CN117767285A - Short-term photovoltaic power generation power prediction method, device, storage medium and equipment based on time neighborhood meteorological data - Google Patents
Short-term photovoltaic power generation power prediction method, device, storage medium and equipment based on time neighborhood meteorological data Download PDFInfo
- Publication number
- CN117767285A CN117767285A CN202311734549.9A CN202311734549A CN117767285A CN 117767285 A CN117767285 A CN 117767285A CN 202311734549 A CN202311734549 A CN 202311734549A CN 117767285 A CN117767285 A CN 117767285A
- Authority
- CN
- China
- Prior art keywords
- data
- photovoltaic power
- power generation
- generation power
- neighborhood
- 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
- 238000010248 power generation Methods 0.000 title claims abstract description 62
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 238000012549 training Methods 0.000 claims description 18
- 238000012795 verification Methods 0.000 claims description 17
- 230000005855 radiation Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 10
- 230000002123 temporal effect Effects 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000015654 memory Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
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
- 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
Abstract
The invention discloses a short-term photovoltaic power generation power prediction method, a device, a storage medium and equipment based on time neighborhood meteorological data, belonging to the technical field of photovoltaic power generation power prediction, and comprising the following steps: acquiring solar altitude and K width time neighborhood meteorological data around a certain moment of a photovoltaic power station; inputting solar altitude and K width time neighborhood meteorological data into a trained improved prediction model to obtain photovoltaic power generation power at the moment; improvements to the improved predictive model include: changing input data from single-moment weather data to K-width time neighborhood weather data, setting the number of input nodes to be 1+ (2 x K+1) x n, wherein n is the number of single-moment weather data; according to the invention, an improved prediction model is adopted, the time neighborhood weather data is added in the input data to be changed into the wide time neighborhood weather data, and the time sequence of the weather data is fully considered, so that a more accurate prediction result is obtained.
Description
Technical Field
The invention relates to a short-term photovoltaic power generation power prediction method, device, storage medium and equipment based on time neighborhood meteorological data, and belongs to the technical field of photovoltaic power generation power prediction.
Background
Along with the rapid increase of the installed capacity of the photovoltaic power station, large-scale photovoltaic grid connection is performed, and in order to reduce adverse effects on power consumption of power planning and scheduling caused by inherent intermittence and instability of photovoltaic power generation, the power generation power of a photovoltaic power generation system needs to be predicted as accurately as possible so as to improve the operation reliability of the power system.
The photovoltaic power generation power is influenced by a plurality of factors, and is closely related to factors such as real-time meteorological data, running states and the like besides the data of the power station; when used for power prediction, weather forecast data for a predicted time period is also considered. Due to the limitation of weather forecast data in the geographic space scale and the complexity of weather conditions, unavoidable time sequence exists between the forecast occurrence time of the weather data and the actual occurrence time of the weather data. According to the requirements of a photovoltaic power generation power prediction system, a data point is predicted every 15 minutes, and the prediction system is more difficult to accurately capture short-term weather changes such as short-time storm or storm in a small area, so that the difference between weather prediction data and actual data is larger. Therefore, this method for predicting the photovoltaic power generation power at 15 minutes of small time resolution has been a difficulty.
The existing photovoltaic power generation power prediction technology with higher prediction precision is generally based on a deep learning mode, main influence factors influencing the power generation power are screened out by means of principal component analysis and the like, and then a neural network model such as BP (back propagation neural network) or LSTM (long short-term memory neural network) and the like is built, so that the prediction of the output power of the photovoltaic equipment is realized. The input parameters of the general model comprise weather forecast data of the moment to be predicted, and the generated power data of the moment to be predicted is output. However, due to the time difference between weather forecast data and actual data, the accuracy of the photovoltaic power generation power prediction is still not ideal, namely the prediction result and the actual result are in unavoidable time sequence.
Disclosure of Invention
The invention aims to provide a short-term photovoltaic power generation power prediction method, device, storage medium and equipment based on time neighborhood meteorological data, and solves the problem of low accuracy in the prior art.
In order to achieve the above purpose, the invention is realized by adopting the following technical scheme:
in a first aspect, the present invention provides a method for predicting short-term photovoltaic power generation power based on time neighborhood meteorological data, including:
acquiring solar altitude and K width time neighborhood meteorological data around a certain moment of a photovoltaic power station;
inputting the solar altitude and the K width time neighborhood meteorological data into a trained improved prediction model to obtain photovoltaic power generation power at the moment;
the improvement of the improved prediction model comprises: the input data is changed from single-moment weather data to K-width time neighborhood weather data, the number of input nodes is set to be 1+ (2 x K+1) x n, and n is the number of single-moment weather data.
