Typical industry load concentration area-based high-impact meteorological element extraction method and extraction device

Abstract

The invention relates to the technical field of meteorological analysis, and discloses a high-impact meteorological element extraction method and device based on a typical industry load concentration area, and the method comprises the steps: obtaining historical load data and historical meteorological data of a target area; performing data cleaning on the historical meteorological data to obtain cleaned data; based on the cleaned historical load data, typical industry loads of the target area are analyzed, and typical industry space load density distribution data are obtained; based on the typical industry space load density distribution data and the cleaned meteorological data, meteorological influence factors of the target area are extracted; executing influence analysis corresponding to the meteorological influence factors based on the cleaned data, and generating an analysis result; and determining the high-influence meteorological elements based on the analysis result. According to the method, historical meteorological data of a typical industry load concentration area is quantitatively analyzed, and meteorological factors which greatly influence the historical meteorological data are extracted, so that data support is provided for subsequent key monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of meteorological analysis, and in particular to a method for extracting high-impact meteorological elements based on typical industry load concentration areas and a device for extracting high-impact meteorological elements based on typical industry load concentration areas. Background Art

[0002] Stable power supply has a great impact on people's daily life. In order to ensure power supply, traditional technologies often use hydropower, thermal power and other methods to generate electricity. However, the above power generation methods are relatively single and highly dependent on natural resources. Once natural resources are affected, the entire power supply will be affected. In order to ensure the stability of power supply, with the development of new energy technologies, technicians have proposed power supply based on new energy technologies.

[0003] The current new energy power supply mainly includes wind power generation, solar power generation, etc., and its power generation process depends on the corresponding power generation device, which is often set up in specific outdoor scenes, such as mountains and plains, to maximize the use of natural resources. However, in the actual application process, technicians have found that the existing technology has at least the following technical problems:

[0004] Since the renewable energy power generation of a single device is relatively small, in order to increase its power generation scale and stability, it is configured in a centralized load manner, often by configuring the power generation equipment in a centralized area to maximize the use of natural resources. However, the above configuration method is easily affected by meteorological conditions, resulting in unstable power generation. At present, it is mainly monitored and adjusted manually, which cannot meet the needs of automated and intelligent monitoring. Summary of the invention

[0005] In order to overcome the above-mentioned technical problems existing in the prior art, an embodiment of the present invention provides a method and device for extracting high-impact meteorological elements based on load-concentrated areas. By quantitatively analyzing the historical meteorological data of the load-concentrated areas, the meteorological factors that have a greater impact on them are extracted, thereby providing data support for subsequent key monitoring.

[0006] In order to achieve the above-mentioned purpose, an embodiment of the present invention provides a method for extracting high-impact meteorological elements based on typical industry load concentration areas, and the method includes: acquiring historical load data and historical meteorological data of the target area; performing data cleaning on the historical meteorological data to obtain cleaned historical meteorological data; performing data cleaning on the historical load data to obtain cleaned historical load data; based on the cleaned historical load data, analyzing the typical industry load in the target area to obtain typical industry spatial load density distribution data; based on the typical industry spatial load density distribution data and the cleaned meteorological data, extracting meteorological influencing elements of the target area; performing impact analysis corresponding to the meteorological influencing elements based on the cleaned historical load data to generate analysis results; and determining high-impact meteorological elements based on the analysis results.

[0007] Preferably, the data cleaning of the historical meteorological data to obtain the cleaned meteorological data includes: performing storage format unification processing on the historical meteorological data to generate first processed data; performing data interpolation processing on the first processed data according to a preset data density to generate second processed data; performing non-business data cleaning on the second processed data to generate third processed data; performing outlier cleaning on the third processed data to generate cleaned meteorological data.

[0008] Preferably, the data cleaning of the historical load data to obtain cleaned historical load data includes: performing storage format unification processing on the historical load data to generate first processed data; filling missing data in the first processed data to generate second processed data; and cleaning outliers in the second processed data to generate cleaned load data.

[0009] Preferably, the load of typical industries in the target area is analyzed based on the cleaned historical load data to obtain spatial load density distribution data of typical industries, including: analyzing the distribution location and electricity consumption information of typical industries in the region based on the cleaned historical load data; performing spatial grid division based on the distribution location of the typical industries to generate gridded distribution location distribution data of typical industries; performing load density calculation based on the gridded distribution location distribution data of typical industries and electricity consumption information data of typical industries to generate spatial load density distribution data of typical industries.

[0010] Preferably, the extraction of meteorological influencing factors of the target area based on the typical industry spatial load density distribution data and the cleaned meteorological data includes: obtaining all influencing factors for all power load scenarios; determining the critical density of the typical industry load spatial density distribution to obtain the typical industry load high-density distribution area; performing environmental characteristic analysis on the typical industry load high-density distribution area to generate corresponding environmental characteristics; screening all influencing factors based on the environmental characteristics to generate meteorological influencing factors for the typical industry load high-density distribution area. Based on the meteorological influencing factors of the typical industry load high-density distribution area, perform spatial mask extraction on the cleaned meteorological data to generate a first extraction result; perform spatial interpolation on the first extraction result to generate extracted meteorological data.

