Prediction method, device and equipment of sand and dust characteristic parameters and medium

Abstract

The invention discloses a sand and dust characteristic parameter prediction method and device, equipment and a medium, and belongs to the technical field of new energy power generation. According to the embodiment of the invention, the AOD intensity of each first sub-grid is obtained by performing gridding processing on the AOD intensity of the preset area at the first moment, and the AOD target intensity and the target coverage range of each first sub-grid in the first prediction time period are predicted based on the target meteorological prediction data of each sub-grid in the first prediction time period. And determining the sand and dust intensity and the sand and dust coverage range of the preset region in the first prediction time period based on the target intensity and the target coverage range of the AOD of each first sub-grid in the first prediction time period, so that particle collection equipment does not need to be arranged; therefore, the problem of inaccurate sand and dust characteristic parameter prediction caused by non-uniform distribution or small quantity of particle collection equipment can be avoided, and the accuracy of a sand and dust characteristic parameter prediction result is improved.

Description

Technical Field

[0001] The present application relates to the field of renewable energy power generation technology, and in particular to a method, device, equipment and medium for predicting characteristic parameters of dust. Background Art

[0002] The occurrence of sandstorms has a great impact on the power generation of photovoltaic power plants. On the one hand, a large amount of sand and dust in the air will reduce the intensity of direct sunlight, that is, the irradiance intensity will decrease; on the other hand, when sandstorms occur, a large amount of sand and dust will be left on the photovoltaic panels, thereby reducing the conversion efficiency of the photovoltaic panels and affecting the power of photovoltaic power generation. Therefore, in sandstorms, it is of great significance to reasonably predict the power loss of photovoltaic power generation to ensure the safe and stable operation of the power system.

[0003] The power loss of photovoltaic power generation is usually related to parameters such as the intensity of dust. Therefore, before predicting the power loss of photovoltaic power generation, it is usually necessary to predict parameters such as the intensity of dust.

[0004] At present, the particle collection equipment is mainly used to collect the particles in the dust, and the intensity and other parameters of the dust are predicted based on the particles, but the accuracy is poor. Summary of the invention

[0005] The embodiments of the present application provide a method, device, equipment and medium for predicting characteristic parameters of dust, which can accurately predict the characteristic parameters of dust within a preset time period in the future.

[0006] In a first aspect, a method for predicting dust characteristic parameters is proposed according to an embodiment of the present application, including:

[0007] Obtaining a first intensity of aerosol optical thickness AOD in a preset area at a first moment;

[0008] Performing grid processing on the space where the preset area is located to obtain a first grid, where the first grid includes at least one sub-grid;

[0009] For a first subgrid in a first grid, obtaining target meteorological forecast data of the first subgrid within a first forecast time period, the first subgrid being any subgrid in the first grid, and the first forecast time period being a time period after a first moment;

[0010] Predicting a target intensity and a target coverage of the AOD in each first subgrid within a first prediction time period according to the first intensity of the AOD in each first subgrid and the target meteorological forecast data;

[0011] According to the target intensity and target coverage of the AOD of each first subgrid in the first prediction time period, characteristic parameters of dust in the preset area in the first prediction time period are determined.

[0012] In some embodiments, obtaining target meteorological forecast data of a first subgrid within a first forecast time period includes:

[0013] Acquire meteorological observation data of a first observation point in a first subgrid at a first moment, and initial meteorological forecast data of the first subgrid in a first forecast time period;

[0014] The initial meteorological forecast data is corrected according to the meteorological observation data to obtain the target meteorological forecast data of the first subgrid in the first forecast time period.

[0015] In some embodiments, the initial meteorological forecast data is corrected according to the meteorological observation data to obtain the target meteorological forecast data of the first subgrid in the first forecast time period, including:

[0016] Determine a spatial distance between the first subgrid and the first observation point according to the first spatial position information of the first subgrid and the second spatial position information of the first observation point;

[0017] Determine the time distance between the first subgrid and the first observation point in the first prediction time period according to the first wind speed at each preset time point in the first prediction time period;

[0018] According to the spatial distance and the temporal distance, combined with the weight calculation formula, the first weight of the first observation point at the first moment is determined;

[0019] The initial meteorological forecast data is corrected according to the first weight and the meteorological observation data to obtain the target meteorological forecast data of the first subgrid within the first forecast time period.

[0020] In some embodiments, determining the first weight of the first observation point at the first moment according to the spatial distance and the temporal distance in combination with a weight calculation formula includes:

[0021] The first weight of the first observation point at the first moment is determined by:

[0022]

[0023] Among them, w(t) i is the first weight of the i-th first observation point in the first subgrid at the first moment, t is the first moment, t+Δt is the first preset time period, DIS1i is the spatial distance between the first subgrid and the i-th first observation point, and DIS2i is the time distance between the first subgrid and the i-th first observation point in the first prediction time period;

[0024] DIS2i=v1+v2+…+v m

[0025] v1, v2, ..., v mis the first wind speed at each preset time point in the first prediction time period, and m is the number of preset time points.

[0026] In some embodiments, the initial meteorological forecast data is corrected according to the first weight and the meteorological observation data to obtain the target meteorological forecast data of the first subgrid in the first forecast time period, including:

[0027] The initial weather forecast data is corrected by:

[0028] Y(t1) rev =Y(t1) mod +w(t)1·[OBS(t)1-Y(t1) mod ]+w(t)2

[0029] ·[OBS(t)2-Y(t1) mod ]+…+w(t) i ·[OBS(t) i -Y(t1) mod ]

[0030] Wherein, t1 is the first preset time period, t1=t+Δt, t is the first moment, Y(t1) mod is the initial meteorological forecast data of the first subgrid in the first forecast period, OBS(t) i is the meteorological observation data of the first observation point i in the first subgrid at the first moment, w(t) i is the first weight of the first observation point i in the first subgrid at the first moment, Y(t1) rev It is the target meteorological forecast data of the first subgrid in the first forecast time period.

[0031] In some embodiments, according to the first intensity of the AOD in each first subgrid and the target meteorological forecast data, predicting the target intensity and target coverage of the AOD in each first subgrid in the first forecast time period includes:

[0032] The first prediction model is used to process the first intensity of the AOD in each first subgrid and the target meteorological prediction data to obtain the target intensity and target coverage of the AOD in each first subgrid in the first prediction time period.

[0033] In some embodiments, the target weather forecast data includes a predicted wind speed and a predicted wind direction, and the first subgrid includes a preset number of particles, each particle moving with the predicted wind speed and the predicted wind direction;

[0034] The first intensity of the AOD in each first subgrid and the target meteorological forecast data are processed by using the first forecast model to obtain the target coverage of the AOD in each first subgrid in the first forecast time period, including:

[0035] Inputting the first intensity of the AOD in each first subgrid and the target meteorological forecast data into the first forecast model, and using the first processing module of the first forecast model, in combination with the predicted wind speed and the predicted wind direction, determining the position vector of each particle in each first subgrid in the first forecast time period;

[0036] According to the position vector of each particle, the target coverage range of the AOD of each first subgrid within the first prediction time period is determined.

[0037] In some embodiments, the first intensity of AOD in each first subgrid and the target meteorological forecast data are processed using the first forecast model to obtain the target intensity of AOD in each first subgrid in the first forecast time period, including:

[0038] For each first subgrid, using the second processing module of the first prediction model, combined with the target coverage range of the AOD of the first subgrid in the first prediction time period, determine the particles contained in the first subgrid at each sampling time, where each sampling time is a time in the first prediction time period;

[0039] Determine a second intensity of the AOD of the first subgrid at each sampling moment according to the particles of the first subgrid at each sampling moment and the intensity of the equivalent AOD corresponding to each particle;

[0040] The average value of the second intensity of the AOD at each sampling moment is determined as the target intensity of the AOD of the first subgrid in the first prediction time period.

[0041] In some embodiments, the characteristic parameters of the dust include dust intensity and dust coverage;

[0042] Determining characteristic parameters of dust in a preset area in the first prediction time period according to the target intensity and target coverage of the AOD of each first subgrid in the first prediction time period includes:

[0043] Determine the target intensity of the AOD of each first subgrid in the first prediction time period as the dust intensity of each position in the preset area in the first prediction time period, and each position in the preset area corresponds to the position of each first subgrid;

[0044] The total target coverage range of the AOD of each first subgrid in the first prediction time period is determined as the dust coverage range of the preset area in the first prediction time period.

[0045] In some embodiments, after predicting the target intensity and target coverage of the AOD in each first subgrid within the first prediction time period according to the first intensity of the AOD in each first subgrid and the target meteorological forecast data, the method further includes:

[0046] Determine a target first subgrid corresponding to the first observation point according to spatial position information of the first observation point in the first subgrid, and determine a target intensity of the AOD in the target first subgrid as the AOD intensity of the first observation point;

[0047] According to the AOD intensity of the first observation point and in combination with the correlation between the AOD intensity and the power reduction ratio, a target power reduction ratio of the first observation point in the first prediction time period is determined.