With reference to the first aspect, further, the prototype of the improved prediction model includes BP and LSTM.
With reference to the first aspect, further, the training includes:
acquiring historical weather forecast data and photovoltaic power generation power of a photovoltaic power station for a plurality of days, wherein the historical weather forecast data comprises forecast total radiation, forecast scattered radiation, forecast direct radiation, forecast temperature and forecast humidity;
the historical weather forecast data and the photovoltaic power generation power are in one-to-one correspondence at the same time, and are divided into a plurality of groups of input data according to a preset time resolution;
adding solar altitude data into the input data, and then preprocessing the input data;
and inputting the preprocessed input data into the improved prediction model for training, so as to obtain a trained improved prediction model.
With reference to the first aspect, further, the preprocessing includes deleting outliers and missing values, and then normalizing the input data.
With reference to the first aspect, further, the training further includes a process of optimizing the value of K:
and respectively setting the values of K to be 1 to a preset threshold value, training and verifying the improved prediction model, and taking the value with the highest accuracy of the verification result from all the values of K as the optimal value of K.
With reference to the first aspect, further, the verifying includes:
dividing the acquired historical weather forecast data and photovoltaic power generation power into a part to serve as a verification set, and verifying the prediction accuracy by using the data in the verification set.
With reference to the first aspect, further, the value of K is 4.
In a second aspect, the present invention also provides a short-term photovoltaic power prediction apparatus based on time neighborhood meteorological data, including:
a data acquisition module configured to: acquiring K width time neighborhood meteorological data around a certain moment of a photovoltaic power station;
a photovoltaic power generation power prediction module configured to: inputting the K width time neighborhood meteorological data into a trained improved prediction model to obtain photovoltaic power generation power at the moment;
the improvement of the improved prediction model comprises: and changing the input data from single-moment weather data to K-width time neighborhood weather data.
In a third aspect, the present invention also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the short-term photovoltaic power generation power prediction method based on temporal neighborhood weather data according to any one of the first aspects.
In a fourth aspect, the present invention also provides a computer device comprising:
a memory for storing instructions;
a processor for executing the instructions to cause the computer device to perform operations implementing the short-term photovoltaic power generation power prediction method based on temporal neighborhood weather data as in any one of the first aspects.
Compared with the prior art, the invention has the following beneficial effects:
according to the short-term photovoltaic power generation power prediction method, device, storage medium and equipment based on the time neighborhood meteorological data, the improved prediction model is adopted, the time neighborhood meteorological data is added in the input data, the single-moment meteorological data are changed into the wide time neighborhood meteorological data, the time succession of the meteorological data is fully considered, a more accurate prediction result is obtained, the more accurate power prediction is finally realized, and the method has the characteristic of good universality.
Drawings
FIG. 1 is one of the flowcharts of a short-term photovoltaic power generation power prediction method based on time neighborhood meteorological data provided by an embodiment of the present invention;
fig. 2 is a second flowchart of a short-term photovoltaic power prediction method based on time neighborhood weather data according to an embodiment of the present invention.
Detailed Description
The present invention will be further described with reference to the accompanying drawings, and the following examples are only for more clearly illustrating the technical aspects of the present invention, and are not to be construed as limiting the scope of the present invention.
Example 1
As shown in fig. 1, the invention provides a short-term photovoltaic power generation power prediction method based on time neighborhood meteorological data, which comprises the following steps:
s1, acquiring solar altitude and K width time neighborhood meteorological data around a certain moment of a photovoltaic power station.
The solar altitude is the solar angle of the time space calculated according to the longitude and latitude of the photovoltaic station and each group of data moment, and is actually a time variable and has strong correlation with the photovoltaic power generation power.
K represents that the meteorological data is obtained by taking K more time point data forwards and backwards from the original time point; the specific input parameters, the original prediction model comprises: the solar altitude and 1 set of meteorological data, the input parameters of the improved predictive model include: solar altitude and 2 x k+1 sets of meteorological data.
