A wind speed forecast correction method and device integrating wind farm observation data
By obtaining and analyzing the wind speed observation data of the wind farm, determining the relevant wind farm and performing weight calculations, the problem of ignoring the tiny terrain influence in the wind speed forecast is solved, the accuracy of wind speed forecast and the reliability of new energy power generation are improved, and the power grid is dispatched. Provide scientific basis.
Patent Information
- Application Number
- CN201910591048.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2019-07-02
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2039-07-02
AI Technical Summary
The existing technology ignores the impact of tiny terrain on wind speed in the wind speed forecast, resulting in inaccurate prediction of output power of wind farms, affecting grid scheduling and output optimization, and the data quality is uneven, making it difficult to build high-quality, full-factor, and spatial-temporal resolution. High wind speed correction data.
By obtaining the wind speed observations of the wind farm in the area, determining the relevant wind farms in the adjacent grid, using the observation data similarity and weight calculation to correct the wind speed forecast value, and improving the accuracy and reliability of the wind speed forecast.
It achieves higher accuracy and availability of wind speed forecasts, reduces labor costs and resource waste, and provides a scientific basis for the prediction and scheduling of new energy power generation power.
Smart Images

Figure CN112183801B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of wind power generation power prediction of new energy sources, and in particular to a method and device for correcting wind speed forecasts by integrating wind farm observation data. Background Art
[0002] Wind power has been developed on a large scale as a typical renewable energy power generation. Its large-scale grid-connected operation has a great impact on the safe, stable and economic operation of the power system. The output power of wind farms and photovoltaic power stations is mainly determined by meteorological factors such as wind speed, wind direction and irradiance. In order to reflect the changes in the atmospheric system within the forecast time, the prediction of renewable energy power generation needs to use the wind speed, wind direction and irradiance data of the high-resolution numerical weather forecast (Numerical Weather Prediction-NWP) near the renewable energy power station as input, and then the prediction algorithm converts the NWP meteorological element forecast into the output power prediction of the renewable energy station.
[0003] In nature, wind is affected by the region, topography and climate, and is highly random and uncontrollable. Therefore, the wind speed forecast is one of the meteorological elements with the lowest forecast accuracy. Inaccurate wind speed forecasts will directly affect the inaccuracy of wind farm output power, which will affect many important decisions in the process of output optimization and grid dispatching. At present, research on post-correction of wind speed forecasts mainly focuses on operational experience correction. Generally speaking, forecasters in various regions will correct the wind speed forecast results based on the different geographical and climatic conditions of each region and refer to the forecast results of different models. However, specific corrections are mostly determined according to the forecast area. The current operational numerical weather forecast resolution is 9km, and the correction range is large. In wind farm forecasts, the impact of tiny terrain on wind speed is often ignored. The power industry has larger amounts of meteorological data, denser time intervals, and more complex formats, requiring more means and methods to process. The data quality varies, and needs to be tested and corrected from different time and space dimensions. Integration is more difficult. It is an urgent problem to construct high-quality, complete-factor, consistent-format, and high-time and space resolution wind speed correction data for wind power forecasting. Summary of the invention
[0004] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a method for correcting the wind speed forecast results of weather forecasts, so as to obtain wind speed forecast results with higher final accuracy, further improve the availability and applicability of existing wind speed forecast products, and thus serve the prediction and scheduling of new energy power generation.
[0005] The purpose of the present invention is achieved by adopting the following technical solutions:
[0006] The present invention provides a wind speed forecast correction method integrating wind farm observation data, wherein the method comprises:
[0007] Determine the wind speed observation value of the node in the grid network corresponding to the region according to the wind speed observation value of the wind farm in the region;
[0008] The wind speed forecast values of the nodes in the grid network corresponding to the region are corrected according to the wind speed observation values of the nodes in the grid network corresponding to the region.
[0009] Preferably, the step of determining the wind speed observation values of the nodes in the grid network corresponding to the region according to the wind speed observation values of the wind farms in the region includes:
[0010] Obtaining wind farms in grids adjacent to nodes in a grid network corresponding to a region that have correlations with other wind farms in the region;
[0011] The wind speed observation value of the node in the grid network corresponding to the region is determined according to the wind speed observation value of the wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region.
