CN115795381A - Method and device for estimating accumulated dust of photovoltaic module - Google Patents
Method and device for estimating accumulated dust of photovoltaic module Download PDFInfo
- Publication number
- CN115795381A CN115795381A CN202211542691.9A CN202211542691A CN115795381A CN 115795381 A CN115795381 A CN 115795381A CN 202211542691 A CN202211542691 A CN 202211542691A CN 115795381 A CN115795381 A CN 115795381A
- Authority
- CN
- China
- Prior art keywords
- index
- photovoltaic module
- dust
- training
- index 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and equipment for estimating dust deposition of a photovoltaic module, which are used for considering different factors influencing the dust deposition of the photovoltaic module, predicting the dust concentration of the photovoltaic module through a random forest model and comprehensively evaluating the dust deposition condition of the photovoltaic module. The method comprises the following steps: determining an index set of a photovoltaic module, wherein the index set comprises index data respectively corresponding to different types of indexes, and the different types of indexes represent different factors influencing the dust deposition of the photovoltaic module; inputting the index set into a random forest model for dust concentration prediction, and outputting dust concentration corresponding to the index set; the random forest model is obtained by training a sample set marked with the dust concentration; and estimating the dust deposition degree of the photovoltaic module according to the dust concentration output by the random forest model.
Description
Technical Field
The invention relates to the technical field of photovoltaic power generation, in particular to a method and equipment for estimating accumulated dust of a photovoltaic module.
Background
The photovoltaic module is used in outdoor environment, and dust particles with different shapes are distributed in atmospheric environment. In practical engineering, dust is easily accumulated on the surface of a cell panel of a photovoltaic module, and the dust has influence on the battery power generation performance and the use safety of the photovoltaic module to different degrees. On one hand, dust falling on the surface of the photovoltaic module can block sunlight, reduce the transmissivity of glass on the surface of the photovoltaic module and reduce solar radiation on the surface of a battery of the photovoltaic module; on the other hand, the dust can absorb solar radiation and convert the solar radiation into self heat energy to block the external heat dissipation of the photovoltaic module cover glass.
The influence factors of the dust deposition of the photovoltaic module are more, the factors of the dust deposition loss of the current photovoltaic module are single, and the dust deposition condition of the photovoltaic module cannot be comprehensively evaluated.
Disclosure of Invention
The invention provides a method and equipment for estimating dust deposition of a photovoltaic module, which are used for considering different factors influencing the dust deposition of the photovoltaic module, predicting the dust concentration of the photovoltaic module through a random forest model and comprehensively evaluating the dust deposition condition of the photovoltaic module.
In a first aspect, an embodiment of the present invention provides a method for estimating a soot deposition of a photovoltaic module, including:
determining an index set of a photovoltaic assembly, wherein the index set comprises index data respectively corresponding to different types of indexes, and the different types of indexes represent different factors influencing the dust deposition of the photovoltaic assembly;
inputting the index set into a random forest model for dust concentration prediction, and outputting dust concentration corresponding to the index set; the random forest model is obtained by training a sample set marked with the dust concentration;
and estimating the dust deposition degree of the photovoltaic module according to the dust concentration output by the random forest model.
According to the method for estimating the dust deposition of the photovoltaic module, the dust deposition condition of the photovoltaic module can be comprehensively estimated by considering various factors influencing the dust deposition of the photovoltaic module and predicting the dust concentration of the photovoltaic module by using the random forest model, and the accuracy of estimating the dust deposition degree of the photovoltaic module is effectively improved.
As an alternative embodiment, the random forest model includes a plurality of decision trees, and the training process of the random forest model includes:
inputting the sample sets labeled with the dust concentration into a plurality of decision trees respectively, and outputting sub-concentration sets predicted by the decision trees respectively;
aggregating the sub-concentration sets predicted by the decision trees respectively to determine an output concentration set;
and determining a loss function value according to the dust concentration marked by the input set and the output concentration set, and training the random forest model according to the loss function value to obtain the trained random forest model.
As an optional embodiment, the determining the index set of the photovoltaic module includes:
acquiring a historical index set of the photovoltaic module in a historical time period, wherein the historical index set comprises index data sequences corresponding to various indexes, and the index data sequences comprise a plurality of index data arranged according to an acquisition time sequence;
for the index data sequence corresponding to each index contained in the historical index set, predicting the index data sequence corresponding to the index by using a time sequence model corresponding to the index to obtain predicted index data corresponding to the index;
and determining the index set of the photovoltaic module according to the prediction index data respectively corresponding to the plurality of indexes.
As an optional implementation manner, the time series model corresponding to the index is obtained by preprocessing a training set and then training the training set by using the preprocessed training set;
the training set comprises a training index data sequence corresponding to the index, and the training index data sequence comprises a plurality of training index data arranged according to an acquisition time sequence.
As an optional implementation, the preprocessing the training set includes:
performing time sequence stationarity check on the training index data sequence contained in the training set;
and if the training index data sequence is a non-stationary time sequence, processing the training index data sequence into a stationary time sequence by using a difference method.
As an optional implementation manner, the training process of the time series model corresponding to the index includes:
determining initial model parameters of the time series model corresponding to the indexes according to the preprocessed autocorrelation function and the preprocessed partial autocorrelation function of the training set;
and training the initial model parameters by utilizing the preprocessed training set to obtain the time sequence model corresponding to the trained indexes.
As an optional implementation manner, after outputting the dust concentration corresponding to the index set, the method further includes:
and determining the dust deposition loss power generation amount of the photovoltaic module according to the dust concentration and the operation information of the photovoltaic module, wherein the dust deposition loss power generation amount represents the power generation amount loss of the photovoltaic module caused by the dust deposition of the photovoltaic module.
