Load influence air temperature sensitivity analysis method and system based on regional characteristic analysis

Abstract

The invention relates to the technical field of air temperature prediction, in particular to a load influence air temperature sensitivity analysis method and system based on regional characteristic analysis. The method comprises the following steps: acquiring historical power load data, air temperature data, geographic information data and energy use proportion data corresponding to a target area, and performing time sequence synchronization preprocessing and area characteristic index quantification to obtain corresponding power area characteristic indexes in the same sub-area; performing region classification influence evaluation and load sensitivity accounting on the corresponding geographic sub-regions in the target region to obtain sensitivity coefficients of power loads of different types of regions to air temperature; and performing power resource allocation management on the corresponding geographic sub-regions in the target region, and generating power resource allocation management strategies corresponding to different air temperature sensitive regions so as to execute corresponding power resource optimal allocation management work. According to the invention, more accurate load prediction and power resource optimization configuration can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature prediction, and in particular to a method and system for analyzing the sensitivity of load to temperature based on regional characteristic analysis. Background Art

[0002] In the operation and management of power systems, accurately grasping the variation law of power load is crucial for ensuring the stability and economy of power supply. Temperature is one of the important factors affecting power load, and there are significant differences in the sensitivity of power loads in different regions to temperature. For example, in some industrially developed regions, the industrial load accounts for a large proportion, and its sensitivity to temperature is very different from that of regions mainly composed of residential loads. Moreover, within different seasons and different time periods, the response of the load to temperature also changes. However, most of the existing methods for analyzing the load-temperature sensitivity adopt simple linear regression or models based on global data, ignoring the influence of characteristics such as geography, climate, industrial structure, and energy consumption habits in different regions on the load-temperature relationship. These methods cannot accurately reflect the detailed changes in the load within the region, resulting in large errors in load prediction and power resource scheduling. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide a method and system for analyzing the sensitivity of load to temperature based on regional characteristic analysis to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for analyzing the sensitivity of load to temperature based on regional characteristic analysis includes the following steps: Step S1: Obtain the historical power load data, temperature data, geographical information data, and energy usage ratio data corresponding to the target region, and perform time-series synchronization preprocessing on the historical power load data, temperature data, and energy usage ratio data corresponding to the target region based on the geographical sub-regions corresponding to the geographical information data and in accordance with the time series, so as to obtain the power load standard sequence data, temperature standard sequence data, and energy usage standard sequence data corresponding to the same sub-region; Step S2: Quantify the regional characteristic indexes of the power load standard sequence data, temperature standard sequence data, and energy usage standard sequence data corresponding to the same sub-region to obtain the power regional characteristic indexes corresponding to the same sub-region, including the industrial structure load power consumption index, temperature fluctuation stability index, and energy usage index corresponding to the same geographical sub-region; Step S3: Based on the corresponding power region characteristic indicators in the same sub-region, conduct an impact assessment on the regional classification of the corresponding geographical sub-regions in the target region to obtain the load-temperature non-linear impact index or the load-temperature linear impact index corresponding to different category regions; obtain the response speed and change range of the load to the temperature in different category regions, and combine the load-temperature non-linear impact index or the load-temperature linear impact index to conduct a load sensitivity calculation on the corresponding geographical sub-regions in the target region, and obtain the sensitivity coefficient of the power load to the temperature in different category regions. Step S4: Based on the sensitivity coefficient of the power load to the temperature in different category regions, conduct power resource allocation management on the corresponding geographical sub-regions in the target region, generate power resource allocation management strategies corresponding to different temperature-sensitive regions, and execute the corresponding power resource optimization allocation management work.

[0005] Further, step S1 includes the following steps: Step S11: Obtain the historical power load data corresponding to the target region through the power company database; Step S12: Obtain the temperature data corresponding to the target region through the meteorological monitoring station; Step S13: Obtain the geographical information data corresponding to the target region through the geographical information database, including the terrain, landform, and urban terrain distribution corresponding to the target region; Step S14: Obtain the energy usage ratio data corresponding to the target region through the power energy usage records, including the usage amount and ratio corresponding to various types of energy; Step S15: Divide the corresponding geographical sub-regions based on the terrain, landform, and urban terrain distribution of the geographical information data, and based on the geographical sub-regions, conduct sub-region data division on the historical power load data, temperature data, and energy usage ratio data corresponding to the target region to obtain the power load data, temperature data, and energy usage data corresponding to the same sub-region; synchronize the time series and preprocess the power load data, temperature data, and energy usage data corresponding to the same sub-region according to the time series, so as to unify the corresponding data within the same time range, and clean, remove outliers, missing values, and standardize them to obtain the power load standard sequence data, temperature standard sequence data, and energy usage standard sequence data corresponding to the same sub-region.

[0006] Further, the geographical sub-regions described in step S15 include mountainous areas, plain areas, industrial areas, agricultural areas, and residential areas.

[0007] Further, step S2 includes the following steps: Step S21: Obtain the corresponding regional industrial structure through the geographical sub-region, and quantify the regional electricity consumption proportion of the corresponding electricity load standard sequence data under the same sub-region based on the regional industrial structure, so as to obtain the electricity consumption proportion of the electricity load corresponding to different industrial structures, and obtain the industrial structure load electricity consumption index corresponding to the same geographical sub-region; Step S22: Quantify the regional temperature fluctuation index of the corresponding temperature standard sequence data under the same sub-region, so as to obtain the corresponding seasonal fluctuation amplitude and fluctuation frequency of the temperature, and obtain the temperature fluctuation stability index corresponding to the same geographical sub-region; Step S23: Quantify the regional energy proportion index through the usage amount and proportion of various energy sources in the corresponding energy usage standard sequence data under the same sub-region, so as to obtain the corresponding proportion of clean energy usage and the proportion of non-clean energy usage, and obtain the energy usage index corresponding to the same geographical sub-region.

[0008] Further, Step S3 includes the following steps: Step S31: Perform principal component feature dimensionality reduction on the corresponding power regional characteristic index under the same sub-region, so as to perform dimensionality reduction operation using the principal component analysis technology, and extract the index corresponding to the main characteristics of the geographical sub-region, and obtain the power regional dimensionality reduction index corresponding to the same sub-region; Step S32: Perform regional characteristic similarity measurement between the corresponding power regional dimensionality reduction indexes under each sub-region, so as to obtain the similarity between the characteristic indexes under each sub-region; Step S33: Classify the geographical sub-regions corresponding to the target region based on the similarity between the characteristic indexes under each sub-region. If the similarity between the characteristic indexes under each sub-region is greater than or equal to 90%, the corresponding geographical sub-region is classified as a complex load change region; if the similarity between the characteristic indexes under each sub-region is less than 90%, the corresponding geographical sub-region is classified as another relatively simple load change region; Step S34: Use a non-linear model to evaluate the complex region impact on the corresponding electricity load and temperature change in the complex load change region, so as to obtain the load-temperature non-linear impact index corresponding to the complex load category region; use a linear regression model to evaluate the simple region impact on the corresponding electricity load and temperature change in the relatively simple load change region, so as to obtain the load-temperature linear impact index corresponding to the simple load category region; Step S35: Obtain the response speed and change amplitude of the load to the temperature in different category regions, and combine the load-temperature non-linear impact index or the load-temperature linear impact index to calculate the load sensitivity of the corresponding geographical sub-regions in the target region, and obtain the sensitivity coefficient of the electricity load in different category regions to the temperature.

[0009] Further, step S35 includes the following steps: Step S351: Conduct a statistical analysis of the response speed through the corresponding power loads and temperature changes in different category areas to obtain the response speed of the loads to temperature in different category areas; Step S352: Conduct an analysis of the temperature change trend between the corresponding power loads and temperature changes in different category areas to obtain the temperature change trend line corresponding to different category areas under the power load condition; Step S353: Calculate the change amplitude of the corresponding temperature change based on the temperature change trend line corresponding to different category areas under the power load condition to obtain the change amplitude of the loads to temperature in different category areas; Step S354: Based on the response speed and change amplitude of the loads to temperature in different category areas and in combination with the load-temperature non-linear influence index or the load-temperature linear influence index, use the load-temperature sensitivity calculation formula to conduct a load sensitivity calculation for the corresponding geographical sub-areas in the target area to obtain the sensitivity coefficient of the power loads in different category areas to temperature.

[0010] Further, the load-temperature sensitivity calculation formula described in step S354 is specifically: For areas with complex load changes: ; For areas with relatively simple load changes: ; In the formula, is the sensitivity coefficient of the regional power load to temperature, is the response speed of the load in the area to temperature, is the change amplitude of the load in the area to temperature, is the temperature change parameter corresponding to the geographical sub-area, is the load-temperature non-linear influence index, is the load-temperature linear influence index.