[0012] Furthermore, the obtaining of wind farms in grids adjacent to nodes in the grid network corresponding to the region and having correlation with other wind farms in the region includes:
[0013] If the similarities between various types of observation data of the i-th wind farm within the grid range adjacent to the node in the grid network corresponding to the region and various types of observation data of the j-th wind farm in other wind farms in the region are greater than the first similarity threshold corresponding to each type of observation data, then there is a correlation between the i-th wind farm and the j-th wind farm, and the i-th wind farm is obtained;
[0014] Otherwise, there is no correlation between the i-th wind farm and the j-th wind farm, and the i-th wind farm is deleted;
[0015] Where, i∈(0,e); j∈(0,b); e is the total number of wind farms within the grid range adjacent to the node in the grid network corresponding to the region; b is the total number of wind farms in the region except the i-th wind farm;
[0016] The categories of the observation data include: temperature observation data, air pressure observation data, relative humidity observation data, wind speed observation data and precipitation observation data.
[0017] Further, the similarity of the observation data between the x-th type of observation data of the i-th wind farm and the x-th type of observation data of the j-th wind farm is determined as follows:
[0018]
[0019] In the formula, is the xth type of observation data of the ith wind farm at the lth historical moment; is the xth type of observation data of the jth wind farm at the lth historical moment; w x is the second similarity threshold of the x-th type of observation data; d is the total number of historical moments.
[0020] Further, determining the wind speed observation value of the node in the grid network corresponding to the region according to the wind speed observation value of the wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region includes:
[0021] The wind speed observation value V of the node in the grid network corresponding to the region is determined as follows: GZ :
[0022]
[0023] Where η p is the weight of the p-th wind farm in the grids adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region; V p is the wind speed observation value of the pth wind farm in the grids adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region; n is the total number of wind farms in the grids adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region;
[0024] The weight η occupied by the p-th wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region is determined as follows: p :
[0025]
[0026] In the formula, k p is the weight ratio coefficient of the pth wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region;
[0027] The weight ratio coefficient k of the p-th wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region is determined as follows: p :
[0028]
[0029] Where, L p It is the distance between the p-th wind farm in the grid adjacent to the node in the grid network corresponding to the region and the node in the grid network corresponding to the region, which has a correlation with other wind farms in the region.
[0030] Preferably, the correcting the wind speed forecast value of the node in the grid network corresponding to the region according to the wind speed observation value of the node in the grid network corresponding to the region comprises:
[0031] If the number of wind farms in the grids adjacent to the node in the region corresponding to the grid network that are correlated with other wind farms in the region is not less than 5, the wind speed forecast value of the node in the region corresponding to the grid network is corrected to 0.5V Y +0.5V GZ Otherwise, the wind speed forecast value of the node in the grid network corresponding to the area is corrected to (1-0.1·k)V Y +0.1 kV GZ ;
[0032] Among them, V Y V is the wind speed forecast value of the node in the grid network corresponding to the region; GZ is the wind speed observation value of the node in the grid network corresponding to the region; k is the number of wind farms in the grids adjacent to the node in the grid network corresponding to the region that are correlated with other wind farms in the region.
[0033] Preferably, after correcting the wind speed forecast value of the node in the grid network corresponding to the region according to the wind speed observation value of the node in the grid network corresponding to the region, the method further comprises:
[0034] If the relative error between the wind speed forecast value of the node in the regional corresponding grid network and the corrected wind speed forecast value of the node in the regional corresponding grid network is less than 20%, the corrected wind speed forecast value of the node in the regional corresponding grid network is published; otherwise, the wind speed forecast value of the node in the regional corresponding grid network before correction is published.
[0035] Preferably, the relative error μ between the wind speed forecast value of the node in the regional corresponding grid network and the corrected wind speed forecast value of the node in the regional corresponding grid network is determined according to the following formula:
[0036]
[0037] Where V X V is the wind speed forecast value of the node in the grid network corresponding to the region after correction; Y It is the wind speed forecast value of the node in the grid network corresponding to the region.
[0038] The present invention provides a wind speed forecast correction device integrating wind farm observation data, wherein the device comprises:
[0039] Determination module: used to determine the wind speed observation value of the node in the grid network corresponding to the region according to the wind speed observation value of the wind farm in the region;
[0040] Correction module: used to correct the wind speed forecast value of the node in the grid network corresponding to the area according to the wind speed observation value of the node in the grid network corresponding to the area.
