A method for power resource allocation based on big data

Abstract

The present invention discloses a power resource allocation method based on big data, relates to the field of power allocation, solves the problem of poor effect of existing power resource allocation methods, and comprises: step S1: obtaining the first analysis sample date to the ath analysis sample date to obtain sample date data, step S2: obtaining the first sample power unit to the bth sample power unit and the target year-on-year power consumption coefficient, the first year-on-year power consumption coefficient to the bth year-on-year power consumption coefficient and the target year-on-year power consumption coefficient according to the sample date data to obtain year-on-year power consumption data, step S3: obtaining the predicted benchmark power consumption, the target cycle power consumption coefficient and the first cycle power consumption coefficient to the bth cycle power consumption coefficient according to the year-on-year power consumption data to obtain the cycle power consumption data, step S4: creating a power consumption prediction model according to the year-on-year power consumption data and the cycle power consumption data to perform power prediction for the power control area, and perform power control according to the prediction result. The present invention can reduce the risk of power waste and insufficient supply.

Description

Technical Field

[0001] The present invention belongs to the field of power allocation and relates to big data technology, and specifically is a power resource allocation method based on big data. Background Art

[0002] The existing power resource allocation method has the following defects when allocating power resources:

[0003] 1. When predicting regional power consumption, the existing power resource allocation method usually does not predict the power consumption of a single unit, but usually only predicts the power consumption of a large area, resulting in a lack of accuracy in the prediction results;

[0004] 2. The existing power resource allocation method uses big data technology to select data analysis samples without matching the power consumption of the target power users, and the selected sample dates do not match the weather of the target power dispatch dates, resulting in a lack of specificity in the data analysis samples obtained, which leads to deviations in the prediction results.

[0005] To this end, we propose a power resource allocation method based on big data. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention aims to provide a method for allocating electric power resources based on big data. The present invention obtains sample date data based on the first analysis sample date to the ath analysis sample date, obtains the first electricity consumption year-on-year coefficient to the bth electricity consumption year-on-year coefficient, the first sample electricity consumption unit to the bth sample electricity consumption unit and the target electricity consumption year-on-year coefficient according to the sample date data, obtains the year-on-year electricity consumption data, obtains the predicted benchmark electricity consumption, the target cycle electricity consumption coefficient and the first cycle electricity consumption coefficient to the bth cycle electricity consumption coefficient according to the year-on-year electricity consumption data, obtains the cycle electricity consumption data, creates an electricity consumption prediction model based on the year-on-year electricity consumption data and the cycle electricity consumption data to perform electricity prediction for the power control area, and performs electricity control on the power control area based on the predicted electricity consumption in the power control area.

[0007] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: a method for allocating electric power resources based on big data, comprising the following specific steps:

[0008] Step S1: obtaining a power control area, selecting a target power consumption unit in the power control area, obtaining a target power dispatch date, selecting multiple characteristic dates corresponding to the target power consumption unit according to the target power dispatch date, performing weather analysis on each characteristic date, obtaining multiple weather matching coefficients, and filtering the first analysis sample date to the ath analysis sample date from the multiple characteristic dates by the weather matching coefficients to obtain sample date data;

[0009] Step S2: obtaining a first electricity consumption critical value, a second electricity consumption critical value, and a plurality of electricity consumption units according to the sample date data, screening out a plurality of sample electricity consumption units from the plurality of electricity consumption units according to the first electricity consumption critical value and the second electricity consumption critical value, and respectively obtaining electricity consumption year-on-year coefficients for the sample electricity consumption units and the plurality of sample electricity consumption units to obtain a plurality of electricity consumption year-on-year coefficients, and defining the electricity consumption year-on-year coefficients and the plurality of sample electricity consumption units as year-on-year electricity consumption data;

[0010] Step S3: acquiring the periodic power consumption coefficients corresponding to the target power consumption unit and the multiple sample power consumption units respectively according to the year-on-year power consumption data, obtaining multiple periodic power consumption coefficients, and performing periodic average daily power consumption analysis on the multiple sample power consumption units to obtain predicted benchmark power consumption, and defining the multiple periodic power consumption coefficients and the predicted benchmark power consumption as periodic power consumption data;

[0011] Step S4: Create a power consumption forecasting model based on the year-on-year power consumption data and the periodic power consumption data to forecast power in the power control area, obtain the predicted power consumption in the power control area, and conduct power control in the power control area based on the predicted power consumption in the power control area.

[0012] Furthermore, the step S1 further includes the following specific steps:

[0013] Step S11: randomly selecting a power consumption unit in the power control area as a target power consumption unit;

[0014] Step S12: obtaining a target power dispatch date, and marking a power consumption analysis period with the target power dispatch date as an intermediate date;

[0015] Step S13: Select d historical years as comparative analysis years respectively, mark the electricity consumption analysis period in each comparative analysis year respectively, obtain multiple characteristic dates, and randomly select a sample characteristic date from the multiple characteristic dates;

[0016] Step S14: Perform weather analysis on the sample characteristic date to obtain a weather matching coefficient corresponding to the sample characteristic date;

[0017] Step S15: Repeat step S14 to obtain the weather matching coefficient corresponding to each characteristic date;

[0018] Step S16: Obtain a weather matching coefficient threshold, compare the weather matching coefficient corresponding to each characteristic date with the weather matching coefficient threshold, and when the weather matching coefficient is less than the weather matching coefficient threshold, mark the corresponding characteristic date as an analysis sample date, obtain multiple analysis sample dates, and name them as the first analysis sample date to the ath analysis sample date respectively;

[0019] Step S17: define the first analysis sample date to the ath analysis sample date as sample date data.

[0020] Furthermore, the step S14 further includes the following specific steps:

[0021] Step S141: Acquire historical weather data, and acquire the temperature value and wind strength value corresponding to the sample characteristic date according to the historical weather data, and name them as the first temperature value and the first wind strength value respectively;

[0022] Step S142: obtaining a temperature value and a wind strength value corresponding to the target power dispatch date, and naming them as a second temperature value and a second wind strength value, respectively;

[0023] Step S143: obtaining a weather matching coefficient by calculating the first temperature value, the first wind strength value, the second temperature value and the second wind strength value;

[0024] Calculate the weather matching coefficient, the specific formula configuration is as follows:

[0025] ;

[0026] Among them, Tqx is the weather matching coefficient, Qw1 is the first temperature value, Qw2 is the second temperature value, Wd1 is the first wind strength value, and Wd2 is the second wind strength value.

[0027] Furthermore, the step S2 further includes the following specific steps:

[0028] Step S21: Obtain sample date data, and obtain the first analysis sample date to the ath analysis sample date according to the sample date data;

[0029] Step S22: Obtain historical electricity consumption records, and obtain the daily electricity consumption of the target electricity user unit from the first analysis sample date to the ath analysis sample date according to the historical electricity consumption records, and obtain the electricity consumption from the first single day to the ath single day;

[0030] Step S23: Calculate the average of the electricity consumption from the first single day to the ath single day to obtain the daily average electricity consumption, and calculate the variance of the electricity consumption from the first single day to the ath single day to obtain the daily average consumption variance;

[0031] Step S24: obtaining a first power usage threshold and a second power usage threshold;

[0032] Step S25: obtaining a number of electricity consumption units through big data crawler technology, obtaining the average daily electricity consumption of each electricity consumption unit from the first analysis sample date to the ath analysis sample date, and obtaining multiple average daily electricity consumptions;

[0033] Step S26: when the average daily power consumption is between the first power consumption critical value and the second power consumption critical value, the corresponding power consumption unit is marked as a sample power consumption unit, and a plurality of sample power consumption units are obtained, and they are named as the first sample power consumption unit to the bth sample power consumption unit respectively;

[0034] Step S27: Perform year-on-year analysis on the target electricity consumption unit based on the electricity consumption from the first single day to the ath single day to obtain the target electricity consumption year-on-year coefficient;

[0035] Step S28: acquiring year-on-year electricity consumption coefficients for the first sample electricity consumption unit to the bth sample electricity consumption unit respectively, and obtaining the first year-on-year electricity consumption coefficient to the bth year-on-year electricity consumption coefficient;

[0036] Step S29: define the first to bth year-on-year electricity consumption coefficients, the first to bth sample electricity consumption units, and the target year-on-year electricity consumption coefficients as year-on-year electricity consumption data.

