CN117390340A - Wind speed dynamic time regulation method and system - Google Patents
Wind speed dynamic time regulation method and system Download PDFInfo
- Publication number
- CN117390340A CN117390340A CN202311288694.9A CN202311288694A CN117390340A CN 117390340 A CN117390340 A CN 117390340A CN 202311288694 A CN202311288694 A CN 202311288694A CN 117390340 A CN117390340 A CN 117390340A
- Authority
- CN
- China
- Prior art keywords
- wind speed
- wind direction
- matching
- wind
- point
- 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
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 241000220317 Rosa Species 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 7
- 238000010586 diagram Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000011144 upstream manufacturing Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
Classifications
-
- 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
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Water Supply & Treatment (AREA)
- Software Systems (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Algebra (AREA)
- Public Health (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Indicating Or Recording The Presence, Absence, Or Direction Of Movement (AREA)
Abstract
The invention discloses a wind speed dynamic time regulation method and a system, wherein the method comprises the following steps: preprocessing the acquired wind speed and direction time sequences of a plurality of stations to obtain a complete wind speed time sequence and a complete wind direction time sequence; encoding the complete wind speed time sequence, and calculating the matching cost between the wind speed time sequences; encoding the complete wind direction time sequence, and calculating the matching cost between the wind speed time sequences; expanding the matching cost of the two time sequences from one dimension to two dimensions, and optimizing a matching minimum path by combining the spatial relationship between the wind direction and the position between stations; and calculating a wind speed dynamic time warping score by combining the matched minimum paths. According to the method, the to-be-processed wind speed with reasonable target position can be selected in advance before the interpolation and the prediction of the spatial wind speed are carried out, and the spatial wind speed interpolation and the prediction accuracy are improved.
Description
Technical Field
The invention relates to the technical field of wind energy information processing, in particular to a wind speed dynamic time regulation method and system.
Background
Wind energy is one of the most important renewable energy sources, has the characteristics of cleanness, inexhaustibility, reasonable price and the like, and is widely used for large-scale renewable energy source power generation. Accurate wind resource assessment and prediction are important links for developing renewable energy power generation.
The existing space wind speed interpolation and prediction method defaults to processing the regional static wind field. However, wind speed is a fluid, which is flowing in the natural environment, and it takes a certain time to flow from one location to another, which results in wind speeds measured by anemometers distributed at different locations not being the same gust. Therefore, in order to obtain wind speed data with accurate position, a large error is necessarily generated by interpolation using wind measurement data of different positions in space at a certain moment. Therefore, how to face spatial interpolation and prediction of wind speed, considering the fluidity of regional wind speed in space, and improving the accuracy of wind speed interpolation and prediction is an important problem to be solved.
Disclosure of Invention
The invention aims to solve the technical problems that: according to the time sequence matching principle, a dynamic time warping algorithm for a wind speed time sequence is provided, and a matching cost function is optimized through encoding wind speed and wind direction, so that accurate matching of the wind speed time sequence at different observation points in space is realized.
The invention adopts the following technical scheme for solving the technical problems:
the invention provides a wind speed dynamic time regulation method, which comprises the following steps:
s1, preprocessing the acquired wind speed and direction time series of a plurality of stations in space to obtain a complete wind speed time series and a wind direction time series.
S2, in order to digitally describe the wind speed time series from the data dimension and the shape dimension, the complete wind speed time series in the step S1 is encoded, and the matching cost between the wind speed time series is calculated.
S3, in order to acquire flow direction information of wind speed, the complete wind direction time sequence in the step S1 is encoded, and matching cost between the wind direction time sequences is calculated.
S4, expanding the matching cost in the steps S2 and S3 from one dimension to two dimensions, and optimizing a matching minimum path by combining the spatial relationship between the wind direction and the position between stations.
S5, calculating a wind speed dynamic time warping score by combining the matched minimum paths in the step S4.
Further, in step S1, the preprocessing includes detecting and rejecting abnormal values of the wind speed time series and the wind direction time series by using a spatial regression algorithm.
Further, in step S2, calculating the matching cost between the wind speed time series includes the following:
s201, sampling contour points of the contour of the wind speed time sequence by using the shape context descriptor.
S202, constructing a polar-logarithmic coordinate system comprising a certain number of angle areas and distance areas, and counting the number of contour points falling into each area of the shape context descriptor.
