Comprehensive meteorological calculation method and device considering complex terrain in regional power load prediction, equipment and storage medium

Abstract

The invention discloses a comprehensive meteorological calculation method, device and equipment considering a complex terrain in regional power load prediction and a storage medium, and relates to the technical field of computers, and the method comprises the steps: determining an altitude average value, an altitude standard deviation value and terrain gradient information based on the elevation grid data of a target region; determining a gradient mean value and a topographic relief mean value based on the topographic gradient information; determining a feature matrix based on the altitude average value, the altitude standard deviation value, the gradient average value and the topographic relief average value, and processing the feature matrix by using a preset clustering algorithm and a preset evaluation index to obtain a clustering result; and determining regional meteorological information and regional weight based on the population density and power consumption of each region in the target region and each terrain in the clustering result, determining target meteorological information based on the regional weight and the regional meteorological information, and performing power consumption load prediction on the target meteorological information by using a preset power consumption load prediction model, and obtaining an electrical load prediction result. Therefore, the accuracy of predicting the electrical load can be improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a comprehensive meteorological calculation method, device, equipment and storage medium for regional power load forecasting taking complex terrain into consideration. Background Art

[0002] At present, the short-term load forecast results of residents play a key role in the operation and scheduling of the power grid and production planning. Especially during the peak summer period, accurate load forecasting is of great significance for ensuring the stability and safety of people's electricity consumption.

[0003] Furthermore, meteorological information is a key factor influencing summer residential load. Currently, existing short-term residential load forecasts only consider meteorological information from a single location. Therefore, when the area to be forecasted is large and the terrain is significantly different, using only meteorological data from a single location for short-term residential load forecasting can result in significant errors.

[0004] From the above, it can be seen that how to improve the accuracy of electricity load forecasting in the process of electricity load forecasting is a problem that needs to be solved urgently. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a comprehensive meteorological calculation method, device, equipment, and storage medium that considers complex terrain in regional power load forecasting, which can improve the accuracy of power load forecasting during the power load forecasting process. The specific solution is as follows:

[0006] In a first aspect, the present application provides a comprehensive meteorological calculation method for regional power load forecasting taking complex terrain into account, including:

[0007] Determining the average altitude, the standard deviation of altitude, and terrain gradient information corresponding to the target area based on the elevation grid data corresponding to the target area, and then determining the mean slope and the mean terrain relief based on the terrain gradient information;

[0008] Determining a feature matrix based on the average altitude value, the standard deviation of altitude value, the mean slope value, and the mean terrain undulation value, and processing the feature matrix using a preset clustering algorithm and a preset evaluation index to obtain a clustering result including a plurality of terrains;

[0009] Based on the population density, power consumption corresponding to each area in the target area and the terrain in the clustering result, the regional meteorological information and regional weight corresponding to the area are determined, and the target meteorological information is determined based on the regional weight and the regional meteorological information. Then, the target meteorological information is used to predict the power load using a preset power load prediction model to obtain the power load prediction result corresponding to the target area.

[0010] Optionally, determining the average altitude value, the standard deviation of altitude, and the terrain gradient information corresponding to the target area based on the elevation grid data corresponding to the target area includes:

[0011] Determining elevation grid data corresponding to a target area using a preset digital elevation model; the elevation grid data includes elevation values ​​of each grid cell corresponding to the target area;

[0012] determining an average altitude value corresponding to the target area based on the elevation grid data and the number of grid cells in the target area, and determining an altitude standard deviation value corresponding to the target area based on the average altitude value, the elevation grid data, and the number of grid cells in the target area;

[0013] A preset gradient algorithm is used to determine a first gradient along the x-axis and a second gradient along the y-axis corresponding to the target area based on each elevation value.

[0014] Optionally, determining the slope mean and the terrain relief mean based on the first gradient and the second gradient includes:

[0015] Determining a slope to be processed based on the first gradient and the second gradient, and performing slope mean calculation processing on the slope to be processed using a preset inverse tangent function to obtain a slope mean; the slope mean is a value representing the inclination of the terrain surface;

[0016] The average terrain undulation is determined based on a first absolute value corresponding to the first gradient and a second absolute value corresponding to the second gradient; wherein the average terrain undulation is a value for measuring terrain complexity, and the numerical value of the average terrain undulation is positively correlated with the magnitude of regional undulation.