[0011] Preferably, the impact analysis corresponding to the meteorological influencing factor is performed based on the cleaned historical load data to generate an analysis result, including: determining the initial weight of each sub-element in the extracted meteorological influencing factor; performing an impact analysis on each sub-element based on the cleaned historical load data, the extracted meteorological data and the initial weight to generate a preliminary analysis result; adjusting the initial weight based on the preliminary analysis result to generate an adjusted weight; judging whether each sub-element and its corresponding adjusted weight meet the data accuracy requirement; if so, generating an analysis result based on each sub-element and the corresponding adjusted weight; otherwise, performing a cyclic adjustment on the adjusted weight until it meets the data accuracy requirement, and generating an analysis result based on each sub-element and the corresponding adjusted weight.

[0012] Preferably, the method also includes: after generating the adjusted weights, determining the meteorological impact cycle; dividing the meteorological impact cycle into time periods to generate multiple time periods, and the meteorological impact trends in different time periods are different; performing data feature analysis on the cleaned data to generate meteorological impact features; optimizing the adjusted weights within the time period based on the meteorological impact features to generate optimized weights; generating dynamically optimized adjusted weights based on the time periods and corresponding optimized weights.

[0013] Correspondingly, the present invention also provides a high-impact meteorological element extraction device based on a typical industry load concentration area, the device comprising: a data acquisition unit, used to acquire historical load data and historical meteorological data of a target area; a cleaning unit, used to clean the historical meteorological data and historical load data to obtain cleaned historical meteorological data and historical load data; a load density determination unit, used to determine the spatial load density distribution of a typical industry; an element extraction unit, used to extract meteorological influencing elements in the typical industry load high-density area; an analysis unit, used to perform an impact analysis corresponding to the meteorological influencing elements based on the cleaned historical load data to generate an analysis result; a high-impact element determination unit, used to determine the high-impact meteorological elements based on the analysis result.

[0014] Preferably, the cleaning unit is specifically used to: unify the storage format of the historical meteorological data to generate first processed data; perform data interpolation processing on the first processed data according to a preset data density to generate second processed data; perform non-business data cleaning on the second processed data to generate third processed data; perform outlier cleaning on the third processed data to generate cleaned meteorological data; unify the storage format of the historical load data to generate first processed data; fill in missing data on the first processed data to generate second processed data; perform outlier cleaning on the second processed data to generate cleaned load data.

[0015] Preferably, the load density determination unit is specifically used to: analyze the distribution location and electricity consumption information of typical industries in the region based on the cleaned historical load data; perform spatial grid division based on the distribution location of the typical industries, and generate gridded distribution location data of typical industries; perform load density calculation based on the gridded distribution location data of typical industries and electricity consumption information data of typical industries, and generate spatial load density distribution data of typical industries.

[0016] Preferably, the factor extraction unit is specifically used to: obtain all influencing factors for all power load scenarios; determine the critical density of the typical industry load spatial density distribution, and obtain the typical industry load high-density distribution area; perform environmental characteristic analysis on the typical industry load high-density distribution area to generate corresponding environmental characteristics; screen all the influencing factors based on the environmental characteristics to generate meteorological influencing factors for the typical industry load high-density distribution area; perform spatial mask extraction on the cleaned meteorological data based on the meteorological influencing factors in the typical industry load high-density distribution area to generate a first extraction result; perform spatial interpolation on the first extraction result to generate extracted meteorological data.

[0017] Preferably, the analysis unit is specifically used to: determine the initial weight of each sub-element in the extracted meteorological influencing factor; perform an impact analysis on each sub-element based on the cleaned historical load data, the extracted meteorological data and the initial weight, and generate a preliminary analysis result; adjust the initial weight based on the preliminary analysis result to generate an adjusted weight; determine whether each sub-element and its corresponding adjusted weight meet the data accuracy requirements; if so, generate an analysis result based on each sub-element and the corresponding adjusted weight; otherwise, perform a cyclic adjustment on the adjusted weight until it meets the data accuracy requirements, and generate an analysis result based on each sub-element and the corresponding adjusted weight.

[0018] Preferably, the device also includes a dynamic optimization unit, which is specifically used to: determine the meteorological impact cycle after generating the adjusted weights; divide the meteorological impact cycle into time periods to generate multiple time periods, and the meteorological impact trends in different time periods are different; perform data feature analysis on the cleaned data to generate meteorological impact features; optimize the adjusted weights within the time period based on the meteorological impact features to generate optimized weights; generate dynamically optimized adjusted weights based on the time periods and corresponding optimized weights.