[0011] Further, step S4 includes the following steps: Step S41: Conduct a regional sensitive statistical feature analysis on the corresponding geographical sub-areas in the target area based on the sensitivity coefficient of the power loads in different category areas to temperature to obtain the mean value, variance and peak statistical features corresponding to the temperature sensitivity coefficients in different category areas at different time periods; Step S42: Conduct a temperature sensitivity difference analysis on the corresponding geographical sub-areas in the target area based on the mean value, variance and peak statistical features corresponding to the temperature sensitivity coefficients in different category areas at different time periods to obtain the load-temperature sensitivity differences corresponding to different category areas; Step S43: Based on the differences in load temperature sensitivities corresponding to different category regions, perform power resource allocation management on the corresponding geographical sub-regions within the target region, generate power resource allocation management strategies corresponding to different temperature-sensitive regions, and execute the corresponding optimized power resource allocation management work.

[0012] Further, the power resource allocation management strategies corresponding to different temperature-sensitive regions described in Step S43 are specifically as follows: If it is determined that the sensitivity coefficient differences within the corresponding geographical sub-region are large and the load growth is fast, then it is planned as a load temperature-sensitive region to set the corresponding constraints for power resource allocation, including grid transmission capacity limits and power generation equipment output limits, and use the simulated annealing algorithm to find the optimal power resource allocation result while satisfying the constraints; If it is determined that the sensitivity coefficient differences within the corresponding geographical sub-region are small and the load growth is slow, then it is planned as a load non-temperature-sensitive region to implement power loss adjustment and load control measures during high or low temperature periods, so as to achieve the corresponding optimized utilization of power resources and energy conservation and emission reduction.

[0013] Further, the present invention also provides a load impact temperature sensitivity analysis system based on regional characteristic analysis for executing the load impact temperature sensitivity analysis method based on regional characteristic analysis as described above. The load impact temperature sensitivity analysis system based on regional characteristic analysis includes: A regional data time series synchronization module, which is used to obtain the historical power load data, temperature data, geographical information data, and energy usage ratio data corresponding to the target region, and perform time series synchronization preprocessing on the historical power load data, temperature data, and energy usage ratio data corresponding to the target region based on the geographical sub-regions corresponding to the geographical information data and according to the time series, so as to obtain the corresponding power load standard sequence data, temperature standard sequence data, and energy usage standard sequence data under the same sub-region; A regional characteristic index quantification module, which is used to quantify the regional characteristic indexes of the power load standard sequence data, temperature standard sequence data, and energy usage standard sequence data corresponding to the same sub-region, so as to obtain the corresponding power regional characteristic indexes under the same sub-region, including the industrial structure load electricity consumption index, temperature fluctuation stability index, and energy usage index corresponding to the same geographical sub-region; The regional load sensitivity calculation module is used to evaluate the impact of regional classification on the corresponding geographical sub-regions in the target region based on the corresponding power region characteristic indicators in the same sub-region, so as to obtain the load-temperature non-linear impact index or load-temperature linear impact index corresponding to different types of regions; obtain the response speed and change range of the load to the temperature in different types of regions, and combine the load-temperature non-linear impact index or load-temperature linear impact index to calculate the load sensitivity of the corresponding geographical sub-regions in the target region, so as to obtain the sensitivity coefficient of the power load to the temperature in different types of regions; The power resource allocation and management module is used to allocate and manage the power resources of the corresponding geographical sub-regions in the target region based on the sensitivity coefficient of the power load to the temperature in different types of regions, generate the power resource allocation and management strategies corresponding to different temperature-sensitive regions, and perform the corresponding power resource optimization allocation and management work.

[0014] The beneficial effects of the present invention: 1. The load impact temperature sensitivity analysis method based on regional characteristic analysis proposed by the present invention, compared with the prior art, the beneficial effects of this application are as follows: By obtaining the historical power load data, temperature data, geographical information data, and energy usage ratio data of the target area, it provides basic data for subsequent analysis, and through time series synchronization preprocessing, it ensures that these data can be analyzed on the same time axis. The key to this processing step is mainly reflected in the time series consistency and accuracy of the data. Different data sources often have different time scales and update frequencies. The power load data is updated hourly, daily, or monthly, while the temperature data is provided hourly, and the energy usage ratio data depends on quarterly or annual statistical information. Time series synchronization processing can adjust the time scale of the data through interpolation or other means, so as to ensure that various data are comparable at the same time point. This step not only improves the consistency of the data but also reduces the errors caused by time asynchronization, providing a reliable data basis for subsequent analysis. Secondly, by quantifying the regional characteristic indicators such as the power load, temperature fluctuation, and energy usage structure of different geographical sub-regions in the target area, the key to this step is reflected in its ability to transform complex regional characteristics into operable data indicators through the quantification of key factors, which is convenient for analysis and decision-making. Specifically, the industrial structure load electricity consumption index can reveal the electricity demand of different industries in different sub-regions, reflect the relationship between regional economic development and electricity consumption, and thus provide a theoretical basis for the prediction and optimization of electricity demand; the temperature fluctuation stability index helps to identify the impact degree of temperature change on the power load and provides a reference for adaptation measures to climate change; the energy usage index reflects the rationality and sustainability of the energy structure within the region and helps to evaluate the energy usage efficiency of different regions. These quantified indicators not only provide important reference data for power load prediction and energy management but also provide a more accurate decision-making basis for subsequent regional power management. Then, by analyzing the non-linear or linear relationship between the load and the temperature, it can better analyze the influence of the geographical, climatic, industrial structure, and energy usage and other characteristics of different regions on the load-temperature relationship. This analysis can also help to identify the response speed and change range of the temperature to the power load in different regions by evaluating the non-linear impact index or linear impact index of the load-temperature, and then calculate the power load sensitivity coefficient of the region. The power load sensitivity coefficient is an important indicator for evaluating the reaction degree of electricity demand to temperature change. It helps regional managers to evaluate the fluctuation degree of the power load under the condition of temperature change. The calculation of this indicator helps to accurately predict the change of electricity demand within the region and provides a scientific basis for coping with the power pressure brought by extreme weather or climate change, and can provide a more accurate risk assessment for subsequent power resource management.Finally, by formulating a targeted power resource allocation management strategy based on the sensitivity coefficient of temperature to power load in different geographical sub-regions, the key to this step mainly lies in its ability to effectively optimize the allocation of power resources and ensure the stable operation of the power system. Especially in the case of large temperature fluctuations, based on the temperature sensitivity of different regions, the response characteristics of regional power loads vary greatly. This requires considering the special needs of the region when allocating power resources. For example, in regions with large temperature fluctuations, the simulated annealing algorithm is used to find the optimal power resource allocation result while meeting the constraints. Therefore, it is necessary to increase the power supply capacity during these periods. In regions with small temperature fluctuations, the power supply can be reduced during high or low temperature periods to save power resources. Through this strategy, it is possible to avoid waste of resources or power shortages, and at the same time improve the load-bearing capacity within the power system and the reliability of power resource scheduling.

[0015] 2. The system for analyzing the sensitivity of load impact on temperature based on regional characteristic analysis proposed by the present invention is generally composed of a regional data time series synchronization module, a regional characteristic index quantification module, a regional load sensitivity accounting module, and a power resource allocation management module. It can implement any method for analyzing the sensitivity of load impact on temperature based on regional characteristic analysis described in the present invention. It is used to realize the method for analyzing the sensitivity of load impact on temperature based on regional characteristic analysis through the operation between computer programs running on each module. The internal structure of the system cooperates with each other, which can greatly reduce repetitive work and manpower input, and can quickly and effectively provide a more accurate and efficient process for analyzing the sensitivity of load impact on temperature based on regional characteristic analysis, thus simplifying the operation process of the system for analyzing the sensitivity of load impact on temperature based on regional characteristic analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] By reading the detailed description of the non-limiting embodiments with reference to the following drawings, other features, objects, and advantages of the present invention will become more apparent: Figure 1 It is a schematic flow chart of the steps of the method for analyzing the sensitivity of load impact on temperature based on regional characteristic analysis of the present invention; Figure 2 For Figure 1 it is a detailed schematic flow chart of step S1; Figure 3 For Figure 1 it is a detailed schematic flow chart of step S2. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The technical method of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative work belong to the scope of protection of the present invention.

[0018] In addition, the accompanying drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0019] It should be understood that although terms such as "first" and "second" may be used here to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit can be called the second unit, and similarly the second unit can be called the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed related items.

