CN116702068A - Wind speed forecast extremum extraction method and related device for multi-terrain station - Google Patents
Wind speed forecast extremum extraction method and related device for multi-terrain station Download PDFInfo
- Publication number
- CN116702068A CN116702068A CN202310981549.2A CN202310981549A CN116702068A CN 116702068 A CN116702068 A CN 116702068A CN 202310981549 A CN202310981549 A CN 202310981549A CN 116702068 A CN116702068 A CN 116702068A
- Authority
- CN
- China
- Prior art keywords
- wind speed
- data
- forecast
- mode
- speed forecast
- 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.)
- Granted
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 39
- 238000007637 random forest analysis Methods 0.000 claims abstract description 23
- 230000003068 static effect Effects 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims abstract description 18
- 230000005684 electric field Effects 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 11
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 4
- 238000003379 elimination reaction Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 15
- 230000007812 deficiency Effects 0.000 abstract description 3
- 230000008901 benefit Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012876 topography Methods 0.000 description 2
- 238000011144 upstream manufacturing Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/10—Devices for predicting weather conditions
-
- 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
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- 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)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Environmental & Geological Engineering (AREA)
- Probability & Statistics with Applications (AREA)
- Atmospheric Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Ecology (AREA)
- Environmental Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a wind speed forecast extremum extraction method and a related device for a multi-terrain station, wherein the method comprises the following steps: acquiring and splicing small-area topographic data blocks; collecting numerical mode wind speed forecast data, and extracting a strong wind extreme value and a strong wind average value to obtain a wind speed forecast extreme value; interpolation is carried out on the wind speed forecast data to form mode forecast data with the same resolution as that of the small-area topographic data block, and site observation events corresponding to time nodes of the mode forecast data are marked; the observation event containing the label, the high-resolution mode topographic data and the mode forecast data are input into a random forest model for training, the probability value of the occurrence of the extreme wind speed is used as the output result of the model, so that the probability value of the occurrence of the electric field shutdown on the grid point is determined, and the probability value is multiplied with the wind speed forecast data to obtain a wind speed extreme value extraction data set. The method solves the problem that the wind speed risk classification of the existing static terrain is oriented to the representative deficiency of weather process early warning products caused by inaccurate analysis of specific large weather processes.
Description
Technical Field
The application relates to the technical field of meteorological prediction of electric power fields, in particular to a wind speed prediction extremum extraction method and a related device for a multi-terrain station.
Background
The power energy station fields established under different terrains are different in risk resistance to wind disasters. The capability of resisting wind disasters is greatly enhanced when the station yard is influenced by the blocking effect of the lee surface of the terrain under the favorable terrain, and the capability of resisting wind disasters of the station yard is obviously weakened when the station yard is influenced by wind acceleration terrains such as a narrow pipe effect and the like in an unfavorable area of the pad surface under the terrain. Thus, one typically places the historical wind speed extremum for that region into the range of site building risk considerations for that region through historical empirical statistics.
Based on statistical history information, each station has independent wind disaster risk level evaluation indexes, but in the face of different high wind speed weather processes, the station cannot accurately judge whether the current high wind speed process can cause disasters exceeding wind disaster risk level warning. The existing common solution is therefore near the reference yard.
At present, weather forecast is more public welfare forecast for the public, but weather services required in different fields are actually quite different. Specifically, in the face of wind speed and wind forecast data for dynamically evaluating the wind disaster grade of a station, daily average wind speed forecast of main cities of all places is mainly provided by the multi-place meteorological bureau of China, the forecast result updating time frequency is more than 6 hours, and a single point is taken as a representative average wind speed of a nearby area. In this way, the time abrupt change of the wind speed cannot be accurately reflected, and meanwhile, the wind speed forecast of a single point is not strong in representativeness facing the distribution of a plurality of stations in a certain area. The targeted optimization professional meteorological service for meeting the station yard requirements in the new energy field represented by wind power and photovoltaic cannot be realized.
