Regional economic development prediction method based on electric power big data

Abstract

The invention relates to the technical field of economic prediction, and comprises a regional economic development prediction method based on electric power big data, and the method comprises the following steps: setting a fixed time window, obtaining the power load of a rural enterprise, carrying out the statistics of the power consumption behaviors of rural residents, analyzing the power use mode of the rural residents, and generating the characteristic data of the power load of the rural residents. According to the invention, based on the power consumption data, the rural economic development prediction can capture the dynamic change of power use, construct an economic stability evaluation system, ensure that the analysis of the load fluctuation and recovery capability of a rural enterprise is more accurate, and enable the prediction to cover different industrial characteristics and periodic fluctuation. And an economic growth trend deviation value is calculated, so that economic trend prediction can be combined with regional power operation characteristics, a potential signal reflecting rural economic growth or decline, an economically fragile industry is identified, the abnormal amplitude of power load change of the economically fragile industry is analyzed, the real-time performance and the refinement degree of prediction are enhanced, and the method accords with the nonlinear growth characteristics of rural economy.

Description

Technical Field

[0001] The present invention relates to the technical field of economic forecasting, and particularly to a method for forecasting regional economic development based on big data of electric power. Background Art

[0002] The technical field of economic forecasting includes using means such as historical data, statistical models, machine learning methods, etc. to analyze and predict future economic trends. The core contents include trend analysis based on macroeconomic indicators, segmented market forecasting based on industry data, and economic development evaluation based on regional data. In this field, common data sources include economic statistical data, enterprise operation data, financial market data, and other relevant economic indicators. The analysis methods usually involve time series analysis, regression analysis, causal relationship modeling, etc., aiming to make scientific predictions about future economic conditions through data mining and modeling methods. With the development of big data technology, economic forecasting has gradually incorporated more heterogeneous data sources, including social media, Internet transaction records, power consumption data, etc., which has improved the accuracy and applicability of the forecasting.

[0003] Among them, the method for forecasting regional economic development based on big data of electric power refers to using power consumption data to analyze and predict the economic development status of a specific region. Regarding the correlation between regional economic activities and power consumption, it covers aspects such as data collection, feature extraction, construction of economic indicators, and prediction of economic development trends. In the data collection link, indicators such as enterprise power consumption, residential power consumption, and industry power consumption structure are recorded. In the feature extraction link, information such as time series change features, peak-valley fluctuation features, and industry power consumption ratio is extracted from the power data. The construction of economic indicators is based on the corresponding relationship between power consumption characteristics and traditional economic indicators to establish an index system reflecting regional economic activities. In the economic development trend prediction link, regression analysis methods are used to model the power consumption data and multivariate analysis is combined with regional economic data to obtain the prediction results of future economic development levels.

[0004] In the existing rural economic forecasting process, it mainly relies on traditional macroeconomic data, industry statistical data, and financial market data, making it difficult to comprehensively cover the real-time changes in the rural economy. The data sources mainly focus on historical statistics, making it difficult to quickly capture the actual economic activities of enterprises and residents, resulting in a relatively slow response of the forecast to short-term fluctuations. Time series analysis and regression models have large errors in dealing with seasonal fluctuations and sudden economic changes. Especially in the rural economy, affected by factors such as the agricultural cycle and industrial adjustment, and at the same time, the construction of economic indicators is relatively single and fails to directly depict the changes in industrial activities by combining power consumption data, making the forecasting model insufficient in identifying economic stability and growth trends. The classification of industry data is based on traditional standards and is difficult to adapt to the development of emerging rural industries, restricting the applicability of the forecasting model to the characteristic economy. The modeling of economic development trends mainly relies on past economic data and lacks sensitivity to short-term market mutations, resulting in insufficient reliability of the forecast results in dealing with economic uncertainties. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art and propose a method for predicting regional economic development based on big power data.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions: A method for predicting regional economic development based on big power data, comprising the following steps: S1: Set a fixed time window to obtain the electricity load of rural enterprises, count the electricity consumption behaviors of rural residents, analyze the electricity usage patterns of rural residents, and generate rural electricity load characteristic data; S2: Based on the rural electricity load characteristic data, calculate the adjustment amplitude of the electricity load of rural enterprises, the change rate of the electricity demand of rural enterprises, and the load recovery rate, analyze the electricity load recovery ability of rural enterprises, and generate a rural economic stability index through weighted calculation; S3: According to the rural electricity load characteristic data, determine the seasonal electricity consumption characteristics of rural enterprises, count the electricity consumption characteristics of rural residents' production and living, analyze the periodic change trend of electricity consumption, and generate rural industrial electricity usage pattern characteristic data; S4: According to the rural economic stability index and the rural industrial electricity usage pattern characteristic data, determine the change characteristics of rural power operation, calculate the offset value of the rural economic growth trend, and generate a prediction result of the rural economic growth trend; S5: According to the prediction result of the rural economic growth trend, calculate the abnormal adjustment amplitude of the electricity load of vulnerable rural industries, analyze the offset situation of the electricity load change of rural industries, and generate a rural economic warning index.

[0007] As a further solution of the present invention, the rural power load characteristic data includes the current power load value, the power load change range, the change rate of electricity demand, the electricity consumption behavior of rural residents, the electricity usage pattern of rural residents, the power supply stability, and the change range of power supply frequency. The rural economic stability index includes the load adjustment range, the change rate of electricity demand, the load recovery rate, and the power load recovery ability of rural enterprises. The rural industrial electricity usage pattern characteristic data includes the equipment operation duration, the power fluctuation range, the seasonal electricity usage characteristics of rural enterprises, the electricity usage change situation during high load periods, the electricity usage characteristics of rural residents' production and living, and the periodic change trend of electricity usage. The predicted result of the rural economic growth trend includes the electricity adjustment range of rural enterprises, the seasonal load change trend of rural industries, the change characteristics of rural power operation, the deviation value of rural economic growth trend, the economic cycle fluctuation characteristics of rural industries, and the economic operation trend of industries. The rural economic warning indicators include the rural economic operation fluctuation threshold, the rural industries with economic fluctuations exceeding the preset threshold, the abnormal amplitude of power load adjustment of rural economic vulnerable industries, the abnormal load change rate, and the deviation of rural industrial power load changes.

[0008] As a further solution of the present invention, the specific steps for setting a fixed time window to obtain the electricity load of rural enterprises, counting the electricity consumption behavior of rural residents, analyzing the electricity usage pattern of rural residents, and generating rural power load characteristic data are as follows: S111: Set a fixed time window, collect the current power load value, the power load change range, and the change rate of electricity demand, obtain the electricity consumption data of rural residents, sort out the electricity consumption data and calculate the average value of the load change amount and the demand change rate at different time points to obtain the basic electricity consumption data of rural residents; S112: Based on the basic electricity consumption data of rural residents, count the electricity usage fluctuations of rural residents during different time periods, calculate the electricity demand fluctuation range, analyze the residential electricity concentration during different time periods, calculate the peak-valley difference of electricity demand for each time period, and use the formula: ; Calculate the electricity demand dispersion of rural residents , obtain the electricity demand dispersion of rural residents, where represents the power load value at the th time point, represents the average power load within the time window, represents the number of time points counted, represents the change rate of electricity demand at the th time point, represents the average change rate of electricity demand within the time window; S113: Analyze the impact of the change rate of electricity demand on the power load based on the discreteness of rural residents' electricity demand, calculate the power supply stability within the differential time window, count the change range of the power supply frequency, and obtain the rural power load characteristic data.

