CN113516320A - Wind speed correction and predicted wind speed optimization method and device based on multi-objective genetic algorithm - Google Patents
Wind speed correction and predicted wind speed optimization method and device based on multi-objective genetic algorithm Download PDFInfo
- Publication number
- CN113516320A CN113516320A CN202111071261.9A CN202111071261A CN113516320A CN 113516320 A CN113516320 A CN 113516320A CN 202111071261 A CN202111071261 A CN 202111071261A CN 113516320 A CN113516320 A CN 113516320A
- Authority
- CN
- China
- Prior art keywords
- wind speed
- optimization
- wind
- prediction
- data
- 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
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Evolutionary Biology (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Primary Health Care (AREA)
- Computing Systems (AREA)
- Public Health (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Water Supply & Treatment (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Wind Motors (AREA)
Abstract
The invention provides a wind speed correction and predicted wind speed optimization method based on a multi-objective genetic algorithm, which comprises the steps of obtaining historical data of a wind power plant, and selecting k optimization targets at different time intervals; allocating m/k groups of predicted wind speed data to each fan one by one according to each optimization target; for each target, calculating a value of an optimization objective function based on the measured wind speed and the m/k group prediction members; extracting m/k predicted wind speeds without replacing; selecting variation strategies and elite strategies at different time intervals, performing cross operation and variation to obtain m generations, and calculating the optimized objective function values of the generations; and when the optimization objective function value of the filial generation meets the condition, finishing the optimization. The invention provides multi-objective optimization for wind speed correction and wind speed prediction optimization, and a dispatcher and a decision maker can make strategies in different time periods according to different objectives so as to ensure that the wind speed prediction can ensure the stability of electric power transaction income to a greater extent.
Description
Technical Field
The invention belongs to the field of wind speed prediction, and particularly relates to a wind speed correction and predicted wind speed optimization method and device based on a multi-objective genetic algorithm.
Background
The national policy supports the development of new energy resources greatly, so that the proportion of wind power in a power system is improved, the fluctuation of the wind power is strong, and the wind power mainly depends on the accuracy of wind speed prediction, so that the power prediction by depending on the current actually measured wind speed and the wind speed of numerical weather prediction becomes an important ring for short-term wind power prediction. The existing wind speed prediction method is a power downscaling method which mainly depends on numerical weather forecast and products thereof, and mainly considers the optimization of a physical parameterization scheme, ensemble forecast and data assimilation technology; the other statistical downscaling method based on wind speed and other element prediction results interpolates grid point wind speed to wind speed of a wind power plant, and mainly uses numerical extrapolation or a data-driven machine learning model to return to predict the wind speed. The criteria for finally evaluating whether the predicted wind speed is accurate are usually based on actual measurement and predicted distance, and an optimized objective function is selected for evaluation, such as root mean square error or absolute deviation, or a single target with the shortest Euclidean distance and the like to correct the predicted wind speed; therefore, different predicted wind speed results are generated respectively in the presence of multiple optimization targets, the final deterministic prediction needs a single wind speed prediction, the final wind speed is often determined through one target, and few systematic methods are used for helping a decision maker to simultaneously consider the multiple optimization targets and combine the trends of the decision maker to select the optimized correction and prediction results.
The power trading needs to consider comprehensive information of power supply and demand, so that various strategies exist to generate deterministic power forecasts for different periods of time, and the demand for more diversified optimization targets is generated. The relationship between the profitability of the peak time and the off-peak time of the electricity consumption and the accuracy of the wind speed forecasting is different, the false alarm rate and the missing report rate as well as the extreme strong wind and the low wind time of the electricity consumption all have different influences on the profitability, the false alarm rate and the missing report rate of the profitability of the peak time and the off-peak time as well as the influences of the extreme strong wind and the low wind on the profitability are all considered, so that the evaluation index of the wind speed forecasting is diversified, and the forecasting index of the decisive forecasting element of the wind speed can not keep a single target optimization standard any more.
