CN112801357B - Solar radiation quantity prediction method, device, equipment and storage medium - Google Patents
Solar radiation quantity prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112801357B CN112801357B CN202110085252.9A CN202110085252A CN112801357B CN 112801357 B CN112801357 B CN 112801357B CN 202110085252 A CN202110085252 A CN 202110085252A CN 112801357 B CN112801357 B CN 112801357B
- Authority
- CN
- China
- Prior art keywords
- data
- model
- machine learning
- solar radiation
- prediction model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000005855 radiation Effects 0.000 title claims abstract description 242
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000010606 normalization Methods 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 22
- 238000007781 pre-processing Methods 0.000 claims abstract description 18
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000010801 machine learning Methods 0.000 claims description 98
- 230000004927 fusion Effects 0.000 claims description 62
- 238000012549 training Methods 0.000 claims description 51
- 238000012795 verification Methods 0.000 claims description 14
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000007405 data analysis Methods 0.000 claims description 6
- 230000007812 deficiency Effects 0.000 claims description 4
- 230000001373 regressive effect Effects 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 abstract description 7
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000000295 complement effect Effects 0.000 description 2
- 238000004134 energy conservation Methods 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Evolutionary Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of weather prediction, and discloses a method, a device, equipment and a storage medium for predicting solar radiation quantity. The method comprises the steps of obtaining the hour-level weather forecast data of each meteorological site, and preprocessing the hour-level weather forecast data to obtain model input data; inputting the model input data into a solar radiation quantity prediction model for analysis so as to obtain predicted radiation data corresponding to each meteorological site; and carrying out inverse normalization processing on the predicted radiation data to obtain the hour-level predicted solar radiation quantity corresponding to each meteorological site. Because the solar radiation quantity prediction model is a model obtained by fusing a plurality of models constructed by different model construction methods, the model constructed according to the current regression is not simple, the prediction accuracy is high, and the solar radiation quantity can be accurately predicted.
Description
Technical Field
The invention relates to the technical field of weather prediction, in particular to a method, a device, equipment and a storage medium for predicting solar radiation quantity.
Background
For a building with energy conservation emphasis and an object to be regulated, the indoor cold and hot load of the building can be predicted based on the sunlight radiation quantity (including the direct solar radiation quantity, the solar scattering quantity and the moon radiation quantity), and then the indoor cold and hot source system of the building is optimized according to the predicted indoor cold and hot load so as to achieve the effect of energy conservation.
However, in practical application, the solar radiation amount is difficult to acquire in time, so that the solar radiation amount needs to be predicted, but the accuracy of estimating the solar radiation amount in the prior art is low, the solar radiation amount is difficult to accurately predict, and the solar radiation amount cannot be accurately predicted, so that the indoor cold and heat source system is difficult to reasonably optimize.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The invention mainly aims to provide a method, a device, equipment and a storage medium for predicting solar radiation quantity, and aims to solve the technical problems that the accuracy of estimating the solar radiation quantity is low and the solar radiation quantity is difficult to accurately predict in the prior art.
To achieve the above object, the present invention provides a solar radiation amount prediction method, the method comprising the steps of:
acquiring the hour-level weather forecast data of each meteorological site, and preprocessing the hour-level weather forecast data to obtain model input data;
inputting the model input data into a solar radiation quantity prediction model for analysis so as to obtain predicted radiation data corresponding to each meteorological site;
and carrying out inverse normalization processing on the predicted radiation data to obtain the hour-level predicted solar radiation quantity corresponding to each meteorological site.
Preferably, before the step of obtaining the hour-level weather forecast data of each meteorological site and preprocessing the hour-level weather forecast data to obtain the model input data, the method further includes:
acquiring hour-level meteorological data and hour-level solar radiation data of each meteorological site, and constructing a sample data set according to the hour-level meteorological data and the hour-level solar radiation data;
preprocessing the sample data set to obtain a training sample set;
constructing a regression prediction model and a machine learning model according to the training sample set;
and determining a solar radiation quantity prediction model according to the training sample set, the regression prediction model and the machine learning model.
Preferably, the step of collecting the hour-level weather data and the hour-level solar radiation data of each weather site and constructing a sample data set according to the hour-level weather data and the hour-level solar radiation data includes:
collecting hour-level meteorological data and hour-level solar radiation data of each meteorological site;
acquiring meteorological acquisition time corresponding to the hour-level meteorological data, and acquiring radiation acquisition time corresponding to the hour-level solar radiation data;
Correlating the hour-level meteorological data with hour-level insolation radiation data based on the radiation acquisition time and the meteorological acquisition time to obtain sample data;
constructing a data set according to the sample data;
and sequencing the sample data in the data set according to the radiation acquisition time or the meteorological acquisition time to obtain a sample data set.
Preferably, the step of preprocessing the sample dataset to obtain a training sample set comprises:
determining a sample data median and a sample data quarter pitch according to the sample data in the sample data set;
and carrying out normalization processing on the sample data in the sample data set according to the median of the sample data and the sample data quarter pitch so as to obtain a training sample set.
Preferably, the step of determining the median of the sample data and the quarter pitch of the sample data according to the sample data in the sample data set comprises:
performing tag coding on each sample data in the sample data set, and performing value deficiency complementation on each sample data in the sample data set after tag coding by using a mean value method to obtain a modified sample data set;
And determining the median of the sample data and the quarter pitch of the sample data according to the sample data in the modified sample data set.