As an alternative embodiment, the operational information includes installed capacity and efficiency of the photovoltaic module;
the determining the accumulated dust loss power generation amount of the photovoltaic module according to the dust concentration and the operation information of the photovoltaic module comprises the following steps:
determining the dust deposition loss power generation amount of the photovoltaic module according to the dust concentration, the operation information, the irradiation data of the photovoltaic module and a dust coefficient, wherein the dust coefficient is determined based on the dust type.
In a second aspect, an embodiment of the present invention provides a device for estimating soot deposition of a photovoltaic module, including a processor and a memory, where the memory is used to store a program executable by the processor, and the processor is used to read the program in the memory and execute the following steps:
determining an index set of a photovoltaic assembly, wherein the index set comprises index data respectively corresponding to different types of indexes, and the different types of indexes represent different factors influencing the dust deposition of the photovoltaic assembly;
inputting the index set into a random forest model for dust concentration prediction, and outputting the dust concentration corresponding to the index set; the random forest model is obtained by training a sample set marked with the dust concentration;
and estimating the dust deposition degree of the photovoltaic module according to the dust concentration output by the random forest model.
As an optional implementation, the random forest model comprises a plurality of decision trees, and the processor is configured to perform:
inputting the sample sets labeled with the dust concentration into a plurality of decision trees respectively, and outputting sub-concentration sets predicted by the decision trees respectively;
aggregating the sub-concentration sets predicted by the decision trees respectively to determine an output concentration set;
and determining a loss function value according to the dust concentration marked by the input set and the output concentration set, and training the random forest model according to the loss function value to obtain the trained random forest model.
As an alternative embodiment, the processor is configured to perform:
acquiring a historical index set of the photovoltaic module in a historical time period, wherein the historical index set comprises index data sequences corresponding to various indexes, and the index data sequences comprise a plurality of index data arranged according to an acquisition time sequence;
for the index data sequence corresponding to each index contained in the historical index set, predicting the index data sequence corresponding to the index by using a time sequence model corresponding to the index to obtain predicted index data corresponding to the index;
and determining the index set of the photovoltaic module according to the prediction index data respectively corresponding to the plurality of indexes.
As an optional implementation manner, the time series model corresponding to the index is obtained by preprocessing a training set and then training the training set by using the preprocessed training set;
the training set comprises a training index data sequence corresponding to the index, and the training index data sequence comprises a plurality of training index data arranged according to an acquisition time sequence.
As an alternative embodiment, the treatment appliance is configured to perform:
performing time sequence stationarity check on the training index data sequence contained in the training set;
and if the training index data sequence is a non-stationary time sequence, processing the training index data sequence into a stationary time sequence by using a difference method.
As an alternative embodiment, the treatment appliance is configured to perform:
determining initial model parameters of the time series model corresponding to the indexes according to the preprocessed autocorrelation function and the preprocessed partial autocorrelation function of the training set;
and training the initial model parameters by using the preprocessed training set to obtain the time sequence model corresponding to the trained indexes.
As an optional implementation manner, after outputting the dust concentration corresponding to the index set, the processor is specifically further configured to perform:
and determining the accumulated dust loss power generation amount of the photovoltaic module according to the dust concentration and the operation information of the photovoltaic module, wherein the accumulated dust loss power generation amount represents the power generation amount loss of the photovoltaic module caused by the accumulated dust of the photovoltaic module.
As an alternative embodiment, the operational information includes installed capacity and efficiency of the photovoltaic module; the processor is configured to perform:
determining the dust deposition loss power generation amount of the photovoltaic module according to the dust concentration, the operation information, the irradiation data of the photovoltaic module and a dust coefficient, wherein the dust coefficient is determined based on the dust type.
In a third aspect, an embodiment of the present invention further provides a device for estimating soot deposition of a photovoltaic module, including:
the index determining unit is used for determining an index set of the photovoltaic module, wherein the index set comprises index data respectively corresponding to different types of indexes, and the different types of indexes represent different factors influencing the dust deposition of the photovoltaic module;
the concentration prediction unit is used for inputting the index set into a random forest model to predict the dust concentration and outputting the dust concentration corresponding to the index set; the random forest model is obtained by training a sample set marked with the dust concentration;
and the dust accumulation evaluation unit is used for estimating the dust accumulation degree of the photovoltaic module according to the dust concentration output by the random forest model.
As an optional implementation, the random forest model includes a plurality of decision trees, and the concentration prediction unit is specifically configured to:
inputting the sample sets labeled with the dust concentration into a plurality of decision trees respectively, and outputting the sub-concentration sets predicted by the decision trees respectively;
aggregating the sub-concentration sets predicted by the decision trees respectively to determine an output concentration set;
and determining a loss function value according to the dust concentration marked by the input set and the output concentration set, and training the random forest model according to the loss function value to obtain the trained random forest model.
As an optional implementation manner, the index determining unit is specifically configured to:
acquiring a historical index set of the photovoltaic module in a historical time period, wherein the historical index set comprises index data sequences corresponding to various indexes, and the index data sequences comprise a plurality of index data arranged according to an acquisition time sequence;
for the index data sequence corresponding to each index contained in the historical index set, predicting the index data sequence corresponding to the index by using a time sequence model corresponding to the index to obtain predicted index data corresponding to the index;
and determining the index set of the photovoltaic module according to the prediction index data respectively corresponding to the plurality of indexes.
As an optional implementation manner, the time series model corresponding to the index is obtained by preprocessing a training set and then training the training set by using the preprocessed training set;
the training set comprises a training index data sequence corresponding to the index, and the training index data sequence comprises a plurality of training index data arranged according to an acquisition time sequence.
As an optional implementation manner, the index determining unit is specifically configured to:
performing time sequence stationarity check on the training index data sequence contained in the training set;
and if the training index data sequence is a non-stationary time sequence, processing the training index data sequence into a stationary time sequence by using a difference method.