[0041] Preferably, the determining module includes:
[0042] An acquisition unit: used for acquiring wind farms in grids adjacent to nodes in a grid network corresponding to a region, which have correlations with other wind farms in the region;
[0043] The determination unit is used to determine the wind speed observation value of the node in the grid network corresponding to the region according to the wind speed observation value of the wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region.
[0044] Furthermore, the acquisition unit is used to:
[0045] If the similarities between various types of observation data of the i-th wind farm within the grid range adjacent to the node in the grid network corresponding to the region and various types of observation data of the j-th wind farm in other wind farms in the region are greater than the first similarity threshold corresponding to each type of observation data, then there is a correlation between the i-th wind farm and the j-th wind farm, and the i-th wind farm is obtained;
[0046] Otherwise, there is no correlation between the i-th wind farm and the j-th wind farm, and the i-th wind farm is deleted;
[0047] Where, i∈(0,e); j∈(0,b); e is the total number of wind farms within the grid range adjacent to the node in the grid network corresponding to the region; b is the total number of wind farms in the region except the i-th wind farm;
[0048] The categories of the observation data include: temperature observation data, air pressure observation data, relative humidity observation data, wind speed observation data and precipitation observation data.
[0049] Further, the similarity of the observation data between the x-th type of observation data of the i-th wind farm and the x-th type of observation data of the j-th wind farm is determined as follows:
[0050]
[0051] In the formula, is the xth type of observation data of the ith wind farm at the lth historical moment; is the xth type of observation data of the jth wind farm at the lth historical moment; w x is the second similarity threshold of the x-th type of observation data; d is the total number of historical moments.
[0052] Further, a unit is determined for:
[0053] The wind speed observation value V of the node in the grid network corresponding to the region is determined as follows: GZ :
[0054]
[0055] Where η p is the weight of the p-th wind farm in the grids adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region; V p is the wind speed observation value of the pth wind farm in the grids adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region; n is the total number of wind farms in the grids adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region;
[0056] The weight η occupied by the p-th wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region is determined as follows: p :
[0057]
[0058] In the formula, k p is the weight ratio coefficient of the pth wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region;
[0059] The weight ratio coefficient k of the p-th wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region is determined as follows: p :
[0060]
[0061] Where, L p It is the distance between the p-th wind farm in the grid adjacent to the node in the grid network corresponding to the region and the node in the grid network corresponding to the region, which has a correlation with other wind farms in the region.
[0062] Preferably, the correction module is used to:
[0063] If the number of wind farms in the grids adjacent to the node in the region corresponding to the grid network that are correlated with other wind farms in the region is not less than 5, the wind speed forecast value of the node in the region corresponding to the grid network is corrected to 0.5V Y +0.5V GZ Otherwise, the wind speed forecast value of the node in the grid network corresponding to the area is corrected to (1-0.1·k)V Y+0.1 kV GZ ;
[0064] Among them, V Y V is the wind speed forecast value of the node in the grid network corresponding to the region; GZ is the wind speed observation value of the node in the grid network corresponding to the region; k is the number of wind farms in the grids adjacent to the node in the grid network corresponding to the region that are correlated with other wind farms in the region.
[0065] Preferably, the device further comprises:
[0066] A publishing module is used to publish the revised wind speed forecast value of the node in the regional corresponding grid network if the relative error between the wind speed forecast value of the node in the regional corresponding grid network and the revised wind speed forecast value of the node in the regional corresponding grid network is less than 20%; otherwise, publish the wind speed forecast value of the node in the regional corresponding grid network before correction.
[0067] Preferably, the relative error μ between the wind speed forecast value of the node in the regional corresponding grid network and the corrected wind speed forecast value of the node in the regional corresponding grid network is determined according to the following formula:
[0068]
[0069] Where V X V is the wind speed forecast value of the node in the grid network corresponding to the region after correction; Y It is the wind speed forecast value of the node in the grid network corresponding to the region.
[0070] Compared with the closest prior art, the present invention has the following beneficial effects:
[0071] The control method and device provided by the present invention determine the wind speed observation values of the nodes in the regional corresponding grid network according to the wind speed observation values of the wind farms in the region; correct the wind speed forecast values of the nodes in the regional corresponding grid network according to the wind speed observation values of the nodes in the regional corresponding grid network, and use the wind farm observation data to correct the forecast wind speed in response to the demand for wind speed forecasting technology for new energy power prediction. The correction process is more reasonable, objective and scientific, maximizes the availability of forecast data, provides a scientific basis for new energy power prediction and scheduling, and minimizes labor costs and reduces resource waste. BRIEF DESCRIPTION OF THE DRAWINGS
[0072] Figure 1 This is a flow chart of a wind speed forecast correction method integrating wind farm observation data provided by the present invention;
[0073] Figure 2 It is a structural diagram of a wind speed forecast correction device integrating wind farm observation data provided by the present invention. DETAILED DESCRIPTION
[0074] The specific implementation modes of the present invention will be further described in detail below in conjunction with the accompanying drawings.
