Ultra-short-term wind power prediction method, device, equipment and medium

Abstract

The invention discloses an ultra-short-term wind power prediction method and device, equipment and a medium, and relates to the technical field of wind power generation, and the method comprises the steps: carrying out the micro-scale coupling simulation of a CFD flow field simulation model through the current weather forecast data of a WRF model and historical wind power plant wind resource parameters, obtaining an optimal simulation parameter set, and carrying out the calculation of the optimal simulation parameter set; performing directional calculation on the basis of the optimal simulation parameter set to generate a flow field simulation result of a wind direction sector boundary, extrapolating a free flow wind speed at each location point in the wind direction sector, performing wake flow calculation, and interpolating a wake flow region wind speed at each location point to obtain a power prediction result; a first ratio of the power prediction result to the actual operation power is a comprehensive loss factor; correcting the weather forecast data based on the current wind power plant wind resource parameters to obtain corrected weather forecast data; and generating a target ultra-short-term power prediction result according to the corrected weather forecast data, the comprehensive loss factor and the flow field simulation result. And the accuracy of ultra-short-term wind power prediction is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power generation, and in particular to an ultra-short-term wind power prediction method, device, equipment and medium. Background Art

[0002] As an important part of renewable energy, wind farms are mainly used to convert natural wind energy into electrical energy for people's daily production and life. This not only helps to reduce dependence on fossil fuels, but also effectively reduces carbon emissions and promotes environmental protection and sustainable development.

[0003] Power forecasting plays a vital role in wind power grid-connected operation. It provides an important reference for grid dispatching by estimating the future power generation capacity of wind farms. Accurate power forecasting helps the grid balance supply and demand, ensure the stability and reliability of power supply, and thus improve the safety and economy of the grid.

[0004] However, current power forecasting technology still has some significant shortcomings. The primary problem is the insufficient prediction accuracy, which may lead to deviations between the grid dispatch plan and the actual power generation situation, thus affecting the stable operation of the grid. In addition, when performing model simulation, there is also a large deviation between the simulation results and the actual observation data, which further weakens the credibility of power forecasts. Especially for ultra-short-term wind power forecasts, due to the low accuracy of the weather forecasts they rely on, the prediction results are often significantly different from the actual power generation situation.

[0005] From the above, it can be seen that how to improve the accuracy of ultra-short-term wind power prediction is a problem to be solved in this field. Summary of the invention

[0006] In view of this, the purpose of the present invention is to provide a method, device, equipment and medium for ultra-short-term wind power prediction to improve the accuracy of ultra-short-term wind power prediction. The specific scheme is as follows:

[0007] In a first aspect, the present application discloses an ultra-short-term wind power prediction method, comprising:

[0008] The current weather forecast data and historical wind farm wind resource parameters provided by the WRF model are used to perform micro-scale coupled simulation on the CFD flow field simulation model to obtain the optimal simulation parameter set, and directional calculation is performed based on the optimal simulation parameter set to generate the flow field simulation results at the boundary of the wind direction sector;

[0009] Based on the flow field simulation result, the free stream wind speed at each machine point in the wind direction sector is extrapolated, and the wake calculation is performed on the free stream wind speed to obtain the wake area wind speed at each machine point, and the wake area wind speed is interpolated to obtain the power prediction result;

[0010] Determine a first ratio of the power prediction result to the actual operating power as a comprehensive loss factor;

[0011] Correcting the weather forecast data at the location of the wind farm based on the current wind resource parameters of the wind farm to obtain corrected weather forecast data;

[0012] A target ultra-short-term power prediction result is generated according to the corrected weather forecast data, the comprehensive loss factor and the flow field simulation result.

[0013] Optionally, the current weather forecast data and historical wind farm wind resource parameters provided by the WRF model are used to perform micro-scale coupled simulation on the CFD flow field simulation model to obtain an optimal simulation parameter set, including:

[0014] Preprocess the terrain data and surface roughness of the wind farm to obtain the wind farm grid file;

[0015] Based on the wind farm grid file, a grid file is constructed including CFD flow field simulation model of turbulence model; wherein the simulation boundary of CFD flow field simulation model includes thermal stability, inlet wind speed condition, and each wind direction sector;

[0016] When micro-scale coupling simulation of the CFD flow field simulation model is performed using the current weather forecast data provided by the WRF model as the inflow boundary condition of the CFD flow field simulation model and the RANS equation as the control equation of the CFD flow field simulation model, the inflow boundary condition and the parameters of the CFD flow field simulation model are tuned using historical wind farm wind resource parameters to obtain an optimal simulation parameter set.

[0017] Optionally, the extrapolating the free stream wind speed at each machine point in the wind direction sector based on the flow field simulation result includes:

[0018] Determine each wind direction sector in the wind farm as the current wind direction sector in sequence, and obtain the measured wind direction of the current wind measurement tower in the current wind direction sector;

[0019] Determine a first wind direction sector boundary and a second wind direction sector boundary adjacent to the target wind direction sector from each wind direction sector, and extract a first wind tower simulated wind direction at the first wind direction sector boundary and a second wind tower simulated wind direction at the second wind direction sector boundary from the flow field simulation result;

[0020] Determine a first weight of the simulated wind direction of the first wind tower and a second weight of the simulated wind direction of the second wind tower based on the measured wind direction, and use the first weight and the second weight to determine the simulated wind speed at the current wind tower and the simulated wind speed at the current machine point corresponding to the current wind tower;

[0021] The free stream wind speed at the current station site is determined based on the simulated wind speed at the current wind tower and the simulated wind speed at the current station site, so as to obtain the free stream wind speed at each station site in the sector.