[0020] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides a method for analyzing the sensitivity of load impact on temperature based on regional characteristic analysis. The method includes the following steps: Step S1: Obtain the historical power load data, temperature data, geographic information data, and energy usage ratio data corresponding to the target area, and perform time-series synchronization preprocessing on the historical power load data, temperature data, and energy usage ratio data corresponding to the target area based on the geographical sub-areas corresponding to the geographic information data and in accordance with the time series, to obtain the corresponding power load standard sequence data, temperature standard sequence data, and energy usage standard sequence data in the same sub-area; Step S2: Quantify the regional characteristic indicators of the power load standard sequence data, temperature standard sequence data, and energy usage standard sequence data corresponding to the same sub-area to obtain the corresponding power regional characteristic indicators in the same sub-area, including the industrial structure load power consumption indicator, temperature fluctuation stability indicator, and energy usage indicator corresponding to the same geographical sub-area; Step S3: Based on the corresponding power region characteristic indexes in the same sub-region, conduct an impact assessment on the regional classification of the corresponding geographical sub-regions in the target region to obtain the load-temperature non-linear impact index or the load-temperature linear impact index corresponding to different category regions; obtain the response speed and change range of the load to the temperature in different category regions, and combine the load-temperature non-linear impact index or the load-temperature linear impact index to conduct a load sensitivity calculation on the corresponding geographical sub-regions in the target region, so as to obtain the sensitivity coefficient of the power load to the temperature in different category regions. Step S4: Based on the sensitivity coefficient of the power load to the temperature in different category regions, conduct power resource allocation management on the corresponding geographical sub-regions in the target region, generate power resource allocation management strategies corresponding to different temperature-sensitive regions, so as to execute the corresponding power resource optimization allocation management work.

[0021] In the embodiment of the present invention, please refer to Figure 1 As shown in the figure, it is a schematic flow chart of the steps of the load impact temperature sensitivity analysis method based on regional characteristic analysis of the present invention. In this example, the load impact temperature sensitivity analysis method based on regional characteristic analysis includes the following steps: Step S1: Obtain the historical power load data, temperature data, geographical information data, and energy usage proportion data corresponding to the target region, and based on the geographical sub-regions corresponding to the geographical information data, perform time series synchronization preprocessing on the historical power load data, temperature data, and energy usage proportion data corresponding to the target region according to the time series, so as to obtain the corresponding power load standard sequence data, temperature standard sequence data, and energy standard sequence data in the same sub-region. In the embodiments of the present invention, by obtaining historical power load data, temperature data, geographical information data, and energy usage ratio data of the target area. Specifically, the power load data can be obtained from the historical power grid data provided by the power company or extracted from the smart meter system, ensuring coverage of each sub-area of the target area. The data range should include historical data of no less than 3 years or a longer time period selected according to the actual situation of the target area. The temperature data can be obtained through the climate monitoring system of the meteorological department, selecting a time period matching the power load data to ensure timeliness and geographical correspondence. The geographical information data should include the administrative division of the target area, the regional boundary, and the specific spatial locations of each sub-area, etc., which can usually be extracted from the geographical information system (GIS) database. The energy usage ratio data includes the usage proportions of different energy types (such as coal power, wind power, solar energy, etc.), which are usually provided by the statistics of the energy competent department. Through GIS tools and database systems, preprocessing of time series synchronization is performed on the power load data, temperature data, and energy usage ratio data. The specific operation steps are as follows: First, for each sub-area, according to the geographical information data, the power load data, temperature data, and energy usage ratio data are matched at the same time point, and missing values, outliers, and inconsistencies are processed. Second, interpolation processing is performed according to the time series to align the time points of different data sources. Finally, the power load standard sequence data, temperature standard sequence data, and energy usage standard sequence data in the same sub-area are obtained.

[0022] Step S2: Quantify the regional characteristic indicators of the corresponding power load standard sequence data, temperature standard sequence data, and energy usage standard sequence data in the same sub-area to obtain the corresponding power regional characteristic indicators in the same sub-area, including the industrial structure load electricity consumption indicator, temperature fluctuation stability indicator, and energy usage indicator corresponding to the same geographical sub-area; In the embodiments of the present invention, by quantifying the regional characteristic indicators of the power load standard sequence data, temperature standard sequence data, and energy usage standard sequence data. Specifically, first, the power load standard sequence data needs to be classified according to the industrial structure of each geographical sub-area, considering the demand characteristics of different industries for power load, and calculating the industrial structure load electricity consumption indicator. This indicator can reflect the contribution ratio of each industry (such as manufacturing, service industry, agriculture, etc.) to the power load and can be quantified through the historical data of industrial and commercial electricity consumption. Second, the temperature fluctuation stability indicator should calculate the fluctuation range and change frequency of the temperature data, using statistical methods such as standard deviation and root mean square fluctuation to quantify the stability of temperature fluctuations, thereby obtaining the temperature stability indicator of each geographical sub-area. The energy usage indicator analyzes the energy usage ratio data, combines the energy consumption characteristics of each sub-area, and calculates the usage proportions of different energies (including clean energy and non-clean energy) in each area, thereby quantifying the energy usage indicator.

[0023] Step S3: Based on the corresponding power region characteristic indexes in the same sub-region, conduct an evaluation of the impact of regional classification on the corresponding geographical sub-regions within the target region to obtain the load-temperature non-linear impact index or load-temperature linear impact index corresponding to different category regions; obtain the response speed and change range of the load to the temperature within different category regions, and combine the load-temperature non-linear impact index or load-temperature linear impact index to conduct a load sensitivity calculation for the corresponding geographical sub-regions within the target region, so as to obtain the sensitivity coefficient of the power load of different category regions to the temperature. In the embodiment of the present invention, through the evaluation of the impact of regional classification based on the power region characteristic indexes, specifically, according to the standard sequence data of power load, the standard sequence data of temperature, and the standard sequence data of energy use, clustering analysis methods (such as K-means clustering or hierarchical clustering) can be used to classify each geographical sub-region within the target region, and regions with different temperature sensitivity categories are divided. The load-temperature non-linear impact index or linear impact index corresponding to each category of regions can be calculated by the regression analysis method. The linear regression analysis method calculates the linear response relationship between the power load and the temperature change in the region where the load change is relatively simple; the non-linear regression analysis method can handle the non-linear relationship between the power load and the temperature in the region where the load change is complex. Through the parameters of the regression model, the load-temperature non-linear impact index or load-temperature linear impact index corresponding to each region can be obtained, and further evaluate the response speed and change range of the load to the temperature. Based on the regression analysis results, the load sensitivity coefficient of each geographical sub-region can be calculated. Specifically: the load sensitivity coefficient = the ratio of the response amplitude of the power load to the temperature change to the amplitude of the temperature change multiplied by the corresponding impact index. Use these coefficients to evaluate the sensitivity of the power load of different category regions within the target region to the temperature change, and finally obtain the sensitivity coefficient of the power load of different category regions to the temperature.

[0024] Step S4: Based on the sensitivity coefficients of the power load of different category regions to the temperature, conduct power resource allocation management for the corresponding geographical sub-regions within the target region, generate power resource allocation management strategies corresponding to different temperature-sensitive regions, so as to perform the corresponding power resource optimization allocation management work.

[0025] In the embodiments of the present invention, by performing power resource allocation management according to the sensitivity coefficients of power loads in different category regions to temperature, first, through analyzing the results of regional classification impact assessment, regions with high sensitivity of power loads to temperature changes are defined as temperature-sensitive regions. For these regions, the power resource allocation management strategy should be optimized according to the load change characteristics and temperature fluctuation characteristics, and the power demands of these regions during peak temperature periods should be preferentially guaranteed. For example, the energy allocation can be dynamically adjusted through an intelligent dispatching system, and low-carbon or renewable energy sources (such as solar energy, wind energy, etc.) are preferentially dispatched to reduce the dependence on traditional fossil energy sources, and the energy efficiency and environmental protection of the system are improved. Specifically, optimization algorithms (such as linear programming, integer programming, etc.) can be used to calculate the optimal power resource allocation plan, and combined with the regional temperature change trend, power demand forecasting and load regulation are implemented for temperature-sensitive regions. By adjusting the power supply and optimizing the resource allocation, it is ensured that there will be no power supply shortage when the power load fluctuates greatly or under extreme weather conditions, thus ensuring the stability and reliability of the power system. For regions where the load is not sensitive to temperature, the power resource allocation strategy is different. The temperature sensitivity coefficients of such regions have small differences and the load growth is slow, and the impact of temperature changes on them is small. Therefore, power loss adjustment and load control measures can be implemented during high-temperature or low-temperature periods to achieve the effect of energy conservation and emission reduction, and finally the corresponding power resource optimization allocation management work is executed.