[0017] Optionally, a feature matrix is ​​determined based on the average altitude value, the standard deviation of altitude value, the mean slope value, and the mean terrain undulation value, and the feature matrix is ​​processed using a preset clustering algorithm and a preset evaluation index to obtain a clustering result including several terrains, including:

[0018] Determining a characteristic matrix corresponding to the target area based on the average altitude values, the standard deviation altitude values, the average slope values, and the average terrain undulation values; the characteristic matrix includes the average altitude values, the standard deviation altitude values, the average slope values, and the average terrain undulation values ​​corresponding to each area in the target area;

[0019] The feature matrix is ​​processed using a K-Means clustering algorithm to obtain a current cluster corresponding to each of the regions, and the current cluster is processed using a preset distance square sum determination formula to obtain a corresponding distance square sum, and then it is determined whether the distance square sum meets a preset condition; the center point of the current cluster is the feature mean corresponding to each of the regions in the current cluster;

[0020] If the sum of squared distances meets a preset condition, a clustering result is determined based on each current cluster; if the sum of squared distances does not meet the preset condition, the step of processing the feature matrix using a K-Means clustering algorithm is triggered.

[0021] Optionally, determining regional meteorological information corresponding to each area in the target region based on the population density and electricity consumption corresponding to each area and each terrain in the clustering result includes:

[0022] Determining each district or county in each of the regions and a first population density and a first power consumption corresponding to each of the district or county, determining a population density ratio based on the first population density and a second population density corresponding to the region, and then determining a first power consumption ratio based on the first power consumption and the second power consumption corresponding to the region;

[0023] Determine a county weight corresponding to the county based on each of the terrains, the population density ratio, the first electricity consumption ratio, a first preset weight corresponding to the population density ratio, and a second preset weight corresponding to the first electricity consumption ratio in the clustering result;

[0024] The regional meteorological information is determined based on the weights of each of the counties and the county meteorological information corresponding to the county; the county meteorological information is measured meteorological information.

[0025] Optionally, determining target meteorological information based on the regional weight and the regional meteorological information includes:

[0026] Determining the regional power consumption corresponding to each area in the target area and the total power consumption corresponding to the target area, and determining a second power consumption ratio based on the proportion of the power consumption of each area in the total power consumption, and setting the second power consumption ratio as the regional weight;

[0027] Based on the weight of each area and the comprehensive meteorological information of the area, weighted processing is performed to obtain target meteorological information; the target meteorological information is based on integrated data information including temperature, humidity, wind speed, and precipitation probability.

[0028] Optionally, after performing power load forecasting on the target meteorological information using a preset power load forecasting model to obtain a power load forecast result corresponding to the target area, the method further includes:

[0029] Evaluate the power load forecast result using a preset determination coefficient algorithm, a preset root mean square error algorithm, a preset mean absolute error algorithm, and a preset mean absolute percentage error algorithm to obtain an evaluation result;

[0030] The preset adaptive optimization algorithm is used and the model parameters of the preset power load forecasting model are iteratively adjusted based on each of the evaluation results to obtain a new power load forecasting model; the model parameters include model learning rate, regularization coefficient, hidden layer structure parameters and feature weight distribution parameters.

[0031] In a second aspect, the present application provides a comprehensive meteorological calculation device that considers complex terrain in regional power load forecasting, comprising:

[0032] a raster data processing module for determining an average altitude value, an altitude standard deviation value, and terrain gradient information corresponding to the target area based on the elevation raster data corresponding to the target area, and then determining a mean slope value and a mean terrain relief value based on the terrain gradient information;

[0033] a clustering result determination module, configured to determine a feature matrix based on the average altitude value, the standard deviation of altitude value, the mean slope value, and the mean terrain relief value, and process the feature matrix using a preset clustering algorithm and a preset evaluation index to obtain a clustering result including a plurality of terrains;

[0034] A prediction result determination module is used to determine the regional meteorological information and regional weight corresponding to the area based on the population density, power consumption and each terrain in the clustering result corresponding to each area in the target area, and determine the target meteorological information based on the regional weight and the regional meteorological information, and then use a preset power load prediction model to predict the power load of the target meteorological information to obtain the power load prediction result corresponding to the target area.

[0035] In a third aspect, the present application provides an electronic device, comprising:

[0036] Memory, used to store computer programs;

[0037] A processor is used to execute the computer program to implement the aforementioned comprehensive meteorological calculation method considering complex terrain in regional power load forecasting.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the aforementioned comprehensive meteorological calculation method considering complex terrain in regional power load forecasting.

[0039] As can be seen from the above, before the present application performs power load forecasting, it is necessary to determine the average altitude, standard deviation of altitude, first gradient along the x-axis and second gradient along the y-axis corresponding to the target area based on the elevation raster data corresponding to the target area, and then determine the mean slope and the mean terrain undulation based on the first gradient and the second gradient; determine the characteristic matrix based on the average altitude, standard deviation of altitude, mean slope and mean terrain undulation, and use the preset clustering algorithm and preset evaluation indicators to process the characteristic matrix to obtain a clustering result including several terrains; determine the regional meteorological information and regional weight corresponding to the region based on the population density, power consumption and various terrains in the clustering results of each region in the target area, and determine the target meteorological information based on the regional weight and the regional meteorological information, and then use the preset power load forecasting model to forecast the target meteorological information to obtain the power load forecast result corresponding to the target area.