[0009] As a further solution of the present invention, based on the rural power load characteristic data, the specific steps for calculating the adjustment range of rural enterprise power load, the change rate of rural enterprise electricity demand, and the load recovery rate, and analyzing the rural enterprise power load recovery ability, and calculating the rural economic stability index by weighted calculation are as follows: S211: Based on the rural power load characteristic data, count the load reduction value of rural enterprises during the power supply change period, obtain the corresponding reference load value, calculate the ratio, and perform integrated calculation on the data of multiple time periods to obtain the rural enterprise load reduction ratio data; S212: Based on the rural enterprise load reduction ratio data, count the load adjustment frequency of the enterprise during the differential time period, and use the formula: ; Calculate the adjustment range of rural enterprise power load , and obtain the rural enterprise power load adjustment range data, where represents the enterprise power load value at the th time point, represents the reference load value at the th time point, represents the number of time points counted, represents the load adjustment frequency at the th time point; S213: Based on the rural enterprise power load adjustment range data, combine the change rate of electricity demand and the load recovery rate of each time window, and perform weighted calculation to obtain the rural economic stability index.

[0010] As a further solution of the present invention, according to the rural power load characteristic data, determine the seasonal electricity consumption characteristics of rural enterprises, count the electricity consumption characteristics of rural residents' production and life, analyze the periodic change trend of electricity consumption, and the specific steps for generating the rural industrial electricity consumption pattern characteristic data are as follows: S311: Obtain the rural power load characteristic data, calculate the running time of the equipment during the differential time period, and count the power fluctuation range. Aggregate the power data of multiple devices, perform mean calculation and standard deviation calculation on the power change situation of each time period, and obtain the rural enterprise equipment operation characteristic data; S312: Based on the rural enterprise equipment operation characteristic data, judge the seasonal change trend of enterprise electricity consumption, count the seasonal electricity consumption peak and valley values, and use the formula: ; Calculate the seasonal electricity consumption eigenvalue of enterprises , obtain the seasonal electricity consumption characteristic data of rural enterprises, where represents the power value at the th time point, represents the power weight at the th time point, represents the number of time points for statistics, represents the equipment operation duration at the th time point, represents the average equipment operation duration within the time window; S313: Based on the seasonal electricity consumption characteristic data of the rural enterprises, extract the electricity consumption change situation during high-load periods, and combine with the electricity consumption characteristics of rural residents' production and living, analyze the periodic change trend of electricity consumption, and obtain the characteristic data of the electricity consumption pattern of rural industries.

[0011] As a further solution of the present invention, according to the rural economic stability index and the characteristic data of the rural industrial electricity consumption pattern, determine the characteristic of the rural power operation change, calculate the deviation value of the rural economic growth trend, and the specific steps for generating the rural economic growth trend prediction result are as follows: S411: Based on the rural economic stability index and the characteristic data of the rural industrial electricity consumption pattern, count the electricity consumption adjustment amplitude of enterprises within different time periods, and combine with historical period data to calculate the seasonal load change rate, and obtain the electricity consumption adjustment amplitude data of rural enterprises; S412: Based on the electricity consumption adjustment amplitude data of the rural enterprises, calculate the characteristic of the rural power operation change, analyze the industrial economic cycle fluctuation situation, and use the formula: ; Calculate the deviation value of the rural economic growth trend , measure the electricity consumption fluctuation of the rural economy, and obtain the deviation data of the rural economic growth trend, where represents the enterprise power load value at the th time point, represents the benchmark load value at the th time point, represents the number of statistical time points, represents the electricity consumption adjustment time at the th time point, represents the load recovery rate at the th time point, represents the weight factor at the th time point, represents the average load value within the time window; S413: Based on the rural economic growth trend deviation data, combined with the industrial economic operation trend, analyze the cyclical fluctuations of rural economic growth, and obtain the prediction result of the rural economic growth trend.

[0012] As a further solution of the present invention, according to the prediction result of the rural economic growth trend, calculate the abnormal amplitude of the power load adjustment of the vulnerable industries in rural economy, analyze the deviation of the change of the rural industrial power load, and the specific steps for generating the rural economic warning index are as follows: S511: Based on the prediction result of the rural economic growth trend, set the threshold value of the rural economic operation fluctuation, screen the industries exceeding the preset threshold value, calculate the load fluctuation range within the target time period, and obtain the screening result of the rural economic fluctuation industries; S512: Based on the screening result of the rural economic fluctuation industries, calculate the abnormal amplitude of the power load adjustment of the vulnerable industries in rural economy, and count the abnormal load change rate, using the formula: ; Calculate the deviation value of the change of the rural industrial power load , and obtain the analysis result of the deviation of the change of the rural industrial power load, where represents the actual load value at the th time point, represents the reference load value at the th time point, represents the corresponding number of time points for statistics, represents the load adjustment time at the th time point, represents the recovery rate at the th time point; S513: Based on the analysis result of the deviation of the change of the rural industrial power load, combined with the characteristics of industrial economic fluctuations, analyze the change of the rural economic operation trend, and count the key industries affecting the rural economic fluctuations, so as to obtain the rural economic warning index.

[0013] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In the present invention, based on power consumption data, the electricity consumption patterns of rural enterprises and residents are extracted to establish power load characteristic data, enabling the prediction of rural economic development to capture the dynamic changes in power usage. Combining indicators such as the load adjustment range, the rate of change in electricity demand, and the load recovery rate, an economic stability assessment system is constructed to ensure more accurate analysis of the load fluctuations and recovery capabilities of rural enterprises. By statistically analyzing the operating duration of equipment, the power fluctuation range, and the electricity consumption changes during high-load periods, the prediction can cover different industrial characteristics and periodic fluctuations. Calculating the offset value of the economic growth trend enables the economic trend prediction to incorporate the regional power operation characteristics, more accurately reflecting the potential signals of rural economic growth or decline, identifying economically vulnerable industries, and analyzing the abnormal amplitude of their power load changes, making the economic warning mechanism more accurate, effectively enhancing the economic risk identification ability, enabling economic prediction to rely not only on static data but also on the dynamic changes in power consumption, enhancing the real-time and refined nature of the prediction, and better conforming to the non-linear growth characteristics of rural economy. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a main flowchart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0015] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0016] In the description of the present invention, it should be understood that the orientation or positional relationships indicated by terms such as "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. In addition, in the description of the present invention, the meaning of "a plurality" is two or more unless otherwise specifically defined.