[0075] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.
[0076] The present invention provides a wind speed forecast correction method integrating wind farm observation data, such as Figure 1 As shown, including:
[0077] Determine the wind speed observation value of the node in the grid network corresponding to the region according to the wind speed observation value of the wind farm in the region;
[0078] In the optimal embodiment of the present invention, the nodes in the area corresponding to the grid network include: the global ground is divided into a grid network of 2.5°×2.5° (longitude and latitude), and each grid serves as a node of the network. The geographical areas occupied by the network nodes obtained by this spatial sampling are different, but the nodes are regularly distributed, and the location of the network nodes is the actual geographical location of the meteorological observation site.
[0079] The wind speed forecast values of the nodes in the grid network corresponding to the region are corrected according to the wind speed observation values of the nodes in the grid network corresponding to the region.
[0080] Specifically, the step of determining the wind speed observation value of a node in the grid network corresponding to the region according to the wind speed observation value of the wind farm in the region includes:
[0081] Obtaining wind farms in grids adjacent to nodes in a grid network corresponding to a region that have correlations with other wind farms in the region;
[0082] The wind speed observation value of the node in the grid network corresponding to the region is determined according to the wind speed observation value of the wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region.
[0083] Furthermore, the obtaining of wind farms in grids adjacent to nodes in the grid network corresponding to the region and having correlation with other wind farms in the region includes:
[0084] If the similarities between various types of observation data of the i-th wind farm within the grid range adjacent to the node in the grid network corresponding to the region and various types of observation data of the j-th wind farm in other wind farms in the region are greater than the first similarity threshold corresponding to each type of observation data, then there is a correlation between the i-th wind farm and the j-th wind farm, and the i-th wind farm is obtained;
[0085] Otherwise, there is no correlation between the i-th wind farm and the j-th wind farm, and the i-th wind farm is deleted;
[0086] Where, i∈(0,e); j∈(0,b); e is the total number of wind farms within the grid range adjacent to the node in the grid network corresponding to the region; b is the total number of wind farms in the region except the i-th wind farm;
[0087] If one of the observation data of a certain type at the same time of the i-th wind farm and the j-th wind farm is missing, the similarity between the observation data of this type at the i-th wind farm and the j-th wind farm is considered to be 0;
[0088] The categories of the observation data include: temperature observation data, air pressure observation data, relative humidity observation data, wind speed observation data and precipitation observation data.
[0089] In the optimal embodiment of the present invention, forecast data and observation data within a relatively continuous and complete time period of at least 5 years are selected, and the correctness, real-time, repeatability and file priority of the selected data are verified, and duplicate data and abnormal data are preliminarily eliminated and corrected, and preliminary quality control is performed on the data, finally obtaining complete and accurate forecast and observation data.
[0090] After checking the data integrity in time and space, the data needs to be further verified from four aspects: time and space error verification, climate limit value verification, station extreme value verification and internal consistency verification.
[0091] Further, the similarity of the observation data between the x-th type of observation data of the i-th wind farm and the x-th type of observation data of the j-th wind farm is determined as follows:
[0092]
[0093] In the formula, is the xth type of observation data of the ith wind farm at the lth historical moment; is the xth type of observation data of the jth wind farm at the lth historical moment; w x is the second similarity threshold of the x-th type of observation data; d is the total number of historical moments;
[0094] In the best embodiment of the present invention, the first similarity threshold and the second similarity threshold between the x-th type of observation data of the i-th wind farm and the x-th type of observation data of the j-th wind farm are neither too small nor too large in selection; thereby retaining statistically significant strong similarity data and removing some weak similarity data (usually caused by noise or measurement error);
[0095] Because if the threshold is too large, a lot of data with reference value will be filtered out; if the threshold is too small, the data at the selected point will contain too much redundant information, making further calculations difficult.