As an optional implementation manner, the index determining unit is specifically configured to:
determining initial model parameters of the time series model corresponding to the indexes according to the preprocessed autocorrelation function and the preprocessed partial autocorrelation function of the training set;
and training the initial model parameters by utilizing the preprocessed training set to obtain the time sequence model corresponding to the trained indexes.
As an optional implementation manner, after the dust concentration corresponding to the index set is output, the determining a lost electric quantity unit is specifically configured to:
and determining the dust deposition loss power generation amount of the photovoltaic module according to the dust concentration and the operation information of the photovoltaic module, wherein the dust deposition loss power generation amount represents the power generation amount loss of the photovoltaic module caused by the dust deposition of the photovoltaic module.
As an alternative embodiment, the operational information includes installed capacity and efficiency of the photovoltaic module; the unit for determining electric quantity lost is specifically configured to:
determining the dust deposition loss power generation amount of the photovoltaic module according to the dust concentration, the operation information, the irradiation data of the photovoltaic module and a dust coefficient, wherein the dust coefficient is determined based on the dust type.
In a fourth aspect, an embodiment of the present invention further provides a computer storage medium, on which a computer program is stored, where the computer program is used to implement the steps of the method in the first aspect when executed by a processor.
These and other aspects of the present application will be more readily apparent from the following description of the embodiments.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required to be used in the description of the embodiments will be briefly introduced below, and it is apparent that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings may be obtained according to the drawings without inventive labor.
Fig. 1 is a flowchart illustrating an embodiment of a method for estimating soot deposition of a photovoltaic module according to the present invention;
FIG. 2 is a schematic diagram of a time series model prediction process according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating a general flow of soot estimation for a photovoltaic module according to an embodiment of the present invention;
fig. 4 is a schematic diagram of an apparatus for estimating soot deposition of a photovoltaic module according to an embodiment of the present invention;
fig. 5 is a schematic view of an apparatus for estimating soot deposition of a photovoltaic module according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the embodiment of the present invention, the term "and/or" describes an association relationship of an associated object, and indicates that three relationships may exist, for example, a and/or B, and may indicate: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
The application scenario described in the embodiment of the present invention is for more clearly illustrating the technical solution of the embodiment of the present invention, and does not form a limitation on the technical solution provided in the embodiment of the present invention, and it can be known by a person skilled in the art that, with the occurrence of a new application scenario, the technical solution provided in the embodiment of the present invention is also applicable to similar technical problems. In the description of the present invention, the term "plurality" means two or more unless otherwise specified.
In example 1, the photovoltaic module was used in an outdoor environment, and dust particles of various shapes were distributed in an atmospheric environment. In practical engineering, dust is easily accumulated on the surface of a cell panel of a photovoltaic module, and the dust has influence on the battery power generation performance and the use safety of the photovoltaic module to different degrees. On one hand, dust falling on the surface of the photovoltaic module can block sunlight, reduce the transmissivity of glass on the surface of the photovoltaic module and reduce solar radiation on the surface of a battery of the photovoltaic module; on the other hand, the dust can absorb solar radiation and convert the solar radiation into self heat energy to block the external heat dissipation of the photovoltaic module cover glass. The influence factors of the dust deposition of the photovoltaic module are more, the factors of the dust deposition loss of the current photovoltaic module are single, and the dust deposition condition of the photovoltaic module cannot be comprehensively evaluated.
According to the method for estimating the dust deposition of the photovoltaic module, provided by the embodiment of the invention, various influence factors of the dust deposition on the photovoltaic surface are comprehensively considered, and the random forest model is adopted to model the dust deposition index and the dust concentration of the photovoltaic module, so that the estimation is more accurate, the method can be simultaneously suitable for the conditions of more or less samples, and the use method of the random forest model is more flexible.
As shown in fig. 1, a specific implementation of the method for estimating the soot deposition of the photovoltaic module provided by this embodiment is as follows:
in some embodiments, the metrics in the set of metrics include any one or any plurality of:
representing meteorological indexes of meteorological factors; dust indexes representing dust factors; a component index characterizing a photovoltaic component factor.
Optionally, the meteorological parameters include, but are not limited to, any one or more of the following:
reducing the dust amount; rainfall intensity; wind strength; the degree of environmental severity.
Optionally, the dust indicators include, but are not limited to, any one or more of:
the pH value of the dust; the particle size of the dust.
Optionally, the component index includes, but is not limited to, the installation tilt angle of the photovoltaic component.
In the implementation, the comprehensive indexes of dust deposition caused by the photovoltaic module under different factors are considered, and the dust deposition condition of the photovoltaic module is comprehensively evaluated by collecting meteorological factors, dust factors and indexes under the photovoltaic module factors, so that the evaluation accuracy is improved.
In some embodiments, the various indices in the index set for the photovoltaic module are calculated as follows:
the calculation process of the dust reduction amount of the index (1) comprises the following steps:
the dust reduction amount refers to the mass of dust naturally falling to the ground surface per unit area, and is an important factor influencing the surface area dust amount of the photovoltaic module. Measuring dust fall amount and recording PM in air 10 Mass concentration and average relative humidity of air, wherein PM 10 Characterizing the dust concentration in air, 10 denotes the diameter range of the dust/particles. Calculating the dust reduction amount of a battery panel of the photovoltaic module by the following formula:
wherein PM is more than 0 10 A is less than 1, a is taken out by 8;
1＜PM 10 if < 2, a is 4;
1＜PM 10 a is less than 2, a is taken out of 2;
PM 10 more than 10, a is 1;
in formula (1), D represents the dust reduction amount, a represents a calibration coefficient related to the installation inclination angle of the panel of the photovoltaic module, and RH represents the average relative humidity of air. According to the formula, the PM issued by the station can be detected according to the air quality 10 And (4) calculating the dust reduction amount of the solar panel of the photovoltaic module in any time section (for example, 1 day or 1 h).
Index (2) rainfall intensity and wind intensity.