Disclosure of Invention
The application provides a wind speed forecast extremum extraction method and a related device for a multi-terrain station, which are used for solving the problem that the wind speed risk classification of static terrain is oriented to the representative deficiency of weather process early warning products caused by inaccurate analysis of a specific large weather process.
In view of this, the first aspect of the present application provides a method for extracting wind speed forecast extremum for a multi-terrain station, the method comprising:
acquiring small-area topographic data blocks in an area to be extracted of the extremum, and splicing the small-area topographic data blocks to obtain static high-resolution mode topographic data;
collecting numerical mode wind speed forecast data, and extracting a strong wind extreme value and a strong wind average value in the wind speed forecast data to obtain a wind speed forecast extreme value;
performing interpolation processing on the wind speed forecast data to form mode forecast data with the same resolution as the small-area topographic data block, and analyzing and marking observation events in site observation data corresponding to time nodes of the mode forecast data to obtain the observation events marked with successful and failed observation labels;
inputting the observation event, the high-resolution mode topographic data and the mode forecast data containing the label into a random forest model for regression training, and taking a probability value of the occurrence of the extreme wind speed as a final output result of the random forest model;
and determining a probability value of electric field shutdown at the grid point according to the output result, multiplying the probability value with the wind speed forecast data to obtain a wind speed extremum extraction data set corrected by a random forest model, and generating an image product from the wind speed extremum extraction data set.
Optionally, the obtaining the small area topographic data blocks in the to-be-extracted area of the extremum, and splicing the small area topographic data blocks to obtain the static high resolution mode topographic data specifically includes:
generating small-area topographic data blocks in an extremum to-be-extracted area through an initialization module SI of a CMA-GD mode system numerical mode, wherein the horizontal resolution of each small-area topographic data block is 100m x 100m;
and performing null value elimination processing on a plurality of groups of data edges through an adaptive CloughTocher interpolation scheme, and splicing all small-area topographic data blocks to obtain static topographic data in a high-resolution mode.
Optionally, collecting numerical mode wind speed forecast data, and extracting a strong wind extremum and a strong wind average value in the wind speed forecast data to obtain a wind speed forecast extremum, and obtaining the wind speed forecast extremum specifically includes:
collecting numerical mode wind speed forecast data, wherein the wind speed forecast data is hour-by-hour data within 0-72 hours;
and carrying out distribution analysis on different wind speed forecast values on each data grid point according to the stacking arrangement of different time points of the data points in the region of the wind speed forecast data, and determining a strong wind extremum and a strong wind average value to obtain the wind speed forecast extremum.
Optionally, the interpolating the wind speed forecast data to form mode forecast data with the same resolution as the small-area topographic data block specifically includes:
and interpolating the wind speed forecast data with grid point resolution of 3km by using a spline interpolation method rule to a horizontal scale with horizontal resolution of 100m to form mode forecast data with the same resolution as that of the small-area topographic data block.
The second aspect of the application provides a wind speed forecast extremum extraction system for a multi-terrain station, the system comprising:
the acquisition unit is used for acquiring small-area topographic data blocks in the region to be extracted of the extreme value, and splicing the small-area topographic data blocks to obtain static high-resolution mode topographic data;
the collection unit is used for collecting the wind speed forecast data in the numerical mode, extracting a strong wind extreme value and a strong wind average value in the wind speed forecast data, and obtaining a wind speed forecast extreme value;
the interpolation unit is used for carrying out interpolation processing on the wind speed forecast data to form mode forecast data with the same resolution as the small-area topographic data block, analyzing and marking observation events in site observation data corresponding to time nodes of the mode forecast data to obtain the observation events marked with successful and failed observation labels;
the training unit is used for inputting the observation event containing the label, the high-resolution mode terrain data and the mode forecast data into a random forest model for regression training, and taking the probability value of the occurrence of the extreme wind speed as the final output result of the random forest model;
the generation unit is used for determining a probability value of electric field shutdown at a grid point according to the output result, multiplying the probability value with the wind speed forecast data to obtain a wind speed extremum extraction data set corrected by a random forest model, and generating an image product from the wind speed extremum extraction data set.