[0037] Furthermore, the step S24 further includes the following specific steps:

[0038] Step S241: Calculate the daily average power consumption and the daily average power consumption variance to obtain a first power consumption critical value;

[0039] The first power consumption critical value is calculated, and the specific formula is as follows:

[0040] ;

[0041] Among them, Fw1 is the first critical value of electricity consumption, Ydp is the average daily electricity consumption, and Ydf is the variance of the average daily consumption;

[0042] Step S242: Calculate the daily average power consumption and the daily average power consumption variance to obtain a second power consumption threshold;

[0043] The second power consumption critical value is calculated, and the specific formula is as follows:

[0044] ;

[0045] Among them, Fw2 is the second power consumption critical value, Ydp is the daily average power consumption, and Ydf is the daily average power consumption variance.

[0046] Furthermore, the step S27 further includes the following specific steps:

[0047] Step S271: grouping the first day's electricity consumption to the a-th day's electricity consumption according to year to obtain i-year electricity consumption groups, and naming them as the first year's electricity consumption group to the i-th year's electricity consumption group respectively;

[0048] Step S272: Calculate the average of several daily electricity consumptions in the electricity consumption group of the first year to obtain the average daily electricity consumption of the first year;

[0049] Step S273: Obtain the average daily electricity consumption of the years corresponding to the electricity consumption grouping from the second year to the electricity consumption grouping from the i-th year, and obtain the average daily electricity consumption from the second year to the i-th year;

[0050] Step S274: Calculate the average daily electricity consumption in the first year to the average daily electricity consumption in the i-th year to obtain the year-on-year electricity consumption coefficient corresponding to the target electricity consumption unit, and name it the target year-on-year electricity consumption coefficient;

[0051] The details are as follows:

[0052] ;

[0053] Among them, Hbm is the year-on-year electricity consumption coefficient corresponding to the target electricity consumption unit, and Nf1 to Nfi are the average daily electricity consumption in the first year to the average daily electricity consumption in the i-th year respectively.

[0054] Furthermore, the step S3 further includes the following specific steps:

[0055] Step S31: obtaining year-on-year electricity consumption data, and obtaining first to bth sample electricity consumption units respectively according to the year-on-year electricity consumption data;

[0056] Step S32: before the current date, a monitoring time period is selected, and multiple period monitoring dates are selected in the monitoring period, and are named as the first period monitoring date to the cth period monitoring date respectively;

[0057] Step S33: Performing periodic power consumption analysis on the target power consumption unit to obtain a target periodic power consumption coefficient;

[0058] Step S34: respectively acquiring the periodic power consumption coefficients corresponding to the first sample power consumption unit to the bth sample power consumption unit to obtain the first periodic power consumption coefficient to the bth periodic power consumption coefficient;

[0059] Step S35: Obtain the daily power consumption of the first sample power consumption unit corresponding to the first target cycle power consumption to the cth target cycle power consumption, obtain multiple daily power consumptions, and average the multiple daily power consumptions to obtain the cycle average daily power consumption corresponding to the first sample power consumption unit;

[0060] Step S36: respectively obtaining the period average daily power consumption corresponding to the second sample power consumption unit to the bth sample power consumption unit, obtaining multiple period average daily power consumptions, and calculating the average thereof to obtain the predicted reference power consumption;

[0061] Step S37: define the predicted reference power consumption, the target cycle power consumption coefficient, and the first cycle power consumption coefficient to the bth cycle power consumption coefficient as cycle power consumption data.

[0062] Furthermore, the step S33 further includes the following specific steps:

[0063] Step S331: Obtain the power consumption of the target power user unit corresponding to the first cycle monitoring date to the cth cycle monitoring date, and obtain the power consumption of the first target cycle to the cth target cycle;

[0064] Step S332: Calculate the first target cycle power consumption to the cth target cycle power consumption to obtain the cycle power consumption coefficient corresponding to the target power consumption unit, and name it the target cycle power consumption coefficient;

[0065] Calculate the periodic power consumption coefficient corresponding to the target power consumption unit. The specific formula is as follows:

[0066] ;

[0067] Among them, Zym is the periodic power consumption coefficient corresponding to the target power consumption unit, and Zy1 to Zyc are the first target periodic power consumption to the cth target periodic power consumption respectively.

[0068] Furthermore, the step S4 further includes the following specific steps:

[0069] Step S41: Obtain year-on-year electricity consumption data, and obtain the first year-on-year electricity consumption coefficient to the bth year-on-year electricity consumption coefficient, the first sample electricity consumption unit to the bth sample electricity consumption unit, and the target year-on-year electricity consumption coefficient according to the year-on-year electricity consumption data;

[0070] Step S42: obtaining the power consumption prediction coefficient corresponding to the target power consumption unit;

[0071] Step S43: acquiring the power consumption prediction coefficients corresponding to the first sample power consumption unit to the bth sample power consumption unit according to the first cycle power consumption coefficient to the bth cycle power consumption coefficient, the first year-on-year power consumption coefficient to the bth year-on-year power consumption coefficient, and the predicted reference power consumption, to obtain the first power consumption prediction coefficient to the bth power consumption prediction coefficient;

[0072] Step S44: Mark a prediction verification date before the target power dispatch date, obtain the daily power consumption of the first sample power unit to the bth sample power unit on the prediction verification date, and obtain the first verification power consumption to the bth verification power consumption;

[0073] Step S45: establishing a power consumption prediction model through the first power consumption prediction coefficient to the bth power consumption prediction coefficient and the first verification power consumption to the bth verification power consumption;

[0074] Step S46: Substitute the power consumption prediction coefficient corresponding to the target power consumption unit into the power consumption prediction model, and obtain the verification power consumption output by the power consumption prediction model to obtain the predicted power consumption of the target power consumption unit on the target power dispatch date;

[0075] Step S47: respectively obtaining the predicted power consumption of each power user in the power control area on the target power dispatch date to obtain multiple predicted power consumptions, and summing the obtained multiple predicted power consumptions to obtain the predicted power consumption of the power control area;

[0076] Step S48: obtaining the estimated power supply of the power control area through big data; when the predicted power consumption of the power control area is greater than the estimated power supply of the power control area, increasing the power supply to the power control area; when the predicted power consumption of the area is less than the estimated power supply of the power control area, reducing the power supply to the power control area;

[0077] The step S42 further includes the following specific steps:

[0078] Step S421: Acquire periodic power consumption data, and acquire predicted reference power consumption, target periodic power consumption coefficient, and first periodic power consumption coefficient to bth periodic power consumption coefficient according to the periodic power consumption data;

[0079] Step S422: Calculate the target electricity consumption year-on-year coefficient, the target period electricity consumption coefficient, and the predicted reference electricity consumption to obtain the electricity consumption prediction coefficient corresponding to the target electricity consumption unit;

[0080] The electricity consumption forecast coefficient is calculated as follows:

[0081] ;

[0082] Among them, Ydx is the electricity consumption forecast coefficient corresponding to the target electricity consumption unit, Jyl is the predicted benchmark electricity consumption, Hbm is the target electricity consumption year-on-year coefficient, and Zym is the target period electricity consumption coefficient.