S203, obtaining a shape context histogram matrix according to the number of contour points in the step S202.
S204, in order to describe the matching score condition of the shape outlines of the two wind speed time sequences in the shape context coding process, the matching cost of the two wind speed time sequences is defined, and the specific formula is as follows:
wherein p is i The ith point, q, representing the wind speed time series p j The j-th point C of the wind speed time sequence q WSij Representing the matching cost of the wind speed time series p and q, b WS Represents the wind speed shape profile, h i Representing point p i Is a logarithmic polar histogram of wind speed, h j Representation point q j A log-polar histogram of wind speed; b (B) WS Representation b WS Is of the order of (2)Number of bodies, B WS =m×n, m is the number of angle areas, and n is the number of distance areas.
Further, in step S3, calculating the matching cost between the wind direction time series includes the following:
s301, sampling contour points of the contour of the wind direction time sequence by using the wind direction rose descriptor.
S302, constructing a polar-logarithmic coordinate system comprising a certain number of wind direction areas, and counting the number of contour points falling into each area of the wind direction rose descriptor.
S303, obtaining a wind direction rose histogram matrix according to the number of contour points in the step S302.
S304, in order to describe the matching condition of any wind direction time sequence in two wind direction shape outlines, a wind direction rose descriptor is proposed by referring to a wind direction rose diagram, and the matching cost of the two wind direction time sequences is defined, wherein the specific formula is as follows:
wherein m is i An ith point, n, representing a wind direction time series m j The j-th point C of the wind direction time sequence n WDij Time series m representing wind direction i And n j B) matching costs of (b) WD Represents the shape outline of wind direction, h i Representation point m i Is a logarithmic wind direction polar coordinate histogram of h j Representing point n j Is a log-polar histogram of wind direction. B (B) WD Representation b WD Is a bin count of (b).
Further, step S4 comprises the following sub-steps:
s401, calculating an optimal path by using a classical DTW algorithm and dynamic programming, wherein the specific formula is as follows:
where DTW represents the cumulative minimum dynamic regular distance score and d (i, j) represents the minimum path set when the two sets of input sequences euclidean distances match.
S402, acquiring longitude and latitude of wind speed of a point to be processed and longitude and latitude of wind speed of a matching point, and projecting an angle between the point to be processed and the matching point to coordinates of wind direction, wherein the coordinate conversion mode is as follows:
wherein a represents an intermediate variable, angle represents an angle between a point to be processed and a matching point under wind direction coordinates, [ Lon, lat ] represents longitude and latitude of a wind speed of the point to be processed, [ Lon ', lat' ] represents longitude and latitude of a wind speed of the matching point.
S403, introducing a sin (-) function to optimize the wind direction matching cost in the step S3 to enable the wind directions with obvious upstream and downstream relations to be matched more easily:
C′ WDij ＝C WDij ·|sin(dir-angle)|
wherein dir represents the average value of the wind direction time sequence in the wind direction coding process, C' WDij And representing the optimized wind direction coding matching cost.
S404, optimizing a matching minimum path in a classical DTW formula, and replacing a matching minimum path d (i, j) of the classical DTW, wherein the specific formula is as follows:
di′,j＝CWSij+αC′WDij
wherein α represents a scale factor for balancing C WDij And C' WDij 。
Further, in step S4, a final matching score of the wind speed and direction time series of the two stations is calculated, and the specific formula is as follows:
furthermore, the invention also provides a wind speed dynamic time warping system, which comprises
The sequence preprocessing module is used for preprocessing the acquired wind speed and direction time sequences of a plurality of stations in space to obtain a complete wind speed time sequence and a wind direction time sequence.
The matching cost acquisition module is used for encoding the complete wind speed time sequence in the sequence preprocessing module to obtain the matching cost between the wind speed time sequences; and encoding the complete wind direction time sequence in the sequence preprocessing module to obtain a matching cost function between the wind direction time sequences.
The dynamic regular matching result obtaining module is used for expanding the matching cost in the matching cost obtaining module from one dimension to two dimensions, and optimizing the matching minimum path by combining the spatial relationship between the wind direction and the position between the stations.
The wind speed dynamic time warping score obtaining module is used for combining the matching minimum path of the dynamic warping matching result obtaining module to calculate the wind speed dynamic time warping score.
Furthermore, the invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the steps of the wind speed dynamic time regulation method are realized when the processor executes the computer program.