Preferably, the regression prediction model includes: a first regression prediction model, a second regression prediction model, and a third regression prediction model; the machine learning model includes: a first machine learning model and a second machine learning model;
the step of determining a solar radiation amount prediction model according to the training sample set, the regression prediction model and the machine learning model comprises the following steps:
based on a K-fold model fusion algorithm and the training sample set, carrying out model fusion on the first regression prediction model, the second regression prediction model and the third regression prediction model to obtain a fused radiation prediction model;
acquiring preset fusion weights corresponding to the fusion radiation prediction model, the first machine learning model and the second machine learning model respectively;
and fusing the fused radiation prediction model, the fourth radiation prediction model and the fifth radiation prediction model based on the preset fusion weight to obtain a solar radiation quantity prediction model.
Preferably, the step of obtaining the preset fusion weights corresponding to the fused radiation prediction model, the first machine learning model and the second machine learning model respectively includes:
Acquiring a verification sample set, and determining prediction accuracy corresponding to the fusion radiation prediction model, the first machine learning model and the second machine learning model respectively according to the verification sample set;
and determining preset fusion weights respectively corresponding to the fusion radiation prediction model, the first machine learning model and the second machine learning model according to the prediction accuracy.
In addition, in order to achieve the above object, the present invention also provides a solar radiation amount prediction apparatus, which includes the following modules:
the data conversion module is used for acquiring the hour-level weather forecast data of each meteorological site and preprocessing the hour-level weather forecast data to obtain model input data;
the data analysis module is used for inputting the model input data into a solar radiation quantity prediction model for analysis so as to obtain predicted radiation data corresponding to each meteorological site;
and the data processing module is used for carrying out inverse normalization processing on the predicted radiation data so as to obtain the hour-level predicted solar radiation quantity corresponding to each meteorological site.
In addition, in order to achieve the above object, the present invention also proposes a solar radiation amount prediction apparatus including: the solar radiation amount prediction system comprises a processor, a memory and a solar radiation amount prediction program which is stored in the memory and can run on the processor, wherein the solar radiation amount prediction program realizes the steps of the solar radiation amount prediction method when being executed by the processor.
In addition, in order to achieve the above object, the present invention also proposes a computer-readable storage medium having stored thereon a solar radiation amount prediction program that, when executed, implements the steps of the solar radiation amount prediction method as described above.
The method comprises the steps of obtaining the hour-level weather forecast data of each meteorological site, and preprocessing the hour-level weather forecast data to obtain model input data; inputting the model input data into a solar radiation quantity prediction model for analysis so as to obtain predicted radiation data corresponding to each meteorological site; and carrying out inverse normalization processing on the predicted radiation data to obtain the hour-level predicted solar radiation quantity corresponding to each meteorological site. Because the solar radiation quantity prediction model is a model obtained by fusing a plurality of models constructed by different model construction methods, the model constructed according to the current regression is not simple, the prediction accuracy is high, and the solar radiation quantity can be accurately predicted.
Drawings
FIG. 1 is a schematic diagram of an electronic device of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for predicting solar radiation level according to a first embodiment of the present invention;
FIG. 3 is a flowchart of a second embodiment of the solar radiation amount prediction method according to the present invention;
fig. 4 is a block diagram showing the construction of a first embodiment of the solar radiation amount predicting apparatus of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a solar radiation amount prediction apparatus in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the electronic device may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Those skilled in the art will appreciate that the structure shown in fig. 1 is not limiting of the electronic device and may include more or fewer components than shown, or may combine certain components, or may be arranged in different components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a solar radiation amount prediction program may be included in the memory 1005 as one type of storage medium.
In the electronic device shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the electronic device of the present invention may be provided in a solar radiation amount prediction device, where the electronic device invokes a solar radiation amount prediction program stored in the memory 1005 through the processor 1001, and executes the solar radiation amount prediction method provided by the embodiment of the present invention.
An embodiment of the present invention provides a method for predicting solar radiation, and referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of a method for predicting solar radiation according to the present invention.
In this embodiment, the solar radiation amount prediction method includes the following steps:
Step S10: and acquiring the hour-level weather forecast data of each meteorological site, and preprocessing the hour-level weather forecast data to obtain model input data.
It should be noted that, the execution body of the embodiment may be the solar radiation amount prediction device, and the solar radiation amount prediction device may be an electronic device such as a personal computer, a server, or other devices capable of implementing the same or similar functions, which is not limited in this embodiment, and in this embodiment and the embodiments below, the solar radiation amount prediction method of the present invention is described by taking the solar radiation amount prediction device as an example.
It should be noted that the weather station may be a basic weather unit for performing weather observation and developing weather forecast of a single station. The hour-level weather forecast data may be weather data periodically predicted on a one hour period, and the weather data may include: time, wind direction, air pressure, highest air pressure, lowest air pressure, maximum air speed, highest air temperature, lowest air temperature, water vapor pressure, humidity, minimum relative humidity, precipitation, horizontal visibility, total cloud cover, wind power, body temperature and the like. The preprocessing may select the same preprocessing mode as the model training input data to convert the hour level weather forecast data into a data format that the model can input.
