CN116307018A - Wind speed prediction method and system based on WRF mode sensitivity parameter adjustment - Google Patents
Wind speed prediction method and system based on WRF mode sensitivity parameter adjustment Download PDFInfo
- Publication number
- CN116307018A CN116307018A CN202211096010.0A CN202211096010A CN116307018A CN 116307018 A CN116307018 A CN 116307018A CN 202211096010 A CN202211096010 A CN 202211096010A CN 116307018 A CN116307018 A CN 116307018A
- Authority
- CN
- China
- Prior art keywords
- sensitivity
- scheme
- wind speed
- parameter
- physical
- 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
- 230000035945 sensitivity Effects 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012360 testing method Methods 0.000 claims abstract description 22
- 230000005855 radiation Effects 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 13
- 230000000694 effects Effects 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 2
- 238000002474 experimental method Methods 0.000 claims description 2
- 238000004088 simulation Methods 0.000 abstract description 6
- 238000012163 sequencing technique Methods 0.000 abstract description 3
- 238000011160 research Methods 0.000 description 9
- 238000009826 distribution Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 101000585775 Homo sapiens Myoneurin Proteins 0.000 description 1
- 102100030166 Myoneurin Human genes 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Images
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
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/17—Function evaluation by approximation methods, e.g. inter- or extrapolation, smoothing, least mean square method
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Operations Research (AREA)
- Economics (AREA)
- Algebra (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Aerodynamic Tests, Hydrodynamic Tests, Wind Tunnels, And Water Tanks (AREA)
Abstract
The invention provides a wind speed prediction method and a wind speed prediction system based on WRF mode sensibility parameter adjustment, which adopt different alternatives corresponding to seven types of physical parameters of the WRF mode to carry out sensibility tests on a case wind field so as to obtain the sensibility of the seven types of physical parameters; gradually determining the optimal scheme combination of seven types of physical parameters according to the order from large to small of the sensitivity of the various types of physical parameters; and carrying out wind speed prediction on the forecast area based on the optimal physical parameter scheme. And determining the sensitivity of various parameters to wind speed simulation based on two indexes of average absolute error and average root mean square error, performing a parameter sensitivity test, and then gradually establishing an optimal parameter combination from large to small based on sensitivity gradient sequencing.
Description
Technical Field
The invention belongs to the technical field of wind speed prediction, and particularly relates to a wind speed prediction method and system based on WRF mode sensitivity parameter adjustment.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
In actual wind speed prediction research, weather Research and Forecasting (WRF) mode developed by national atmospheric research center (NCAR) is used as one of physical models, and is widely applied to weather forecast research and actual business. Not only is the WRF mode mature, but also codes are open-source, and a large number of domestic scholars conduct a large amount of wind speed forecasting research based on the WRF mode. After weather forecast such as wind speed is realized, the wind field can screen out elements with higher correlation with future power from the recorded data and the forecast data as the input of a power prediction model. After data preprocessing, selecting a proper statistical or artificial intelligent model to predict the future wind power.
The WRF mode adopts a high-degree modularization, parallelization and layering design technology, and can meet the requirements of most mesoscale weather research and forecasting work. The ARW (the Advanced Research WRF) framework in the WRF can be perfectly applied to numerical simulation of regional mode weather phenomenon, because the WRF is a non-static balanced numerical mode, eta coordinates are adopted in the vertical direction, and the great number of physical parameterization schemes contained in the WRF enable the WRF to be used as a regional weather mode to be more flexible and reliable. Simulation and real-time forecasting experiments show that the WRF mode has better performance in forecasting various weathers, and meanwhile, the online completely nested atmospheric air mode is realized, so that the WRF mode has better weather forecasting level and air quality forecasting capability. The parameter categories comprise seven categories of boundary layer, near stratum, micro-physical process, cloud accumulation convection parameter, short wave radiation, long wave radiation and land surface process, each category of parameter comprises a large number of operation schemes, and different scheme combinations can be selected to cope with various complex terrains.