[0083] Furthermore, the step S45 further includes the following specific steps:

[0084] Step S451: establishing a polynomial fitting function with the first power consumption prediction coefficient to the bth power consumption prediction coefficient and the first verification power consumption to the bth verification power consumption;

[0085] The polynomial fitting function is as follows:

[0086] ;

[0087] Among them, y is the verified power consumption, x is the power consumption prediction coefficient, and a0 to a n The coefficients of the polynomial fitting function, n is the order of the polynomial fitting function;

[0088] Step S452: Substitute the first power consumption prediction coefficient to the bth power consumption prediction coefficient and the first verification power consumption to the bth verification power consumption into the polynomial fitting function respectively, and calculate the residual sum of squares function RSS of the verification power consumption;

[0089] Step S453: respectively calculate the coefficients a0 to a1 of the polynomial fitting function in the residual sum of squares function RSS. n Calculate partial derivatives and obtain n unknown numbers a0 to a n Function expression, and convert n unknown numbers a0 to a n The function expressions of are combined to obtain n groups containing a0 to a n The system of equations, and solve the system of equations to obtain a0 to a n Specific value of

[0090] Step S454: Convert a0 to a n The specific value of is substituted back into the polynomial fitting function to obtain the electricity consumption prediction model.

[0091] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0092] 1. The present invention obtains multiple weather matching coefficients by performing weather analysis on each characteristic date, and obtains sample date data by filtering the first analysis sample date to the ath analysis sample date from multiple characteristic dates through the weather matching coefficients. This can effectively improve the weather correlation between the sample date and the target power dispatch date, thereby ensuring the accuracy of power consumption forecasting.

[0093] 2. The present invention creates an electricity consumption prediction model based on year-on-year electricity consumption data and periodic electricity consumption data to predict electricity in the power control area, obtains the predicted electricity consumption in the power control area, and performs electricity control in the power control area based on the predicted electricity consumption in the power control area, thereby reducing the risk of electricity waste and insufficient supply and ensuring the stability and reliability of power supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0094] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0095] Figure 1 It is a diagram of the implementation steps of the present invention;

[0096] Figure 2 is the overall system block diagram of the present invention;

[0097] Figure 3 A schematic diagram is established for the electricity consumption prediction model in the present invention. DETAILED DESCRIPTION

[0098] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0099] Embodiment 1

[0100] See also Figure 1 The present invention provides a technical solution: a method for allocating electric power resources based on big data, comprising the following specific steps:

[0101] Step S1: obtaining a power control area, selecting a target power user in the power control area, obtaining a target power dispatch date, selecting multiple characteristic dates corresponding to the target power user according to the target power dispatch date, performing weather analysis on each characteristic date, obtaining multiple weather matching coefficients, and filtering the first analysis sample date to the ath analysis sample date by the weather matching coefficient to obtain sample date data;

[0102] Step S11: randomly selecting a power consumption unit in the power control area as a target power consumption unit;

[0103] Step S12: obtaining a target power dispatch date, and marking a power consumption analysis period with the target power dispatch date as an intermediate date;

[0104] Step S13: Select d historical years as comparative analysis years respectively, mark the electricity consumption analysis period in each comparative analysis year respectively, obtain multiple characteristic dates, and randomly select a sample characteristic date from the multiple characteristic dates;

[0105] Step S14: Perform weather analysis on the sample characteristic date to obtain a weather matching coefficient corresponding to the sample characteristic date;

[0106] The step S14 further includes the following specific steps:

[0107] The details are as follows:

[0108] Step S141: Acquire historical weather data, and acquire the temperature value and wind strength value corresponding to the sample characteristic date according to the historical weather data, and name them as the first temperature value and the first wind strength value respectively;

[0109] Step S142: obtaining a temperature value and a wind strength value corresponding to the target power dispatch date, and naming them as a second temperature value and a second wind strength value, respectively;

[0110] Step S143: obtaining a weather matching coefficient by calculating the first temperature value, the first wind strength value, the second temperature value and the second wind strength value;

[0111] Calculate the weather matching coefficient, the specific formula configuration is as follows:

[0112] ;

[0113] Wherein, Tqx is the weather matching coefficient, Qw1 is the first temperature value, Qw2 is the second temperature value, Wd1 is the first wind strength value, and Wd2 is the second wind strength value;

[0114] Step S15: Repeat the process of obtaining the weather matching coefficient corresponding to the sample characteristic date, and obtain the weather matching coefficient corresponding to each characteristic date respectively;

[0115] Step S16: Obtain a weather matching coefficient threshold, compare the weather matching coefficient corresponding to each characteristic date with the weather matching coefficient threshold, and when the weather matching coefficient is less than the weather matching coefficient threshold, mark the corresponding characteristic date as an analysis sample date, obtain multiple analysis sample dates, and name them as the first analysis sample date to the ath analysis sample date respectively;

[0116] Step S17: defining the first analysis sample date to the ath analysis sample date as sample date data;

[0117] Step S2: obtaining a first electricity consumption critical value, a second electricity consumption critical value, and a number of electricity consumption units according to the sample date data, screening out a first sample electricity consumption unit to a b-th sample electricity consumption unit from a number of electricity consumption units according to the first electricity consumption critical value and the second electricity consumption critical value, and respectively performing electricity consumption year-on-year coefficients on the first sample electricity consumption unit to the b-th sample electricity consumption unit and the target electricity consumption unit to obtain year-on-year electricity consumption data;

[0118] Step S21: Obtain sample date data, and obtain the first analysis sample date to the ath analysis sample date according to the sample date data;

[0119] Step S22: Obtain historical electricity consumption records, and obtain the daily electricity consumption of the target electricity user unit from the first analysis sample date to the ath analysis sample date according to the historical electricity consumption records, and obtain the electricity consumption from the first single day to the ath single day;

[0120] Step S23: Calculate the average of the electricity consumption from the first single day to the ath single day to obtain the daily average electricity consumption, and calculate the variance of the electricity consumption from the first single day to the ath single day to obtain the daily average consumption variance;

[0121] Step S24: obtaining a first power usage threshold and a second power usage threshold;

[0122] The step S24 further includes the following specific steps:

[0123] Step S241: Calculate the daily average power consumption and the daily average power consumption variance to obtain a first power consumption critical value;

[0124] The first power consumption critical value is calculated, and the specific formula is as follows:

[0125] ;

[0126] Among them, Fw1 is the first critical value of electricity consumption, Ydp is the average daily electricity consumption, and Ydf is the variance of the average daily consumption;

[0127] Step S242: Calculate the daily average power consumption and the daily average power consumption variance to obtain a second power consumption threshold;

[0128] The second power consumption critical value is calculated, and the specific formula is as follows:

[0129] ;

[0130] Among them, Fw2 is the second critical value of electricity consumption, Ydp is the average daily electricity consumption, and Ydf is the variance of the average daily consumption;

[0131] Step S25: obtaining a number of electricity consumption units through big data crawler technology, obtaining the average daily electricity consumption of each electricity consumption unit from the first analysis sample date to the ath analysis sample date, and obtaining multiple average daily electricity consumptions;

[0132] Step S26: when the average daily power consumption is between the first power consumption critical value and the second power consumption critical value, the corresponding power consumption unit is marked as a sample power consumption unit, and a plurality of sample power consumption units are obtained, and they are named as the first sample power consumption unit to the bth sample power consumption unit respectively;