[0040] It can be seen that the present application first needs to determine the average altitude, standard deviation of altitude, first gradient along the x-axis and second gradient along the y-axis corresponding to the target area based on the elevation grid data corresponding to the target area, and then determine the slope mean and terrain undulation mean based on the first gradient and the second gradient; then, determine the characteristic matrix based on the average altitude, standard deviation of altitude, slope mean and terrain undulation mean, and use the preset clustering algorithm and the preset evaluation index to process the characteristic matrix to obtain a clustering result including several terrains; finally, determine the regional meteorological information and regional weight corresponding to the region based on the population density, power consumption and each terrain in the clustering result of each region in the target area, and determine the target meteorological information based on the regional weight and regional meteorological information, and then use the preset power load forecast model to forecast the power load of the target meteorological information to obtain the power load forecast result corresponding to the target area. In this way, the accuracy of the power load forecast is improved in the power load forecast process, thereby improving the safety of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0042] Figure 1 This is a flow chart of a comprehensive meteorological calculation method for considering complex terrain in regional power load forecasting disclosed in this application;

[0043] Figure 2 This is a schematic diagram of a clustering result obtained by performing K-Means clustering based on a specific feature matrix disclosed in this application;

[0044] Figure 3 This is a schematic diagram comparing a city-wide comprehensive meteorological temperature curve obtained based on city-wide meteorological information and a temperature curve of a single location, as disclosed in this application;

[0045] Figure 4 A schematic diagram of a load forecasting result obtained by using meteorological data of a specific single county and comprehensive meteorological data of the entire city as input features of a preset electricity load forecasting model disclosed in this application;

[0046] Figure 5 This is a schematic diagram of an evaluation result obtained by evaluating each prediction result using an evaluation indicator disclosed in this application;

[0047] Figure 6 This is a schematic diagram of the structure of a comprehensive meteorological calculation device for considering complex terrain in regional power load forecasting disclosed in this application;

[0048] Figure 7 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0050] At present, the results of short-term load forecasts for residents play a key role in the operation and scheduling of power grids and production planning, especially during the peak summer period. Accurate load forecasts are extremely important for ensuring the stability and safety of electricity consumption for people’s livelihood. In addition, meteorological information is a key factor affecting the load on residents in summer. At present, the meteorological information considered in the existing short-term load forecasts for residents only takes data from a single location. Therefore, when the area to be predicted is large and the terrain differences are significant, using only meteorological data from a single location for short-term load forecasts for residents will result in large errors. To this end, the present application provides a comprehensive meteorological calculation method that takes complex terrain into consideration in regional power load forecasting, which can improve the accuracy of power load forecasting during the power load forecasting process, thereby improving the safety of the production process.

[0051] See also Figure 1 As shown, an embodiment of the present invention discloses a method for predicting electric load, comprising:

[0052] Step S11: determining the average altitude, standard deviation of altitude, and terrain gradient information corresponding to the target area based on the elevation grid data corresponding to the target area, and then determining the mean slope and the mean terrain relief based on the terrain gradient information.

[0053] In this embodiment, before clustering the regions with complex terrain, the embodiment of the present application needs to consider the impact of elevation data altitude, slope, and terrain undulations on the weather, and thus, on the basis of determining the regional boundaries, use the K-means clustering algorithm to cluster the regions according to different terrain conditions.

[0054] It is worth mentioning that the embodiment of the present application requires the determination of the elevation data altitude, slope and terrain undulation corresponding to the target area. Specifically, determining the average altitude, standard deviation of altitude and terrain gradient information corresponding to the target area based on the elevation grid data corresponding to the target area may include: using a preset digital elevation model to determine the elevation grid data corresponding to the target area; the elevation grid data includes the elevation values ​​of each grid cell corresponding to the target area; determining the average altitude corresponding to the target area based on the elevation grid data and the number of grid cells in the target area, and determining the standard deviation of altitude corresponding to the target area based on the average altitude, the elevation grid data and the number of grid cells in the target area; using a preset gradient algorithm and based on each elevation value, determining a first gradient along the x-axis and a second gradient along the y-axis corresponding to the target area.

[0055] In a specific embodiment, the embodiment of the present application needs to determine the average altitude corresponding to the target area based on the elevation data grid value of the target area. and the standard deviation of altitude , and the average altitude The formula for determining the standard deviation of altitude The determination formulas are as follows:

[0056] ;

[0057] ;

[0058] in, The target area The elevation value of each grid cell, is the number of daily grid cells in the region.

[0059] In addition, since the slope is a measure of the inclination of the terrain surface, and the slope is usually expressed by the magnitude of the gradient, the embodiment of the present application needs to determine the gradient corresponding to the target area, and the gradient determination formula is as follows:

[0060] ;

[0061] in, and are the gradients of the elevation values ​​corresponding to the target area along the X-axis and Y-axis, respectively, and and The calculation formulas are as follows:

[0062] ;

[0063] ;

[0064] in, is the coordinate The elevation value at .