However, in the study of wind speed prediction using WRF mode, there are three problems:
(1) The seven types of physical parameters for determining the WRF simulation effect are not independent, have interaction, and the physical basis is a set of thermodynamic and hydrodynamic equations which are mutually coupled, so that parameter adjustment cannot be carried out on a certain physical parameter alone. Many researches are only focused on experimental analysis of a certain parameter, and focus on parameters which have great influence on wind speed in theory, such as boundary layers, near stratum and the like, and there is still room for improvement in wind speed forecasting accuracy.
(2) The actual application of the WRF mode is an integrated software comprising a plurality of exe files, and along with the running of the weather theory research, in the alternation of the WRF mode version, more schemes are added to improve the original parameter combination, or the improvement of the original scheme can influence the actual effect of the scheme, and the scheme can be abandoned to be replaced by a new scheme.
(3) Production activities of humans change the geographical topography of the ground level, such as tall buildings, which are not updated into static geographical data in time, and there is also a problem of insufficient resolution of modeling geographical data for complex terrain. In addition, the large number of fan operations within a fan can also affect the airflow movement of the area. These all contribute to the geographical deviation of the wind speed forecast.
Based on the analysis of insufficient research at the current stage, a comprehensive and reasonable parameter adjustment strategy is needed for the parameter adjustment problem of WRF wind speed prediction, and the influence of seven types of physical parameters on target area wind speed prediction and the problem of WRF version iteration are fully considered.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a wind speed prediction method and a wind speed prediction system based on WRF mode sensibility parameter adjustment, which are used for determining the sensibility of various parameters to wind speed simulation based on two indexes of MAE and RMSE, carrying out a parameter sensibility test, and then gradually establishing an optimal parameter combination from large to small based on sensibility gradient sequencing.
To achieve the above object, one or more embodiments of the present invention provide the following technical solutions: the wind speed prediction method based on WRF mode sensitivity parameter adjustment is characterized by comprising the following steps of:
carrying out sensitivity tests on the case wind field by adopting different alternatives corresponding to seven types of physical parameters of the WRF mode to obtain the sensitivity of the seven types of physical parameters;
gradually determining the optimal scheme combination of seven types of physical parameters according to the order from large to small of the sensitivity of the various types of physical parameters;
and carrying out wind speed prediction on the forecast area based on the optimal physical parameter scheme.
A second aspect of the present invention provides a wind speed prediction system based on WRF mode sensitivity modulation, comprising:
sensitivity test module: the method comprises the steps of carrying out sensitivity tests on a case wind field by using different alternatives corresponding to seven types of physical parameters of a WRF mode to obtain the sensitivity of the seven types of physical parameters;
the physical parameter scheme determining module is used for gradually determining the optimal scheme of each type of physical parameters according to the order from large to small of the sensitivity of each type of physical parameters;
and the wind speed prediction module is used for predicting the wind speed of the forecast area based on the optimal scheme of each type of physical parameter.
A third aspect of the invention provides a computer readable storage medium storing computer instructions which, when executed by a processor, perform the steps of the method described above.
A fourth aspect of the invention provides an electronic device comprising a memory and a processor and computer instructions stored on the memory and running on the processor, which when executed by the processor, perform the steps of the method described above.
The one or more of the above technical solutions have the following beneficial effects:
in the invention, the scheme specially used for equator and polar region and the scheme to be abandoned are removed before the sensitivity test is carried out, so that the number of the schemes to be selected is reduced, the follow-up parameter adjusting process is simplified, and the workload and the working difficulty are effectively reduced.
In the invention, the sensitivity of various parameters to wind speed simulation is determined based on two indexes of MAE and RMSE, a parameter sensitivity test is carried out, and then the optimal parameter combination is established step by step from large to small based on sensitivity gradient sequencing.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
FIG. 1 is a flow chart of a sensitivity adjustment according to a first embodiment of the present invention;
fig. 2 is a wind farm equipment distribution diagram in accordance with a first embodiment of the present invention.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention.
Embodiments of the invention and features of the embodiments may be combined with each other without conflict.