[0022] Optionally, the using the first weight and the second weight to determine the simulated wind speed at the current wind tower and the simulated wind speed at the current machine position corresponding to the current wind tower includes:

[0023] Using the first weight and the second weight, respectively, weighted sum is performed on the simulated wind direction of the first wind direction sector at the boundary of the first wind direction and the simulated wind direction of the second wind direction sector at the boundary of the second wind direction to obtain the simulated wind speed at the current wind direction tower;

[0024] The first weight and the second weight are used to perform weighted summation on the simulated wind direction at the first machine point at the boundary of the first wind direction sector and the simulated wind direction at the second machine point at the boundary of the second wind direction sector, respectively, to obtain the simulated wind speed at the current machine point corresponding to the current wind measurement tower.

[0025] Optionally, determining the free stream wind speed at the current machine site based on the simulated wind speed at the current wind tower and the simulated wind speed at the current machine site includes:

[0026] A second ratio between the simulated wind speed at the current station site and the simulated wind speed at the current wind tower is obtained, and the product of the second ratio and the measured wind speed of the current wind tower is determined as the free stream wind speed at the current station site.

[0027] Optionally, interpolating the wind speed in the wake area to obtain a power prediction result includes:

[0028] Fit the real-time operation data of wind turbines recorded by the wind farm SCADA system to obtain the actual power curve of each wind turbine in the wind turbine;

[0029] The wind speed in the wake region is interpolated based on the actual power curve to obtain a power prediction result.

[0030] Optionally, generating a target ultra-short-term power prediction result according to the corrected weather forecast data, the comprehensive loss factor and the flow field simulation result includes:

[0031] generating an initial ultra-short-term power prediction result according to the corrected weather forecast data, the comprehensive loss factor and the flow field simulation result;

[0032] Obtain the operation and maintenance events of the wind farm to conduct power loss assessment and obtain the operation and maintenance loss power;

[0033] The initial ultra-short-term power prediction result is corrected based on the operation and maintenance loss power to obtain a target ultra-short-term power prediction result.

[0034] In a second aspect, the present application discloses an ultra-short-term wind power prediction device, comprising:

[0035] The model simulation module is used to use the current weather forecast data and historical wind farm wind resource parameters provided by the WRF model to perform micro-scale coupled simulation on the CFD flow field simulation model to obtain the optimal simulation parameter set, and perform directional calculation based on the optimal simulation parameter set to generate the flow field simulation results at the wind direction sector boundary;

[0036] A wind speed interpolation module, used for extrapolating the free stream wind speed at each machine site in the wind direction sector based on the flow field simulation result, performing wake calculation on the free stream wind speed to obtain the wake area wind speed at each machine site, and interpolating the wake area wind speed to obtain a power prediction result;

[0037] A loss factor acquisition module, used to determine a first ratio of the power prediction result to the actual operating power as a comprehensive loss factor;

[0038] A data correction module is used to correct the weather forecast data of the location of the wind farm based on the current wind resource parameters of the wind farm to obtain corrected weather forecast data;

[0039] The power prediction module is used to generate a target ultra-short-term power prediction result based on the corrected weather forecast data, the comprehensive loss factor and the flow field simulation result.

[0040] In a third aspect, the present application discloses an electronic device, comprising:

[0041] Memory, used to store computer programs;

[0042] A processor is used to execute the computer program to implement the steps of the ultra-short-term wind power prediction method disclosed above.

[0043] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the steps of the ultra-short-term wind power prediction method disclosed above are implemented.

[0044] The beneficial effects of the present application are as follows: the present application utilizes the current weather forecast data and historical wind farm wind resource parameters provided by the WRF model to perform micro-scale coupling simulation on the CFD flow field simulation model to obtain an optimal simulation parameter set, and performs directional calculation based on the optimal simulation parameter set to generate a flow field simulation result at the boundary of the wind direction sector; based on the flow field simulation result, the free stream wind speed at each machine site in the wind direction sector is extrapolated, and a wake calculation is performed on the free stream wind speed to obtain the wake area wind speed at each machine site, and the wake area wind speed is interpolated to obtain a power prediction result; a first ratio of the power prediction result to the actual operating power is determined as a comprehensive loss factor; based on the current wind farm wind resource parameters, the weather forecast data at the location of the wind farm is corrected to obtain corrected weather forecast data; and a target ultra-short-term power prediction result is generated according to the corrected weather forecast data, the comprehensive loss factor and the flow field simulation result. It can be seen that the present application uses the current weather forecast data and historical wind farm wind resource parameters provided by the WRF model to perform micro-scale coupling simulation on the CFD flow field simulation model, that is, through the micro-scale coupling technology of the CFD flow field simulation model and the WRF model, a more reasonable optimal simulation parameter set is obtained; based on the optimal simulation parameter set, a directional calculation is performed to generate the flow field simulation results of the wind direction sector boundary, and then the free stream wind speed at each machine point in the wind direction sector is extrapolated based on the flow field simulation results, and the wake calculation and interpolation are performed to obtain the power prediction results, and then the first ratio of the power prediction results to the actual operating power is determined as the comprehensive loss factor, that is, the comprehensive loss factor can quantify the error between the flow field simulation and the actual results; further, in response to the deviation problem of the weather forecast data at the location of the wind farm, the present application corrects the weather forecast data based on the current wind farm wind resource parameters, so that the target ultra-short-term power prediction results generated according to the corrected weather forecast data, the comprehensive loss factor and the flow field simulation results are more reliable and more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0046] Figure 1 An ultra-short-term wind power prediction flow chart disclosed in this application;