[0096] Further, determining the wind speed observation value of the node in the grid network corresponding to the region according to the wind speed observation value of the wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region includes:
[0097] The wind speed observation value V of the node in the grid network corresponding to the region is determined as follows: GZ :
[0098]
[0099] Where η p is the weight of the p-th wind farm in the grids adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region; V p is the wind speed observation value of the pth wind farm in the grids adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region; n is the total number of wind farms in the grids adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region;
[0100] The weight η occupied by the p-th wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region is determined as follows: p :
[0101]
[0102] In the formula, k p is the weight ratio coefficient of the pth wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region;
[0103] The weight ratio coefficient k of the p-th wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region is determined as follows: p :
[0104]
[0105] Where, L p It is the distance between the p-th wind farm in the grid adjacent to the node in the grid network corresponding to the region and the node in the grid network corresponding to the region, which has a correlation with other wind farms in the region.
[0106] In the optimal embodiment of the present invention, the smaller the distance between the p-th wind farm in the grid adjacent to the node in the regional corresponding grid network and the node in the regional corresponding grid network, the larger the corresponding weight proportional coefficient; if the p-th wind farm in the grid adjacent to the node in the regional corresponding grid network and the node in the regional corresponding grid network coincides with the node in the regional corresponding grid network, the corresponding weight proportional coefficient is 1.
[0107] Specifically, the method of correcting the wind speed forecast value of the node in the grid network corresponding to the region according to the wind speed observation value of the node in the grid network corresponding to the region includes:
[0108] If the number of wind farms in the grids adjacent to the node in the region corresponding to the grid network that are correlated with other wind farms in the region is not less than 5, the wind speed forecast value of the node in the region corresponding to the grid network is corrected to 0.5V Y +0.5V GZ Otherwise, the wind speed forecast value of the node in the grid network corresponding to the area is corrected to (1-0.1·k)V Y +0.1 kV GZ ;
[0109] Among them, V Y V is the wind speed forecast value of the node in the grid network corresponding to the region; GZ is the wind speed observation value of the node in the grid network corresponding to the region; k is the number of wind farms in the grids adjacent to the node in the grid network corresponding to the region that are correlated with other wind farms in the region.
[0110] Specifically, after correcting the wind speed forecast value of the node in the grid network corresponding to the region according to the wind speed observation value of the node in the grid network corresponding to the region, it includes:
[0111] If the relative error between the wind speed forecast value of the node in the regional corresponding grid network and the corrected wind speed forecast value of the node in the regional corresponding grid network is less than 20%, the corrected wind speed forecast value of the node in the regional corresponding grid network is published; otherwise, the wind speed forecast value of the node in the regional corresponding grid network before correction is published.
[0112] Specifically, the relative error μ between the wind speed forecast value of the node in the regional corresponding grid network and the corrected wind speed forecast value of the node in the regional corresponding grid network is determined as follows:
[0113]
[0114] Where V X V is the wind speed forecast value of the node in the grid network corresponding to the region after correction; Y It is the wind speed forecast value of the node in the grid network corresponding to the region.
[0115] In the best embodiment of the present invention, there are characteristic differences in the wind speed forecast error under different climate conditions in the region. Therefore, when correcting the wind speed forecast value of the node in the grid network corresponding to the region,
[0116] First, the climate type at the node in the grid network corresponding to the area should be confirmed;
[0117] Secondly, various types of observation data at historical moments corresponding to the same climate type as the climate type at the node in the grid network corresponding to the region are selected to determine the wind farms in the grids adjacent to the node in the grid network corresponding to the region that have a correlation with other wind farms in the region;
[0118] Thirdly, determining the wind speed observation data of the node in the regional corresponding grid network according to the wind speed observation values of the wind farms in the grids adjacent to the node in the regional corresponding grid network and having a correlation with other wind farms in the region;
[0119] Finally, the wind speed observation data of the nodes in the regional corresponding grid network are used to correct the wind speed forecast data of the nodes in the regional corresponding grid network.
[0120] The different climatic conditions in the region can be divided into strong wind period, light wind period and calm wind period according to the wind period; according to the weather type, they can be divided into continuous sunny days, cold wave passing and heavy rainfall weather; according to the terrain, they can be divided into complex terrain and flat terrain; so there are a total of 2*3*3=18 types.
[0121] In the optimal embodiment of the present invention, the technical solution of the present invention can be used to correct the historical forecast data of the nodes in the regional corresponding grid network, thereby enhancing the reliability of the historical forecast data of the nodes in the regional corresponding grid network.