Example 1
The embodiment discloses a wind speed prediction method based on WRF mode sensitivity parameter adjustment, which is characterized by comprising the following steps:
step 1: carrying out sensitivity tests on the case wind field by adopting different alternatives corresponding to seven types of physical parameters of the WRF mode to obtain the sensitivity of the seven types of physical parameters;
step 2: gradually determining the optimal scheme combination of seven types of physical parameters according to the order from large to small of the sensitivity of the various types of physical parameters;
step 3: and carrying out wind speed prediction on the forecast area based on the optimal physical parameter scheme.
The WRF version 3.9.1 used in this example is given as an example, and the initial parameter combinations are shown in table 1, using the initial parameter combinations as a reference for comparison.
Table 1:
prior to this embodiment step 1, specific studies were based on the manual WRF3.9.1 protocol for the equatorial and polar protocol culled prior to the sensitivity test. Meanwhile, the scheme with the code number (99) is about to be abandoned and does not participate in the test. Finally, confirming the alternative scheme and code number of each type of parameter as follows:
the micro-physical process comprises the following steps: purde-Lin scheme (2); WRF Single-movement 3class scheme (3); WSM5 protocol (4); WSM6 protocol (6); goddard scheme (7); thompson protocol (8).
Long wave radiation RRTM scheme (1); CAM scheme (3); RRTMG long wave scheme (4); new Goddard Long wave scheme (5).
Short wave radiation: dudhia protocol (1); goddard shortwave scheme (2); CMA protocol (3); RRTMG shortwave scheme (4); new Goddard shortwave scheme (5).
Near-stratum: MM5 similarity protocol (1); MYJ Monin-Obukhov scheme (2); QNSE regimen (4); MYNN protocol (5); eta similarity scheme (7); the MM5 similarity scheme is revised (91).
The road surface process comprises the following steps: a 5-layer thermal diffusion scheme (1); noah Liu Mianmo formula (2); a RUC land process mode (3); noah-MP road surface course mode (4); pleim-Xiu Liu Mianmo formula (7); SSiB Liu Mianmo formula (8).
Planetary boundary layer: university of Yonsei protocol (1); MYJ protocol (2); NCEP global forecast System scheme (3); MYN-NL-2.5PBL protocol (5); MYN-NL-3PBL protocol (6); ACM2 PBL scheme (7); shin-Hong protocol (11).
Cloud parameters: kain-Fritsch scheme (1); betts-Miller-Janjic protocol (2); grell-development aggregation scheme (3); arakawa-Schubert protocol (4); grell three-dimensional integrated cloud scheme (5).
In step 2 of this embodiment, the equipment distribution of the case wind farm is shown in fig. 2, which includes 33 fans with 3MW capacity, a anemometer tower, and a booster station. The anemometer tower is positioned at a more central position and can better represent the overall wind speed condition of the wind field.
Since the case wind field is in hilly areas, the equipment distribution is extremely irregular, which increases the difficulty of forecasting. Meanwhile, the wind measuring tower is positioned among four wind speed points, the wind speed average value of four surrounding points is taken as a predicted wind speed in consideration of possible geographical deviation, the wind speed of 4 months in 2020 is taken as a case, a WRF mode is operated to carry out a one-month wind speed prediction test, and the actual wind speed and the predicted wind speed daily average error are counted to complete a parameter sensitivity test in spring of the wind field area.
The sensitivity S is determined by mean absolute error (Mean Absolute Error, MAE) and root mean square error (Root Mean Square Error, RMSE), and represents the influence of such physical parameters on the wind speed forecasting precision of the forecasting area, and the calculation formula is as follows:
S=0.5*(max(MAE)-min(MAE))+0.5*(max(RMSE)-min(RMSE)) (1)
the sensitivity test results are shown in Table 2, with a combined baseline parameter prediction error MAE of 2.272m/s and a RMSE of 3.041m/s.
In this embodiment, the formula (1) is based on the maximum value and the minimum value in one month. For example, max (MAE) is the maximum average error in month 4 of 2020.