Disclosure of Invention
The invention provides a wind speed correction and predicted wind speed optimization method and device based on a multi-objective genetic algorithm, which are added with different optimization objectives of power consumption peak and low ebb, and the contribution of wind speed prediction to the electric power market income is enlarged.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
a wind speed correction and prediction wind speed optimization method based on a multi-objective genetic algorithm comprises the following steps:
s1, acquiring historical data of the wind power plant, including measured wind speeds of n fans and m wind speed prediction data obtained by predicting the wind speed of each fan based on m meteorological data; dividing into training and verifying sets; selecting k optimization targets in different time periods;
s2, dividing the m kinds of wind speed prediction data into m/k groups of wind speed prediction data for each fan, namely allocating m/k groups of predicted wind speed data for each optimization target;
s3, normalizing different optimization targets; for each target, calculating a value of an optimization objective function based on the measured wind speed and the m/k group prediction members; extracting m/k predicted wind speeds without replacing;
s4, selecting variation strategies and elite strategies at different time intervals, performing cross operation and variation on m/k predicted wind speeds in k different target groups according to the variation strategies and the elite strategies to obtain m generations, and calculating optimized objective function values of the generations;
and S5, when the optimization objective function value of the filial generation meets the condition, finishing the optimization, and otherwise, returning to S2 to continue the multi-objective genetic optimization.
Further, the step S1 of obtaining the actually measured wind speeds of the n wind turbines further includes performing quality control on the actually measured wind speeds, and eliminating the situations including power limitation and maintenance.
Further, in step S1, the specific method for acquiring m types of wind speed prediction data obtained by each wind turbine based on the wind speed forecasts of the m types of meteorological data prediction sources includes:
s101, obtaining the hub height and accurate longitude and latitude information of a single fan;
s102, acquiring a wind speed forecasting result of a numerical weather forecast corresponding to various weather data forecasting sources of a single fan, wherein the type of the weather data is m;
s103, obtaining a corresponding predicted wind speed corresponding to a wind speed period of the fan based on the wind speed forecast result of the numerical weather forecast and the fan modeling information; and extracting and determining the near-ground wind speeds in the meteorological sources to each fan point by using the height and longitude and latitude information of the hubs of the n fans and using a thin-disk smooth spline interpolation method, and taking the predicted wind speeds corresponding to the n fans as m kinds of wind speed prediction data.
Further, the method for selecting k optimization targets in different time periods in step S1 includes: calculating a plurality of optimization objectives based on the n groups of measured wind speeds and wind speed prediction data, including a common correlation coefficient, a mean absolute deviation (MAE), a Mean Absolute Percentage Error (MAPE), a Root Mean Square Error (RMSE); and optimization objectives based on different power supply and demand conditions, including reduction of negative deviation during peak electricity usage periods, resistance to risk under extreme high wind conditions, and fault tolerance of high wind threshold prediction; the optimization target class is k.
The invention also provides a wind speed correcting and forecasting wind speed optimizing device based on the multi-objective genetic algorithm, which comprises the following components:
the data module is used for acquiring historical data of the wind power plant, including measured wind speeds of n fans and m wind speed prediction data obtained by predicting the wind speed of each fan based on m meteorological data; dividing into training and verifying sets; selecting k optimization targets in different time periods;
the target distribution module is used for dividing the m types of wind speed prediction data into m/k groups of wind speed prediction data for each fan, namely distributing the m/k groups of predicted wind speed data for each optimized target;
the normalization and extraction module is used for normalizing different optimization targets; for each target, calculating a value of an optimization objective function based on the measured wind speed and the m/k group prediction members; extracting m/k predicted wind speeds without replacing;
the cross variation module is used for selecting variation strategies and elite strategies in different time periods, carrying out cross operation and variation on m/k predicted wind speeds in k different target groups according to the variation strategies and the elite strategies to obtain m generations, and calculating the optimized objective function values of the generations;
and the ending judgment module is used for finishing the optimization when judging that the optimization objective function value of the filial generation meets the condition, or returning to the objective distribution module to continue the multi-objective genetic optimization.
Further, the data module comprises a quality control unit for performing quality control on the actually measured wind speed and eliminating the conditions including power limitation and maintenance.
Further, the data module further includes:
the single fan data acquisition unit is used for acquiring the hub height and the accurate longitude and latitude information of the single fan;
the wind speed forecast acquisition unit is used for acquiring a wind speed forecast result of a numerical weather forecast corresponding to various meteorological data forecasting sources of a single fan, wherein the meteorological data type is m;
the wind speed prediction data unit is used for obtaining corresponding predicted wind speed corresponding to a wind speed period of the fan based on a wind speed prediction result of the numerical weather prediction and fan modeling information; and extracting and determining the near-ground wind speeds in the meteorological sources to each fan point by using the height and longitude and latitude information of the hubs of the n fans and using a thin-disk smooth spline interpolation method, and taking the predicted wind speeds corresponding to the n fans as m kinds of wind speed prediction data.