[0122] The present invention also provides a wind speed forecast correction device integrating wind farm observation data, such as Figure 2 As shown, the device comprises:
[0123] Determination module: used to determine the wind speed observation value of the node in the grid network corresponding to the region according to the wind speed observation value of the wind farm in the region;
[0124] Correction module: used to correct the wind speed forecast value of the node in the grid network corresponding to the area according to the wind speed observation value of the node in the grid network corresponding to the area.
[0125] Specifically, the determination module includes:
[0126] An acquisition unit: used for acquiring wind farms in grids adjacent to nodes in a grid network corresponding to a region, which have correlations with other wind farms in the region;
[0127] The determination unit is used to determine the wind speed observation value of the node in the grid network corresponding to the region according to the wind speed observation value of the wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region.
[0128] Specifically, the acquisition unit is used to:
[0129] If the similarities between various types of observation data of the i-th wind farm within the grid range adjacent to the node in the grid network corresponding to the region and various types of observation data of the j-th wind farm in other wind farms in the region are greater than the first similarity threshold corresponding to each type of observation data, then there is a correlation between the i-th wind farm and the j-th wind farm, and the i-th wind farm is obtained;
[0130] Otherwise, there is no correlation between the i-th wind farm and the j-th wind farm, and the i-th wind farm is deleted;
[0131] Where, i∈(0,e); j∈(0,b); e is the total number of wind farms within the grid range adjacent to the node in the grid network corresponding to the region; b is the total number of wind farms in the region except the i-th wind farm;
[0132] The categories of the observation data include: temperature observation data, air pressure observation data, relative humidity observation data, wind speed observation data and precipitation observation data.
[0133] Further, the similarity of the observation data between the x-th type of observation data of the i-th wind farm and the x-th type of observation data of the j-th wind farm is determined as follows:
[0134]
[0135] In the formula, is the xth type of observation data of the ith wind farm at the lth historical moment; is the xth type of observation data of the jth wind farm at the lth historical moment; w x is the second similarity threshold of the x-th type of observation data; d is the total number of historical moments.
[0136] Further, a unit is determined for:
[0137] The wind speed observation value V of the node in the grid network corresponding to the region is determined as follows: GZ :
[0138]
[0139] Where η p is the weight of the p-th wind farm in the grids adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region; V p is the wind speed observation value of the pth wind farm in the grids adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region; n is the total number of wind farms in the grids adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region;
[0140] The weight η occupied by the p-th wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region is determined as follows: p :
[0141]
[0142] In the formula, k p is the weight ratio coefficient of the pth wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region;
[0143] The weight ratio coefficient k of the p-th wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region is determined as follows: p :
[0144]
[0145] Where, L p It is the distance between the p-th wind farm in the grid adjacent to the node in the grid network corresponding to the region and the node in the grid network corresponding to the region, which has a correlation with other wind farms in the region.
[0146] Specifically, the correction module is used to:
[0147] If the number of wind farms in the grids adjacent to the node in the region corresponding to the grid network that are correlated with other wind farms in the region is not less than 5, the wind speed forecast value of the node in the region corresponding to the grid network is corrected to 0.5V Y +0.5V GZ Otherwise, the wind speed forecast value of the node in the grid network corresponding to the area is corrected to (1-0.1·k)V Y +0.1 kV GZ ;
[0148] Among them, V Y V is the wind speed forecast value of the node in the grid network corresponding to the region; GZis the wind speed observation value of the node in the grid network corresponding to the region; k is the number of wind farms in the grids adjacent to the node in the grid network corresponding to the region that are correlated with other wind farms in the region.
[0149] Specifically, the device further includes:
[0150] A publishing module is used to publish the revised wind speed forecast value of the node in the regional corresponding grid network if the relative error between the wind speed forecast value of the node in the regional corresponding grid network and the revised wind speed forecast value of the node in the regional corresponding grid network is less than 20%; otherwise, publish the wind speed forecast value of the node in the regional corresponding grid network before correction.
[0151] Specifically, the relative error μ between the wind speed forecast value of the node in the regional corresponding grid network and the corrected wind speed forecast value of the node in the regional corresponding grid network is determined as follows:
[0152]
[0153] Where V X V is the wind speed forecast value of the node in the grid network corresponding to the region after correction; Y It is the wind speed forecast value of the node in the grid network corresponding to the region.