Step S20: and inputting the model input data into a solar radiation quantity prediction model for analysis so as to obtain predicted radiation data corresponding to each meteorological site.
The solar radiation amount prediction model may be a model obtained by fusing a plurality of models constructed by different model construction methods and sample data sets, compared with a single model, the solar radiation amount may be predicted more accurately, the sample data sets may be a set of sample data constructed by preprocessing collected weather data of each weather site and solar radiation amount through tag coding, data complement, normalization and the like, and the normalization processing may be performed on the data by using a normalization method such as StandardScaler, minMaxScaler, robustScaler. The input of the solar radiation prediction model may be the preprocessed meteorological data, and the output may be the normalized predicted radiation data. The predicted radiation data may be normalized data, not the final amount of solar radiation.
Step S30: and carrying out inverse normalization processing on the predicted radiation data to obtain the hour-level predicted solar radiation quantity corresponding to each meteorological site.
The predicted radiation data is normalized data, and the predicted radiation data is inversely normalized to obtain the solar radiation amount, i.e. the hour-level predicted solar radiation amount.
For example: assuming that the solar radiation quantity prediction model is obtained by training a sample set normalized by the RobustScaler method, the predicted radiation data can be understood as data normalized by the RobustScaler method, so that the inverse normalization formula can be obtained by deforming the normalization formula of the RobustScaler method:
x i ＝x i '*IQR+median
wherein x is i ' is the value after normalization, i.e. the predicted radiation data, x i Is the original value, i.e. the hour levelThe solar radiation quantity is predicted, mean is the median of sample data calculated according to the sample data in the sample set, and IQR is the quarter-distance of the sample data calculated according to the sample data in the sample set.
In actual use, after the hour-level predicted solar radiation amount corresponding to each meteorological site is obtained, a solar radiation amount prediction report can be generated and displayed according to the hour-level predicted solar radiation amount and the hour-level weather forecast data.
According to the embodiment, the hourly weather forecast data of each meteorological site are obtained, and are preprocessed to obtain model input data; inputting the model input data into a solar radiation quantity prediction model for analysis so as to obtain predicted radiation data corresponding to each meteorological site; and carrying out inverse normalization processing on the predicted radiation data to obtain the hour-level predicted solar radiation quantity corresponding to each meteorological site. Because the solar radiation quantity prediction model is a model obtained by fusing a plurality of models constructed by different model construction methods, the model constructed according to the current regression is not simple, the prediction accuracy is high, and the solar radiation quantity can be accurately predicted.
Referring to fig. 3, fig. 3 is a flowchart of a second embodiment of a solar radiation amount prediction method according to the present invention.
Based on the first embodiment, the solar radiation amount prediction method of the present embodiment further includes, before the step S10:
step S01: and acquiring the hour-level meteorological data and the hour-level solar radiation data of each meteorological site, and constructing a sample data set according to the hour-level meteorological data and the hour-level solar radiation data.
The hour-level meteorological data may be meteorological data periodically collected by a meteorological site with an hour as a period. The hour-level solar radiation data can be solar radiation data periodically collected by a meteorological site with an hour as a period, and the solar radiation data can comprise solar radiation quantity, collection time and the like.
Further, in order to reasonably construct the sample data set, step S01 of this embodiment may include:
collecting hour-level meteorological data and hour-level solar radiation data of each meteorological site; acquiring meteorological acquisition time corresponding to the hour-level meteorological data, and acquiring radiation acquisition time corresponding to the hour-level solar radiation data; correlating the hour-level meteorological data with hour-level insolation radiation data based on the radiation acquisition time and the meteorological acquisition time to obtain sample data; constructing a data set according to the sample data; and sequencing the sample data in the data set according to the radiation acquisition time or the meteorological acquisition time to obtain a sample data set.
The weather collection time may be a time for the weather station to collect the hour-level weather data, and the radiation collection time may be a time for the weather station to collect the hour-level solar radiation data. The sample data may be comprised of hour-level weather data and hour-level solar radiation data.
In actual use, the preset duration threshold may be set according to actual data, for example: 5 seconds, 10 seconds and the like, calculating a time difference between the radiation collection time and the weather collection time, correlating the hour-level solar radiation data and the weather collection time hour-level weather data corresponding to the radiation collection time with the time difference being smaller than a preset time threshold value to form sample data, after correlating the hour-level weather data and the hour-level solar radiation data, obtaining a plurality of sample data, combining the obtained plurality of sample data to obtain a data set, and then, for facilitating observation of a user, sorting the sample data in the data set according to the radiation collection time or the weather collection time at the moment, so as to obtain the sample data and, for example: the sample data in the data set is prioritized according to the radiation acquisition time from large to small or from small to large.
Step S02: the sample data set is preprocessed to obtain a training sample set.
It should be noted that, if the model training is directly performed by using the sample data in the sample data set, because the data is scattered, the accuracy of the training model is difficult to ensure, so that the sample data can be preprocessed before the model is trained, and converted into a training sample suitable for model training, and the accuracy of the trained model can be improved.
Further, in order to facilitate training of the model, step S02 of this embodiment may include:
determining a sample data median and a sample data quarter pitch according to the sample data in the sample data set; and carrying out normalization processing on the sample data in the sample data set according to the median of the sample data and the sample data quarter pitch so as to obtain a training sample set.