Further, the data module further comprises an optimization target selection unit, and a plurality of optimization targets are calculated based on the n groups of actually measured wind speeds and wind speed prediction data, wherein the optimization targets comprise general correlation coefficients, mean absolute deviation (MAE), Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE); and optimization objectives based on different power supply and demand conditions, including reduction of negative deviation during peak electricity usage periods, resistance to risk under extreme high wind conditions, and fault tolerance of high wind threshold prediction; the optimization target class is k.
Compared with the prior art, the invention has the following beneficial effects:
the multi-objective optimization prediction wind speed optimization method based on multiple meteorological sources modifies the optimization objective and the optimization strategy in the time interval according to different requirements of power utilization peaks and valleys, and comprises the steps of optimizing by multi-objective prediction wind speed directional variation and an elite strategy for reserving certain numerical weather forecast results to ensure the stability of the wind speed prediction results, so that multi-objective optimization is provided for wind speed correction and wind speed prediction optimization, and dispatchers and decision makers can make strategies in different time intervals according to different objectives to ensure that the wind speed prediction can ensure the stability of power trading income to a greater extent.
Drawings
FIG. 1 is a schematic flow chart of an embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
The embodiments of the present invention relate to the following terms:
multi-objective optimization: the method belongs to the field of multi-criterion decision making, and relates to a mathematical problem of simultaneous optimization of a plurality of objective functions.
Genetic algorithm: is a search algorithm for solving the optimization in computational mathematics, and is one of evolutionary algorithms.
And (3) cross operation: the general genetic algorithm has a mating probability (also called cross probability), the range is generally 0.6-1, and the mating probability reflects the probability of mating two selected individuals. For example, a mating probability of 0.8, 80% of the predicted wind velocity vectors will produce a swap of predicted values.
Mutation: new "child" individuals are generated by mutation. Genetic algorithms generally have a fixed mutation constant (also called mutation probability), usually 0.1 or less, which represents the probability of mutation. For example, the wind speed may increase by 10% over a 10% period.
In order to make the objects and features of the present invention more comprehensible, embodiments accompanying the present invention are further described below.
As shown in fig. 1, the specific process of the present invention is as follows:
1) and acquiring historical data of the actually measured wind speed of the wind power plant fans, wherein the number of the fans is n. Firstly, the measured wind speeds of n fans or n fan groups are subjected to quality control, and the conditions of power limitation, maintenance and the like are eliminated.
2) And obtaining the hub height and the accurate longitude and latitude information of the single fan.
3) And acquiring multiple meteorological data prediction sources corresponding to a single fan, wherein the meteorological data type is m. Inputting global short-term numerical forecast wind speeds of all global meteorological institutions, mesoscale numerical weather forecast lattice point wind speeds obtained by taking global forecasts as driving data, and collective forecast results generated by different parameterization schemes and initial disturbance, wherein all the wind speed forecasts can be used as deterministic wind speed forecast results.
4) And obtaining a corresponding predicted wind speed corresponding to the wind speed period of the fan based on the wind speed of the numerical weather forecast and the fan modeling information. The method comprises the steps of extracting and determining the near-ground wind speed in the meteorological sources to each fan point by using the height and longitude and latitude information of n fan hubs and using a thin-disc smooth spline interpolation method, specifically fitting a smooth plane to connect the measured wind speeds of the n fans at each position, then interpolating the wind speeds of the grid points to the positions of the fans according to the plane, and taking the predicted wind speeds corresponding to the n fans as m predicted wind speed vectors.
5) Calculating various optimization objectives, such as general correlation coefficients, mean absolute deviation (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), etc., based on the n sets of measured and predicted wind speeds; reducing negative bias based on optimization goals for different power supply and demand conditions, such as peak hours; for example, the risk resistance under the condition of extreme strong wind, the fault tolerance rate predicted by a strong wind critical value and the like, the optimization target type is k.
6) Determining the optimized target type k, selecting different time periods, dividing historical data into a training set and a verification set, performing multi-target genetic algorithm optimization on the training set, and performing the same strategy on the verification set to obtain the predicted wind speed. The calculation steps of the multi-objective genetic optimization algorithm are specifically 7) to 10) below. Before training, a variation strategy (namely determining a variation coefficient and the like) and an elite strategy (namely, a wind speed prediction result of a meteorological source with a better retention effect directly enters the next generation) are selected.