[0048] In some embodiments, before obtaining a first intensity of aerosol optical thickness AOD of a preset area at a first moment, the method further includes:

[0049] Obtaining the historical power loss ratio of each first observation point in the preset area at each preset historical moment and the third intensity of the AOD of each first subgrid at each preset historical moment;

[0050] Determining, from the third intensities, a fourth intensity corresponding to each first observation point according to the spatial position information of each first observation point;

[0051] Function fitting is performed on the fourth intensity of each first observation point at each preset historical moment and the historical power loss ratio to obtain a correlation between the AOD intensity and the power loss ratio.

[0052] In a second aspect, an embodiment of the present application provides a device for predicting dust characteristic parameters, including: an acquisition module, a processing module, a prediction module, and a determination module;

[0053] An acquisition module, used to acquire a first intensity of aerosol optical thickness AOD in a preset area at a first moment;

[0054] A processing module, configured to perform grid processing on the space where the preset area is located to obtain a first grid, wherein the first grid includes at least one sub-grid;

[0055] The acquisition module is further used to acquire, for a first subgrid in the first grid, target meteorological forecast data of the first subgrid within a first forecast time period, the first subgrid being any subgrid in the first grid, and the first forecast time period being a time period after the first moment;

[0056] A prediction module, used for predicting a target intensity and a target coverage range of the AOD of each first subgrid in a first prediction time period according to the first intensity of the AOD in each first subgrid and the target meteorological prediction data;

[0057] The determination module is used to determine the characteristic parameters of dust in the preset area within the first prediction time period according to the target intensity and target coverage of the AOD of each first sub-grid within the first prediction time period.

[0058] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0059] processor;

[0060] a memory for storing computer program instructions;

[0061] When the computer program instructions are executed by the processor, the method according to the first aspect is implemented.

[0062] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the method described in the first aspect is implemented.

[0063] The embodiment of the present application obtains the AOD intensity of each first sub-grid by gridding the AOD intensity of the preset area at the first moment, and predicts the target intensity and target coverage of the AOD of each first sub-grid in the first prediction time period based on the target meteorological forecast data of each sub-grid in the first prediction time period. Then, based on the target intensity and target coverage of the AOD of each first sub-grid in the first prediction time period, the dust intensity and dust coverage of the preset area in the first prediction time period are determined, without setting up a particle collection device. In this way, the problem of inaccurate prediction of dust characteristic parameters due to uneven distribution or small number of particle collection devices can be avoided, thereby improving the accuracy of the prediction results of dust characteristic parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The features, advantages and technical effects of exemplary embodiments of the present application will be described below with reference to the accompanying drawings.

[0065] Figure 1 A flow chart of a method for predicting dust characteristic parameters provided in an embodiment of the present application;

[0066] Figure 2 A flowchart of another method for predicting dust characteristic parameters provided in an embodiment of the present application;

[0067] Figure 3 A flowchart of another method for predicting dust characteristic parameters provided in an embodiment of the present application;

[0068] Figure 4 A flowchart of another method for predicting dust characteristic parameters provided in an embodiment of the present application;

[0069] Figure 5 A flowchart of another method for predicting dust characteristic parameters provided in an embodiment of the present application;

[0070] Figure 6A schematic diagram of a correlation between AOD intensity and power loss ratio based on sigmoid function fitting provided in an embodiment of the present application;

[0071] Figure 7 A schematic diagram of a correlation between AOD intensity and power loss ratio based on linear function fitting provided in an embodiment of the present application;

[0072] Figure 8 A schematic diagram comparing a predicted result and an actual result of a power loss ratio provided in an embodiment of the present application;

[0073] Fig. 9 A structural diagram of a device for predicting dust characteristic parameters provided in an embodiment of the present application;

[0074] Fig.10 A structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0075] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In the detailed description below, many specific details are proposed to provide a comprehensive understanding of the present application. However, it is obvious to those skilled in the art that the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating examples of the present application. In the accompanying drawings and the following description, at least some of the known structures and technologies are not shown to avoid unnecessary ambiguity in the present application; and, for clarity, the size of some structures may be exaggerated. In addition, the features, structures or characteristics described below may be combined in one or more embodiments in any suitable manner.

[0076] The directional words appearing in the following description are all directions shown in the figures, and do not limit the specific structure of this application. In the description of this application, it should also be noted that, unless otherwise clearly specified and limited, the terms "installation" and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be directly connected or indirectly connected. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to the specific circumstances.

[0077] The occurrence of sandstorms has a great impact on the power generation of photovoltaic fields. Therefore, in sandstorms, reasonably predicting the power loss of photovoltaic power generation is of great significance to ensure the safe and stable operation of the power system.

[0078] The power loss of photovoltaic power generation is usually related to the characteristic parameters of dust, such as intensity. Therefore, before predicting the power loss of photovoltaic power generation, it is usually necessary to predict parameters such as the intensity of dust.

[0079] At present, the particle collection equipment is mainly used to collect the particles in the dust, and the intensity and other parameters of the dust are predicted based on the particles, but the accuracy is poor.

[0080] To this end, the embodiments of the present application provide a method, device, equipment and medium for predicting characteristic parameters of sand and dust, which can accurately predict the characteristic parameters of sand and dust within a preset time period in the future.

[0081] The following is a detailed description of the method, device, equipment and medium for predicting dust characteristic parameters provided in the embodiments of the present application through specific examples.

[0082] Figure 1 A flow chart of a method for predicting dust characteristic parameters provided in an embodiment of the present application, such as Figure 1 As shown, the method for predicting dust characteristic parameters may include the following steps:

[0083] S110: Obtain a first intensity of aerosol optical thickness AOD in a preset area at a first moment.

[0084] S120: Grid the space where the preset area is located to obtain a first grid.

[0085] The first grid includes at least one sub-grid.

[0086] S130. For a first subgrid in a first grid, obtain target meteorological forecast data of the first subgrid within a first forecast time period.

[0087] The first sub-grid is any sub-grid in the first grid, and the first prediction time period is a time period after the first moment.

[0088] S140 , predicting a target intensity and a target coverage range of the AOD in each first subgrid within a first prediction time period according to the first intensity of the AOD in each first subgrid and the target meteorological forecast data.

[0089] S150: Determine characteristic parameters of dust in a preset area in the first prediction time period according to the target intensity and target coverage of the AOD of each first subgrid in the first prediction time period.

[0090] The embodiment of the present application obtains the AOD intensity of each first sub-grid by gridding the AOD intensity of the preset area at the first moment, and predicts the target intensity and target coverage of the AOD of each first sub-grid in the first prediction time period based on the target meteorological forecast data of each sub-grid in the first prediction time period. Then, based on the target intensity and target coverage of the AOD of each first sub-grid in the first prediction time period, the dust intensity and dust coverage of the preset area in the first prediction time period are determined, without setting up a particle collection device. In this way, the problem of inaccurate prediction of dust characteristic parameters due to uneven distribution or small number of particle collection devices can be avoided, thereby improving the accuracy of the prediction results of dust characteristic parameters.

[0091] The above steps are described in detail below:

[0092] In S110, the preset area can be selected as needed, for example, the area where one or more photovoltaic stations are located can be used as the preset area.

[0093] Exemplarily, the first moment may be the current moment. Aerosol Optical Depth (AOD) is the vertical integral of the atmospheric extinction coefficient. It is an optical parameter that describes the degree of aerosol extinction and a key physical quantity that describes the degree of atmospheric turbidity. Therefore, based on the intensity of AOD in the preset area at the first moment, the characteristic parameters of dust in the preset area in the future preset time period can be predicted, providing a basis for the subsequent prediction of the power loss of the corresponding photovoltaic station in the preset area.

[0094] The first intensity of the AOD of the preset area at the first moment may be a value of the AOD of the preset area at the first moment, which is used to characterize the dust intensity of the preset area at the first moment.

[0095] Exemplarily, the AOD value of the preset area at the first moment can be obtained from multiple satellites. The multiple satellites may include, for example, a Visible infrared Imaging Radiometer (VIIRS), a Moderate-resolution Imaging Spectroradiometer (MODIS), and multiple sunflower satellites. Of course, other satellites may also be included, which is not limited in the embodiments of the present application.

[0096] In actual application, the obtained AOD value may be positive or negative, wherein AOD<0 is an invalid value. Therefore, after obtaining the first intensity of AOD in the preset area at the first moment from each satellite, data cleaning can be performed to delete the data of AOD<0. That is, the embodiment of the present application is based on the characteristic parameters of effective AOD prediction of sand and dust, which can improve the accuracy of sand and dust prediction results.