Furthermore, the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to execute the wind speed dynamic time regulation method.
Compared with the prior art, the invention adopts the technical proposal and has the following remarkable technical effects:
the wind speed matching algorithm provided by the invention is used for carrying out wind speed interpolation and prediction in a wind speed space analysis theory. The method solves the problem that in the original wind speed space analysis theory, only the static distribution wind speed is processed and analyzed, and the wind speed to be processed with reasonable target position can be selected in advance before the interpolation and the prediction of the space wind speed are carried out, so that the accuracy of the space wind speed interpolation and the prediction is improved.
Drawings
FIG. 1 is a flow chart of an overall implementation of the present invention.
Fig. 2 is a site distribution diagram of an embodiment of the present invention.
FIG. 3 is a schematic diagram of a wind speed encoding process according to an embodiment of the present invention.
FIG. 4 is a schematic diagram of a wind direction encoding process according to an embodiment of the present invention.
Fig. 5 is a graph of matching results according to an embodiment of the present invention.
Detailed Description
In order to describe the technical content, constructional features, achieved objects and effects of the present invention in detail, the present invention is described in detail below with reference to the accompanying drawings and examples.
In order to achieve the above objective, the present invention provides a method for regulating wind speed dynamic time, as shown in fig. 1, comprising the following steps:
s1, selecting 41 meteorological stations in Jiangsu province, wherein the distribution of the meteorological stations is shown in fig. 2, selecting wind measurement data of 3 months in 2023, and preprocessing a plurality of station wind speed and wind direction sequences of an acquisition space by using a spatial regression algorithm to obtain a complete wind speed time sequence and a complete wind direction time sequence.
S2, encoding the wind speed time sequences of the target station and surrounding stations by using the shape context descriptor, and calculating the matching cost between the wind speed time sequences, wherein the specific content is as shown in fig. 3:
s201, as shown in fig. 3 (a), contour point sampling is performed on the contour of the wind speed time series using the shape context descriptor.
S202, as shown in (b) of FIG. 3, constructing a polar-logarithmic coordinate system comprising 12 angle areas and 5 distance areas, and counting the number of contour points falling into each area of the shape context descriptor.
S203, as shown in fig. 3 (c), a shape context histogram matrix is obtained from the number of contour points in step S202.
S204, in order to describe the matching score condition of the shape outlines of the two wind speed time sequences in the shape context coding process, the matching cost of the two wind speed time sequences is defined, and the specific formula is as follows:
wherein p is i The ith point, q, representing the wind speed time series p j The j-th point C of the wind speed time sequence q WSij Representing the matching cost of the wind speed time series p and q, b WS Represents the wind speed shape profile, h i Representing point p i Is a logarithmic polar histogram of wind speed, h j Representation point q j A log-polar histogram of wind speed; b (B) WS Representation b WS Is a box number of the box.
In this embodiment, B WS =12×5=60, 12 is the number of angle areas, and 5 is the number of distance areas.
Table 1 shows the wind speed code matching results of the surrounding stations and the target station. From the table, the wind speed time series of the station 6 and the target station has the lowest matching cost and the best matching effect.
TABLE 1 wind speed matching costs for surrounding stations and target stations
S3, encoding the preprocessed wind direction time sequence in order to acquire the flow direction information of the wind speed. The wind direction sequence of the station and the other station is encoded using a wind direction rose descriptor, the details of which are shown in fig. 3:
s301, as shown in fig. 4 (a), contour points of the contour of the wind direction time series are sampled by using the wind direction rose descriptor.
S302, as shown in (b) of FIG. 4, constructing a polar-logarithmic coordinate system comprising 16 wind direction areas, and counting the number of contour points falling into each area of the wind direction rose descriptor.
S303, as shown in fig. 4 (c), a wind direction rose histogram matrix is obtained from the number of contour points in step S302.
S304, in order to describe the matching condition of any two wind direction time sequences in two wind direction shape outlines, a wind direction rose descriptor is proposed by referring to a wind direction rose diagram, and the matching cost of the two wind direction time sequences is defined, wherein the specific formula is as follows:
wherein m is i An ith point, n, representing a wind direction time series m j The j-th point C of the wind direction time sequence n WDij Time series m representing wind direction i And n j B) matching costs of (b) WD Represents the shape outline of wind direction, h i Representation point m i Is a logarithmic wind direction polar coordinate histogram of h j Representing point n j Is a log-polar histogram of wind direction; b (B) WD Representation b WD Is a bin count of (b).