[0154] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0155] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0156] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0157] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0158] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.
Claims
1. A wind speed forecast correction method integrating wind farm observation data, characterized in that: The method comprises: Determine the wind speed observation value of the node in the grid network corresponding to the region according to the wind speed observation value of the wind farm in the region; Correcting the wind speed forecast values of the nodes in the grid network corresponding to the region according to the wind speed observation values of the nodes in the grid network corresponding to the region; The step of determining the wind speed observation value of a node in the grid network corresponding to the region according to the wind speed observation value of the wind farm in the region includes: Obtaining wind farms in grids adjacent to nodes in a grid network corresponding to a region that have correlations with other wind farms in the region; Determine the wind speed observation value of the node in the grid network corresponding to the region according to the wind speed observation value of the wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region; Determining the wind speed observation value of a node in the grid network corresponding to the region according to the wind speed observation value of a wind farm in a grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region includes: The wind speed observation value V of the node in the grid network corresponding to the region is determined as follows: GZ : Where η p is the weight of the p-th wind farm in the grids adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region; V p is the wind speed observation value of the pth wind farm in the grids adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region; n is the total number of wind farms in the grids adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region; The weight η occupied by the p-th wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region is determined as follows: p : In the formula, k p is the weight ratio coefficient of the pth wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region; The weight ratio coefficient k of the p-th wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region is determined as follows: p : Where, L p It is the distance between the p-th wind farm in the grid adjacent to the node in the grid network corresponding to the region and the node in the grid network corresponding to the region, which has a correlation with other wind farms in the region.
2. The method according to claim 1, characterized in that The obtaining of wind farms in grids adjacent to nodes in the grid network corresponding to the region and having correlation with other wind farms in the region includes: If the similarities between various types of observation data of the i-th wind farm within the grid range adjacent to the node in the grid network corresponding to the region and various types of observation data of the j-th wind farm in other wind farms in the region are greater than the first similarity threshold corresponding to each type of observation data, then there is a correlation between the i-th wind farm and the j-th wind farm, and the i-th wind farm is obtained; Otherwise, there is no correlation between the i-th wind farm and the j-th wind farm, and the i-th wind farm is deleted; Where, i∈(0,e); j∈(0,b); e is the total number of wind farms within the grid range adjacent to the node in the grid network corresponding to the region; b is the total number of wind farms in the region except the i-th wind farm; The categories of the observation data include: temperature observation data, air pressure observation data, relative humidity observation data, wind speed observation data and precipitation observation data.
3. The method according to claim 2, characterized in that The similarity of the observation data between the x-th type of observation data of the i-th wind farm and the x-th type of observation data of the j-th wind farm is determined as follows: In the formula, is the xth type of observation data of the ith wind farm at the lth historical moment; is the xth type of observation data of the jth wind farm at the lth historical moment; w x is the second similarity threshold of the x-th type of observation data; d is the total number of historical moments.
4. The method according to claim 1, characterized in that The method of correcting the wind speed forecast value of the node in the grid network corresponding to the region according to the wind speed observation value of the node in the grid network corresponding to the region comprises: If the number of wind farms in the grids adjacent to the node in the region corresponding to the grid network that are correlated with other wind farms in the region is not less than 5, the wind speed forecast value of the node in the region corresponding to the grid network is corrected to 0.5V Y +0.5V GZ Otherwise, the wind speed forecast value of the node in the grid network corresponding to the area is corrected to (1-0.1·k)V Y +0.1 kV GZ ; Among them, V Y V is the wind speed forecast value of the node in the grid network corresponding to the region; GZ is the wind speed observation value of the node in the grid network corresponding to the region; k is the number of wind farms in the grids adjacent to the node in the grid network corresponding to the region that are correlated with other wind farms in the region.
5. The method according to claim 1, characterized in that After correcting the wind speed forecast value of the node in the grid network corresponding to the region according to the wind speed observation value of the node in the grid network corresponding to the region, the method comprises: If the relative error between the wind speed forecast value of the node in the regional corresponding grid network and the corrected wind speed forecast value of the node in the regional corresponding grid network is less than 20%, the corrected wind speed forecast value of the node in the regional corresponding grid network is published; otherwise, the wind speed forecast value of the node in the regional corresponding grid network before correction is published.