[0097] In S120, in order to improve the accuracy of the prediction results of the dust characteristic parameters, illustratively, the space where the preset area is located can be gridded to obtain a first grid, and the first grid can include one or more sub-grids. The embodiment of the present application takes the first grid including multiple sub-grids as an example.

[0098] The size of each character grid can be set according to actual needs, and the size of each sub-grid can be the same or different.

[0099] Exemplarily, the plane where the preset area is located can be divided into 2km*2km subgrids. Because the first intensity of the AOD in the preset area at the first moment may be multiple, that is, from different satellites, in some embodiments, if there are multiple satellite AODs in the same subgrid at a certain moment, the AOD value of one satellite can be selected as the AOD value of the subgrid at that moment.

[0100] For example, the priorities of VIIRS, MODIS and Sunflower satellites decrease in turn, and the AOD value of the satellite with the highest priority can be preferentially selected as the AOD value of each subgrid at a certain moment. In actual application, the AOD values ​​of each subgrid can come from the same satellite or from different satellites.

[0101] In some embodiments, the AOD values ​​of each satellite may be averaged as the AOD value of each subgrid at a certain moment, and the AOD value of each satellite may be multiplied by the weight corresponding to the satellite, and the weighted sum of the AOD of each satellite may be determined as the AOD value of each subgrid at a certain moment. The weight of each satellite may be determined based on the priority of each satellite, for example, the higher the priority, the greater the corresponding weight. The priority of each satellite may be specified by the user.

[0102] In S130, the first prediction time period is a time period after the first moment. For example, if the first moment is moment t, the first prediction time period may be t+Δt, and the value of Δt may be set according to actual needs.

[0103] The target meteorological forecast data is the meteorological forecast data of the first subgrid within the first preset time period, and the meteorological forecast data may be forecast data of the wind speed and wind direction of the meteorological elements.

[0104] Because wind direction and wind speed have a significant impact on the diffusion process of sand and dust, after gridding the space where the preset area is located, the embodiment of the present application can obtain the target meteorological forecast data of each first sub-grid within the first prediction time period, thereby improving the accuracy of subsequent sand and dust characteristic parameter prediction results.

[0105] The process of acquiring target weather forecast data can be seen in the following embodiments.

[0106] In S140, since wind direction and wind speed have a certain influence on the diffusion of sand and dust, and the intensity of AOD can reflect the intensity of sand and dust, based on wind direction and wind speed, combined with the first intensity of AOD of each first sub-grid at the first moment, the target intensity and target coverage range of AOD of each first sub-grid in the first prediction time period can be predicted first, so as to facilitate the subsequent prediction of characteristic parameters of sand and dust.

[0107] For example, the target intensity and target coverage of the AOD of each first subgrid in the first prediction time period can be predicted based on the prediction model, the prediction model takes the first intensity of the AOD of each first subgrid at the first moment and the target meteorological prediction data as input, and the target intensity and target coverage of the AOD of each first subgrid in the first prediction time period as output. The structure of the prediction model can be set according to actual needs, for example, an existing deep learning model can be used, or a model can be built.

[0108] For example, the relationship between the intensity of AOD and the meteorological forecast data can also be learned based on the historical meteorological forecast data and the intensity of AOD of each first subgrid at a historical moment, and based on the relationship, the target intensity of AOD of each first subgrid within the first forecast time period can be predicted. Based on the AOD distribution of each first subgrid within the first forecast time period, the target coverage range of each first subgrid within the first forecast time period can be obtained.

[0109] Of course, other methods may also be used to predict the target intensity and target coverage of AOD in each first subgrid within the first prediction time period based on the first intensity of AOD in each first subgrid and the target meteorological forecast data, which is not limited in the embodiments of the present application.

[0110] In S150, after the target intensity and target coverage range of AOD of each first subgrid in the first prediction time period are determined, the characteristic parameters of dust in the preset area in the first prediction time period can be determined based on the target intensity and target coverage range of AOD of each first subgrid in the first prediction time period.

[0111] Exemplarily, the characteristic parameters of sand and dust in the preset area within the first prediction time period may include the intensity and coverage of sand and dust in the preset area within the first prediction time period.

[0112] For example, the intensity and coverage of dust in a preset area during the first prediction time period may be determined in the following manner:

[0113] Determine the target intensity of the AOD of each first subgrid in the first prediction time period as the dust intensity of each position in the preset area in the first prediction time period, and each position in the preset area corresponds to the position of each first subgrid;

[0114] The total target coverage range of the AOD of each first subgrid in the first prediction time period is determined as the dust coverage range of the preset area in the first prediction time period.

[0115] Different subgrids correspond to different positions in the preset area, and the target intensity of AOD of each first subgrid in the first prediction time period is also the dust intensity of each position in the preset area in the first prediction time period.

[0116] Each position here may be a position corresponding to an area on the plane where the first subgrid is located, that is, the target intensity of AOD of each first subgrid in the first prediction time period, that is, the dust intensity of each sub-area of ​​the preset area in the first prediction time period.

[0117] The total target coverage range of the AOD of each first subgrid in the first prediction time period is the dust coverage range of the preset area in the first prediction time period.

[0118] That is, the embodiment of the present application can characterize the intensity and coverage of sandstorms in a preset area during the first prediction time period through the intensity and coverage of AOD in each first subgrid during the first prediction time period, thereby achieving quantitative processing of the weather phenomenon of sandstorms.

[0119] The embodiment of the present application predicts the target intensity and target coverage of the AOD in each first subgrid within the first prediction time period through the first intensity of the AOD in each first subgrid and the target meteorological forecast data, thereby improving the accuracy of the prediction results. Therefore, when predicting the characteristic parameters of sand and dust in a preset area within the first prediction time period based on the target intensity and target coverage of the AOD in each first subgrid within the first prediction time period, the accuracy of the dust prediction results is improved.

[0120] In some embodiments, Figure 2 As shown, the method for predicting dust characteristic parameters may include the following steps:

[0121] S210: Obtain a first intensity of aerosol optical thickness AOD in a preset area at a first moment.

[0122] S220: Gridding the space where the preset area is located to obtain a first grid, where the first grid includes at least one sub-grid.

[0123] S230. For a first subgrid in a first grid, obtain meteorological observation data of a first observation point in the first subgrid at a first moment, and initial meteorological forecast data of the first subgrid in a first forecast time period.

[0124] S240: Correct the initial meteorological forecast data according to the meteorological observation data to obtain target meteorological forecast data for the first subgrid within the first forecast time period.

[0125] S250 , predicting the target intensity and target coverage of the AOD in each first subgrid within a first prediction time period according to the first intensity of the AOD in each first subgrid and the target meteorological forecast data.

[0126] S260: Determine characteristic parameters of dust in a preset area in the first prediction time period according to the target intensity and target coverage of the AOD of each first subgrid in the first prediction time period.

[0127] Among them, the processes of S210, S220, S250 and S260 are the same as the processes of S110, S120, S140 and S150 mentioned above. For details, please refer to the description of S110, S120, S140 and S150. For the sake of brevity, they will not be repeated here.

[0128] The other steps above are described in detail below:

[0129] In S230, the first observation point here may be a photovoltaic station or a meteorological station, and one photovoltaic station may correspond to one or more meteorological stations. The first subgrid may include one or more first observation points.

[0130] Meteorological observation data may include meteorological elements wind direction and wind speed. Exemplarily, the meteorological observation data may be obtained from a photovoltaic station. If the meteorological observation data cannot be obtained from the photovoltaic station, it may be obtained from a meteorological station corresponding to the photovoltaic station.

[0131] The initial meteorological forecast data may be data obtained by predicting various meteorological elements through a meteorological numerical model (The Weather Research and Forecasting Model, WRF).

[0132] In S240, the initial meteorological forecast data actually obtained from official or unofficial meteorological agencies may contain errors. In order to accurately predict the intensity and coverage of AOD of each first subgrid within the first prediction time period, the embodiment of the present application can use the meteorological observation data of the first observation point in the first subgrid at the first moment to correct the initial meteorological forecast data of the first subgrid within the first prediction time period to obtain the target meteorological forecast data.

[0133] Exemplarily, for each first subgrid, the difference between the meteorological observation data of each first observation point contained in the first subgrid at the first moment and the initial meteorological forecast data of the first subgrid in the first forecast time period may be determined;

[0134] Then, each difference is weighted and summed to obtain a weighted summation result, and the weighted summation result is used to correct the initial weather forecast data. For example, the weighted summation result can be directly added to the initial weather forecast data to obtain the target weather forecast data.

[0135] The weighted summation result and the initial weather forecast data may also be calculated by other calculation methods to obtain the target weather forecast data.