As can be seen from table 2, the scheme with the smallest prediction error of the micro-physical process is: a scheme code (8); the scheme with the largest prediction error in the micro-physical process is as follows: scheme code (2).
The scheme with the minimum long-wave radiation forecast error is as follows: a scheme code (5); the scheme with the largest long-wave radiation forecast error is as follows: scheme code (4).
The scheme with the minimum short wave radiation forecast error is as follows: a scheme code (2); the scheme with the largest short wave radiation forecast error is as follows: scheme code (5).
The scheme with the minimum near-stratum prediction error is as follows: a scheme code (2); the scheme with the largest near-stratum prediction error is as follows: scheme code (4).
The scheme with the smallest prediction error in the land process is as follows: a scheme code (1); the scheme with the largest prediction error in the land process is as follows: scheme code (8).
The scheme with the minimum prediction error of the planetary boundary layer is as follows: a scheme code (7); the scheme with the largest prediction error of the planetary boundary layer is as follows: scheme code (11).
The scheme with the minimum error of the cloud parameter forecast is as follows: a scheme code (2); the scheme with the largest error of the cloud parameter forecast is as follows: scheme code (3).
Table 2:
based on the above table 2, it is known that, for the forecast area, the physical parameter with the highest sensitivity is the planetary boundary layer, the sensitivity is 0.332m/s, the lowest sensitivity is the long wave radiation, the sensitivity is 0.101m/s, the sensitivity represents the influence of the physical parameter on wind speed forecast, and the sensitivity gradient of seven types of physical parameters can be obtained according to the result of the forecast test, as shown in table 3.
Table 3:
according to the table 3, it can be known that the sensitivity gradient ordering of each physical parameter of the case wind field adopts a step-by-step optimized parameter selection strategy, and starts from the physical parameter with high sensitivity, and by taking the reference scheme as a reference, all the alternatives of the parameter are operated each time, the scheme with the best forecasting effect is selected as the final forecasting scheme, and after the scheme of the physical parameter is determined, the optimizing of the next physical parameter is continued.
The results of the step-wise optimization of the 7 types of physical parameters are shown in table 4, and each type of physical parameters is determined starting from the planetary boundary layer.
Table 4:
table 4 shows the best-case establishment procedure from the planetary boundary layer to long-wave radiation, with the final case determined for each type of physical parameters: a planetary boundary layer scheme (8); a near-formation plan (5); a microphysics process scheme (8); land process scheme (1); a cloud parameter scheme (4); a short wave radiation scheme (1); a long wave radiation scheme (5). Compared with a reference scheme, the running scheme of the short wave radiation parameters is kept consistent, the error MAE of wind speed forecasting is reduced by 0.333m/s, the RMSE is reduced by 0.443m/s, and compared with the annual average wind speed of 5.15m/s of the wind field, the wind speed forecasting accuracy is improved considerably.
Example two
An object of the present embodiment is to provide a wind speed prediction system based on WRF mode sensitivity modulation, including:
sensitivity test module: the method comprises the steps of carrying out sensitivity tests on a case wind field by using different alternatives corresponding to seven types of physical parameters of a WRF mode to obtain the sensitivity of the seven types of physical parameters;
the physical parameter scheme determining module is used for gradually determining the optimal scheme of each type of physical parameters according to the order from large to small of the sensitivity of each type of physical parameters;
and the wind speed prediction module is used for predicting the wind speed of the forecast area based on the optimal scheme of each type of physical parameter.
In the sensitivity test module, the sensitivity S is determined by MAE and RMSE, and the calculation formula is as follows:
S=0.5*(max(MAE)-min(MAE))+0.5*(max(RMSE)-min(RMSE))
wherein MAE is average absolute error of average of the day; RMSE is the mean square root error.
In the physical parameter scheme determining module, starting from the physical parameter with highest sensitivity, taking a reference scheme as a reference, each time, operating all the alternatives of the physical parameter, selecting the scheme with the best forecasting effect as the final scheme of the physical parameter, continuing to select the next physical parameter, determining the final scheme of the next physical parameter, and sequentially completing the determination of the final scheme of all the physical parameters.