[0047] Figure 2 A schematic diagram of a specific flow field modeling disclosed in this application;

[0048] Figure 3A specific sector schematic diagram disclosed in this application;

[0049] Figure 4 A schematic diagram of a Jensen wake model disclosed in this application;

[0050] Figure 5 A specific prediction process data processing schematic diagram disclosed in this application;

[0051] Figure 6 A schematic diagram of a specific ultra-short-term wind power prediction process disclosed in this application;

[0052] Figure 7 This is a schematic diagram of the structure of an ultra-short-term wind power prediction device disclosed in this application;

[0053] Figure 8 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0055] As an important part of renewable energy, wind farms are mainly used to convert natural wind energy into electrical energy for people's daily production and life. This not only helps to reduce dependence on fossil fuels, but also effectively reduces carbon emissions and promotes environmental protection and sustainable development.

[0056] Power forecasting plays a vital role in wind power grid-connected operation. It provides an important reference for grid dispatching by estimating the future power generation capacity of wind farms. Accurate power forecasting helps the grid balance supply and demand, ensure the stability and reliability of power supply, and thus improve the safety and economy of the grid.

[0057] However, current power forecasting technology still has some significant shortcomings. The primary problem is the insufficient prediction accuracy, which may lead to deviations between the grid dispatch plan and the actual power generation situation, thus affecting the stable operation of the grid. In addition, when performing model simulation, there is also a large deviation between the simulation results and the actual observation data, which further weakens the credibility of power forecasts. Especially for ultra-short-term wind power forecasts, due to the low accuracy of the weather forecasts they rely on, the prediction results are often significantly different from the actual power generation situation.

[0058] To this end, the present application accordingly provides an ultra-short-term wind power prediction solution to improve the accuracy of ultra-short-term wind power prediction.

[0059] See also Figure 1 As shown, the embodiment of the present application discloses an ultra-short-term wind power prediction method, comprising:

[0060] Step S11: Use the current weather forecast data and historical wind farm wind resource parameters provided by the WRF model to perform micro-scale coupling simulation on the CFD flow field simulation model to obtain the optimal simulation parameter set, and perform directional calculation based on the optimal simulation parameter set to generate the flow field simulation results at the wind direction sector boundary.

[0061] In this embodiment, the current weather forecast data and historical wind farm wind resource parameters provided by the WRF (The Weather Research and Forecasting Mode) model are used to perform micro-scale coupling simulation on the CFD flow field simulation model to obtain an optimal simulation parameter set, including: pre-processing the terrain data and surface roughness of the wind farm to obtain a wind farm grid file; constructing a wind farm grid file based on the wind farm grid file A CFD flow field simulation model of a turbulence model; wherein the simulation boundaries of the CFD flow field simulation model include thermal stability, inlet wind speed conditions, and various wind direction sectors; when the current weather forecast data provided by the WRF model is used as the inflow boundary conditions of the CFD flow field simulation model and the RANS equation is used as the control equation of the CFD flow field simulation model to perform micro-scale coupled simulation on the CFD flow field simulation model, the inflow boundary conditions and the parameters of the CFD flow field simulation model are tuned using historical wind farm wind resource parameters to obtain an optimal simulation parameter set.

[0062] First, obtain the terrain data and surface roughness of the wind farm; obtain high-precision terrain data and roughness data of the wind farm and surrounding areas. Specifically, the three-dimensional terrain model of the wind farm area can be obtained through remote sensing measurement, geographic information system and high-precision terrain mapping. The surface roughness characteristics, including vegetation type, surface cover characteristics and the impact of human facilities, landmark roughness, can be obtained through field surveys and remote sensing analysis. Determined by the following formula:

[0063] ;

[0064] in, is the wind height, is the reference height, It is the friction wind speed, determined in combination with surface conditions such as vegetation type and surface cover characteristics.

[0065] Single or multiple wind towers near the site contain measured data for a full year and multiple height layers, and a grid file of the wind farm area is generated based on the preprocessed three-dimensional terrain model, including complex terrain and roughness characteristics.

[0066] Furthermore, a CFD (Computational Fluid Dynamics) flow field simulation model can be constructed based on the wind farm grid file. CFD flow field simulation models of turbulence models, such as Figure 2 A specific flow field modeling schematic diagram is shown, and the simulation boundary of the CFD flow field simulation model includes thermal stability, inlet wind speed conditions, and various wind direction sectors; Turbulent Kinetic Energy of Turbulence Models The formula is:

[0067] ;

[0068] In the formula, represents the fluid density, k represents the turbulent kinetic energy, that is, the energy intensity of turbulence, is the turbulent viscosity coefficient, represents the molecular dynamic viscosity coefficient of the fluid, is the turbulence production term, represents the turbulent dissipation rate, The Prandtl number, which represents the turbulent kinetic energy k, is an empirical constant, and t represents time;

[0069] Turbulence dissipation rate The formula is:

[0070] ;

[0071] in, is the turbulence production term, is the turbulent viscosity coefficient, is an empirical constant, represents the turbulent dissipation rate.