Optionally, the acquiring unit is specifically configured to:
generating small-area topographic data blocks in an extremum to-be-extracted area through an initialization module SI of a CMA-GD mode system numerical mode, wherein the horizontal resolution of each small-area topographic data block is 100m x 100m;
and performing null value elimination processing on a plurality of groups of data edges through an adaptive CloughTocher interpolation scheme, and splicing all small-area topographic data blocks to obtain static topographic data in a high-resolution mode.
Optionally, the collecting unit is specifically configured to:
collecting numerical mode wind speed forecast data, wherein the wind speed forecast data is hour-by-hour data within 0-72 hours;
and carrying out distribution analysis on different wind speed forecast values on each data grid point according to the stacking arrangement of different time points of the data points in the region of the wind speed forecast data, and determining a strong wind extremum and a strong wind average value to obtain the wind speed forecast extremum.
Optionally, the interpolation unit is specifically configured to:
interpolating the wind speed forecast data with grid point resolution of 3km by using a spline interpolation method rule to a horizontal scale with horizontal resolution of 100m to form mode forecast data with the same resolution as that of the small-area topographic data block;
and analyzing and marking the observation events in the site observation data corresponding to the time nodes of the mode forecast data to obtain the observation events marked with the successful and failed observation labels.
A third aspect of the application provides a wind speed forecast extremum extraction apparatus, the apparatus comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the steps of the wind speed forecast extremum extraction method according to the first aspect according to the instructions in the program code.
A fourth aspect of the present application provides a computer readable storage medium storing program code for executing the wind speed forecast extremum extraction method according to the first aspect above.
From the above technical scheme, the application has the following advantages:
compared with the traditional technical scheme, the wind speed forecast extremum extraction method for the multi-terrain station has the greatest advantage that a wind speed forecast extremum analysis product with ultra-high resolution, namely 100m x 100m horizontal grid point scale, can be generated, and compared with the extremum estimation of a single station single point, the wind speed forecast extremum extraction method is an obvious breakthrough. Meanwhile, due to the advantage of time resolution of the upstream wind speed numerical forecast data, the hour-by-hour forecast data within 0-72 hours are input, so that the extreme value analysis of a specific weather process can be updated more effectively, and the problem that the weather process early warning product is insufficient in representative caused by inaccurate analysis of static topography wind speed risk classification to the specific large weather process is solved.
Drawings
FIG. 1 is a schematic flow chart of a wind speed forecast extremum extraction method for a multi-terrain station provided in an embodiment of the application;
FIG. 2 is a schematic diagram of a fully synthetic terrain data presentation provided in an embodiment of the present application;
fig. 3 is a schematic structural diagram of a wind speed forecast extremum extraction system for a multi-terrain station according to an embodiment of the present application.
Detailed Description
In order to make the present application better understood by those skilled in the art, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1, a method for extracting wind speed forecast extremum for a multi-terrain station according to an embodiment of the present application includes:
step 101, acquiring small-area topographic data blocks in an area to be extracted of an extremum, and splicing the small-area topographic data blocks to obtain static high-resolution mode topographic data;
it should be noted that, static terrain refinement data generation (the whole process is only required to be performed once): generating small-area topographic data blocks in the corresponding areas through an initialization module SI of a CMA-GD mode system numerical mode, wherein the horizontal resolution of each block of data is 100m x 100m, and the difference is only that analysis areas are different; the terrain blocks are then spliced in sequence.
The CMA-GD mode system is developed by a specific mode research and application of Guangzhou tropical ocean meteorological institute of China, and is developed by a domestic advanced semi-Euler semi-Lagrange power framework and has strong three-dimensional atmosphere modeling and forecast data output capability.