Rainfall and wind can wash away the dust of photovoltaic module, can reduce the dust concentration on photovoltaic module surface especially when rainfall intensity is great, wind strength is great. The rainfall intensity and the wind intensity in the embodiment can be obtained through the real-time rainfall intensity and the real-time wind intensity broadcasted by the weather forecast website.
Index (3) environmental severity.
Because the photovoltaic module is in the northwest area, or there are situations such as building site around, can increase photovoltaic module surface deposition degree, and clean environment can reduce the deposition degree on photovoltaic module surface. The environmental severity in this embodiment may be determined according to a preset level, where the preset level may be obtained by performing manual evaluation based on a plurality of factors, for example, the environmental severity may be divided into the following levels, and a corresponding score is given by a full score of 10:
| good environment | General environment | Poor environment | Poor environment | The environment is severe |
| 10 | 8 | 6 | 4 | 2 |
Index (4) dust pH value and dust particle size.
Because the dust can present different pH values, and pH value can have erosion of different degrees to photovoltaic module's glass apron along with time for the transmission homogeneity of light in the glass apron receives the destruction, thereby leads to photovoltaic module's generating efficiency to reduce, and photovoltaic module's deposition coefficient reduces.
The dust ph value and the dust particle size of the surface dust of the photovoltaic module in this embodiment are obtained by testing the surface dust of the photovoltaic module.
And (5) the installation inclination angle of the photovoltaic module.
In implementation, the installation inclination angle of the photovoltaic module can be determined after the installation of the photovoltaic module is completed.
In some embodiments, the set of metrics for the photovoltaic module is determined by:
step 1) acquiring a historical index set of the photovoltaic module in a historical time period, wherein the historical index set comprises index data sequences corresponding to various indexes, and the index data sequences comprise a plurality of index data arranged according to an acquisition time sequence;
optionally, the historical period refers to a preset period before the current time, and the historical index set includes index data related to the photovoltaic module collected in the historical period, including but not limited to dust fall amount, rainfall intensity, wind intensity, dust ph value, dust particle size, and environmental severity. It should be noted that the historical index set includes index data sequences corresponding to various indexes, each index data sequence is equivalent to a time sequence and includes one kind of index data of the photovoltaic module collected at different times; for example, in the index data sequence corresponding to the dust reduction amount index, each index data represents the dust reduction amount acquired at the corresponding time, and so on, so the historical index set can be regarded as a time sequence set.
Step 2) aiming at the index data sequence corresponding to each index contained in the historical index set, predicting the index data sequence corresponding to the index by using a time sequence model corresponding to the index to obtain predicted index data corresponding to the index;
in the implementation, each index corresponds to one time series model, the index data series corresponding to the index is predicted by using the time series model corresponding to the index, the index data series corresponding to each index is input into the time series model corresponding to the index, and the predicted index data corresponding to the index is output. And finally, obtaining the prediction index data corresponding to each index.
And 3) determining the index set of the photovoltaic module according to the prediction index data respectively corresponding to the multiple indexes.
In implementation, the prediction index data corresponding to the various indexes and the installation inclination angle of the photovoltaic module are determined as the index set of the photovoltaic module.
It should be noted that the historical index set in this embodiment includes index data sequences corresponding to a plurality of indexes, each index corresponds to a time series model for predicting the index data sequence corresponding to the index, and the number of the time series models in this embodiment is determined based on the number of types of the indexes. And respectively predicting index data sequences under different indexes by using the plurality of time sequence models to obtain prediction index data respectively corresponding to the plurality of indexes, and determining the prediction index data as a final index set of the photovoltaic module.
In some embodiments, the time series model corresponding to the index is obtained by preprocessing a training set and then training the training set by using the preprocessed training set;
the training set comprises a training index data sequence corresponding to the index, and the training index data sequence comprises a plurality of training index data arranged according to an acquisition time sequence.
In some embodiments, the training set is preprocessed by:
performing time sequence stationarity check on the training index data sequence contained in the training set;
and if the training index data sequence is a non-stationary time sequence, processing the training index data sequence into a stationary time sequence by using a difference method.
In implementation, ADF (time sequence stationarity) verification may be performed on a training index data sequence included in a training set to obtain a verification value, and if the obtained verification value is smaller than a preset value (e.g., 0.05), it is determined that the training index data sequence is a non-stationary time sequence; and if the obtained check value is greater than or equal to the preset value, determining that the training index data sequence is a stable time sequence.
The time series model in the present embodiment includes, but is not limited to, an ARMA (Auto regressive moving Average) model, an ARIMA model (Auto regressive sum moving Average model), and the like. The time series model is used for predicting information in a future period of time by using data in a past period of time, the time series model depends on the chronological order of the data, and the result generated by inputting the data with the same size into the model after changing the order is different.
In some embodiments, the training process of the time series model corresponding to each index is as follows:
determining initial model parameters of the time series model corresponding to the indexes according to the preprocessed autocorrelation function and the preprocessed partial autocorrelation function of the training set; and training the initial model parameters by utilizing the preprocessed training set to obtain the time sequence model corresponding to the trained indexes.
In implementation, the calculation is performed according to the autocorrelation function and the partial autocorrelation function of the training set, and the initial model parameters are determined according to the calculation result, optionally, the initial model parameters include an initial order of the time series model, and taking the ARMA model as an example, the initial model parameters include an AR (autoregressive) order p, a differential order d, an MA (moving average) order q, and the like; according to an input training set and initial model parameters (AR order p, difference order d and MA order q), ARMA fitting training is carried out, the initial model parameters are continuously adjusted according to the prediction result of the time series model in the training process, the model parameters meeting the prediction requirement are used as the trained model parameters, and the trained time series model is determined according to the trained model parameters.