[0026] Further, step S1 includes the following steps: Step S11: Obtain the historical power load data corresponding to the target region through the power company database; Step S12: Obtain the temperature data corresponding to the target region through the meteorological monitoring station; Step S13: Obtain the geographical information data corresponding to the target region through the geographical information database, including the terrain, landform, and urban terrain distribution corresponding to the target region; Step S14: Obtain the energy usage ratio data corresponding to the target region through the power energy usage records, including the usage amounts and ratios corresponding to various types of energy; Step S15: Divide the corresponding geographical sub-regions based on the terrain, landform, and urban terrain distribution corresponding to the geographical information data, and perform sub-region data division on the historical power load data, temperature data, and energy usage ratio data corresponding to the target region to obtain the corresponding power load data, temperature data, and energy usage data under the same sub-region; synchronize the time series and preprocess the corresponding power load data, temperature data, and energy usage data under the same sub-region according to the time series to unify their corresponding data within the same time range, and clean, remove outliers, missing values, and standardize them to obtain the corresponding power load standard sequence data, temperature standard sequence data, and energy usage standard sequence data under the same sub-region.

[0027] As an embodiment of the present invention, refer to Figure 2 shown, for Figure 1 the detailed step flow diagram of step S1 in Step S11: Obtain the historical power load data corresponding to the target region through the power company database; In the embodiment of the present invention, by obtaining the historical power load data of the target region from the power company database, first, according to the geographical boundary of the target region (such as administrative region divisions such as cities, counties, and districts), obtain the corresponding historical load data through the load management system or smart meter system of the power company. These data include the specific time series of the historical load, usually in hours or days, covering the electricity consumption under different seasons and weather conditions. The data acquisition method used can be API interface, database query, or batch data export. After obtaining the data, it is necessary to ensure its time coverage, accuracy, and compatibility with other data sources. Through database management tools (such as MySQL, PostgreSQL, etc.), perform data query operations, extract and confirm the accuracy of the data, and finally obtain the historical power load data corresponding to the target region.

[0028] Step S12: Obtain the temperature data corresponding to the target region through the meteorological monitoring station; In an embodiment of the present invention, temperature data of a target area is obtained from a meteorological monitoring station or the national meteorological bureau. These data can be obtained through the API interface of the government meteorological department, an open meteorological data platform, or a regularly released meteorological report. The temperature data includes parameters such as historical daily average temperature, maximum temperature, and minimum temperature, and is usually collected by an automatic weather station. The time range of the data should be aligned with the historical power load data, and the time accuracy of the data should reach the hourly level for subsequent time series analysis. For long time series data, the temperature data is usually stored in a Geographic Information System (GIS) database, and the corresponding temperature data can be obtained using a spatial query method based on the longitude and latitude information of the target area, and finally the temperature data corresponding to the target area is obtained.

[0029] Step S13: Obtain the geographical information data corresponding to the target area through a geographical information database, including the terrain, landform, and urban terrain distribution corresponding to the target area; In an embodiment of the present invention, the geographical information data of the target area is obtained through a geographical information database. The specific content includes the terrain, landform, and urban terrain distribution of the area. The data in the geographical information database is usually obtained through remote sensing technology, satellite imagery, or on-site surveys. The data format can be vector data or raster data. First, according to the administrative boundary or specific area division of the target area, relevant topographic maps and geomorphic maps are retrieved. The data includes the spatial distribution of natural geographical features such as mountains, hills, rivers, and lakes, and also includes urban terrain information such as the elevation difference of the city and the transportation network. Because geographical factors (such as the temperature difference between mountainous areas and plains) have a significant impact on power demand, data visualization and spatial analysis are performed through GIS software (such as ArcGIS or QGIS) to accurately extract the geographical feature information within the target area, and finally the geographical information data corresponding to the target area is obtained.

[0030] Step S14: Obtain the energy usage proportion data corresponding to the target area through power energy usage records, including the usage amount and proportion corresponding to various types of energy; In an embodiment of the present invention, energy usage records of a target area are obtained through a power company or a local energy management department. The energy usage records generally include consumption data of different types of energy, such as the usage amounts of coal, electricity, natural gas, petroleum, and renewable energy (wind energy, solar energy, etc.). The data sources include energy consumption reports provided by the power company or real-time data collected from smart metering devices (such as smart electricity meters, heat meters, etc.). These data can reflect the usage proportions of various types of energy and their changing trends. Based on the statistics of the energy consumption amounts, the proportions of different energy types are obtained through the weighted average method or ratio calculation. For example, indicators such as the proportion of coal power and the proportion of clean energy. By analyzing the energy usage data, the characteristics of the target area in energy usage and its progress in the clean energy transformation can be identified, and finally, the energy usage proportion data corresponding to the target area is obtained.

[0031] Step S15: Corresponding geographical sub-regions are divided according to the terrain, landform, and urban terrain distribution corresponding to the geographical information data, and based on the geographical sub-regions, the historical power load data, temperature data, and energy usage proportion data corresponding to the target area are divided into sub-region data, obtaining the corresponding power load data, temperature data, and energy usage data under the same sub-region; by synchronizing the time series and preprocessing the corresponding power load data, temperature data, and energy usage data under the same sub-region, so as to unify their corresponding data within the same time range, and cleaning, removing outliers, missing values, and standardizing them, obtaining the corresponding power load standard sequence data, temperature standard sequence data, and energy usage standard sequence data under the same sub-region.

[0032] In an embodiment of the present invention, by analyzing the terrain, landform and urban terrain information of the target area, multiple geographical sub-areas are divided, such as mountainous areas, plain areas, industrial areas, agricultural areas and residential areas. These areas are spatially analyzed and divided through a GIS platform. The division of each geographical sub-area is based on the geographical characteristics, urban planning and distribution of regional economic activities of the area. After the division, according to the historical power load data, temperature data and energy usage data corresponding to each sub-area, data division and pairing are carried out. At this time, SQL queries or data processing libraries in Python (such as Pandas) can be used to extract the data subsets corresponding to each sub-area. Then, it is necessary to perform time series synchronization and data preprocessing on the data of different sub-areas. First, ensure that the time ranges of the power load data, temperature data and energy usage data are the same. Use the time series matching algorithm to align the data to ensure that the data items corresponding to each time point are the same. During the data cleaning process, remove outliers and missing values, and use interpolation methods (such as linear interpolation, spline interpolation, etc.) to supplement the missing values to ensure the integrity of the data. Subsequently, perform standardization processing to unify the dimensions of different data sources, so that data such as power load, temperature, and energy usage can be compared on the same scale. Finally, obtain the standard sequence data of power load, standard sequence data of temperature, and standard sequence data of energy usage in the same sub-area.

[0033] Further, the geographical sub-areas described in step S15 include mountainous areas, plain areas, industrial areas, agricultural areas and residential areas.

[0034] Further, step S2 includes the following steps: Step S21: Obtain the corresponding regional industrial structure through the geographical sub-area, and quantify the regional electricity consumption ratio of the standard sequence data of power load corresponding to the same sub-area based on the regional industrial structure, so as to obtain the electricity consumption ratio of power load corresponding to different industrial structures, and obtain the industrial structure load electricity consumption index corresponding to the same geographical sub-area; Step S22: Quantify the regional temperature fluctuation index of the standard sequence data of temperature corresponding to the same sub-area, so as to obtain the corresponding seasonal fluctuation amplitude and fluctuation frequency of temperature, and obtain the temperature fluctuation stability index corresponding to the same geographical sub-area; Step S23: Quantify the regional energy proportion index through the usage amount and proportion of various energy sources in the standard sequence data of energy usage corresponding to the same sub-area, so as to obtain the corresponding proportion of clean energy usage and non-clean energy usage, and obtain the energy usage index corresponding to the same geographical sub-area.

[0035] As an embodiment of the present invention, refer to Figure 3 shown as Figure 1Schematic diagram of the detailed step flow of step S2. In this embodiment, step S2 includes the following steps: Step S21: Obtain the corresponding regional industrial structure through the geographical sub-region, and quantify the regional electricity consumption ratio of the corresponding electricity load standard sequence data under the same sub-region based on the regional industrial structure, so as to obtain the electricity consumption ratio of the electricity load corresponding to different industrial structures, and obtain the industrial structure load electricity consumption index corresponding to the same geographical sub-region; In the embodiment of the present invention, through the geographical sub-region information of the region, the industrial structure data of each industry in the sub-region is obtained. Specifically, when operating, using the established geographical information system (GIS) or regional division database, according to the administrative division or economic activity area division, retrieve the proportion data of each industry in the sub-region. For example, through the data in the statistical bureau or relevant industry reports, analyze the output value, employment number, etc. of different industries in the region to obtain detailed information on the industrial distribution. Then, combine the industrial structure data with the corresponding electricity load standard sequence data, and by comparing the relevance between historical power consumption and the output value of each industry, obtain the electricity load ratio corresponding to different industries in the sub-region. Using statistical regression analysis methods or machine learning algorithms (such as linear regression, support vector machines, etc.), a mathematical model can be established between the electricity load data and the industrial structure data to quantify the contribution ratio of each industry to the electricity load. The result obtained is the electricity consumption ratio index of the electricity load corresponding to different industrial structures in the sub-region, and finally, the industrial structure load electricity consumption index corresponding to the same geographical sub-region is obtained.