[0136] Exemplarily, the weights corresponding to different difference values ​​may be determined based on the spatial distance between each first observation point and the first subgrid. For example, the larger the spatial distance, the smaller the corresponding weight.

[0137] Exemplarily, the weights corresponding to different differences may also be determined based on the time distance between the first subgrid and the first observation point, for example, the larger the time distance, the smaller the corresponding weight. The time distance may be determined based on the wind speed corresponding to a preset time interval within the first prediction time period.

[0138] Exemplarily, the weights corresponding to different difference values ​​may also be determined based on the spatial distance between each first observation point and the first subgrid and the temporal distance between the first subgrid and the first observation point.

[0139] The embodiment of the present application utilizes the meteorological observation data of the first observation point in the first sub-grid at the first moment to correct the initial meteorological forecast data of the first sub-grid in the first prediction time period to obtain the target meteorological forecast data, thereby improving the accuracy of the target meteorological forecast data. In this way, when predicting the target intensity and target coverage range of the AOD of the first sub-grid in the first prediction time period based on the target meteorological forecast data, the accuracy of the prediction result can be improved.

[0140] In some embodiments, Figure 3 As shown, the method for predicting dust characteristic parameters may include the following steps:

[0141] S310: Obtain a first intensity of aerosol optical thickness AOD in a preset area at a first moment.

[0142] S320: Grid the space where the preset area is located to obtain a first grid.

[0143] S330, obtaining meteorological observation data of a first observation point in a first subgrid at a first moment, and initial meteorological forecast data of the first subgrid in a first forecast time period.

[0144] S340: Determine a spatial distance between the first subgrid and the first observation point according to the first spatial position information of the first subgrid and the second spatial position information of the first observation point.

[0145] S350. Determine the time distance between the first subgrid and the first observation point in the first prediction time period according to the first wind speed at each preset time point in the first prediction time period.

[0146] S360: Determine a first weight of the first observation point at the first moment according to the spatial distance and the temporal distance in combination with a weight calculation formula.

[0147] S370. Correct the initial meteorological forecast data according to the first weight and the meteorological observation data to obtain the target meteorological forecast data of the first subgrid within the first forecast time period.

[0148] S380: predict the target intensity and target coverage of the AOD in each first subgrid within the first prediction time period according to the first intensity of the AOD in each first subgrid and the target meteorological forecast data.

[0149] S390: Determine characteristic parameters of dust in a preset area in the first prediction time period according to the target intensity and target coverage of the AOD of each first subgrid in the first prediction time period.

[0150] Among them, the processes of S310-S330, S380 and S390 are the same as the above-mentioned processes of S210-S230 and S250 and S260. For details, please refer to the description of S210-S230 and S250 and S260. For the sake of brevity, they will not be repeated here.

[0151] The other steps above are described in detail below:

[0152] In S340, the first spatial position information is the spatial position information of the first subgrid, and exemplarily, the first spatial position information may be the longitude and latitude of the first subgrid. The second spatial position information is the spatial position information of the first observation point, and exemplarily, the second spatial position information may be the longitude and latitude of the first observation point.

[0153] Based on the longitude and latitude of the first subgrid and the longitude and latitude of the first observation point, the spatial distance between the first subgrid and the first observation point can be determined. The spatial distance between the first subgrid and the first observation point is the square root of the sum of the square of the longitude difference and the square of the latitude difference.

[0154] For example, DIS1i is the spatial distance between the first subgrid and the i-th first observation point, Δloni is the longitude difference between the first subgrid and the i-th first observation point, and Δlati is the latitude difference between the first subgrid and the i-th first observation point.

[0155] In S350, the time distance between the first subgrid and the first observation point in the first prediction time period is the sum of the wind speeds at each preset time point in the first prediction time period.

[0156] The preset time points can be set according to actual needs, and the time intervals between two adjacent preset time points can be the same or different.

[0157] For example, DIS2i=(v1+v2+…+v m ), DIS2i is the time distance between the first subgrid and the i-th first observation point, v1, v2, …, v m is the wind speed at each preset time point, and m is the number of preset time points set within the first prediction time period.

[0158] In S360, according to the spatial distance between the first subgrid and the i-th first observation point and the temporal distance between the first subgrid and the i-th first observation point, combined with the weight calculation formula, the first weight of the first observation point at the first moment can be determined.

[0159] Exemplarily, the first weight of the first observation point at the first moment may be determined in the following manner:

[0160]

[0161] Among them, w(t) i is the first weight of the i-th first observation point in the first sub-grid at the first moment, t is the first moment, t+Δt is the first preset time period, DIS1i is the spatial distance between the first sub-grid and the i-th first observation point, and DIS2i is the time distance between the first sub-grid and the i-th first observation point in the first prediction time period.

[0162] The determination process of DIS1i and DIS2i can refer to the above embodiment. The first weight of the i-th first observation point at the first moment can be obtained through the above weight calculation formula.

[0163] In the embodiment of the present application, taking the determination of the first weight of the i-th first observation point at the first moment based on the spatial distance between the first subgrid and the i-th first observation point and the temporal distance between the first subgrid and the i-th first observation point within the first prediction time period as an example, more comprehensive factors are considered and the weights are more accurate.

[0164] In S370, after the first weights of each first observation point in the first sub-grid at the first moment are determined, the initial meteorological forecast data of the first sub-grid in the first prediction time period can be corrected based on the first weights of each first observation point at the first moment and the meteorological observation data of each first observation point at the first moment to obtain the target meteorological forecast data.

[0165] The embodiment of the present application utilizes the spatial distance between the first sub-grid and each first observation point and the temporal distance between the first sub-grid and each first observation point within the first prediction time period to determine the first weight of each first observation point, and then based on the first weight of each first observation point and combined with the meteorological observation data of each first observation point at the first moment, correct the initial meteorological forecast data of the first sub-grid within the first prediction time period, taking into account more comprehensive information, thereby improving the accuracy of the target meteorological forecast data.

[0166] Exemplarily, the initial weather forecast data may be corrected in the following manner:

[0167] Y(t1) rev =Y(t1) mod +w(t)1·[OBS(t)1-Y(t1) mod ]+w(t)2

[0168] ·[OBS(t)2-Y(t1) mod ]+…+w(t) i ·[OBS(t) i -Y(t1) mod ]

[0169] Wherein, t1 is the first preset time period, t1=t+Δt, t is the first moment, Y(t1) mod is the initial meteorological forecast data of the first subgrid in the first forecast period, OBS(t) i is the meteorological observation data of the first observation point i in the first subgrid at the first moment, w(t) i is the first weight of the first observation point i in the first subgrid at the first moment, Y(t1) rev It is the target meteorological forecast data of the first subgrid in the first forecast time period.

[0170] Exemplarily, for each first observation point within the first subgrid, the difference between the meteorological observation data of the first observation point at the first moment and the initial meteorological forecast data of the first subgrid within the first prediction time period can be determined, and then the difference is weighted with the first weight corresponding to the first observation point to obtain the weighted result of the first observation point.

[0171] Then, the weighted results of each first observation point are summed and added to the initial meteorological forecast data of the first subgrid in the first forecast time period to obtain the target meteorological forecast data.

[0172] The embodiment of the present application utilizes the meteorological observation data of each first observation point in the first sub-grid, combined with the weight of each first observation point, to correct the initial meteorological forecast data of the first sub-grid in the first prediction time period, fully considering the impact of the meteorological elements of each first observation point at the first moment on the prediction result, thereby improving the accuracy of the target meteorological forecast data.

[0173] Taking the prediction of the target intensity and target coverage of the AOD of each first subgrid in the first prediction time period by the prediction model as an example, illustratively, the above S140 may include the following steps:

[0174] The first prediction model is used to process the first intensity of the AOD in each first subgrid and the target meteorological prediction data to obtain the target intensity and target coverage of the AOD in each first subgrid in the first prediction time period.

[0175] The specific structure of the first prediction model is not limited in the present application embodiment. Any model structure that can predict the target intensity and target coverage of the AOD of each first subgrid in the first prediction time period based on the first intensity of the AOD in each first subgrid and the target meteorological forecast data of each first subgrid in the first prediction time period can be applied to the present application embodiment.

[0176] Exemplarily, the first prediction model takes the first intensity of AOD in each first subgrid and the target meteorological prediction data of each first subgrid in the first prediction time period as input, and takes the target intensity and target coverage range of AOD in each first subgrid in the first prediction time period as output.

[0177] Before application, the first prediction model may be trained based on the sample intensity of the AOD in each first subgrid and the sample meteorological prediction data of each first subgrid in a historical time period.

[0178] The embodiment of the present application utilizes the first prediction model to simultaneously predict the target intensity and target coverage of the AOD of each first subgrid in the preset area within the first prediction time period at multiple points, thereby improving the computational efficiency.