7) And dividing the m types of wind speed prediction data into m/k groups of wind speed prediction data for each fan, namely allocating m/k groups of predicted wind speeds for each target.
8) The different optimization objectives are normalized. For each target, calculating a value of an optimization objective function based on the measured wind speed and the m/k predicted members; and extracting m/k predicted wind speeds without replacing, wherein the probability in extraction is positively correlated with the value of the objective function.
9) According to the variation tendency and the elite strategy, performing cross operation and variation on m/k predicted wind speeds in k different target groups according to the previous variation and elite strategy to obtain m generations, and calculating the optimized objective function value of the filial generation.
10) And (4) when the optimization objective function values of the filial generation meet the conditions, finishing the optimization, or returning to the step 7) to continue the multi-objective genetic optimization.
In this embodiment, a wind farm in northwest china with better data quality is selected, the prediction data are meteorological sources and collective forecast members thereof issued by 4 large domestic and foreign meteorological institutions, 94 sets of forecast results are interpolated to the positions of 50 fans, and 6 kinds of optimization objective functions are given: and taking the predicted performance of each optimization target in one year of history as an optimization target threshold value. And (4) carrying out back calculation according to the flow, optimizing the correlation coefficient, the average absolute deviation, the average absolute percentage error and the root mean square error by 1-2%, and improving the recall rate and the accuracy rate of the gale forecast by 4-6% on the basis.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. A wind speed correction and prediction wind speed optimization method based on a multi-objective genetic algorithm is characterized by comprising the following steps:
s1, acquiring historical data of the wind power plant, including measured wind speeds of n fans and m wind speed prediction data obtained by predicting the wind speed of each fan based on m meteorological data; dividing into training and verifying sets; selecting k optimization targets in different time periods;
s2, dividing the m kinds of wind speed prediction data into m/k groups of wind speed prediction data for each fan, namely allocating m/k groups of predicted wind speed data for each optimization target;
s3, normalizing different optimization targets; for each target, calculating a value of an optimization objective function based on the measured wind speed and the m/k group prediction members; extracting m/k predicted wind speeds without replacing;
s4, selecting variation strategies and elite strategies at different time intervals, performing cross operation and variation on m/k predicted wind speeds in k different target groups according to the variation strategies and the elite strategies to obtain m generations, and calculating optimized objective function values of the generations;
and S5, when the optimization objective function value of the filial generation meets the condition, finishing the optimization, and otherwise, returning to S2 to continue the multi-objective genetic optimization.
2. The wind speed correction and predicted wind speed optimization method based on the multi-objective genetic algorithm as claimed in claim 1, wherein the step S1 of obtaining the measured wind speeds of the n wind turbines further comprises quality control of the measured wind speeds and elimination of situations including power limitation and maintenance.
3. The method for wind speed correction and predicted wind speed optimization based on multi-objective genetic algorithm of claim 1, wherein the specific obtaining method of m wind speed prediction data obtained by each wind turbine based on wind speed forecast of m meteorological data prediction sources in step S1 comprises:
s101, obtaining the hub height and accurate longitude and latitude information of a single fan;
s102, acquiring a wind speed forecasting result of a numerical weather forecast corresponding to various weather data forecasting sources of a single fan, wherein the type of the weather data is m;
s103, obtaining a corresponding predicted wind speed corresponding to a wind speed period of the fan based on the wind speed forecast result of the numerical weather forecast and the fan modeling information; and extracting and determining the near-ground wind speeds in the meteorological sources to each fan point by using the height and longitude and latitude information of the hubs of the n fans and using a thin-disk smooth spline interpolation method, and taking the predicted wind speeds corresponding to the n fans as m kinds of wind speed prediction data.
4. The method for wind speed correction and predicted wind speed optimization based on multi-objective genetic algorithm as claimed in claim 1, wherein the method for selecting k optimization objectives in different time periods in step S1 comprises: calculating various optimization targets based on n groups of actually measured wind speeds and wind speed prediction data, wherein the optimization targets comprise a general correlation coefficient, an average absolute deviation MAE, an average absolute percentage error MAPE and a root mean square error RMSE; and optimization objectives based on different power supply and demand conditions, including reduction of negative deviation during peak electricity usage periods, resistance to risk under extreme high wind conditions, and fault tolerance of high wind threshold prediction; the optimization target class is k.
5. A wind speed correction and prediction wind speed optimization device based on a multi-objective genetic algorithm is characterized by comprising the following components:
the data module is used for acquiring historical data of the wind power plant, including measured wind speeds of n fans and m wind speed prediction data obtained by predicting the wind speed of each fan based on m meteorological data; dividing into training and verifying sets; selecting k optimization targets in different time periods;
the target distribution module is used for dividing the m types of wind speed prediction data into m/k groups of wind speed prediction data for each fan, namely distributing the m/k groups of predicted wind speed data for each optimized target;
the normalization and extraction module is used for normalizing different optimization targets; for each target, calculating a value of an optimization objective function based on the measured wind speed and the m/k group prediction members; extracting m/k predicted wind speeds without replacing;
the cross variation module is used for selecting variation strategies and elite strategies in different time periods, carrying out cross operation and variation on m/k predicted wind speeds in k different target groups according to the variation strategies and the elite strategies to obtain m generations, and calculating the optimized objective function values of the generations;
and the ending judgment module is used for finishing the optimization when judging that the optimization objective function value of the filial generation meets the condition, or returning to the objective distribution module to continue the multi-objective genetic optimization.
6. The wind speed correction and prediction wind speed optimization device based on the multi-objective genetic algorithm as claimed in claim 5, wherein the data module comprises a quality control unit for performing quality control on the measured wind speed to eliminate the situations including power limitation and maintenance.
7. The wind speed correction and prediction wind speed optimization device based on multi-objective genetic algorithm as claimed in claim 5, wherein the data module further comprises:
the single fan data acquisition unit is used for acquiring the hub height and the accurate longitude and latitude information of the single fan;
the wind speed forecast acquisition unit is used for acquiring a wind speed forecast result of a numerical weather forecast corresponding to various meteorological data forecasting sources of a single fan, wherein the meteorological data type is m;
the wind speed prediction data unit is used for obtaining corresponding predicted wind speed corresponding to a wind speed period of the fan based on a wind speed prediction result of the numerical weather prediction and fan modeling information; and extracting and determining the near-ground wind speeds in the meteorological sources to each fan point by using the height and longitude and latitude information of the hubs of the n fans and using a thin-disk smooth spline interpolation method, and taking the predicted wind speeds corresponding to the n fans as m kinds of wind speed prediction data.
8. The wind speed correction and prediction wind speed optimization device based on the multi-objective genetic algorithm as claimed in claim 5, wherein the data module further comprises an optimization target selection unit for calculating a plurality of optimization targets including a general correlation coefficient, a mean absolute deviation MAE, a mean absolute percentage error MAPE, a root mean square error RMSE based on n groups of measured wind speeds and wind speed prediction data; and optimization objectives based on different power supply and demand conditions, including reduction of negative deviation during peak electricity usage periods, resistance to risk under extreme high wind conditions, and fault tolerance of high wind threshold prediction; the optimization target class is k.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111071261.9A CN113516320B (en) | 2021-09-14 | 2021-09-14 | Wind speed correction and predicted wind speed optimization method and device based on multi-objective genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111071261.9A CN113516320B (en) | 2021-09-14 | 2021-09-14 | Wind speed correction and predicted wind speed optimization method and device based on multi-objective genetic algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113516320A true CN113516320A (en) | 2021-10-19 |
| CN113516320B CN113516320B (en) | 2021-12-10 |
Family
ID=78063055
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111071261.9A Active CN113516320B (en) | 2021-09-14 | 2021-09-14 | Wind speed correction and predicted wind speed optimization method and device based on multi-objective genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113516320B (en) |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102914969A (en) * | 2012-09-28 | 2013-02-06 | 南方电网科学研究院有限责任公司 | Comprehensive error correction method of short-period wind power prediction system |
| CN103441506A (en) * | 2013-06-18 | 2013-12-11 | 国家电网公司 | Method for multi-target coordination reactive power optimization control of distributed wind farm in different time scales |
| CN105868534A (en) * | 2016-03-24 | 2016-08-17 | 大连理工大学 | Multi-objective optimization sampling based hydrologic model uncertainty analysis method |
| CN105956708A (en) * | 2016-05-12 | 2016-09-21 | 扬州大学 | Grey correlation time sequence based short-term wind speed forecasting method |
| CN109214582A (en) * | 2018-09-20 | 2019-01-15 | 中南大学 | A kind of Along Railway wind speed forecasting method of wind direction space correlation driving |
| KR102028606B1 (en) * | 2018-11-06 | 2019-10-04 | 한국산업기술시험원 | Windlidar calibration system and calibration method using the same |
| CN110543929A (en) * | 2019-08-29 | 2019-12-06 | 华北电力大学（保定） | wind speed interval prediction method and system based on Lorenz system |
| CN110633864A (en) * | 2019-09-20 | 2019-12-31 | 国网湖南省电力有限公司 | Wind speed numerical prediction correction method and system based on range deviation |
| CN110852016A (en) * | 2019-12-04 | 2020-02-28 | 中国直升机设计研究所 | Reliability simulation test model correction method |
| CN111469125A (en) * | 2020-04-01 | 2020-07-31 | 南京浦航机械科技开发有限公司 | Hole site correction method applied to automatic drilling and riveting of curved surface product |
| CN112084706A (en) * | 2020-09-02 | 2020-12-15 | 合肥工业大学 | NSGA-II-based multi-objective optimization method for capacitor module assembly configuration |
| CN112288164A (en) * | 2020-10-29 | 2021-01-29 | 四川大学 | Wind power combined prediction method considering spatial correlation and correcting numerical weather forecast |
| CN112417734A (en) * | 2020-11-25 | 2021-02-26 | 国能日新科技股份有限公司 | Wind speed correction method and device based on geographic information of wind power plant |
| CN112561125A (en) * | 2020-11-20 | 2021-03-26 | 浙江省气象科学研究所 | Wind speed forecast multi-data fusion correction method |
| CN112633544A (en) * | 2019-11-28 | 2021-04-09 | 北京金风慧能技术有限公司 | Predicted wind speed correction method and device |
| CN113159714A (en) * | 2021-04-01 | 2021-07-23 | 国网河南省电力公司电力科学研究院 | Meteorological data correction method for power grid |
| CN113191526A (en) * | 2021-03-19 | 2021-07-30 | 华南理工大学 | Short-term wind speed interval multi-objective optimization prediction method and system based on random sensitivity |
| CN113204061A (en) * | 2021-07-06 | 2021-08-03 | 中国气象局公共气象服务中心(国家预警信息发布中心) | Method and device for constructing lattice point wind speed correction model |
| CN113253364A (en) * | 2021-06-30 | 2021-08-13 | 中国气象局公共气象服务中心(国家预警信息发布中心) | Method and device for correcting station wind speed forecast result |
-
2021
- 2021-09-14 CN CN202111071261.9A patent/CN113516320B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102914969A (en) * | 2012-09-28 | 2013-02-06 | 南方电网科学研究院有限责任公司 | Comprehensive error correction method of short-period wind power prediction system |
| CN103441506A (en) * | 2013-06-18 | 2013-12-11 | 国家电网公司 | Method for multi-target coordination reactive power optimization control of distributed wind farm in different time scales |
| CN105868534A (en) * | 2016-03-24 | 2016-08-17 | 大连理工大学 | Multi-objective optimization sampling based hydrologic model uncertainty analysis method |
| CN105956708A (en) * | 2016-05-12 | 2016-09-21 | 扬州大学 | Grey correlation time sequence based short-term wind speed forecasting method |
| CN109214582A (en) * | 2018-09-20 | 2019-01-15 | 中南大学 | A kind of Along Railway wind speed forecasting method of wind direction space correlation driving |
| KR102028606B1 (en) * | 2018-11-06 | 2019-10-04 | 한국산업기술시험원 | Windlidar calibration system and calibration method using the same |
| CN110543929A (en) * | 2019-08-29 | 2019-12-06 | 华北电力大学（保定） | wind speed interval prediction method and system based on Lorenz system |
| CN110633864A (en) * | 2019-09-20 | 2019-12-31 | 国网湖南省电力有限公司 | Wind speed numerical prediction correction method and system based on range deviation |
| CN112633544A (en) * | 2019-11-28 | 2021-04-09 | 北京金风慧能技术有限公司 | Predicted wind speed correction method and device |
| CN110852016A (en) * | 2019-12-04 | 2020-02-28 | 中国直升机设计研究所 | Reliability simulation test model correction method |