Example III
It is an object of the present embodiment to provide a computing device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, which processor implements the steps of the method described above when executing the program.
Example IV
An object of the present embodiment is to provide a computer-readable storage medium.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above method.
The steps involved in the devices of the second, third and fourth embodiments correspond to those of the first embodiment of the method, and the detailed description of the embodiments can be found in the related description section of the first embodiment. The term "computer-readable storage medium" should be taken to include a single medium or multiple media including one or more sets of instructions; it should also be understood to include any medium capable of storing, encoding or carrying a set of instructions for execution by a processor and that cause the processor to perform any one of the methods of the present invention.
It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented by general-purpose computer means, alternatively they may be implemented by program code executable by computing means, whereby they may be stored in storage means for execution by computing means, or they may be made into individual integrated circuit modules separately, or a plurality of modules or steps in them may be made into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.
Claims (10)
1. The wind speed prediction method based on WRF mode sensitivity parameter adjustment is characterized by comprising the following steps of:
carrying out sensitivity tests on the case wind field by adopting different alternatives corresponding to seven types of physical parameters of the WRF mode to obtain the sensitivity of the seven types of physical parameters;
gradually determining the optimal scheme combination of seven types of physical parameters according to the order from large to small of the sensitivity of the various types of physical parameters;
and carrying out wind speed prediction on the forecast area based on the optimal physical parameter scheme.
2. A method for predicting wind speed based on WRF mode sensitivity modulation as claimed in claim 1, wherein the physical parameter schemes specific to the equator and polar region are eliminated before the sensitivity experiment is performed.
3. The method for predicting wind speed based on WRF mode sensitivity modulation as claimed in claim 1, wherein the sensitivity S is determined by MAE and RMSE, and the calculation formula is:
S=0.5*(max(MAE)-min(MAE))+0.5*(max(RMSE)-min(RMSE))
wherein MAE is the average absolute error of the average day, and RMSE is the average root mean square error of the average day.
4. The wind speed prediction method based on WRF mode sensitivity parameter adjustment according to claim 1, wherein starting from the physical parameter with highest sensitivity, taking a reference scheme as a reference, each time all the alternatives of the physical parameter are operated, selecting the scheme with the best prediction effect as the final scheme of the physical parameter, continuing to select the next physical parameter, determining the final scheme of the next physical parameter, and sequentially completing the determination of the final scheme of all the physical parameters.
5. A method of predicting wind speed based on WRF mode sensitivity modulation as claimed in claim 1, wherein the selected physical parameters include: microphysics, long wave radiation, short wave radiation, near-stratum, pavement process, planetary boundary layer, and cloud accumulation parameters.
6. A WRF mode sensitivity modulation based wind speed prediction system, comprising:
sensitivity test module: the method comprises the steps of carrying out sensitivity tests on a case wind field by using different alternatives corresponding to seven types of physical parameters of a WRF mode to obtain the sensitivity of the seven types of physical parameters;
the physical parameter scheme determining module is used for gradually determining the optimal scheme of each type of physical parameters according to the order from large to small of the sensitivity of each type of physical parameters;
and the wind speed prediction module is used for predicting the wind speed of the forecast area based on the optimal scheme of each type of physical parameter.
7. The WRF mode sensitivity-based wind speed prediction system according to claim 6, wherein in the sensitivity test module, the sensitivity S is determined by MAE and RMSE, and the calculation formula is:
S=0.5*(max(MAE)-min(MAE))+0.5*(max(RMSE)-min(RMSE))
wherein MAE is the average absolute error of the average day, and RMSE is the average root mean square error of the average day.
8. The wind speed prediction system based on WRF mode sensitivity parameter adjustment as claimed in claim 6, wherein in the physical parameter scheme determining module, starting from the physical parameter with highest sensitivity, taking a reference scheme as a reference, each time all alternatives of the physical parameter are operated, selecting the scheme with the best prediction effect as the final scheme of the physical parameter, continuing to select the next physical parameter, determining the final scheme of the next physical parameter, and sequentially completing the determination of the final scheme of all the physical parameters.