[0179] It should be understood that the intensity and coverage of AOD in the first sub-grid vary with wind direction and wind speed. In order to facilitate the determination of the coverage range of AOD, each first sub-grid can be regarded as a certain number of particles, which move with the wind direction and wind speed. Therefore, the position of each particle at each moment can be predicted based on the first prediction model to obtain the target coverage range of AOD of each first sub-grid in the first prediction time period.

[0180] Then, based on the target coverage of AOD of each first subgrid in the first prediction time period, the AOD intensity of each particle contained in each first subgrid can be determined, and then the target intensity of AOD in each first subgrid can be obtained.

[0181] Taking the target weather forecast data including the forecast wind speed and the forecast wind direction, the first subgrid includes a preset number of particles, and each particle moves with the forecast wind speed and the forecast wind direction as an example, for example, Figure 4 As shown, the method for predicting dust characteristic parameters may include the following steps:

[0182] S410: Obtain a first intensity of aerosol optical thickness AOD in a preset area at a first moment.

[0183] S420: Grid the space where the preset area is located to obtain a first grid.

[0184] S430. For a first subgrid in the first grid, obtain target meteorological forecast data of the first subgrid within a first forecast time period.

[0185] S440, inputting the first intensity of AOD in each first subgrid and the target meteorological forecast data into the first forecast model, using the first processing module of the first forecast model, combining the predicted wind speed and the predicted wind direction, to determine the position vector of each particle in each first subgrid within the first forecast time period.

[0186] S450 , determining the target coverage range of the AOD of each first subgrid within the first prediction time period according to the position vector of each particle.

[0187] S460 , for each first sub-grid, using the second processing module of the first prediction model and combining the target coverage range of the AOD of the first sub-grid in the first prediction time period, determine the particles contained in the first sub-grid at each sampling time.

[0188] Each sampling moment is a moment within the first prediction time period.

[0189] S470 , determining a second intensity of the AOD of the first sub-grid at each sampling moment according to the particles of the first sub-grid at each sampling moment and the intensity of the equivalent AOD corresponding to each particle.

[0190] S480: Determine the average of the second intensity of the AOD at each sampling moment as the target intensity of the AOD of the first subgrid in the first prediction time period.

[0191] S490: Determine characteristic parameters of dust in a preset area in the first prediction time period according to the target intensity and target coverage of the AOD of each first subgrid in the first prediction time period.

[0192] Among them, the processes of S410-S430 and S490 are the same as the processes of S110-S130 and S150 mentioned above. For details, please refer to the description of S110-S130 and S150 mentioned above. For the sake of brevity, they will not be repeated here.

[0193] The other steps above are described in detail below:

[0194] In S440, the first processing module is used to predict the position vector of each particle of each first subgrid within the first prediction time period. The number of particles contained in each first subgrid can be the same or different, and the number of particles contained in each first subgrid can be set according to actual needs. For example, in order to improve the accuracy of the prediction result, each first subgrid can contain as many particles as possible. For example, each first subgrid can contain 30,000 particles.

[0195] Exemplarily, the first processing module may combine the first-order motion equation to predict the position vector of each particle within the first prediction time period.

[0196] The first-order equation of motion takes the form:

[0197] X(t+Δt)=X(t)+v(x,t)·Δt

[0198] Among them, X(t) is the position vector of the particle at the first moment t, v(x,t) is the movement speed of the particle, Δt is the time increment, and X(t+Δt) is the position vector of the particle at the moment (t+Δt).

[0199] For example, the particle velocity v(x, t) can be obtained by the modified grid-scale wind speed Turbulent wind speed (v t ) and mesoscale disturbance wind speed (v ′ ) is determined in three parts. Among them, v t and v ′ It can be obtained from WRF. The corrected grid-scale wind speed is also the predicted wind speed. Exemplarily, the particle movement speed is the vector sum of the predicted wind speed, the turbulent disturbance wind speed and the mesoscale wind speed.

[0200] Through the above first-order motion equation, the first processing module can determine the position vector of each particle at the time (t+Δt).

[0201] In S450, after the position vector of each particle at the time (t+Δt) is determined, the target coverage range of the AOD of each first subgrid within the first prediction time period can be determined based on the position vector of each particle.

[0202] The embodiment of the present application equates each first sub-grid to a certain number of particles, and based on the characteristics of each particle moving with the wind direction and wind speed, combined with the first-order motion equation, predicts the position vector of each particle at the time (t+Δt), and then determines the target coverage range of the AOD of each first example grid within the first prediction time period based on the position vector of each particle at the time (t+Δt), thereby realizing multi-point concurrent short-term sandstorm deduction calculation, and improving the calculation efficiency and the accuracy of the prediction results.

[0203] In S460, the second processing module is used to predict the target intensity of the AOD of each first subgrid in the first prediction time period. After the target coverage of the AOD of each first subgrid in the first prediction time period is determined, the AOD distribution in each first subgrid is also determined, and based on the AOD distribution in each first subgrid, the target intensity of the AOD in each first subgrid can be determined.

[0204] Exemplarily, for each first subgrid, based on the target coverage range of the AOD of the first subgrid in the first prediction time period, the particles contained in the first subgrid at each sampling time may be counted, where the sampling time is a time in the first prediction time period.

[0205] Exemplarily, sampling can be performed according to a preset sampling frequency to obtain particles contained in the first subgrid at each sampling time. Exemplarily, the sampling frequency can be set to 180s.

[0206] According to the diffusion characteristics of particles, particles in the same subgrid can diffuse to other subgrids under the influence of wind direction and wind speed. Therefore, the particles contained in the first subgrid at each sampling time can come from the first subgrid or from other first subgrids. Counting the particles contained in the first subgrid at each sampling time can facilitate the subsequent determination of the intensity of the AOD of the first subgrid at each sampling time.

[0207] In S470, the intensity of the equivalent AOD corresponding to each particle can be determined based on the number of particles initially contained in the first sub-grid and the intensity of the AOD corresponding to the first sub-grid. The intensity of the AOD corresponding to the first sub-grid can be determined in combination with the first intensity of the AOD of the preset area when the space where the preset area is located is gridded.

[0208] For example, assuming that the first subgrid initially contains N1 particles, the intensity of the AOD initially corresponding to the first subgrid is Then the intensity of the equivalent AOD of each particle in the first sub-grid is

[0209] According to the particles of the first sub-grid at each sampling moment and the intensity of the equivalent AOD corresponding to each particle, the second intensity of the AOD of the first sub-grid at each sampling moment can be determined.

[0210] Exemplarily, for each sampling moment, the intensities of the equivalent AOD of each particle contained in the first sub-grid can be accumulated to obtain a cumulative sum, and the cumulative sum can be determined as the second intensity of the AOD of the first sub-grid at the sampling moment. In a similar manner, the second intensity of the AOD of the first sub-grid at each sampling moment can be obtained.

[0211] After the second intensity of the AOD of the first subgrid at each sampling moment is determined, the target intensity of the AOD of the first subgrid in the first prediction time period can be determined based on the second intensity of the AOD of the first subgrid at each sampling moment.

[0212] For example, Among them, C t+Δt is the target intensity of AOD for the first subgrid in the first prediction time period, is the second intensity of AOD of the first subgrid at the i-th sampling time, N is the number of sampling times, Δt s is the sampling frequency.

[0213] The embodiment of the present application utilizes the second processing module, combined with the coverage of the first sub-grid within the first prediction time period, to determine the particles contained in the first sub-grid at each sampling moment, and based on the intensity of the equivalent AOD of each particle, the second intensity of the AOD of the first sub-grid at each sampling moment can be determined, and then based on the second intensity of the AOD of the first sub-grid at each sampling moment, the target intensity of the AOD of the first sub-grid within the first prediction time period can be determined, thereby realizing multi-point concurrent short-term sand and dust deduction operations, and improving the operation efficiency and the accuracy of the prediction results.

[0214] The embodiment of the present application utilizes the first intensity of AOD in each first subgrid and the target meteorological forecast data of the first subgrid in the first prediction time period, combined with the first prediction model, to equate the first subgrid to a certain number of particles, and combined with the mobility characteristics of the particles, predict the position vector of each particle in the first prediction time period, and obtain the AOD distribution of the first subgrid in the first prediction time period, that is, the target coverage range of AOD of the first subgrid in the first prediction time period. On this basis, the target intensity of AOD of the first subgrid in the first prediction time period is determined by further combining the particles of the first subgrid at each sampling moment and the intensity of the equivalent AOD corresponding to each particle, thereby realizing multi-point concurrent short-term sandstorm deduction operations and improving the prediction efficiency and accuracy of the prediction results.