[0019] Through the technical solution provided by the present invention, the present invention has at least the following technical effects:

[0020] By performing multi-dimensional data cleaning on the historical meteorological data of the target area to improve its data accuracy, the characteristic analysis of the historical load data is carried out to obtain the load density distribution characteristics of typical industries. On this basis, the meteorological influencing factors in the high-density distribution areas of typical industry loads are quantitatively analyzed to determine the high-impact meteorological elements, which greatly improves the analysis accuracy and objectivity of the meteorological influencing factors in the load-concentrated areas, provides accurate data support for subsequent key monitoring and management, optimizes the work content of technical personnel, and meets the business needs of the enterprise.

[0021] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0023] Figure 1 It is a specific implementation flow chart of the method for extracting high-impact meteorological elements based on typical industry load concentration areas provided by an embodiment of the present invention;

[0024] Figure 2 This is a specific implementation flow chart of performing data cleaning on historical meteorological data provided by an embodiment of the present invention;

[0025] Figure 3 This is a specific implementation flow chart of performing the impact analysis on the meteorological influencing factors provided by the embodiment of the present invention;

[0026] Figure 4 It is a structural schematic diagram of a high-impact meteorological element extraction device based on a typical industry load concentration area provided by an embodiment of the present invention;

[0027] Figure 5 is a flow chart of analysis results generated by performing an impact analysis corresponding to the meteorological influencing factors based on the cleaned historical load data provided by an embodiment of the present invention;

[0028] Figure 6 It is a structural schematic diagram of a high-impact meteorological element extraction device based on a typical industry load concentration area provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0030] The terms "system" and "network" in the embodiments of the present invention can be used interchangeably. "Multiple" means two or more than two. In view of this, "multiple" can also be understood as "at least two" in the embodiments of the present invention. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / ", unless otherwise specified, generally indicates that the previous and subsequent associated objects are in an "or" relationship. In addition, it should be understood that in the description of the embodiments of the present invention, the words "first", "second", etc. are only used to distinguish the purpose of description, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying order.

[0031] See also Figure 1 The embodiment of the present invention provides a method for extracting high-impact meteorological elements based on load concentration areas, the method comprising:

[0032] S10) obtaining historical load data and historical meteorological data of the target area;

[0033] S20) performing data cleaning on the historical meteorological data to obtain cleaned data;

[0034] S30) performing data cleaning on the historical load data to obtain cleaned historical load data;

[0035] S40) Based on the cleaned historical load data, analyze the load of typical industries in the target area to obtain the spatial load density distribution data of typical industries

[0036] S50) Extract meteorological factors affecting the target area based on typical industry spatial load density distribution data and cleaned meteorological data

[0037] S60) performing an impact analysis corresponding to the meteorological influencing factors based on the post-cleaning historical load data to generate an analysis result;

[0038] S70) Determine high-impact meteorological elements based on the analysis results.

[0039] In one possible implementation, historical meteorological data and historical load data of the target area are first obtained. In this embodiment, for areas where new energy loads are about to be or have been concentratedly deployed, their historical meteorological data and historical load data are collected, and then the historical meteorological data are cleaned to obtain cleaned meteorological data.

[0040] See also Figure 2 In an embodiment of the present invention, the step of performing data cleaning on the historical meteorological data to obtain cleaned meteorological data includes:

[0041] S21) performing storage format unification processing on the historical meteorological data to generate first processed data;

[0042] S22) performing data interpolation processing on the first processed data according to a preset data density to generate second processed data;

[0043] S23) performing non-business data cleaning on the second processed data to generate third processed data;

[0044] S24) performing outlier cleaning on the third processed data to generate cleaned meteorological data.

[0045] In a possible implementation, the storage format of historical meteorological data is first unified. Since the acquired meteorological data may come from multiple platforms and multiple systems, their data types, data categories, and storage formats may be different. In order to facilitate subsequent unified analysis and processing, the storage format of all acquired historical meteorological data is first unified. Specifically, for data with different data types, data structure conversion is performed to generate meteorological data with a unified data type; for data with different data categories, data quantization is performed, and data type normalization is performed on the quantized data to generate meteorological data with a unified data type; for data with different storage formats, storage format conversion is performed to obtain the first processed data.

[0046] On the other hand, the historical meteorological data obtained from different channels may be missing to varying degrees, thus causing trouble for subsequent data analysis. Therefore, data interpolation processing is further performed on the first processed data according to a preset data density. Specifically, the preset data density can be predetermined by a technician according to actual needs or work experience. According to the data density, data interpolation processing is performed on the first processed data according to the change trend of the data in the first processed data to generate the second processed data.