In this embodiment, B WD =16, 16 is the number of wind direction areas defined by the meteorological department.
S4, expanding the matching cost in the steps S2 and S3 from one dimension to two dimensions, and optimizing a matching minimum path by combining the spatial relationship between the wind direction and the position between stations, wherein the specific contents are as follows:
s401, calculating an optimal path by using a classical DTW algorithm and dynamic programming, wherein the specific formula is as follows:
where DTW represents the cumulative minimum dynamic regular distance score and d (i, j) represents the minimum path set when the two sets of input sequences euclidean distances match.
S402, acquiring longitude and latitude of wind speed of a point to be processed and longitude and latitude of wind speed of a matching point, and projecting an angle between the point to be processed and the matching point to coordinates of wind direction, wherein the coordinate conversion mode is as follows:
wherein a represents an intermediate variable, angle represents an angle between a point to be processed and a matching point under the coordinates of wind direction, [ Lon, lat ] represents longitude and latitude of wind speed of the point to be processed, [ Lon ', lat' ] represents longitude and latitude of wind speed of the matching point.
S403, introducing a sin (-) function to optimize the wind direction matching cost in the step S3 to enable the wind directions with obvious upstream and downstream relations to be matched more easily:
C′ WDij ＝C WDij ·|sin(dir-angle)|
wherein dir represents the average value of the wind direction time sequence in the wind direction coding process, C' WDij And representing the optimized wind direction coding matching cost.
S404, optimizing a matching minimum path in a classical DTW formula, and replacing a matching minimum path d (i, j) of the classical DTW, wherein the specific formula is as follows:
d′ i,j ＝C WSij +αC′ WDij
wherein α represents a scale factor for balancing C WDij And C' WDij 。
In the present embodiment of the present invention,
table 2 shows the wind direction code matching results of the surrounding stations and the target station. From the table, the time series matching cost of the wind direction of the stations 24, 28 and 39 and the target station is the lowest, and the matching effect is good.
TABLE 2 wind speed matching costs for surrounding stations and target stations
S405, calculating a wind speed dynamic time warping score by using a dynamic programming method, wherein the specific formula is as follows:
table 3 shows the results of the dynamic time warping score for the information of both wind speed and wind direction. The result shows that the matching score of the target station and the surrounding stations No. 1 is the smallest, 745, and the matching degree is the best.
TABLE 3WSDTW results
Finally, the result of the alignment of the wind speed at the target station and the wind speeds at the 40 stations around is shown in fig. 5. Fig. 5 (a) is an original wind speed sequence of 41 sites, fig. 5 (b) is a wind speed sequence after wind speed dynamic time warping matching, black broken lines are target site wind speed sequences, and gray is a surrounding site wind speed sequence. The graph shows that after wind speed dynamic time warping matching, the original wind speeds with obvious dislocation are normalized together, and the sequence dislocation caused by wind speed flowing time is eliminated. The embodiment of the invention has good matching effect and can be applied to actual situations.
The embodiment of the invention also provides a wind speed dynamic time warping system which comprises a sequence preprocessing module, a matching cost acquisition module, a dynamic warping matching result acquisition module, a wind speed dynamic time warping score acquisition module and a computer program capable of running on a processor. It should be noted that each module in the above system corresponds to a specific step of the method provided by the embodiment of the present invention, and has a corresponding functional module and beneficial effect of executing the method. Technical details not described in detail in this embodiment may be found in the methods provided in the embodiments of the present invention.
The embodiment of the invention also provides an electronic device which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor. It should be noted that, when executing the computer program, the processor corresponds to the specific steps of the method provided by the embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. Technical details not described in detail in this embodiment may be found in the methods provided in the embodiments of the present invention.
The embodiment of the invention also provides a computer readable storage medium, and the computer readable storage medium stores a computer program. It should be noted that, when the computer program is executed by the processor, the specific steps of the method provided by the embodiment of the present invention are corresponding to the functional modules and beneficial effects of the execution method. Technical details not described in detail in this embodiment may be found in the methods provided in the embodiments of the present invention.