It should be further noted that, the present application hopefully obtains the description of the situation closer to the actual terrain by the ultra-high resolution fine terrain data including valleys, canyons and height differences, and the description should conform to the fluctuation of the actual terrain and simultaneously can match with the wind speed forecast data directly output by the mode. However, the area mode has its own maximum bearing capacity, and the large array with the number of cells 12101 x 22601 cannot be converged correctly, so the flow of the present application adopts a method of reconstructing the divided small areas. The interpolation scheme selected during the period is an optimization algorithm provided in a relatively classical python-scipy extension package, and the application environment of the algorithm for data deficiency in a regular grid is quite wide. Finally, the high-precision topographic data information shown in fig. 2 is presented.
As shown in fig. 2, the abscissa and ordinate values respectively represent 12101×22601 grid points of the grid point distribution of the secondary terrain elevation map in the direction, and the total memory data size is about 2.18GB for each variable, so that the data size cannot be directly put into large-scale network training. The present application therefore adds an additional data access format in this section to use the HDF5 format to store these huge data files that need to be read directly. "HDF5" is an abbreviation for "Hierarchical Data Format ver.5". The HDF5 is a comparatively ideal storage format for storing large-scale numerical data, the suffix name of the file is h5, the storage and reading speed is very high, the data can be stored in the file according to a definite hierarchy, the same HDF5 can be regarded as a highly integrated folder, and different types of data can be stored in the folder.
102, collecting numerical mode wind speed forecast data, and extracting a strong wind extreme value and a strong wind average value in the wind speed forecast data to obtain a wind speed forecast extreme value;
after obtaining the static high-resolution mode topographic data, collecting 'mode wind speed forecast data' of the embodiment through a CMA-GD mode system, wherein the time period is hour-by-hour data within 0-72 hours; then, wind speed forecast extremum extraction is carried out: and stacking and arranging data points in the forecast data area according to different time points, carrying out distribution analysis on different wind speed forecast values on each data grid point, defining a maximum value as a strong wind extremum, and defining an average value of more than 50% of the data points as a strong wind average value, thereby obtaining a wind speed forecast extremum.
Step 103, carrying out interpolation processing on the wind speed forecast data to form mode forecast data with the same resolution as that of the small-area topographic data block, and analyzing and marking observation events in site observation data corresponding to time nodes of the mode forecast data to obtain the observation events marked with successful and failed observation labels;
it should be noted that, the mode is interpolated from the original wind speed forecast data obtained in step 102 to the higher resolution horizontal scale of the region of 100m x 100m by the spline interpolation method on the scale of coarser lattice point resolution (3 km x 3 km), so as to form the mode wind speed extremum forecast data with the same resolution as the terrain data; and then, defining observation event samples with the ground wind speed greater than 20m/s and the wind speed forecast data extremum greater than 25m/s and the wind average value greater than 15m/s in site observation data corresponding to time nodes of the mode forecast data as one-time successful judgment on the actually-occurring extremum wind speed weather conditions, and marking all data samples participating in training.
104, inputting the observation event containing the label, the high-resolution mode terrain data and the mode forecast data into a random forest model for regression training, and taking the probability value of the extreme wind speed as the final output result of the random forest model;
the observation labels marked with success and failure, high-resolution mode terrain data and mode forecast wind speed extremum data are input into a random forest model together for regression training, and the probability value of extremum wind speed is used as a final output result of the model.
It should be further noted that, the random forest is formed by combining a plurality of "decision trees", each decision tree contains a part of feature quantities randomly distributed in the whole training sample, and the manner of randomly distributing the feature quantities conforms to a certain distribution. Firstly, it is a tree-like branch algorithm structure from top to bottom, selecting an optimum branch on every node to make next layer of continuous classification, and specifically, the function F for determining branch direction by means of mode wind speed forecast extreme value is the Root Mean Square Error (RMSE) of forecast (extreme value about 25m/s forecast event) and observation (wind speed observation result above 20m/s at the corresponding time of nearby site) of training sample, and according to the function F, it is continuously split until F value reaches minimum and reaches lowest layer leaf node, so that the final forecast result correspondent to input can be obtained, and continuously iterating training this tree-like structure so as to make its variance in the whole sample set be minimum, and can implement one-time decision tree training. The model after convergence through training can be used for generating wind speed extreme value forecast products facing different forecast periods.