[0047] On this basis, since the acquired historical meteorological data may also contain non-business meteorological data that is not related to the preset load concentration area, such as equipment monitoring data of the previously monitored equipment, verification data of the data port, etc., in order to further improve the accuracy of data cleaning, non-business data cleaning operations are further performed on the second processed data to generate third processed data. Finally, outlier cleaning is performed on the third processed data. Specifically, data distribution analysis can be performed on the third processed data based on the kernel density analysis algorithm, and data that obviously deviates from the normal value range can be cleaned out to generate cleaned meteorological data.

[0048] In an embodiment of the present invention, by performing data cleaning operations on historical meteorological data from multiple dimensions according to actual collection and use issues of historical meteorological data, the accuracy and reliability of the cleaned meteorological data can be effectively improved, and the accuracy of subsequent meteorological element analysis can be improved.

[0049] See also Figure 3 In an embodiment of the present invention, the step of performing data cleaning on the historical load data to obtain the cleaned historical load data includes:

[0050] S31) performing storage format unification processing on the historical load data to generate first processed data;

[0051] S32) filling missing data in the first processed data to generate second processed data;

[0052] S33) Cleaning the second processed data for outliers to generate cleaned load data.

[0053] In one possible implementation, the storage format of historical load data is first unified. Since the acquired load data may come from multiple platforms and multiple systems, their data types, data types, and storage formats may be different. In order to facilitate subsequent unified analysis and processing, all acquired historical load data are first processed in a unified storage format. Specifically, data with different data types are converted into a data structure to generate load data with a unified data type; data with different data types are quantized, and data type normalization is performed on the quantized data to generate load data with a unified data type; for data with different storage formats, storage format conversion is performed to obtain the first processed data.

[0054] Further, the first processed data is filled with missing data to generate the second processed data. Specifically, the first processed data is first analyzed to identify missing values ​​or outliers therein. Then, an appropriate filling method is selected according to the characteristics and missing conditions of the data. In the filling process, the seasonality, periodicity and long-term trend of the data also need to be considered to ensure that the filled data can maintain the original data distribution and statistical characteristics to obtain the second processed data.

[0055] On this basis, the second processed data is cleaned for outliers to generate cleaned load data. First, through statistical analysis methods and combined with domain knowledge, it is determined whether these potential outliers are indeed abnormal. For confirmed outliers, a variety of processing strategies can be adopted: you can choose to delete them directly, replace them with statistics such as the median, or use interpolation methods such as linear interpolation and spline interpolation to correct them and generate cleaned historical load data.

[0056] In the embodiment of the present invention, by performing data cleaning operations on historical load data from multiple dimensions according to actual collection and usage issues, the accuracy and reliability of the cleaned load data can be effectively improved, and the accuracy of subsequent typical industry load analysis in the region can be improved.

[0057] See also Figure 4 In the embodiment of the present invention, the analysis of typical industry loads in the target area based on the cleaned historical load data to obtain typical industry spatial load density distribution data includes:

[0058] S41) analyzing the distribution location and electricity consumption information of typical industries in the region based on the cleaned historical load data;

[0059] S42) Based on the distribution location of the typical industries, spatial grid division is performed to generate gridded distribution location data of the typical industries;

[0060] S43) Based on the grid-based distribution location distribution data of typical industries and the electricity consumption information data of typical industries, load density calculation is performed to generate spatial load density distribution data of typical industries.

[0061] In one possible implementation, based on the cleaned historical load data, we can conduct an in-depth analysis of the distribution location and electricity consumption information of typical industries in the region. First, the cleaned load data is combined with the geographical location information using geographic information system technology to draw a regional electricity load distribution heat map. Then, the concentrated electricity load areas in the region are identified through cluster analysis methods. Combining the geographical characteristics of these areas with the known industry distribution information, the distribution location of typical industries can be preliminarily determined.

[0062] Furthermore, based on the distribution location of the typical industries, spatial grid division is performed to generate gridded typical industry distribution location data. Specifically, the appropriate grid size and shape are determined based on the historical meteorological data of the study area. Usually, a regular rectangular grid is used to divide the entire study area into several grid units of equal size. The location information of the identified typical industries is superimposed on the grid system, and the industry types and number of users contained in each grid are counted. For large users or industrial parks spanning multiple grids, they can be allocated according to the proportion of their electricity consumption.

[0063] Furthermore, the electricity consumption information of typical industries in each grid is associated with its distribution location data. For each grid unit, the electricity load of all industries within it is accumulated and divided by the area of ​​the grid to obtain the average load density of the grid. At this point, the load of typical industries in the target area is further analyzed to obtain the spatial load density distribution data of typical industries.

[0064] In the embodiment of the present invention, by analyzing the spatial distribution of load density of typical industries from historical load data, it is possible to effectively identify high-impact areas of load changes and improve the accuracy of subsequent regional meteorological element load impact analysis.