It should be noted that the number of bits in the sample data may include a plurality of bits, for example: temperature data median, barometric data median, etc., the sample data quarter pitch may also include a plurality of, for example: temperature data quarter pitch, air pressure data quarter pitch, etc. Normalization processing the sample data in the sample data set by using a RobustScaler method according to the median and the quarter pitch of the sample data.
In practical use, all sample data in the sample data set can be obtained, and the corresponding sample data median and sample data quarter-distance are calculated according to specific data values in the sample data.
For example: the total of 8 sample data in the sample data set, and the temperature data corresponding to each sample data are respectively: 11 ℃, 12 ℃, 15 ℃, 7 ℃, 17 ℃, 6 ℃, 8 ℃, 13 ℃, the temperature data can be firstly ordered from small to large, and the median T of the temperature data can be obtained at the temperature of 7 ℃, 8 ℃, 11 ℃, 12 ℃, 13 ℃, 15 ℃, 17 DEG m Temperature data quarter distance d = (11+12)/2 = 11.5 °c IQR ＝(12+13)/2-(8+7)/2＝5℃。
It should be noted that, when actually processing data, the sample data may be inconvenient to calculate due to different format requirements or acquisition omission during the acquisition of each meteorological site, and even some data may be missing, which may affect the calculation of the median and the quarter distance of the sample data, and may make the normalization of the data difficult or have larger errors.
Further, in order to prevent inconvenient calculation of data and avoid data missing, the step of determining the median of the sample data and the quarter pitch of the sample data according to the sample data in the sample data set according to the embodiment may include:
Performing tag coding on each sample data in the sample data set, and performing value deficiency complementation on each sample data in the sample data set after tag coding by using a mean value method to obtain a modified sample data set; and determining the median of the sample data and the quarter pitch of the sample data according to the sample data in the modified sample data set.
It should be noted that, the tag encoding may be to quantize the data of the sample data, which is similar to the descriptive data and is inconvenient to calculate, and convert the data into data beneficial to calculate, for example: the wind direction is converted into a value of 1-16 by using a hexadecimal method. The method comprises the steps of obtaining the radiation collection time or the weather collection time of sample data of missing data as a mark time by using a mean value method to complement the missing value, and taking the sample data with the minimum time difference between the radiation collection time or the weather collection time and the mark time and the radiation collection time or the weather collection time and the mark time which are larger than the mark time as target sample data. Determining the data type of the missing data in the sample data of the missing data, and complementing the sample data of the missing data by taking the average value of the data which is the same as the data type of the missing data in the target sample data as the missing data.
For example: and the sample data B and the sample data C with the minimum time difference between the weather acquisition time and the sample data A and the weather acquisition time less than the mark time are used as target sample data, the temperature data in the target sample data B and the target sample data C are obtained and the obtained values are used as the temperature data missing in the A to carry out data completion on the sample data A.
Step S03: and constructing a regression prediction model and a machine learning model according to the training sample set.
It should be noted that the regression prediction model may be a model constructed according to a regression algorithm and a training sample set, and the machine learning model may be a model constructed according to a machine learning algorithm. The regression prediction model may be one or more, and the machine learning model may be one or more.
Step S04: and determining a solar radiation quantity prediction model according to the training sample set, the regression prediction model and the machine learning model.
In actual use, the built regression prediction model and the machine learning model can be trained according to the training sample set and subjected to model fusion, so that the solar radiation quantity prediction model can be obtained.
Further, in order to improve the prediction accuracy of the solar radiation amount prediction model, the regression prediction model may include: a first regression prediction model, a second regression prediction model, and a third regression prediction model; the machine learning model includes: a first machine learning model and a second machine learning model.
Step S04 of this embodiment may include:
based on a K-fold model fusion algorithm and the training sample set, carrying out model fusion on the first regression prediction model, the second regression prediction model and the third regression prediction model to obtain a fused radiation prediction model; acquiring preset fusion weights corresponding to the fusion radiation prediction model, the first machine learning model and the second machine learning model respectively; and fusing the fused radiation prediction model, the fourth radiation prediction model and the fifth radiation prediction model based on the preset fusion weight to obtain a solar radiation quantity prediction model.
It should be noted that the first regression prediction model, the second regression prediction model, and the third regression prediction model may be models constructed by three different regression algorithms and training sample sets, and the regression algorithm may be Lasso regression algorithm, ridge regression algorithm, elastic net regression algorithm, or other regression algorithms. The first machine learning model and the second machine learning model may be models constructed by two different machine learning algorithms and training sample sets, and the machine learning algorithm may be a machine learning algorithm such as xgBoost, lightGBM, or may be another machine learning algorithm.
