CN117332237A - Real-time calculation method for solar irradiation intensity of photovoltaic power station and related equipment - Google Patents
Real-time calculation method for solar irradiation intensity of photovoltaic power station and related equipment Download PDFInfo
- Publication number
- CN117332237A CN117332237A CN202311462296.4A CN202311462296A CN117332237A CN 117332237 A CN117332237 A CN 117332237A CN 202311462296 A CN202311462296 A CN 202311462296A CN 117332237 A CN117332237 A CN 117332237A
- Authority
- CN
- China
- Prior art keywords
- data
- photovoltaic power
- power station
- feature
- operation 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
Links
- 238000004364 calculation method Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 claims abstract description 48
- 230000007613 environmental effect Effects 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims description 25
- 238000013528 artificial neural network Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 230000005855 radiation Effects 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 abstract description 11
- 238000012706 support-vector machine Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 238000010248 power generation Methods 0.000 description 7
- 238000010845 search algorithm Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000012216 screening Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Water Supply & Treatment (AREA)
- General Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Photovoltaic Devices (AREA)
Abstract
The embodiment of the invention provides a method for calculating solar irradiation intensity of a photovoltaic power station in real time, which comprises the following steps: acquiring operation data of a photovoltaic power station; extracting the characteristics of the operation data to obtain characteristic data; modeling the characteristic data to generate an estimated value of the ambient temperature; and obtaining the solar irradiance estimation value of the photovoltaic power station based on the environmental temperature estimation value. The solar irradiation intensity data are obtained through calculation of the operation data of the photovoltaic power station, and have a certain guiding significance for researching the operation characteristics of the photovoltaic power station, reasonably planning layout places and monitoring operation states.
Description
Technical Field
The invention relates to the technical field of photovoltaic power generation, in particular to a real-time calculation method for solar irradiation intensity of a photovoltaic power station and related equipment.
Background
In recent years, under the background of greenhouse effect and energy crisis, photovoltaic power generation is a sustainable and green novel energy source, and is rapidly developed. Because the distributed photovoltaic power station generally lacks a solar radiation monitoring device, and a single solar radiation monitoring station in the centralized photovoltaic is difficult to characterize the actual solar radiation receiving condition of the power station, the loss of real-time solar radiation information seriously affects the realization of core key functions such as power generation amount calculation, power prediction, fault diagnosis, scheduling plan and the like.
Therefore, a real-time calculation method for solar irradiation intensity of a photovoltaic power station is urgently needed to solve the problem that the existing solar irradiation information is lack to seriously influence the realization of core key functions such as power generation calculation, power prediction, fault diagnosis and scheduling plan, solar irradiation intensity data is obtained through calculation of operation data of the photovoltaic power station, and the method has a certain guiding significance for researching the operation characteristics of the photovoltaic power station, reasonably planning layout places and monitoring operation states.
Disclosure of Invention
The embodiment of the invention provides a real-time calculation method for solar irradiation intensity of a photovoltaic power station, which aims to solve the problem that the loss of existing solar irradiation information seriously affects the realization of core key functions such as power generation calculation, power prediction, fault diagnosis, scheduling plan and the like. The solar irradiation intensity data are obtained through calculation of the operation data of the photovoltaic power station, and have a certain guiding significance for researching the operation characteristics of the photovoltaic power station, reasonably planning layout places and monitoring operation states.
In a first aspect, an embodiment of the present invention provides a method for calculating solar irradiation intensity of a photovoltaic power station in real time, where the method includes:
acquiring operation data of a photovoltaic power station;
extracting the characteristics of the operation data to obtain characteristic data;
modeling the characteristic data to generate an estimated value of the ambient temperature;
and obtaining a solar irradiance estimation value of the photovoltaic power station based on the environmental temperature estimation value.
Optionally, the step of acquiring the operation data of the photovoltaic power station includes:
collecting operation data parameters of a photovoltaic power station;
and carrying out data processing on the operation data parameters to obtain the operation data of the photovoltaic power station.
Optionally, the step of extracting the characteristics of the operation data to obtain the characteristic data includes:
extracting the characteristics of the operation data to obtain a characteristic data set;
and performing data dimension reduction on the characteristic data set to obtain characteristic data.
Optionally, the step of extracting the characteristics of the operation data to obtain a characteristic data set includes:
acquiring mutual information between the output power of the power station and the electrical characteristic quantity in the operation data;
and when the mutual information reaches a preset maximum value, determining a characteristic data set.
Optionally, the step of performing data dimension reduction on the feature data set to obtain feature data includes:
performing feature calculation on the feature data set through a preset algorithm to obtain a feature subset;
determining, based on the subset of features, whether a number of features of the subset reaches n;
if the feature quantity of the subset reaches n, determining feature data.