[0017] Please refer to Figure 1 , a method for predicting regional economic development based on power big data, comprising the following steps: S1: Set a fixed time window to obtain the electricity load of rural enterprises, collect the current power load value, the power load change amplitude, and the rate of change in electricity demand, statistically analyze the electricity consumption behavior of rural residents, analyze the electricity usage patterns of rural residents, record the power supply stability and the change amplitude of the power supply frequency, and generate rural power load characteristic data; S2: Based on the rural power load characteristic data, statistically calculate the ratio of the enterprise load reduction value to the benchmark load value during the power supply change period, calculate the adjustment range of the rural enterprise power load, obtain the load adjustment frequency of the enterprise in different time periods, set short-term, medium-term, and long-term time windows, calculate the change rate of the electricity demand of rural enterprises in each stage, statistically calculate the recovery time after load reduction, calculate the load recovery rate, analyze the power load recovery ability of rural enterprises, and perform weighted calculation by combining the load adjustment range, the change rate of electricity demand, and the load recovery rate to generate the rural economic stability index; S3: According to the rural power load characteristic data, calculate the equipment operation duration and the power fluctuation range, determine the seasonal electricity consumption characteristics of rural enterprises, extract the electricity consumption change situation during high-load periods through threshold comparison, statistically calculate the electricity consumption characteristics of rural residents' production and living, analyze the periodic change trend of electricity consumption, and generate the rural industrial electricity consumption pattern characteristic data; S4: According to the rural economic stability index and the rural industrial electricity consumption pattern characteristic data, statistically calculate the electricity adjustment range of rural enterprises, analyze the seasonal load change trend of rural industries, determine the change characteristics of rural power operation, calculate the deviation value of the rural economic growth trend, analyze the characteristics of the economic cycle fluctuation of rural industries, statistically calculate the trend of industrial economic operation, and generate the prediction result of the rural economic growth trend; S5: According to the prediction result of the rural economic growth trend, set the fluctuation threshold of rural economic operation, screen the industries with economic fluctuations exceeding the preset threshold, calculate the abnormal adjustment range of the power load of rural economic vulnerable industries, statistically calculate the abnormal load change rate, analyze the deviation of the power load change of rural industries, and generate the rural economic early warning indicators.

[0018] The rural power load characteristic data includes the current power load value, the power load change range, the change rate of electricity demand, the power consumption behavior of rural residents, the power usage pattern of rural residents, power supply stability, and the change range of power supply frequency. The rural economic stability index includes the load adjustment range, the change rate of electricity demand, the load recovery rate, and the power load recovery ability of rural enterprises. The rural industrial electricity consumption pattern characteristic data includes the equipment operation duration, the power fluctuation range, the seasonal electricity consumption characteristics of rural enterprises, the electricity consumption change situation during high-load periods, the electricity consumption characteristics of rural residents' production and living, and the periodic change trend of electricity consumption. The prediction result of the rural economic growth trend includes the electricity adjustment range of rural enterprises, the seasonal load change trend of rural industries, the change characteristics of rural power operation, the deviation value of the rural economic growth trend, the characteristics of the economic cycle fluctuation of rural industries, and the trend of industrial economic operation. The rural economic early warning indicators include the fluctuation threshold of rural economic operation, the rural industries with economic fluctuations exceeding the preset threshold, the abnormal adjustment range of the power load of rural economic vulnerable industries, the abnormal load change rate, and the deviation of the power load change of rural industries.

[0019] The specific steps of S1 are as follows: S111: Set a fixed time window, collect the current power load value, the amplitude of power load change, and the change rate of electricity demand, obtain the electricity consumption data of rural residents, organize the electricity consumption data, calculate the load change amount at the difference time points and the average value of the demand change rate, and obtain the basic electricity consumption data of rural residents; Set a fixed time window, and collect the current power load value, the amplitude of power load change, and the change rate of electricity demand. The time window can be set to 24 hours of a day or 7 days of a week. According to the set time window, record the power load situation of rural enterprises step by step at intervals of every hour or every 15 minutes. For example, within a certain day, the load values of a rural enterprise from 8 am to 12 pm are 120kW, 135kW, 140kW, 150kW, and from 2 pm to 6 pm are 130kW, 125kW, 115kW, 110kW respectively. At the same time, record the amplitude of load change in each time period, that is, the difference between the current moment load value and the previous moment load value. For example, at 9 am, the load value is 135kW, compared with 120kW at 8 am, the change amplitude is 15kW. The change rate of electricity demand represents the relative change rate of the load value, and is calculated by the ratio of the load change amount within a unit time to the initial load value. For example, at 9 am, the load is 135kW, compared with 120kW at 8 am, the change rate is (135 - 120) / 120 = 0.125. Statistically analyze the electricity consumption data of rural residents, classify them by different types of users, such as residential households, commercial stores, agricultural machinery equipment, etc., collect their electricity consumption data at different time periods respectively, and arrange them in time series. For example, the hourly electricity consumption data of 500 rural residents can be expressed as an array {1.5, 1.8, 2.0, 2.2, 2.5, 2.7, 3.0} kWh / hour. Finally, classify all the collected data, calculate the average value and the change amplitude of the power load in the whole rural area, and obtain the basic electricity consumption data of rural residents.

[0020] S112: Based on the basic electricity consumption data of rural residents, statistically analyze the electricity consumption fluctuations of rural residents in different time periods, calculate the electricity demand fluctuation range, analyze the electricity consumption concentration of residents in different time periods, calculate the peak-valley difference of electricity demand in each time period, and use the formula: ; Calculate the electricity demand dispersion of rural residents , obtain the electricity demand dispersion of rural residents, where represents the power load value at the th time point, represents the average value of the power load within the time window, represents the number of time points counted, represents the change rate of electricity demand at the th time point, Represents the average rate of change of electricity consumption demand within the time window, is the average deviation of the power load, is the variance of the rate of change of demand; Based on the basic data of rural residents' electricity consumption, the electricity consumption fluctuations in different time periods are statistically analyzed to obtain the fluctuation range of the daily electricity load. Assuming that the daily peak load in a certain rural area is 180 kW and the valley load is 75 kW, then the peak-valley difference is:

[0021] The load values at different time points of each day are statistically analyzed to form a time series matrix, as shown in Table 1.1.

[0022] Table 1.1 Data table of rural residents' electricity load in different time periods

[0023] As shown in Table 1.1, the load values in the rural area fluctuate greatly in different time periods. Further calculate the fluctuation range of electricity consumption demand, and calculate the mean and dispersion of the load values at different time points of each day to calculate the dispersion of rural residents' electricity demand.

[0024] It is set that the load data at 5 moments are collected in a rural area in one day, and its mean value is:

[0025]

[0026] Calculate the degree of dispersion at each moment. For example, if the load value at a certain moment is 150 kW, its deviation from the mean value is:

[0027] At another moment is -0.08, and the square of its deviation from the mean value is:

[0028] After accumulating all moments, it is calculated that:

[0029]

[0030]

[0031]

[0032] The finally calculated dispersion of rural residents' electricity demand is 20.2.