[0065] At this time, the meteorological influencing factors of the target area are further determined. In traditional methods, technicians often directly use the meteorological influencing factors of all application scenarios for meteorological factor analysis. However, in actual application, different application scenarios (such as mountain scenes, plain scenes, ocean scenes, urban scenes, etc.) may have different environmental impacts. Therefore, the impact weights of different meteorological impression factors on load concentration areas are different.

[0066] In order to improve the accuracy of the analysis of meteorological influencing factors, in an embodiment of the present invention, the meteorological influencing factors of the target area are extracted based on the typical industry spatial load density distribution data and the cleaned meteorological data, including: obtaining all influencing factors for all power load scenarios; determining the critical density of the typical industry load spatial density distribution to obtain the typical industry load high-density distribution area; performing environmental feature analysis on the typical industry load high-density distribution area to generate corresponding environmental features; screening all the influencing factors based on the environmental features to generate meteorological influencing factors for the typical industry load high-density distribution area. Based on the meteorological influencing factors of the typical industry load high-density distribution area, perform spatial mask extraction on the cleaned meteorological data to generate a first extraction result; perform spatial interpolation on the first extraction result to generate extracted meteorological data.

[0067] In a possible implementation, we first obtain all influencing factors for all power load scenarios, including meteorological factors such as temperature, humidity, wind speed, precipitation, and socioeconomic factors such as economic indicators and population density. Then, the critical density value of the spatial density distribution of typical industry loads is determined through statistical analysis or expert experience, and the areas above this value are defined as typical industry load high-density distribution areas. Environmental characteristics of these high-density areas are analyzed to examine their topography, climate type, urbanization level and other characteristics. Based on these environmental characteristics, we screen all the influencing factors previously obtained, retaining factors that have a significant impact on the load in high-density areas, such as temperature changes under the urban heat island effect, pollutant concentrations in industrial areas, etc., so as to obtain key meteorological influencing factors for typical industry load high-density distribution areas. Next, these screened meteorological influencing factors are used as spatial masks to extract the cleaned meteorological data to obtain the first extraction result. Finally, we perform spatial interpolation processing on the first extraction result to integrate the data of multiple spatial points into a representative single-point data. This can be achieved by calculating the weighted average of all points in the high-density area, where the weight can be based on the load density of each point or by determining a representative point and calculating the distance weights between all points and the representative point to obtain the extracted meteorological data.

[0068] In an embodiment of the present invention, by accurately screening and confirming the meteorological influencing factors based on the environmental characteristics of the typical industry load high-density distribution area, the meteorological influencing factors that have a greater impact on it can be determined more accurately, avoiding the situation where non-high-impact factors are misidentified as high-impact meteorological factors due to their impact on historical meteorological data at a specific time or under specific circumstances, thereby improving the accuracy of the analysis of meteorological influencing factors.

[0069] For further analysis of meteorological factors at this time, see Figure 5In an embodiment of the present invention, the impact analysis corresponding to the meteorological influencing factors is performed based on the cleaned historical load data to generate analysis results, including:

[0070] S51) determining the initial weight of each sub-element in the extracted meteorological influencing element;

[0071] S52) performing an impact analysis on each sub-element based on the cleaned historical load data, the extracted meteorological data and the initial weight, and generating a preliminary analysis result;

[0072] S53) adjusting the initial weights based on the preliminary analysis results to generate adjusted weights;

[0073] S54) determining whether each sub-element and its corresponding adjusted weight meet the data accuracy requirements;

[0074] S561) If yes, generate analysis results based on each sub-element and the corresponding adjusted weight;

[0075] S562) Otherwise, perform a cyclic adjustment on the adjusted weight until it meets the data accuracy requirement, and generate an analysis result based on each sub-element and the corresponding adjusted weight.

[0076] In a possible implementation, since the meteorological influencing factors initially determined include multiple sub-elements, and the impact of each sub-element on the preset load concentration area is different, the initial weight of each sub-element is first determined. Specifically, the weight can be assigned by a technician based on actual work experience, or by a computer based on big data. After determining the initial weight, an impact analysis is performed on each sub-element based on the cleaned data and the initial weight. Specifically, the simulated impact data of all sub-elements on the preset load concentration area under the influence of the initial weight can be calculated by simulating the same scene and impact time, and it is determined whether the simulated impact data matches the cleaned data. Specifically, it is determined whether the data distribution is consistent, and the corresponding preliminary analysis results are generated. According to the preliminary analysis results, the initial weights of all sub-elements are adjusted to keep the impact of each sub-element on the preset load concentration area consistent with the cleaned data.

[0077] At this time, the data accuracy of each sub-element and its corresponding adjusted weight is further analyzed. Specifically, it is calculated under unified conditions whether the meteorological impact of each sub-element and the corresponding adjusted weight on the preset load concentration area is within the second deviation range (for example, ±10%) of the cleaned data. If so, the analysis results of the meteorological impact factors are generated according to each sub-element and the corresponding adjusted weight; otherwise, the adjusted weights are continuously adjusted in a loop to adjust their data accuracy to meet the requirements, and the analysis results of the meteorological impact factors are generated for the sub-element and the corresponding adjusted weight.