Optionally, the step of modeling the feature data to generate an estimated value of the ambient temperature includes:
normalizing the characteristic data to obtain processed characteristic data;
initializing the processed characteristic data to obtain initialized data;
performing iterative computation on the initialization data to determine initialization data parameters;
and carrying out data modeling on the initialized data parameters through a preset prediction model to generate an environment temperature estimated value.
Optionally, the step of obtaining the estimated solar irradiance value of the photovoltaic power station based on the estimated ambient temperature value includes:
correcting the operation data of the photovoltaic power station by using the environment temperature estimated value to obtain corrected operation data;
and carrying out data modeling on the corrected operation data through a preset neural network to generate a solar irradiance estimation value of the photovoltaic power station.
In a second aspect, an embodiment of the present invention further provides a device for calculating solar irradiation intensity of a photovoltaic power station in real time, where the device for calculating solar irradiation intensity of the photovoltaic power station in real time includes:
the acquisition module is used for acquiring the operation data of the photovoltaic power station;
the extraction module is used for extracting the characteristics of the operation data to obtain characteristic data;
the generation module is used for carrying out data modeling on the characteristic data and generating an environmental temperature estimated value;
and the processing module is used for obtaining the solar irradiance estimation value of the photovoltaic power station based on the environmental temperature estimation value.
In a third aspect, an embodiment of the present invention provides an electronic device, including: the method comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the steps in the method for calculating the solar irradiation intensity of the photovoltaic power station in real time are realized when the processor executes the computer program.
In a fourth aspect, an embodiment of the present invention provides a computer readable storage medium, where a computer program is stored on the computer readable storage medium, where the computer program when executed by a processor implements the steps in the method for calculating solar irradiation intensity of a photovoltaic power station according to the embodiment of the present invention.
In the embodiment of the invention, the operation data of the photovoltaic power station is obtained; extracting the characteristics of the operation data to obtain characteristic data; modeling the characteristic data to generate an estimated value of the ambient temperature; and obtaining the solar irradiance estimation value of the photovoltaic power station based on the environmental temperature estimation value. The solar irradiation intensity data are obtained through calculation of the operation data of the photovoltaic power station, and have a certain guiding significance for researching the operation characteristics of the photovoltaic power station, reasonably planning layout places and monitoring operation states.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for calculating solar irradiation intensity of a photovoltaic power station in real time according to an embodiment of the present invention;
FIG. 2 is a flowchart of another method for calculating solar irradiation intensity of a photovoltaic power station in real time according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a neural network for secondary modeling according to an embodiment of the present invention;
FIG. 4 is a graph of actual and calculated temperature and irradiance for each power station provided by an embodiment of the invention;
FIG. 5 is a graph of irradiance calculation error versus irradiance provided by an embodiment of the invention;
fig. 6 is a schematic structural diagram of a real-time calculation device for solar irradiation intensity of a photovoltaic power station according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that all directional indicators (such as up, down, left, right, front, and rear … …) in the embodiments of the present invention are merely used to explain the relative positional relationship, movement, etc. between the components in a particular posture (as shown in the drawings), and if the particular posture is changed, the directional indicator is changed accordingly.
Furthermore, the description of "first," "second," etc. in this disclosure is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not within the scope of protection claimed in the present invention.
As shown in fig. 1, fig. 1 is a flowchart of a method for calculating solar irradiation intensity of a photovoltaic power station in real time according to an embodiment of the present invention. The method for calculating the solar irradiation intensity of the photovoltaic power station in real time comprises the following steps:
101. and acquiring operation data of the photovoltaic power station.
In the embodiment of the invention, the method for calculating the solar irradiance of the photovoltaic power station in real time is used for the photovoltaic power station. The photovoltaic power station is a place for generating electricity by utilizing solar energy, and mainly comprises a photovoltaic panel assembly which can convert the solar energy into electric energy.
The operation data comprise photovoltaic module voltage, current and power and photovoltaic module temperature data.
The photovoltaic module voltage, current and power and photovoltaic module temperature data in the operation data of the photovoltaic power station are integrated, and missing data deficiency and abnormal value replacement processing are carried out.
102. And extracting the characteristics of the operation data to obtain the characteristic data.
In the embodiment of the invention, the feature extraction refers to a method and a process for extracting information belonging to features.
Furthermore, the data dimension reduction can be performed on the operation data, and the important information of the data can be reserved by reducing the feature dimension, so that the calculation complexity and the storage requirement are reduced.
The characteristic data can be characteristic data obtained after characteristic extraction and dimension reduction, and the characteristic data comprises screened electric characteristic data such as voltage, current, component temperature and the like.