S2, inputting the solar altitude and the K width time neighborhood meteorological data into a trained improved prediction model to obtain photovoltaic power generation power at the moment; the improvement of the improved prediction model comprises: the input data is changed from single-moment weather data to K-width time neighborhood weather data, the number of input nodes is set to be 1+ (2 x K+1) x n, and n is the number of single-moment weather data.
The original prediction model can be a neural network model such as BP or LSTM which is mature before, and the proper K value can be found out through the upgrade prediction model, so that the prediction precision of the original model can be improved.
The training comprises the following steps:
acquiring historical weather forecast data and photovoltaic power generation power of a photovoltaic power station for a plurality of days, wherein the historical weather forecast data comprises forecast total radiation, forecast scattered radiation, forecast direct radiation, forecast temperature and forecast humidity;
the historical weather forecast data and the photovoltaic power generation power are in one-to-one correspondence at the same time, and are divided into a plurality of groups of input data according to a preset time resolution;
adding solar altitude data into the input data, and then preprocessing the input data;
and inputting the preprocessed input data into the improved prediction model for training, so as to obtain a trained improved prediction model.
Preprocessing involves deleting outliers and missing values and then normalizing the input data.
Training also includes the process of optimizing the value of K:
and respectively setting the values of K to be 1 to a preset threshold value, training and verifying the improved prediction model, and taking the value with the highest accuracy of the verification result from all the values of K as the optimal value of K.
The verification includes: dividing the acquired historical weather forecast data and photovoltaic power generation power into a part to serve as a verification set, and verifying the prediction accuracy by using the data in the verification set.
In actual verification, the best K4 obtaining effect is found through comprehensive verification of multiple groups of data of multiple photovoltaic stations.
In order to verify the effect of the invention, the power generated in a certain photovoltaic station is actually tested, historical data of 2022, 8 months and 2023, 8 months and one year are extracted from the system as training data, the power generated in 2023, 9 months and 2023, 10 months is predicted, compared with the actual power generated, the prediction accuracy of an original prediction model (K=0) is 93.18%, the prediction accuracy of an improved prediction model (K=4) is 94.07%, and the accuracy is improved by 0.89% compared with that before improvement.
Example 2
As shown in fig. 2, the embodiment of the invention further provides a short-term photovoltaic power generation power prediction method based on time neighborhood meteorological data, which comprises the following steps:
step one, data acquisition and cleaning. And acquiring historical weather forecast data and photovoltaic power generation power data of the photovoltaic power station for a plurality of days. 5 kinds of data with stronger correlation with photovoltaic power generation power are screened from weather forecast data, including: forecasting total radiation, forecasting scattered radiation, forecasting direct radiation, forecasting temperature and forecasting humidity. The weather forecast data and the photovoltaic power generation power data are in one-to-one correspondence at the same time, and the time resolution is 15 minutes, namely a group of data is obtained at every 15 minutes. In addition, a solar altitude data is added in the input data besides weather forecast data, the solar altitude refers to the solar angle of the time space calculated according to the longitude and latitude of the photovoltaic station and each group of data moment, and the solar altitude is actually a time variable and has strong correlation with the photovoltaic power generation power. In order to reduce the undesirable prediction result caused by the non-uniform dimension between the dirty data and the feature data, the feature data needs to be preprocessed, including deleting abnormal values and missing values in the feature data, and normalizing the feature data to obtain a new set of data.
And step two, constructing a prediction model. An original prediction model (K=0) is improved, the input parameters are increased by dynamic variable parameters, and the original single-moment meteorological data is modified into K width time neighborhood meteorological data; k represents that the meteorological data is obtained by taking K more time point data forwards and backwards from the original time point; the specific input parameters, the original model comprises: the solar altitude and 1 set of meteorological data, the input parameters of the improved predictive model include: solar altitude and 2 x k+1 sets of meteorological data. The output parameter is the power value of the power generation at that time. The original prediction model can be a neural network model such as BP or LSTM which is mature before, and the proper K value can be found out through the upgrade prediction model, so that the prediction precision of the original model can be improved.