[0072] Secondly, the large-scale current weather forecast data provided by WRF (The Weather Research and Forecasting Mode) is used as the inflow boundary condition of the CFD model, the current weather forecast data is used as the inflow boundary condition of the CFD flow field simulation model, and the RANS (Reynolds-averaged Navier-Stokes) equation is used as the control equation of the CFD flow field simulation model to perform micro-scale coupled simulation on the CFD flow field simulation model. For example, Fluent software or OpenFOAM can be used for simulation, and in the process of simulation, the historical wind farm wind resource parameters are used to perform multiple optimizations on the inflow boundary conditions and the parameters of the CFD flow field simulation model, so that the simulation results are more in line with the wind field characteristics, thereby obtaining the optimal simulation parameter set.

[0073] Next, directional calculations are performed based on the optimal simulation parameter set to generate flow field simulation results at the boundaries of wind direction sectors. The flow field simulation results form a refined database of the site wind flow field, and simulation boundaries are set for each wind direction sector (0~360°), thermal stability (stable, neutral, unstable), and inlet wind speed conditions.

[0074] Step S12: extrapolating the free stream wind speed at each machine site in the wind direction sector based on the flow field simulation result, performing wake calculation on the free stream wind speed to obtain the wake area wind speed at each machine site, and interpolating the wake area wind speed to obtain a power prediction result.

[0075] In this embodiment, the extrapolating the free-flow wind speed at each machine site in the wind direction sector based on the flow field simulation result includes: determining each wind direction sector in the wind farm as the current wind direction sector in turn, and obtaining the measured wind direction of the current wind tower in the current wind direction sector; determining a first wind direction sector boundary and a second wind direction sector boundary adjacent to the target wind direction sector from each wind direction sector, and extracting the first wind tower simulated wind direction at the first wind direction sector boundary and the second wind tower simulated wind direction at the second wind direction sector boundary from the flow field simulation result; determining a first weight of the first wind tower simulated wind direction and a second weight of the second wind tower simulated wind direction based on the measured wind direction, and determining the simulated wind speed at the current wind tower and the simulated wind speed at the current machine site corresponding to the current wind tower by using the first weight and the second weight; determining the free-flow wind speed at the current machine site based on the simulated wind speed at the current wind tower and the simulated wind speed at the current machine site, so as to obtain the free-flow wind speed at each machine site in the sector.

[0076] It can be understood that a wind farm includes various wind direction sectors, each of which includes a number of machine sites and wind towers, and there may also be machine sites and wind towers at the boundaries of each wind direction sector. The simulation results at the machine sites that are not at the boundaries of the wind direction sectors and the simulation results at the wind towers need to be extrapolated based on the flow field simulation results at the boundaries of the wind direction sectors. Taking the current wind tower in the current wind direction sector in the wind farm as an example, first, obtain the measured wind direction of the current wind tower. , find the simulated wind direction results of the wind tower at two adjacent angles and That is, the first wind direction sector boundary and the second wind direction sector boundary adjacent to the target wind direction sector are determined from each wind direction sector, and the simulated wind direction of the first wind tower at the boundary of the first wind direction sector is extracted from the flow field simulation results. The second wind tower simulates the wind direction at the boundary of the second wind direction sector Next, the weights of the directional calculation results of the respective angles are calculated, that is, the first weight of the simulated wind direction of the first wind tower is determined based on the measured wind direction. and the second weight of the simulated wind direction of the second wind tower ,like Figure 3 A specific sector diagram is shown, the actual wind direction of the current wind tower is located at the boundary of the first wind direction sector and the simulated wind direction of the wind tower at the boundary of the second wind direction sector and The first weight and the second weight are determined by the following formula:

[0077] ;

[0078] ;

[0079] Further, the simulated wind speed at the current wind tower is determined using the first weight and the second weight. And the simulated wind speed at the current position of the current wind tower ; Then, the free-stream wind speed at the current station is determined based on the simulated wind speed at the current wind tower and the simulated wind speed at the current station, so as to obtain the free-stream wind speed at each station in the sector. .

[0080] In this embodiment, the method of using the first weight and the second weight to determine the simulated wind speed at the current wind tower and the simulated wind speed at the current station corresponding to the current wind tower includes: using the first weight and the second weight to weighted sum the simulated wind direction of the first wind tower at the boundary of the first wind direction sector and the simulated wind direction of the second wind tower at the boundary of the second wind direction sector, respectively, to obtain the simulated wind speed at the current wind tower; using the first weight and the second weight to weighted sum the simulated wind direction at the first station at the boundary of the first wind direction sector and the simulated wind direction at the second station at the boundary of the second wind direction sector, respectively, to obtain the simulated wind speed at the current station corresponding to the current wind tower. Specifically, based on the weights of the two directional calculation results calculated, the simulated wind speed at the station and the wind tower is calculated by using the wind speed scalar weighted average method, that is, using the first weight and the second weight to weighted sum the simulated wind direction of the first wind tower at the boundary of the first wind direction sector and the simulated wind direction of the second wind tower at the boundary of the second wind direction sector, respectively, to obtain the simulated wind speed at the current wind tower, and the specific formula is as follows:

[0081] ;

[0082] The simulated wind direction at the first machine point at the boundary of the first wind direction sector and the simulated wind direction at the second machine point at the boundary of the second wind direction sector are weighted and summed using the first weight and the second weight, so as to obtain the simulated wind speed at the current machine point corresponding to the current wind measurement tower. The specific formula is as follows:

[0083] .

