CN111461444A - Prediction method, system, medium and electronic device for unit power of wind power plant - Google Patents
Prediction method, system, medium and electronic device for unit power of wind power plant Download PDFInfo
- Publication number
- CN111461444A CN111461444A CN202010266686.4A CN202010266686A CN111461444A CN 111461444 A CN111461444 A CN 111461444A CN 202010266686 A CN202010266686 A CN 202010266686A CN 111461444 A CN111461444 A CN 111461444A
- Authority
- CN
- China
- Prior art keywords
- historical
- data
- period
- forecast data
- weather 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000010801 machine learning Methods 0.000 claims abstract description 90
- 238000012549 training Methods 0.000 claims abstract description 31
- 238000005457 optimization Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000007619 statistical method Methods 0.000 description 6
- 238000000053 physical method Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/10—Devices for predicting weather conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Environmental & Geological Engineering (AREA)
- Environmental Sciences (AREA)
- Medical Informatics (AREA)
- Biodiversity & Conservation Biology (AREA)
- Ecology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Atmospheric Sciences (AREA)
- Evolutionary Computation (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a system, a medium and an electronic device for predicting unit power of a wind power plant, wherein the prediction method comprises the following steps: acquiring historical meteorological forecast data and historical actual meteorological observation data corresponding to a first historical time period; acquiring historical SCADA meteorological data corresponding to a second historical time period; training a first machine learning model by taking historical meteorological forecast data corresponding to the first historical period and historical SCADA meteorological data corresponding to the second historical period as input and taking actual meteorological observation data corresponding to the first historical period as output; optimizing the weather forecast data of the future time period to be predicted by utilizing the trained first machine learning model; and predicting the unit power of the future time period to be predicted by using the optimized weather forecast data. The invention effectively improves the accuracy of power prediction.
Description
Technical Field
The invention relates to the technical field of wind power generation, in particular to a method, a system, a medium and electronic equipment for predicting unit power of a wind power plant.
Background
The unit power prediction of the wind power plant is to establish a prediction model of the output power of the wind power plant by using the data of the historical power, the historical wind speed, the topographic features, the numerical weather forecast, the running state of the wind power plant and the like of the wind power plant, use the data of the wind speed, the power curve, the numerical weather forecast and the like as the input of the model, and predict the future active power of the units in the wind power plant by combining the equipment state and the running working condition of the units in the wind power plant.
In the prior art, the main flow of short-term wind power prediction is to obtain mesoscale meteorological information of a wind power plant region in the future days through numerical meteorological forecasting, and predict the power of the wind power plant by using a statistical method or a physical modeling method based on the data. The statistical method is that the relation between the weather condition and the wind field output is found out according to historical statistical data without considering the physical process of the spatial variation of the wind speed, and then the output power of the wind power plant is predicted according to the measured data and the numerical weather forecast data; the physical method is that according to meteorological element prediction values such as wind speed, wind direction, air pressure and air temperature predicted by a numerical meteorological model and information such as contour lines, roughness and obstacles around a wind power plant, meteorological information such as wind speed and wind direction of the height of a hub of the wind generation set is calculated by adopting a micro-meteorology theory or a computational fluid mechanics method, then the predicted power of each wind generation set is calculated according to a power curve of the wind generation set, then the wake flow influence among the wind generation sets is considered, and finally the predicted power of all the wind generation sets is summed to obtain the predicted power of the wind power plant.
Factors influencing the wind power prediction accuracy of a wind power plant are many, the influence of numerical weather prediction on power prediction is the largest, and according to statistics, the numerical weather prediction link contributes more than 70% of errors of wind power prediction. The numerical weather forecast forecasts weather data such as wind speed, wind direction, air temperature, air pressure and the like, is the basis and input for carrying out wind power forecast on a wind power plant, and whether accurate numerical weather forecast can be obtained has great influence on the wind power forecast accuracy. For example: due to the randomness and uncertainty of wind, and because many wind power plants in China are built in mountainous areas, the terrain difference is large, the wind changes rapidly in a short time, the difficulty of numerical prediction of the wind speed on the near ground is large, and the wind power density is in direct proportion to the cubic power of the wind speed, so the accuracy of the numerical prediction of the wind speed directly influences the accuracy of the wind power prediction.
Based on the analysis, in the prior art, the unit power of the wind power plant is predicted by directly utilizing the numerical weather forecast, and errors caused by various factors exist in numerical weather forecast data, so that the accuracy of power prediction is seriously influenced.
Disclosure of Invention
The invention aims to overcome the defect that the accuracy of predicting the unit power of a wind power plant by directly utilizing numerical weather forecast data in the prior art is poor, and provides a method, a system, a medium and electronic equipment for predicting the unit power of the wind power plant.
The invention solves the technical problems through the following technical scheme:
a prediction method of unit power of a wind power plant comprises the following steps:
acquiring historical meteorological forecast data and historical actual meteorological observation data corresponding to a first historical time period;
acquiring historical SCADA meteorological data corresponding to a second historical time period, wherein the second historical time period is a historical time period which takes the end time of the first historical time period as a reference and forwards shifts the interval length corresponding to a future time period to be predicted, and the length of the first historical time period is equal to that of the second historical time period;
training a first machine learning model by taking historical meteorological forecast data corresponding to the first historical period and historical SCADA meteorological data corresponding to the second historical period as input and taking actual meteorological observation data corresponding to the first historical period as output;
optimizing the weather forecast data of the future time period to be predicted by using the trained first machine learning model to obtain optimized weather forecast data;
and predicting the unit power of the future time period to be predicted by using the optimized weather forecast data.
Preferably, the step of optimizing the weather forecast data of the future period to be predicted by using the trained first machine learning model to obtain optimized weather forecast data includes:
acquiring weather forecast data in a future period to be predicted and historical SCADA weather data in a third history period, wherein the third history period is a history period which is shifted forwards by an interval length corresponding to the future period to be predicted by taking the starting time of the future period to be predicted as a reference;
inputting the weather forecast data in the future period to be predicted and the historical SCADA weather data in the third historical period into the trained first machine learning model to obtain optimized weather forecast data corresponding to the future period to be predicted.
Preferably, the future time period to be predicted includes N × M weather forecast data, where N is the number of the start-up times, and M is the number of spatial resolutions respectively corresponding to each of the start-up times; n and M are positive integers;
the step of training the first machine learning model comprises:
and respectively training the first machine learning model by taking the historical weather forecast data of the first historical period and the historical SCADA weather data of the second historical period corresponding to the N x M weather forecast data as input and taking the actual weather observation data corresponding to the first historical period as output so as to obtain the N x M trained first machine learning models.
Preferably, the step of training the first machine learning model further comprises:
respectively and correspondingly inputting historical weather forecast data corresponding to the first historical time period and historical SCADA weather data corresponding to the second historical time period, which correspond to the N x M weather forecast data, into the trained N x M first machine learning models to obtain N x M optimized historical weather forecast data;
calculating weather prediction probabilities by using the N × M optimized historical weather forecast data and the N × M historical actual weather observation data to obtain N × M weather prediction probabilities;
and training the second machine learning model by taking the N × M optimized historical meteorological forecast data as input and the N × M meteorological prediction probabilities as output so as to obtain a trained second machine learning model.
Preferably, the step of optimizing the weather forecast data of the future period to be predicted by using the trained first machine learning model to obtain optimized weather forecast data includes:
respectively optimizing the N × M weather forecast data of the future time period to be predicted by using the trained N × M first machine learning models to obtain N × M optimized weather forecast data;
the step of predicting the unit power of the future time period to be predicted by using the optimized weather forecast data comprises the following steps:
inputting each optimized weather forecast data corresponding to the future time period to be predicted into the trained second machine learning model respectively to obtain a weather prediction probability corresponding to each optimized weather forecast data;
multiplying each optimized weather forecast data by the corresponding weather forecast probability to obtain N × M forecast member data;
summing the N × M forecast member data to obtain ensemble forecast data;
and predicting the unit power of the future time period to be predicted by using the ensemble prediction data.
Preferably, the historical meteorological forecast data, the historical SCADA meteorological data, and the actual meteorological observation data include at least one of wind speed, wind direction, air temperature, and air pressure.
A prediction system of a group power of a wind farm, the prediction system comprising:
the data acquisition module is used for acquiring historical meteorological forecast data and historical actual meteorological observation data corresponding to the first historical time period;
the data acquisition module is further used for acquiring historical SCADA meteorological data corresponding to a second historical time period, the second historical time period is a historical time period which takes the end time of the first historical time period as a reference and is shifted forwards by an interval length corresponding to a future time period to be predicted, and the length of the first historical time period is equal to that of the second historical time period;
the training module is used for training a first machine learning model by taking historical weather forecast data corresponding to the first historical period and historical SCADA weather data corresponding to the second historical period as input and taking actual weather observation data corresponding to the first historical period as output;
the optimization module is used for optimizing the weather forecast data of the future time period to be predicted by utilizing the trained first machine learning model so as to obtain optimized weather forecast data;
and the prediction module is used for predicting the unit power of the future time period to be predicted by utilizing the optimized weather forecast data.
Preferably, the optimization module is configured to obtain weather forecast data in a future period to be predicted and historical SCADA weather data in a third historical period, where the third historical period is a historical period that is shifted forward by an interval length corresponding to the future period to be predicted with reference to the starting time of the future period to be predicted; inputting the weather forecast data in the future period to be predicted and the historical SCADA weather data in the third historical period into the trained first machine learning model to obtain optimized weather forecast data corresponding to the future period to be predicted.
Preferably, the future time period to be predicted includes N × M weather forecast data, where N is the number of the start-up times, and M is the number of spatial resolutions respectively corresponding to each of the start-up times; n and M are positive integers;
the training module is further used for taking historical weather forecast data of the first historical time period and historical SCADA weather data of the second historical time period, which correspond to the N x M weather forecast data respectively, as input, and taking actual weather observation data corresponding to the first historical time period as output, and respectively training the first machine learning model to obtain the N x M first machine learning models.
Preferably, the prediction system further comprises a calculation module;
the optimization module is further used for correspondingly inputting historical weather forecast data corresponding to the first historical time period and historical SCADA weather data corresponding to the second historical time period, which correspond to the N x M weather forecast data, into the trained N x M first machine learning models respectively so as to obtain N x M optimized historical weather forecast data;
the calculation module is further used for calculating weather prediction probabilities by using the N × M optimized historical weather forecast data and the N × M historical actual weather observation data to obtain N × M weather prediction probabilities;
the training module is further used for training the second machine learning model by taking the N × M optimized historical meteorological forecast data as input and the N × M meteorological prediction probabilities as output so as to obtain a trained second machine learning model.
Preferably, the optimization module is further configured to optimize the N × M weather forecast data of the future time period to be predicted by using the trained N × M first machine learning models, respectively, so as to obtain N × M optimized weather forecast data;
the prediction module is further configured to input each optimized weather forecast data corresponding to the future time period to be predicted into the trained second machine learning model, so as to obtain a weather prediction probability corresponding to each optimized weather forecast data; multiplying each optimized weather forecast data by the corresponding weather forecast probability to obtain N × M forecast member data; summing the N × M forecast member data to obtain ensemble forecast data; and predicting the unit power of the future time period to be predicted by using the ensemble prediction data.
Preferably, the historical meteorological forecast data, the historical SCADA meteorological data, and the actual meteorological observation data include at least one of wind speed, wind direction, air temperature, and air pressure.
An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor when executing the computer program implementing the steps of the aforementioned method for predicting a power of a group of a wind farm.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the aforementioned method of predicting a group power of a wind farm.
The positive progress effects of the invention are as follows: according to the prediction method and the prediction system for the unit power of the wind power plant, provided by the invention, the machine learning model is trained through the historical data, and then the trained machine learning model is used for optimizing the meteorological forecast data, so that the error between the meteorological forecast data and the actual data is reduced, the uncertainty of the input data in the wind power prediction system is further reduced, and the power prediction precision is effectively improved.
Drawings
Fig. 1 is a flowchart of a method for predicting a group power of a wind farm in embodiment 1.
Fig. 2 is a schematic diagram showing the correlation between a plurality of periods in embodiment 1.
Fig. 3 is a flowchart of a method for predicting the group power of the wind farm in embodiment 2.
Fig. 4 is a block diagram of a prediction system of group power of a wind farm in embodiment 3.
Fig. 5 is a block diagram showing a configuration of a prediction system of group power of a wind farm in embodiment 4.
Fig. 6 is a block diagram showing the configuration of an electronic apparatus according to embodiment 5.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
Example 1
The embodiment provides a method for predicting unit power of a wind farm, as shown in fig. 1, the method includes the following steps:
step S10: acquiring historical meteorological forecast data and historical actual meteorological observation data corresponding to a first historical time period;
preferably, the weather forecast data may be mesoscale weather forecast data, said mesoscale corresponding to a spatial resolution in the order of a few kilometres to a few tens of kilometres. The actual meteorological observation data may refer to meteorological observation data at a hub height of a wind tower fan in a wind farm.
Step S11: acquiring historical SCADA meteorological data corresponding to a second historical time period, wherein the second historical time period is a historical time period which takes the end time of the first historical time period as a reference and forwards shifts the interval length corresponding to a future time period to be predicted, and the length of the first historical time period is equal to that of the second historical time period;
step S12: training a first machine learning model by taking historical meteorological forecast data corresponding to the first historical period and historical SCADA meteorological data corresponding to the second historical period as input and taking actual meteorological observation data corresponding to the first historical period as output;
specifically, the first machine learning model may be trained using methods that employ extreme tree regression, random forest, or gradient boosting regression trees, among others.
Step S13: optimizing the weather forecast data of the future time period to be predicted by using the trained first machine learning model to obtain optimized weather forecast data;
step S14: and predicting the unit power of the future time period to be predicted by using the optimized weather forecast data.
Specifically, a statistical method or a physical method in the prior art may be adopted to predict the power of the wind farm, where the statistical method is to establish a statistical relationship according to historical weather forecast data and historical power output of the wind farm (or each wind turbine), so as to obtain a predicted value of the power output of the wind farm (or each wind turbine) at each future time by using the relationship for the weather forecast data at each future time; the physical method is to calculate the wind speed condition at the hub height of each fan position according to the weather forecast data in the form of a physical equation, and obtain the power output of each fan at each future time according to the power curve (corresponding relation between the wind speed and the power output) of the fan, so as to obtain the power output of the whole wind power plant at each future time.
The historical meteorological forecast data, the historical SCADA meteorological data, and the actual meteorological observation data comprise at least one of wind speed, wind direction, air temperature, and air pressure.
Further, the step S13 may specifically include the following steps: acquiring weather forecast data in a future period to be predicted and historical SCADA weather data in a third history period, wherein the third history period is a history period which is shifted forwards by an interval length corresponding to the future period to be predicted by taking the starting time of the future period to be predicted as a reference; and then, inputting the weather forecast data in the future period to be predicted and the historical SCADA weather data in the third historical period into the trained first machine learning model to obtain optimized weather forecast data corresponding to the future period to be predicted.
As shown in fig. 2, in a specific application scenario, if the current day is sunday, the data of the sunday and the data before the sunday are known. If the future period to be predicted is monday and tuesday (the interval length is 2 days), the first history period (the history period is the time interval before the future period to be predicted occurs) may be determined to include sunday, saturday, and friday, and the second history period may be determined to be wednesday, thursday, and friday, that is, the first history period is shifted forward by the interval length of the future period to be predicted. The third history period is saturday and sunday of the last week.
According to the prediction method for the unit power of the wind power plant, the machine learning model is trained through the historical data, and then the trained machine learning model is used for optimizing the meteorological forecast data, so that the error between the meteorological forecast data and the actual data is reduced, the uncertainty of the input data in the wind power prediction system is further reduced, and the power prediction precision is effectively improved.
Example 2
The embodiment provides a method for predicting the unit power of a wind power plant, which is a further improvement on the basis of embodiment 1, as shown in fig. 3.
In this embodiment, the future time period to be predicted may include N × M weather forecast data, where N is the number of reporting times (e.g., 0h, 6h, 12h, and 18h … of the day before the current time), and M is the number of spatial resolutions (e.g., 3km, 9km, and 27km …) respectively corresponding to each of the reporting times; n and M are both positive integers.
Based on this, the step S12 may include:
step S121: and respectively training the first machine learning model by taking the historical weather forecast data of the first historical period and the historical SCADA weather data of the second historical period corresponding to the N x M weather forecast data as input and taking the actual weather observation data corresponding to the first historical period as output so as to obtain the N x M trained first machine learning models.
The step S12 may further include:
step S20: respectively and correspondingly inputting historical weather forecast data corresponding to the first historical time period and historical SCADA weather data corresponding to the second historical time period, which correspond to the N x M weather forecast data, into the trained N x M first machine learning models to obtain N x M optimized historical weather forecast data;
step S21: calculating weather prediction probabilities by using the N × M optimized historical weather forecast data and the N × M historical actual weather observation data to obtain N × M weather prediction probabilities;
specifically, the weather prediction probability may be obtained by performing normalization after calculating an inverse of an absolute value of a deviation between the optimized historical weather forecast data and the historical actual weather observation data.
Step S22: and training the second machine learning model by taking the N × M optimized historical meteorological forecast data as input and the N × M meteorological prediction probabilities as output so as to obtain a trained second machine learning model.
Specifically, the training of the second machine learning model may be performed by using a bp (back propagation) neural network.
The step S13 may be specifically executed by:
step S131: respectively optimizing the N × M weather forecast data of the future time period to be predicted by using the trained N × M first machine learning models to obtain N × M optimized weather forecast data;
the step S14 may specifically include:
step S141: inputting each optimized weather forecast data corresponding to the future time period to be predicted into the trained second machine learning model respectively to obtain a weather prediction probability corresponding to each optimized weather forecast data;
step S142: multiplying each optimized weather forecast data by the corresponding weather forecast probability to obtain N × M forecast member data;
step S143: summing the N × M forecast member data to obtain ensemble forecast data;
step S144: and predicting the unit power of the future time period to be predicted by using the ensemble prediction data.
In one particular application scenario, for example: aiming at a certain wind power plant which starts to operate, a production wind measuring tower is built in the wind power plant, and the wind measuring height of the wind measuring tower is not lower than the height of a fan hub. The method comprises the steps that numerical weather forecast is conducted on the wind power plant for three days in the future every day based on a moderate weather mode WRF (weather forecast mode), 3 layers of nested grids are used in the mode, horizontal resolutions are respectively 27km, 9km and 3km, numerical forecast is conducted on weather forecast background fields issued by 0 point, 6 points, 12 points and 18 points in the previous day respectively, and medium-scale numerical weather forecast data of the wind power plant for three days in the future are obtained, wherein the medium-scale numerical weather forecast data are 12 different in spatial resolution and reporting time.
The method comprises the steps of establishing an optimization model (a first machine learning model) for each member by adopting historical mesoscale meteorological forecasts (comprising meteorological elements such as wind speed, wind direction, air pressure and air temperature) of 12 members, corresponding SCADA meteorological data of a fan in a wind field and actual meteorological observation data of a hub height layer of the fan of a wind measuring tower, obtaining optimized mesoscale meteorological forecast data of each member through the model, then establishing a set member forecast accuracy probability prediction model (a second machine learning model) based on a BP neural network method, and obtaining the probability that the optimized forecast data of each member is closest to an observed value through the model.
And then, optimizing the weather forecast data to be optimized by utilizing the established model. For example, collective forecasting can be performed on three days in the future to obtain mesoscale numerical weather forecast data of 12 wind farm areas in three days in the future, the data are input into the established first machine learning model and the second machine learning model to obtain weather forecast data after 12 members are optimized and the probability of the weather forecast data being closest to the observed value, and weighted average is performed to obtain final collective forecast data. And inputting the ensemble prediction data as mesoscale data for wind power plant power prediction, and performing power prediction on the wind power plant for three days in the future.
According to the prediction method for the unit power of the wind power plant, a mode of integrating ensemble prediction and various machine learning algorithms is introduced, the prediction result of the unit power is closer to a real scene through a plurality of spatial resolutions, weather prediction data corresponding to a plurality of starting moments and the probability that each weather prediction can be accurately predicted by combining, and therefore prediction accuracy is improved.
Example 3
The present embodiment provides a system for predicting a unit power of a wind farm, as shown in fig. 4, where the prediction system 1 includes:
the data acquisition module 11 is configured to acquire historical weather forecast data and historical actual weather observation data corresponding to a first historical time period;
preferably, the weather forecast data may be mesoscale weather forecast data, said mesoscale corresponding to a spatial resolution in the order of a few kilometres to a few tens of kilometres. The actual meteorological observation data may refer to meteorological observation data at a hub height of a wind tower fan in a wind farm.
The data acquisition module 11 is further configured to acquire historical SCADA meteorological data corresponding to a second historical period, where the second historical period is a historical period that is shifted forward by an interval length corresponding to a future period to be predicted with reference to the end time of the first historical period, and the length of the first historical period is equal to the length of the second historical period;
a training module 12, configured to train a first machine learning model by taking historical weather forecast data corresponding to the first historical period and historical SCADA weather data corresponding to the second historical period as inputs, and taking actual weather observation data corresponding to the first historical period as an output;
specifically, the first machine learning model may be trained using methods that employ extreme tree regression, random forest, or gradient boosting regression trees, among others.
The optimization module 13 is configured to optimize the weather forecast data in the future period to be predicted by using the trained first machine learning model to obtain optimized weather forecast data;
and the prediction module 14 is configured to predict the unit power in the future time period to be predicted by using the optimized weather forecast data.
Specifically, a statistical method or a physical method in the prior art may be adopted to predict the power of the wind farm, where the statistical method is to establish a statistical relationship according to historical weather forecast data and historical power output of the wind farm (or each wind turbine), so as to obtain a predicted value of the power output of the wind farm (or each wind turbine) at each future time by using the relationship for the weather forecast data at each future time; the physical method is to calculate the wind speed condition at the hub height of each fan position according to the weather forecast data in the form of a physical equation, and obtain the power output of each fan at each future time according to the power curve (corresponding relation between the wind speed and the power output) of the fan, so as to obtain the power output of the whole wind power plant at each future time.
The historical meteorological forecast data, the historical SCADA meteorological data, and the actual meteorological observation data comprise at least one of wind speed, wind direction, air temperature, and air pressure.
In this embodiment, the optimization module 13 is configured to obtain weather forecast data in a future period to be predicted and historical SCADA weather data in a third historical period, where the third historical period is a historical period that is shifted forward by an interval length corresponding to the future period to be predicted with reference to the starting time of the future period to be predicted; inputting the weather forecast data in the future period to be predicted and the historical SCADA weather data in the third historical period into the trained first machine learning model to obtain optimized weather forecast data corresponding to the future period to be predicted.
When the prediction system for the unit power of the wind power plant provided by the embodiment operates, the machine learning model is trained through the historical data, and then the trained machine learning model is used for optimizing the weather forecast data, so that the error between the weather forecast data and the actual data is reduced, the uncertainty of the input data in the wind power prediction system is further reduced, and the power prediction precision is effectively improved.
Example 4
The embodiment provides a prediction system of the unit power of the wind power plant, which is a further improvement on the basis of embodiment 3, as shown in fig. 5.
In this embodiment, the future time period to be predicted may include N × M weather forecast data, where N is the number of reporting times (e.g., 0h, 6h, 12h, and 18h … of the day before the current time), and M is the number of spatial resolutions (e.g., 3km, 9km, and 27km …) respectively corresponding to each of the reporting times; n and M are both positive integers.
The training module 12 is further configured to train a first machine learning model by using, as inputs, historical weather forecast data of the first historical period and historical SCADA weather data of the second historical period, which correspond to the N × M weather forecast data, respectively, and by using, as outputs, actual weather observation data corresponding to the first historical period, respectively, to obtain the N × M first machine learning models.
The prediction system 1 further comprises a calculation module 15;
the optimization module 13 is further configured to correspondingly input the trained N × M first machine learning models to the historical meteorological forecast data corresponding to the first historical time period and the historical SCADA meteorological data corresponding to the second historical time period, respectively, corresponding to the N × M meteorological forecast data, so as to obtain N × M optimized historical meteorological forecast data;
the calculating module 15 is further configured to calculate weather prediction probabilities by using the N × M optimized historical weather forecast data and the N × M historical actual weather observation data, so as to obtain N × M weather prediction probabilities;
specifically, the weather prediction probability may be obtained by performing normalization after calculating an inverse of an absolute value of a deviation between the optimized historical weather forecast data and the historical actual weather observation data.
The training module 12 is further configured to train the second machine learning model with the N × M optimized historical weather forecast data as input and the N × M weather prediction probabilities as output, so as to obtain a trained second machine learning model.
Specifically, the training of the second machine learning model may be performed by using a bp (back propagation) neural network.
In this embodiment, the optimization module is further configured to optimize the N × M weather forecast data of the future time period to be predicted by using the trained N × M first machine learning models, respectively, so as to obtain N × M optimized weather forecast data;
the prediction module 14 is further configured to input each optimized weather forecast data corresponding to the future time period to be predicted into the trained second machine learning model, so as to obtain a weather prediction probability corresponding to each optimized weather forecast data; multiplying each optimized weather forecast data by the corresponding weather forecast probability to obtain N × M forecast member data; summing the N × M forecast member data to obtain ensemble forecast data; and predicting the unit power of the future time period to be predicted by using the ensemble prediction data.
In one particular application scenario, for example: aiming at a certain wind power plant which starts to operate, a production wind measuring tower is built in the wind power plant, and the wind measuring height of the wind measuring tower is not lower than the height of a fan hub. The method comprises the steps that numerical weather forecast is conducted on the wind power plant for three days in the future every day based on a moderate weather mode WRF (weather forecast mode), 3 layers of nested grids are used in the mode, horizontal resolutions are respectively 27km, 9km and 3km, numerical forecast is conducted on weather forecast background fields issued by 0 point, 6 points, 12 points and 18 points in the previous day respectively, and medium-scale numerical weather forecast data of the wind power plant for three days in the future are obtained, wherein the medium-scale numerical weather forecast data are 12 different in spatial resolution and reporting time.
The method comprises the steps of establishing an optimization model (a first machine learning model) for each member by adopting historical mesoscale meteorological forecasts (comprising meteorological elements such as wind speed, wind direction, air pressure and air temperature) of 12 members, corresponding SCADA meteorological data of a fan in a wind field and actual meteorological observation data of a hub height layer of the fan of a wind measuring tower, obtaining optimized mesoscale meteorological forecast data of each member through the model, then establishing a set member forecast accuracy probability prediction model (a second machine learning model) based on a BP neural network method, and obtaining the probability that the optimized forecast data of each member is closest to an observed value through the model.
And then, optimizing the weather forecast data to be optimized by utilizing the established model. For example, collective forecasting can be performed on three days in the future to obtain mesoscale numerical weather forecast data of 12 wind farm areas in three days in the future, the data are input into the established first machine learning model and the second machine learning model to obtain weather forecast data after 12 members are optimized and the probability of the weather forecast data being closest to the observed value, and weighted average is performed to obtain final collective forecast data. And inputting the ensemble prediction data as mesoscale data for wind power plant power prediction, and performing power prediction on the wind power plant for three days in the future.
The prediction system for the unit power of the wind power plant provided by the embodiment introduces a mode of fusing ensemble prediction and various machine learning algorithms, and enables the prediction result of the unit power to be closer to a real scene by combining the weather prediction data corresponding to a plurality of spatial resolutions and a plurality of starting moments and the probability that each weather prediction can be accurately predicted, so that the prediction accuracy is improved.
Example 5
The present invention also provides an electronic device, as shown in fig. 6, which may include a memory, a processor, and a computer program stored on the memory and executable on the processor, the processWhen the device executes a computer program Method for predicting unit power of wind farm in aforementioned embodiment 1 or 2The steps of the method.
It should be understood that the electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of the application of the embodiments of the present invention.
As shown in fig. 6, the electronic device 2 may be embodied in the form of a general purpose computing device, such as: which may be a server device. The components of the electronic device 2 may include, but are not limited to: the at least one processor 3, the at least one memory 4, and a bus 5 connecting the various system components (including the memory 4 and the processor 3).
The bus 5 may include a data bus, an address bus, and a control bus.
The memory 4 may include volatile memory, such as Random Access Memory (RAM)41 and/or cache memory 42, and may further include Read Only Memory (ROM) 43.
The memory 4 may also include a program tool 45 (or utility tool) having a set (at least one) of program modules 44, such program modules 44 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The processor 3 executes various functional applications and data processing, such as the steps of the prediction method of the group power of the wind farm in the foregoing embodiment 1 or 2 of the present invention, by running the computer program stored in the memory 4.
The electronic device 2 may also communicate with one or more external devices 6 (e.g., keyboard, pointing device, etc.), such communication may be through input/output (I/O) interfaces 7, and the model-generated electronic device 2 may also communicate with one or more networks (e.g., a local area network L AN, a wide area network WAN, and/or a public network) through a network adapter 8.
As shown in FIG. 6, the network adapter 8 may communicate with other modules of the model-generated electronic device 2 via the bus 5. It will be appreciated by those skilled in the art that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the model-generated electronic device 2, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.
It should be noted that although in the above detailed description several units/modules or sub-units/modules of the electronic device are mentioned, such division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more of the units/modules described above may be embodied in one unit/module according to embodiments of the invention. Conversely, the features and functions of one unit/module described above may be further divided into embodiments by a plurality of units/modules.
Example 6
The present embodiment provides a computer-readable storage medium on which a computer program is stored, which when executed by a processor implements the steps of the prediction method of the group power of the wind farm in the foregoing embodiment 1 or 2.
More specific ways in which the computer-readable storage medium may be employed may include, but are not limited to: a portable disk, a hard disk, random access memory, read only memory, erasable programmable read only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing.
In a possible implementation, the invention can also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps of implementing the method for predicting the power of a group of wind farms in the preceding embodiment 1 or 2, when the program product is run on the terminal device.
Where program code for carrying out the invention is written in any combination of one or more programming languages, the program code may execute entirely on the user device, partly on the user device, as a stand-alone software package, partly on the user device and partly on a remote device or entirely on the remote device.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.
Claims (14)
1. A prediction method for unit power of a wind power plant is characterized by comprising the following steps:
acquiring historical meteorological forecast data and historical actual meteorological observation data corresponding to a first historical time period;
acquiring historical SCADA meteorological data corresponding to a second historical time period, wherein the second historical time period is a historical time period which takes the end time of the first historical time period as a reference and forwards shifts the interval length corresponding to a future time period to be predicted, and the length of the first historical time period is equal to that of the second historical time period;
training a first machine learning model by taking historical meteorological forecast data corresponding to the first historical period and historical SCADA meteorological data corresponding to the second historical period as input and taking actual meteorological observation data corresponding to the first historical period as output;
optimizing the weather forecast data of the future time period to be predicted by using the trained first machine learning model to obtain optimized weather forecast data;
and predicting the unit power of the future time period to be predicted by using the optimized weather forecast data.
2. The method for predicting the unit power of a wind farm according to claim 1, wherein the step of optimizing the weather forecast data of the future period to be predicted by using the trained first machine learning model to obtain the optimized weather forecast data comprises:
acquiring weather forecast data in a future period to be predicted and historical SCADA weather data in a third history period, wherein the third history period is a history period which is shifted forwards by an interval length corresponding to the future period to be predicted by taking the starting time of the future period to be predicted as a reference;
inputting the weather forecast data in the future period to be predicted and the historical SCADA weather data in the third historical period into the trained first machine learning model to obtain optimized weather forecast data corresponding to the future period to be predicted.
3. The method for predicting the unit power of the wind farm according to claim 1, wherein the future period to be predicted comprises N × M weather forecast data, where N is the number of the start-up times and M is the number of spatial resolutions respectively corresponding to each of the start-up times; n and M are positive integers;
the step of training the first machine learning model comprises:
and respectively training the first machine learning model by taking the historical weather forecast data of the first historical period and the historical SCADA weather data of the second historical period corresponding to the N x M weather forecast data as input and taking the actual weather observation data corresponding to the first historical period as output so as to obtain the N x M trained first machine learning models.
4. The method for predicting the group power of a wind farm according to claim 3,
the step of training the first machine learning model further comprises:
respectively and correspondingly inputting historical weather forecast data corresponding to the first historical time period and historical SCADA weather data corresponding to the second historical time period, which correspond to the N x M weather forecast data, into the trained N x M first machine learning models to obtain N x M optimized historical weather forecast data;
calculating weather prediction probabilities by using the N × M optimized historical weather forecast data and the N × M historical actual weather observation data to obtain N × M weather prediction probabilities;
and training the second machine learning model by taking the N × M optimized historical meteorological forecast data as input and the N × M meteorological prediction probabilities as output so as to obtain a trained second machine learning model.
5. The method for predicting the unit power of a wind farm according to claim 4,
the step of optimizing the weather forecast data of the future period to be predicted by using the trained first machine learning model to obtain the optimized weather forecast data comprises the following steps:
respectively optimizing the N × M weather forecast data of the future time period to be predicted by using the trained N × M first machine learning models to obtain N × M optimized weather forecast data;
the step of predicting the unit power of the future time period to be predicted by using the optimized weather forecast data comprises the following steps:
inputting each optimized weather forecast data corresponding to the future time period to be predicted into the trained second machine learning model respectively to obtain a weather prediction probability corresponding to each optimized weather forecast data;
multiplying each optimized weather forecast data by the corresponding weather forecast probability to obtain N × M forecast member data;
summing the N × M forecast member data to obtain ensemble forecast data;
and predicting the unit power of the future time period to be predicted by using the ensemble prediction data.
6. A method of predicting unit power for a wind farm according to any of the claims 1 to 5, wherein said historical meteorological forecast data, said historical SCADA meteorological data and said actual meteorological observation data comprise at least one of wind speed, wind direction, air temperature and air pressure.
7. A prediction system for group power of a wind farm, the prediction system comprising:
the data acquisition module is used for acquiring historical meteorological forecast data and historical actual meteorological observation data corresponding to the first historical time period;
the data acquisition module is further used for acquiring historical SCADA meteorological data corresponding to a second historical time period, the second historical time period is a historical time period which takes the end time of the first historical time period as a reference and is shifted forwards by an interval length corresponding to a future time period to be predicted, and the length of the first historical time period is equal to that of the second historical time period;
the training module is used for training a first machine learning model by taking historical weather forecast data corresponding to the first historical period and historical SCADA weather data corresponding to the second historical period as input and taking actual weather observation data corresponding to the first historical period as output;
the optimization module is used for optimizing the weather forecast data of the future time period to be predicted by utilizing the trained first machine learning model so as to obtain optimized weather forecast data;
and the prediction module is used for predicting the unit power of the future time period to be predicted by utilizing the optimized weather forecast data.
8. The system for predicting group power of a wind farm according to claim 7,
the optimization module is used for acquiring weather forecast data in a future period to be predicted and historical SCADA weather data in a third historical period, wherein the third historical period is a historical period which takes the starting time of the future period to be predicted as a reference and forwards shifts the interval length corresponding to the future period to be predicted; inputting the weather forecast data in the future period to be predicted and the historical SCADA weather data in the third historical period into the trained first machine learning model to obtain optimized weather forecast data corresponding to the future period to be predicted.
9. The system for predicting the unit power of a wind farm according to claim 7, wherein the future period to be predicted comprises N x M weather forecast data, where N is the number of the attack moments and M is the number of spatial resolutions respectively corresponding to each of the attack moments; n and M are positive integers;
the training module is further used for taking historical weather forecast data of the first historical time period and historical SCADA weather data of the second historical time period, which correspond to the N x M weather forecast data respectively, as input, and taking actual weather observation data corresponding to the first historical time period as output, and respectively training the first machine learning model to obtain the N x M first machine learning models.
10. The system for predicting the group power of a wind farm according to claim 9,
the prediction system further comprises a calculation module;
the optimization module is further used for correspondingly inputting historical weather forecast data corresponding to the first historical time period and historical SCADA weather data corresponding to the second historical time period, which correspond to the N x M weather forecast data, into the trained N x M first machine learning models respectively so as to obtain N x M optimized historical weather forecast data;
the calculation module is further used for calculating weather prediction probabilities by using the N × M optimized historical weather forecast data and the N × M historical actual weather observation data to obtain N × M weather prediction probabilities;
the training module is further used for training the second machine learning model by taking the N × M optimized historical meteorological forecast data as input and the N × M meteorological prediction probabilities as output so as to obtain a trained second machine learning model.
11. The system for predicting group power of a wind farm according to claim 10,
the optimization module is further used for respectively optimizing the N × M weather forecast data of the future time period to be predicted by using the trained N × M first machine learning models to obtain N × M optimized weather forecast data;
the prediction module is further configured to input each optimized weather forecast data corresponding to the future time period to be predicted into the trained second machine learning model, so as to obtain a weather prediction probability corresponding to each optimized weather forecast data; multiplying each optimized weather forecast data by the corresponding weather forecast probability to obtain N × M forecast member data; summing the N × M forecast member data to obtain ensemble forecast data; and predicting the unit power of the future time period to be predicted by using the ensemble prediction data.
12. A prediction system of crew power for a wind farm according to any of the claims 7-11, characterized in that the historical meteorological forecast data, the historical SCADA meteorological data and the actual meteorological observation data comprise at least one of wind speed, wind direction, air temperature and air pressure.
13. 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, when executing the computer program, implements the steps of the method for prediction of group power for a wind farm according to any of claims 1-6.
14. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method for prediction of group power for a wind farm according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010266686.4A CN111461444B (en) | 2020-04-07 | 2020-04-07 | Method, system, medium and electronic equipment for predicting unit power of wind power plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010266686.4A CN111461444B (en) | 2020-04-07 | 2020-04-07 | Method, system, medium and electronic equipment for predicting unit power of wind power plant |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111461444A true CN111461444A (en) | 2020-07-28 |
| CN111461444B CN111461444B (en) | 2023-07-18 |
Family
ID=71683570
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010266686.4A Active CN111461444B (en) | 2020-04-07 | 2020-04-07 | Method, system, medium and electronic equipment for predicting unit power of wind power plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111461444B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111881568A (en) * | 2020-07-22 | 2020-11-03 | 旻投(上海)数据科技有限公司 | Method and system for improving wind power prediction precision |
| CN112101626A (en) * | 2020-08-14 | 2020-12-18 | 安徽继远软件有限公司 | Distributed photovoltaic power generation power prediction method and system |
| CN112836870A (en) * | 2021-01-25 | 2021-05-25 | 华北电力大学 | Method, device, equipment and computer readable storage medium for predicting wind power |
| CN113095562A (en) * | 2021-04-07 | 2021-07-09 | 安徽天能清洁能源科技有限公司 | Ultra-short term power generation prediction method and device based on Kalman filtering and LSTM |
| CN113341481A (en) * | 2021-07-02 | 2021-09-03 | 北京玖天气象科技有限公司 | Method and device for determining weather forecast result |
| CN113449928A (en) * | 2021-07-14 | 2021-09-28 | 清华四川能源互联网研究院 | Wind field power prediction method, system, server and computer readable storage medium |
| CN113537595A (en) * | 2021-07-16 | 2021-10-22 | 上海电气风电集团股份有限公司 | Model training method, wind power prediction method, system, device and medium |
| CN113822418A (en) * | 2021-09-24 | 2021-12-21 | 中节能风力发电股份有限公司 | Wind power plant power prediction method, system, device and storage medium |
| CN113988394A (en) * | 2021-10-21 | 2022-01-28 | 中国电建集团华东勘测设计研究院有限公司 | Wind power ultra-short-term power prediction method based on gram matrix and convolutional neural network |
| CN114418180A (en) * | 2021-12-16 | 2022-04-29 | 广东电网有限责任公司 | Ultra-short-term prediction method and device for wind power and storage medium |
| CN114565057A (en) * | 2022-03-15 | 2022-05-31 | 中科三清科技有限公司 | Machine learning-based grading field identification method and device, storage medium and terminal |
| CN114744623A (en) * | 2022-06-09 | 2022-07-12 | 深圳万甲荣实业有限公司 | New energy power generation prediction method and system based on deep learning |
| CN115186907A (en) * | 2022-07-14 | 2022-10-14 | 华润电力技术研究院有限公司 | Method, system, equipment and medium for predicting long-term power generation amount in wind power plant |
| CN115905997A (en) * | 2022-10-28 | 2023-04-04 | 安徽省国家电投和新电力技术研究有限公司 | Wind turbine generator meteorological disaster early warning method and system based on prediction deviation optimization |
| CN116307153A (en) * | 2023-03-07 | 2023-06-23 | 广东热矩智能科技有限公司 | Meteorological prediction method and device for energy conservation of refrigeration and heating system and electronic equipment |
| CN117892099A (en) * | 2024-03-18 | 2024-04-16 | 湖南科技大学 | Wind turbine generator service efficiency evaluation method and system based on probabilistic neural network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955749A (en) * | 2014-03-19 | 2014-07-30 | 内蒙古电力勘测设计院 | Sun direct radiation value prediction method and system |
| CN104299044A (en) * | 2014-07-01 | 2015-01-21 | 沈阳工程学院 | Clustering-analysis-based wind power short-term prediction system and prediction method |
| CN104318332A (en) * | 2014-10-29 | 2015-01-28 | 国家电网公司 | Power load predicting method and device |
| CN108832663A (en) * | 2018-07-18 | 2018-11-16 | 北京天诚同创电气有限公司 | The prediction technique and equipment of the generated output of micro-capacitance sensor photovoltaic generating 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 |
-
2020
- 2020-04-07 CN CN202010266686.4A patent/CN111461444B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955749A (en) * | 2014-03-19 | 2014-07-30 | 内蒙古电力勘测设计院 | Sun direct radiation value prediction method and system |
| CN104299044A (en) * | 2014-07-01 | 2015-01-21 | 沈阳工程学院 | Clustering-analysis-based wind power short-term prediction system and prediction method |
| CN104318332A (en) * | 2014-10-29 | 2015-01-28 | 国家电网公司 | Power load predicting method and device |
| CN108832663A (en) * | 2018-07-18 | 2018-11-16 | 北京天诚同创电气有限公司 | The prediction technique and equipment of the generated output of micro-capacitance sensor photovoltaic generating 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 |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111881568A (en) * | 2020-07-22 | 2020-11-03 | 旻投(上海)数据科技有限公司 | Method and system for improving wind power prediction precision |
| CN112101626A (en) * | 2020-08-14 | 2020-12-18 | 安徽继远软件有限公司 | Distributed photovoltaic power generation power prediction method and system |
| CN112836870A (en) * | 2021-01-25 | 2021-05-25 | 华北电力大学 | Method, device, equipment and computer readable storage medium for predicting wind power |
| CN112836870B (en) * | 2021-01-25 | 2023-12-12 | 华北电力大学 | Method, apparatus, device and computer readable storage medium for predicting wind power |
| CN113095562A (en) * | 2021-04-07 | 2021-07-09 | 安徽天能清洁能源科技有限公司 | Ultra-short term power generation prediction method and device based on Kalman filtering and LSTM |
| CN113341481A (en) * | 2021-07-02 | 2021-09-03 | 北京玖天气象科技有限公司 | Method and device for determining weather forecast result |
| CN113449928A (en) * | 2021-07-14 | 2021-09-28 | 清华四川能源互联网研究院 | Wind field power prediction method, system, server and computer readable storage medium |
| CN113537595A (en) * | 2021-07-16 | 2021-10-22 | 上海电气风电集团股份有限公司 | Model training method, wind power prediction method, system, device and medium |
| CN113822418A (en) * | 2021-09-24 | 2021-12-21 | 中节能风力发电股份有限公司 | Wind power plant power prediction method, system, device and storage medium |
| CN113988394A (en) * | 2021-10-21 | 2022-01-28 | 中国电建集团华东勘测设计研究院有限公司 | Wind power ultra-short-term power prediction method based on gram matrix and convolutional neural network |
| CN114418180B (en) * | 2021-12-16 | 2023-01-20 | 广东电网有限责任公司 | Ultra-short-term prediction method and device for wind power and storage medium |
| CN114418180A (en) * | 2021-12-16 | 2022-04-29 | 广东电网有限责任公司 | Ultra-short-term prediction method and device for wind power and storage medium |
| CN114565057A (en) * | 2022-03-15 | 2022-05-31 | 中科三清科技有限公司 | Machine learning-based grading field identification method and device, storage medium and terminal |
| CN114565057B (en) * | 2022-03-15 | 2022-10-21 | 中科三清科技有限公司 | Machine learning-based grading field identification method and device, storage medium and terminal |
| CN114744623A (en) * | 2022-06-09 | 2022-07-12 | 深圳万甲荣实业有限公司 | New energy power generation prediction method and system based on deep learning |
| CN115186907A (en) * | 2022-07-14 | 2022-10-14 | 华润电力技术研究院有限公司 | Method, system, equipment and medium for predicting long-term power generation amount in wind power plant |
| CN115186907B (en) * | 2022-07-14 | 2024-06-18 | 华润电力技术研究院有限公司 | Method, system, equipment and medium for predicting long-term power generation capacity in wind power plant |
| CN115905997A (en) * | 2022-10-28 | 2023-04-04 | 安徽省国家电投和新电力技术研究有限公司 | Wind turbine generator meteorological disaster early warning method and system based on prediction deviation optimization |
| CN115905997B (en) * | 2022-10-28 | 2023-07-07 | 安徽省国家电投和新电力技术研究有限公司 | Wind turbine generator meteorological disaster early warning method and system based on prediction deviation optimization |
| CN116307153A (en) * | 2023-03-07 | 2023-06-23 | 广东热矩智能科技有限公司 | Meteorological prediction method and device for energy conservation of refrigeration and heating system and electronic equipment |
| CN117892099A (en) * | 2024-03-18 | 2024-04-16 | 湖南科技大学 | Wind turbine generator service efficiency evaluation method and system based on probabilistic neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111461444B (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111461444B (en) | Method, system, medium and electronic equipment for predicting unit power of wind power plant | |
| US20220275788A1 (en) | Forecasting output power of wind turbine in wind farm | |
| JP2016136001A (en) | Prediction device | |
| CN110929963A (en) | Wind speed prediction method, wind speed prediction device, and storage medium | |
| CN114493050B (en) | Multi-dimensional fusion new energy power parallel prediction method and device | |
| CN113822418A (en) | Wind power plant power prediction method, system, device and storage medium | |
| CN112862274A (en) | WRF-LES and Deepar combined wind power prediction method | |
| CN114330110A (en) | Model training method, photovoltaic power generation power prediction method and system | |
| CN112906757A (en) | Model training method, optical power prediction method, device, equipment and storage medium | |
| CN117526274A (en) | New energy power prediction method, electronic equipment and storage medium in extreme climate | |
| US20230327440A1 (en) | Power generation amount management system and power generation amount management method | |
| CN111340307A (en) | Method for predicting wind power generation power of fan and related device | |
| CN114895380A (en) | Solar radiation prediction method, device, equipment and medium | |
| JP7346356B2 (en) | Prediction device and prediction method | |
| CN113344252A (en) | Wind power prediction method based on virtual meteorological technology | |
| CN110188939B (en) | Wind power prediction method, system, equipment and storage medium of wind power plant | |
| CN115905997B (en) | Wind turbine generator meteorological disaster early warning method and system based on prediction deviation optimization | |
| CN116307282A (en) | Wind power prediction method and system based on mechanism model and data driving | |
| US20230281730A1 (en) | Neural network for model-blended time series forecast | |
| TW201740296A (en) | Method and system for predicting power generation capacity of renewable energy using a neural network to accurately calculate the power generation capacity of renewable energy | |
| CN115860248A (en) | Wind speed numerical assimilation short-term prediction method and system | |
| CN115983104A (en) | Wind speed prediction method and device, storage medium and electronic equipment | |
| Karamitsou et al. | Open weather data evaluation for crop irrigation prediction mechanisms in the AUGEIAS project | |
| CN110705769B (en) | New energy power generation power prediction optimization method and device | |
| CN112580899A (en) | Medium-and-long-term wind power generation prediction method and system fused with machine learning model |
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 |