[0065] Furthermore, the slope It is a value determined based on the square root of the sum of the squares of the gradients along the X-axis and the Y-axis using the arctan function, and the determination formula is as follows:

[0066] ;

[0067] In addition, the terrain is undulating It is an indicator for measuring terrain complexity, and in one embodiment, it is measured by calculating the elevation change of the neighborhood. Areas with large undulations are usually mountainous areas or hills, and areas with small undulations are usually plains. Its calculation formula is shown in formula (7):

[0068] ;

[0069] Specifically, determining the slope mean and the terrain undulation mean based on the first gradient and the second gradient may include: determining the slope to be processed based on the first gradient and the second gradient, and performing slope mean calculation processing on the slope to be processed using a preset inverse tangent function to obtain the slope mean; the slope mean is a numerical value characterizing the inclination of the terrain surface; determining the terrain undulation mean based on a first absolute value corresponding to the first gradient and a second absolute value corresponding to the second gradient; wherein the terrain undulation mean is a numerical value for measuring the complexity of the terrain, and the numerical value of the terrain undulation mean is positively correlated with the magnitude of the regional undulation.

[0070] Step S12: determining a feature matrix based on the average altitude, the standard deviation of altitude, the mean slope, and the mean terrain undulation, and processing the feature matrix using a preset clustering algorithm and a preset evaluation index to obtain a clustering result including several terrains.

[0071] In this embodiment, after obtaining the mean altitude, standard deviation of altitude, mean slope, and mean terrain undulation, the embodiment of the present application needs to splice the mean altitude, standard deviation of altitude, mean slope, and mean terrain undulation into a feature matrix 𝑋 in order to perform cluster analysis operations using the feature matrix. Specifically, a feature matrix is ​​determined based on the average altitude, the standard deviation of altitude, the mean slope and the mean terrain undulation, and the feature matrix is ​​processed using a preset clustering algorithm and a preset evaluation index to obtain a clustering result including several terrains, which may include: determining a feature matrix corresponding to the target area based on the average altitude, the standard deviation of altitude, the mean slope and the mean terrain undulation; the feature matrix includes the average altitude, the standard deviation of altitude, the mean slope and the mean terrain undulation corresponding to each area in the target area; processing the feature matrix using the K-Means clustering algorithm to obtain the current cluster corresponding to each area, and processing the current cluster using a preset distance square determination formula to obtain the corresponding distance square sum, and then judging whether the distance square sum meets the preset conditions; the center point of the current cluster is the feature mean corresponding to each area in the current cluster; if the distance square sum meets the preset conditions, the clustering result is determined based on each current cluster, and if the distance square sum does not meet the preset conditions, the step of processing the feature matrix using the K-Means clustering algorithm is triggered.

[0072] In a specific implementation, if each region has 𝑘 features, the resulting feature matrix is ​​as follows:

[0073] ;

[0074] in, It is The average altitude of the region, It is The standard deviation of the altitude of the region, It is The slope value of the area, It is The terrain relief value of an area.

[0075] In a specific embodiment, the clustering result obtained by performing K-Means clustering based on the feature matrix is ​​as follows: Figure 2 As shown in the figure, the comparison between the comprehensive meteorological temperature curve of the whole city and the temperature curve of a single location based on the city's meteorological information is shown in the figure Figure 3 shown.

[0076] The K-Means clustering algorithm is used to assign multiple regions to different clusters, and the center point of each cluster is the feature mean of all regions in the cluster. After continuous iterative calculations, the K-Means algorithm will find the best cluster assignment, so that the sum of squared distances (WCSS) within the cluster is minimized. The calculation formula is as follows:

[0077] ;

[0078] in, It is The feature vector of the region, It is The center point of the cluster, is the indicator function, indicating the area Belongs to a cluster .

[0079] Step S13: Determine the regional meteorological information and regional weight corresponding to the region based on the population density, power consumption, and terrain in the clustering result corresponding to each region in the target region, and determine the target meteorological information based on the regional weight and the regional meteorological information. Then, use a preset power load prediction model to perform power load prediction on the target meteorological information to obtain a power load prediction result corresponding to the target region.

[0080] In this embodiment, after processing the feature matrix based on a preset clustering algorithm and a preset evaluation index to obtain a clustering result including several terrains, the embodiment of the present application needs to consider the population density and electricity consumption of each district and county, so as to calculate the regional comprehensive meteorological information based on the clustering according to different terrains, and further determine the comprehensive meteorological information of the entire city based on the regional comprehensive meteorological information. Specifically, determining the regional meteorological information corresponding to the region based on the population density, electricity consumption corresponding to each region in the target area and each terrain in the clustering result may include: determining each district and county in each region and the first population density and first electricity consumption corresponding to each district and county, and determining the population density ratio based on the first population density and the second population density corresponding to the region, and then determining the first electricity consumption ratio based on the first electricity consumption and the second electricity consumption corresponding to the region; determining the district and county weights corresponding to the district and county based on the terrain, population density ratio, first electricity consumption ratio, first preset weight corresponding to the population density ratio and second preset weight corresponding to the first electricity consumption ratio in the clustering result; determining the regional meteorological information based on the weights of each district and county and the district and county meteorological information corresponding to the district and county; the district and county meteorological information is measured meteorological information.