[0133] Step S27: Perform year-on-year analysis on the target electricity consumption unit based on the electricity consumption from the first single day to the ath single day to obtain the target electricity consumption year-on-year coefficient;

[0134] The step S27 further includes the following specific steps:

[0135] Step S271: grouping the first day's electricity consumption to the a-th day's electricity consumption according to year to obtain i-year electricity consumption groups, and naming them as the first year's electricity consumption group to the i-th year's electricity consumption group respectively;

[0136] Step S272: Calculate the average of several daily electricity consumptions in the electricity consumption group of the first year to obtain the average daily electricity consumption of the first year;

[0137] Step S273: Obtain the average daily electricity consumption of the years corresponding to the electricity consumption grouping from the second year to the electricity consumption grouping from the i-th year, and obtain the average daily electricity consumption from the second year to the i-th year;

[0138] Step S274: Calculate the average daily electricity consumption in the first year to the average daily electricity consumption in the i-th year to obtain the year-on-year electricity consumption coefficient corresponding to the target electricity consumption unit, and name it the target year-on-year electricity consumption coefficient;

[0139] The details are as follows:

[0140] ;

[0141] Among them, Hbm is the year-on-year electricity consumption coefficient corresponding to the target electricity consumption unit, and Nf1 to Nfi are the average daily electricity consumption in the first year to the average daily electricity consumption in the i-th year respectively;

[0142] Step S28: acquiring year-on-year electricity consumption coefficients for the first sample electricity consumption unit to the bth sample electricity consumption unit respectively, and obtaining the first year-on-year electricity consumption coefficient to the bth year-on-year electricity consumption coefficient;

[0143] Step S29: defining the first electricity consumption year-on-year coefficient to the bth electricity consumption year-on-year coefficient, the first sample electricity consumption unit to the bth sample electricity consumption unit, and the target electricity consumption year-on-year coefficient as year-on-year electricity consumption data;

[0144] Step S3: acquiring the periodic power consumption coefficients corresponding to the target power consumption unit and the multiple sample power consumption units respectively according to the year-on-year power consumption data, obtaining multiple periodic power consumption coefficients, and performing periodic average daily power consumption analysis on the multiple sample power consumption units to obtain predicted benchmark power consumption, and defining the multiple periodic power consumption coefficients and the predicted benchmark power consumption as periodic power consumption data;

[0145] Step S31: obtaining year-on-year electricity consumption data, and obtaining first to bth sample electricity consumption units respectively according to the year-on-year electricity consumption data;

[0146] Step S32: before the current date, a monitoring time period is selected, and multiple period monitoring dates are selected in the monitoring period, and are named as the first period monitoring date to the cth period monitoring date respectively;

[0147] Step S33: Performing periodic power consumption analysis on the target power consumption unit to obtain a target periodic power consumption coefficient;

[0148] The step S33 further includes the following specific steps:

[0149] Step S331: Obtain the power consumption of the target power user unit corresponding to the first cycle monitoring date to the cth cycle monitoring date, and obtain the power consumption of the first target cycle to the cth target cycle;

[0150] Step S332: Calculate the first target cycle power consumption to the cth target cycle power consumption to obtain the cycle power consumption coefficient corresponding to the target power consumption unit, and name it the target cycle power consumption coefficient;

[0151] Calculate the periodic power consumption coefficient corresponding to the target power consumption unit. The specific formula is as follows:

[0152] ;

[0153] Among them, Zym is the periodic power consumption coefficient corresponding to the target power consumption unit, and Zy1 to Zyc are the first target periodic power consumption to the cth target periodic power consumption respectively;

[0154] Step S34: respectively acquiring the periodic power consumption coefficients corresponding to the first sample power consumption unit to the bth sample power consumption unit to obtain the first periodic power consumption coefficient to the bth periodic power consumption coefficient;

[0155] Step S35: Obtain the daily power consumption of the first sample power consumption unit corresponding to the first target cycle power consumption to the cth target cycle power consumption, obtain multiple daily power consumptions, and average the multiple daily power consumptions to obtain the cycle average daily power consumption corresponding to the first sample power consumption unit;

[0156] Step S36: respectively obtaining the period average daily power consumption corresponding to the second sample power consumption unit to the bth sample power consumption unit, obtaining multiple period average daily power consumptions, and calculating the average thereof to obtain the predicted reference power consumption;

[0157] Step S37: defining the predicted reference power consumption, the target cycle power consumption coefficient, and the first cycle power consumption coefficient to the bth cycle power consumption coefficient as cycle power consumption data;

[0158] Step S4: Create a power consumption prediction model based on the year-on-year power consumption data and the periodic power consumption data to perform power prediction for the power control area, obtain the predicted power consumption of the power control area, and perform power control for the power control area based on the predicted power consumption of the power control area;

[0159] Step S41: Obtain year-on-year electricity consumption data, and obtain the first year-on-year electricity consumption coefficient to the bth year-on-year electricity consumption coefficient, the first sample electricity consumption unit to the bth sample electricity consumption unit, and the target year-on-year electricity consumption coefficient according to the year-on-year electricity consumption data;

[0160] Step S42: obtaining the power consumption prediction coefficient corresponding to the target power consumption unit;

[0161] The step S42 further includes the following specific steps:

[0162] Step S421: Acquire periodic power consumption data, and acquire predicted reference power consumption, target periodic power consumption coefficient, and first periodic power consumption coefficient to bth periodic power consumption coefficient according to the periodic power consumption data;

[0163] Step S422: Calculate the target electricity consumption year-on-year coefficient, the target period electricity consumption coefficient, and the predicted reference electricity consumption to obtain the electricity consumption prediction coefficient corresponding to the target electricity consumption unit;

[0164] The electricity consumption forecast coefficient is calculated as follows:

[0165] ;

[0166] Among them, Ydx is the electricity consumption forecast coefficient corresponding to the target electricity consumption unit, Jyl is the predicted benchmark electricity consumption, Hbm is the target electricity consumption year-on-year coefficient, and Zym is the target period electricity consumption coefficient;

[0167] Step S43: acquiring the power consumption prediction coefficients corresponding to the first sample power consumption unit to the bth sample power consumption unit according to the first cycle power consumption coefficient to the bth cycle power consumption coefficient, the first year-on-year power consumption coefficient to the bth year-on-year power consumption coefficient, and the predicted reference power consumption, to obtain the first power consumption prediction coefficient to the bth power consumption prediction coefficient;

[0168] Step S44: Mark a prediction verification date before the target power dispatch date, obtain the daily power consumption of the first sample power unit to the bth sample power unit on the prediction verification date, and obtain the first verification power consumption to the bth verification power consumption;

[0169] Step S45: establishing a power consumption prediction model through the first power consumption prediction coefficient to the bth power consumption prediction coefficient and the first verification power consumption to the bth verification power consumption;

[0170] Step S46: Substitute the power consumption prediction coefficient corresponding to the target power consumption unit into the power consumption prediction model, and obtain the verification power consumption output by the power consumption prediction model to obtain the predicted power consumption of the target power consumption unit on the target power dispatch date;

[0171] Step S47: respectively obtaining the predicted power consumption of each power user in the power control area on the target power dispatch date to obtain multiple predicted power consumptions, and summing the obtained multiple predicted power consumptions to obtain the predicted power consumption of the power control area;

[0172] Step S48: obtaining the estimated power supply of the power control area through big data; when the predicted power consumption of the power control area is greater than the estimated power supply of the power control area, increasing the power supply to the power control area; when the predicted power consumption of the area is less than the estimated power supply of the power control area, reducing the power supply to the power control area;