[0215] The embodiment of the present application utilizes the target intensity and target coverage of the AOD of the first sub-grid in the first prediction time period to characterize the intensity and coverage of the dust, thereby realizing the quantitative processing of the dust. In order to more accurately predict the power loss ratio of the first observation point in the first prediction time period, the power loss ratio of the first observation point in the first prediction time period can be predicted based on the target intensity of the AOD of the first sub-grid in the first prediction time period.

[0216] For example, Figure 5 As shown, the method for predicting dust characteristic parameters may include the following steps:

[0217] S510: Obtain a first intensity of aerosol optical thickness AOD in a preset area at a first moment.

[0218] S520: Grid the space where the preset area is located to obtain a first grid.

[0219] S530: For a first subgrid in a first grid, obtain target meteorological forecast data of the first subgrid within a first forecast time period.

[0220] S540: predict the target intensity and target coverage of the AOD in each first subgrid within the first prediction time period according to the first intensity of the AOD in each first subgrid and the target meteorological forecast data.

[0221] S550: Determine a target first sub-grid corresponding to the first observation point according to the spatial position information of the first observation point in the first sub-grid, and determine the target intensity of the AOD in the target first sub-grid as the AOD intensity of the first observation point.

[0222] S560: Determine a target power reduction ratio of the first observation point in the first prediction time period according to the AOD intensity of the first observation point and the correlation between the AOD intensity and the power reduction ratio.

[0223] S570: Determine characteristic parameters of dust in a preset area in the first prediction time period according to the target intensity and target coverage of the AOD of each first subgrid in the first prediction time period.

[0224] Among them, the processes of S510-S540 and S570 are the same as the processes of S110-S150 mentioned above. For details, please refer to the description of S110-S150 mentioned above. For the sake of brevity, they will not be repeated here.

[0225] The other steps above are described in detail below:

[0226] In S550, the target first subgrid corresponding to the first observation point may include one or more. For example, when the first observation point is located inside the first subgrid, the first subgrid may be determined as the target first subgrid of the first observation point.

[0227] When the first observation point is located at the edge of the first sub-grid, the first sub-grid and a first sub-grid adjacent to the first sub-grid may be determined as the target first sub-grid of the first observation point.

[0228] Exemplarily, when there is one target first sub-grid, the target intensity of the AOD in the target first sub-grid may be determined as the AOD intensity of the first observation point.

[0229] Exemplarily, when there are multiple target first sub-grids, the average of the target intensities of the AOD in each target first sub-grid may be determined as the AOD intensity of the first observation point.

[0230] In S560, the correlation between the AOD intensity and the power loss ratio is used to characterize the corresponding relationship between the AOD intensity and the power loss ratio of the first observation point. Exemplarily, the correlation between the AOD intensity and the power loss ratio can be a functional relationship, which takes the AOD intensity as the independent variable and the power loss ratio as the dependent variable.

[0231] The correlation between AOD intensity and power loss ratio can be determined in advance by the historical power loss ratio of each first observation point at each preset historical moment and the AOD intensity of each first subgrid at each preset historical moment. The specific determination process can be found in the following embodiments.

[0232] For example, the correlation between AOD intensity and power loss ratio can be expressed as:

[0233]

[0234] Among them, p i is the power loss ratio of the first observation point i, C iis the AOD intensity of the i-th first observation point.

[0235] After determining the AOD intensity at a first observation point, the AOD intensity can be substituted into the above formula to obtain the power loss ratio of the first observation point caused by sandstorm weather.

[0236] In actual application, S550 and S570 can be executed simultaneously.

[0237] In dusty weather, the embodiment of the present application can predict in advance the photovoltaic power loss generated by the first observation point within the first prediction time period based on the target intensity of AOD in each first sub-grid, thereby guiding the relevant departments of the photovoltaic station to make decisions in advance and ensure the safe and stable operation of the power system.

[0238] In some embodiments, before S110, the correlation between the AOD intensity and the power loss ratio may be determined in the following manner:

[0239] Obtaining the historical power loss ratio of each first observation point in the preset area at each preset historical moment and the third intensity of the AOD of each first subgrid at each preset historical moment;

[0240] Determining, from the third intensities, a fourth intensity corresponding to each first observation point according to the spatial position information of each first observation point;

[0241] Function fitting is performed on the fourth intensity of each first observation point at each preset historical moment and the historical power loss ratio to obtain a correlation between the AOD intensity and the power loss ratio.

[0242] Exemplarily, the historical power loss ratio of each first observation point in the preset area at each preset historical moment and the intensity of AOD of each first subgrid at each preset historical moment, ie, the third intensity, can be obtained from the database.

[0243] According to the spatial position information of each first observation point, the fourth intensity corresponding to each first observation point can be determined from the intensity of AOD of each first sub-grid at each preset historical moment, that is, the single-point AOD intensity of each first observation point. The determination process of the fourth intensity can refer to the above-mentioned process of determining the AOD intensity of the first observation point based on the target intensity of AOD in the target first sub-grid.

[0244] After the fourth intensity of each first observation point is determined, function fitting can be performed on the fourth intensity of each first observation point at each preset historical moment and the corresponding historical power loss ratio to obtain the correlation between the AOD intensity and the power loss ratio.

[0245] Exemplarily, the fourth intensity of each first observation point at each preset historical moment and the corresponding historical power loss ratio may be fitted based on the sigmoid function.

[0246] The results obtained by fitting based on the sigmoid function can be found in Figure 6 , compared to Figure 7 The linear fitting based on the sigmoid function has a better fitting effect and can more accurately reflect the correlation between the AOD intensity and the power loss ratio, so as to more accurately predict the power loss of the first observation point in the next hour.

[0247] Among them, the fitting effects of different methods can be based on the determination coefficient R 2 It is determined that the value of the determination coefficient is between 0 and 1. The larger the value, the better the fitting effect. Through simulation, it is found that the determination coefficient of the fitting based on the sigmoid function is 0.4733, and the determination coefficient of the linear fitting is 0.3101. It can be seen that the fitting based on the sigmoid function has a better effect. Of course, the fitting method based on the sigmoid function can also be compared with other fitting methods.

[0248] For a first observation point, the relationship between the power loss ratio predicted by the above scheme and the actual power loss ratio can be seen in Figure 8 ,Depend on Figure 8 It can be seen that the above scheme can predict the change of power loss ratio well, especially during the period of 13:45-14:00, the predicted power loss ratio curve is highly consistent with the actual power loss ratio curve.

[0249] The embodiment of the present application can fit the sigmoid function based on the historical power loss ratio of each first observation point in the preset area at each preset historical moment and the AOD intensity of each first sub-grid at each preset historical moment, and obtain the correlation between the AOD intensity and the power loss ratio, so as to more accurately predict the power loss ratio of each first observation point in the first prediction time period, guide the relevant departments of the photovoltaic station to make decisions in advance, and ensure the safe and stable operation of the power system.

[0250] Based on the same inventive concept, the embodiment of the present application also provides a device for predicting dust characteristic parameters. Fig. 9 The device for predicting dust characteristic parameters provided in the embodiment of the present application is described in detail.

[0251] Fig. 9 A structural diagram of a device for predicting dust characteristic parameters provided in an embodiment of the present application.

[0252] like Fig. 9 As shown, the dust characteristic parameter prediction device may include: an acquisition module 901, a processing module 902, a prediction module 903 and a determination module 904;

[0253] An acquisition module 901 is used to acquire a first intensity of aerosol optical thickness AOD in a preset area at a first moment;

[0254] A processing module 902 is used to perform grid processing on the space where the preset area is located to obtain a first grid, where the first grid includes at least one sub-grid;

[0255] The acquisition module 901 is further used to acquire, for a first subgrid in the first grid, target meteorological forecast data of the first subgrid within a first forecast time period, the first subgrid being any subgrid in the first grid, and the first forecast time period being a time period after the first moment;

[0256] A prediction module 903 is used to predict the target intensity and target coverage of the AOD of each first subgrid in the first prediction time period according to the first intensity of the AOD in each first subgrid and the target meteorological prediction data;

[0257] The determination module 904 is used to determine characteristic parameters of dust in a preset area within the first prediction time period according to the target intensity and target coverage of the AOD of each first subgrid within the first prediction time period.

[0258] The embodiment of the present application obtains the AOD intensity of each first sub-grid by gridding the AOD intensity of the preset area at the first moment, and predicts the target intensity and target coverage of the AOD of each first sub-grid in the first prediction time period based on the target meteorological forecast data of each sub-grid in the first prediction time period. Then, based on the target intensity and target coverage of the AOD of each first sub-grid in the first prediction time period, the dust intensity and dust coverage of the preset area in the first prediction time period are determined, without setting up a particle collection device. In this way, the problem of inaccurate prediction of dust characteristic parameters due to uneven distribution or small number of particle collection devices can be avoided, thereby improving the accuracy of the prediction results of dust characteristic parameters.

