining historical power generation data with a length of c, and preprocessing the obtained data to obtain a historical power generation data set X, which is expressed as: x= [ X ] 1 ,...,x t-1 ,x t ,...,x n ] T ；
Step S42, training is carried out by taking the historical wind power data set X as input to construct a first neural network model, and the influence factor characteristics positively related to the generated energy in the historical wind power data set X are extracted and output through the constructed model;
and step S43, training and constructing a second neural network model by taking the influence factor characteristics output by the first neural network model as input, learning the influence factor characteristic output rule by the second neural network model, and outputting the power generation quantity prediction result.
5. The method for estimating a power generation amount of a photovoltaic power plant based on a neural network according to claim 4, wherein in step s42, the method for determining the influence factors positively correlated with the power generation amount comprises the steps of:
step s421, collecting data of all possible influencing factors and corresponding generating capacity data;
step s422, preprocessing the collected data to obtain a data set X of each influencing factor i Corresponding generated energy data set Y i Wherein, the method comprises the steps of, wherein,x ij a j-th value expressed as an i-th influencing factor;y ij generating capacity data corresponding to a j-th value expressed as the i-th influencing factor;
step s423, calculating correlation coefficients r of the data of each influencing factor and the corresponding power generation amount data i Wherein r is i For the correlation coefficient of the ith influence factor and the generated energy, the calculation formula is as follows:
wherein,for the ith influenceThe mean value of the factor data; />The average value of the generated energy corresponding to the ith influence factor is obtained, and j is the number of samples;
in step s424, the influence factor greater than 0 in the calculation result of the correlation coefficient is selected as the influence factor positively correlated with the power generation amount.
6. A photovoltaic power station generated energy prediction system based on a neural network is characterized by comprising:
the photovoltaic module monitoring module is used for monitoring the operation state of the photovoltaic module in real time and collecting the operation parameter data of the photovoltaic module in the photovoltaic power station, including the operation time and the fault probability value;
the fault analysis module is connected with the photovoltaic module monitoring module and is used for calculating the failure probability of the photovoltaic module according to the Weibull distribution model and the operation parameter data of the photovoltaic module;
the data acquisition module is used for acquiring historical data of the photovoltaic power station;
the data analysis module is connected with the data acquisition module and is used for preprocessing the acquired data, carrying out correlation analysis on the data of each influence factor and the corresponding generated energy data, and acquiring the influence factors positively correlated with the generated energy;
the power generation amount prediction module takes collected historical data of the photovoltaic power station as input to construct a prediction model, and outputs a power generation amount predicted value P of an ith group of photovoltaic modules of the photovoltaic power station within a time interval t through the model i ；
The correction prediction module calculates a total power generation amount correction value P according to a prediction result of the failure probability of the photovoltaic module and a total power generation amount prediction value c Wherein the total power generation amount correction value P c The calculation formula of (a) is as follows,
wherein F (t) e ) i Denoted as the ith group of photovoltaic modules at the end time t of time interval t e Is a failure probability of (1); f (t) b ) i Denoted as the ith group of photovoltaic modules at an initial instant t of time interval t b Is a failure probability of (1); f (t) e ) i -F(t b ) i Expressed as the probability of failure of the ith group of photovoltaic modules within the time interval t.
7. The system for estimating a power generation capacity of a photovoltaic power plant based on a neural network according to claim 6, further comprising a memory, a processor and an electronic program stored in the memory and executable on the processor, wherein the processor is capable of implementing the steps of the method according to any one of claims 1 to 5 when the electronic program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311519348.7A CN117540859B (en) | 2023-11-15 | 2023-11-15 | Method and system for estimating generated energy of photovoltaic power station based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311519348.7A CN117540859B (en) | 2023-11-15 | 2023-11-15 | Method and system for estimating generated energy of photovoltaic power station based on neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117540859A true CN117540859A (en) | 2024-02-09 |
| CN117540859B CN117540859B (en) | 2024-07-05 |
Family
ID=89783621
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311519348.7A Active CN117540859B (en) | 2023-11-15 | 2023-11-15 | Method and system for estimating generated energy of photovoltaic power station based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117540859B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118174453A (en) * | 2024-03-14 | 2024-06-11 | 信阳师范学院 | Distributed photovoltaic power station intelligent monitoring platform and method |
| CN118277893A (en) * | 2024-06-03 | 2024-07-02 | 国网辽宁省电力有限公司信息通信分公司 | Multi-element associated power generation equipment energy state identification method based on non-invasive monitoring |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130013233A1 (en) * | 2010-03-19 | 2013-01-10 | Yoshiki Murakami | Electric-power-generation level predicting apparatus, method and program |
| CN108256690A (en) * | 2018-02-07 | 2018-07-06 | 国网辽宁省电力有限公司电力科学研究院 | Photovoltaic generation Forecasting Methodology based on form parameter confidence interval |
| CN110443405A (en) * | 2019-06-28 | 2019-11-12 | 国网山东省电力公司济宁市任城区供电公司 | A kind of built photovoltaic power station power generation amount forecasting system and method |
-
2023
- 2023-11-15 CN CN202311519348.7A patent/CN117540859B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130013233A1 (en) * | 2010-03-19 | 2013-01-10 | Yoshiki Murakami | Electric-power-generation level predicting apparatus, method and program |
| CN108256690A (en) * | 2018-02-07 | 2018-07-06 | 国网辽宁省电力有限公司电力科学研究院 | Photovoltaic generation Forecasting Methodology based on form parameter confidence interval |
| CN110443405A (en) * | 2019-06-28 | 2019-11-12 | 国网山东省电力公司济宁市任城区供电公司 | A kind of built photovoltaic power station power generation amount forecasting system and method |
Non-Patent Citations (1)
| Title |
|---|
| 李军;许继生;王生渊;景满德;李春来;尚国斌;: "一种并网型光伏电站光功率及发电量预测的方法", 青海电力, no. 02, 30 June 2010 (2010-06-30) * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118174453A (en) * | 2024-03-14 | 2024-06-11 | 信阳师范学院 | Distributed photovoltaic power station intelligent monitoring platform and method |
| CN118277893A (en) * | 2024-06-03 | 2024-07-02 | 国网辽宁省电力有限公司信息通信分公司 | Multi-element associated power generation equipment energy state identification method based on non-invasive monitoring |
| CN118277893B (en) * | 2024-06-03 | 2024-09-27 | 国网辽宁省电力有限公司信息通信分公司 | Multi-element associated power generation equipment energy state identification method based on non-invasive monitoring |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117540859B (en) | 2024-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117540859B (en) | Method and system for estimating generated energy of photovoltaic power station based on neural network | |
| CN108647716B (en) | Photovoltaic array fault diagnosis method based on composite information | |
| CN109842373B (en) | Photovoltaic array fault diagnosis method and device based on space-time distribution characteristics | |
| Samara et al. | Intelligent real-time photovoltaic panel monitoring system using artificial neural networks | |
| Mellit et al. | Short-term forecasting of power production in a large-scale photovoltaic plant | |
| Gao et al. | A novel fault identification method for photovoltaic array via convolutional neural network and residual gated recurrent unit | |
| Adhya et al. | Performance assessment of selective machine learning techniques for improved PV array fault diagnosis | |
| CN111612651B (en) | Abnormal electric quantity data detection method based on long-term and short-term memory network | |
| KR101882106B1 (en) | Method and apparatus for predicting the generated energy of the solar cell module | |
| CN117172620B (en) | Building photovoltaic potential evaluation method and system based on parameterized analysis | |
| Rao et al. | Dropout and pruned neural networks for fault classification in photovoltaic arrays | |
| CN110503153B (en) | Photovoltaic system fault diagnosis method based on differential evolution algorithm and support vector machine | |
| CN117318111B (en) | Weather prediction-based dynamic adjustment method and system for light energy storage source | |
| CN111695736A (en) | Photovoltaic power generation short-term power prediction method based on multi-model fusion | |
| Shi et al. | Expected output calculation based on inverse distance weighting and its application in anomaly detection of distributed photovoltaic power stations | |
| He et al. | Compound fault diagnosis for photovoltaic arrays based on multi-label learning considering multiple faults coupling | |
| CN117669960A (en) | New energy power prediction method based on multivariable meteorological factors | |
| Djalab et al. | Robust method for diagnosis and detection of faults in photovoltaic systems using artificial neural networks | |
| Nour-eddine et al. | Power forecasting of three silicon-based PV technologies using actual field measurements | |
| CN117893057A (en) | Deep learning-based photovoltaic string dust accumulation degree evaluation method and system | |
| CN117787698A (en) | Micro-grid risk assessment method and system based on power supply range maximization | |
| TW201727559A (en) | Management method and system of renewable energy power plant checking whether the power generation of a renewable energy power plant is normal according to the estimated power generation amount | |
| Pahmi et al. | Artificial neural network based forecasting of power under real time monitoring environment | |
| Azad et al. | A data lens into MPPT efficiency and PV power prediction | |
| Li et al. | Detection and Analyze of Off-Maximum Power Points of PV Systems Based on PV-Pro Modelling |
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 | ||
| CP03 | Change of name, title or address |
Address after: Unit 2301, Building A, Phase II, China Merchants Qianhai Economic and Trade Center, No. 3041 Yihai Avenue, Liwan Community, Nanshan Street, Nanshan District, Shenzhen City, Guangdong Province, 518000 Patentee after: Guangdong Huakong New Energy Co.,Ltd. Country or region after: China Address before: 2301 Block A Phase II Qianhai Economic and Trade Center China Merchants Group No 3041 Yihai Avenue Liwan Community Nanshan Street Nanshan District Shenzhen Guangdong Province Patentee before: Shenzhen Nankong New Energy Co.,Ltd. Country or region before: China |