[0033] S113: Analyze the impact of the change rate of electricity demand on the power load based on the discreteness of rural residents' electricity demand, calculate the power supply stability within the differential time window, count the variation range of the power supply frequency, and obtain the rural power load characteristic data; Based on the discreteness of rural residents' electricity demand, analyze the impact of the change rate of electricity demand on the power load. Based on the daily statistical load change data, calculate the power supply stability for different time windows. For example, a day is divided into three time windows (6:00 - 12:00, 12:00 - 18:00, 18:00 - 24:00), and count the average load within this time window. For example, the average load of a certain time window (6:00 - 12:00) is 120 kW. The variation range of the power supply frequency is expressed as the ratio of the load fluctuation within the time window, that is, the ratio of the difference between the maximum load value and the minimum load value within the time window relative to the average value. For example, if the maximum load value within the window is 140 kW and the minimum load value is 110 kW, the calculation of the variation range of the power supply frequency is as follows:

[0034] The variation range of the power supply frequency can be further evaluated in combination with the fluctuation range of electricity demand and the dynamic adjustment ability of power supply equipment, and set the evaluation index of power supply stability. The threshold is set based on the carrying capacity of the rural power grid and the load regulation ability of the transformer. When the load regulation ability of the transformer is the maximum change of 20%, exceeding this value may lead to unstable power grid load. Therefore, the threshold 0.2 is set as the power supply fluctuation judgment standard, that is, when the variation range of the power supply frequency > 0.2, it is considered that the fluctuation is large and may affect the stable power supply, otherwise the power supply is considered stable. Combining the electricity consumption data of rural enterprises and residents, further calculate the power supply stability, and count the load fluctuation frequency within the continuous time period. For example, the calculation data of the power supply stability on a certain day is shown in Table 1.2 as follows: Table 1.2 Statistical data table of power supply stability

[0035] As shown in Table 1.2, there are differences in the power supply stability of different time windows. When the variation range of the power supply frequency is greater than the set threshold 0.2, the power supply state is judged to be unstable, which means that the load change within this time period exceeds the power grid regulation ability and may cause voltage fluctuation or even power supply interruption. When the frequency variation range is lower than 0.2, the load change range is within the power grid regulation range, which can ensure stable power supply. Finally, obtain the rural power load characteristic data.

[0036] The specific steps of S2 are as follows: S211: Based on the rural power load characteristic data, count the load reduction value of rural enterprises during the power supply change period, obtain the corresponding reference load value, calculate the ratio, and integrate and calculate the data for multiple time periods to obtain the rural enterprise load reduction ratio data; Obtain rural power load characteristic data, count the load reduction values of rural enterprises during the power supply change period, and obtain the benchmark load values of the enterprises. These data can be obtained through the daily electricity consumption records of the enterprises, smart meter data, and data from the power grid dispatching center. Record the current power load values of the enterprises at specific time points (such as 8:00 am, 12:00 pm, and 6:00 pm every day), and calculate the load difference values for each time period before and after the power supply adjustment. For example, if the load value of an enterprise at 8:00 am in a day is 500 kW and it is reduced to 350 kW due to power regulation at 12:00 pm, then the load reduction value is 150 kW. Similarly, record the benchmark load value. The setting of the benchmark load value is based on the average electricity consumption level of the enterprise, and this value should consider the typical load situation of the enterprise without external intervention. For industrial enterprises, the average load during stable production activities can be used as the benchmark load value. For example, the electricity consumption data of a certain factory at the same time period every day in the past 30 days is as follows (unit: kW): Table 2.1 Calculation Table of Benchmark Load Values for Rural Enterprises Date Load Value (kW) No. 1 470 No. 2 480 No. 3 490 No. 4 485 No. 5 475 … … No. 30 480 As shown in Table 2.1, the average electricity consumption load of this enterprise during this time period within 30 days is:

[0037] Therefore, the benchmark load value of this enterprise is taken as 480 kW. This value fluctuates with the change of the production load of the enterprise. If the production mode of the enterprise changes or it expands production, then this value needs to be recalculated. After collecting the electricity consumption data of multiple enterprises, calculate the ratio of the load reduction value to the benchmark load value to obtain the load reduction ratio. For example:

[0038] That is, the enterprise reduced 31.25% of its load during this time period. For the data of multiple enterprises, statistical methods can be used to calculate the average value of the load reduction ratio. For example, the load reduction ratio data for 5 enterprises is as follows: Table 2.2 Table of Load Reduction Ratios for Rural Enterprises

[0039] As shown in Table 2.2, calculate the average load reduction ratio of 5 enterprises:

[0040] Finally, obtain the load reduction ratio data of rural enterprises.

[0041] S212: Based on the load reduction ratio data of rural enterprises, count the load adjustment frequencies of enterprises in different time periods, and use the formula: ; Calculate the power load adjustment amplitude of rural enterprises , and obtain the power load adjustment amplitude data of rural enterprises. Among them, represents the The enterprise's power load value at a certain time point, represents the benchmark load value at the th time point, represents the number of time points for statistics, represents the load adjustment frequency at the th time point, represents the corrected mean of the load change value in terms of time weight, represents the change range of the corrected load adjustment frequency;

[0042] During the calculation process, the load adjustment situations at 5 time periods within a day (6:00, 10:00, 14:00, 18:00, 22:00) are set as follows: Table 2.3 Rural enterprise load adjustment data table

[0043] As shown in Table 2.3, calculate the sum of each parameter:

[0044]

[0045]

[0046] Calculate each part of the formula:

[0047]

[0048]

[0049] The calculated power load adjustment range of rural enterprises is 260.9, and after rounding it is 261 kW.

[0050] S213: Based on the rural enterprise power load adjustment range data, combined with the power consumption demand change rate and load recovery rate of each time window, perform weighted calculation to obtain the rural economic stability index; Based on the data of the power load adjustment amplitude of rural enterprises, combined with the change rate of electricity demand and the load recovery rate in each time window, weighted calculation is carried out. The change rate of electricity demand of rural enterprises can be defined as the demand change rate in the short term (1 day), medium term (7 days), and long term (30 days). Assuming that the short-term electricity demand change rate is 3.5%, the medium-term is 2.1%, and the long-term is 1.4%. The load recovery rate is defined as the time ratio required to recover to the benchmark load value after load reduction. For example, the time for a certain enterprise to recover to the benchmark load value after load reduction is as follows: Table 2.4 Time data for an enterprise to recover to the benchmark load value after load reduction

[0051] Calculate the average recovery rate:

[0052] Finally, weighted calculation is carried out by combining the load adjustment amplitude, the change rate of electricity demand, and the load recovery rate. The setting of the weighting coefficient is based on the degree of influence of each factor on the stability of the rural economy. Among them, the influence of the load adjustment amplitude is the most significant because it directly determines the production damage of the enterprise. Therefore, the weight is set to 0.5. The change rate of electricity demand reflects the adaptability of the enterprise to the grid adjustment, and the weight is set to 0.3. The load recovery rate determines the recovery ability of the enterprise and is set to 0.2. If the enterprises in the region are mainly high-energy-consuming industries (such as smelting, chemical industry), the weight of the load adjustment amplitude can be appropriately increased. If it is mainly light industrial enterprises, the weight of the load recovery rate can be increased. The calculation formula is as follows:

[0053]

[0054]

[0055] Finally, the rural economic stability index is obtained as 140.636.