[0173] See also Figure 3 In step S45, the specific following steps are also included:

[0174] Step S451: establishing a polynomial fitting function with the first power consumption prediction coefficient to the bth power consumption prediction coefficient and the first verification power consumption to the bth verification power consumption;

[0175] The polynomial fitting function is as follows:

[0176] ;

[0177] Among them, y is the verified power consumption, x is the power consumption prediction coefficient, and a0 to a n The coefficients of the polynomial fitting function, n is the order of the polynomial fitting function;

[0178] Step S452: Substitute the first power consumption prediction coefficient to the bth power consumption prediction coefficient and the first verification power consumption to the bth verification power consumption into the polynomial fitting function respectively, and calculate the residual sum of squares function RSS of the verification power consumption;

[0179] Step S453: respectively calculate the coefficients a0 to a1 of the polynomial fitting function in the residual sum of squares function RSS. n Calculate partial derivatives and obtain n unknown numbers a0 to a n Function expression, and convert n unknown numbers a0 to a n The function expressions of are combined to obtain n groups containing a0 to a n The system of equations, and solve the system of equations to obtain a0 to a n Specific value of

[0180] Step S454: Convert a0 to a n The specific value of is substituted back into the polynomial fitting function to obtain the electricity consumption prediction model.

[0181] In this application, if corresponding calculation formulas appear, the above calculation formulas are all dimensionless and take their numerical calculations. The weight coefficients, proportional coefficients and other coefficients in the formulas are set to a result value obtained by quantifying each parameter. The size of the weight coefficient and the proportional coefficient can be determined as long as it does not affect the proportional relationship between the parameter and the result value.

[0182] Embodiment 2

[0183] See also Figure 2 Based on another concept of the same invention, a power resource dispatching system based on big data is now proposed and applied to a power resource dispatching method based on big data. The power resource dispatching system includes a data acquisition module, a year-on-year analysis module, a periodic power consumption module, a prediction and dispatching module and a server. The data acquisition module, the year-on-year analysis module, the periodic power consumption module and the prediction and dispatching module are respectively connected to the server, and the server controls the data acquisition module, the year-on-year analysis module, the periodic power consumption module and the prediction and dispatching module respectively;

[0184] The data acquisition module acquires sample date data;

[0185] Randomly select a power user in the power control area as the target power user;

[0186] Obtain a target power dispatch date, and mark a power consumption analysis period with the target power dispatch date as the intermediate date;

[0187] It should be noted here that:

[0188] The target electricity user is a sample power resource dispatching location in this application, and the target electricity user here is specifically a family residence;

[0189] The power consumption analysis period involved here is specifically a period of time in which the target power dispatch date is an intermediate date. For example, if the target power dispatch date is August 15, the power consumption analysis period can be August 11 to August 19;

[0190] Select d historical years as comparative analysis years respectively, mark the electricity consumption analysis period in each comparative analysis year, obtain multiple characteristic dates, and randomly select a sample characteristic date from the multiple characteristic dates;

[0191] It should be noted here that:

[0192] The comparative analysis year involved here is the d natural years before the year of the target power dispatch date, and the d involved here is specifically the quantity value corresponding to the comparative analysis year, and d is an integer greater than 0;

[0193] Perform weather analysis on the sample characteristic date to obtain the weather matching coefficient corresponding to the sample characteristic date;

[0194] The details are as follows:

[0195] Obtain historical weather data, and obtain a temperature value and a wind strength value corresponding to a sample characteristic date according to the historical weather data, and name them as a first temperature value and a first wind strength value, respectively;

[0196] Obtain a temperature value and a wind strength value corresponding to a target power dispatch date, and name them as a second temperature value and a second wind strength value, respectively;

[0197] It should be noted here that:

[0198] The wind force intensity value involved here is specifically the wind force level corresponding to the prevailing wind direction of the day reported in the weather forecast;

[0199] The first temperature value, the first wind strength value, the second temperature value and the second wind strength value are calculated to obtain a weather matching coefficient;

[0200] Calculate the weather matching coefficient, the specific formula configuration is as follows:

[0201] ;

[0202] Wherein, Tqx is the weather matching coefficient, Qw1 is the first temperature value, Qw2 is the second temperature value, Wd1 is the first wind strength value, and Wd2 is the second wind strength value;

[0203] Repeat the process of obtaining the weather matching coefficient corresponding to the sample characteristic date, and obtain the weather matching coefficient corresponding to each characteristic date respectively;

[0204] Obtain a weather matching coefficient threshold, compare the weather matching coefficient corresponding to each characteristic date with the weather matching coefficient threshold, and when the weather matching coefficient is less than the weather matching coefficient threshold, mark the corresponding characteristic date as an analysis sample date, obtain multiple analysis sample dates, and name them as the first analysis sample date to the ath analysis sample date respectively;

[0205] It should be noted here that:

[0206] In this application, a is the quantity value corresponding to the analysis sample date, and a is an integer greater than 0;

[0207] The first analysis sample date to the ath analysis sample date are defined as sample date data;

[0208] The data acquisition module acquires the sample date data and transmits it to the year-on-year analysis module;

[0209] The year-on-year analysis module performs year-on-year power consumption analysis on the target power-consuming unit based on the sample date data to obtain year-on-year power consumption data;

[0210] Obtain sample date data, and obtain the first analysis sample date to the ath analysis sample date according to the sample date data;

[0211] Obtain historical electricity consumption records, and obtain the daily electricity consumption of the target electricity user unit corresponding to the first analysis sample date to the ath analysis sample date according to the historical electricity consumption records, and obtain the electricity consumption from the first single day to the ath single day;

[0212] Calculate the average of the electricity consumption from the first single day to the ath single day to obtain the daily average electricity consumption;

[0213] Calculate the variance of the electricity consumption from the first single day to the ath single day to obtain the daily average consumption variance;

[0214] The average daily electricity consumption and the average daily electricity consumption variance are calculated to obtain a first electricity consumption critical value;

[0215] The first power consumption critical value is calculated, and the specific formula is as follows:

[0216] ;

[0217] Among them, Fw1 is the first critical value of electricity consumption, Ydp is the average daily electricity consumption, and Ydf is the variance of the average daily consumption;

[0218] The second critical value of electricity consumption is obtained by calculating the average daily electricity consumption and the variance of the average daily electricity consumption;

[0219] The second power consumption critical value is calculated, and the specific formula is as follows:

[0220] ;

[0221] Among them, Fw2 is the second critical value of electricity consumption, Ydp is the average daily electricity consumption, and Ydf is the variance of the average daily consumption;

[0222] Obtain a number of electricity users through big data crawler technology, obtain the average daily electricity consumption of each electricity user from the first analysis sample date to the ath analysis sample date, and obtain multiple average daily electricity consumptions;

[0223] When the average daily electricity consumption is between the first electricity consumption critical value and the second electricity consumption critical value, the corresponding electricity consumption unit is marked as a sample electricity consumption unit, and a plurality of sample electricity consumption units are obtained, and they are named as the first sample electricity consumption unit to the bth sample electricity consumption unit respectively;

[0224] It should be noted here that:

[0225] The b involved here is the quantity value corresponding to the sample electricity unit, and b is an integer greater than 0;

[0226] Conduct a year-on-year analysis of the target electricity consumption unit based on the electricity consumption from the first single day to the a-th single day, and obtain the target electricity consumption year-on-year coefficient;

[0227] The details are as follows:

[0228] The electricity consumption from the first single day to the ath single day is grouped according to the year to obtain i-year electricity consumption groups, which are named the first year electricity consumption group to the i-year electricity consumption group respectively;