In practical use, the training sample set may be divided into K folds (K is a positive integer, a specific value may be set according to practical needs) according to a K-fold model fusion algorithm (K-folding stacking), and the K-1 folds are used to fit the first-stage regressor (i.e., the first regression prediction model, the second regression prediction model, and the third regression prediction model) in K consecutive cycles. In each round (a total of K rounds), a first-order regressor is then applied to the remaining 1 subset of model fits that have not been used in each iteration. And then, superposing the obtained predictions and providing the obtained predictions as input data for a secondary regressive device, and obtaining a fusion model, namely a fusion radiation prediction model after the training of the secondary regressive device is finished. And then, respectively corresponding preset fusion weights of the fusion radiation prediction model, the first machine learning model and the second machine learning model can be obtained, and the fusion radiation prediction model, the first machine learning model and the second machine learning model are subjected to weighted fusion according to the preset fusion weights, so that the solar radiation quantity prediction model can be obtained. The preset fusion weight can be set according to actual needs.
Further, in order to reasonably set a preset fusion weight, the step of obtaining the preset fusion weights corresponding to the fused radiation prediction model, the first machine learning model and the second machine learning model respectively in this embodiment may include:
Acquiring a verification sample set, and determining prediction accuracy corresponding to the fusion radiation prediction model, the first machine learning model and the second machine learning model respectively according to the verification sample set; and determining preset fusion weights respectively corresponding to the fusion radiation prediction model, the first machine learning model and the second machine learning model according to the prediction accuracy.
It should be noted that, the verification sample set may be a verification sample set obtained by using the same manner as that of the training sample set, and the verification sample is input into the fusion radiation prediction model, the first machine learning model and the second machine learning model to be analyzed, so as to obtain a prediction result, and the prediction accuracy corresponding to each of the fusion radiation prediction model, the first machine learning model and the second machine learning model is obtained by comparing the prediction result with a standard result in the verification sample set.
In practical use, an accuracy threshold may be preset, an accuracy difference value with the accuracy threshold is calculated according to the prediction accuracy corresponding to the fused radiation prediction model, the first machine learning model and the second machine learning model, and a preset fusion weight corresponding to the fused radiation prediction model, the first machine learning model and the second machine learning model is determined according to the accuracy difference value.
For example: an accuracy threshold value is preset to be 0.9, and assuming that the prediction accuracy corresponding to the fusion radiation prediction model, the first machine learning model and the second machine learning model is 0.970, 0.915 and 0.915 respectively, the accuracy difference value can be calculated to be 0.070, 0.015 and 0.015 respectively, the preset fusion weight value corresponding to the fusion radiation prediction model=0.070/(0.070+0.015+0.015) =0.7, and the preset fusion weight value corresponding to the first machine learning model and the second machine learning model=0.015/(0.070+0.015+0.015) =0.15.
According to the embodiment, the hour-level meteorological data and the hour-level solar radiation data of each meteorological site are collected, and a sample data set is constructed according to the hour-level meteorological data and the hour-level solar radiation data; preprocessing the sample data set to obtain a training sample set; constructing a regression prediction model and a machine learning model according to the training sample set; and determining a solar radiation quantity prediction model according to the training sample set, the regression prediction model and the machine learning model. After the sample data set is constructed, the sample data and the data which are unfavorable for calculation are subjected to label coding, and the missing data in the sample data are subjected to complementation, so that the sample data are normalized more accurately, model training is facilitated, a K-fold model fusion algorithm and a reasonable weighting fusion algorithm are adopted when the models are fused, the universality of the solar radiation quantity prediction model obtained by fusion is stronger, the defect of low precision of a single model is avoided, the prediction precision of the solar radiation quantity prediction model is further improved, and the predicted solar radiation quantity is more accurate.
In addition, the embodiment of the invention also provides a storage medium, wherein the storage medium is stored with a solar radiation quantity prediction program, and the solar radiation quantity prediction program realizes the steps of the solar radiation quantity prediction method when being executed by a processor.
Referring to fig. 4, fig. 4 is a block diagram showing the construction of a first embodiment of the solar radiation amount predicting apparatus according to the present invention.
As shown in fig. 4, the solar radiation amount prediction apparatus according to the embodiment of the present invention includes:
the data conversion module 401 is configured to obtain hour-level weather forecast data of each meteorological site, and pre-process the hour-level weather forecast data to obtain model input data;
the data analysis module 402 is configured to input the model input data into a solar radiation amount prediction model for analysis, so as to obtain predicted radiation data corresponding to each meteorological site;
and the data processing module 403 is configured to perform inverse normalization processing on the predicted radiation data, so as to obtain an hour-level predicted solar radiation amount corresponding to each meteorological site.
According to the embodiment, the hourly weather forecast data of each meteorological site are obtained, and are preprocessed to obtain model input data; inputting the model input data into a solar radiation quantity prediction model for analysis so as to obtain predicted radiation data corresponding to each meteorological site; and carrying out inverse normalization processing on the predicted radiation data to obtain the hour-level predicted solar radiation quantity corresponding to each meteorological site. Because the solar radiation quantity prediction model is a model obtained by fusing a plurality of models constructed by different model construction methods, the model constructed according to the current regression is not simple, the prediction accuracy is high, and the solar radiation quantity can be accurately predicted.
Further, the data conversion module 401 is further configured to collect hour-level weather data and hour-level solar radiation data of each weather site, and construct a sample data set according to the hour-level weather data and the hour-level solar radiation data; preprocessing the sample data set to obtain a training sample set; constructing a regression prediction model and a machine learning model according to the training sample set; and determining a solar radiation quantity prediction model according to the training sample set, the regression prediction model and the machine learning model.