9. A computer readable storage medium having stored thereon a computer program, which when executed by a processor performs the steps of a WRF mode-sensitive pitch-shifting based wind speed prediction method according to any of claims 1-7.
10. A processing device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor performs the steps of a WRF mode-sensitive pitch-based wind speed prediction method according to any one of claims 1 to 7 when the program is executed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211096010.0A CN116307018A (en) | 2022-09-08 | 2022-09-08 | Wind speed prediction method and system based on WRF mode sensitivity parameter adjustment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211096010.0A CN116307018A (en) | 2022-09-08 | 2022-09-08 | Wind speed prediction method and system based on WRF mode sensitivity parameter adjustment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116307018A true CN116307018A (en) | 2023-06-23 |
Family
ID=86827427
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211096010.0A Pending CN116307018A (en) | 2022-09-08 | 2022-09-08 | Wind speed prediction method and system based on WRF mode sensitivity parameter adjustment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116307018A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116565864A (en) * | 2023-07-11 | 2023-08-08 | 上海融和元储能源有限公司 | Photovoltaic power generation power forecasting method based on PCA-RBF algorithm |
-
2022
- 2022-09-08 CN CN202211096010.0A patent/CN116307018A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116565864A (en) * | 2023-07-11 | 2023-08-08 | 上海融和元储能源有限公司 | Photovoltaic power generation power forecasting method based on PCA-RBF algorithm |
CN116565864B (en) * | 2023-07-11 | 2023-10-20 | 上海融和元储能源有限公司 | Photovoltaic power generation power forecasting method based on PCA-RBF algorithm |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112348292B (en) | Short-term wind power prediction method and system based on deep learning network | |
CN103268572B (en) | A kind of microcosmic structure method of ten million multikilowatt large-scale wind electricity base wind measurement network | |
CN107909211B (en) | Wind field equivalent modeling and optimization control method based on fuzzy c-means clustering algorithm | |
CN108108836A (en) | A kind of ozone concentration distribution forecasting method and system based on space-time deep learning | |
CN111210082A (en) | Optimized BP neural network algorithm-based precipitation prediction method | |
CN103699944A (en) | Wind and photovoltaic generation power prediction system with multiple prediction modes | |
US20240054267A1 (en) | Method for planning a layout of a renewable energy site | |
CN112862274A (en) | WRF-LES and Deepar combined wind power prediction method | |
CN107230003A (en) | A kind of power forecasting method of grid-connected power generation system | |
CN116307018A (en) | Wind speed prediction method and system based on WRF mode sensitivity parameter adjustment | |
CN118095789B (en) | Cloud computing-based intelligent garden data management method and system | |
CN113988364A (en) | Photovoltaic power output prediction method based on variational modal decomposition and multi-scale down-sampling | |
CN109426901A (en) | Long-term power consumption prediction method and device in one kind | |
CN116305757A (en) | Method for analyzing agricultural non-point source pollution under different scenes based on SWAT and PLUS | |
CN116050163A (en) | Meteorological station-based ecological system water flux calculation method and system | |
Yang et al. | Spatial distribution characteristics and influencing factors of agricultural specialized villages in Guangdong Province, China | |
CN112700349A (en) | Anemometer tower site selection method and device | |
CN113051845A (en) | Method, system, equipment and storage medium for visually evaluating real-time wind resources of in-service mountain wind power plant | |
CN117195449A (en) | Wind farm arrangement optimization method, device, equipment and medium | |
CN117251989A (en) | Meteorological site carbon water flux information determination method, system and electronic equipment | |
CN115983478A (en) | Distributed photovoltaic power generation power prediction analysis method, system, terminal and medium | |
CN115034159A (en) | Power prediction method, device, storage medium and system for offshore wind farm | |
CN115983104A (en) | Wind speed prediction method and device, storage medium and electronic equipment | |
Gan et al. | UDGAN: A new urban design inspiration approach driven by using generative adversarial networks | |
CN112784477A (en) | WRF-LES and BP-PSO-Bagging combined wind power prediction method |
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 |