[0036] Step S22: Quantify the regional temperature fluctuation index of the corresponding temperature standard sequence data under the same sub-region, so as to obtain the corresponding seasonal temperature fluctuation amplitude and fluctuation frequency, and obtain the temperature fluctuation stability index corresponding to the same geographical sub-region; In the embodiment of the present invention, by collecting the temperature data of the geographical sub-region, these data can usually be obtained from the meteorological bureau or relevant meteorological data service platforms. The temperature standard sequence data should include the daily temperature change data of the long-term (for example: at least 10 years) history of the region. For each sub-region, based on the temperature data, first conduct a seasonal temperature fluctuation analysis to identify the temperature fluctuation amplitude in different seasons of the region, that is, calculate the standard deviation of the temperature in different months or quarters of the region, and the difference between the maximum value and the minimum value, and then obtain the amplitude index of the temperature fluctuation. Then, based on time series analysis methods (such as Fourier transform or wavelet transform), conduct a frequency domain analysis of the temperature data to identify the frequency characteristics of the temperature fluctuation, and further quantify the frequency of the temperature fluctuation. Through these quantification indicators, the seasonal fluctuation amplitude and frequency characteristics of the regional temperature fluctuation can be obtained, and finally, the temperature fluctuation stability index of the sub-region can be obtained.

[0037] Step S23: Quantify the regional energy proportion index by using the usage amounts and proportions of various types of energy in the corresponding energy usage standard sequence data under the same sub-region, so as to obtain the corresponding proportion of clean energy usage and the proportion of non-clean energy usage, and obtain the energy usage index corresponding to the same geographical sub-region.

[0038] In the embodiment of the present invention, by collecting the energy usage data in this sub-region, especially the usage amounts and proportions of different types of energy, these data can be obtained through local energy management departments, energy statistical reports or industrial energy consumption databases. Next, according to the types of energy (such as coal, natural gas, petroleum, electricity, renewable energy, etc.), quantify the usage proportion of various types of energy in this region. For example, through statistical analysis of the energy consumption, calculate the ratio of the usage amount of each type of energy to the total energy usage amount, so as to obtain the usage proportion of various types of energy in the region. By distinguishing clean energy (such as wind energy, solar energy, water energy, etc.) from non-clean energy (such as coal, petroleum, etc.), calculate their respective proportions. In order to ensure the accuracy of the data, the weighted average method or multiple regression analysis based on energy consumption can be used to obtain more accurate usage proportions of clean energy and non-clean energy, and finally obtain the energy usage index corresponding to the same geographical sub-region.

[0039] Further, step S3 includes the following steps: Step S31: Perform principal component feature dimensionality reduction on the corresponding power region characteristic index under the same sub-region, so as to perform dimensionality reduction operation by using principal component analysis technology, and extract the index corresponding to the main characteristics of the geographical sub-region, and obtain the power region dimensionality reduction index corresponding to the same sub-region; In the embodiment of the present invention, by selecting the power region characteristic indexes in the same geographical sub-region, these indexes include but are not limited to the industrial structure load power consumption index, the temperature fluctuation stability index, and the energy usage index, etc. Principal component analysis (PCA) is applied to these multi-dimensional data sets, aiming to extract a group of fewer indexes representing the core of the regional characteristics. Specifically, when implementing, first standardize the power region characteristic indexes so that their mean is 0 and the standard deviation is 1, to ensure that each index participates in the analysis on the same scale. Then, calculate the covariance matrix between the indexes, and through eigenvalue decomposition or singular value decomposition technology, extract the corresponding principal components. Each principal component represents a main change direction in the regional characteristics. Sort according to the contribution rate, and retain the first few principal components whose cumulative contribution rate reaches more than 80%. These principal components will be used as the characteristic indexes after dimensionality reduction of the power region, reflecting the main influencing factors of power demand and climate change in the geographical sub-region, and finally obtaining the power region dimensionality reduction index corresponding to the same sub-region.

[0040] Step S32: Perform regional characteristic similarity measurement on the reduced-dimension indicators of the corresponding power regions under each sub-region to obtain the similarity between the characteristic indicators under each sub-region; In the embodiment of the present invention, by calculating the similarity between the reduced-dimension indicators of the power regions within different geographical sub-regions, first, use the Euclidean distance, cosine similarity or other suitable similarity measurement methods to measure the similarity degree between each geographical sub-region in the principal component space after dimension reduction. Through these similarity measurement methods, a similarity matrix between each sub-region can be obtained. Each element in the matrix represents the characteristic similarity of the corresponding sub-region. In specific implementation, for each pair of sub-regions, calculate the distance or angle between their reduced-dimension indicator vectors to obtain a value between 0 and 1, where 1 represents complete similarity and 0 represents complete dissimilarity. By performing this process on all sub-regions of the entire region, the regional characteristic similarity between each sub-region can be further analyzed, and finally the similarity between the characteristic indicators under each sub-region can be obtained.

[0041] Step S33: Classify the corresponding geographical sub-regions in the target region based on the similarity between the characteristic indicators under each sub-region. If the similarity between the characteristic indicators under each sub-region is greater than or equal to 90%, then classify the corresponding geographical sub-region as a complex load change region; if the similarity between the characteristic indicators under each sub-region is less than 90%, then classify the corresponding geographical sub-region as another relatively simple load change region; In the embodiment of the present invention, through the similarity matrix of the characteristic indicators of each sub-region obtained previously, perform regional characteristic classification. If the similarity between the reduced-dimension characteristic indicators of a certain sub-region is greater than or equal to 90%, it indicates that the relationship between the power load change and the temperature change in this sub-region is relatively stable and the load change is relatively complex. At this time, classify this sub-region as a "complex load change region". On the contrary, if the similarity is less than 90%, the power load change in this sub-region is relatively simple and is classified as a "relatively simple load change region". In implementation, use clustering algorithms (such as K-means, hierarchical clustering, etc.) to classify each sub-region according to the similarity, and set a threshold to ensure the accuracy of the classification. Further, by statistically analyzing and verifying the load data of each type of region, ensure the effectiveness and accuracy of the classification results.

[0042] Step S34: Use a non-linear model to evaluate the influence of the corresponding power load and temperature change in the complex load change region to obtain the load-temperature non-linear influence index corresponding to the complex load category region; use a linear regression model to evaluate the influence of the corresponding power load and temperature change in the relatively simple load change region to obtain the load-temperature linear influence index corresponding to the simple load category region; In the embodiments of the present invention, for the "complex load change area", a non-linear model (such as support vector machine regression, neural network, etc.) is used to evaluate the impact of the power load and temperature change in this area. In specific implementation, first, historical power load data and corresponding temperature data in this area are collected. Then, the non-linear regression technology is used to train the model, taking the power load and temperature as input and output for learning. After training, the model can output the response relationship of the power load under temperature change, considering the non-linear relationship between the load and temperature, which is usually analyzed through polynomial regression or other non-linear models. Its calculation formula can be expressed as: Non-linear impact index = , where: is the regression coefficient (usually obtained by fitting historical data), is the temperature, is the order of the non-linear polynomial, which can be selected according to the complexity of the data, so as to generate the load-temperature non-linear impact index. For the "relatively simple load change area", a linear regression model is used for impact evaluation. By establishing a linear relationship model between the load and temperature, the load-temperature linear impact index of this type of area is obtained, that is, the slope of the load and temperature in linear regression. The specific steps include data preprocessing, feature selection, model training, and model evaluation and optimization, to obtain the impact indexes of various areas, and finally obtain the load-temperature non-linear impact index and the load-temperature linear impact index.

[0043] Step S35: Obtain the response speed and change range of the load to the temperature in different category areas, and combine the load-temperature non-linear impact index or the load-temperature linear impact index to calculate the load sensitivity of the corresponding geographical sub-areas in the target area, so as to obtain the sensitivity coefficient of the power load to the temperature in different category areas.