[0259] In some embodiments, the acquisition module 901 includes:

[0260] An acquisition unit, used to acquire meteorological observation data of a first observation point in a first subgrid at a first moment, and initial meteorological forecast data of the first subgrid in a first forecast time period;

[0261] The correction unit is used to correct the initial meteorological forecast data according to the meteorological observation data to obtain the target meteorological forecast data of the first subgrid within the first forecast time period.

[0262] In some embodiments, the determination module 904 is further configured to determine a spatial distance between the first subgrid and the first observation point according to the first spatial position information of the first subgrid and the second spatial position information of the first observation point;

[0263] The determination module 904 is further used to determine the time distance between the first subgrid and the first observation point in the first prediction time period according to the first wind speed at each preset time point in the first prediction time period;

[0264] The determination module 904 is further used to determine a first weight of the first observation point at the first moment according to the spatial distance and the temporal distance in combination with a weight calculation formula;

[0265] Correction unit, specifically used for:

[0266] The initial meteorological forecast data is corrected according to the first weight and the meteorological observation data to obtain the target meteorological forecast data of the first subgrid within the first forecast time period.

[0267] In some embodiments, the determination module N04 is specifically configured to:

[0268] The first weight of the first observation point at the first moment is determined by:

[0269]

[0270] Among them, w(t) i is the first weight of the i-th first observation point in the first subgrid at the first moment, t is the first moment, t+Δt is the first preset time period, DIS1i is the spatial distance between the first subgrid and the i-th first observation point, and DIS2i is the time distance between the first subgrid and the i-th first observation point in the first prediction time period;

[0271] DIS2i=v1+v2+…+v m

[0272] v1, v2, ..., v m is the first wind speed at each preset time point in the first prediction time period, and m is the number of preset time points.

[0273] In some embodiments, the correction unit is specifically configured to:

[0274] The initial weather forecast data is corrected by:

[0275] Y(t1) rev =Y(t1) mod +w(t)1·[OBS(t)1-Y(t1) mod ]+w(t)2

[0276] ·[OBS(t)2-Y(t1) mod ]+…+w(t) i ·[OBS(t) i -Y(t1) mod ]

[0277] Wherein, t1 is the first preset time period, t1=t+Δt, t is the first moment, Y(t1) mod is the initial meteorological forecast data of the first subgrid in the first forecast period, OBS(t) i is the meteorological observation data of the first observation point i in the first subgrid at the first moment, w(t) i is the first weight of the first observation point i in the first subgrid at the first moment, Y(t1) rev It is the target meteorological forecast data of the first subgrid in the first forecast time period.

[0278] In some embodiments, the prediction module 903 is specifically configured to:

[0279] The first prediction model is used to process the first intensity of the AOD in each first subgrid and the target meteorological prediction data to obtain the target intensity and target coverage of the AOD in each first subgrid in the first prediction time period.

[0280] In some embodiments, the target weather forecast data includes a predicted wind speed and a predicted wind direction, and the first subgrid includes a preset number of particles, each particle moving with the predicted wind speed and the predicted wind direction;

[0281] The prediction module 903 is specifically used for:

[0282] The first intensity of the AOD in each first subgrid and the target meteorological forecast data are processed by using the first forecast model to obtain the target coverage of the AOD in each first subgrid in the first forecast time period, including:

[0283] Inputting the first intensity of the AOD in each first subgrid and the target meteorological forecast data into the first forecast model, and using the first processing module of the first forecast model, in combination with the predicted wind speed and the predicted wind direction, determining the position vector of each particle in each first subgrid in the first forecast time period;

[0284] The determination module 904 is further configured to determine the target coverage range of the AOD of each first subgrid within the first prediction time period according to the position vector of each particle.

[0285] In some embodiments, the prediction module 903 is specifically configured to:

[0286] For each first subgrid, using the second processing module of the first prediction model, combined with the target coverage range of the AOD of the first subgrid in the first prediction time period, determine the particles contained in the first subgrid at each sampling time, where each sampling time is a time in the first prediction time period;

[0287] Determine a second intensity of the AOD of the first subgrid at each sampling moment according to the particles of the first subgrid at each sampling moment and the intensity of the equivalent AOD corresponding to each particle;

[0288] The average value of the second intensity of the AOD at each sampling moment is determined as the target intensity of the AOD of the first subgrid in the first prediction time period.

[0289] In some embodiments, the characteristic parameters of the dust include dust intensity and dust coverage;

[0290] The determination module 904 is specifically configured to:

[0291] Determine the target intensity of the AOD of each first subgrid in the first prediction time period as the dust intensity of each position in the preset area in the first prediction time period, and each position in the preset area corresponds to the position of each first subgrid;

[0292] The total target coverage range of the AOD of each first subgrid in the first prediction time period is determined as the dust coverage range of the preset area in the first prediction time period.

[0293] In some embodiments, the determination module 904 is further configured to determine the target first subgrid corresponding to the first observation point according to the spatial position information of the first observation point in the first subgrid, and determine the target intensity of the AOD in the target first subgrid as the AOD intensity of the first observation point after the prediction module 903 predicts the target intensity and target coverage of the AOD in each first subgrid in the first prediction time period according to the first intensity of the AOD in each first subgrid and the target meteorological prediction data;

[0294] The determination module 904 is further configured to determine a target power reduction ratio of the first observation point within the first prediction time period according to the AOD intensity of the first observation point and in combination with the correlation between the AOD intensity and the power reduction ratio.

[0295] In some embodiments, before obtaining the first intensity of the aerosol optical thickness AOD of the preset area at the first moment, the obtaining module 901 obtains the historical power loss ratio of each first observation point in the preset area at each preset historical moment and the third intensity of the AOD of each first subgrid at each preset historical moment;

[0296] The determination module 904 is further configured to determine, according to the spatial position information of each first observation point, a fourth intensity corresponding to each first observation point from the third intensities;

[0297] The device for predicting dust characteristic parameters may also include a fitting module for performing function fitting on the fourth intensity of each first observation point at each preset historical moment and the historical power loss ratio to obtain a correlation between the AOD intensity and the power loss ratio.

[0298] The prediction device for dust characteristic parameters provided in the embodiment of the present application can achieve Figure 1-8 To avoid repetition, the various processes in the embodiment of the method for predicting dust characteristic parameters are not described again here.

[0299] Based on the same inventive concept, the embodiment of the present application also provides an electronic device, which may be, for example, a tablet computer, a notebook computer, a handheld computer, etc. Fig.10 The electronic device provided in the embodiments of the present application is described in detail.

[0300] like Fig.10 As shown, the electronic device may include a processor 101 and a memory 102 for storing computer program instructions.

[0301] The processor 101 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0302] The memory 102 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 102 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In one example, the memory 102 may include a removable or non-removable (or fixed) medium, or the memory 102 is a non-volatile solid-state memory. In one example, the memory 102 may be a read-only memory (ROM). In one example, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM) or a flash memory or a combination of two or more of these.

[0303] The processor 101 reads and executes the computer program instructions stored in the memory 102 to implement Figure 1-Figure 8 The method in the embodiment shown in the figure is achieved Figure 1-Figure 8 The corresponding technical effects achieved by executing the method in the illustrated embodiment are not described in detail here for the sake of brevity.

[0304] In one example, the electronic device may further include a communication interface 103 and a bus 104. Fig.10 As shown, the processor 101, the memory 102, and the communication interface 103 are connected via a bus 104 and communicate with each other.

[0305] The communication interface 103 is mainly used to implement communication between various modules, devices and / or equipment in the embodiments of the present application.

[0306] Bus 104 includes hardware, software or both, and each component of electronic device is coupled to each other.For example, but not limitation, bus 104 may include accelerated graphics port (Accelerated Graphics Port, AGP) or other graphics bus, enhanced industry standard architecture (Extended Industry Standard Architecture, EISA) bus, front side bus (Front Side Bus, FSB), Hyper Transport (Hyper Transport, HT) interconnection, industry standard architecture (Industry Standard Architecture, ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 104 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0307] After obtaining the first intensity of the aerosol optical thickness AOD in the preset area at the first moment, the electronic device can execute the prediction method of the dust characteristic parameters in the embodiment of the present application, thereby realizing the combination of Figure 1-8 The prediction method of dust characteristic parameters described in Fig. 9 Describe the prediction device of dust characteristic parameters.

[0308] In addition, in combination with the dust characteristic parameter prediction method in the above embodiment, the present application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the dust characteristic parameter prediction methods in the above embodiment is implemented.