In some embodiments, the stability of the time series model may also be checked, the time series model passing the check is used as the time series model finally used, and the prediction of the index data sequence of the corresponding index is performed, and the checking method includes, but is not limited to, any one or more of the following:
checking the distribution of the characteristic roots, namely checking whether the characteristic roots of the output result of the time series model are all distributed outside the unit circle, and if so, checking to pass;
the residual error normality test can test the normality of the residual error of the output result of the time sequence model, if the residual error does not meet the normal distribution, the time sequence model has deviation, and the test fails;
and residual white noise check, namely residual errors are white noise sequences which are independent of each other. The residual error of the output result of the time series model can be judged, and whether the time series model has the property of white noise, such as zero mean, equal variance, normality and the like, can be determined according to the judgment result. If the residual error of the time series model has the property of white noise, the time series model can be used for prediction after passing the check.
In implementation, when the time series model is used to predict the index data sequence corresponding to each index, the time series stationarity check may be performed on the input index data sequence first, and if the input index data sequence is a stationarity time sequence, the index data sequence is predicted, otherwise, the index data sequence is predicted after being processed into a stationarity time sequence by using a difference method.
After the index data sequence is predicted by using the time sequence model corresponding to each index, the predicted index data can be obtained, including but not limited to: predicting the dust reduction amount, predicting the rainfall intensity, predicting the wind power intensity, predicting the dust pH value, predicting the dust particle size and predicting the environment severity. And taking a set formed by the prediction index data corresponding to each index as an index set of the photovoltaic module, and determining the dust concentration corresponding to the index set.
As shown in fig. 2, this embodiment further provides a schematic diagram of a time series model prediction process, where the prediction process is as follows:
200, acquiring an index data sequence corresponding to indexes of the photovoltaic module in a historical time period;
optionally, the indexes include but are not limited to dust fall amount, rainfall intensity, wind intensity, dust pH value, dust particle size and environment severity;
optionally, it may also be verified whether useful information in the index data sequence has been extracted, and white noise inspection is performed on the index data sequence, if the useful information in the index data sequence is a white noise sequence, it indicates that the useful information in the index data sequence has been extracted, and the rest is all random disturbance, and cannot be predicted and used.
and step 207, processing the index data sequence into a stable time sequence by using a difference method, and executing step 201.
In implementation, for the time series model corresponding to each index, modeling and prediction can be performed through the above steps, which is not described herein again.
and 102, estimating the dust deposition degree of the photovoltaic module according to the dust concentration output by the random forest model.
It should be noted that the random forest is an idea of ensemble learning. The random forest regression model establishes a plurality of mutually-independent decision trees by randomly extracting samples and characteristics, and obtains a prediction result in a parallel mode. Each decision tree can obtain a prediction result through the extracted samples and characteristics, and the regression prediction result of the whole forest is obtained by integrating the results of all the trees.
In some embodiments, the random forest model comprises a plurality of decision trees, and the training process for the random forest model comprises:
a) inputting the sample sets labeled with the dust concentrations into a plurality of decision trees respectively, and outputting sub-concentration sets predicted by the decision trees respectively;
in implementation, a sample set includes a plurality of sample subsets, each sample subset includes index data corresponding to a plurality of indexes, N sample subsets (which can be repeated) are randomly extracted from the sample set by using a bootstrap method, the N sample subsets are extracted K times to obtain N × K sample subsets, and then M sample indexes are randomly extracted from each sample subset of the N × K sample subsets to obtain an input set containing N × K × M sample indexes; and training the random forest model by using a plurality of input sets, wherein K data sets are mutually independent and equally distributed, and each data set comprises N sample subsets. N, K and M are positive integers, N is smaller than the total number of samples contained in the sample set, and M is smaller than the number of types of indexes contained in the sample subset.
Optionally, the multiple indexes include, but are not limited to, dust reduction amount D, rainfall intensity I, wind power intensity W, dust pH value Ph, dust particle size P, installation inclination angle a of the photovoltaic module, environment severity degree B, and the like.
Process b) aggregating the sub-concentration sets predicted by each of the plurality of decision trees to determine an output concentration set;
optionally, the sub-concentration sets predicted by the decision trees respectively may be averaged, and the average value is determined as the concentration set corresponding to the output of the input set; the final output concentration set may also be determined from the respective predicted sub-concentration sets of the plurality of decision trees in the form of democratic votes.
And c) determining a loss function value according to the dust concentration marked by the input set and the output concentration set, and training the random forest model according to the loss function value to obtain the trained random forest model.
In some embodiments, after outputting the dust concentration corresponding to the index set, the following steps may be further performed:
and determining the dust deposition loss power generation amount of the photovoltaic module according to the dust concentration and the operation information of the photovoltaic module, wherein the dust deposition loss power generation amount represents the power generation amount loss of the photovoltaic module caused by the dust deposition of the photovoltaic module.
In some embodiments, the operational information includes installed capacity and efficiency of the photovoltaic module; determining the power generation capacity of the photovoltaic module due to the ash deposition loss through the following method:
determining the dust deposition loss power generation amount of the photovoltaic module according to the dust concentration, the operation information, the irradiation data of the photovoltaic module and a dust coefficient, wherein the dust coefficient is determined based on the dust type.
In implementation, the power generation capacity of the photovoltaic module is determined by the following formula:
Q loss of power ＝w 1 ×Y * Formula (2) of × sxpaz ×;
in the formula (2), Q Loss of power Representing the power generation capacity of the accumulated dust loss, w 1 Is a coefficient, and w is w when the dust type is loess according to the difference of the dust type 1 Is 0.0144; when the dust type is laterite, w 1 Is 0.0127; when the dust type is kaolin, w 1 Is 0.0317;
Y * representing dust concentration, wherein S is irradiation data of the photovoltaic module; PAZ is the installed capacity of the photovoltaic module; η is the efficiency of the photovoltaic module.