The foregoing describes in detail preferred embodiments of the present invention. It should be understood that numerous modifications and variations can be made in accordance with the concepts of the invention by one of ordinary skill in the art without undue burden. Therefore, all technical solutions which can be obtained by logic analysis, reasoning or limited experiments based on the prior art by the person skilled in the art according to the inventive concept shall be within the scope of protection defined by the claims.
Claims (9)
1. A method for dynamic time alignment of wind speed, comprising:
s1, preprocessing wind speed and direction sequences of a plurality of stations in an acquired space to obtain a complete wind speed time sequence and a complete wind direction time sequence;
s2, encoding the complete wind speed time sequence in the step S1, and calculating the matching cost between the wind speed time sequences;
s3, encoding the complete wind direction time sequence in the step S1, and calculating the matching cost between the wind direction time sequences;
s4, expanding the matching cost in the steps S2 and S3 from one dimension to two dimensions, and optimizing a matching minimum path by combining the spatial relationship between the wind direction and the position between stations;
s5, calculating a wind speed dynamic time warping score by combining the matched minimum paths in the step S4.
2. The method according to claim 1, wherein in step S1, abnormal values of the wind speed time series and the wind direction time series are detected and removed by using a spatial regression algorithm, so as to obtain a complete wind speed time series and a wind direction time series.
3. The method according to claim 1, wherein in step S2, calculating the matching costs between the wind speed time series comprises:
s201, sampling contour points of the contour of the wind speed time sequence by using the shape context descriptor;
s202, constructing a polar-logarithmic coordinate system comprising a certain number of angle areas and distance areas, and counting the number of contour points falling into each area of the shape context descriptor;
s203, obtaining a shape context histogram matrix according to the number of contour points in the step S202;
s204, defining matching costs of two wind speed time sequences, wherein the specific formula is as follows:
wherein p is i The ith point, q, representing the wind speed time series p j The j-th point C of the wind speed time sequence q WSij Representing the matching cost of the wind speed time series p and q, b WS Represents the wind speed shape profile, h i Representing point p i Is a logarithmic polar histogram of wind speed, h j Representation point q j A log-polar histogram of wind speed; b (B) WS Representation b WS Number of boxes of B WS =m×n, m is the number of angle areas, and n is the number of distance areas.
4. The method according to claim 1, wherein the calculating of the matching costs between the wind direction time series in step S3 comprises the following:
s301, sampling contour points of the contour of a wind direction time sequence by using a wind direction rose descriptor;
s302, constructing a polar-logarithmic coordinate system comprising a certain number of wind direction areas, and counting the number of contour points falling into each area of the wind direction rose descriptor;
s303, obtaining a wind direction rose histogram matrix according to the number of contour points in the step S302;
s304, providing a wind direction rose descriptor by referring to a wind direction rose diagram, and defining the matching cost of two wind direction time sequences, wherein the specific formula is as follows:
wherein m is i An ith point, n, representing a wind direction time series m j The j-th point C of the wind direction time sequence n WDij Representing a wind direction sequence m i And n j B) matching costs of (b) WD Represents the shape outline of wind direction, h i Representation point m i Is a logarithmic wind direction polar coordinate histogram of h j Representing point n j Is a log-polar histogram of wind direction; b (B) WD Representation b WD Is a bin count of (b).
5. The method according to claim 1, characterized in that step S4 comprises the sub-steps of:
s401, calculating an optimal path by using a classical DTW algorithm and dynamic programming, wherein the specific formula is as follows:
wherein DTW represents the cumulative minimum dynamic regular distance score and d (i, j) represents the minimum path set when the euclidean distances of the two sets of input sequences match;
s402, acquiring longitude and latitude of wind speed of a point to be processed and longitude and latitude of wind speed of a matching point, and projecting an angle between the point to be processed and the matching point to coordinates of wind direction, wherein the coordinate conversion mode is as follows:
wherein a represents an intermediate variable, angle represents an angle between a point to be processed and a matching point under a wind direction coordinate, [ Lon, lat ] represents longitude and latitude of a wind speed of the point to be processed, [ Lon ', lat' ] represents longitude and latitude of a wind speed of the matching point;
s403, introducing a sin (-) function, and optimizing the wind direction time sequence matching cost in the step S3 as follows:
C′ WDij ＝C WDij ·|sin(dir-angle)|
wherein dir represents the average value of the wind direction time sequence in the wind direction coding process, C' WDij Representing the optimized wind direction time sequence matching cost;
s404, optimizing a matching minimum path in a classical DTW formula, and replacing a matching minimum path d (i, j) of the classical DTW, wherein the specific formula is as follows:
d′ i,j ＝C WSij +αC′ WDij
where α represents a scale factor.
6. The method according to claim 1, wherein in step S4, the final matching score of the wind speed and direction time series of the two stations is calculated, and the specific formula is:
7. a wind speed dynamic time warping system is characterized by comprising
The sequence preprocessing module is used for preprocessing the acquired wind speed and direction time sequences of a plurality of stations in space to obtain a complete wind speed time sequence and a complete wind direction time sequence;
the matching cost acquisition module is used for encoding the complete wind speed time sequence in the sequence preprocessing module to obtain a matching cost function between the wind speed time sequences; encoding the complete wind direction time sequence in the sequence preprocessing module to obtain a matching cost function between the wind direction time sequences;
the dynamic regular matching result obtaining module is used for expanding the matching cost in the matching cost obtaining module from one dimension to two dimensions, and optimizing a matching minimum path by combining the spatial relationship between the wind direction and the position between stations;
the wind speed dynamic time warping score obtaining module is used for combining the matching minimum path of the dynamic warping matching result obtaining module to calculate the wind speed dynamic time warping score.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any one of claims 1 to 6 when the computer program is executed by the processor.
9. A computer-readable storage medium, having stored thereon a computer program, characterized in that the computer program, when executed by a processor, performs the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311288694.9A CN117390340A (en) | 2023-10-07 | 2023-10-07 | Wind speed dynamic time regulation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311288694.9A CN117390340A (en) | 2023-10-07 | 2023-10-07 | Wind speed dynamic time regulation method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117390340A true CN117390340A (en) | 2024-01-12 |
Family
ID=89435299
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311288694.9A Pending CN117390340A (en) | 2023-10-07 | 2023-10-07 | Wind speed dynamic time regulation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117390340A (en) |
-
2023
- 2023-10-07 CN CN202311288694.9A patent/CN117390340A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111199016B (en) | Daily load curve clustering method for improving K-means based on DTW | |
| CN106529719B (en) | Wind power prediction method based on particle swarm optimization algorithm wind speed fusion | |
| Sun et al. | Short-term multi-step wind power forecasting based on spatio-temporal correlations and transformer neural networks | |
| US20120230821A1 (en) | Wind power prediction method of single wind turbine generator | |
| Cheng et al. | Augmented convolutional network for wind power prediction: A new recurrent architecture design with spatial-temporal image inputs | |
| CN109636171A (en) | A kind of comprehensive diagnos and risk evaluating method that regional vegetation restores | |
| CN113592822B (en) | Insulator defect positioning method for electric power inspection image | |
| CN116307291B (en) | Distributed photovoltaic power generation prediction method and prediction terminal based on wavelet decomposition | |
| CN110909738A (en) | Automatic reading method of pointer instrument based on key point detection | |
| CN108985490A (en) | Wind-driven generator power curve modification method based on the fitting of sliding window characteristic | |
| Li et al. | Deep spatio-temporal wind power forecasting | |
| CN112862274A (en) | WRF-LES and Deepar combined wind power prediction method | |
| CN110991701A (en) | Wind power plant fan wind speed prediction method and system based on data fusion | |
| CN115660232A (en) | Ultra-short-term prediction method, device and system for wind power | |
| CN105590167A (en) | Method and device for analyzing electric field multivariate operating data | |
| CN117390340A (en) | Wind speed dynamic time regulation method and system | |
| CN117060407A (en) | Wind power cluster power prediction method and system based on similar day division | |
| CN111310121A (en) | New energy output probability prediction method and system | |
| CN110852597B (en) | Electricity consumption peak period resident load ratio calculation method based on generation of countermeasure network | |
| CN110925147B (en) | Method for tracking wake flow of wind driven generator | |
| CN110019167A (en) | Long-term new forms of energy resource data base construction method and system in one kind | |
| CN111539577A (en) | Short-term wind power prediction method based on wind speed change rate and Gaussian process regression | |
| CN112215383A (en) | Distributed photovoltaic power generation power prediction method and system | |
| CN110705650A (en) | Metal plate layout method based on deep learning | |
| CN114188989B (en) | Correlation-considered distributed photovoltaic power station output 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 |