[0309] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0310] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), appropriate firmware, plug-in, function card, etc. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or communication link by a data signal carried in a carrier. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (Radio Frequency, RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0311] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0312] The above reference is according to the method of the present application embodiment, the flow chart of the device (system) and the computer program product and / or the block diagram of the present application embodiment. It should be understood that each square box in the flow chart and / or the block diagram and the combination of each square box in the flow chart and / or the block diagram can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the realization of the function / action specified in one or more square boxes of the flow chart and / or the block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each square box in the block diagram and / or the flow chart and the combination of the square boxes in the block diagram and / or the flow chart can also be realized by the dedicated hardware that performs the specified function or action, or can be realized by the combination of dedicated hardware and computer instructions.

[0313] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for predicting dust characteristic parameters, characterized in that: include: Obtaining a first intensity of aerosol optical thickness AOD in a preset area at a first moment; Performing grid processing on the space where the preset area is located to obtain a first grid, where the first grid includes at least one sub-grid; For a first subgrid in the first grid, obtaining target meteorological forecast data of the first subgrid within a first forecast time period, the first subgrid being any subgrid in the first grid, and the first forecast time period being a time period after the first moment; Predicting a target intensity and a target coverage range of the AOD in each of the first subgrids within the first prediction time period according to the first intensity of the AOD in each of the first subgrids and the target meteorological forecast data; The characteristic parameters of dust in the preset area during the first prediction time period are determined according to the target intensity and target coverage range of the AOD of each of the first subgrids during the first prediction time period.

2. The method according to claim 1, characterized in that Acquiring target meteorological forecast data of the first subgrid within a first forecast time period includes: Acquire meteorological observation data of a first observation point in the first subgrid at the first moment, and initial meteorological forecast data of the first subgrid in the first forecast time period; The initial meteorological forecast data is corrected according to the meteorological observation data to obtain target meteorological forecast data for the first subgrid within the first forecast time period.

3. The method according to claim 2, characterized in that The step of correcting the initial meteorological forecast data according to the meteorological observation data to obtain target meteorological forecast data of the first subgrid within the first forecast time period includes: Determining a spatial distance between the first subgrid and the first observation point according to the first spatial position information of the first subgrid and the second spatial position information of the first observation point; determining a time distance between the first subgrid and the first observation point within the first prediction time period according to the first wind speed at each preset time point within the first prediction time period; Determine a first weight of the first observation point at the first moment according to the spatial distance and the temporal distance in combination with a weight calculation formula; The initial meteorological forecast data is corrected according to the first weight and the meteorological observation data to obtain target meteorological forecast data for the first subgrid within the first forecast time period.

4. The method according to claim 3, characterized in that The determining, according to the spatial distance and the temporal distance and in combination with a weight calculation formula, a first weight of the first observation point at the first moment includes: The first weight of the first observation point at the first moment is determined by: Among them, w(t) i is the first weight of the i-th first observation point in the first subgrid at the first moment, t is the first moment, t+Δt is the first preset time period, DIS1i is the spatial distance between the first subgrid and the i-th first observation point, and DIS2i is the time distance between the first subgrid and the i-th first observation point in the first prediction time period; <h2 style=";text-align:left;direction:ltr">DIS2i = v1 + v2 +… + v<h2 style=";text-align:left;direction:ltr"> m v1, v2, ..., v m is the first wind speed at each preset time point in the first prediction time period, and m is the number of preset time points.

5. The method according to claim 3, characterized in that: The step of correcting the initial meteorological forecast data according to the first weight and the meteorological observation data to obtain target meteorological forecast data of the first subgrid within the first forecast time period includes: The initial weather forecast data is corrected by: Y(t1) rev =Y(t1) mod +w(t)1·[OBS(t)1-Y(t1) mod ]+w(t)2 ·[OBS(t)2-Y(t1) mod ]+…+w(t) i ·[OBS(t) i -Y(t1) mod ] Wherein, t1 is the first preset time period, t1=t+Δt, t is the first moment, Y(t1) mod is the initial meteorological forecast data of the first subgrid in the first forecast time period, OBS(t) i is the meteorological observation data of the first observation point i in the first subgrid at the first moment, w(t) i is the first weight of the first observation point i in the first subgrid at the first moment, Y(t1) rev It is the target meteorological forecast data of the first subgrid in the first forecast time period.

6. The method according to claim 1, characterized in that The predicting, according to the first intensity of the AOD in each of the first subgrids and the target meteorological forecast data, the target intensity and target coverage of the AOD in each of the first subgrids in the first forecast time period includes: The first intensity of the AOD in each of the first subgrids and the target meteorological forecast data are processed by using the first forecast model to obtain the target intensity and target coverage of the AOD in each of the first subgrids in the first forecast time period.

7. The method according to claim 6, characterized in that The target meteorological forecast data includes a predicted wind speed and a predicted wind direction, the first subgrid includes a preset number of particles, and each of the particles moves with the predicted wind speed and the predicted wind direction; Using the first prediction model, the first intensity of the AOD in each of the first subgrids and the target meteorological forecast data are processed to obtain the target coverage of the AOD in each of the first subgrids in the first prediction time period, including: Inputting the first intensity of the AOD in each of the first subgrids and the target meteorological forecast data into the first forecast model, and determining the position vector of each particle in each of the first subgrids in the first forecast time period by combining the forecast wind speed and the forecast wind direction using the first processing module of the first forecast model; The target coverage range of the AOD of each of the first sub-grids within the first prediction time period is determined according to the position vector of each of the particles.

8. The method according to claim 7, characterized in that Using a first prediction model, processing the first intensity of the AOD in each of the first subgrids and the target meteorological forecast data to obtain the target intensity of the AOD in each of the first subgrids in the first prediction time period includes: For each first subgrid, using the second processing module of the first prediction model, combined with the target coverage range of the AOD of the first subgrid in the first prediction time period, determine the particles contained in the first subgrid at each sampling time, where each sampling time is a time in the first prediction time period; Determine a second intensity of the AOD of the first subgrid at each sampling moment according to the particles of the first subgrid at each sampling moment and the intensity of the equivalent AOD corresponding to each particle; The average value of the second intensity of the AOD at each of the sampling moments is determined as the target intensity of the AOD of the first subgrid in the first prediction time period.

9. The method according to claim 1, characterized in that: The characteristic parameters of the dust include dust intensity and dust coverage; The determining, according to the target intensity and target coverage of the AOD of each of the first subgrids in the first prediction time period, characteristic parameters of dust in the preset area in the first prediction time period includes: Determine the target intensity of the AOD of each of the first subgrids in the first prediction time period as the dust intensity of each position of the preset area in the first prediction time period, and each position of the preset area corresponds to the position of each of the first subgrids; The total target coverage range of the AOD of each of the first sub-grids in the first prediction time period is determined as the dust coverage range of the preset area in the first prediction time period.

10. The method according to any one of claims 1 to 9, characterized in that: After predicting the target intensity and target coverage of the AOD in each of the first subgrids within the first prediction time period according to the first intensity of the AOD in each of the first subgrids and the target meteorological forecast data, the method further includes: Determine a target first subgrid corresponding to the first observation point according to the spatial position information of the first observation point in the first subgrid, and determine the target intensity of the AOD in the target first subgrid as the AOD intensity of the first observation point; According to the AOD intensity of the first observation point and in combination with the correlation between the AOD intensity and the power reduction ratio, a target power reduction ratio of the first observation point in the first prediction time period is determined.

11. The method according to claim 10, characterized in that Before obtaining the first intensity of the aerosol optical thickness AOD of the preset area at the first moment, the method further includes: Obtaining a historical power loss ratio of each first observation point in the preset area at each preset historical moment and a third intensity of the AOD of each first subgrid at each preset historical moment; determining, according to the spatial position information of each of the first observation points, a fourth intensity corresponding to each of the first observation points from the third intensities; Function fitting is performed on the fourth intensity of each of the first observation points at each of the preset historical moments and the historical power loss ratio to obtain a correlation between the AOD intensity and the power loss ratio.

12. A device for predicting dust characteristic parameters, characterized in that: include: Acquisition module, processing module, prediction module and determination module; The acquisition module is used to acquire a first intensity of aerosol optical thickness AOD in a preset area at a first moment; The processing module is used to perform grid processing on the space where the preset area is located to obtain a first grid, where the first grid includes at least one sub-grid; The acquisition module is further used to acquire, for a first subgrid in the first grid, target meteorological forecast data of the first subgrid within a first forecast time period, the first subgrid being any subgrid in the first grid, and the first forecast time period being a time period after the first moment; The prediction module is used to predict the target intensity and target coverage of the AOD of each of the first subgrids within the first prediction time period according to the first intensity of the AOD in each of the first subgrids and the target meteorological prediction data; The determination module is used to determine the characteristic parameters of dust in the preset area within the first prediction time period according to the target intensity and target coverage range of the AOD of each of the first sub-grids within the first prediction time period.

13. An electronic device, characterized in that: include: processor; a memory for storing computer program instructions; When the computer program instructions are executed by the processor, the method according to any one of claims 1 to 11 is implemented.

14. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images