And 105, determining a probability value of electric field shutdown at the grid point according to the output result, multiplying the probability value with wind speed forecast data to obtain a wind speed extremum extraction data set corrected by the random forest model, and generating an image product from the wind speed extremum extraction data set.
It should be noted that, a probability value of 0-1.0 output by the random forest model represents a probability value of electric field shutdown occurring on the lattice point, and the probability value is multiplied by a result of forecasting wind speed in an original numerical mode to obtain a wind speed extremum extraction dataset corrected by the random forest model, and the dataset is saved and an image product is made, thus completing the whole flow of generating the product by the wind speed extremum extraction method for the multi-terrain station.
The wind speed forecast extremum extraction method for the multi-terrain station has the greatest advantage that a wind speed forecast extremum analysis product with ultra-high resolution, namely 100m x 100m horizontal grid point scale can be generated, and compared with extremum estimation of single-station single points, the wind speed forecast extremum extraction method is an obvious breakthrough. Meanwhile, due to the advantage of time resolution of the upstream wind speed numerical forecast data, the hour-by-hour forecast data within 0-72 hours are input, so that the extreme value analysis of a specific weather process can be updated more effectively, and the problem that the weather process early warning product is insufficient in representative caused by inaccurate analysis of static topography wind speed risk classification to the specific large weather process is solved.
The above is a method for extracting wind speed forecast extremum for a multi-terrain station provided in the embodiment of the present application, and the following is a system for extracting wind speed forecast extremum for a multi-terrain station provided in the embodiment of the present application.
Referring to fig. 3, a wind speed forecast extremum extraction system for a multi-terrain station according to an embodiment of the present application includes:
the acquiring unit 201 is configured to acquire small-area topographic data blocks in an area to be extracted of the extremum, and splice the small-area topographic data blocks to obtain static high-resolution mode topographic data;
the collecting unit 202 is configured to collect the numerical mode wind speed forecast data, and extract a strong wind extremum and a strong wind average value in the wind speed forecast data to obtain a wind speed forecast extremum;
the interpolation unit 203 is configured to perform interpolation processing on the wind speed forecast data to form mode forecast data with the same resolution as the small-area topographic data block, and analyze and mark observation events in site observation data corresponding to time nodes of the mode forecast data to obtain observation events marked with successful and failed observation labels;
the training unit 204 is configured to input the observation event including the tag, the high-resolution mode terrain data and the mode forecast data into the random forest model for regression training, and take a probability value of occurrence of the extreme wind speed as a final output result of the random forest model;
the generating unit 205 is configured to determine a probability value of an electric field outage occurring at a grid point according to the output result, multiply the probability value with wind speed forecast data, obtain a wind speed extremum extraction dataset corrected by the random forest model, and generate an image product from the wind speed extremum extraction dataset.
Further, in an embodiment of the present application, there is also provided a wind speed forecast extremum extraction apparatus, including a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the steps of the wind speed forecast extremum extraction method according to the instructions in the program code.
Further, in an embodiment of the present application, there is also provided a computer readable storage medium for storing a program code for executing the method described in the above method embodiment.
It will be clear to those skilled in the art that, for convenience and brevity of description, the specific working procedures of the above-described system and unit may refer to the corresponding procedures in the foregoing method embodiments, which are not repeated here.