Further, the data conversion module 401 is further configured to collect hour-level meteorological data and hour-level solar radiation data of each meteorological site; acquiring meteorological acquisition time corresponding to the hour-level meteorological data, and acquiring radiation acquisition time corresponding to the hour-level solar radiation data; correlating the hour-level meteorological data with hour-level insolation radiation data based on the radiation acquisition time and the meteorological acquisition time to obtain sample data; constructing a data set according to the sample data; and sequencing the sample data in the data set according to the radiation acquisition time or the meteorological acquisition time to obtain a sample data set.
Further, the data conversion module 401 is further configured to determine a median of the sample data and a quarter pitch of the sample data according to the sample data in the sample data set; and carrying out normalization processing on the sample data in the sample data set according to the median of the sample data and the sample data quarter pitch so as to obtain a training sample set.
Further, the data conversion module 401 is further configured to perform tag encoding on each sample data in the sample data set, and perform value deficiency completion on each sample data in the sample data set after tag encoding by using a mean value method, so as to obtain a modified sample data set; and determining the median of the sample data and the quarter pitch of the sample data according to the sample data in the modified sample data set.
Further, the data conversion module 401 is further configured to perform model fusion on the first regression prediction model, the second regression prediction model, and the third regression prediction model based on a K-fold model fusion algorithm and the training sample set, so as to obtain a fused radiation prediction model; acquiring preset fusion weights corresponding to the fusion radiation prediction model, the first machine learning model and the second machine learning model respectively; and fusing the fused radiation prediction model, the fourth radiation prediction model and the fifth radiation prediction model based on the preset fusion weight to obtain a solar radiation quantity prediction model.
Further, the data conversion module 401 is further configured to obtain a verification sample set, and determine prediction accuracies corresponding to the fused radiation prediction model, the first machine learning model, and the second machine learning model respectively according to the verification sample set; and determining preset fusion weights respectively corresponding to the fusion radiation prediction model, the first machine learning model and the second machine learning model according to the prediction accuracy.
It should be understood that the foregoing is illustrative only and is not limiting, and that in specific applications, those skilled in the art may set the invention as desired, and the invention is not limited thereto.
It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
In addition, technical details not described in detail in this embodiment may refer to the method for predicting solar radiation amount provided in any embodiment of the present invention, which is not described herein.
Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory)/RAM, magnetic disk, optical disk) and including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
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 is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (8)
1. A solar radiation amount prediction method, characterized in that the solar radiation amount prediction method comprises the following steps:
acquiring the hour-level weather forecast data of each meteorological site, and preprocessing the hour-level weather forecast data to obtain model input data;
inputting the model input data into a solar radiation quantity prediction model for analysis so as to obtain predicted radiation data corresponding to each meteorological site;
performing inverse normalization processing on the predicted radiation data to obtain an hour-level predicted solar radiation quantity corresponding to each meteorological site;
before the model input data is input into the solar radiation quantity prediction model for analysis to obtain the predicted radiation data corresponding to each meteorological site, the method further comprises the following steps:
determining a solar radiation amount prediction model according to a training sample set, a regression prediction model and a machine learning model, wherein the regression prediction model comprises: the first regression prediction model, the second regression prediction model and the third regression prediction model are models constructed through three different regression algorithms and training sample sets, and the machine learning model comprises: the system comprises a first machine learning model and a second machine learning model, wherein the first machine learning model and the second machine learning model are models constructed through two different machine learning algorithms and training sample sets;
The step of determining the solar radiation quantity prediction model according to the training sample set, the regression prediction model and the machine learning model comprises the following steps:
splitting the training sample set into K folds based on a K-fold model fusion algorithm, and fitting a primary regression device through K-1 folds in K continuous loops, wherein the primary regression device comprises the first regression prediction model, the second regression prediction model and the third regression prediction model;
applying the primary regressor to the remaining 1 folds of model fitting that are not used in each iteration to obtain a predicted value;
the predicted values are overlapped and then input into a secondary regressive for training, and a fused radiation prediction model is obtained;
acquiring preset fusion weights corresponding to the fusion radiation prediction model, the first machine learning model and the second machine learning model respectively;
fusing the fused radiation prediction model, the first machine learning model and the second machine learning model based on the preset fusion weight to obtain a solar radiation quantity prediction model;
the step of obtaining the preset fusion weights respectively corresponding to the fusion radiation prediction model, the first machine learning model and the second machine learning model comprises the following steps:
Acquiring a verification sample set, and determining prediction accuracy corresponding to the fusion radiation prediction model, the first machine learning model and the second machine learning model respectively according to the verification sample set;
and determining preset fusion weights respectively corresponding to the fusion radiation prediction model, the first machine learning model and the second machine learning model according to the prediction accuracy.
2. The method of claim 1, wherein the steps of obtaining and preprocessing hour-level weather forecast data for each meteorological site to obtain model input data are preceded by the steps of:
acquiring hour-level meteorological data and hour-level solar radiation data of each meteorological site, and constructing a sample data set according to the hour-level meteorological data and the hour-level solar radiation data;
preprocessing the sample data set to obtain a training sample set;
constructing a regression prediction model and a machine learning model according to the training sample set;
and determining a solar radiation quantity prediction model according to the training sample set, the regression prediction model and the machine learning model.