It should be noted that, considering that the dimension of the collected operation data of the photovoltaic power station is higher, the calculation complexity is high, and the feature screening in the processed original data finds a group of features with the largest correlation with the final output result, but the features have the smallest correlation with each other.
103. And carrying out data modeling on the characteristic data to generate an estimated value of the ambient temperature.
In the embodiment of the invention, the data modeling can be understood as a process of converting an actual problem into a mathematical model, and through research and analysis of the model, deep understanding and solution of the problem can be obtained.
The above-mentioned ambient temperature estimation value may be understood as a predicted value calculated from the collected ambient data in combination with a correlation algorithm and a model. The estimated ambient temperature value can help people to better know the temperature condition of the surrounding environment, so that corresponding countermeasures can be taken.
Specifically, a Support Vector Machine (SVM) prediction model may be selected to train at least one feature data, and a corresponding regression model is established.
104. And obtaining the solar irradiance estimation value of the photovoltaic power station based on the environmental temperature estimation value.
In the embodiment of the invention, the operation data of the photovoltaic power station can be corrected by using the environmental temperature estimated value, and modeling is performed through a preset neural network to generate the irradiance estimated value.
The preset neural network may be a BP neural network prediction model, and the BP neural network prediction model continuously adjusts the network weight and the threshold value by back propagation of the error function, so that the error function drops along the negative gradient direction and approaches the expected output.
The modified operation data can be used for more accurately evaluating the generated energy of the photovoltaic power station.
The solar irradiance estimation value of the photovoltaic power station refers to the total solar radiation received by the photovoltaic power station and is used for estimating the power generation amount and the equipment performance of the photovoltaic power station.
In the embodiment, operation data of a photovoltaic power station is obtained; extracting the characteristics of the operation data to obtain characteristic data; modeling the characteristic data to generate an estimated value of the ambient temperature; and obtaining a solar irradiance estimation value of the photovoltaic power station based on the environmental temperature estimation value. The solar irradiation intensity data are obtained through calculation of the operation data of the photovoltaic power station, and have a certain guiding significance for researching the operation characteristics of the photovoltaic power station, reasonably planning layout places and monitoring operation states.
Optionally, in the step of acquiring the operation data of the photovoltaic power station, the operation data parameters of the photovoltaic power station may be collected; and carrying out data processing on the operation data parameters to obtain the operation data of the photovoltaic power station.
In the embodiment of the invention, the photovoltaic power station refers to a place for generating electricity by utilizing solar energy, wherein the photovoltaic power station mainly comprises a photovoltaic panel assembly, and can convert the solar energy into electric energy.
The operation data parameters comprise data parameters such as voltage, current and power of the photovoltaic module, temperature data of the photovoltaic module and the like.
The data processing may be missing data replacement processing and outlier replacement processing.
The operation data of the photovoltaic power station comprise photovoltaic module voltage, current and power and photovoltaic module temperature data.
Optionally, in the step of extracting features of the operation data to obtain feature data, feature extraction may be performed on the operation data to obtain a feature data set; and performing data dimension reduction on the characteristic data set to obtain characteristic data.
In the embodiment of the invention, the feature extraction refers to a method and a process for extracting information belonging to features.
The feature data set refers to a set of data obtained through feature extraction, wherein each data contains some feature information.
The above data dimension reduction refers to a process of mapping high-dimensional data to a low-dimensional space in order to reduce complexity of the data while preserving information of the original data.
The characteristic data can be characteristic data obtained after characteristic extraction and dimension reduction, and the characteristic data comprises screened electric characteristic data such as voltage, current, component temperature and the like.
Optionally, in the step of extracting the characteristics of the operation data to obtain the characteristic data set, mutual information between the output power of the power station in the operation data and the electrical characteristic quantity may be obtained; and when the mutual information reaches a preset maximum value, determining a characteristic data set.
In the embodiment of the present invention, the mutual information refers to the information amount between two random variables, and may be used to describe the correlation between different variables. In the invention, the output power and the electrical characteristic quantity of the power station can be regarded as two random variables, and the correlation degree and the influence relation between the output power and the electrical characteristic quantity of the power station can be known by calculating the mutual information between the output power and the electrical characteristic quantity of the power station, so that the operation state of the power system is analyzed and evaluated.
When the mutual information reaches the maximum value, this means that the correlation between the output power of the power station and the electrical characteristic quantity is the strongest, and the characteristic data set can be determined.
Further, the feature data is used as input features for machine learning model training, data analysis and other operations to obtain more accurate predictions or results.