Wherein, Y * Is determined by:
firstly, collecting a historical index set of the photovoltaic module in a historical time period, wherein the historical index set comprises a plurality of indexesThe index data sequences respectively correspond to the index data sequences, and the index data sequences comprise a plurality of index data arranged according to the acquisition time sequence; aiming at an index data sequence corresponding to each index contained in the historical index set, wherein various indexes comprise dust fall amount D, rainfall intensity I, wind power intensity W, dust pH value Ph, dust particle size P and environment severity B; predicting an index data sequence corresponding to the index by using a time sequence model corresponding to the index to obtain predicted index data corresponding to the index; determining the index set of the photovoltaic module according to prediction index data respectively corresponding to the various indexes; the index set comprises predicted dust reduction quantity D, rainfall intensity I, wind power intensity W, dust pH value Ph, dust particle size Ph and environment severity B, the index set also comprises an installation inclination angle of a photovoltaic module, an input matrix X is established according to the dust reduction quantity D, the rainfall intensity I, the wind power intensity W, the dust pH value Ph, the dust particle size Ph, the environment severity B and the installation inclination angle A, the input matrix X is input to a random forest model for prediction as input parameters of a random forest, and the output dust concentration Y is output * 。
As shown in fig. 3, the present embodiment further provides a total flow of estimating the deposition of the photovoltaic module, which is specifically as follows:
300, collecting a historical index set of the photovoltaic module in a historical time period;
the historical index set comprises index data sequences corresponding to various indexes, and the index data sequences comprise a plurality of index data arranged according to the acquisition time sequence;
and step 304, determining the accumulated dust loss power generation amount of the photovoltaic module according to the dust concentration and the installed capacity and efficiency of the photovoltaic module.
Wherein the ash deposition loss power generation amount represents the loss of power generation amount of the photovoltaic module caused by the ash deposition of the photovoltaic module.
In practice, the dust deposition loss power generation amount of the photovoltaic module is determined according to the dust concentration, the operation information, irradiation data of the photovoltaic module and a dust coefficient, wherein the dust coefficient is determined based on the dust type.
The method for estimating the dust deposition of the photovoltaic module provided by this embodiment comprehensively considers various influence factors of the dust deposition on the surface of the photovoltaic module, and selects a series of indexes that influence the dust deposition of the photovoltaic module, including but not limited to: the dust reduction amount, the rainfall intensity, the wind power intensity, the dust pH value, the dust particle size, the installation inclination angle of the photovoltaic module, the environment severity and the like, and a random forest model is adopted to model the dust accumulation index and the dust concentration of the photovoltaic module, so that the evaluation is more accurate. And the indexes of the photovoltaic module, the dust reduction amount, the rainfall intensity, the wind power intensity, the dust pH value, the dust particle size, the installation inclination angle of the photovoltaic module and the environment severity are respectively predicted by combining a time sequence model, the prediction result is input into a trained random forest model to predict the dust concentration, and the power generation amount of the photovoltaic module caused by dust deposition loss is calculated according to the predicted dust concentration, so that the method has practical application significance.
Embodiment 2 is based on the same inventive concept, and the embodiment of the present invention further provides a device for estimating soot deposition of a photovoltaic module, and since the estimation device is an estimation device in the method in the embodiment of the present invention, and the principle of the estimation device for solving the problem is similar to that of the method, the implementation of the estimation device may refer to the implementation of the method, and repeated details are omitted.
As shown in fig. 4, the estimation device comprises a processor 400 and a memory 401, wherein the memory 401 is used for storing programs executable by the processor 400, and the processor 400 is used for reading the programs in the memory 401 and executing the following steps:
determining an index set of a photovoltaic assembly, wherein the index set comprises index data respectively corresponding to different types of indexes, and the different types of indexes represent different factors influencing the dust deposition of the photovoltaic assembly;
inputting the index set into a random forest model for dust concentration prediction, and outputting dust concentration corresponding to the index set; the random forest model is obtained by training a sample set marked with the dust concentration;
and estimating the dust deposition degree of the photovoltaic module according to the dust concentration output by the random forest model.
As an alternative embodiment, the random forest model comprises a plurality of decision trees, and the processor 400 is specifically configured to perform:
inputting the sample sets labeled with the dust concentration into a plurality of decision trees respectively, and outputting the sub-concentration sets predicted by the decision trees respectively;
aggregating the sub-concentration sets predicted by the decision trees to determine an output concentration set;
and determining a loss function value according to the dust concentration marked by the input set and the output concentration set, and training the random forest model according to the loss function value to obtain the trained random forest model.
As an alternative embodiment, the processor 400 is specifically configured to perform:
acquiring a historical index set of the photovoltaic module in a historical time period, wherein the historical index set comprises index data sequences corresponding to various indexes, and the index data sequences comprise a plurality of index data arranged according to an acquisition time sequence;
for the index data sequence corresponding to each index contained in the historical index set, predicting the index data sequence corresponding to the index by using a time sequence model corresponding to the index to obtain predicted index data corresponding to the index;
and determining the index set of the photovoltaic module according to the prediction index data respectively corresponding to the plurality of indexes.
As an optional implementation manner, the time series model corresponding to the index is obtained by preprocessing a training set and then training the training set by using the preprocessed training set;
the training set comprises a training index data sequence corresponding to the index, and the training index data sequence comprises a plurality of training index data arranged according to an acquisition time sequence.
As an alternative implementation, the processor 400 is specifically configured to perform:
performing time sequence stationarity check on the training index data sequence contained in the training set;
and if the training index data sequence is a non-stationary time sequence, processing the training index data sequence into a stationary time sequence by using a difference method.
As an alternative implementation, the processor 400 is specifically configured to perform:
determining initial model parameters of the time series model corresponding to the indexes according to the preprocessed autocorrelation function and the preprocessed partial autocorrelation function of the training set;
and training the initial model parameters by utilizing the preprocessed training set to obtain the time sequence model corresponding to the trained indexes.