[0078] At this time, according to the analysis results of the above-mentioned meteorological influencing factors, the influencing factors with greater influence weights among the meteorological influencing factors are used as high-impact meteorological factors in the preset load concentration area for subsequent key monitoring. However, in the implementation process, since meteorological conditions change periodically (for example, often in a 1-year cycle), and the climate environment or natural environment is different at different times in each cycle, the high-impact meteorological factors produced in the preset load concentration area are also different.

[0079] In order to further improve the analysis accuracy of high-impact meteorological elements, in an embodiment of the present invention, after generating the adjusted weights, the method also includes: determining a meteorological impact cycle; dividing the meteorological impact cycle into time periods to generate multiple time periods, and the preset load concentration area is subject to different meteorological impact characteristics in different time periods; performing data feature analysis on the cleaned data to generate meteorological impact characteristics; optimizing the adjusted weights within the time period based on the meteorological impact characteristics to generate optimized weights; and generating dynamically optimized adjusted weights based on the time periods and corresponding optimized weights.

[0080] In a possible implementation, after the high-impact meteorological elements are preliminarily determined, the meteorological impact period is further determined. Specifically, depending on the load type, the meteorological impact period can be 1 year, 5-6 years, or 10 years, etc. The meteorological impact period is related to the load type deployed in the preset load concentration area. After the meteorological impact period is determined, it is divided into time periods. Specifically, the data change trend within each meteorological impact period can be analyzed based on its historical meteorological big data, and the data period belonging to the same change trend can be regarded as an independent time period, thereby completing the time period division of the entire meteorological impact period.

[0081] At this time, the data characteristics of the cleaned data are analyzed to analyze the data distribution characteristics in the preset load concentration area during the meteorological influence period, and further determine the meteorological influence characteristics corresponding to the preset load concentration area under the influence of the above-mentioned meteorological influence factors. At this time, the adjusted weights are further dynamically optimized in each time period according to the meteorological influence characteristics to generate optimized weights. Finally, the corresponding two-dimensional vectors are established according to the optimized weights and their corresponding time periods to generate more accurate adjusted weights. On this basis, the high-impact meteorological elements in the preset load concentration area in each time period are analyzed to more accurately determine its high-impact meteorological elements and quantify their degree of influence by weight.

[0082] In an embodiment of the present invention, by conducting a multi-dimensional analysis of the meteorological data of typical industry load concentration areas and quantifying the impact of different meteorological elements on them, the high-impact meteorological elements for the preset load concentration areas are accurately determined, providing favorable data support for subsequent key monitoring and management, and meeting the business needs of the enterprise.

[0083] The following describes a high-impact meteorological element extraction device based on load concentration areas provided by an embodiment of the present invention in conjunction with the accompanying drawings.

[0084] See also Figure 6 Based on the same inventive concept, an embodiment of the present invention provides a high-impact meteorological element extraction device based on a typical industry load concentration area, the device comprising: a data acquisition unit, used to acquire historical load data and historical meteorological data of a target area; a cleaning unit, used to clean the historical meteorological data and historical load data to obtain cleaned historical meteorological data and historical load data; a load density determination unit, used to determine the spatial load density distribution of a typical industry; an element extraction unit, used to extract meteorological influencing elements in the typical industry load high-density area; an analysis unit, used to perform an impact analysis corresponding to the meteorological influencing elements based on the cleaned historical load data to generate an analysis result; a high-impact element determination unit, used to determine the high-impact meteorological elements based on the analysis result.

[0085] In an embodiment of the present invention, the cleaning unit is specifically used to: perform storage format unification processing on the historical meteorological data to generate first processed data; perform data interpolation processing on the first processed data according to a preset data density to generate second processed data; perform non-business data cleaning on the second processed data to generate third processed data; perform outlier cleaning on the third processed data to generate cleaned meteorological data; perform storage format unification processing on the historical load data to generate first processed data; perform missing data filling on the first processed data to generate second processed data; perform outlier cleaning on the second processed data to generate cleaned load data.

[0086] In the embodiment of the present invention, the load density determination unit is specifically used for:

[0087] Based on the cleaned historical load data, the distribution location and electricity consumption information of typical industries in the region are analyzed; based on the distribution location of the typical industries, spatial grid division is performed to generate gridded distribution location distribution data of typical industries; based on the gridded distribution location distribution data of typical industries and the electricity consumption information data of typical industries, load density calculation is performed to generate spatial load density distribution data of typical industries.