| CN111469125A (en) * | 2020-04-01 | 2020-07-31 | 南京浦航机械科技开发有限公司 | Hole site correction method applied to automatic drilling and riveting of curved surface product |
| CN112084706A (en) * | 2020-09-02 | 2020-12-15 | 合肥工业大学 | NSGA-II-based multi-objective optimization method for capacitor module assembly configuration |
| CN112288164A (en) * | 2020-10-29 | 2021-01-29 | 四川大学 | Wind power combined prediction method considering spatial correlation and correcting numerical weather forecast |
| CN112561125A (en) * | 2020-11-20 | 2021-03-26 | 浙江省气象科学研究所 | Wind speed forecast multi-data fusion correction method |
| CN112417734A (en) * | 2020-11-25 | 2021-02-26 | 国能日新科技股份有限公司 | Wind speed correction method and device based on geographic information of wind power plant |
| CN113191526A (en) * | 2021-03-19 | 2021-07-30 | 华南理工大学 | Short-term wind speed interval multi-objective optimization prediction method and system based on random sensitivity |
| CN113159714A (en) * | 2021-04-01 | 2021-07-23 | 国网河南省电力公司电力科学研究院 | Meteorological data correction method for power grid |
| CN113253364A (en) * | 2021-06-30 | 2021-08-13 | 中国气象局公共气象服务中心(国家预警信息发布中心) | Method and device for correcting station wind speed forecast result |
| CN113204061A (en) * | 2021-07-06 | 2021-08-03 | 中国气象局公共气象服务中心(国家预警信息发布中心) | Method and device for constructing lattice point wind speed correction model |
Non-Patent Citations (5)
| Title |
|---|
| LIFANG ZHANG等: ""Wind Speed Forecasting Using a Two-Stage Forecasting System With an Error Correcting and Nonlinear Ensemble Strategy"", 《IEEE ACCESS》 * |
| SAHRA KHAZAEI等: ""A high-accuracy hybrid method for short-term wind power forecasting"", 《ENERGY》 * |
| 张子杭: ""基于现场数据的风速校准及其对风电机组功率曲线的修正"", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 郭暘: ""基于风速修正的风电功率短期预测研究"", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 高淑杰: ""基于误差修正和模糊评价的风速预测研究"", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113516320B (en) | 2021-12-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dong et al. | Wind power day-ahead prediction with cluster analysis of NWP | |
| Tascikaraoglu et al. | A review of combined approaches for prediction of short-term wind speed and power | |
| Chen et al. | Short-Term Wind Power Forecasting Using Gaussian Processes. | |
| CN102938562B (en) | Prediction method of total wind electricity power in area | |
| CN105868853A (en) | Method for predicting short-term wind power combination probability | |
| CN107403015B (en) | Short-term optical power prediction method based on time series similarity | |
| CN112580900B (en) | Short-term power prediction method and system based on single fan modeling | |
| Mandal et al. | A new recursive neural network algorithm to forecast electricity price for PJM day‐ahead market | |
| CN115034485A (en) | Wind power interval prediction method and device based on data space | |
| CN115759467A (en) | Time-division integrated learning photovoltaic prediction method for error correction | |
| Das et al. | Optimized support vector regression-based model for solar power generation forecasting on the basis of online weather reports | |
| CN112465266A (en) | Bus load prediction accuracy analysis method and device and computer equipment | |
| CN112307672A (en) | BP neural network short-term wind power prediction method based on cuckoo algorithm optimization | |
| CN113516320B (en) | Wind speed correction and predicted wind speed optimization method and device based on multi-objective genetic algorithm | |
| CN115544895B (en) | Photovoltaic power station annual output guarantee rate model optimization method | |
| CN116484998A (en) | Distributed photovoltaic power station power prediction method and system based on meteorological similar day | |
| CN116191412A (en) | Power load prediction method | |
| CN115907228A (en) | Short-term power load prediction analysis method based on PSO-LSSVM | |
| CN105787813A (en) | Short-term wind power prediction method based on covariance | |
| CN115456286A (en) | Short-term photovoltaic power prediction method | |
| KR20230072219A (en) | A system for determining the optimal bid amount of a stochastic scenario technique using weather forecast data | |
| CN115563848A (en) | Distributed photovoltaic total radiation prediction method and system based on deep learning | |
| CN115310648A (en) | Medium-and-long-term wind power combination prediction method based on multi-meteorological variable model identification | |
| CN113610285A (en) | Power prediction method for distributed wind power | |
| Wang et al. | A probabilistic wind power forecasting approach based on gaussian process regression |
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 |