[0056] The specific steps of S3 are as follows: S311: Obtain the rural power load characteristic data, calculate the operation duration of the equipment in different time periods, and count the power fluctuation range. Aggregate the power data of multiple devices, calculate the mean value and standard deviation of the power change situation in each time period, and obtain the operation characteristic data of rural enterprise equipment; Obtain rural power load characteristic data, count the operating hours and power fluctuation range of rural enterprise equipment. In specific implementation, there are differences in the power fluctuation characteristics of enterprise equipment in different industries. For example, the equipment of manufacturing enterprises is mostly in continuous operation with small fluctuations, while the equipment of agricultural product processing enterprises has a high start-stop frequency and large fluctuations. To ensure the accuracy of data collection, the monitoring period is set to 30 days, and the operating hours and instantaneous power values ​​of the equipment are recorded every day. The data sources may include smart meters, power grid management systems, and enterprise production monitoring systems. After the data is acquired, the power changes in each time period are aggregated, and the power values ​​of the equipment in different time periods are averaged to obtain the daily power consumption characteristics of the enterprise. For example, the equipment power values ​​of an enterprise at 8 am, 12 pm, and 6 pm are 50kW, 80kW, and 100kW respectively, and the average value is calculated as follows:

[0057] In addition, the standard deviation is calculated to measure the power fluctuation.

[0058] Assume that the company's 30-day monitoring data is as follows: Table 3.1 Rural enterprise equipment power monitoring data

[0059] Calculate the standard deviation of the enterprise's power fluctuation:

[0060] After the final calculation, we get , which represents the power fluctuation of the enterprise equipment during the entire monitoring period. If the value is high, it means that the equipment load changes greatly. For example, in the food processing industry, the value may be as high as 20kW, while in a continuous production manufacturing enterprise, the value may be less than 5kW. This information is of great reference value for grid load scheduling and enterprise energy management. Finally, the power fluctuation range is calculated and combined with the operation time data to obtain the operation characteristics of rural enterprise equipment.

[0061] S312: Based on the equipment operation characteristic data of rural enterprises, determine the seasonal change trend of enterprise electricity consumption, calculate the peak and valley values ​​of seasonal electricity consumption, and use the formula: ; Calculate the seasonal electricity consumption characteristics of enterprises , obtain seasonal electricity consumption characteristic data of rural enterprises, among which, Representative The power value at a time point, Representative The power weight at each time point, Represents the time point of statistics, Representative The operation duration of the device at a certain time point represents the average operation duration of the device within the time window; Based on the operation characteristics of rural enterprise devices, calculate the seasonal electricity consumption characteristics of rural enterprises, judge the changing trend of enterprise electricity consumption in different seasons, set the data collection periods for the four seasons of spring, summer, autumn, and winter, and count the electricity consumption in each season. Calculate the seasonal electricity consumption characteristics using the power average values at different time points. For example, for a certain rural food processing enterprise, the power average values in spring, summer, autumn, and winter are 60kW, 80kW, 70kW, and 50kW respectively. This value is calculated from the power data of the enterprise at the same time period every day in the past three years. The setting of the power average value is mainly affected by factors such as production load, temperature influence, and electricity demand. For example, in the food processing industry, the demand increases in summer, and the device operation time is extended, so the power average value is relatively high. While in winter, the production demand decreases, the device starts and stops less, and the power average value drops accordingly. If the enterprise introduces a new production line or increases seasonal orders, this average value may be adjusted accordingly.

[0062] Then use the formula for calculation. Among them, set the power weight Allocate according to the proportion of device usage time. For example, a certain enterprise sets the operation duration proportion in spring to be 30%, in summer to be 40%, in autumn to be 20%, and in winter to be 10%. The setting of this weight is based on the proportion of the device's daily operation duration in the whole year. During the calculation process, holidays and shutdown days are excluded to ensure the accuracy of the seasonal electricity consumption characteristics. If the enterprise's production cycle is adjusted, such as increasing the heating demand in winter or reducing some non-essential loads in summer, then this weight should be adjusted accordingly. Then calculate the weighted power average value of this enterprise as follows:

[0063]

[0064] Calculate the variance of the device operation duration. Assume that in the monitoring data of this enterprise, the average operation durations of the device in the four seasons are 8h, 10h, 9h, and 7h respectively. This operation duration data is obtained based on the actual start and stop records of the enterprise's devices. The operation duration of the device is affected by production plans and market demand fluctuations. For example, food processing enterprises will increase the operation time of cold chain devices in summer high-temperature weather, so the duration in summer is longer. While in winter, the demand is less, and the device operation duration decreases. Then the variance calculation is as follows:

[0065]

[0066] Finally, calculate:

[0067]

[0068] This value indicates that the seasonal electricity consumption characteristic value of the enterprise is -1120 (far less than 0), which shows that the electricity consumption characteristics of the enterprise fluctuate little among seasons. If this value is positive and large, it means that the electricity load of the enterprise in a certain season far exceeds that in other seasons. For example, agricultural product processing enterprises reach the production peak in autumn, and their power may be more than 50% higher than that in other seasons, resulting in a higher S value. Therefore, this indicator can reflect the seasonal electricity consumption trend of the enterprise. If the seasonal electricity consumption characteristic value of the enterprise is large, load management measures should be taken, such as adjusting production time or optimizing energy use. Finally, calculate the seasonal electricity consumption characteristics by combining the equipment operation duration data to obtain the seasonal electricity consumption characteristics of rural enterprises.

[0069] S313: Based on the seasonal electricity consumption characteristic data of rural enterprises, extract the electricity consumption changes during high-load periods, and combine with the electricity consumption characteristics of rural residents' production and life to analyze the periodic change trend of electricity consumption, and obtain the characteristic data of the electricity consumption pattern of rural industries; Based on the seasonal electricity consumption characteristics of rural enterprises, extract the electricity consumption changes during high-load periods, and combine with the electricity consumption characteristics of rural residents' production and life to analyze the periodic change trend of electricity consumption. In the specific implementation process, set the data collection ranges for daily, weekly, and monthly cycles to count the load changes in different time periods. For example, the load of a rural enterprise peaks at 10:00 - 12:00 and 18:00 - 20:00 every day, and its electricity consumption increases by more than 20% compared with the average daily electricity consumption. This value is calculated based on the power statistical data of different time periods throughout the day. When judging high-load periods, use the average daily load as the reference value. If the load value in a certain period exceeds the reference value by more than 20%, it is determined as a high-load period. For example, the load at 10:00 - 12:00 is 90 kW, and the average daily value is 75 kW, then the calculation is as follows:

[0070] Therefore, this period can be defined as a high-load period, and further extract the electricity consumption characteristics of this enterprise as follows: Table 3.2 Statistical Table of High-Load Periods of Rural Enterprises

[0071] As shown in Table 3.2, the load change rate of this enterprise during high-load periods exceeds 20%. The setting of this judgment standard is based on the analysis of the enterprise's historical data. Generally, if the load change rate in a certain period exceeds 15% - 25% of the reference average value, this period can be considered as a high-load period. In actual applications, if the enterprise's load change rate is high, it is necessary to adjust its electricity consumption structure, such as optimizing production scheduling or using energy storage equipment to reduce peak loads. In the calculation of the periodic change trend, compare the load fluctuations on a daily, weekly, and monthly basis, and calculate the daily average load:

[0072] Calculations show that the average daily load value of this enterprise is 82 kW. Compared with the load value during high-load periods, the load change rate is relatively obvious. If this value remains above 20% for a long time, the enterprise should consider adjusting its production arrangements during high-load periods to reduce electricity costs and the load pressure on the power grid. Finally, by combining the data during high-load periods and the cyclical electricity consumption changes, characteristic data of the electricity consumption patterns of rural industries is obtained.