[0088] In an embodiment of the present invention, the element extraction unit is specifically used to: obtain all influencing factors for all power load scenarios; determine the critical density of the typical industry load spatial density distribution to obtain the typical industry load high-density distribution area; perform environmental feature analysis on the typical industry load high-density distribution area to generate corresponding environmental features; screen all influencing factors based on the environmental features to generate meteorological influencing factors for the typical industry load high-density distribution area. Based on the meteorological influencing factors of the typical industry load high-density distribution area, perform spatial mask extraction on the cleaned meteorological data to generate a first extraction result; perform spatial interpolation on the first extraction result to generate extracted meteorological data.

[0089] In an embodiment of the present invention, the analysis unit is specifically used to: determine the initial weight of each sub-element in the extracted meteorological influencing factor; perform an impact analysis on each sub-element based on the cleaned historical load data, the extracted meteorological data and the initial weight, and generate a preliminary analysis result; adjust the initial weight based on the preliminary analysis result to generate an adjusted weight; determine whether each sub-element and its corresponding adjusted weight meet the data accuracy requirements; if so, generate an analysis result based on each sub-element and the corresponding adjusted weight; otherwise, perform a cyclic adjustment on the adjusted weight until it meets the data accuracy requirements, and generate an analysis result based on each sub-element and the corresponding adjusted weight.

[0090] In an embodiment of the present invention, the device also includes a dynamic optimization unit, which is specifically used to: determine the meteorological impact cycle after generating the adjusted weights; divide the meteorological impact cycle into time periods to generate multiple time periods, and the meteorological impact trends in different time periods are different; perform data feature analysis on the cleaned data to generate meteorological impact features; optimize the adjusted weights within the time period based on the meteorological impact features to generate optimized weights; generate dynamically optimized adjusted weights based on the time period and the corresponding optimized weights.

[0091] The optional implementation modes of the embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above implementation modes. Within the technical concept of the embodiments of the present invention, various simple modifications can be made to the technical scheme of the embodiments of the present invention, and these simple modifications all belong to the protection scope of the embodiments of the present invention.

[0092] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0093] Those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions for making a single-chip microcomputer, a chip or a processor (processor) execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0094] In addition, various implementation modes of the embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the embodiments of the present invention, they should also be regarded as the contents disclosed by the embodiments of the present invention.

Claims

1. A method for extracting high-impact meteorological elements based on typical industry load concentration areas, characterized in that: The method comprises: Obtain historical load data and historical meteorological data of the target area; Performing data cleaning on the historical meteorological data to obtain cleaned historical meteorological data; Performing data cleaning on the historical load data to obtain cleaned historical load data; Based on the cleaned historical load data, the load of typical industries in the target area is analyzed to obtain the spatial load density distribution data of typical industries; Based on the spatial load density distribution data of typical industries and cleaned meteorological data, the meteorological influencing factors of the target area are extracted; Performing an impact analysis corresponding to the meteorological influencing factors based on the cleaned historical load data to generate an analysis result; High-impact meteorological elements are determined based on the analysis results.

2. The method according to claim 1, characterized in that: The step of performing data cleaning on the historical meteorological data to obtain cleaned meteorological data includes: Performing storage format unification processing on the historical meteorological data to generate first processed data; Performing data interpolation processing on the first processed data according to a preset data density to generate second processed data; performing non-business data cleaning on the second processed data to generate third processed data; Outlier cleaning is performed on the third processed data to generate cleaned meteorological data.

3. The method according to claim 1, characterized in that: The step of performing data cleaning on the historical load data to obtain the cleaned historical load data includes: Performing storage format unification processing on the historical load data to generate first processed data; Filling missing data on the first processed data to generate second processed data; The second processed data is cleaned of outliers to generate cleaned load data.

4. The method according to claim 1, characterized in that: The typical industry loads in the target area are analyzed based on the cleaned historical load data to obtain the spatial load density distribution data of the typical industries; including: Based on the cleaned historical load data, analyze the distribution location and electricity consumption information of typical industries in the region; Based on the distribution location of the typical industries, spatial grid division is performed to generate gridded distribution location data of the typical industries; Based on the gridded location distribution data of typical industries and the electricity consumption information data of typical industries, load density calculation is performed to generate spatial load density distribution data of typical industries.

5. The method according to claim 1, characterized in that The meteorological influencing factors of the target area are extracted based on the typical industry spatial load density distribution data and cleaned meteorological data, including: Obtain all influencing factors for all power load scenarios; Determine the critical density of the typical industry load spatial density distribution, and obtain the typical industry load high density distribution area; Perform environmental characteristic analysis on the typical industry load high-density distribution area to generate corresponding environmental characteristics; All the influencing factors are screened based on the environmental characteristics to generate meteorological influencing factors for areas with high density distribution of typical industry loads. Based on the meteorological influencing factors in the high-density distribution area of ​​the type of industry load, performing spatial mask extraction on the cleaned meteorological data to generate a first extraction result; The first extraction result is spatially interpolated to generate extracted meteorological data.