[0081] In a specific embodiment, the calculation process of regional comprehensive meteorological information is as follows: the weight of each district and county in the region is determined based on the population density and electricity consumption ratio in the region, that is, a weight is assigned to each factor using a preset weight assignment method, and a weighted average calculation is performed based on the obtained weight and factors, and the expression is as follows:

[0082] ;

[0083] in, is the number of districts and counties in the current region, and is the weight coefficient corresponding to each factor. The weights of population density and electricity consumption can be set equal, that is, .

[0084] It is worth mentioning that the comprehensive meteorological information of each region is the weighted average calculation result of the weights of all districts and counties in the region. The calculation formula for the comprehensive meteorological information of the region is as follows:

[0085] ;

[0086] After obtaining the regional comprehensive meteorological information, the embodiment of the present application needs to determine the city-wide comprehensive meteorological information based on the regional comprehensive meteorological information. Specifically, determining the target meteorological information based on the regional weight and the regional meteorological information may include:

[0087] Determining the regional electricity consumption corresponding to each area in the target area and the total electricity consumption corresponding to the target area, determining a second electricity consumption ratio based on the proportion of the electricity consumption of each area in the total electricity consumption, and setting the second electricity consumption ratio as the regional weight;

[0088] The target meteorological information is obtained by weighted processing based on the weight of each region and the regional comprehensive meteorological information; the target meteorological information is based on integrated data information including temperature, humidity, wind speed, and precipitation probability.

[0089] The weight of each area needs to be calculated based on the proportion of the corresponding power consumption in the power consumption of all areas, and the expression is as follows:

[0090] ;

[0091] Subsequently, the city's comprehensive meteorological information is determined based on the regional weights and the corresponding regional meteorological information, and the determination formula is as follows:

[0092] ;

[0093] in, is the number of regions with different terrains.

[0094] In a specific embodiment, the meteorological data of a single district or county and the comprehensive meteorological data of the entire city are selected as the input features of the preset power load forecasting model to perform load forecasting. The forecast result diagram is as follows: Figure 4 Then, the coefficient of determination, root mean square error, mean absolute error and mean absolute percentage error were used as evaluation indicators to evaluate the obtained prediction results respectively, and the obtained evaluation results are shown as follows: Figure 5As shown in the figure, the forecast results obtained by using the city's comprehensive meteorological information have a smaller overall error than the forecast results obtained by using the meteorological data of a single district or county.

[0095] Specifically, after using a preset electricity load forecasting model to forecast the target meteorological information for electricity load and obtaining the electricity load forecast result corresponding to the target area, it can also include: using a preset determination coefficient algorithm, a preset root mean square error algorithm, a preset mean absolute error algorithm and a preset mean absolute percentage error algorithm to evaluate the electricity load forecast result to obtain an evaluation result; using a preset adaptive optimization algorithm and iteratively adjusting the model parameters of the preset electricity load forecasting model based on each evaluation result to obtain a new electricity load forecasting model; the model parameters include model learning rate, regularization coefficient, hidden layer structure parameters and feature weight distribution parameters.

[0096] As can be seen from the above, the embodiment of the present application first needs to determine the average altitude, standard deviation of altitude, first gradient along the x-axis and second gradient along the y-axis corresponding to the target area based on the elevation raster data corresponding to the target area, and then determine the slope mean and terrain undulation mean based on the first gradient and the second gradient; then, determine the feature matrix based on the average altitude, standard deviation of altitude, slope mean and terrain undulation mean, and use the preset clustering algorithm and the preset evaluation index to process the feature matrix to obtain a clustering result including several terrains; finally, determine the regional meteorological information and regional weight corresponding to the region based on the population density, power consumption and each terrain in the clustering result of each region in the target area, and determine the target meteorological information based on the regional weight and the regional meteorological information, and then use the preset power load forecasting model to forecast the power load of the target meteorological information to obtain the power load forecast result corresponding to the target area. In this way, the accuracy of the power load forecast is improved in the power load forecasting process, thereby improving the safety of the production process.