[0073] The specific steps of S4 are as follows. S411: Based on the rural economic stability index and the characteristic data of the electricity consumption patterns of rural industries, statistically analyze the electricity consumption adjustment amplitude of enterprises within different time cycles, and calculate the seasonal load change rate in combination with historical cycle data to obtain the data on the electricity consumption adjustment amplitude of rural enterprises. Based on the rural economic stability index and the characteristic data of the electricity consumption patterns of rural industries, statistically analyze the electricity consumption adjustment amplitude of enterprises within different time cycles, and calculate the seasonal load change rate in combination with historical cycle data. First, obtain the electricity consumption data of rural enterprises in a certain area, including the daily electricity load, equipment operation time, and power grid power supply fluctuations. For the electricity consumption adjustment amplitude of enterprises, calculate the load changes within different time cycles, such as short cycles (1 day), medium cycles (7 days), and long cycles (30 days). For the data of an enterprise within a week, it is as follows: Table 4.1 Table of Electricity Consumption Adjustment Amplitude of Rural Enterprises

[0074] As shown in Table 4.1, by calculating the average load:

[0075] Calculate the load adjustment amplitude:

[0076]

[0077] The electricity consumption adjustment amplitude of this enterprise is 13.27 kW. By combining the data of different enterprises, calculate the average adjustment amplitude of enterprises across the entire rural area to obtain the data on the electricity consumption adjustment amplitude of rural enterprises.

[0078] S412: Based on the data on the electricity consumption adjustment amplitude of rural enterprises, calculate the characteristics of rural power operation changes, analyze the cyclical fluctuations of the industrial economy, and use the formula: ; Calculate the deviation value of the rural economic growth trend , measure the electricity consumption fluctuations of the rural economy, and obtain the data on the deviation of the rural economic growth trend. Among them, represents the The enterprise's electricity load value at a certain time point, representing the electricity consumption load of the enterprise on a certain day. Represents the benchmark load value at a certain time point, representing the average electricity consumption load of the enterprise under normal conditions. Represents the number of statistical time points, that is, the time range involved in the calculation process. Represents the power consumption adjustment time at a certain time point, representing the time experienced by the enterprise for load adjustment at this time point. Represents the load recovery rate at a certain time point, representing the ratio of the enterprise to recover to the benchmark load value after load adjustment. Represents the weight factor at a certain time point, used to adjust the importance of each time point in the calculation process. Represents the average load value within the time window, calculating the load average value of all time points; Based on the electricity consumption adjustment range of rural enterprises, calculate the characteristics of rural power operation changes, analyze the industrial economic cycle fluctuations, and use the formula to calculate the deviation value of rural economic growth trend. In the calculation process, select the load data of a certain enterprise for 5 days, and the daily load fluctuation is as follows: Table 4.2 Calculation Parameter Table of Rural Enterprise Economic Growth Trend

[0079] As shown in Table 4.2, calculate each parameter item: Load ratio calculation:

[0080] Take the data of the first 5 days for calculation:

[0081] Normalized calculation of power consumption adjustment time:

[0082] Take the data of the first 5 days for calculation:

[0083]

[0084] Load standard deviation calculation:

[0085] Calculate the load average value:

[0086] Calculate the standard deviation:

[0087]

[0088] Finally, calculate the deviation value of the rural economic growth trend:

[0089]

[0090] The result shows that the deviation value of the rural economic growth trend is -73.8428 (within 5 days). The negative value indicates that during the current economic cycle, the adjustment range of the enterprise load is relatively high, while the recovery rate is relatively low, resulting in poor load stability. It can be used to judge the short-term fluctuations of the economic growth trend and combine the data analysis of a longer time period to analyze the long-term trend.

[0091] S413: Based on the deviation data of the rural economic growth trend, combined with the operation trend of the industrial economy, analyze the cyclical fluctuations of the rural economic growth, and obtain the prediction result of the rural economic growth trend; Based on the deviation value of the rural economic growth trend, combined with the operation trend of the industrial economy, analyze the cyclical fluctuations of the rural economic growth. First, decompose the electricity consumption data of each enterprise in different seasons. The whole year is divided into four quarters. Calculate the average load value, load fluctuation range, and electricity consumption recovery rate within each quarter, extract the load growth or decline trend of each quarter, and perform weighted normalization combined with the enterprise data within the whole rural area to calculate the industrial operation trend value of each quarter. Finally, obtain the annual industrial economic cycle fluctuation situation through curve fitting, as follows: Table 4.3 Prediction Table of Rural Economic Growth Trend

[0092] As shown in Table 4.3, the annual rural economic growth trend can be predicted to obtain the final prediction result of the rural economic growth trend.

[0093] The specific steps of S5 are as follows S511: Based on the prediction result of the rural economic growth trend, set the threshold of the rural economic operation fluctuation, screen the industries that exceed the preset threshold, calculate the load fluctuation range within the target time period, and obtain the screening result of the rural economic fluctuation industries; Based on the prediction result of the rural economic growth trend, set the threshold of the rural economic operation fluctuation, and screen the industries that exceed the preset threshold. For this purpose, it is first necessary to count the economic fluctuation situations of multiple industries in different time periods, extract the economic fluctuation indexes of each industry. The economic fluctuation index can be calculated through parameters such as the total industrial output value, profit change rate, and power load adjustment range. For example, in 5 major industries in a certain rural area, the daily average output value and power load adjustment ratio of each industry are as follows: Table 5.1 Data Table of Rural Industrial Economic Fluctuations

[0094] As shown in Table 5.1, calculate the mean of the industrial economic fluctuation index:

[0095] Set the economic fluctuation threshold to 1.2 times the mean, that is:

[0096] Screen the industries with an economic fluctuation index exceeding 1.776. Through comparison, only Industry 4 meets the conditions, and this industry is selected as the screening result of the rural economic fluctuation industry.

[0097] S512: Based on the screening results of the rural economic fluctuation industry, calculate the abnormal amplitude of the power load adjustment of the rural economic vulnerable industries, and count the abnormal load change rate. Use the formula: ; Calculate the deviation value of the rural industrial power load change , and obtain the analysis result of the deviation of the rural industrial power load change. Among them, represents the actual load value at the th time point, represents the reference load value at the th time point, represents the corresponding number of statistical time points, represents the load adjustment time at the th time point, represents the recovery rate at the th time point; Based on the screening results of the rural economic fluctuation industry, calculate the abnormal amplitude of the power load adjustment of the rural economic vulnerable industries, and count the abnormal load change rate, and calculate in combination with the formula.

[0098] Table 5.2 Data table of power load adjustment of Industry 4

[0099] Calculate each parameter:

[0100]

[0101]

[0102]

[0103]

[0104]

[0105]

[0106]

[0107]

[0108] Final calculation:

[0109] The result shows that the abnormal range of power load adjustment in Industry 4 is relatively large, and finally the deviation value of rural industrial power load change is obtained.