[0229] It should be noted here that:

[0230] In this application, i is the quantity value corresponding to the year power consumption group, and i is an integer greater than 0. In the first year power consumption group to the i-th year power consumption group, the year values ​​corresponding to each two consecutive year power consumption groups are also consecutive;

[0231] For example: if the year corresponding to the electricity consumption group in year i-2 is 2022, then the year corresponding to the electricity consumption group in year i-1 is 2021;

[0232] Calculate the average of several single-day electricity consumptions in the electricity consumption group of the first year to obtain the average single-day electricity consumption of the first year;

[0233] Obtain the average daily electricity consumption of the years corresponding to the electricity consumption grouping from the second year to the electricity consumption grouping from the i-th year, and obtain the average daily electricity consumption from the second year to the average daily electricity consumption from the i-th year;

[0234] The average daily electricity consumption in the first year is calculated to the average daily electricity consumption in the i-th year to obtain the year-on-year electricity consumption coefficient corresponding to the target electricity consumption unit, and it is named the target year-on-year electricity consumption coefficient;

[0235] The details are as follows:

[0236] ;

[0237] Among them, Hbm is the year-on-year electricity consumption coefficient corresponding to the target electricity consumption unit, and Nf1 to Nfi are the average daily electricity consumption in the first year to the average daily electricity consumption in the i-th year respectively;

[0238] Obtaining year-on-year electricity consumption coefficients for the first sample electricity consumption unit to the bth sample electricity consumption unit respectively, and obtaining the first year-on-year electricity consumption coefficient to the bth year-on-year electricity consumption coefficient;

[0239] The first electricity consumption year-on-year coefficient to the bth electricity consumption year-on-year coefficient, the first sample electricity consumption unit to the bth sample electricity consumption unit and the target electricity consumption year-on-year coefficient are defined as year-on-year electricity consumption data;

[0240] The year-on-year analysis module acquires the year-on-year electricity consumption data and transmits it to the periodic electricity consumption module;

[0241] The periodic electricity consumption module performs periodic electricity consumption analysis based on the year-on-year electricity consumption data to obtain periodic month-on-month data;

[0242] Obtain year-on-year electricity consumption data, and obtain first to b-th sample electricity consumption units respectively according to the year-on-year electricity consumption data;

[0243] Before the current date, a monitoring time period is selected, and multiple period monitoring dates are selected within the monitoring period, and they are named as the first period monitoring date to the cth period monitoring date respectively;

[0244] It should be noted here that:

[0245] The monitoring time period involved here is a number of dates that are close to the current date, and c involved here is the number value corresponding to the periodic monitoring date, and c is an integer greater than 0;

[0246] Conduct periodic electricity consumption analysis on the target electricity-consuming unit to obtain the target periodic electricity consumption coefficient;

[0247] The details are as follows:

[0248] Obtain the power consumption of the target power user from the first cycle monitoring date to the cth cycle monitoring date, and obtain the power consumption from the first target cycle to the cth target cycle;

[0249] The periodic electricity consumption coefficient corresponding to the target electricity consumption unit is obtained by calculating the first target periodic electricity consumption to the cth target periodic electricity consumption, and is named the target periodic electricity consumption coefficient;

[0250] Calculate the periodic electricity consumption coefficient corresponding to the target electricity consumption unit. The specific formula is as follows:

[0251] ;

[0252] Among them, Zym is the periodic power consumption coefficient corresponding to the target power consumption unit, and Zy1 to Zyc are the first target periodic power consumption to the cth target periodic power consumption respectively;

[0253] Respectively obtain the periodic power consumption coefficients corresponding to the first sample power consumption unit to the bth sample power consumption unit to obtain the first periodic power consumption coefficient to the bth periodic power consumption coefficient;

[0254] Obtain the daily power consumption of the first sample power consumption unit corresponding to the first target cycle power consumption to the cth target cycle power consumption, obtain multiple daily power consumptions, and average the multiple daily power consumptions to obtain the period average daily power consumption corresponding to the first sample power consumption unit;

[0255] The average daily power consumption of the cycles corresponding to the second sample power consumption unit to the bth sample power consumption unit is obtained respectively, and the average daily power consumption of multiple cycles is obtained, and the average is calculated to obtain the predicted benchmark power consumption;

[0256] The predicted reference power consumption, the target cycle power consumption coefficient, and the first cycle power consumption coefficient to the bth cycle power consumption coefficient are defined as cycle power consumption data;

[0257] The periodic power consumption module acquires the periodic power consumption data and transmits it to the prediction and scheduling module;

[0258] The prediction and dispatching module predicts the power consumption of the target power user based on the year-on-year power consumption data and the periodic power consumption data to obtain the target power consumption data;

[0259] Obtain year-on-year electricity consumption data, and obtain the first year-on-year electricity consumption coefficient to the bth year-on-year electricity consumption coefficient, the first sample electricity consumption unit to the bth sample electricity consumption unit, and the target year-on-year electricity consumption coefficient according to the year-on-year electricity consumption data;

[0260] Obtaining periodic power consumption data, and obtaining predicted reference power consumption, target periodic power consumption coefficient, and first periodic power consumption coefficient to b periodic power consumption coefficient according to the periodic power consumption data;

[0261] The target electricity consumption year-on-year coefficient, the target period electricity consumption coefficient and the predicted reference electricity consumption are calculated to obtain the electricity consumption prediction coefficient corresponding to the target electricity consumption unit;

[0262] The electricity consumption forecast coefficient is calculated as follows:

[0263] ;

[0264] Among them, Ydx is the electricity consumption forecast coefficient corresponding to the target electricity consumption unit, Jyl is the predicted benchmark electricity consumption, Hbm is the target electricity consumption year-on-year coefficient, and Zym is the target period electricity consumption coefficient;

[0265] Obtain the electricity consumption prediction coefficients corresponding to the first sample electricity consumption unit to the bth sample electricity consumption unit according to the first cycle electricity consumption coefficient to the bth cycle electricity consumption coefficient, the first year-on-year electricity consumption coefficient to the bth year-on-year electricity consumption coefficient, and the predicted reference electricity consumption, to obtain the first electricity consumption prediction coefficient to the bth electricity consumption prediction coefficient;

[0266] Mark a forecast verification date before the target power dispatch date, obtain the daily power consumption of the first sample power unit to the bth sample power unit on the forecast verification date, and obtain the first verification power consumption to the bth verification power consumption;

[0267] It should be noted here that:

[0268] The forecast verification date involved here is one day before the target power dispatch date;

[0269] Establishing an electricity consumption prediction model through the first electricity consumption prediction coefficient to the bth electricity consumption prediction coefficient and the first verification electricity consumption to the bth verification electricity consumption;

[0270] Substitute the power consumption prediction coefficient corresponding to the target power consumption unit into the power consumption prediction model, and obtain the verification power consumption output by the power consumption prediction model to obtain the predicted power consumption of the target power consumption unit on the target power dispatch date;

[0271] The predicted power consumption of each power user in the power control area on the target power dispatch date is obtained respectively to obtain multiple predicted power consumptions, and the obtained multiple predicted power consumptions are summed to obtain the predicted power consumption of the power control area;

[0272] Obtain the estimated power supply in the power control area through big data. When the predicted power consumption in the power control area is greater than the estimated power supply in the power control area, increase the power supply to the power control area. When the predicted power consumption in the area is less than the estimated power supply in the power control area, reduce the power supply to the power control area.