[0097] Accordingly, see Figure 6 As shown, the present application also provides a comprehensive meteorological calculation device that considers complex terrain in regional power load forecasting, including:

[0098] The raster data processing module 11 is used to determine the average altitude, the standard deviation of altitude, and the terrain gradient information corresponding to the target area based on the elevation raster data corresponding to the target area, and then determine the mean slope and the mean terrain relief based on the terrain gradient information;

[0099] a clustering result determination module 12 for determining a characteristic matrix based on the average altitude, the standard deviation of altitude, the mean slope, and the mean terrain relief, and processing the characteristic matrix using a preset clustering algorithm and a preset evaluation index to obtain a clustering result including a plurality of terrains;

[0100] The prediction result determination module 13 is used to determine the regional meteorological information and regional weight corresponding to the area based on the population density, power consumption and each terrain in the clustering result corresponding to each area in the target area, and determine the target meteorological information based on the regional weight and the regional meteorological information, and then use a preset power load prediction model to predict the power load of the target meteorological information to obtain the power load prediction result corresponding to the target area.

[0101] It can be seen that the embodiment of the present application first needs to determine the average altitude, standard deviation of altitude, first gradient along the x-axis and second gradient along the y-axis corresponding to the target area based on the elevation raster data corresponding to the target area, and then determine the slope mean and terrain undulation mean based on the first gradient and the second gradient; then, determine the feature matrix based on the average altitude, standard deviation of altitude, slope mean and terrain undulation mean, and use the preset clustering algorithm and the preset evaluation index to process the feature matrix to obtain a clustering result including several terrains; finally, determine the regional meteorological information and regional weight corresponding to the region based on the population density, power consumption and each terrain in the clustering result of each region in the target area, and determine the target meteorological information based on the regional weight and regional meteorological information, and then use the preset power load forecast model to forecast the power load of the target meteorological information to obtain the power load forecast result corresponding to the target area. In this way, the accuracy of the power load forecast is improved in the power load forecast process, thereby improving the safety of the production process.

[0102] In some specific implementations, the raster data processing module 11 may specifically include:

[0103] An elevation value determination unit, configured to determine elevation grid data corresponding to a target area using a preset digital elevation model; the elevation grid data includes elevation values ​​of each grid cell corresponding to the target area;

[0104] an altitude standard deviation value determining unit, configured to determine an average altitude value corresponding to the target area based on the elevation grid data and the number of grid cells in the target area, and to determine an altitude standard deviation value corresponding to the target area based on the average altitude value, the elevation grid data, and the number of grid cells in the target area;

[0105] The gradient determining unit is configured to determine a first gradient along the x-axis and a second gradient along the y-axis corresponding to the target area based on each of the elevation values ​​using a preset gradient algorithm.

[0106] In some specific implementations, the raster data processing module 11 may specifically include:

[0107] a slope mean value determining unit, configured to determine a slope to be processed based on the first gradient and the second gradient, and perform slope mean calculation processing on the slope to be processed using a preset inverse tangent function to obtain a slope mean value; the slope mean value is a numerical value representing the inclination of the terrain surface;

[0108] A terrain undulation mean determination unit is used to determine a terrain undulation mean based on a first absolute value corresponding to the first gradient and a second absolute value corresponding to the second gradient; wherein the terrain undulation mean is a numerical value for measuring terrain complexity, and the numerical value of the terrain undulation mean is positively correlated with the magnitude of regional undulation.

[0109] In some specific implementations, the clustering result determination module 12 may specifically include:

[0110] a characteristic matrix determining unit, configured to determine a characteristic matrix corresponding to the target area based on the average altitude values, the standard deviation altitude values, the average slope values, and the average terrain relief values; the characteristic matrix including the average altitude values, the standard deviation altitude values, the average slope values, and the average terrain relief values ​​corresponding to each area in the target area;

[0111] a distance square sum determination unit, configured to process the feature matrix using a K-Means clustering algorithm to obtain a current cluster corresponding to each of the regions, and process the current cluster using a preset distance square sum determination formula to obtain a corresponding distance square sum, and then determine whether the distance square sum satisfies a preset condition; the center point of the current cluster being the feature mean corresponding to each of the regions in the current cluster;

[0112] A distance square sum judgment unit is used to determine a clustering result based on each current cluster if the distance square sum meets a preset condition, and trigger the step of processing the feature matrix using the K-Means clustering algorithm if the distance square sum does not meet the preset condition.

[0113] In some specific implementations, the prediction result determination module 13 may specifically include:

[0114] a first electricity consumption ratio determining unit, configured to determine each district or county in each of the regions and a first population density and a first electricity consumption corresponding to each of the districts or counties, determine a population density ratio based on the first population density and a second population density corresponding to the region, and then determine a first electricity consumption ratio based on the first electricity consumption and the second electricity consumption corresponding to the region;

[0115] a district / county weight determination unit, configured to determine a district / county weight corresponding to the district / county based on each of the terrains, the population density ratio, the first electricity consumption ratio, a first preset weight corresponding to the population density ratio, and a second preset weight corresponding to the first electricity consumption ratio in the clustering result;

[0116] The regional meteorological information determination unit is used to determine the regional meteorological information based on the county meteorological information corresponding to each county weight and the county; the county meteorological information is measured meteorological information.