Specifically, mutual information I (P, v) between the output power of the power station and the electrical characteristic quantity is calculated, and when I (P, v) reaches a maximum value, the data set s= { v } is marked, and f=f- { v }.
Wherein P is the output power of the power station, v is the electrical characteristic quantity of the power station, S is the filtered characteristic set, and F is the characteristic set to be filtered.
Optionally, in the step of performing data dimension reduction on the feature data set to obtain feature data, feature calculation can be performed on the feature data set through a preset algorithm to obtain a feature subset; determining, based on the feature subset, whether a feature number of the subset reaches n; if the feature quantity of the subset reaches n, determining feature data.
In the embodiment of the present invention, the preset algorithm may be an incremental search algorithm; the incremental search algorithm searches for an optimal solution by continuously reducing the scale of a feasible solution set, generally adopts a divide-and-conquer strategy to decompose a large problem into a plurality of small problems, then solves the small problems in sequence, and finally obtains a global optimal solution.
The number n may be understood as a preset number, and may be 5, 6, 7, or the like.
It should be noted that, the feature subset is calculated according to the incremental search algorithm, whether the feature data of the feature subset reaches n is judged, if so, the subset is output, and thus the feature data is determined.
Specifically, a feature subset F is calculated according to an incremental search algorithm, wherein the feature v satisfies the equation s=s { v }, f=f- { v }; judging whether the feature quantity of the subset reaches n, and if so, outputting a subset S; if n is not reached, repeatedly calculating the feature subset according to the search algorithm, and continuing searching until the number of features reaches n.
Wherein P is the output power of the power station, v is the electrical characteristic quantity of the power station, S is the filtered characteristic set, and F is the characteristic set to be filtered.
Optionally, in the step of modeling the feature data to generate the estimated value of the ambient temperature, normalization processing may be performed on the feature data to obtain processed feature data; initializing the processed characteristic data to obtain initialized data; performing iterative computation on the initialization data to determine initialization data parameters; and carrying out data modeling on the initialized data parameters through a preset prediction model to generate an estimated value of the ambient temperature.
In the embodiment of the invention, the characteristic data comprise screened electric characteristic data such as voltage, current, component temperature and the like.
The normalization process described above can be understood as linearly transforming the data so that it scales at the same scale.
The above initialization process can be understood as initializing a population, encoding and initializing parameters.
The iterative calculation is a numerical calculation method, and the solution of the problem can be approximated by repeatedly using the same formula, namely, a rough approximation value is firstly taken, and then the initial value is continuously corrected by using the same formula until the preset precision requirement is met.
The preset prediction model may be a support vector machine prediction model. The support vector machine (support vector machines, SVM) is a classification model, which refers to a classification function relationship of, for example, a plurality of features (independent variable X) to another tag item (dependent variable Y). The support vector machine prediction model may classify or regress data by finding a hyperplane.
The above-mentioned ambient temperature estimation value may be understood as a predicted value calculated from the collected ambient data in combination with a correlation algorithm and a model. The estimated ambient temperature value can help people to better know the temperature condition of the surrounding environment, so that corresponding countermeasures can be taken.
Specifically, the screened electrical characteristic data such as voltage, current, component temperature and the like can be normalized; initializing a population, encoding parameters and initializing; calculating the fitness of all individuals for measuring the quality degree of the individuals; the roulette method can be used for selecting, crossing and mutating individuals with high fitness value, and finally forming a new population.
Further, the iterative calculation determines the optimal value of the initialized data parameter as the primary prediction model parameter.
Furthermore, a support vector machine prediction model is selected, at least one sample is required to be trained, and a corresponding regression model f (x) 1 ，x 2 ，...x n )＝y i . Wherein x is 1 ，x 2 ，...x n To input variables including voltage, current, component temperature, y i For output, i.e. ambient temperature. Training results are characterized by Mean Absolute Error (MAE) and Root Mean Square Error (RMSE):
optionally, in the step of obtaining the solar irradiance estimation value of the photovoltaic power station based on the environmental temperature estimation value, the operation data of the photovoltaic power station may be corrected by using the environmental temperature estimation value to obtain corrected operation data; and carrying out data modeling on the corrected operation data through a preset neural network to generate a solar irradiance estimated value of the photovoltaic power station.
In the embodiment of the invention, the preset neural network may be a BP neural network prediction model, and the BP neural network prediction model continuously adjusts the network weight and the threshold value through back propagation of the error function, so that the error function drops along the negative gradient direction and approaches the expected output.
The modified operation data can be used for more accurately evaluating the generated energy of the photovoltaic power station.
The solar irradiance estimation value of the photovoltaic power station refers to the total solar radiation received by the photovoltaic power station and is used for estimating the power generation amount and the equipment performance of the photovoltaic power station.