[0273] Establishing electricity consumption forecasting model;

[0274] The details are as follows:

[0275] Establish a polynomial fitting function for the first power consumption prediction coefficient to the bth power consumption prediction coefficient and the first verification power consumption to the bth verification power consumption;

[0276] The polynomial fitting function is as follows:

[0277] ;

[0278] Among them, y is the verified power consumption, x is the power consumption prediction coefficient, and a0 to a n The coefficients of the polynomial fitting function, n is the order of the polynomial fitting function;

[0279] It should be noted here that:

[0280] In this application, the verification power consumption is the dependent variable and the power consumption prediction coefficient is the independent variable;

[0281] Substitute the first power consumption prediction coefficient to the bth power consumption prediction coefficient and the first verification power consumption to the bth verification power consumption into the polynomial fitting function respectively, and calculate the residual sum of squares function RSS of the verification power consumption;

[0282] The coefficients a0 to a of the polynomial fitting function in the residual sum of squares function RSS are respectively n Calculate partial derivatives and obtain n unknown numbers a0 to a n Function expression, and convert n unknown numbers a0 to a n The function expressions of are combined to obtain n groups containing a0 to a n The system of equations, and solve the system of equations to obtain a0 to a n Specific value of

[0283] Change a0 to a n Substitute the specific value of into the polynomial fitting function to obtain the electricity consumption prediction model;

[0284] Assumptions: The first to third electricity consumption prediction coefficients are 1, 2, and 3 respectively; the first to third verification electricity consumptions are 2, 4, and 6 respectively;

[0285] There are three sets of data points: when x=1, y=2, when x=2, y=3, when x=3, y=6;

[0286] The residual sum of squares (RSS) function is: ;

[0287] in, The model's predicted value at xi, and ;

[0288] Substituting the three sets of data points, we get:

[0289] ;

[0290] Take the partial derivatives of RSS with respect to a0 and a1 respectively, and set them to 0, and we get a0=0, a1=2.

[0291] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for allocating electric power resources based on big data, characterized in that: include: Step S1: obtaining a power control area, selecting a target power user in the power control area, obtaining a target power dispatch date, selecting multiple characteristic dates according to the target power dispatch date, performing weather analysis on each characteristic date, obtaining multiple weather matching coefficients, obtaining the first analysis sample date to the ath analysis sample date through the weather matching coefficients, and obtaining sample date data; Step S2: obtaining a first electricity consumption critical value and a second electricity consumption critical value according to the sample date data, obtaining a plurality of electricity consumption units, screening a plurality of sample electricity consumption units from the plurality of electricity consumption units according to the first electricity consumption critical value and the second electricity consumption critical value, obtaining a plurality of electricity consumption year-on-year coefficients for the sample electricity consumption units and the plurality of sample electricity consumption units, and defining the electricity consumption year-on-year coefficients and the plurality of sample electricity consumption units as year-on-year electricity consumption data; Step S3: acquiring periodic power consumption coefficients for the target power consumption unit and multiple sample power consumption units according to the year-on-year power consumption data, obtaining multiple periodic power consumption coefficients, and analyzing the average daily power consumption of multiple sample power consumption units to obtain predicted benchmark power consumption, and defining the multiple periodic power consumption coefficients and the predicted benchmark power consumption as periodic power consumption data; Step S4: Create a power consumption prediction model based on the year-on-year power consumption data and the periodic power consumption data to perform power prediction for the power control area, obtain the predicted power consumption of the power control area, and perform power control for the power control area based on the predicted power consumption of the power control area; The step S4 further includes the following specific steps: Step S41: acquiring year-on-year electricity consumption data, and acquiring the first year-on-year electricity consumption coefficient to the bth year-on-year electricity consumption coefficient and the target year-on-year electricity consumption coefficient according to the year-on-year electricity consumption data; Step S42: obtaining the power consumption prediction coefficient corresponding to the target power consumption unit; Step S43: acquiring the power consumption prediction coefficients corresponding to the first sample power consumption unit to the bth sample power consumption unit according to the first cycle power consumption coefficient to the bth cycle power consumption coefficient, the first year-on-year power consumption coefficient to the bth year-on-year power consumption coefficient, and the predicted reference power consumption, to obtain the first power consumption prediction coefficient to the bth power consumption prediction coefficient; Step S44: Mark a prediction verification date before the target power dispatch date, obtain the daily power consumption of the first sample power unit to the bth sample power unit on the prediction verification date, and obtain the first verification power consumption to the bth verification power consumption; Step S45: establishing a power consumption prediction model through the first power consumption prediction coefficient to the bth power consumption prediction coefficient and the first verification power consumption to the bth verification power consumption; Step S46: Substitute the power consumption prediction coefficient corresponding to the target power consumption unit into the power consumption prediction model, and obtain the verification power consumption output by the power consumption prediction model to obtain the predicted power consumption of the target power consumption unit on the target power dispatch date; Step S47: respectively obtaining the predicted power consumption of each power user in the power control area on the target power dispatch date to obtain multiple predicted power consumptions, and summing the obtained multiple predicted power consumptions to obtain the predicted power consumption of the power control area; Step S48: obtaining the estimated power supply of the power control area through big data; when the predicted power consumption of the power control area is greater than the estimated power supply of the power control area, increasing the power supply to the power control area; when the predicted power consumption of the area is less than the estimated power supply of the power control area, reducing the power supply to the power control area; The step S42 further includes the following specific steps: Step S421: Acquire periodic power consumption data, and acquire predicted reference power consumption, target periodic power consumption coefficient, and first periodic power consumption coefficient to bth periodic power consumption coefficient according to the periodic power consumption data; Step S422: Calculate the target electricity consumption year-on-year coefficient, the target period electricity consumption coefficient, and the predicted reference electricity consumption to obtain the electricity consumption prediction coefficient corresponding to the target electricity consumption unit; The details are as follows: ； Among them, Hbm is the year-on-year electricity consumption coefficient corresponding to the target electricity consumption unit, and Nf1 to Nfi are the average daily electricity consumption in the first year to the average daily electricity consumption in the i-th year respectively; Calculate the periodic electricity consumption coefficient corresponding to the target electricity consumption unit. The specific formula is as follows: ； Among them, Zym is the periodic power consumption coefficient corresponding to the target power consumption unit, and Zy1 to Zyc are the first target periodic power consumption to the cth target periodic power consumption respectively; The electricity consumption forecast coefficient is calculated as follows: ； Among them, Ydx is the electricity consumption forecast coefficient corresponding to the target electricity consumption unit, Jyl is the predicted benchmark electricity consumption, Hbm is the target electricity consumption year-on-year coefficient, and Zym is the target period electricity consumption coefficient.

2. According to the big data-based power resource allocation method of claim 1, it is characterized in that: The step S1 further includes the following specific steps: Step S11: randomly selecting a power consumption unit in the power control area as a target power consumption unit; Step S12: obtaining a target power dispatch date, and marking a power consumption analysis period with the target power dispatch date as an intermediate date; Step S13: Select d historical years as comparative analysis years respectively, mark the electricity consumption analysis period in each comparative analysis year, obtain multiple characteristic dates, and randomly select a sample characteristic date from the multiple characteristic dates; Step S14: Perform weather analysis on the sample characteristic date to obtain a weather matching coefficient corresponding to the sample characteristic date; Step S15: Repeat step S14 to obtain the weather matching coefficient corresponding to each characteristic date; Step S16: Obtain a weather matching coefficient threshold, compare the weather matching coefficient corresponding to each characteristic date with the weather matching coefficient threshold, and when the weather matching coefficient is less than the weather matching coefficient threshold, mark the corresponding characteristic date as an analysis sample date, obtain multiple analysis sample dates, and name them as the first analysis sample date to the ath analysis sample date respectively; Step S17: define the first analysis sample date to the ath analysis sample date as sample date data.