[0117] In some specific implementations, the prediction result determination module 13 may specifically include:

[0118] a second power consumption ratio determining unit, configured to determine the regional power consumption corresponding to each area in the target area and the total power consumption corresponding to the target area, determine a second power consumption ratio based on the proportion of the power consumption of each area in the total power consumption, and set the second power consumption ratio as the regional weight;

[0119] The target meteorological information determination unit is used to perform weighted processing based on the weight of each area and the comprehensive meteorological information of the area to obtain target meteorological information; the target meteorological information is based on integrated data information including temperature, humidity, wind speed, and precipitation probability.

[0120] In some specific embodiments, the comprehensive meteorological calculation device for considering complex terrain in regional power load forecasting may further include:

[0121] An evaluation result determination unit is used to evaluate the power load forecast result using a preset determination coefficient algorithm, a preset root mean square error algorithm, a preset mean absolute error algorithm, and a preset mean absolute percentage error algorithm to obtain an evaluation result;

[0122] A model parameter adjustment unit is used to iteratively adjust the model parameters of the preset power load forecasting model using a preset adaptive optimization algorithm and based on each of the evaluation results to obtain a new power load forecasting model; the model parameters include a model learning rate, a regularization coefficient, hidden layer structure parameters, and feature weight allocation parameters.

[0123] Furthermore, the embodiment of the present application also discloses an electronic device, Figure 7This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be considered as any limitation on the scope of use of this application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps of the comprehensive meteorological calculation method for considering complex terrain in regional power load forecasting disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0124] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device. The communication protocol it follows is any communication protocol that can be applied to the technical solution of this application and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world. Its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0125] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or CD, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0126] The operating system 221 is used to manage and control the hardware devices on the electronic device 20 and the computer program 222, and can be Windows Server, NetWare, Unix, Linux, etc. In addition to including a computer program capable of implementing the comprehensive meteorological calculation method for considering complex terrain in regional power load forecasting performed by the electronic device 20 as disclosed in any of the aforementioned embodiments, the computer program 222 can further include computer programs capable of performing other specific tasks.

[0127] Furthermore, this application discloses a computer-readable storage medium for storing a computer program. When executed by a processor, the computer program implements the aforementioned comprehensive meteorological calculation method for regional power load forecasting that considers complex terrain. The specific steps of this method can be found in the corresponding content disclosed in the aforementioned embodiments and will not be further elaborated here.

[0128] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. Reference can be made to the descriptions of the identical or similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and the relevant parts can be referred to the descriptions of the methods.

[0129] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0130] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0131] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0132] The above is a detailed introduction to the technical solution provided by the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the ideas of the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A comprehensive meteorological calculation method considering complex terrain in regional power load forecasting, characterized by: include: Determining the average altitude, the standard deviation of altitude, and terrain gradient information corresponding to the target area based on the elevation grid data corresponding to the target area, and then determining the mean slope and the mean terrain relief based on the terrain gradient information; Determining a feature matrix based on the average altitude value, the standard deviation of altitude value, the mean slope value, and the mean terrain undulation value, and processing the feature matrix using a preset clustering algorithm and a preset evaluation index to obtain a clustering result including a plurality of terrains; Based on the population density, power consumption corresponding to each area in the target area and the terrain in the clustering result, the regional meteorological information and regional weight corresponding to the area are determined, and the target meteorological information is determined based on the regional weight and the regional meteorological information. Then, the target meteorological information is used to predict the power load using a preset power load prediction model to obtain the power load prediction result corresponding to the target area.

2. The comprehensive meteorological calculation method considering complex terrain in regional power load forecasting according to claim 1 is characterized in that: The determining of the average altitude value, the standard deviation of altitude, and the terrain gradient information corresponding to the target area based on the elevation grid data corresponding to the target area includes: Determining elevation grid data corresponding to a target area using a preset digital elevation model; the elevation grid data includes elevation values ​​of each grid cell corresponding to the target area; determining an average altitude value corresponding to the target area based on the elevation grid data and the number of grid cells in the target area, and determining an altitude standard deviation value corresponding to the target area based on the average altitude value, the elevation grid data, and the number of grid cells in the target area; A preset gradient algorithm is used to determine a first gradient along the x-axis and a second gradient along the y-axis corresponding to the target area based on each elevation value.

3. The comprehensive meteorological calculation method considering complex terrain in regional power load forecasting according to claim 2 is characterized in that: The determining of the slope mean and the terrain relief mean based on the first gradient and the second gradient includes: Determining a slope to be processed based on the first gradient and the second gradient, and performing slope mean calculation processing on the slope to be processed using a preset inverse tangent function to obtain a slope mean; the slope mean is a value representing the inclination of the terrain surface; The average terrain undulation is determined based on a first absolute value corresponding to the first gradient and a second absolute value corresponding to the second gradient; wherein the average terrain undulation is a value for measuring terrain complexity, and the numerical value of the average terrain undulation is positively correlated with the magnitude of regional undulation.