[0084] In this embodiment, the determining of the free flow wind speed at the current station location based on the simulated wind speed at the current wind tower and the simulated wind speed at the current station location includes: obtaining a second ratio between the simulated wind speed at the current station location and the simulated wind speed at the current wind tower, and determining the product of the second ratio and the measured wind speed of the current wind tower as the free flow wind speed at the current station location. The specific formula for obtaining the free flow wind speed is as follows:

[0085] .

[0086] Furthermore, the conventional wake model can be used to perform wake calculation on the free stream wind speed to obtain the wake area wind speed at each aircraft station. The conventional wake model is, for example, the Jensen wake model, such as Figure 4 A schematic diagram of a Jensen wake model is shown in FIG. 1 , and the specific formula is as follows:

[0087] ;

[0088] In the formula, is the wind speed in the wake area, is the free stream wind speed, a is the fan absorption factor, k is the wake diffusion coefficient, is the fan spacing, is the fan diameter.

[0089] In this embodiment, the wind speed in the wake area is interpolated to obtain a power prediction result, including: fitting the real-time operation data of the wind turbines recorded by the wind farm SCADA system to obtain the actual power curve of each wind turbine in the wind turbine; interpolating the wind speed in the wake area based on the actual power curve to obtain the power prediction result. The real-time operation data of the wind turbine recorded by the wind turbine SCADA system (Supervisory Control And Data Acquisition, i.e., data acquisition and monitoring control system) is collected. The real-time operation data of the wind turbine includes wind speed, power and status information. Specifically, the real-time operation data of the wind turbine can be fitted based on a piecewise linear fitting method or a polynomial regression method to obtain the actual power curve of each wind turbine in the wind turbine. The fitting formula is as follows:

[0090] ;

[0091] in, is the power output, is the wind speed, is the fitting coefficient;

[0092] Next, the actual power prediction result is obtained by interpolating the wind speed calculated after the wake, that is, the wind speed in the wake area is interpolated based on the actual power curve to obtain the power prediction result.

[0093] Step S13: Determine a first ratio of the power prediction result to the actual operating power as a comprehensive loss factor.

[0094] The power prediction results The actual operating power The first ratio is determined as the comprehensive loss factor, and the specific calculation formula is as follows:

[0095] .

[0096] Step S14: Correcting the weather forecast data at the location of the wind farm based on the current wind resource parameters of the wind farm to obtain corrected weather forecast data.

[0097] Based on the current wind resource parameters of the wind farm, the downscaled weather forecast data of the wind farm location is corrected to obtain the corrected weather forecast data, that is, based on the real-time data of the wind power wind tower in the field, the wind speed and wind direction of the daily weather forecast are corrected. Specifically, the downscaled weather forecast data can be adjusted by statistical regression correction or machine learning based on deviation correction to improve the forecast accuracy. Specifically, the weather forecast data correction method is, for example, a weighted linear regression correction method, and its formula is as follows:

[0098] ;

[0099] In the formula, is the revised weather forecast data, is the original weather forecast data; a and b are the regression coefficients calculated based on historical data and weather forecast data.

[0100] Step S15: generating a target ultra-short-term power prediction result according to the corrected weather forecast data, the comprehensive loss factor and the flow field simulation result.

[0101] In this embodiment, generating a target ultra-short-term power forecast result based on the corrected weather forecast data, the comprehensive loss factor and the flow field simulation result includes: generating an initial ultra-short-term power forecast result based on the corrected weather forecast data, the comprehensive loss factor and the flow field simulation result; obtaining operation and maintenance events of the wind farm to perform power loss assessment to obtain operation and maintenance loss power; and correcting the initial ultra-short-term power forecast result based on the operation and maintenance loss power to obtain a target ultra-short-term power forecast result.

[0102] For example Figure 5 A specific data processing diagram of the prediction process is shown, in which an initial ultra-short-term power prediction result is generated according to the corrected weather forecast data, the comprehensive loss factor and the flow field simulation result; further, the uncertainty factors are quantified according to the input operation and maintenance plan, that is, the time and power loss evaluation of planned operation and maintenance (such as regular maintenance) and unplanned downtime events are performed, and the power prediction results of the machine site are corrected in combination with the actual operation of the wind farm and the power generation reduction plan, and the influence of uncertain factors on the power prediction is added to the prediction results. That is to say, first, the operation and maintenance events of the wind farm are obtained to perform power loss evaluation to obtain the operation and maintenance loss power, and secondly, the initial ultra-short-term power prediction result is corrected based on the operation and maintenance loss power to obtain the target ultra-short-term power prediction result. The specific correction model is shown as follows:

[0103] ;

[0104] In this embodiment, the influence of external factors such as wind farm operation and maintenance, shutdown, power restriction, etc. is comprehensively considered to improve the accuracy and reliability of the prediction results.