3. The method for allocating electric power resources based on big data according to claim 2, characterized in that: The step S14 further includes the following specific steps: Step S141: Acquire historical weather data, and acquire the temperature value and wind strength value corresponding to the sample characteristic date according to the historical weather data, and name them as the first temperature value and the first wind strength value respectively; Step S142: obtaining a temperature value and a wind strength value corresponding to the target power dispatch date, and naming them as a second temperature value and a second wind strength value, respectively; Step S143: obtaining a weather matching coefficient by calculating the first temperature value, the first wind strength value, the second temperature value and the second wind strength value; Calculate the weather matching coefficient, the specific formula configuration is as follows: ； Among them, Tqx is the weather matching coefficient, Qw1 is the first temperature value, Qw2 is the second temperature value, Wd1 is the first wind strength value, and Wd2 is the second wind strength value.

4. The method for allocating electric power resources based on big data according to claim 1, characterized in that: The step S2 further includes the following specific steps: Step S21: Obtain sample date data, and obtain the first analysis sample date to the ath analysis sample date according to the sample date data; Step S22: Obtain historical electricity consumption records, and obtain the daily electricity consumption of the target electricity user unit from the first analysis sample date to the ath analysis sample date according to the historical electricity consumption records, and obtain the electricity consumption from the first single day to the ath single day; Step S23: Calculate the average of the electricity consumption from the first single day to the ath single day to obtain the daily average electricity consumption, and calculate the variance of the electricity consumption from the first single day to the ath single day to obtain the daily average consumption variance; Step S24: obtaining a first power usage threshold and a second power usage threshold; Step S25: obtaining a number of electricity consumption units through big data crawler technology, obtaining the average daily electricity consumption of each electricity consumption unit from the first analysis sample date to the ath analysis sample date, and obtaining multiple average daily electricity consumptions; Step S26: when the average daily power consumption is between the first power consumption critical value and the second power consumption critical value, the corresponding power consumption unit is marked as a sample power consumption unit, and a plurality of sample power consumption units are obtained, and they are named as the first sample power consumption unit to the bth sample power consumption unit respectively; Step S27: Perform year-on-year analysis on the target electricity consumption unit based on the electricity consumption from the first single day to the ath single day to obtain the target electricity consumption year-on-year coefficient; Step S28: acquiring year-on-year electricity consumption coefficients for the first sample electricity consumption unit to the bth sample electricity consumption unit respectively, and obtaining the first year-on-year electricity consumption coefficient to the bth year-on-year electricity consumption coefficient; Step S29: define the first to bth year-on-year electricity consumption coefficients, the first to bth sample electricity consumption units, and the target year-on-year electricity consumption coefficients as year-on-year electricity consumption data.

5. The method for allocating electric power resources based on big data according to claim 4 is characterized in that: The step S24 further includes the following specific steps: Step S241: Calculate the daily average power consumption and the daily average power consumption variance to obtain a first power consumption critical value; The first power consumption critical value is calculated, and the specific formula is as follows: ； Among them, Fw1 is the first critical value of electricity consumption, Ydp is the average daily electricity consumption, and Ydf is the variance of the average daily consumption; Step S242: Calculate the daily average power consumption and the daily average power consumption variance to obtain a second power consumption threshold; The second power consumption critical value is calculated, and the specific formula is as follows: ； Among them, Fw2 is the second power consumption critical value, Ydp is the daily average power consumption, and Ydf is the daily average power consumption variance.

6. The method for allocating electric power resources based on big data according to claim 4, characterized in that: The step S27 further includes the following specific steps: Step S271: grouping the first day's electricity consumption to the a-th day's electricity consumption according to year to obtain i-year electricity consumption groups, and naming them as the first year's electricity consumption group to the i-th year's electricity consumption group respectively; Step S272: Calculate the average of several daily electricity consumptions in the electricity consumption group of the first year to obtain the average daily electricity consumption of the first year; Step S273: Obtain the average daily electricity consumption of the years corresponding to the electricity consumption grouping from the second year to the electricity consumption grouping from the i-th year, and obtain the average daily electricity consumption from the second year to the i-th year; Step S274: Calculate the average daily electricity consumption in the first year to the average daily electricity consumption in the i-th year to obtain the year-on-year electricity consumption coefficient corresponding to the target electricity consumption unit, and name it the target year-on-year electricity consumption coefficient.

7. The method for allocating electric power resources based on big data according to claim 1, characterized in that: The step S3 further includes the following specific steps: Step S31: obtaining year-on-year electricity consumption data, and obtaining first to bth sample electricity consumption units respectively according to the year-on-year electricity consumption data; Step S32: before the current date, a monitoring time period is selected, and multiple period monitoring dates are selected in the monitoring period, and are named as the first period monitoring date to the cth period monitoring date respectively; Step S33: Performing periodic power consumption analysis on the target power consumption unit to obtain a target periodic power consumption coefficient; Step S34: respectively acquiring the periodic power consumption coefficients corresponding to the first sample power consumption unit to the bth sample power consumption unit to obtain the first periodic power consumption coefficient to the bth periodic power consumption coefficient; Step S35: Obtain the daily power consumption of the first sample power consumption unit corresponding to the first target cycle power consumption to the cth target cycle power consumption, obtain multiple daily power consumptions, and average the multiple daily power consumptions to obtain the cycle average daily power consumption corresponding to the first sample power consumption unit; Step S36: respectively obtaining the period average daily power consumption corresponding to the second sample power consumption unit to the bth sample power consumption unit, obtaining multiple period average daily power consumptions, and calculating the average thereof to obtain the predicted reference power consumption; Step S37: define the predicted reference power consumption, the target cycle power consumption coefficient, and the first cycle power consumption coefficient to the bth cycle power consumption coefficient as cycle power consumption data.

8. The method for dispatching electric power resources based on big data according to claim 7 is characterized in that: The step S33 further includes the following specific steps: Step S331: Obtain the power consumption of the target power user from the first cycle monitoring date to the cth cycle monitoring date, and obtain the power consumption from the first target cycle to the cth target cycle; Step S332: Calculate the periodic power consumption coefficient corresponding to the target power consumption unit from the first target periodic power consumption to the cth target periodic power consumption, and name it the target periodic power consumption coefficient.

9. The method for allocating electric power resources based on big data according to claim 1, characterized in that: The step S45 further includes the following specific steps: Step S451: establishing a polynomial fitting function with the first power consumption prediction coefficient to the bth power consumption prediction coefficient and the first verification power consumption to the bth verification power consumption; The polynomial fitting function is as follows: ； Among them, y is the verified power consumption, x is the power consumption prediction coefficient, and a0 to a n The coefficients of the polynomial fitting function, n is the order of the polynomial fitting function; Step S452: Substitute the first power consumption prediction coefficient to the bth power consumption prediction coefficient and the first verification power consumption to the bth verification power consumption into the polynomial fitting function respectively, and calculate the residual sum of squares function RSS of the verification power consumption; Step S453: respectively calculate the coefficients a0 to a1 of the polynomial fitting function in the residual sum of squares function RSS. n Calculate partial derivatives and obtain n unknown numbers a0 to a n Function expression, and convert n unknown numbers a0 to a n The function expressions of are combined to obtain n groups containing a0 to a n The system of equations, and solve the system of equations to obtain a0 to a n Specific value of Step S454: Convert a0 to a n The specific value of is substituted back into the polynomial fitting function to obtain the electricity consumption prediction model.

Images