The terms "first," "second," "third," "fourth," and the like in the description of the application and in the above figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented, for example, in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in the present application, "at least one (item)" means one or more, and "a plurality" means two or more. "and/or" for describing the association relationship of the association object, the representation may have three relationships, for example, "a and/or B" may represent: only a, only B and both a and B are present, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b or c may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: u disk, mobile hard disk, read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), magnetic disk or optical disk, etc.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (10)
1. The wind speed forecast extremum extraction method for the multi-terrain station is characterized by comprising the following steps of:
acquiring small-area topographic data blocks in an area to be extracted of the extremum, and splicing the small-area topographic data blocks to obtain static high-resolution mode topographic data;
collecting numerical mode wind speed forecast data, and extracting a strong wind extreme value and a strong wind average value in the wind speed forecast data to obtain a wind speed forecast extreme value;
performing interpolation processing on the wind speed forecast data to form mode forecast data with the same resolution as the small-area topographic data block, and analyzing and marking observation events in site observation data corresponding to time nodes of the mode forecast data to obtain the observation events marked with successful and failed observation labels;
inputting the observation event, the high-resolution mode topographic data and the mode forecast data containing the label into a random forest model for regression training, and taking a probability value of the occurrence of the extreme wind speed as a final output result of the random forest model;
and determining a probability value of electric field shutdown at the grid point according to the output result, multiplying the probability value with the wind speed forecast data to obtain a wind speed extremum extraction data set corrected by a random forest model, and generating an image product from the wind speed extremum extraction data set.
2. The method for extracting the wind speed forecast extremum for the multi-terrain station according to claim 1, wherein the steps of obtaining the small-area terrain data blocks in the extremum to be extracted, and splicing the small-area terrain data blocks to obtain the static high-resolution mode terrain data comprise the following steps:
generating small-area topographic data blocks in an extremum to-be-extracted area through an initialization module SI of a CMA-GD mode system numerical mode, wherein the horizontal resolution of each small-area topographic data block is 100m x 100m;
and performing null value elimination processing on a plurality of groups of data edges through an adaptive CloughTocher interpolation scheme, and splicing all small-area topographic data blocks to obtain static topographic data in a high-resolution mode.
3. The method for extracting extreme values of wind speed forecast for a multi-terrain station according to claim 2, wherein the collecting the numerical mode wind speed forecast data and extracting the extreme values of strong wind and the average value of strong wind in the wind speed forecast data to obtain the extreme values of wind speed forecast comprises the following steps:
collecting numerical mode wind speed forecast data, wherein the wind speed forecast data is hour-by-hour data within 0-72 hours;
and carrying out distribution analysis on different wind speed forecast values on each data grid point according to the stacking arrangement of different time points of the data points in the region of the wind speed forecast data, and determining a strong wind extremum and a strong wind average value to obtain the wind speed forecast extremum.
4. The method for extracting extreme values of wind speed forecast for a multi-terrain station according to claim 3, wherein the interpolating the wind speed forecast data to form mode forecast data with the same resolution as the small-area terrain data block specifically comprises:
and interpolating the wind speed forecast data with grid point resolution of 3km by using a spline interpolation method rule to a horizontal scale with horizontal resolution of 100m to form mode forecast data with the same resolution as that of the small-area topographic data block.
5. The wind speed forecast extremum extraction system for the multi-terrain station is characterized by comprising:
the acquisition unit is used for acquiring small-area topographic data blocks in the region to be extracted of the extreme value, and splicing the small-area topographic data blocks to obtain static high-resolution mode topographic data;
the collection unit is used for collecting the wind speed forecast data in the numerical mode, extracting a strong wind extreme value and a strong wind average value in the wind speed forecast data, and obtaining a wind speed forecast extreme value;
the interpolation unit is used for carrying out interpolation processing on the wind speed forecast data to form mode forecast data with the same resolution as the small-area topographic data block, analyzing and marking observation events in site observation data corresponding to time nodes of the mode forecast data to obtain the observation events marked with successful and failed observation labels;
the training unit is used for inputting the observation event containing the label, the high-resolution mode terrain data and the mode forecast data into a random forest model for regression training, and taking the probability value of the occurrence of the extreme wind speed as the final output result of the random forest model;
the generation unit is used for determining a probability value of electric field shutdown at a grid point according to the output result, multiplying the probability value with the wind speed forecast data to obtain a wind speed extremum extraction data set corrected by a random forest model, and generating an image product from the wind speed extremum extraction data set.