The operation data of the photovoltaic power station is corrected by using the ambient temperature estimated value, so that the absolute error of the irradiance estimated value is reduced.
As shown in fig. 2, fig. 2 is a flowchart of a method for calculating solar irradiation intensity of another photovoltaic power station in real time according to an embodiment of the present invention. The method for calculating the solar irradiation intensity of the photovoltaic power station in real time comprises the following steps of:
201. and collecting and processing photovoltaic power station operation data.
And integrating the photovoltaic module voltage, current and power in the photovoltaic power station operation data, and carrying out missing data deficiency and abnormal value replacement processing on the photovoltaic module temperature data.
202. And reducing the dimension of the operation data through feature screening.
Wherein, by calculating the mutual information I (P, v) between the output power of the power station and the electrical characteristic quantity, when the mutual information I (P, v) reaches a maximum value, the data set s= { v }, f=f- { v }; calculating a feature subset F according to an incremental search algorithm, wherein the feature v satisfies the equation S=S { v }, F=F- { v }; and judging whether the feature quantity of the subset reaches n, if so, outputting the subset, otherwise, repeating the increment searching algorithm to calculate the feature subset, and continuing searching until the feature quantity reaches n.
Wherein P is the output power of the power station, v is the electrical characteristic quantity of the power station, S is the filtered characteristic set, and F is the characteristic set to be filtered.
203. An ambient temperature estimate is generated by initial modeling.
The obtained screened electrical characteristic data such as voltage, current, building temperature and the like are input and normalized; initializing a population, encoding parameters and initializing; calculating the fitness of all individuals for measuring the quality degree of the individuals; selecting, crossing and mutating with high adaptability value by roulette method to form new population; iterative calculation is carried out to determine the optimal value as a primary prediction model parameter; selecting a Support Vector Machine (SVM) prediction model, training at least one sample, and establishing a corresponding regression model f (x) 1 ，x 2 ，...x n )＝y i Wherein x is 1 ，x 2 ，...x n To input variables including voltage, current, component temperature, y i For output, i.e. ambient temperature, the training results are characterized by Mean Absolute Error (MAE) and Root Mean Square Error (RMSE):
204. and correcting the photovoltaic power station operation data by using the environmental temperature estimated value, and performing secondary modeling through a neural network to generate an irradiance estimated value.
And integrating the obtained environmental temperature estimated value with the screened voltage, current and photovoltaic module temperature data to obtain an input variable of the BP neural network prediction model, and obtaining an output variable which is an irradiance estimated value.
In the embodiment of the invention, the real-time monitoring of the solar irradiation intensity is realized by using a small amount of data, and the operation and management cost of the photovoltaic power station is reduced. The obtained solar irradiance data of the photovoltaic power station has a certain guiding significance for researching the operation characteristics of the photovoltaic power station, reasonably planning layout places and checking the operation state.
As shown in fig. 3, fig. 3 is a schematic diagram of the present invention when the neural network is used for secondary modeling. And taking the obtained temperature estimated value, the screened voltage, current and photovoltaic module temperature data as input variables of a BP neural network prediction model entirely, and obtaining irradiance as an output variable.
In the embodiment of the invention, the environment temperature of the intermediate variable is calculated, and the original data set is corrected by using the intermediate variable, so that the absolute error of the irradiance estimation value is reduced. Considering that the dimension of the collected photovoltaic power station operation data is higher, the calculation complexity is high, and a group of features (Min-Reductance) with the largest correlation with the final output result but the smallest correlation among the features is found by feature screening in the processed original data. The real-time monitoring of the solar irradiation intensity can be realized by using only a small amount of data, and the operation and management cost of the photovoltaic power station is reduced. The calculated solar irradiance data of the photovoltaic power station has a certain guiding significance for researching the operation characteristics of the photovoltaic power station, reasonably planning layout places and monitoring the operation state.
In one embodiment, the actual operation data of the photovoltaic power station on the roof of the North China electric university can be selected for verifying the accuracy of the photovoltaic power station on the roof under the input variables of the same type and number, and the two-step calculation model and the direct calculation model are compared. The installed capacity of the photovoltaic system was 1.63 megawatts, including about 6650 photovoltaic modules and 512 arrays. The collected data mainly comprise power, current and voltage data of the photovoltaic array, and solar radiation, temperature, humidity and wind speed data. Table 1 shows a direct calculation model for directly estimating irradiance without performing ambient temperature calculations and performance indicators of the results obtained by the method of the present invention.
TABLE 1 comparison of the Performance of the predictions obtained by different prediction methods
It is observed that the method of the present invention has smaller calculation errors.