[0105] The beneficial effects of the present application are as follows: the present application utilizes the current weather forecast data and historical wind farm wind resource parameters provided by the WRF model to perform micro-scale coupling simulation on the CFD flow field simulation model to obtain an optimal simulation parameter set, and performs directional calculation based on the optimal simulation parameter set to generate a flow field simulation result at the boundary of the wind direction sector; based on the flow field simulation result, the free stream wind speed at each machine site in the wind direction sector is extrapolated, and a wake calculation is performed on the free stream wind speed to obtain the wake area wind speed at each machine site, and the wake area wind speed is interpolated to obtain a power prediction result; a first ratio of the power prediction result to the actual operating power is determined as a comprehensive loss factor; based on the current wind farm wind resource parameters, the weather forecast data at the location of the wind farm is corrected to obtain corrected weather forecast data; and a target ultra-short-term power prediction result is generated according to the corrected weather forecast data, the comprehensive loss factor and the flow field simulation result. It can be seen that the present application uses the current weather forecast data and historical wind farm wind resource parameters provided by the WRF model to perform micro-scale coupling simulation on the CFD flow field simulation model, that is, through the micro-scale coupling technology of the CFD flow field simulation model and the WRF model, a more reasonable optimal simulation parameter set is obtained; based on the optimal simulation parameter set, a directional calculation is performed to generate the flow field simulation results of the wind direction sector boundary, and then the free stream wind speed at each machine point in the wind direction sector is extrapolated based on the flow field simulation results, and the wake calculation and interpolation are performed to obtain the power prediction results, and then the first ratio of the power prediction results to the actual operating power is determined as the comprehensive loss factor, that is, the comprehensive loss factor can quantify the error between the flow field simulation and the actual results; further, in response to the deviation problem of the weather forecast data at the location of the wind farm, the present application corrects the weather forecast data based on the current wind farm wind resource parameters, so that the target ultra-short-term power prediction results generated according to the corrected weather forecast data, the comprehensive loss factor and the flow field simulation results are more reliable and more accurate.

[0106] Below Figure 6Taking a specific ultra-short-term wind power prediction process diagram as an example, the present application is explained accordingly. Obtain the topographic data, roughness data and actual wind tower data of the wind farm and its surrounding areas, that is, obtain the topographic data and surface roughness of the wind farm, and pre-process the topographic data and surface roughness of the wind farm to obtain the wind farm grid file; use the CFD+WRF mode to complete the meso-microscale coupling, and establish a CFD simulation model in combination with the wind farm grid file; optimize the simulation parameters and inflow boundary conditions through the historical wind tower data in the site area to generate the optimal simulation parameters for the site area; perform directional calculations for the boundary conditions of different wind directions, thermal stability and wind speeds, generate flow field simulation results, and form a refined simulation database for the wind flow field at a fixed site.

[0107] Based on the directional calculation results and the assumption of wind acceleration factor, a mutual mapping relationship can be established between wind speed and wind direction at different points in the flow field; the free flow wind parameters of each machine site are extrapolated through comprehensive calculation through historical actual wind tower data; the conventional wake model is used to perform wake calculation to obtain the wind parameters of each wind turbine site after the wake effect, that is, the wind speed in the wake area; the real-time operation data recorded by the SCADA system of each wind turbine unit, including wind speed, power and status information, are collected, and the actual power curve of the unit under the operating state is fitted based on the piecewise linear fitting or polynomial regression method; the wind parameters of the unit considering the influence of the wake are combined with the fitted power curve to interpolate and obtain the predicted power output of each machine site, that is, the power prediction result; the operation data of the wind farm SCADA system is used to verify the simulation results, and the comprehensive loss factor between the calculation model and the actual operation results is calculated.

[0108] The wind speed and wind direction of the numerical weather forecast are corrected based on the measured data of the wind power tower in the site; the power output of each machine site is predicted using the corrected numerical weather forecast data and the micro-scale CFD model, and calibrated according to the comprehensive loss factor to complete the ultra-short-term power forecast, that is, the initial ultra-short-term power forecast result is generated according to the corrected weather forecast data, the comprehensive loss factor and the flow field simulation results; the operation and maintenance events of the wind farm are obtained to conduct power loss assessment to obtain the operation and maintenance loss power; the initial ultra-short-term power forecast result is corrected based on the operation and maintenance loss power to obtain the target ultra-short-term power forecast result.

[0109] See also Figure 7 As shown, the embodiment of the present application discloses an ultra-short-term wind power prediction device, comprising:

[0110] The model simulation module 11 is used to perform micro-scale coupling simulation on the CFD flow field simulation model using the current weather forecast data and historical wind farm wind resource parameters provided by the WRF model to obtain an optimal simulation parameter set, and perform directional calculation based on the optimal simulation parameter set to generate a flow field simulation result at the boundary of the wind direction sector;

[0111] A wind speed interpolation module 12 is used to extrapolate the free stream wind speed at each machine site in the wind direction sector based on the flow field simulation result, and perform wake calculation on the free stream wind speed to obtain the wake area wind speed at each machine site, and interpolate the wake area wind speed to obtain a power prediction result;

[0112] A loss factor acquisition module 13, configured to determine a first ratio of the power prediction result to the actual operating power as a comprehensive loss factor;

[0113] The data correction module 14 is used to correct the weather forecast data of the location of the wind farm based on the current wind resource parameters of the wind farm to obtain corrected weather forecast data;

[0114] The power prediction module 15 is used to generate a target ultra-short-term power prediction result according to the corrected weather forecast data, the comprehensive loss factor and the flow field simulation result.