6. The system for extracting extreme values of wind speed forecast for a multi-terrain station according to claim 5, wherein the obtaining unit is specifically configured to:
generating small-area topographic data blocks in an extremum to-be-extracted area through an initialization module SI of a CMA-GD mode system numerical mode, wherein the horizontal resolution of each small-area topographic data block is 100m x 100m;
and performing null value elimination processing on a plurality of groups of data edges through an adaptive CloughTocher interpolation scheme, and splicing all small-area topographic data blocks to obtain static topographic data in a high-resolution mode.
7. The system for extracting extreme values of wind speed forecast for a multi-terrain site according to claim 6, wherein the collecting unit is specifically configured to:
collecting numerical mode wind speed forecast data, wherein the wind speed forecast data is hour-by-hour data within 0-72 hours;
and carrying out distribution analysis on different wind speed forecast values on each data grid point according to the stacking arrangement of different time points of the data points in the region of the wind speed forecast data, and determining a strong wind extremum and a strong wind average value to obtain the wind speed forecast extremum.
8. The system for extracting extreme values of wind speed forecast for a multi-terrain station according to claim 7, wherein the interpolation unit is specifically configured to:
interpolating the wind speed forecast data with grid point resolution of 3km by using a spline interpolation method rule to a horizontal scale with horizontal resolution of 100m to form mode forecast data with the same resolution as that of the small-area topographic data block;
and analyzing and marking the observation events in the site observation data corresponding to the time nodes of the mode forecast data to obtain the observation events marked with the successful and failed observation labels.
9. A wind speed forecast extremum extraction apparatus, the apparatus comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to perform the wind speed forecast extremum extraction method of any of claims 1-4 according to instructions in the program code.
10. A computer readable storage medium, characterized in that the computer readable storage medium is for storing a program code for performing the wind speed forecast extremum extraction method according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310981549.2A CN116702068B (en) | 2023-08-07 | 2023-08-07 | Wind speed forecast extremum extraction method and related device for multi-terrain station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310981549.2A CN116702068B (en) | 2023-08-07 | 2023-08-07 | Wind speed forecast extremum extraction method and related device for multi-terrain station |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116702068A true CN116702068A (en) | 2023-09-05 |
| CN116702068B CN116702068B (en) | 2023-12-29 |
Family
ID=87831535
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310981549.2A Active CN116702068B (en) | 2023-08-07 | 2023-08-07 | Wind speed forecast extremum extraction method and related device for multi-terrain station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116702068B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111105076A (en) * | 2019-11-25 | 2020-05-05 | 上海眼控科技股份有限公司 | Weather forecast data generation method and device, computer equipment and storage medium |
| CN112632799A (en) * | 2021-01-06 | 2021-04-09 | 国核电力规划设计研究院有限公司 | Method and device for valuing design wind speed of power transmission line |
| US20210192627A1 (en) * | 2020-02-27 | 2021-06-24 | Intercontinental Exchange Holdings, Inc. | Systems and methods for converting live weather data to weather index for offsetting weather risk |
| CN114942481A (en) * | 2022-06-08 | 2022-08-26 | 中国气象局上海台风研究所(上海市气象科学研究所) | Method and device for forecasting extreme value wind speed probability in tropical cyclone process and computer equipment |
| CN115657166A (en) * | 2022-12-09 | 2023-01-31 | 中科星图维天信(北京)科技有限公司 | Method and device for determining weather forecast value across multiple climate areas |
| CN115758876A (en) * | 2022-11-14 | 2023-03-07 | 中能融合智慧科技有限公司 | Method, system and computer equipment for forecasting accuracy of wind speed and wind direction |
| CN115808727A (en) * | 2022-11-22 | 2023-03-17 | 北京城市气象研究院 | Hundred-meter-level gust objective forecasting method and device |
-
2023