6. The method according to claim 1, characterized in that The relative error μ between the wind speed forecast value of the node in the regional corresponding grid network and the corrected wind speed forecast value of the node in the regional corresponding grid network is determined by the following formula: Where V X V is the wind speed forecast value of the node in the grid network corresponding to the region after correction; Y It is the wind speed forecast value of the node in the grid network corresponding to the region.
7. A wind speed forecast correction device integrating wind farm observation data, characterized in that: The device comprises: Determination module: used to determine the wind speed observation value of the node in the grid network corresponding to the region according to the wind speed observation value of the wind farm in the region; Correction module: used for correcting the wind speed forecast value of the node in the grid network corresponding to the region according to the wind speed observation value of the node in the grid network corresponding to the region; The determining module comprises: An acquisition unit: used for acquiring wind farms in grids adjacent to nodes in a grid network corresponding to a region, which have correlations with other wind farms in the region; A determination unit: used to determine the wind speed observation value of a node in the grid network corresponding to the region according to the wind speed observation value of a wind farm in a grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region; Identify units for: The wind speed observation value V of the node in the grid network corresponding to the region is determined as follows: GZ : Where η p is the weight of the p-th wind farm in the grids adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region; V p is the wind speed observation value of the pth wind farm in the grids adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region; n is the total number of wind farms in the grids adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region; The weight η occupied by the p-th wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region is determined as follows: p : In the formula, k p is the weight ratio coefficient of the pth wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region; The weight ratio coefficient k of the p-th wind farm in the grid adjacent to the node in the grid network corresponding to the region and having a correlation with other wind farms in the region is determined as follows: p : Where, L p It is the distance between the p-th wind farm in the grid adjacent to the node in the grid network corresponding to the region and the node in the grid network corresponding to the region, which has a correlation with other wind farms in the region.
8. The device according to claim 7, characterized in that The acquisition unit is used to: If the similarities between various types of observation data of the i-th wind farm within the grid range adjacent to the node in the grid network corresponding to the region and various types of observation data of the j-th wind farm in other wind farms in the region are greater than the first similarity threshold corresponding to each type of observation data, then there is a correlation between the i-th wind farm and the j-th wind farm, and the i-th wind farm is obtained; Otherwise, there is no correlation between the i-th wind farm and the j-th wind farm, and the i-th wind farm is deleted; Where, i∈(0,e); j∈(0,b); e is the total number of wind farms within the grid range adjacent to the node in the grid network corresponding to the region; b is the total number of wind farms in the region except the i-th wind farm; The categories of the observation data include: temperature observation data, air pressure observation data, relative humidity observation data, wind speed observation data and precipitation observation data.
9. The device according to claim 8, characterized in that The similarity of the observation data between the x-th type of observation data of the i-th wind farm and the x-th type of observation data of the j-th wind farm is determined as follows: In the formula, is the xth type of observation data of the ith wind farm at the lth historical moment; is the xth type of observation data of the jth wind farm at the lth historical moment; w x is the second similarity threshold of the x-th type of observation data; d is the total number of historical moments.
10. The device according to claim 7, characterized in that The correction module is used to: If the number of wind farms in the grids adjacent to the node in the region corresponding to the grid network that are correlated with other wind farms in the region is not less than 5, the wind speed forecast value of the node in the region corresponding to the grid network is corrected to 0.5V Y +0.5V GZ Otherwise, the wind speed forecast value of the node in the grid network corresponding to the area is corrected to (1-0.1·k)V Y +0.1 kV GZ ; Among them, V Y V is the wind speed forecast value of the node in the grid network corresponding to the region; GZ is the wind speed observation value of the node in the grid network corresponding to the region; k is the number of wind farms in the grids adjacent to the node in the grid network corresponding to the region that are correlated with other wind farms in the region.
11. The device according to claim 7, characterized in that The device also includes: A publishing module is used to publish the revised wind speed forecast value of the node in the regional corresponding grid network if the relative error between the wind speed forecast value of the node in the regional corresponding grid network and the revised wind speed forecast value of the node in the regional corresponding grid network is less than 20%; otherwise, publish the wind speed forecast value of the node in the regional corresponding grid network before correction.
12. The device according to claim 7, characterized in that The relative error μ between the wind speed forecast value of the node in the regional corresponding grid network and the corrected wind speed forecast value of the node in the regional corresponding grid network is determined by the following formula: Where V X V is the wind speed forecast value of the node in the grid network corresponding to the region after correction; Y It is the wind speed forecast value of the node in the grid network corresponding to the region.