[0044] In the embodiments of the present invention, by obtaining the response speed and change amplitude of various regional loads to temperature changes, and combining the non-linear or linear influence index in the foregoing steps for sensitivity calculation. First, calculate the response speed of each sub-region load to temperature changes, which can be achieved by performing differential analysis on the load and temperature data to obtain the load change rate corresponding to the temperature change. Then, combined with the load-temperature non-linear influence index or linear influence index, further calculate the load sensitivity coefficient of each sub-region. In this process, in the area with complex load changes, quantitative calculation is performed by combining the corresponding response speed, temperature change amplitude, temperature change value, and load-temperature non-linear influence index, while in the area with relatively simple load changes, calculation is performed by combining the corresponding response speed, temperature change amplitude, temperature change value, and load-temperature linear influence index, ensuring that the sensitivity calculation results accurately reflect the power load response characteristics of each region under temperature changes, and finally obtaining the sensitivity coefficients of different categories of regional power loads to temperature.

[0045] Further, step S35 includes the following steps: Step S351: Conduct response speed statistical analysis through the corresponding power loads and temperature changes in different categories of regions to obtain the response speed of the loads in different categories of regions to temperature; In the embodiments of the present invention, by collecting the power load and temperature change data of different categories of regions, the data can be sourced from real-time meteorological monitoring and power load data acquisition systems. The classification of regions generally includes urban areas, suburbs, and rural areas, etc. By selecting the load data and temperature change data for a specific time period, calculate the correlation between the power load and temperature change within each category of region. Specifically, a time series analysis method can be used to analyze the ratio of the temperature change value and the response time difference between the load and temperature, thereby obtaining the response speed of the loads in different categories of regions to temperature changes. In the statistical analysis, a regression analysis method can be used to establish a quantitative relationship between the load and temperature changes, so as to determine the response speed of different categories of regions at different time scales, and finally obtain the response speed of the loads in different categories of regions to temperature.

[0046] Step S352: Conduct temperature change trend analysis between the corresponding power loads and temperature changes in different categories of regions to obtain the corresponding temperature change trend lines under the power load conditions in different categories of regions; In an embodiment of the present invention, by comparing the power load data of different category regions with the temperature data, and analyzing the temperature change trend based on the load levels of different category regions. For each category region, according to the collected temperature data, a linear or non-linear regression model is used to fit the trend line of temperature change. Specifically, methods such as the least squares method and the moving average method can be adopted to fit the temperature data, so as to obtain the trend line of temperature change under different power load conditions. Through trend analysis, it is determined whether there are significant differences in the temperature change trends during the load peak period and the trough period, thereby revealing the influence mode of different regional loads on temperature change. Finally, the corresponding temperature change trend lines under the power load conditions in different category regions are obtained.

[0047] Step S353: Calculate the change amplitude of the corresponding temperature change based on the temperature change trend lines corresponding to different category regions under the power load conditions, so as to obtain the change amplitude of the load on temperature in different category regions; In an embodiment of the present invention, by according to the previously obtained temperature change trend line, calculate the amplitude of the temperature change with the load within a specific time range. For example, by selecting a cycle of one day or one week, record the change data of the power load, and combine it with the temperature trend line to calculate the amplitude of the temperature during the load change period. The calculation formula can be obtained by dividing the temperature change amount by the load change amount to get a change rate. For each category region, this process will provide quantitative data for the temperature change amplitude under different load levels. It should be noted that the change amplitude of the temperature is not only directly affected by the power load, but also regulated by external factors such as weather and terrain. Therefore, these factors' possible interference with the temperature change amplitude should be comprehensively considered during the calculation process. In addition, by performing multiple calculations for multiple time periods, the stability and volatility of the temperature change amplitude can be analyzed, and finally the change amplitude of the load on temperature in different category regions can be obtained.

[0048] Step S354: Based on the response speed and change amplitude of the load on temperature in different category regions, and combined with the load-temperature non-linear influence index or the load-temperature linear influence index, use the load-temperature sensitivity calculation formula to calculate the load sensitivity of the corresponding geographical sub-regions in the target region, so as to obtain the sensitivity coefficients of the power load on temperature in different category regions.

[0049] In the embodiments of the present invention, in a region with complex load changes, quantitative calculations are performed by combining the corresponding response speed, temperature change range, temperature change value, and load-temperature non-linear influence index. In a region with relatively simple load changes, calculations are performed by combining the corresponding response speed, temperature change range, temperature change value, and load-temperature linear influence index. The load-temperature non-linear influence index takes into account the complex influence mode of load changes on temperature changes and is applicable to calculations under high load and extreme temperature conditions. The load-temperature linear influence index is applicable to regions where the load and temperature changes show a linear relationship. On this basis, in combination with the load-temperature sensitivity calculation formula, the sensitivity of geographical sub-regions within the target region is calculated. The calculation formula includes multiple parameters such as the range of load changes and the range of temperature changes. By calculating different regional sub-regions, the load sensitivity coefficient of each region is obtained, and finally, the sensitivity coefficient of the power load in different categories of regions to temperature is obtained. In addition, this load-temperature sensitivity calculation formula can also use any temperature-sensitive detection algorithm in the field to replace the process of load sensitivity calculation, and is not limited to this load-temperature sensitivity calculation formula.

[0050] Further, the load-temperature sensitivity calculation formula described in step S354 is specifically: Region with complex load changes: ; Region with relatively simple load changes: ; In the formula, is the sensitivity coefficient of the regional power load to temperature, is the response speed of the load in the region to temperature, is the change range of the load in the region to temperature, is the corresponding temperature change parameter within the geographical sub-region, is the load-temperature non-linear influence index, is the load-temperature linear influence index.

[0051] The present invention has obtained a load temperature sensitivity calculation formula through the use of a specific mathematical model and verification, which is used to calculate the load sensitivity of corresponding geographical sub-regions within the target area. This load temperature sensitivity calculation formula provides a way to quantitatively measure how electrical load responds to temperature changes through a mathematical model, which helps to understand the impact of temperature changes on power demand from a system level, especially in different regions or different types of geographical areas. By adopting two different formulas (nonlinear formula for complex regions and linear formula for simple regions), the different response characteristics of electrical loads to temperature in different regions can be more accurately reflected. For example, in complex regions, due to the more complex relationship between load and temperature changes, the nonlinear formula can better reflect this; while in simple regions, the relationship between temperature and electrical load is relatively direct, and the linear formula is more applicable. By calculating the sensitivity coefficients of different regions, power load forecasting and dispatching optimization of the power system can be better carried out. Especially in areas with large temperature changes, the sensitivity coefficients can help decision-makers understand in which regions the impact of temperature changes on load is more significant, so as to take targeted measures, such as reasonably allocating energy resources in high-temperature or cold weather to avoid overloading of power supply. By using the load-temperature nonlinear influence index and the load-temperature linear influence index, the calculation process can be further optimized to make it closer to the actual climate conditions and power demand response. These indexes can be adjusted according to different environmental conditions or historical data, so as to improve the accuracy and adaptability of the model. To sum up, this formula fully considers the sensitivity coefficient of regional electrical load to temperature , the response speed of the load within the region to temperature , the change range of the load within the region to temperature , the corresponding temperature change parameters within the geographical sub-region , the load-temperature nonlinear influence index , the load-temperature linear influence index , so as to combine the corresponding response speed , temperature change range , temperature change value , and the load-temperature nonlinear influence index for quantitative calculation to form a functional relationship , while in the region with relatively simple load changes, by combining the corresponding response speed , temperature change range , temperature change value , and the load-temperature linear influence index for calculation to form another functional relationship , this formula can implement the calculation process of the load sensitivity of the corresponding geographical sub - regions within the target area, thus improving the accuracy and applicability of the load - temperature sensitivity calculation formula.

[0052] Further, step S4 includes the following steps: Step S41: Based on the sensitivity coefficients of the power loads of different category regions to temperature, conduct regional sensitive statistical feature analysis on the corresponding geographical sub - regions within the target area to obtain the mean, variance, and peak statistical features corresponding to the temperature sensitivity coefficients of different category regions at different time periods; In the embodiment of the present invention, by obtaining the power load data and corresponding temperature data of different geographical sub - regions within the target area, these data are divided into different categories according to the regions, combined with the actual geographical features and climate conditions of the regions, and the previously quantified load - temperature sensitivity coefficients are extracted. Then, by calculating the mean, variance, and peak statistical features of the temperature sensitivity coefficients of each geographical sub - region at different time periods, the temperature sensitivity characteristics of each geographical sub - region are analyzed in detail. The mean reflects the load change trend of the geographical area at different temperatures; the variance is used to measure the influence of temperature changes on the load fluctuations at different time periods; the peak represents the extreme situation of the load response when the temperature changes in the region. These statistical features provide basic data for subsequent analysis. The specific operation can be carried out by using statistical analysis tools such as MATLAB or the Pandas library in Python, combined with the time - series data of temperature and load for calculation, and finally obtain the mean, variance, and peak statistical features corresponding to the temperature sensitivity coefficients of different category regions at different time periods.

[0053] Step S42: Based on the mean, variance, and peak statistical features corresponding to the temperature sensitivity coefficients of different category regions at different time periods, conduct temperature - sensitive difference analysis on the corresponding geographical sub - regions within the target area to obtain the load - temperature sensitivity differences corresponding to different category regions; In the embodiments of the present invention, by using the statistical characteristic data of temperature sensitivity coefficients in different regions obtained previously, further analysis of temperature sensitivity differences is carried out. According to the mean value, variance and peak value of the sensitivity coefficients of each geographical sub-region, the degree of difference between regions is calculated, and special attention is paid to the regions with large differences in sensitivity coefficients. By comparing the temperature sensitivity data of different categories of regions, the differences in load response of different regions under their respective temperature conditions are analyzed, and then the regions where temperature changes have a significant impact on power load are identified. In actual operation, methods such as cluster analysis or principal component analysis can be used to process the data, so as to clarify the temperature sensitivity differences of different geographical regions. This operation can be carried out by using the scikit-learn library in Python for cluster analysis, or by using the PCA function of MATLAB for principal component analysis to identify temperature-sensitive regions and non-sensitive regions, and finally obtain the load temperature sensitivity differences corresponding to different categories of regions.

[0054] Step S43: Based on the load temperature sensitivity differences corresponding to different categories of regions, power resource allocation management is carried out for the corresponding geographical sub-regions within the target region, and power resource allocation management strategies corresponding to different temperature-sensitive regions are generated to perform the corresponding power resource optimal allocation management work.

[0055] In the embodiments of the present invention, according to the analysis results of the temperature sensitivity differences obtained from previous analyses, power resource allocation management strategies for different geographical sub-regions within the target area are determined. If the temperature sensitivity coefficient differences in a certain geographical sub-region are large and the load growth is rapid, then this region is planned as a region where the load is sensitive to temperature. Such regions will be significantly affected by extreme temperature changes and experience a sharp increase in load. Therefore, it is necessary to rationally allocate power resources for optimal management. When allocating power resources, the limitations of the power grid transmission capacity and the output of power generation equipment need to be considered, and by using the simulated annealing algorithm, combined with the actual constraints of the power system, such as grid load and power station output, etc., a global optimization search is carried out to find the optimal power resource allocation plan. The simulated annealing algorithm gradually approaches the optimal solution by simulating the physical annealing process, jumps out of the local optimal solution through multiple iterations, and finally reaches the global optimal. When implementing, the SciPy library in Python can be used to implement the simulated annealing algorithm and optimize power resources in combination with the grid constraints. For regions where the load is not sensitive to temperature, the power resource allocation strategy is different. The temperature sensitivity coefficient differences in such regions are small and the load growth is slow, and the temperature change has little impact on them. Therefore, power loss adjustment and load control measures can be implemented during high-temperature or low-temperature periods to achieve the effect of energy conservation and emission reduction. In these regions, load management focuses on adjusting power loss and optimizing load control to achieve the economical use of power resources. The specific operation can adopt demand response management (DRM) technology to dynamically adjust the power load within the region according to the actual load demand and temperature change, thereby optimizing resource allocation and improving the overall operating efficiency of the power system, and finally implementing the corresponding optimized power resource allocation management work.

[0056] Further, the power resource allocation management strategies corresponding to different temperature-sensitive regions in step S43 are specifically as follows: If it is determined that the sensitivity coefficient differences within the corresponding geographical sub-region are large and the load growth is fast, then it is planned as a region where the load is sensitive to temperature to set the corresponding constraints for power resource allocation, including the limitations of the power grid transmission capacity and the output of power generation equipment, and the simulated annealing algorithm is used to find the optimal power resource allocation result while meeting the constraints; if it is determined that the sensitivity coefficient differences within the corresponding geographical sub-region are small and the load growth is slow, then it is planned as a region where the load is not sensitive to temperature to implement power loss adjustment and load control measures during high-temperature or low-temperature periods, thereby realizing the optimized utilization of power resources corresponding to energy conservation and emission reduction.

[0057] Further, the present invention also provides a load impact temperature sensitivity analysis system based on regional characteristic analysis for performing the load impact temperature sensitivity analysis method based on regional characteristic analysis as described above. The load impact temperature sensitivity analysis system based on regional characteristic analysis includes: The regional data time series synchronization module is used to obtain the historical power load data, temperature data, geographical information data, and energy usage ratio data corresponding to the target region, and perform time series synchronization preprocessing on the historical power load data, temperature data, and energy usage ratio data corresponding to the target region based on the geographical sub-regions corresponding to the geographical information data and in accordance with the time series, so as to obtain the power load standard sequence data, temperature standard sequence data, and energy usage standard sequence data corresponding to the same sub-region; The regional characteristic index quantification module is used to quantify the regional characteristic indexes of the power load standard sequence data, temperature standard sequence data, and energy usage standard sequence data corresponding to the same sub-region, so as to obtain the power regional characteristic indexes corresponding to the same sub-region, including the industrial structure load electricity consumption index, temperature fluctuation stability index, and energy usage index corresponding to the same geographical sub-region; The regional load sensitivity accounting module is used to conduct an impact assessment of regional classification on the geographical sub-regions corresponding to the target region based on the power regional characteristic indexes corresponding to the same sub-region, so as to obtain the load-temperature non-linear impact index or load-temperature linear impact index corresponding to different category regions; obtain the response speed and change range of the load to the temperature in different category regions and combine the load-temperature non-linear impact index or load-temperature linear impact index to conduct load sensitivity accounting on the corresponding geographical sub-regions within the target region, so as to obtain the sensitivity coefficients of the power load to the temperature in different category regions; The power resource allocation and management module is used to conduct power resource allocation and management on the corresponding geographical sub-regions within the target region based on the sensitivity coefficients of the power load to the temperature in different category regions, generate power resource allocation and management strategies corresponding to different temperature-sensitive regions, so as to perform corresponding power resource optimal allocation and management work.

[0058] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application document are intended to be encompassed within the present invention.

[0059] The above description is only the specific implementation manners of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for analyzing the sensitivity of load impact on temperature based on regional characteristic analysis, characterized in that, It includes the following steps: Step S1: Obtain the historical power load data, temperature data, geographical information data, and energy usage ratio data corresponding to the target area, and perform time-series synchronization preprocessing on the historical power load data, temperature data, and energy usage ratio data corresponding to the target area based on the geographical sub-areas corresponding to the geographical information data and in accordance with the time series, so as to obtain the corresponding power load standard sequence data, temperature standard sequence data, and energy usage standard sequence data in the same sub-area; Step S2: Quantify the regional characteristic indicators of the power load standard sequence data, temperature standard sequence data, and energy usage standard sequence data corresponding to the same sub-area to obtain the corresponding power regional characteristic indicators in the same sub-area, including the industrial structure load power consumption indicator, temperature fluctuation stability indicator, and energy usage indicator corresponding to the same geographical sub-area; Step S3: Based on the power regional characteristic indicators corresponding to the same sub-area, evaluate the regional classification impact on the geographical sub-areas corresponding to the target area to obtain the load-temperature non-linear impact index or load-temperature linear impact index corresponding to different category areas; Obtain the response speed and change range of the load to the temperature in different category areas and combine the load-temperature non-linear impact index or load-temperature linear impact index to calculate the load sensitivity of the corresponding geographical sub-areas in the target area, and obtain the sensitivity coefficient of the power load to the temperature in different category areas; Step S4: Based on the sensitivity coefficient of the power load to the temperature in different category areas, manage the power resource allocation for the corresponding geographical sub-areas in the target area, generate the power resource allocation management strategy corresponding to different temperature-sensitive areas, so as to perform the corresponding power resource optimization allocation management work.

2. The method for analyzing the sensitivity of load impact on air temperature based on regional characteristic analysis according to claim 1, wherein Step S1 includes the following steps: Step S11: Obtain the historical power load data corresponding to the target area through the power company database; Step S12: Obtain the temperature data corresponding to the target area through the meteorological monitoring station; Step S13: Obtain the geographical information data corresponding to the target area through the geographical information database, including the terrain, landform, and urban terrain distribution corresponding to the target area; Step S14: Obtain the energy usage ratio data corresponding to the target area through the power energy usage record, including the usage amount and ratio corresponding to various types of energy; Step S15: Divide the corresponding geographical sub-regions according to the terrain, landform and urban terrain distribution corresponding to the geographical information data, and perform sub-region data division on the historical power load data, temperature data and energy usage ratio data corresponding to the target region to obtain the corresponding power load data, temperature data and energy usage data under the same sub-region; Synchronize the time series and preprocess the corresponding power load data, temperature data and energy usage data under the same sub-region to unify their corresponding data within the same time range, and clean, remove outliers, missing values and standardize them to obtain the corresponding power load standard sequence data, temperature standard sequence data and energy usage standard sequence data under the same sub-region.