3. The method of claim 2, wherein the step of collecting hour-level weather data and hour-level solar radiation data for each weather site and constructing a sample data set from the hour-level weather data and hour-level solar radiation data comprises:
collecting hour-level meteorological data and hour-level solar radiation data of each meteorological site;
acquiring meteorological acquisition time corresponding to the hour-level meteorological data, and acquiring radiation acquisition time corresponding to the hour-level solar radiation data;
correlating the hour-level meteorological data with hour-level insolation radiation data based on the radiation acquisition time and the meteorological acquisition time to obtain sample data;
constructing a data set according to the sample data;
and sequencing the sample data in the data set according to the radiation acquisition time or the meteorological acquisition time to obtain a sample data set.
4. The method of predicting solar radiation level of claim 2, wherein said step of preprocessing said sample dataset to obtain a training sample set comprises:
determining a sample data median and a sample data quarter pitch according to the sample data in the sample data set;
And carrying out normalization processing on the sample data in the sample data set according to the median of the sample data and the sample data quarter pitch so as to obtain a training sample set.
5. The method of claim 4, wherein the step of determining a sample data median and a sample data quarter-distance from the sample data in the sample data set comprises:
performing tag coding on each sample data in the sample data set, and performing value deficiency complementation on each sample data in the sample data set after tag coding by using a mean value method to obtain a modified sample data set;
and determining the median of the sample data and the quarter pitch of the sample data according to the sample data in the modified sample data set.
6. A solar radiation amount prediction apparatus, characterized in that the solar radiation amount prediction apparatus comprises:
the data conversion module is used for acquiring the hour-level weather forecast data of each meteorological site and preprocessing the hour-level weather forecast data to obtain model input data;
the data analysis module is used for inputting the model input data into a solar radiation quantity prediction model for analysis so as to obtain predicted radiation data corresponding to each meteorological site;
The data processing module is used for carrying out inverse normalization processing on the predicted radiation data so as to obtain the hour-level predicted solar radiation quantity corresponding to each meteorological site;
the data analysis module is further configured to determine a solar radiation amount prediction model according to the training sample set, the regression prediction model and the machine learning model, where the regression prediction model includes: the first regression prediction model, the second regression prediction model and the third regression prediction model are models constructed through three different regression algorithms and training sample sets, and the machine learning model comprises: the system comprises a first machine learning model and a second machine learning model, wherein the first machine learning model and the second machine learning model are models constructed through two different machine learning algorithms and training sample sets;
the data analysis module is further used for splitting the training sample set into K folds based on a K-fold model fusion algorithm, and fitting a first-level regression device through K-1 folds in K continuous cycles, wherein the first-level regression device comprises the first regression prediction model, the second regression prediction model and the third regression prediction model; applying the primary regressor to the remaining 1 folds of model fitting that are not used in each iteration to obtain a predicted value; the predicted values are overlapped and then input into a secondary regressive for training, and a fused radiation prediction model is obtained; acquiring preset fusion weights corresponding to the fusion radiation prediction model, the first machine learning model and the second machine learning model respectively; fusing the fused radiation prediction model, the first machine learning model and the second machine learning model based on the preset fusion weight to obtain a solar radiation quantity prediction model;
The data analysis module is further used for acquiring a verification sample set and determining prediction accuracy corresponding to the fusion radiation prediction model, the first machine learning model and the second machine learning model respectively according to the verification sample set; and determining preset fusion weights respectively corresponding to the fusion radiation prediction model, the first machine learning model and the second machine learning model according to the prediction accuracy.
7. A solar radiation amount prediction apparatus, characterized by comprising: a processor, a memory and a solar radiation amount prediction program stored on the memory and executable on the processor, which when executed by the processor, implements the steps of the solar radiation amount prediction method of any one of claims 1-5.
8. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a solar radiation amount prediction program, which when executed, implements the steps of the solar radiation amount prediction method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110085252.9A CN112801357B (en) | 2021-01-21 | 2021-01-21 | Solar radiation quantity prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110085252.9A CN112801357B (en) | 2021-01-21 | 2021-01-21 | Solar radiation quantity prediction method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112801357A CN112801357A (en) | 2021-05-14 |
| CN112801357B true CN112801357B (en) | 2024-04-02 |
Family
ID=75811144
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110085252.9A Active CN112801357B (en) | 2021-01-21 | 2021-01-21 | Solar radiation quantity prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112801357B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113537600B (en) * | 2021-07-20 | 2024-04-02 | 浙江省水利水电勘测设计院有限责任公司 | Medium-long-term precipitation prediction modeling method for whole-process coupling machine learning |
| CN117076847B (en) * | 2023-10-12 | 2023-12-15 | 北京香田智能科技有限公司 | Processing method of sheet-shaped object |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013152156A (en) * | 2012-01-25 | 2013-08-08 | Fuji Electric Co Ltd | Device for calculating amount of solar radiation, and control method and program of device for calculating amount of solar radiation |
| CN104601104A (en) * | 2014-12-22 | 2015-05-06 | 国家电网公司 | Ultra-short term photovoltaic prediction method with ARMA correction based on LSSVM |
| CN107527124A (en) * | 2017-10-13 | 2017-12-29 | 众安信息技术服务有限公司 | The method and apparatus for generating industry basic side combination forecasting |
| CN109284870A (en) * | 2018-10-08 | 2019-01-29 | 南昌大学 | Short-term method for forecasting photovoltaic power generation quantity based on shot and long term Memory Neural Networks |
| CN109635118A (en) * | 2019-01-10 | 2019-04-16 | 博拉网络股份有限公司 | A kind of user's searching and matching method based on big data |
| CN110197298A (en) * | 2019-05-10 | 2019-09-03 | 中国电建集团西北勘测设计研究院有限公司 | The method and device of multi-model sun normal direction radiation prediction based on clustering algorithm |
| CN111597609A (en) * | 2020-04-28 | 2020-08-28 | 马辰龙 | Basic operation unit containing solar radiation and building energy consumption rapid simulation method applying same |
| CN111929748A (en) * | 2020-09-17 | 2020-11-13 | 南京浦蓝大气环境研究院有限公司 | Meteorological element forecasting method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170286838A1 (en) * | 2016-03-29 | 2017-10-05 | International Business Machines Corporation | Predicting solar power generation using semi-supervised learning |
-
2021
- 2021-01-21 CN CN202110085252.9A patent/CN112801357B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013152156A (en) * | 2012-01-25 | 2013-08-08 | Fuji Electric Co Ltd | Device for calculating amount of solar radiation, and control method and program of device for calculating amount of solar radiation |
| CN104601104A (en) * | 2014-12-22 | 2015-05-06 | 国家电网公司 | Ultra-short term photovoltaic prediction method with ARMA correction based on LSSVM |
| CN107527124A (en) * | 2017-10-13 | 2017-12-29 | 众安信息技术服务有限公司 | The method and apparatus for generating industry basic side combination forecasting |
| CN109284870A (en) * | 2018-10-08 | 2019-01-29 | 南昌大学 | Short-term method for forecasting photovoltaic power generation quantity based on shot and long term Memory Neural Networks |
| CN109635118A (en) * | 2019-01-10 | 2019-04-16 | 博拉网络股份有限公司 | A kind of user's searching and matching method based on big data |
| CN110197298A (en) * | 2019-05-10 | 2019-09-03 | 中国电建集团西北勘测设计研究院有限公司 | The method and device of multi-model sun normal direction radiation prediction based on clustering algorithm |
| CN111597609A (en) * | 2020-04-28 | 2020-08-28 | 马辰龙 | Basic operation unit containing solar radiation and building energy consumption rapid simulation method applying same |
| CN111929748A (en) * | 2020-09-17 | 2020-11-13 | 南京浦蓝大气环境研究院有限公司 | Meteorological element forecasting method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112801357A (en) | 2021-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pang et al. | Solar radiation prediction using recurrent neural network and artificial neural network: A case study with comparisons | |
| JP5888640B2 (en) | Photovoltaic power generation prediction apparatus, solar power generation prediction method, and solar power generation prediction program | |
| CN112801357B (en) | Solar radiation quantity prediction method, device, equipment and storage medium | |
| CN103489038A (en) | Photovoltaic ultra-short-term power prediction method based on LM-BP neural network | |
| CN104376389A (en) | Master-slave type micro-grid power load prediction system and master-slave type micro-grid power load prediction method based on load balancing | |
| CN111680841B (en) | Short-term load prediction method, system and terminal equipment based on principal component analysis | |
| de Guia et al. | Using stacked long short term memory with principal component analysis for short term prediction of solar irradiance based on weather patterns | |
| Jiang et al. | Day‐ahead renewable scenario forecasts based on generative adversarial networks | |
| US11830090B2 (en) | Methods and systems for an enhanced energy grid system | |
| CN115660233A (en) | Photovoltaic power prediction method and device, electronic equipment and storage medium | |
| CN116595394A (en) | Training method of wind speed correction model, wind speed prediction method, wind speed prediction equipment and medium | |
| CN115759445A (en) | Machine learning and cloud model-based classified flood random forecasting method | |
| Alharbi et al. | Short-term wind speed and temperature forecasting model based on gated recurrent unit neural networks | |
| Bianchini et al. | Estimation of photovoltaic generation forecasting models using limited information | |
| CN116307287B (en) | Prediction method, system and prediction terminal for effective period of photovoltaic power generation | |
| CN111612648A (en) | Training method and device of photovoltaic power generation prediction model and computer equipment | |
| Zhu et al. | Estimation of wind turbine responses with attention-based neural network incorporating environmental uncertainties | |
| Tehrani et al. | Baseline load forecasting using a Bayesian approach | |
| Zhang et al. | Digital twin empowered PV power prediction | |
| Bazine et al. | Prediction of photovoltaic production for smart grid energy management using hidden Markov model: a study case | |
| CN107124003B (en) | Wind power plant wind energy prediction method and device | |
| Peng et al. | LITHIUM‐ION BATTERY REMAINING USEFUL LIFE ESTIMATION BASED ON ENSEMBLE LEARNING WITH LS‐SVM ALGORITHM | |
| US20190006850A1 (en) | Method for forecasting the power daily generable by a solar inverter | |
| Douak et al. | Design of a multiblock general regression neural network for wind speed prediction in Algeria | |
| Yeh et al. | Short-term load power prediction based deep learning gated recurrent unit in solar power plant |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |