Summary of the invention
The objective of the invention is to,, propose short-term wind-electricity power Forecasting Methodology based on many covers numerical value weather forecast source to the problems referred to above, consequently can be to realize surveying precision height, security of operation and good stability in the advantage of power scheduling practicability operation.
For realizing above-mentioned purpose, the technical scheme that the present invention adopts is: the short-term wind-electricity power Forecasting Methodology based on many covers numerical value weather forecast source comprises:
The method that Applied Physics and statistics combine is set up the forecast model of each wind energy turbine set;
Obtain the numerical weather forecast data of each wind energy turbine set, import said forecast model;
Said forecast model carries out prediction processing based on the numerical weather forecast data of input to the wind-powered electricity generation situation of exerting oneself of each wind energy turbine set short-term and ultrashort phase, and obtains can be applied to power scheduling and set up predicting the outcome of new forecast model.
Further, said operation of setting up the forecast model of each wind energy turbine set comprises:
Obtain and comprise the weather forecast of many cover numerical value, historical wind data, Power Output for Wind Power Field historical data, the topography and geomorphology in wind energy turbine set zone of living in and the master data of fan operation state surveyed of wind energy turbine set at least;
Through statistical method, perhaps the method that combines with statistical method of physical method is handled the gained master data, obtains the forecast model of each wind energy turbine set.
Further, said operation of obtaining the numerical weather forecast data of each wind energy turbine set comprises:
From the server of each service provider of numerical weather forecast, download the various places numerical weather forecast;
To gained various places numerical weather forecast, carry out data processing and D/A conversion, obtain each wind energy turbine set prediction period numerical weather forecast;
To each wind energy turbine set prediction period numerical weather forecast data of gained, analyze and weighted calculation, obtain being used to import the numerical weather forecast data of forecast model.
Further, said numerical weather forecast data comprise at least from various places that numerical weather forecast obtains air speed data, wind direction data, temperature record, barometric information and humidity data.
Further, said forecast model is based on the numerical weather forecast data of input, and the operation of the wind-powered electricity generation situation of exerting oneself of each wind energy turbine set short-term and ultrashort phase being carried out prediction processing comprises:
Said numerical weather forecast data are exported rough prediction data after the NWP system handles;
Meteorological theoretical based on atmospheric boundary layer dynamics and boundary layer, said rough prediction data is carried out process of refinement, obtain the predicted value under wind energy turbine set actual landform, the geomorphologic conditions;
With prediction wind speed and the wind direction in the said predicted value, convert the wind speed and the wind direction of wind-powered electricity generation unit hub height into;
In conjunction with wake effect between the wind-powered electricity generation unit, with the wind speed and the wind direction of gained wind-powered electricity generation unit hub height, be applied to the power curve of wind-powered electricity generation unit, draw the predicted power of wind-powered electricity generation unit;
Predicted power to all wind-powered electricity generation units is sued for peace, and obtains the predicted power of whole wind electric field, promptly obtains predicting the outcome of whole wind electric field.
Further, above-described short-term wind-electricity power Forecasting Methodology based on many covers numerical value weather forecast source, this method also comprises:
To the said operation that predicts the outcome and store, and/or,
Said predicting the outcome carried out operation displayed.
Simultaneously, another technical scheme that the present invention adopts is: based on the short-term wind-electricity power prognoses system in many covers numerical value weather forecast source, comprise data of weather forecast collecting unit, EMS system and prediction processing unit, wherein:
Said EMS system is used to provide the data of setting up each wind energy turbine set forecast model;
Said data of weather forecast collecting unit is used to obtain the numerical weather forecast data of each wind energy turbine set, and imports forecast model;
Said prediction processing unit is used for the data of setting up each wind energy turbine set forecast model that provide based on the EMS system, sets up forecast model; And; Be used for the numerical weather forecast data of said forecast model based on the input of data of weather forecast collecting unit; The wind-powered electricity generation situation of exerting oneself to each wind energy turbine set short-term and ultrashort phase is carried out prediction processing, obtains can be applied to power scheduling and set up predicting the outcome of new forecast model.
Further, said EMS system comprises wind energy turbine set real-time information collection module, data dispatch module and EMS system data platform, wherein:
Said wind energy turbine set real-time information collection module is used for from the server of each service provider of numerical weather forecast, downloads the various places numerical weather forecast;
Said EMS system data platform is used for gained various places numerical weather forecast, carries out data processing and D/A conversion, obtains each wind energy turbine set prediction period numerical weather forecast; And,
Be used for each wind energy turbine set prediction period numerical weather forecast data of gained are analyzed and weighted calculation, obtain being used to import the numerical weather forecast data of forecast model;
Said data dispatch module is used for the data interaction between wind energy turbine set real-time information collection module and the EMS system data platform.
Further, said prediction processing unit comprises NWP processing module and prediction and calculation processor, wherein:
Said NWP processing module after being used for the numerical weather forecast data are handled, is exported rough prediction data;
Said prediction and calculation processor is used for based on the meteorological theory of atmospheric boundary layer dynamics and boundary layer said rough prediction data being carried out process of refinement, obtains the predicted value under wind energy turbine set actual landform, the geomorphologic conditions;
With prediction wind speed and the wind direction in the said predicted value, convert the wind speed and the wind direction of wind-powered electricity generation unit hub height into;
In conjunction with wake effect between the wind-powered electricity generation unit, with the wind speed and the wind direction of gained wind-powered electricity generation unit hub height, be applied to the power curve of wind-powered electricity generation unit, draw the predicted power of wind-powered electricity generation unit;
Predicted power to all wind-powered electricity generation units is sued for peace, and obtains the predicted power of whole wind electric field, promptly obtains predicting the outcome of whole wind electric field.
Further. above-described short-term wind-electricity power prognoses system based on many covers numerical value weather forecast source, also comprise prognoses system database, man-machine interaction unit and communication unit, wherein:
Said prognoses system database as data center, is used to store, transfer and upgrades numerical weather forecast data from the data of weather forecast collecting unit, sends out wind power data and predicting the outcome from the prediction processing unit from the reality of EMS system;
Said man-machine interaction unit is used for and user interactions, accomplishes the operation that comprises data and curve display and system management and maintenance at least;
Said communication unit is used for data of weather forecast collecting unit, EMS system, prediction processing unit and man-machine interaction unit data interaction to each other.
Short-term wind-electricity power Forecasting Methodology and the system based on many covers numerical value weather forecast source of the embodiment of various embodiments of the present invention are applied to ten million kilowatt of wind-powered electricity generation base, Jiuquan, and be larger.
The short-term wind-electricity power Forecasting Methodology and the system based on many covers numerical value weather forecast source of various embodiments of the present invention, because this method comprises: the method that Applied Physics and statistics combine is set up the forecast model of each wind energy turbine set; Obtain the numerical weather forecast data of each wind energy turbine set, the input forecast model; Forecast model carries out prediction processing based on the numerical weather forecast data of input to the wind-powered electricity generation situation of exerting oneself of each wind energy turbine set short-term and ultrashort phase, and obtains can be applied to power scheduling and set up predicting the outcome of new forecast model; Can realize wind power prediction in 72 hours, help improving the total specified installed capacity of wind power system; Generation schedule is formulated, sent out the power supply balance, guarantees that power network safety operation has important function, only depend on when solving traffic department's mixing system stand-by power supply the historical data of wind-powered electricity generation installed capacity and wind-powered electricity generation electricity volume to estimate the problem of wind power; Thereby can overcome that precision of prediction in the prior art is low, safety and poor stability so that do not reach the defective that practicability requires, precision is high to realize surveying, security of operation and good stability so that can be in the advantage of power scheduling practicability operation.
Other features and advantages of the present invention will be set forth in specification subsequently, and, partly from specification, become obvious, perhaps understand through embodiment of the present invention.The object of the invention can be realized through the structure that in the specification of being write, claims and accompanying drawing, is particularly pointed out and obtained with other advantages.
Through accompanying drawing and embodiment, technical scheme of the present invention is done further detailed description below.
Embodiment
Below in conjunction with accompanying drawing the preferred embodiments of the present invention are described, should be appreciated that preferred embodiment described herein only is used for explanation and explains the present invention, and be not used in qualification the present invention.
Method embodiment
According to the embodiment of the invention, as depicted in figs. 1 and 2, the short-term wind-electricity power Forecasting Methodology based on many covers numerical value weather forecast source is provided.
As shown in Figure 1, the short-term wind-electricity power Forecasting Methodology based on many covers numerical value weather forecast source of present embodiment comprises:
Step 100: the method that Applied Physics and statistics combine is set up the forecast model of each wind energy turbine set;
Step 101: obtain the numerical weather forecast data of each wind energy turbine set, the input forecast model;
Step 103: said forecast model carries out prediction processing based on the numerical weather forecast data of input to the wind-powered electricity generation situation of exerting oneself of each wind energy turbine set short-term and ultrashort phase, and obtains can be applied to power scheduling and set up predicting the outcome of new forecast model.
Preferably, as shown in Figure 2, the short-term wind-electricity power Forecasting Methodology based on many covers numerical value weather forecast source of the foregoing description specifically comprises:
Step 200: obtain to comprise at least to overlap numerical value weather forecast, historical wind data, Power Output for Wind Power Field historical data, the topography and geomorphology in wind energy turbine set zone of living in and the master datas of fan operation state surveyed of wind energy turbine set more;
Step 201: through statistical method, perhaps the method that combines with statistical method of physical method is handled step 200 gained master data, obtains the forecast model of each wind energy turbine set, execution in step 205;
Step 202:, download the various places numerical weather forecast from the server of each service provider of numerical weather forecast;
Step 203: to step 202 gained various places numerical weather forecast, carry out data processing and D/A conversion, obtain each wind energy turbine set prediction period numerical weather forecast;
Step 204: to each wind energy turbine set prediction period numerical weather forecast data of step 203 gained, analyze and weighted calculation, obtain being used to import the numerical weather forecast data of forecast model, execution in step 205; In step 204, the numerical weather forecast data comprise at least from various places that numerical weather forecast obtains air speed data, wind direction data, temperature record, barometric information and humidity data;
Step 205: with the numerical weather forecast data of each wind energy turbine set of step 204 gained, input step 202 gained forecast models;
Step 206: the numerical weather forecast data of input forecast model in step 205, after the NWP system handles, export rough prediction data;
Step 207: meteorological theoretical based on atmospheric boundary layer dynamics and boundary layer, the prediction data that step 206 gained is rough is carried out process of refinement, obtains the predicted value under wind energy turbine set actual landform, the geomorphologic conditions;
Step 208:, convert the wind speed and the wind direction of wind-powered electricity generation unit hub height into prediction wind speed and the wind direction in the step 207 gained predicted value;
Step 209: combine wake effect between the wind-powered electricity generation unit,, be applied to the power curve of wind-powered electricity generation unit, draw the predicted power of wind-powered electricity generation unit with the wind speed and the wind direction of step 208 gained wind-powered electricity generation unit hub height;
Step 210: all are sued for peace such as the predicted power of step 209 gained wind-powered electricity generation unit, obtain the predicted power of whole wind electric field, promptly obtain predicting the outcome of whole wind electric field.
In step 210, can also predict the outcome to gained store, data and curve display and operations such as system management and maintenance.
In the above-described embodiments; Data such as the topography and geomorphology in the weather forecast of the many covers of utilization numerical value, the historical survey of wind energy turbine set wind data, Power Output for Wind Power Field historical data, wind energy turbine set zone of living in and fan operation state; Through the method that statistical method or physics combine with statistics, set up the forecast model of each wind energy turbine set; Again with of the input of numerical weather forecast data, predict each wind energy turbine set and the whole province's wind-powered electricity generation next day situation of exerting oneself as forecast model.
In the above-described embodiments, when obtaining the numerical weather forecast data, can pass through the numerical weather forecast model.The numerical weather forecast model is very complicated, and needs a large amount of measured datas, generally is responsible for forecast by National Meteorological Bureau.The horizontal resolution of general global models is 80 * 80km2 to 40 * 40km2.Global models drive partial model, and resolution is reduced.The initial condition of confirming prognoses system needs lot of data.Responsible collection data such as a large amount of weather stations, buoy, radar, observation vessel, meteorological satellite and aircraft.World Meteorological Organization has formulated the standard of data format and measuring period.
The all different observations constantly of these data obtain, and the precision of these data is generally all than conventional data difference.Therefore, how utilizing these unconventional observational datas, cooperate them with conventional data, enrich the information of initial field, is an important problem.Need to adopt the four-dimensional assimilate method constantly to import computer to the different moment, different regions, meteorological data of different nature; Through certain Forecast Mode; Make it on power and heating power, to coordinate, obtain the initial field that quality field and wind field reach balance basically, offer Forecast Mode and use.Four-dimensional assimilate mainly contains three parts to be formed, and the one, Forecast Mode, the 2nd, objective analysis, the 3rd, initialization.The effect of pattern is that previous data is extrapolated to current analysis constantly; Analysis is that the information of model predictions and current observational data are combined, in be inserted on the lattice point; Initialization then is that the high frequency gravitational wave in the analysis field is filtered, and guarantees the stability of calculating.
The numerical weather forecast of American-European countries's use at present mainly contains following several kinds.Europe mesoscale Climate Prediction Center's integrated system (ECMWF); The T170L42 forecast system of U.S. environment forecasting centre integrated system (NCEP) exploitation; Japan spectral expansion pattern T213L30; Britain unifies pattern UM, the Lokal modell model of German Meteorological Services mechanism (DWD) exploitation, the T213L31 of China national weather bureau exploitation etc.
The raising that the meteorological element fine forecast of high-spatial and temporal resolution (like wind speed, wind direction etc.) can not only rely on numerical model resolution obtains.This be because, receive on the one hand the restriction of computing power, on the other hand, too high resolution can make the uncertainty of data and pattern itself obtain amplification, even can run counter to desire.So in this case, the numerical forecasting product of use pattern output is added the forecast result that statistics or artificial intelligence technology just can obtain high-resolution.
In the above-described embodiments, the physical method of wind power prediction, mainly meteorological theoretical based on atmospheric boundary layer dynamics and boundary layer; The meticulous predicted value that turns under wind energy turbine set actual landform, the geomorphologic conditions of rough prediction data with the output of NWP system; And will predict that wind speed, wind direction convert the wind speed of wind-powered electricity generation unit hub height, wind direction into, behind the wake effect, will predict that again wind speed is applied to the power curve of wind-powered electricity generation unit between consideration wind-powered electricity generation unit; Draw the predicted power of wind-powered electricity generation unit thus; At last, to the predicted power summation of all wind-powered electricity generation units, obtain the predicted power of whole wind electric field.
The output result of roughness variation model and landform variation model is to upwind research range edge (here for 10km) the speedup factor of disturbed wind speed (relief model is also exported the wind deflection with respect to upwind) not; Therefore; When using the disturbance of speedup factor calculation wind energy turbine set roughness and landform variation stream field; At first need confirm the not disturbed wind speed of upwind, wind direction; And, must set up NWP wind speed, wind direction and getting in touch again with reference to wind speed, wind direction in order to realize prediction to hub height wind speed, wind direction.The bridge of diverse location wind speed, wind direction in the geostrophic wind Chang Zuowei contact boundary layer of reflection large scale variations in flow; And can change the towing law by ground and set up getting in touch of geostrophic wind and ground layer characteristic quantity, and ground commentaries on classics towing law combines logarithm wind profile to extrapolate to surveying wind data.
The influencing factor of Power Output for Wind Power Field mainly contains wind speed, wind direction, temperature, air pressure, humidity and roughness of ground surface etc.Data such as the wind speed that therefore obtains from numerical weather forecast, wind direction, temperature, air pressure, humidity all are necessity inputs of forecast model.But equally also there is certain misdata in the numerical weather forecast historical data, needs further processing just can be applied to the Power Output for Wind Power Field prediction.Is the basis with the digital map, with numerical weather forecast or survey the input of wind data, sets up the physical model that is used for power prediction as model.According to the wind energy turbine set digital model; Consider that wake effect is to the influence of Power Output for Wind Power Field between landform, barrier, roughness and blower fan; The wind speed of ad-hoc location is extrapolated to the wind speed at every typhoon wheel hub height place; In conjunction with the power curve of particular rack, calculate the power output of whole wind electric field.
In the above-described embodiments, the wind energy turbine set information gathering comprises historical power data collection, historical wind speed data acquisition.Power data can be obtained in the wind energy turbine set central monitoring system.Central monitoring system was gathered the situation of exerting oneself of wind energy turbine set in per 15 minutes and was kept in the file of appointment.The central monitoring system data memory format of different company's exploitation is different, needs it under designated environment, just can open.
The collection of air speed data need be set up anemometer tower in the representative place of wind energy turbine set.Anemometer tower of the little wind energy turbine set simple in landform, that wind speed is stable just can be represented the wind conditions of whole wind electric field basically.But, then need select a plurality of type localities to set up the wind conditions that anemometer tower ability correct representation goes out this wind field at wind energy turbine set with a varied topography (such as mountain topography).
The anemometer tower height is generally at 70 meters, and the needs of system data need the transducer of installation that air velocity transducer, wind transducer, temperature sensor, baroceptor and humidity sensor are arranged on anemometer tower according to weather report.
Particularly, the installation of each transducer: temperature sensor, barometric pressure humidity transducer can be installed in 10 meters eminences, and air velocity transducer and wind transducer can respectively be installed one at 10 meters, 30 meters, 50 meters, 70 meters.
The method that can adopt above-mentioned physical method and statistical method to combine is set up forecast model, and this forecast model is mainly wind energy turbine set numerical weather forecast, wind farm wind velocity, the historical power data of wind energy turbine set etc.Be output as the power of wind energy turbine set.
The foregoing description adopts the Forecasting Methodology of many cover numerical value weather forecast, helps improving precision of prediction, and realizing predicts the outcome can be used in the wind power forecasting system of power scheduling department and wind energy turbine set.
System embodiment
According to the embodiment of the invention,, the short-term wind-electricity power Forecasting Methodology based on many covers numerical value weather forecast source is provided like Fig. 3 and shown in Figure 4.
As shown in Figure 3; The short-term wind-electricity power prognoses system based on many covers numerical value weather forecast source of present embodiment; Comprise data of weather forecast collecting unit 1, EMS system 4 and prediction processing unit 5, wherein: EMS system 4 is used to provide the data of setting up each wind energy turbine set forecast model; Data of weather forecast collecting unit 1 is used to obtain the numerical weather forecast data of each wind energy turbine set, and imports forecast model; Forecast model based on the data of setting up each wind energy turbine set forecast model that the EMS system provides, is set up in prediction processing unit 5; And; Be used for the numerical weather forecast data of forecast model based on 1 input of data of weather forecast collecting unit; The wind-powered electricity generation situation of exerting oneself to each wind energy turbine set short-term and ultrashort phase is carried out prediction processing, obtains can be applied to power scheduling and set up predicting the outcome of new forecast model.
Further; The short-term wind-electricity power prognoses system based on many covers numerical value weather forecast source of the foregoing description; Also comprise prognoses system database 3, man-machine interaction unit 2 and communication unit 6; Wherein: prognoses system database 3; As data center, be used to store, transfer and upgrade numerical weather forecast data, send out the wind power data and from the predicting the outcome of prediction processing unit 5, each software module is all accomplished the mutual of data through system database from the reality of EMS system 4 from data of weather forecast collecting unit 1; Man-machine interaction unit 2 is used for and user interactions, accomplishes the operation that comprises data and curve display and system management and maintenance at least; Communication unit 6 is used for data of weather forecast collecting unit 1, EMS system 4, prediction processing unit 5 and man-machine interaction unit 2 data interaction to each other.
In the above-described embodiments, prediction processing unit 5 takes out the numerical weather forecast data from prognoses system database 3, calculate predicting the outcome of wind energy turbine set through forecast model, and will predict the outcome and send prognoses system database 3 back to.
Preferably; As shown in Figure 4; The short-term wind-electricity power prognoses system based on many covers numerical value weather forecast source of the foregoing description; Comprise data of weather forecast collecting unit 1, man-machine interaction unit 2, prognoses system database 3, EMS system 4, prediction processing unit 5 and communication unit 6; Data of weather forecast collecting unit 1, prediction processing unit 5, communication unit 6, EMS system 4 connect successively, and prognoses system database 3 is connected with prediction processing unit 5 and communication unit 6 respectively, and man-machine interaction unit is connected with communication unit 6.
Wherein, above-mentioned data of weather forecast collecting unit 1 comprises internet module 11, European meteorological observatory numerical weather forecast 12, Lanzhou meteorological observatory numerical weather forecast 13 and Chinese DianKeYuan numerical weather forecast 14; Prediction processing unit 5 comprises NWP processing module 51 and prediction and calculation processor 52; Communication unit 6 comprises the Network Security Device 61 and the network switch 62; EMS system 4 comprises wind energy turbine set real-time information collection module 41, data dispatch module 42 and EMS system data platform 43; Prognoses system database 3 comprises prognoses system database interface 31 and prognoses system database server 32; Man-machine interaction unit 2 comprises graphic user interface 21 and graphical user interface module 22.
In the above-described embodiments, wind energy turbine set real-time information collection module 41 is sent to data such as the realtime power of each wind energy turbine set, wind speed in the prognoses system database 3, will predict the outcome simultaneously and take out from prognoses system database 3, sends to EMS system data platform 43.
In the above-described embodiments; Internet module 11; Behind European meteorological observatory numerical weather forecast 12, Lanzhou meteorological observatory numerical weather forecast 13 and Chinese DianKeYuan numerical weather forecast 14, be connected with the network switch 62 with NWP processing module 51, Network Security Device 61 successively respectively; Prognoses system database server 32, prognoses system database interface 31, prediction and calculation processor 52 are connected with the network switch 62 successively, and prognoses system database interface 31, graphic user interface 21 and EMS system data platform 43 all are connected with the network switch 62; EMS system data platform 43, data dispatch module 42 are connected with wind energy turbine set real-time information collection module 41 successively, and graphic user interface 21 is connected with graphical user interface module 22.
In above-mentioned EMS system 4, wind energy turbine set real-time information collection module 41 is used for from the server of each service provider of numerical weather forecast, downloads the various places numerical weather forecast; EMS system data platform 43 is used for gained various places numerical weather forecast, carries out data processing and D/A conversion, obtains each wind energy turbine set prediction period numerical weather forecast; And, be used for each wind energy turbine set prediction period numerical weather forecast data of gained are analyzed and weighted calculation, obtain being used to import the numerical weather forecast data of forecast model; Data dispatch module 42 is used for the data interaction between wind energy turbine set real-time information collection module and the EMS system data platform.
In above-mentioned prediction processing unit 5, NWP processing module 51 after being used for the numerical weather forecast data are handled, is exported rough prediction data; Prediction and calculation processor 52 is used for based on the meteorological theory of atmospheric boundary layer dynamics and boundary layer rough prediction data being carried out process of refinement, obtains the predicted value under wind energy turbine set actual landform, the geomorphologic conditions; With prediction wind speed and the wind direction in the predicted value, convert the wind speed and the wind direction of wind-powered electricity generation unit hub height into; In conjunction with wake effect between the wind-powered electricity generation unit, with the wind speed and the wind direction of gained wind-powered electricity generation unit hub height, be applied to the power curve of wind-powered electricity generation unit, draw the predicted power of wind-powered electricity generation unit; Predicted power to all wind-powered electricity generation units is sued for peace, and obtains the predicted power of whole wind electric field, promptly obtains predicting the outcome of whole wind electric field.
In the embodiment shown in fig. 4; 3 cover more accurate numerical weather forecasts have been comprised in the data of weather forecast collecting unit 1; Be respectively European meteorological observatory numerical weather forecast 12, Lanzhou meteorological observatory numerical weather forecast 13 and Chinese DianKeYuan numerical weather forecast 14, through the numerical weather forecast data that the weather forecast of 51 pairs 3 covers of NWP processing module numerical value is analyzed, weighted calculation draws final prediction wind field.Be connected through network between NWP processing module 51 and Network Security Device 61, the network switch 62.Data acquisition equipment in the wind energy turbine set real-time information collection module 41 comprises wind farm wind velocity, wind direction, temperature, air pressure collector and wind electric field blower real-time information collection device.Prognoses system database server 32 is connected with EMS system data platform 43 through the network switch 62, Network Security Device 61 and NWP processing module 51; EMS system data platform 43 is connected with wind energy turbine set real-time data acquisition equipment (being wind energy turbine set real-time information collection module 41) through data dispatch module 42; Prognoses system database server 32 adopts PC system, the Windows XP operating system of packing into.
Numerical weather forecast provides the various weather forecast data of wind energy turbine set position surface layer, and forecast in per 12 hours was once forecast 2 times, forecast 72 hours at every turn in one day.The data that data of weather forecast collecting unit 1 provides are binary format, through data processing and conversion, convert the input of decimal format as forecast model to.Wind energy turbine set real-time information collection module 41 mainly is to set up anemometer tower at the wind energy turbine set key position, gathers data such as wind speed, wind direction, temperature, air pressure.These data through after the conversion also as the input data of forecast model.Prediction processing unit 5 is mainly predicted wind speed and power, is based on the core of the short-term wind-electricity power prognoses system in many cover numerical value weather forecasts source.Because the geographical position of each wind energy turbine set, meteorological condition are all inequality, so forecast model will have adjustable, software realizes that module mainly comprises data processing conversion and GUI graphical interfaces.
The short-term wind-electricity power Forecasting Methodology and the system based on many covers numerical value weather forecast source of the foregoing description can realize wind power prediction in 72 hours, the specified installed capacity that the raising system is total; Generation schedule is formulated, sent out the power supply balance, guarantees that power network safety operation has important function; Only depend on the historical data of wind-powered electricity generation installed capacity and wind-powered electricity generation electricity volume to estimate the problem of wind power when helping solving traffic department's mixing system stand-by power supply.
In sum, the short-term wind-electricity power Forecasting Methodology and the system based on many covers numerical value weather forecast source of various embodiments of the present invention, because this method comprises: the method that Applied Physics and statistics combine is set up the forecast model of each wind energy turbine set; Obtain the numerical weather forecast data of each wind energy turbine set, the input forecast model; Forecast model carries out prediction processing based on the numerical weather forecast data of input to the wind-powered electricity generation situation of exerting oneself of each wind energy turbine set short-term and ultrashort phase, and obtains can be applied to power scheduling and set up predicting the outcome of new forecast model; Can realize wind power prediction in 72 hours, help improving the total specified installed capacity of wind power system; Generation schedule is formulated, sent out the power supply balance, guarantees that power network safety operation has important function, only depend on when solving traffic department's mixing system stand-by power supply the historical data of wind-powered electricity generation installed capacity and wind-powered electricity generation electricity volume to estimate the problem of wind power; Thereby can overcome that precision of prediction in the prior art is low, safety and poor stability so that do not reach the defective that practicability requires, with realize that precision of prediction is high, security of operation and good stability so that can be in the advantage of power scheduling practicability operation.
What should explain at last is: the above is merely the preferred embodiments of the present invention; Be not limited to the present invention; Although the present invention has been carried out detailed explanation with reference to previous embodiment; For a person skilled in the art, it still can be made amendment to the technical scheme that aforementioned each embodiment put down in writing, and perhaps part technical characterictic wherein is equal to replacement.All within spirit of the present invention and principle, any modification of being done, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.