As an optional implementation manner, after outputting the dust concentration corresponding to the index set, the processor 400 is further specifically configured to perform:
and determining the dust deposition loss power generation amount of the photovoltaic module according to the dust concentration and the operation information of the photovoltaic module, wherein the dust deposition loss power generation amount represents the power generation amount loss of the photovoltaic module caused by the dust deposition of the photovoltaic module.
As an alternative embodiment, the operation information includes installed capacity and efficiency of the photovoltaic module; the processor 400 is specifically configured to perform:
determining the dust deposition loss power generation amount of the photovoltaic module according to the dust concentration, the operation information, the irradiation data of the photovoltaic module and a dust coefficient, wherein the dust coefficient is determined based on the dust type.
Embodiment 3, based on the same inventive concept, the embodiment of the present invention further provides a device for estimating soot deposition of a photovoltaic module, and since the estimation device is the estimation device in the method in the embodiment of the present invention, and the principle of the estimation device for solving the problem is similar to that of the method, the implementation of the estimation device may refer to the implementation of the method, and repeated details are omitted.
As shown in fig. 5, the apparatus includes:
the index determining unit 500 is configured to determine an index set of the photovoltaic module, where the index set includes index data corresponding to different types of indexes, and the different types represent different factors affecting dust deposition of the photovoltaic module;
a concentration prediction unit 501, configured to input the index set into a random forest model to perform dust concentration prediction, and output a dust concentration corresponding to the index set; the random forest model is obtained by training a sample set marked with the dust concentration;
and the dust accumulation evaluation unit 502 is used for estimating the dust accumulation degree of the photovoltaic module according to the dust concentration output by the random forest model.
As an optional implementation manner, the random forest model includes a plurality of decision trees, and the concentration prediction unit 501 is specifically configured to:
inputting the sample sets labeled with the dust concentration into a plurality of decision trees respectively, and outputting the sub-concentration sets predicted by the decision trees respectively;
aggregating the sub-concentration sets predicted by the decision trees respectively to determine an output concentration set;
and determining a loss function value according to the dust concentration marked by the input set and the output concentration set, and training the random forest model according to the loss function value to obtain the trained random forest model.
As an optional implementation manner, the index determining unit 500 is specifically configured to:
acquiring a historical index set of the photovoltaic module in a historical time period, wherein the historical index set comprises index data sequences corresponding to various indexes, and the index data sequences comprise a plurality of index data arranged according to an acquisition time sequence;
for the index data sequence corresponding to each index contained in the historical index set, predicting the index data sequence corresponding to the index by using a time sequence model corresponding to the index to obtain predicted index data corresponding to the index;
and determining the index set of the photovoltaic module according to the prediction index data respectively corresponding to the plurality of indexes.
As an optional implementation manner, the time series model corresponding to the index is obtained by preprocessing a training set and then training the training set by using the preprocessed training set;
the training set comprises a training index data sequence corresponding to the index, and the training index data sequence comprises a plurality of training index data arranged according to an acquisition time sequence.
As an optional implementation manner, the index determining unit 500 is specifically configured to:
performing time sequence stationarity check on the training index data sequence contained in the training set;
and if the training index data sequence is a non-stationary time sequence, processing the training index data sequence into a stationary time sequence by using a difference method.
As an optional implementation manner, the index determining unit 500 is specifically configured to:
determining initial model parameters of the time series model corresponding to the indexes according to the preprocessed autocorrelation function and the preprocessed partial autocorrelation function of the training set;
and training the initial model parameters by utilizing the preprocessed training set to obtain the time sequence model corresponding to the trained indexes.
As an optional implementation manner, after the outputting the dust concentration corresponding to the index set, the determining a power loss unit is specifically configured to:
and determining the accumulated dust loss power generation amount of the photovoltaic module according to the dust concentration and the operation information of the photovoltaic module, wherein the accumulated dust loss power generation amount represents the power generation amount loss of the photovoltaic module caused by the accumulated dust of the photovoltaic module.
As an alternative embodiment, the operation information includes installed capacity and efficiency of the photovoltaic module; the power loss determining unit is specifically configured to:
determining the dust deposition loss power generation amount of the photovoltaic module according to the dust concentration, the operation information, the irradiation data of the photovoltaic module and a dust coefficient, wherein the dust coefficient is determined based on the dust type.
Based on the same inventive concept, the embodiments of the present disclosure provide a computer storage medium, which includes: computer program code which, when run on a computer, causes the computer to perform a method of estimating soot deposition of a photovoltaic module as any one of the preceding discussion. Because the principle of solving the problem of the computer storage medium is similar to the soot deposition estimation method of the photovoltaic module, the implementation of the computer storage medium can refer to the implementation of the method, and repeated details are not repeated.
In particular implementations, computer storage media may include: various storage media capable of storing program codes, such as a Universal Serial Bus Flash Drive (USB), a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Based on the same inventive concept, the embodiments of the present disclosure further provide a computer program product, which includes: computer program code which, when run on a computer, causes the computer to perform a method of estimating soot formation of a photovoltaic module as any one of the preceding discussions. Because the principle of solving the problems of the computer program product is similar to the soot deposition estimation method of the photovoltaic module, the implementation of the computer program product can refer to the implementation of the method, and repeated details are not repeated.
The computer program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A method for estimating soot deposition of a photovoltaic module is characterized by comprising the following steps:
determining an index set of a photovoltaic assembly, wherein the index set comprises index data respectively corresponding to different types of indexes, and the different types of indexes represent different factors influencing the dust deposition of the photovoltaic assembly;
inputting the index set into a random forest model for dust concentration prediction, and outputting the dust concentration corresponding to the index set; the random forest model is obtained by training a sample set marked with the dust concentration;
and estimating the dust deposition degree of the photovoltaic module according to the dust concentration output by the random forest model.