[0115] The beneficial effects of the present application are as follows: the present application utilizes the current weather forecast data and historical wind farm wind resource parameters provided by the WRF model to perform micro-scale coupling simulation on the CFD flow field simulation model to obtain an optimal simulation parameter set, and performs directional calculation based on the optimal simulation parameter set to generate a flow field simulation result at the boundary of the wind direction sector; based on the flow field simulation result, the free stream wind speed at each machine site in the wind direction sector is extrapolated, and a wake calculation is performed on the free stream wind speed to obtain the wake area wind speed at each machine site, and the wake area wind speed is interpolated to obtain a power prediction result; a first ratio of the power prediction result to the actual operating power is determined as a comprehensive loss factor; based on the current wind farm wind resource parameters, the weather forecast data at the location of the wind farm is corrected to obtain corrected weather forecast data; and a target ultra-short-term power prediction result is generated according to the corrected weather forecast data, the comprehensive loss factor and the flow field simulation result. It can be seen that the present application uses the current weather forecast data and historical wind farm wind resource parameters provided by the WRF model to perform micro-scale coupling simulation on the CFD flow field simulation model, that is, through the micro-scale coupling technology of the CFD flow field simulation model and the WRF model, a more reasonable optimal simulation parameter set is obtained; based on the optimal simulation parameter set, a directional calculation is performed to generate the flow field simulation results of the wind direction sector boundary, and then the free stream wind speed at each machine point in the wind direction sector is extrapolated based on the flow field simulation results, and the wake calculation and interpolation are performed to obtain the power prediction results, and then the first ratio of the power prediction results to the actual operating power is determined as the comprehensive loss factor, that is, the comprehensive loss factor can quantify the error between the flow field simulation and the actual results; further, in response to the deviation problem of the weather forecast data at the location of the wind farm, the present application corrects the weather forecast data based on the current wind farm wind resource parameters, so that the target ultra-short-term power prediction results generated according to the corrected weather forecast data, the comprehensive loss factor and the flow field simulation results are more reliable and more accurate.

[0116] Furthermore, an embodiment of the present application also provides an electronic device. Figure 8 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0117] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Specifically, it may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the ultra-short-term wind power prediction method performed by the electronic device disclosed in any of the aforementioned embodiments.

[0118] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device; the communication interface 24 can create a data transmission channel between the electronic device and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0119] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0120] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon include an operating system 221, a computer program 222 and data 223, etc. The storage method can be temporary storage or permanent storage.

[0121] Among them, the operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device to realize the operation and processing of the massive data 223 in the memory 22 by the processor 21, which can be Windows, Unix, Linux, etc. In addition to including a computer program that can be used to complete the ultra-short-term wind power prediction method performed by the electronic device disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks. In addition to data received by the electronic device and transmitted from an external device, the data 223 can also include data collected by its own input and output interface 25, etc.

[0122] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein the computer program, when executed by a processor, implements the ultra-short-term wind power prediction method disclosed above. The specific steps of the method can refer to the corresponding contents disclosed in the above embodiments, and will not be repeated here.

[0123] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0124] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application. The steps of the method or algorithm described in conjunction with the embodiments disclosed herein can be implemented directly with hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in a random access memory (RAM), memory, read-only memory (ROM), electrically programmable EPROM (Erasable Programmable Read Only Memory), electrically erasable programmable EEPROM (Electrically Erasable Programmable read only memory), register, hard disk, removable disk, CD-ROM (Compact Disc Read-Only Memory), or any other form of storage medium known in the technical field.

[0125] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0126] The above is a detailed introduction to an ultra-short-term wind power prediction method, device, equipment and medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for ultra-short-term wind power prediction, characterized in that: include: The current weather forecast data and historical wind farm wind resource parameters provided by the WRF model are used to perform micro-scale coupled simulation on the CFD flow field simulation model to obtain the optimal simulation parameter set, and directional calculation is performed based on the optimal simulation parameter set to generate the flow field simulation results at the boundary of the wind direction sector; Based on the flow field simulation result, the free stream wind speed at each machine point in the wind direction sector is extrapolated, and the wake calculation is performed on the free stream wind speed to obtain the wake area wind speed at each machine point, and the wake area wind speed is interpolated to obtain the power prediction result; Determine a first ratio of the power prediction result to the actual operating power as a comprehensive loss factor; Correcting the weather forecast data at the location of the wind farm based on the current wind resource parameters of the wind farm to obtain corrected weather forecast data; A target ultra-short-term power prediction result is generated according to the corrected weather forecast data, the comprehensive loss factor and the flow field simulation result.