3. The method for analyzing the sensitivity of load impact on air temperature based on regional characteristic analysis according to claim 2, wherein The geographical sub-regions described in Step S15 include mountainous areas, plain areas, industrial areas, agricultural areas and residential areas.

4. The method for analyzing the sensitivity of load impact on air temperature based on regional characteristic analysis according to claim 1, wherein Step S2 includes the following steps: Step S21: Obtain the corresponding regional industrial structure through the geographical sub-region, and quantify the regional electricity consumption ratio of the corresponding power load standard sequence data under the same sub-region based on the regional industrial structure to obtain the power load electricity consumption ratio corresponding to different industrial structures, and obtain the industrial structure load electricity consumption index corresponding to the same geographical sub-region; Step S22: Quantify the regional temperature fluctuation index of the corresponding temperature standard sequence data under the same sub-region to obtain the corresponding seasonal temperature fluctuation amplitude and fluctuation frequency, and obtain the temperature fluctuation stability index corresponding to the same geographical sub-region; Step S23: Quantify the regional energy proportion index through the usage amount and proportion of various energy sources in the corresponding energy usage standard sequence data under the same sub-region to obtain the corresponding clean energy usage proportion and non-clean energy usage proportion, and obtain the energy usage index corresponding to the same geographical sub-region.

5. The method for analyzing the sensitivity of load impact on air temperature based on regional characteristic analysis according to claim 1, wherein Step S3 includes the following steps: Step S31: Perform principal component feature dimensionality reduction on the corresponding power regional characteristic indicators under the same sub-region, perform dimensionality reduction operations using principal component analysis technology, and extract the indicators representing the main characteristics of the geographical sub-region to obtain the corresponding power regional dimensionality reduction indicators under the same sub-region; Step S32: Perform regional characteristic similarity measurement between the corresponding power regional dimensionality reduction indicators under each sub-region to obtain the similarity between the characteristic indicators under each sub-region; Step S33: Classify the geographical sub-regions corresponding to the target region based on the similarity between the characteristic indicators under each sub-region. If the similarity between the characteristic indicators under each sub-region is greater than or equal to 90%, the corresponding geographical sub-region is classified as a complex load change region; if the similarity between the characteristic indicators under each sub-region is less than 90%, the corresponding geographical sub-region is classified as a relatively simple load change region of another type; Step S34: Use a non-linear model to conduct a complex area impact assessment on the corresponding power load and temperature change within the complex load change area to obtain the load-temperature non-linear impact index corresponding to the complex load category area; use a linear regression model to conduct a simple area impact assessment on the corresponding power load and temperature change within the relatively simple load change area to obtain the load-temperature linear impact index corresponding to the simple load category area. Step S35: Obtain the response speed and change range of the load to temperature within different category areas, and combine the load-temperature non-linear impact index or the load-temperature linear impact index to conduct load sensitivity accounting for the corresponding geographical sub-areas within the target area, so as to obtain the sensitivity coefficients of the power loads in different category areas to temperature.

6. The method for analyzing the sensitivity of load impact on air temperature based on regional characteristic analysis according to claim 5, wherein Step S35 includes the following steps: Step S351: Conduct a statistical analysis of the response speed through the corresponding power load and temperature change within different category areas to obtain the response speed of the load to temperature within different category areas. Step S352: Conduct a temperature change trend analysis between the corresponding power load and temperature change within different category areas to obtain the temperature change trend line corresponding to the power load condition within different category areas. Step S353: Calculate the change range of the temperature change based on the temperature change trend line corresponding to the power load condition within different category areas to obtain the change range of the load to temperature within different category areas. Step S354: Based on the response speed and change range of the load to temperature within different category areas, and combining the load-temperature non-linear impact index or the load-temperature linear impact index, use the load-temperature sensitivity calculation formula to conduct load sensitivity accounting for the corresponding geographical sub-areas within the target area, so as to obtain the sensitivity coefficients of the power loads in different category areas to temperature.

7. The method for analyzing the sensitivity of load impact on air temperature based on regional characteristic analysis according to claim 6, characterized in that The load-temperature sensitivity calculation formula described in Step S354 is specifically: Complex load change area: ; Region with relatively simple load changes: ; In the formula, is the sensitivity coefficient of the regional electric load to temperature, is the response speed of the load in the region to temperature, is the change range of the load in the region to temperature, is the corresponding temperature change parameter in the geographical sub-region, is the load-temperature non-linear influence index, is the load-temperature linear influence index.

8. The method for analyzing the sensitivity of load impact on air temperature based on regional characteristic analysis according to claim 1, wherein Step S4 includes the following steps: Step S41: Conduct a regional sensitive statistical feature analysis on the corresponding geographical sub-areas within the target area based on the sensitivity coefficients of the power loads in different category areas to temperature to obtain the mean value, variance, and peak statistical features corresponding to the temperature sensitive coefficients in different category areas at different time periods. Step S42: Conduct a temperature sensitive difference analysis on the corresponding geographical sub-areas within the target area based on the mean value, variance, and peak statistical features corresponding to the temperature sensitive coefficients in different category areas at different time periods to obtain the load-temperature sensitivity differences corresponding to different category areas. Step S43: Conduct power resource allocation management on the corresponding geographical sub-areas within the target area based on the load-temperature sensitivity differences corresponding to different category areas, generate power resource allocation management strategies corresponding to different temperature sensitive areas, so as to execute the corresponding power resource optimization allocation management work.

9. The method for analyzing the sensitivity of load impact on air temperature based on regional characteristic analysis according to claim 8, characterized in that, The power resource allocation management strategies corresponding to different temperature-sensitive regions described in step S43 are specifically as follows: If it is determined that the sensitivity coefficient differences within the corresponding geographical sub-region are large and the load growth is fast, then it is planned as a load temperature-sensitive region to set the corresponding constraint conditions for power resource allocation, including grid transmission capacity limits and power generation equipment output limits, and the simulated annealing algorithm is used to find the optimal power resource allocation result while satisfying the constraint conditions; if it is determined that the sensitivity coefficient differences within the corresponding geographical sub-region are small and the load growth is slow, then it is planned as a load non-temperature-sensitive region to implement power loss adjustment and load control measures during high or low temperature periods, so as to achieve the optimal utilization of power resources and energy conservation and emission reduction.

10. A load impact temperature sensitivity analysis system based on regional characteristic analysis, characterized in that, For implementing the load impact temperature sensitivity analysis method based on regional characteristic analysis as described in claim 1, the load impact temperature sensitivity analysis system based on regional characteristic analysis includes: A regional data time series synchronization module, which is used to obtain the historical power load data, temperature data, geographical information data, and energy usage ratio data corresponding to the target region, and perform time series synchronization preprocessing on the historical power load data, temperature data, and energy usage ratio data corresponding to the target region based on the geographical sub-regions corresponding to the geographical information data and in accordance with the time series, so as to obtain the power load standard sequence data, temperature standard sequence data, and energy usage standard sequence data corresponding to the same sub-region; A regional characteristic index quantification module, which is used to quantify the regional characteristic indexes of the power load standard sequence data, temperature standard sequence data, and energy usage standard sequence data corresponding to the same sub-region, so as to obtain the power regional characteristic indexes corresponding to the same sub-region, including the industrial structure load electricity consumption index, temperature fluctuation stability index, and energy usage index corresponding to the same geographical sub-region; A regional load sensitivity accounting module, which is used to conduct a regional classification impact assessment on the geographical sub-regions corresponding to the target region based on the power regional characteristic indexes corresponding to the same sub-region to obtain the load-temperature non-linear impact index or load-temperature linear impact index corresponding to different category regions; obtain the response speed and change range of the load to temperature within different category regions and combine the load-temperature non-linear impact index or load-temperature linear impact index to conduct load sensitivity accounting on the corresponding geographical sub-regions within the target region, so as to obtain the sensitivity coefficients of the power loads in different category regions to temperature; A power resource allocation management module, which is used to conduct power resource allocation management on the corresponding geographical sub-regions within the target region based on the sensitivity coefficients of the power loads in different category regions to temperature, generate power resource allocation management strategies corresponding to different temperature-sensitive regions, and perform corresponding optimal power resource allocation management work.

Images