And thirdly, model training and tuning. The model training and tuning mainly comprises the steps of finding an optimal value of a time neighborhood weather data width parameter K value while training, wherein the time neighborhood weather data width parameter K value represents that weather data is expanded in single-side width, the time neighborhood weather data width parameter K value is the original prediction model when the K value is 0, the K value is 1, and one time point data is added before and after the weather data, so that the number of groups of the weather data in input parameters is 2 x K+1. The method comprises the steps of firstly taking K as 0, generating a model and data, training and verifying to obtain a verification result; and then taking K as 1, 2 and 3, adding 1 each time, generating a model and data, training and verifying to obtain verification results each time, finding out the optimal K value with the highest accuracy of the verification results each time, and taking the model with the optimal K value trained as an inference model. In actual verification, the best K4 obtaining effect is found through comprehensive verification of multiple groups of data of multiple photovoltaic stations.
And step four, model deployment and reasoning. And determining a good model according to the optimal K value, deploying the good model into a prediction system, organizing input data of each time according to the K value during reasoning, loading the optimal K model, and carrying out reasoning prediction to obtain a final photovoltaic power generation power prediction value.
Example 3
The invention provides a short-term photovoltaic power generation power prediction device based on time neighborhood meteorological data, which comprises the following components:
a data acquisition module configured to: acquiring K width time neighborhood meteorological data around a certain moment of a photovoltaic power station;
a photovoltaic power generation power prediction module configured to: inputting the K width time neighborhood meteorological data into a trained improved prediction model to obtain photovoltaic power generation power at the moment;
the improvement of the improved prediction model comprises: and changing the input data from single-moment weather data to K-width time neighborhood weather data.
Example 4
The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a short-term photovoltaic power generation power prediction method based on temporal neighborhood weather data as provided in embodiment 1:
acquiring solar altitude and K width time neighborhood meteorological data around a certain moment of a photovoltaic power station;
inputting the solar altitude and the K width time neighborhood meteorological data into a trained improved prediction model to obtain photovoltaic power generation power at the moment;
the improvement of the improved prediction model comprises: and changing the input data from single-moment weather data to K-width time neighborhood weather data.
Example 5
The present invention also provides a computer device comprising:
a memory for storing instructions;
a processor configured to execute the instructions to cause the computer device to perform operations of implementing a short-term photovoltaic power generation power prediction method based on temporal neighborhood weather data as provided in embodiment 1:
acquiring solar altitude and K width time neighborhood meteorological data around a certain moment of a photovoltaic power station;
inputting the solar altitude and the K width time neighborhood meteorological data into a trained improved prediction model to obtain photovoltaic power generation power at the moment;
the improvement of the improved prediction model comprises: and changing the input data from single-moment weather data to K-width time neighborhood weather data.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application 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, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. 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.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that modifications and variations could be made by those skilled in the art without departing from the technical principles of the present invention, and such modifications and variations should also be regarded as being within the scope of the invention.
Claims (10)
1. The short-term photovoltaic power generation power prediction method based on the time neighborhood meteorological data is characterized by comprising the following steps of:
acquiring solar altitude and K width time neighborhood meteorological data around a certain moment of a photovoltaic power station;
inputting the solar altitude and the K width time neighborhood meteorological data into a trained improved prediction model to obtain photovoltaic power generation power at the moment;
the improvement of the improved prediction model comprises: the input data is changed from single-moment weather data to K-width time neighborhood weather data, the number of input nodes is set to be 1+ (2 x K+1) x n, and n is the number of single-moment weather data.
2. The method of claim 1, wherein the prototypes of the improved predictive model include BP and LSTM.
3. A method of short term photovoltaic power generation power prediction based on temporal neighborhood meteorological data according to claim 1, wherein the training comprises:
acquiring historical weather forecast data and photovoltaic power generation power of a photovoltaic power station for a plurality of days, wherein the historical weather forecast data comprises forecast total radiation, forecast scattered radiation, forecast direct radiation, forecast temperature and forecast humidity;
the historical weather forecast data and the photovoltaic power generation power are in one-to-one correspondence at the same time, and are divided into a plurality of groups of input data according to a preset time resolution;
adding solar altitude data into the input data, and then preprocessing the input data;
and inputting the preprocessed input data into the improved prediction model for training, so as to obtain a trained improved prediction model.
4. A method of short term photovoltaic power generation power prediction based on time neighborhood meteorological data according to claim 3 wherein the preprocessing comprises deleting outliers and missing values and then normalizing the input data.
5. A method of short term photovoltaic power generation power prediction based on temporal neighborhood meteorological data according to claim 3, wherein the training further comprises the process of optimizing the value of K:
and respectively setting the values of K to be 1 to a preset threshold value, training and verifying the improved prediction model, and taking the value with the highest accuracy of the verification result from all the values of K as the optimal value of K.