In another embodiment, the data of a certain distributed mountain photovoltaic power station group can be selected to verify the effectiveness of the method. Specifically, the installed capacity of the photovoltaic system is 64MWp, 5 distributed photovoltaic power stations are arranged, and 1 meteorological station is arranged in each of the 5 photovoltaic power stations to provide irradiance and temperature measurement values. Fig. 4 shows the actual and calculated curves of 5 plant temperatures and irradiance, with the same line of subgraphs being the calculated temperature, calculated irradiance versus actual value for the same plant. It is observed that the calculation error of the temperature at night is large, because the voltage and current output of the photovoltaic power station at night is 0, and the continuous decline degree of the actual temperature is difficult to estimate.
Table 2 shows the performance index of the prediction results obtained by the present invention. The observation shows that the calculation accuracy of the prediction result obtained by the method is good, and the irradiance average error is controlled within 20. Fig. 5 shows the distribution of irradiance calculation errors, with a skewness of-0.59. It can be obtained that the calculated error distribution of irradiance changes with increasing actual irradiance values, overall the error is biased to the left of the average. The result has a certain guiding significance for researching the operation characteristics of the photovoltaic power station, reasonably planning the layout place and monitoring the operation state.
TABLE 2 calculation result errors for different power stations using the method of the present invention
The method considers that the dimension of the collected photovoltaic power station operation data is higher, the calculation complexity is high, and feature screening is carried out during original data processing; meanwhile, in order to reduce the error of a calculation result, the environment temperature is used as an intermediate quantity, irradiance calculation is performed based on a two-step estimation model, and the method has a certain guiding significance for researching the operation characteristics of the photovoltaic power station, reasonably planning layout places and monitoring operation states.
As shown in fig. 6, an embodiment of the present invention provides a real-time calculation device for solar irradiation intensity of a photovoltaic power station, where the real-time calculation device for solar irradiation intensity of a photovoltaic power station includes:
an acquisition module 601, configured to acquire operation data of a photovoltaic power station;
the extracting module 602 is configured to perform feature extraction on the operation data to obtain feature data;
a generating module 603, configured to perform data modeling on the feature data, and generate an estimated ambient temperature value;
the processing module 604 is configured to obtain an estimated solar irradiance value of the photovoltaic power station based on the estimated ambient temperature value.
Optionally, the acquiring module 601 includes:
the collecting sub-module is used for collecting operation data parameters of the photovoltaic power station;
and the first processing sub-module is used for carrying out data processing on the operation data parameters to obtain the operation data of the photovoltaic power station.
Optionally, the extracting module 602 includes:
the extraction sub-module is used for extracting the characteristics of the operation data to obtain a characteristic data set;
and the second processing sub-module is used for carrying out data dimension reduction on the characteristic data set to obtain characteristic data.
Optionally, the extracting submodule includes:
the acquisition unit is used for acquiring mutual information between the output power of the power station and the electrical characteristic quantity in the operation data;
and the determining unit is used for determining the characteristic data set when the mutual information reaches a preset maximum value.
Optionally, the second processing sub-module includes:
the processing unit is used for carrying out feature calculation on the feature data set through a preset algorithm to obtain a feature subset;
a first determining unit configured to determine, based on the feature subset, whether a feature number of the subset reaches n;
and the second determining unit is used for determining the characteristic data if the characteristic quantity of the subset reaches n.
Optionally, the generating module 603 includes:
the third processing sub-module is used for carrying out normalization processing on the characteristic data to obtain processed characteristic data;
a fourth processing sub-module, configured to perform initialization processing on the processed feature data to obtain initialization data;
the determining submodule is used for carrying out iterative computation on the initialization data and determining initialization data parameters;
the first generation sub-module is used for carrying out data modeling on the initialized data parameters through a preset prediction model to generate an environment temperature estimated value.
Optionally, the processing module 604 includes:
the correction sub-module is used for correcting the operation data of the photovoltaic power station by using the environmental temperature estimated value to obtain corrected operation data;
and the second generation sub-module is used for carrying out data modeling on the corrected operation data through a preset neural network to generate a solar irradiance estimated value of the photovoltaic power station.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 7, including: the system comprises a memory 702, a processor 701 and a computer program stored on the memory 702 and capable of running on the processor 701 for a real-time calculation method of solar irradiation intensity of a photovoltaic power plant, wherein:
the processor 701 is configured to call a computer program stored in the memory 702, and perform the following steps:
acquiring operation data of a photovoltaic power station;
extracting the characteristics of the operation data to obtain characteristic data;
modeling the characteristic data to generate an estimated value of the ambient temperature;
and obtaining a solar irradiance estimation value of the photovoltaic power station based on the environmental temperature estimation value.
Optionally, the step of acquiring the operation data of the photovoltaic power station performed by the processor 701 includes:
collecting operation data parameters of a photovoltaic power station;
and carrying out data processing on the operation data parameters to obtain the operation data of the photovoltaic power station.
Optionally, the step of extracting features from the operation data performed by the processor 701 to obtain feature data includes:
extracting the characteristics of the operation data to obtain a characteristic data set;
and performing data dimension reduction on the characteristic data set to obtain characteristic data.
Optionally, the step of extracting features from the operating data, performed by the processor 701, to obtain a feature data set includes:
acquiring mutual information between the output power of the power station and the electrical characteristic quantity in the operation data;
and when the mutual information reaches a preset maximum value, determining a characteristic data set.
Optionally, the step of performing data dimension reduction on the feature data set performed by the processor 701 to obtain feature data includes:
performing feature calculation on the feature data set through a preset algorithm to obtain a feature subset;
determining, based on the subset of features, whether a number of features of the subset reaches n;
if the feature quantity of the subset reaches n, determining feature data.
Optionally, the step of generating the estimated value of the ambient temperature by data modeling the feature data performed by the processor 701 includes:
normalizing the characteristic data to obtain processed characteristic data;
initializing the processed characteristic data to obtain initialized data;
performing iterative computation on the initialization data to determine initialization data parameters;
and carrying out data modeling on the initialized data parameters through a preset prediction model to generate an environment temperature estimated value.
Optionally, the step of obtaining the solar irradiance estimation value of the photovoltaic power station, which is performed by the processor 701 and is based on the ambient temperature estimation value, includes:
correcting the operation data of the photovoltaic power station by using the environment temperature estimated value to obtain corrected operation data;
and carrying out data modeling on the corrected operation data through a preset neural network to generate a solar irradiance estimation value of the photovoltaic power station.
The electronic equipment provided by the embodiment of the invention can realize each process realized by the photovoltaic power station solar irradiation intensity real-time calculation method in the method embodiment, and can achieve the same beneficial effects. In order to avoid repetition, a description thereof is omitted.
The embodiment of the invention also provides a computer readable storage medium, and a computer program is stored on the computer readable storage medium, and when the computer program is executed by a processor, the method for calculating the solar irradiation intensity of the photovoltaic power station in real time or the method for calculating the solar irradiation intensity of the photovoltaic power station at the application end provided by the embodiment of the invention can achieve the same technical effect, and in order to avoid repetition, the description is omitted here.
Those skilled in the art will appreciate that the processes implementing all or part of the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, and the program may be stored in a computer readable storage medium, and the program may include the processes of the embodiments of the methods as above when executed. The storage medium may be a magnetic disk, an optical disk, a Read-only memory (ROM), a random access memory (Random Access Memory, RAM) or the like.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather, the equivalent structural changes made by the description of the present invention and the accompanying drawings or the direct/indirect application in other related technical fields are included in the scope of the invention.
Claims (10)
1. The real-time calculation method for the solar irradiation intensity of the photovoltaic power station is characterized by comprising the following steps of:
acquiring operation data of a photovoltaic power station;
extracting the characteristics of the operation data to obtain characteristic data;
modeling the characteristic data to generate an estimated value of the ambient temperature;
and obtaining a solar irradiance estimation value of the photovoltaic power station based on the environmental temperature estimation value.
2. The method of claim 1, wherein the step of obtaining operational data of the photovoltaic power plant comprises:
collecting operation data parameters of a photovoltaic power station;
and carrying out data processing on the operation data parameters to obtain the operation data of the photovoltaic power station.
3. The method of claim 2, wherein the step of extracting features from the operational data to obtain feature data comprises:
extracting the characteristics of the operation data to obtain a characteristic data set;
and performing data dimension reduction on the characteristic data set to obtain characteristic data.
4. A method according to claim 3, wherein the step of feature extracting the operational data to obtain a feature data set comprises:
acquiring mutual information between the output power of the power station and the electrical characteristic quantity in the operation data;
and when the mutual information reaches a preset maximum value, determining a characteristic data set.
5. The method of claim 4, wherein the step of performing data dimension reduction on the feature data set to obtain feature data comprises:
performing feature calculation on the feature data set through a preset algorithm to obtain a feature subset;
determining, based on the subset of features, whether a number of features of the subset reaches n;
if the feature quantity of the subset reaches n, determining feature data.
6. The method of claim 5, wherein the step of data modeling the feature data to generate an ambient temperature estimate comprises:
normalizing the characteristic data to obtain processed characteristic data;
initializing the processed characteristic data to obtain initialized data;
performing iterative computation on the initialization data to determine initialization data parameters;
and carrying out data modeling on the initialized data parameters through a preset prediction model to generate an environment temperature estimated value.