4. The comprehensive meteorological calculation method considering complex terrain in regional power load forecasting according to claim 1 is characterized in that: The characteristic matrix is ​​determined based on the average altitude value, the standard deviation of altitude value, the mean slope value, and the mean terrain undulation value, and the characteristic matrix is ​​processed using a preset clustering algorithm and a preset evaluation index to obtain a clustering result including several terrains, including: Determining a characteristic matrix corresponding to the target area based on the average altitude values, the standard deviation altitude values, the average slope values, and the average terrain undulation values; the characteristic matrix includes the average altitude values, the standard deviation altitude values, the average slope values, and the average terrain undulation values ​​corresponding to each area in the target area; The feature matrix is ​​processed using a K-Means clustering algorithm to obtain a current cluster corresponding to each of the regions, and the current cluster is processed using a preset distance square sum determination formula to obtain a corresponding distance square sum, and then it is determined whether the distance square sum meets a preset condition; the center point of the current cluster is the feature mean corresponding to each of the regions in the current cluster; If the sum of squared distances meets a preset condition, a clustering result is determined based on each current cluster; if the sum of squared distances does not meet the preset condition, the step of processing the feature matrix using a K-Means clustering algorithm is triggered.

5. The comprehensive meteorological calculation method considering complex terrain in regional power load forecasting according to claim 1 is characterized in that: The determining of regional meteorological information corresponding to each region in the target area based on the population density and electricity consumption corresponding to each region and each terrain in the clustering result includes: Determining each district or county in each of the regions and a first population density and a first power consumption corresponding to each of the district or county, determining a population density ratio based on the first population density and a second population density corresponding to the region, and then determining a first power consumption ratio based on the first power consumption and the second power consumption corresponding to the region; Determine a county weight corresponding to the county based on each of the terrains, the population density ratio, the first electricity consumption ratio, a first preset weight corresponding to the population density ratio, and a second preset weight corresponding to the first electricity consumption ratio in the clustering result; The regional meteorological information is determined based on the weights of each of the counties and the county meteorological information corresponding to the county; the county meteorological information is measured meteorological information.

6. The comprehensive meteorological calculation method considering complex terrain in regional power load forecasting according to claim 1 is characterized in that: The determining target meteorological information based on the regional weight and the regional meteorological information includes: Determining the regional power consumption corresponding to each area in the target area and the total power consumption corresponding to the target area, and determining a second power consumption ratio based on the proportion of the power consumption of each area in the total power consumption, and setting the second power consumption ratio as the regional weight; Based on the weight of each area and the comprehensive meteorological information of the area, weighted processing is performed to obtain target meteorological information; the target meteorological information is based on integrated data information including temperature, humidity, wind speed, and precipitation probability.

7. The comprehensive meteorological calculation method considering complex terrain in regional power load forecasting according to any one of claims 1 to 6, characterized in that: After performing power load forecasting on the target meteorological information using a preset power load forecasting model to obtain a power load forecast result corresponding to the target area, the method further includes: Evaluate the power load forecast result using a preset determination coefficient algorithm, a preset root mean square error algorithm, a preset mean absolute error algorithm, and a preset mean absolute percentage error algorithm to obtain an evaluation result; The preset adaptive optimization algorithm is used and the model parameters of the preset power load forecasting model are iteratively adjusted based on each of the evaluation results to obtain a new power load forecasting model; the model parameters include model learning rate, regularization coefficient, hidden layer structure parameters and feature weight distribution parameters.

8. A comprehensive meteorological calculation device that considers complex terrain in regional power load forecasting, characterized in that: include: a raster data processing module for determining an average altitude value, an altitude standard deviation value, and terrain gradient information corresponding to the target area based on the elevation raster data corresponding to the target area, and then determining a mean slope value and a mean terrain relief value based on the terrain gradient information; a clustering result determination module, configured to determine a feature matrix based on the average altitude value, the standard deviation of altitude value, the mean slope value, and the mean terrain relief value, and process the feature matrix using a preset clustering algorithm and a preset evaluation index to obtain a clustering result including a plurality of terrains; A prediction result determination module is used to determine the regional meteorological information and regional weight corresponding to the area based on the population density, power consumption and each terrain in the clustering result corresponding to each area in the target area, and determine the target meteorological information based on the regional weight and the regional meteorological information, and then use a preset power load prediction model to predict the power load of the target meteorological information to obtain the power load prediction result corresponding to the target area.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor for executing the computer program to implement the comprehensive meteorological calculation method for considering complex terrain in regional power load forecasting as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that Used to store a computer program, wherein when the computer program is executed by a processor, it implements the comprehensive meteorological calculation method considering complex terrain in regional power load forecasting as described in any one of claims 1 to 7.

Images