2. The ultra-short-term wind power prediction method according to claim 1, characterized in that: The current weather forecast data and historical wind farm wind resource parameters provided by the WRF model are used to perform micro-scale coupled simulation on the CFD flow field simulation model to obtain the optimal simulation parameter set, including: Preprocess the terrain data and surface roughness of the wind farm to obtain the wind farm grid file; Based on the wind farm grid file, a grid file is constructed including CFD flow field simulation model of turbulence model; wherein the simulation boundary of CFD flow field simulation model includes thermal stability, inlet wind speed condition, and each wind direction sector; When micro-scale coupling simulation of the CFD flow field simulation model is performed using the current weather forecast data provided by the WRF model as the inflow boundary condition of the CFD flow field simulation model and the RANS equation as the control equation of the CFD flow field simulation model, the inflow boundary condition and the parameters of the CFD flow field simulation model are tuned using historical wind farm wind resource parameters to obtain an optimal simulation parameter set.

3. The ultra-short-term wind power prediction method according to claim 2, characterized in that: The extrapolating the free stream wind speed at each machine position in the wind direction sector based on the flow field simulation result includes: Determine each wind direction sector in the wind farm as the current wind direction sector in sequence, and obtain the measured wind direction of the current wind measurement tower in the current wind direction sector; Determine a first wind direction sector boundary and a second wind direction sector boundary adjacent to the target wind direction sector from each wind direction sector, and extract a first wind tower simulated wind direction at the first wind direction sector boundary and a second wind tower simulated wind direction at the second wind direction sector boundary from the flow field simulation result; Determine a first weight of the simulated wind direction of the first wind tower and a second weight of the simulated wind direction of the second wind tower based on the measured wind direction, and use the first weight and the second weight to determine the simulated wind speed at the current wind tower and the simulated wind speed at the current machine point corresponding to the current wind tower; The free stream wind speed at the current station site is determined based on the simulated wind speed at the current wind tower and the simulated wind speed at the current station site, so as to obtain the free stream wind speed at each station site in the sector.

4. The ultra-short-term wind power prediction method according to claim 3, characterized in that: The method of using the first weight and the second weight to determine the simulated wind speed at the current wind tower and the simulated wind speed at the current machine position corresponding to the current wind tower includes: Using the first weight and the second weight, respectively, weighted sum is performed on the simulated wind direction of the first wind direction sector at the boundary of the first wind direction and the simulated wind direction of the second wind direction sector at the boundary of the second wind direction to obtain the simulated wind speed at the current wind direction tower; The first weight and the second weight are used to perform weighted summation on the simulated wind direction at the first machine point at the boundary of the first wind direction sector and the simulated wind direction at the second machine point at the boundary of the second wind direction sector, respectively, to obtain the simulated wind speed at the current machine point corresponding to the current wind measurement tower.

5. The ultra-short-term wind power prediction method according to claim 3, characterized in that: The determining the free stream wind speed at the current machine site based on the simulated wind speed at the current wind measurement tower and the simulated wind speed at the current machine site comprises: A second ratio between the simulated wind speed at the current station site and the simulated wind speed at the current wind tower is obtained, and the product of the second ratio and the measured wind speed of the current wind tower is determined as the free stream wind speed at the current station site.

6. The ultra-short-term wind power prediction method according to claim 1, characterized in that: The interpolating the wind speed in the wake area to obtain a power prediction result includes: Fit the real-time operation data of wind turbines recorded by the wind farm SCADA system to obtain the actual power curve of each wind turbine in the wind turbine; The wind speed in the wake region is interpolated based on the actual power curve to obtain a power prediction result.

7. The ultra-short-term wind power prediction method according to any one of claims 1 to 6, characterized in that: The generating of the target ultra-short-term power prediction result according to the corrected weather forecast data, the comprehensive loss factor and the flow field simulation result comprises: generating an initial ultra-short-term power prediction result according to the corrected weather forecast data, the comprehensive loss factor and the flow field simulation result; Obtain the operation and maintenance events of the wind farm to conduct power loss assessment and obtain the operation and maintenance loss power; The initial ultra-short-term power prediction result is corrected based on the operation and maintenance loss power to obtain a target ultra-short-term power prediction result.

8. An ultra-short-term wind power prediction device, characterized in that: include: The model simulation module is used to use the current weather forecast data and historical wind farm wind resource parameters provided by the WRF model to perform micro-scale coupled simulation on the CFD flow field simulation model to obtain the optimal simulation parameter set, and perform directional calculation based on the optimal simulation parameter set to generate the flow field simulation results at the wind direction sector boundary; A wind speed interpolation module, used for extrapolating the free stream wind speed at each machine site in the wind direction sector based on the flow field simulation result, performing wake calculation on the free stream wind speed to obtain the wake area wind speed at each machine site, and interpolating the wake area wind speed to obtain a power prediction result; A loss factor acquisition module, used to determine a first ratio of the power prediction result to the actual operating power as a comprehensive loss factor; A data correction module is used to correct the weather forecast data of the location of the wind farm based on the current wind resource parameters of the wind farm to obtain corrected weather forecast data; The power prediction module is used to generate a target ultra-short-term power prediction result based on the corrected weather forecast data, the comprehensive loss factor and the flow field simulation result.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the ultra-short-term wind power prediction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store computer programs; wherein, when the computer program is executed by a processor, the steps of the ultra-short-term wind power prediction method according to any one of claims 1 to 7 are implemented.

Images