7. The method of claim 6, wherein the step of deriving a photovoltaic power plant solar irradiance estimate based on the ambient temperature estimate comprises:
correcting the operation data of the photovoltaic power station by using the environment temperature estimated value to obtain corrected operation data;
and carrying out data modeling on the corrected operation data through a preset neural network to generate a solar irradiance estimation value of the photovoltaic power station.
8. The device for calculating the solar irradiation intensity of the photovoltaic power station in real time is characterized by comprising the following components:
the acquisition module is used for acquiring the operation data of the photovoltaic power station;
the extraction module is used for extracting the characteristics of the operation data to obtain characteristic data;
the generation module is used for carrying out data modeling on the characteristic data and generating an environmental temperature estimated value;
and the processing module is used for obtaining the solar irradiance estimation value of the photovoltaic power station based on the environmental temperature estimation value.
9. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the method for real-time calculation of solar radiation intensity of a photovoltaic power plant as claimed in any one of claims 1 to 7 when the computer program is executed.
10. A computer-readable storage medium, characterized in that it has stored thereon a computer program which, when executed by a processor, implements the steps of the method for real-time calculation of solar radiation intensity of a photovoltaic power plant according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311462296.4A CN117332237A (en) | 2023-11-06 | 2023-11-06 | Real-time calculation method for solar irradiation intensity of photovoltaic power station and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311462296.4A CN117332237A (en) | 2023-11-06 | 2023-11-06 | Real-time calculation method for solar irradiation intensity of photovoltaic power station and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117332237A true CN117332237A (en) | 2024-01-02 |
Family
ID=89277428
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311462296.4A Pending CN117332237A (en) | 2023-11-06 | 2023-11-06 | Real-time calculation method for solar irradiation intensity of photovoltaic power station and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117332237A (en) |
-
2023
- 2023-11-06 CN CN202311462296.4A patent/CN117332237A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sheng et al. | Short-term solar power forecasting based on weighted Gaussian process regression | |
| Bu et al. | A data-driven game-theoretic approach for behind-the-meter PV generation disaggregation | |
| De Giorgi et al. | Assessment of the benefits of numerical weather predictions in wind power forecasting based on statistical methods | |
| CN113805064B (en) | Lithium ion battery pack health state prediction method based on deep learning | |
| Callaway | Sequential reliability forecasting for wind energy: Temperature dependence and probability distributions | |
| CN110672905A (en) | CNN-based self-supervision voltage sag source identification method | |
| CN112115648A (en) | Transformer top layer oil temperature prediction method based on improved deep learning method | |
| Wang et al. | Health diagnosis for lithium-ion battery by combining partial incremental capacity and deep belief network during insufficient discharge profile | |
| CN103973221A (en) | Photovoltaic array parameter identification method based on measured data | |
| CN111509768A (en) | Scene simulation method and system of comprehensive energy system | |
| CN115908051A (en) | Method for determining energy storage capacity of power system | |
| CN113484774A (en) | Lithium battery pack capacity estimation method based on temperature calibration and neural network | |
| CN115840119A (en) | Power cable line degradation diagnostic system and method using database samples | |
| CN113705887A (en) | Data-driven photovoltaic power generation power prediction method and system | |
| Omer et al. | Adaptive boosting and bootstrapped aggregation based ensemble machine learning methods for photovoltaic systems output current prediction | |
| CN117332237A (en) | Real-time calculation method for solar irradiation intensity of photovoltaic power station and related equipment | |
| El Marghichi | A Solar PV Model Parameter Estimation Based on the Enhanced Self-Organization Maps | |
| CN113609456A (en) | Reliability analysis method, system, medium and terminal for photovoltaic charging station of electric vehicle | |
| Mantri et al. | Solar Power Generation Prediction for Better Energy Efficiency using Machine Learning | |
| Ji et al. | Probabilistic optimal power flow considering the dependence of multiple wind farms using pair diffusive kernel copula | |
| Mellit et al. | Application of artificial neural networks for the prediction of a 20-kWp grid-connected photovoltaic plant power output | |
| Bugaje et al. | Influence of input parameters on artificial neural networks for off-grid solar photovoltaic power forecasting | |
| CN118017474A (en) | Wind power prediction method considering wind power plant space-time correlation and prediction error distribution characteristics | |
| CN117540863A (en) | Photovoltaic power interval prediction method based on photovoltaic output fluctuation rate parting | |
| Ahmad | Wind speed prediction analysis using Rayleigh distribution |
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 |