6. The method for short-term photovoltaic power generation power prediction based on temporal neighborhood weather data of claim 5, wherein the validating comprises:
dividing the acquired historical weather forecast data and photovoltaic power generation power into a part to serve as a verification set, and verifying the prediction accuracy by using the data in the verification set.
7. The short-term photovoltaic power generation power prediction method based on time neighborhood meteorological data according to claim 1, wherein the value of K is 4.
8. A short-term photovoltaic power generation power prediction device based on time neighborhood meteorological data, comprising:
a data acquisition module configured to: acquiring K width time neighborhood meteorological data around a certain moment of a photovoltaic power station;
a photovoltaic power generation power prediction module configured to: inputting the K width time neighborhood meteorological data into a trained improved prediction model to obtain photovoltaic power generation power at the moment;
the improvement of the improved prediction model comprises: and changing the input data from single-moment weather data to K-width time neighborhood weather data.
9. A computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the short term photovoltaic power generation power prediction method based on time neighborhood meteorological data of any of claims 1-7.
10. A computer device, comprising:
a memory for storing instructions;
a processor for executing the instructions to cause the computer device to perform operations implementing the short-term photovoltaic generation power prediction method based on temporal neighborhood weather data according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311734549.9A CN117767285A (en) | 2023-12-18 | 2023-12-18 | Short-term photovoltaic power generation power prediction method, device, storage medium and equipment based on time neighborhood meteorological data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311734549.9A CN117767285A (en) | 2023-12-18 | 2023-12-18 | Short-term photovoltaic power generation power prediction method, device, storage medium and equipment based on time neighborhood meteorological data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117767285A true CN117767285A (en) | 2024-03-26 |
Family
ID=90324869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311734549.9A Pending CN117767285A (en) | 2023-12-18 | 2023-12-18 | Short-term photovoltaic power generation power prediction method, device, storage medium and equipment based on time neighborhood meteorological data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117767285A (en) |
-
2023
- 2023-12-18 CN CN202311734549.9A patent/CN117767285A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102468316B1 (en) | Time series prediction method and apparatus based on past prediction data | |
| CN106570790B (en) | Wind power plant output data restoration method considering wind speed data segmentation characteristics | |
| CN114819374A (en) | Regional new energy ultra-short term power prediction method and system | |
| Kaplan et al. | A novel method based on Weibull distribution for short-term wind speed prediction | |
| CN111709569A (en) | Method and device for predicting and correcting output power of wind power plant | |
| CN115453356B (en) | Power equipment operation state monitoring and analyzing method, system, terminal and medium | |
| CN115034485A (en) | Wind power interval prediction method and device based on data space | |
| CN111461450A (en) | Hydroelectric generating set degradation degree prediction method based on EEMD and L STM | |
| CN113159102A (en) | Multi-time-scale photovoltaic power prediction method and system | |
| CN116599050A (en) | Photovoltaic prediction method and related device based on self-attention mechanism | |
| CN115081597A (en) | Method, system, equipment and medium for performing carbon check by using electricity based on machine learning | |
| CN116976227B (en) | Storm water increasing forecasting method and system based on LSTM machine learning | |
| CN113988398A (en) | Wind turbine generator power prediction method and device, electronic equipment and storage medium | |
| CN113111592A (en) | Short-term wind power prediction method based on EMD-LSTM | |
| CN117218425A (en) | Power generation loss analysis method and system for photovoltaic power station | |
| CN115689067A (en) | Solar irradiance prediction method, device and storage medium | |
| CN117767285A (en) | Short-term photovoltaic power generation power prediction method, device, storage medium and equipment based on time neighborhood meteorological data | |
| CN110555566A (en) | b-spline quantile regression-based photoelectric probability density prediction method | |
| CN117882261A (en) | Predicting grid frequency | |
| CN112669168B (en) | Short-term prediction method for wind power | |
| CN114372615A (en) | Short-term photovoltaic power prediction method and system considering spatial correlation | |
| CN110210657B (en) | Fan power prediction method and system based on single machine model and computer storage medium | |
| Xu et al. | NWP feature selection and GCN-based ultra-short-term wind farm cluster power forecasting method | |
| Chen et al. | Short-term wind power forecasting based on spatial correlation and artificial neural network | |
| CN111178593A (en) | Photovoltaic system output power prediction method and device |
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 |