- 2023-08-07 CN CN202310981549.2A patent/CN116702068B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111105076A (en) * | 2019-11-25 | 2020-05-05 | 上海眼控科技股份有限公司 | Weather forecast data generation method and device, computer equipment and storage medium |
| US20210192627A1 (en) * | 2020-02-27 | 2021-06-24 | Intercontinental Exchange Holdings, Inc. | Systems and methods for converting live weather data to weather index for offsetting weather risk |
| CN112632799A (en) * | 2021-01-06 | 2021-04-09 | 国核电力规划设计研究院有限公司 | Method and device for valuing design wind speed of power transmission line |
| CN114942481A (en) * | 2022-06-08 | 2022-08-26 | 中国气象局上海台风研究所(上海市气象科学研究所) | Method and device for forecasting extreme value wind speed probability in tropical cyclone process and computer equipment |
| CN115758876A (en) * | 2022-11-14 | 2023-03-07 | 中能融合智慧科技有限公司 | Method, system and computer equipment for forecasting accuracy of wind speed and wind direction |
| CN115808727A (en) * | 2022-11-22 | 2023-03-17 | 北京城市气象研究院 | Hundred-meter-level gust objective forecasting method and device |
| CN115657166A (en) * | 2022-12-09 | 2023-01-31 | 中科星图维天信(北京)科技有限公司 | Method and device for determining weather forecast value across multiple climate areas |
Non-Patent Citations (2)
| Title |
|---|
| NATURAL HAZARDS AND EARTH SYSTEM SCIENCES 等: "Statistical downscaling of the French Mediterranean climate: assessment for present and projection in an anthropogenic scenario", 《NATURAL HAZARDS AND EARTH SYSTEM SCIENCES》, vol. 12, pages 651 - 670 * |
| 毛华健: "华南地区登陆台风风场特征及风灾评估", 《中国优秀硕士学位论文全文数据库 (基础科学辑)》, no. 4, pages 009 - 107 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116702068B (en) | 2023-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Almeida et al. | PV power forecast using a nonparametric PV model | |
| CN110019595B (en) | Multi-source meteorological data integration method and system | |
| CN109840260B (en) | Large-scale real-time rainfall automatic observation station hierarchical data processing method based on dynamic interpolation | |
| CN110929963A (en) | Wind speed prediction method, wind speed prediction device, and storage medium | |
| Hülk et al. | Allocation of annual electricity consumption and power generation capacities across multiple voltage levels in a high spatial resolution | |
| CN104239706A (en) | Preparation method for ground-based observation air temperature space-time data set | |
| CN114610706B (en) | Method, system and device for detecting electricity theft based on oversampling and improved random forest | |
| CN112308281A (en) | Temperature information prediction method and device | |
| CN109583467B (en) | Electric power meteorological data fusion method and system | |
| Cai et al. | Statistical feature selection from massive data in distribution fault diagnosis | |
| KR20170025454A (en) | System and method for space-time analysis of social media data | |
| CN113420458A (en) | Wind field data refining processing method and device, terminal and medium | |
| CN118012850B (en) | Intelligent irrigation multisource information-oriented database construction system, method and equipment | |
| CN115795329B (en) | Power utilization abnormal behavior analysis method and device based on big data grid | |
| Mauro et al. | Mapping land use impact of photovoltaic farms via crowdsourcing in the Province of Lecce (Southeastern Italy) | |
| Liu et al. | Estimation of precipitation induced by tropical cyclones based on machine‐learning‐enhanced analogue identification of numerical prediction | |
| CN116340437A (en) | Multi-clustering method for large-scale multi-source heterogeneous data | |
| CN115439753A (en) | Steep river bank identification method and system based on DEM | |
| Koolagudi | Long-range prediction of Indian summer monsoon rainfall using data mining and statistical approaches | |
| CN113779892A (en) | Wind speed and wind direction prediction method | |
| CN116702068B (en) | Wind speed forecast extremum extraction method and related device for multi-terrain station | |
| Kargashin et al. | Data processing as a critical part of GIS based mapping of renewable energy perspectives | |
| CN115600047B (en) | Small watershed surface average rainfall measurement and calculation method and system based on grid analysis | |
| CN116662860A (en) | User portrait and classification method based on energy big data | |
| CN117033923A (en) | Method and system for predicting crime quantity based on interpretable machine learning |
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 |