[0110] S513: Based on the analysis results of the deviation of rural industrial power load change, combined with the characteristics of industrial economic fluctuations, analyze the changes in the rural economic operation trend, and count the key industries affecting rural economic fluctuations to obtain rural economic warning indicators; Based on the deviation value of rural industrial power load change, combined with the characteristics of industrial economic fluctuations, calculate the changes in the economic operation trend, and count the main industries affecting economic fluctuations. For this purpose, it is necessary to calculate economic warning indicators, which can be obtained through weighted calculation of parameters such as industrial load adjustment rate, power load recovery rate, and economic growth fluctuation index. Select representative industry data in the industrial economic operation for calculation. For example, for other industries outside Industry 4, the load adjustment rate and power load recovery rate are as follows: Table 5.3 Data table of power load adjustment of main industries

[0111] Calculate the average load adjustment rate of the industry:

[0112] Calculate the average load recovery rate of the industry:

[0113] Calculate the economic growth fluctuation index:

[0114] Finally, the economic warning indicators are set as follows: The load adjustment rate is an important parameter to measure the power demand response ability of the industry. A higher value indicates a larger adjustment range during power regulation. Therefore, it is calculated with equal weight in the warning indicators. The load recovery rate reflects the ability of enterprises to recover from the power cut state to the normal operation state. A higher industry recovery rate usually indicates better adaptability to short-term power supply fluctuations. However, since the load recovery rate is usually much higher than the adjustment rate, in order to avoid too high a weight of this parameter in the calculation, its weighting coefficient is set to 0.5, that is, this parameter is calculated by halving. The economic growth volatility index reflects the sensitivity of the industry to the macro economy. The larger the index value, the more severe the economic operation fluctuations of the industry. In the rural economic structure, some industries (such as agriculture and light industry) are less sensitive to market fluctuations, while some industries (such as manufacturing and mining) are more affected by the external market and policies. Therefore, a weighting coefficient of 2 is set for this parameter to increase its influence weight in the economic warning indicators. The final calculation formula is as follows:

[0115]

[0116]

[0117] Rural economic warning indicator value is obtained by weighted calculation based on the rural industrial power load adjustment rate, load recovery rate, and economic growth volatility index. This value is used in the economic monitoring system to measure the stability and potential risks of the rural industrial economic operation.

[0118] According to the reference intervals for delimiting economic warning indicators, in order to determine the current state of the rural economy, the following intervals are usually delimited: : The economic operation is stable, the industrial structure is relatively balanced, the power load adjustment range is moderate, the industrial recovery ability is strong, and no additional economic intervention measures are required; : There are slight fluctuations in the economic operation, and some industries are more obviously affected by the cycle, but the overall industrial load adjustment ability is strong, and high-load industries need to be closely monitored; : The economic operation fluctuates greatly, and some industries are more obviously affected by the external market, policies, or energy supply. The load adjustment of some industries is too drastic, affecting economic stability. It is recommended to take control measures for specific industries; : The economic fluctuations are severe, abnormal load adjustments, low recovery rates, or severe growth fluctuations occur in multiple industries, and the rural industry as a whole is strongly impacted, which may affect the sustainable development of the regional economy and corresponding policy interventions need to be formulated.

[0119] The currently calculated economic early warning index value of 34.16 is in the range of 30 - 40, indicating that the rural industrial economy fluctuates greatly. The power load adjustment range of some industries is large, the recovery rate is low, and the economic growth fluctuation index is high. It means that: There are obvious abnormalities in the power load adjustment within the rural industry. For example, some industries cut the load too much during the peak electricity consumption period, which may affect their normal production operations; The economic recovery ability is relatively weak. The power recovery rate of some industries is relatively low, which may cause the production activities of enterprises to be affected for a long time; Economic growth is greatly affected by market fluctuations. Especially in the context of policy regulation, electricity price adjustment or supply - demand changes, the rural industry may experience short - term or long - term economic instability.

[0120] The economic early warning index is not only applicable to static analysis but also can be used for dynamic monitoring. By continuously tracking the rural industrial economic fluctuations and calculating the early warning index values for different time periods, the trend changes of the rural economy can be observed. For example: If the economic early warning index remains in the range of 30 - 40 for three consecutive months, it indicates that the industrial economy is still in the adjustment stage but has not deteriorated; If the index value rises above 40, it shows that the economic fluctuation risk intensifies, and measures such as optimizing power supply, providing financial subsidies or adjusting the industry may be needed; If the index value drops below 20, it indicates that the rural economy has recovered stability and the industrial operation tends to be normal.

[0121] The economic early warning index value of 34.16 generally reflects that there are large fluctuations in the current operation of the rural industrial economy, especially in terms of power load adjustment, recovery rate and economic growth fluctuation index, and the industry faces certain instability. If the index continues to rise, targeted measures should be taken for regulation to prevent the economy from deteriorating further.

[0122] The above is only the preferred embodiment of the present invention, and it is not intended to limit the present invention in other forms. Any person skilled in the relevant art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above - mentioned embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A method for predicting regional economic development based on power big data, characterized in that, It includes the following steps: S1: Set a fixed time window to obtain the electricity load of rural enterprises, count the electricity consumption behaviors of rural residents, analyze the electricity usage patterns of rural residents, and generate rural electricity load characteristic data; S2: Based on the rural electricity load characteristic data, calculate the adjustment range of the electricity load of rural enterprises, the change rate of the electricity demand of rural enterprises, and the load recovery rate, analyze the electricity load recovery ability of rural enterprises, and generate a rural economic stability index through weighted calculation; S3: According to the rural electricity load characteristic data, determine the seasonal electricity usage characteristics of rural enterprises, count the electricity usage characteristics of rural residents' production and living, analyze the periodic change trend of electricity usage, and generate rural industrial electricity usage pattern characteristic data; S4: According to the rural economic stability index and the rural industrial electricity usage pattern characteristic data, determine the change characteristics of rural power operation, calculate the deviation value of the rural economic growth trend, and generate a rural economic growth trend prediction result; S5: According to the rural economic growth trend prediction result, calculate the abnormal adjustment range of the electricity load of rural economic vulnerable industries, analyze the deviation of the electricity load change of rural industries, and generate a rural economic warning index.

2. The method for predicting regional economic development based on power big data according to claim 1, wherein The rural electricity load characteristic data includes the current electricity load value, the change range of the electricity load, the change rate of the electricity demand, the electricity consumption behaviors of rural residents, the electricity usage patterns of rural residents, the power supply stability, and the change range of the power supply frequency. The rural economic stability index includes the adjustment range of the load, the change rate of the electricity demand, the load recovery rate, and the electricity load recovery ability of rural enterprises. The rural industrial electricity usage pattern characteristic data includes the equipment operation duration, the power fluctuation range, the seasonal electricity usage characteristics of rural enterprises, the electricity usage change situation during high load periods, the electricity usage characteristics of rural residents' production and living, and the periodic change trend of electricity usage. The rural economic growth trend prediction result includes the adjustment range of the electricity usage of rural enterprises, the seasonal load change trend of rural industries, the change characteristics of rural power operation, the deviation value of the rural economic growth trend, the cyclic fluctuation characteristics of the rural industrial economy, and the operation trend of the industrial economy. The rural economic warning index includes the fluctuation threshold of rural economic operation, the rural industries with economic fluctuations exceeding the preset threshold, the abnormal adjustment range of the electricity load of rural economic vulnerable industries, the abnormal load change rate, and the deviation of the electricity load change of rural industries.