2. A method as claimed in claim 1, wherein the random forest model comprises a plurality of decision trees, and wherein the training process for the random forest model comprises:
inputting the sample sets labeled with the dust concentration into a plurality of decision trees respectively, and outputting the sub-concentration sets predicted by the decision trees respectively;
aggregating the sub-concentration sets predicted by the decision trees to determine an output concentration set;
and determining a loss function value according to the dust concentration marked by the input set and the output concentration set, and training the random forest model according to the loss function value to obtain the trained random forest model.
3. The method of claim 1, wherein determining the set of metrics for the photovoltaic module comprises:
acquiring a historical index set of the photovoltaic module in a historical time period, wherein the historical index set comprises index data sequences corresponding to various indexes, and the index data sequences comprise a plurality of index data arranged according to an acquisition time sequence;
for the index data sequence corresponding to each index contained in the historical index set, predicting the index data sequence corresponding to the index by using a time sequence model corresponding to the index to obtain predicted index data corresponding to the index;
and determining the index set of the photovoltaic module according to the prediction index data respectively corresponding to the plurality of indexes.
4. The method according to claim 3, wherein the time series model corresponding to the index is obtained by preprocessing a training set and then training the training set by using the preprocessed training set;
the training set comprises a training index data sequence corresponding to the index, and the training index data sequence comprises a plurality of training index data arranged according to an acquisition time sequence.
5. The method of claim 4, wherein preprocessing the training set comprises:
performing time sequence stationarity check on the training index data sequence contained in the training set;
and if the training index data sequence is a non-stationary time sequence, processing the training index data sequence into a stationary time sequence by using a difference method.
6. The method of claim 3, wherein the training process of the time series model corresponding to the index comprises:
determining initial model parameters of the time series model corresponding to the indexes according to the preprocessed autocorrelation function and the preprocessed partial autocorrelation function of the training set;
and training the initial model parameters by utilizing the preprocessed training set to obtain the time sequence model corresponding to the trained indexes.
7. The method according to any one of claims 1 to 6, further comprising, after outputting the dust concentration corresponding to the index set:
and determining the dust deposition loss power generation amount of the photovoltaic module according to the dust concentration and the operation information of the photovoltaic module, wherein the dust deposition loss power generation amount represents the power generation amount loss of the photovoltaic module caused by the dust deposition of the photovoltaic module.
8. The method of claim 7, wherein the operational information includes installed capacity and efficiency of the photovoltaic module;
the determining the accumulated dust loss power generation amount of the photovoltaic module according to the dust concentration and the operation information of the photovoltaic module comprises the following steps:
determining the dust deposition loss power generation amount of the photovoltaic module according to the dust concentration, the operation information, the irradiation data of the photovoltaic module and a dust coefficient, wherein the dust coefficient is determined based on the dust type.
9. An apparatus for estimating soot deposition in a photovoltaic module, the apparatus comprising a processor and a memory, the memory storing a program executable by the processor, the processor being configured to read the program from the memory and to perform the steps of the method of any one of claims 1 to 8.
10. A computer storage medium on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211542691.9A CN115795381A (en) | 2022-12-02 | 2022-12-02 | Method and device for estimating accumulated dust of photovoltaic module |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211542691.9A CN115795381A (en) | 2022-12-02 | 2022-12-02 | Method and device for estimating accumulated dust of photovoltaic module |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115795381A true CN115795381A (en) | 2023-03-14 |
Family
ID=85445294
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211542691.9A Pending CN115795381A (en) | 2022-12-02 | 2022-12-02 | Method and device for estimating accumulated dust of photovoltaic module |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115795381A (en) |
-
2022
- 2022-12-02 CN CN202211542691.9A patent/CN115795381A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108375715B (en) | Power distribution network line fault risk day prediction method and system | |
| CN111539553A (en) | Wind turbine generator fault early warning method based on SVR algorithm and skewness | |
| CN114548509A (en) | Multi-type load joint prediction method and system for multi-energy system | |
| CN116383773A (en) | Data center energy efficiency anomaly detection method, system and medium based on self-adaptive prediction interval | |
| CN115034485A (en) | Wind power interval prediction method and device based on data space | |
| CN116187552A (en) | Abnormality detection method, computing device, and computer storage medium | |
| CN111525615A (en) | Method and system for evaluating output characteristic of mountain photovoltaic power station based on guarantee rate | |
| CN110457821A (en) | Wind power curve Objective Comprehensive Evaluation Method method, apparatus and server | |
| CN110991701A (en) | Wind power plant fan wind speed prediction method and system based on data fusion | |
| CN113988398A (en) | Wind turbine generator power prediction method and device, electronic equipment and storage medium | |
| CN117526274A (en) | New energy power prediction method, electronic equipment and storage medium in extreme climate | |
| CN116823067A (en) | Method and device for determining water quality cleaning state of pipe network and electronic equipment | |
| CN115166625A (en) | Intelligent ammeter error estimation method and device | |
| CN117408394B (en) | Carbon emission factor prediction method and device for electric power system and electronic equipment | |
| CN113486295B (en) | Fourier series-based ozone total amount change prediction method | |
| CN111914424B (en) | Design wind speed value taking method and system based on short-term wind measurement data | |
| CN115795381A (en) | Method and device for estimating accumulated dust of photovoltaic module | |
| CN116933201A (en) | Method and system for identifying illegal electricity utilization behavior of low-voltage charging pile | |
| CN111060755A (en) | Electromagnetic interference diagnosis method and device | |
| CN113408816B (en) | Power grid disaster situation assessment method based on deep neural network | |
| CN115577854A (en) | Quantile regression wind speed interval prediction method based on EEMD-RBF combination | |
| Souza et al. | Evaluation of data based normal behavior models for fault detection in wind turbines | |
| CN110852544B (en) | Reliability evaluation method and device for wind generating set | |
| CN110472801B (en) | Electromagnetic environment assessment method and system for direct-current transmission line | |
| Schreiber et al. | Quantifying the influences on probabilistic wind power forecasts |
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 |