6. The method according to claim 1, characterized in that The performing of the impact analysis corresponding to the meteorological influencing factors based on the cleaned historical load data to generate the analysis results includes: Determining the initial weight of each sub-element in the extracted meteorological influencing element; Performing an impact analysis on each sub-element based on the cleaned historical load data, the extracted meteorological data and the initial weight to generate a preliminary analysis result; Adjusting the initial weights based on the preliminary analysis results to generate adjusted weights; Determine whether each sub-element and its corresponding adjusted weight meet the data accuracy requirements; If so, generate analysis results based on each sub-element and the corresponding adjusted weights; Otherwise, the adjusted weights are repeatedly adjusted until they meet the data accuracy requirement, and an analysis result is generated based on each sub-element and the corresponding adjusted weights.

7. The method according to claim 6, characterized in that The method further comprises: After generating the adjusted weights, determining a meteorological impact period; The meteorological influence cycle is divided into multiple time periods, and the meteorological influence trends in different time periods are different; Performing data feature analysis on the cleaned data to generate meteorological impact features; Optimizing the adjusted weights within the time period based on the meteorological impact characteristics to generate optimized weights; A dynamically optimized adjusted weight is generated based on the time period and the corresponding optimized weight.

8. A high-impact meteorological element extraction device based on typical industry load concentration areas, characterized in that: The device comprises: A data acquisition unit, used to acquire historical load data and historical meteorological data of a target area; A cleaning unit, used for cleaning the historical meteorological data and the historical load data to obtain cleaned historical meteorological data and historical load data; Load density determination unit, used to determine the load density distribution of typical industries; An element extraction unit, used for extracting meteorological influencing elements of the typical industry load high-density area; an analysis unit, configured to perform an impact analysis corresponding to the meteorological influencing factor based on the post-cleaning historical load data, and generate an analysis result; A high-impact element determination unit is used to determine high-impact meteorological elements based on the analysis results.

9. The device according to claim 8, characterized in that The cleaning unit is specifically used for: Performing storage format unification processing on the historical meteorological data to generate first processed data; Performing data interpolation processing on the first processed data according to a preset data density to generate second processed data; performing non-business data cleaning on the second processed data to generate third processed data; performing outlier cleaning on the third processed data to generate cleaned meteorological data; Performing storage format unification processing on the historical load data to generate first processed data; Filling missing data on the first processed data to generate second processed data; The second processed data is cleaned of outliers to generate cleaned load data.

10. The device according to claim 8, characterized in that The load density determination unit is specifically used for: Based on the cleaned historical load data, analyze the distribution location and electricity consumption information of typical industries in the region; Based on the distribution location of the typical industries, spatial grid division is performed to generate gridded distribution location data of the typical industries; Based on the gridded location distribution data of typical industries and the electricity consumption information data of typical industries, load density calculation is performed to generate spatial load density distribution data of typical industries.

11. The device according to claim 8, characterized in that The element extraction unit is specifically used for: Obtain all influencing factors for all power load scenarios; Determine the critical density of the typical industry load spatial density distribution, and obtain the typical industry load high density distribution area; Perform environmental characteristic analysis on the typical industry load high-density distribution area to generate corresponding environmental characteristics; All the influencing factors are screened based on the environmental characteristics to generate meteorological influencing factors for areas with high density distribution of typical industry loads. Based on the meteorological influencing factors in the high-density distribution area of ​​the type of industry load, performing spatial mask extraction on the cleaned meteorological data to generate a first extraction result; The first extraction result is spatially interpolated to generate extracted meteorological data.

12. The device according to claim 8, characterized in that The analysis unit is specifically used for: Determining the initial weight of each sub-element in the extracted meteorological influencing element; Performing an impact analysis on each sub-element based on the cleaned historical load data, the extracted meteorological data and the initial weight to generate a preliminary analysis result; Adjusting the initial weights based on the preliminary analysis results to generate adjusted weights; Determine whether each sub-element and its corresponding adjusted weight meet the data accuracy requirements; If so, generate analysis results based on each sub-element and the corresponding adjusted weights; Otherwise, the adjusted weights are repeatedly adjusted until they meet the data accuracy requirement, and an analysis result is generated based on each sub-element and the corresponding adjusted weights.

13. The device according to claim 12, characterized in that The device further includes a dynamic optimization unit, which is specifically used for: After generating the adjusted weights, determining a meteorological impact period; The meteorological influence cycle is divided into multiple time periods, and the meteorological influence trends in different time periods are different; Performing data feature analysis on the cleaned data to generate meteorological impact features; Optimizing the adjusted weights within the time period based on the meteorological impact characteristics to generate optimized weights; A dynamically optimized adjusted weight is generated based on the time period and the corresponding optimized weight.

Images