3. The method for predicting regional economic development based on power big data according to claim 1, wherein, The specific steps for setting a fixed time window to obtain the electricity load of rural enterprises, counting the electricity consumption behaviors of rural residents, analyzing the electricity usage patterns of rural residents, and generating rural electricity load characteristic data are as follows: S111: Set a fixed time window, collect the current electricity load value, the change range of the electricity load, and the change rate of the electricity demand, obtain the electricity usage data of rural residents, sort out the electricity usage data and calculate the average value of the load change amount and the demand change rate at different time points to obtain the basic electricity consumption data of rural residents; S112: Based on the basic electricity consumption data of rural residents, count the electricity usage fluctuations of rural residents in different time periods, calculate the electricity demand fluctuation range, analyze the electricity consumption concentration of residents in different time periods, calculate the peak-valley difference of the electricity demand in each time period, and use the formula: ； Calculating the Discrepancy of Rural Residents' Electricity Demand , obtaining the discrepancy of rural residents' electricity demand, where represents the electricity load value at the -th time point, represents the average electricity load within the time window, represents the number of time points for statistics, represents the change rate of electricity consumption demand at the -th time point, represents the average change rate of electricity consumption demand within the time window, is the average deviation of the electricity load, is the variance of the change rate of demand; S113: Analyze the impact of the change rate of electricity consumption demand on the power load based on the discreteness of rural residents' electricity demand, calculate the power supply stability within the differential time window, count the change range of the power supply frequency, and obtain the rural power load characteristic data.

4. The method for predicting regional economic development based on power big data according to claim 1, wherein, Based on the rural power load characteristic data, the specific steps for calculating the adjustment range of rural enterprise power load, the change rate of rural enterprise electricity consumption demand, and the load recovery rate, and analyzing the power load recovery ability of rural enterprises, and calculating the rural economic stability index by weighted calculation are as follows: S211: Based on the rural power load characteristic data, count the load reduction values of rural enterprises during the power supply change period, obtain the corresponding reference load values, calculate the ratio, and perform integrated calculation on the data of multiple time periods to obtain the rural enterprise load reduction ratio data; S212: Based on the rural enterprise load reduction ratio data, statistically calculate the load adjustment frequency of the enterprise during different time periods, using the formula: ; Calculate the adjustment range of rural enterprise power load , obtain the data of the adjustment range of rural enterprise power load, where represents the enterprise power load value at the -th time point, represents the reference load value at the -th time point, represents the number of time points for statistics, represents the load adjustment frequency at the -th time point, represents the corrected mean value of the load change value in terms of time weight, represents the change range of the corrected load adjustment frequency; S213: Based on the rural enterprise power load adjustment range data, combine the change rate of electricity consumption demand and the load recovery rate of each time window, and perform weighted calculation to obtain the rural economic stability index.

5. The method for predicting regional economic development based on power big data according to claim 1, wherein The specific steps for determining the seasonal electricity consumption characteristics of rural enterprises, counting the electricity consumption characteristics of rural residents' production and life, analyzing the periodic change trend of electricity consumption, and generating the rural industrial electricity consumption pattern characteristic data based on the rural power load characteristic data are as follows: S311: Obtain the rural power load characteristic data, calculate the operation duration of the equipment in the differential time period, and count the power fluctuation range. Aggregate the power data of multiple devices, calculate the mean value and standard deviation of the power change situation in each time period, and obtain the rural enterprise equipment operation characteristic data; S312: Based on the rural enterprise equipment operation characteristic data, judge the seasonal change trend of enterprise electricity consumption, count the seasonal electricity consumption peak and valley values, and use the formula: ; Calculate the seasonal electricity consumption eigenvalue of enterprises , obtain the seasonal electricity consumption characteristic data of rural enterprises, where represents the power value at the th time point, represents the power weight at the th time point, represents the number of time points counted, represents the equipment operation duration at the th time point, represents the average equipment operation duration within the time window; S313: Based on the rural enterprise seasonal electricity consumption characteristic data, extract the electricity consumption change situation during the high load period, and combine the electricity consumption characteristics of rural residents' production and life to analyze the periodic change trend of electricity consumption, and obtain the rural industrial electricity consumption pattern characteristic data.

6. The method for predicting regional economic development based on power big data according to claim 1, wherein The specific steps for determining the rural power operation change characteristics, calculating the rural economic growth trend deviation value, and generating the rural economic growth trend prediction result based on the rural economic stability index and the rural industrial electricity consumption pattern characteristic data are as follows: S411: Based on the rural economic stability index and the rural industrial electricity consumption pattern characteristic data, count the electricity consumption adjustment range of enterprises within the differential time cycle, and combine the historical cycle data to calculate the seasonal load change rate, and obtain the rural enterprise electricity consumption adjustment range data; S412: Based on the rural enterprise electricity consumption adjustment amplitude data, calculate the characteristics of rural power operation changes, analyze the industrial economic cycle fluctuations, and use the formula: ; Calculate the deviation value of the rural economic growth trend , measure the power consumption fluctuation of the rural economy, and obtain the data of the deviation of the rural economic growth trend. Among them, represents the enterprise power load value at the th time point, represents the reference load value at the th time point, represents the number of statistical time points, represents the power consumption adjustment time at the th time point, represents the load recovery rate at the th time point, represents the weight factor at the th time point, represents the average load value within the time window; S413: Based on the rural economic growth trend deviation data, combine the industrial economic operation trend, analyze the periodic fluctuation of rural economic growth, and obtain the rural economic growth trend prediction result.

7. The method for predicting regional economic development based on power big data according to claim 1, wherein The specific steps for calculating the abnormal adjustment range of the power load of rural economic vulnerable industries, analyzing the deviation of the rural industrial power load change, and generating the rural economic warning index based on the rural economic growth trend prediction result are as follows: S511: Based on the rural economic growth trend prediction result, set the rural economic operation fluctuation threshold, screen the industries that exceed the preset threshold, calculate the load fluctuation range within the target time period, and obtain the rural economic fluctuation industry screening result; S512: Based on the screening results of the rural economic fluctuation industries, calculate the abnormal amplitude of the adjustment of the electricity load of the vulnerable rural industries, and count the abnormal load change rate, using the formula: ; Calculate the deviation value of the rural industrial power load change , and obtain the analysis result of the deviation of the rural industrial power load change, where represents the actual load value at the th time point, represents the reference load value at the th time point, represents the corresponding number of time points for statistics, represents the load adjustment time at the th time point, represents the recovery rate at the th time point; S513: Based on the analysis results of the change deviation of the rural industrial electricity load, combined with the characteristics of industrial economic fluctuations, analyze the changes in the rural economic operation trend, and count the key industries affecting rural economic fluctuations to obtain rural economic warning indicators.

Images