Air conditioner load identification and quantification method and system based on data analysis

Abstract

The invention relates to the technical field of air conditioners, and discloses an air conditioner load identification and quantification method and system based on data analysis. Acquiring historical daily electrical load data and historical temperature data of each user in the past one year through a user data module; s2, analyzing the historical daily power consumption load data of each user through an analysis unit of an analysis module, and screening out power consumption rule users; s3, analyzing historical daily power consumption load data and historical temperature data of the users with the power consumption rules through an identification unit of an analysis module, and screening out air conditioner users; and S4, the historical daily power consumption load data and the historical temperature data of all the air conditioner users are analyzed through a quantification unit of an analysis module, the summer air conditioner load capacity and the winter air conditioner load capacity of all the air conditioner users are calculated, and therefore a power grid company can communicate with the users with the high air conditioner loads to reduce part of the air conditioner loads so as to relieve the situation of insufficient power.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning, and in particular to a method and system for identifying and quantifying air conditioning load based on data analysis. Background Art

[0002] With the rapid development of economy and automation level, the demand for electricity continues to grow. Power grid companies meet the needs of the majority of users by strengthening the construction of power grid infrastructure and improving the power grid's acceptance and configuration capabilities for clean energy.

[0003] During the peak electricity consumption periods at noon and in the evening in summer or winter, users will use air conditioners, and the electricity demand will increase greatly. There will often be power shortages, which makes the users' air conditioners unable to achieve heating or cooling effects. Usually, power grid companies will ensure that there is sufficient electricity in the non-power outage areas of the management area by taking turns to cut off power in the management area.

[0004] However, current user activities are basically inseparable from electricity. Therefore, even if the power outages are carried out in rotation in the management area, it will still seriously affect the living conditions of users in the outage area, reduce the quality of life of users in the outage area, and bring inconvenience to users. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for identifying and quantifying air conditioning load based on data analysis to solve the following technical problems:

[0006] How to solve the problem of power shortage during peak periods of electricity consumption in summer or winter.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A method for identifying and quantifying air conditioning load based on data analysis comprises the following steps:

[0009] S1: Obtain the historical daily power load data and historical temperature data of each user in the past year through the user data module;

[0010] S2: Analyze the historical daily power load data of each user through the analysis unit of the analysis module to screen out users with regular power consumption;

[0011] S3: Analyze the historical daily power load data and historical temperature data of users with regular power consumption through the recognition unit of the analysis module to screen out air-conditioning users;

[0012] S4: Analyze the historical daily power load data and historical temperature data of each air-conditioning user through the quantization unit of the analysis module to calculate the summer air-conditioning load and winter air-conditioning load of each air-conditioning user.

[0013] As a further solution of the present invention: the historical daily electricity load data includes a load change curve of the daily electricity load changing with time;

[0014] The screening process for users with regular electricity consumption is as follows:

[0015] S10: Obtaining a load variation curve of the user's daily electricity load over time in the past year through a user data module;

[0016] S20: By Heaven and Earth The power load of the day is analyzed to obtain the Tianhedi day correlation coefficient; and is any working day in the past year, and ;

[0017] S30: Analyze the correlation coefficient between all working days of each user in the past year and any other working day, and screen out users with regular electricity usage according to the analysis results.

[0018] As a further solution of the present invention: by formula:

[0019] Calculate the user's Tianhedi Correlation coefficient of day ;

[0020] in, is the number of collection points, is the serial number of the collection point; For the Day's The power load of each collection point; For the Day's The power load of each collection point.

[0021] As a further solution of the present invention: in step S30, the process of screening users with regular electricity usage is as follows:

[0022] Calculate the average correlation coefficient of all weekdays of a user in the past year with any other weekday ;

[0023] The average correlation coefficient value With the first preset value Make a comparison;

[0024] when When , the user is a regular electricity user;

[0025] Otherwise, the user is an irregular electricity user.

[0026] As a further solution of the present invention: by formula Calculate the first judgment index ;

[0027] in, is the judgment function, when hour, ;when hour, ; is a second preset value; is the number of data for the first normal temperature day load set, ; The load concentration for the first normal temperature day is The daily average temperature corresponding to the daily electricity load; is the number of data in the high temperature day load set, ; The load concentration for high temperature days is The daily average temperature corresponding to the daily electricity load.

[0028] As a further solution of the present invention: by formula Calculate the second judgment index ;

[0029] in, is the number of data for the first normal temperature day load set, ; The load concentration for the first normal temperature day is The daily average temperature corresponding to the daily electricity load; is the number of data in the high temperature day load set, ; The load concentration for high temperature days is The daily average temperature corresponding to the daily electricity load.

[0030] As a further solution of the present invention: by formula Calculate the third judgment index ;

[0031] in, is the number of data in the third analysis data set, ; For the third analysis data The daily electricity load with low temperature in the group data; For the third analysis data The daily electricity load with high temperature in the group data; is the third preset value.

[0032] As a further solution of the present invention: in step S3000, by formula:

[0033]

[0034] Calculate summer air conditioning load ;

[0035] By formula:

[0036]

[0037] Calculate winter air conditioning load ;

[0038] in, This is a typical representative daily load variation curve in spring; This is a typical representative daily load variation curve in summer; This is a typical representative daily load change curve in autumn; This is a typical representative daily load variation curve in winter.

[0039] An air conditioning load identification and quantification system based on data analysis, the identification and quantification system comprising:

[0040] User data module, used to store historical daily power load data and historical temperature data;

[0041] An analysis module, including an analysis unit, an identification unit and a quantification unit;

[0042] The analysis unit is used to analyze the historical daily power load data of each user and screen out users with regular power consumption;

[0043] The identification unit is used to analyze the historical daily power load data and historical temperature data of users with regular power consumption to screen out air-conditioning users;

[0044] The quantification unit is used to analyze the historical daily electricity load data and historical temperature data of each air-conditioning user, and calculate the summer air-conditioning load and winter air-conditioning load of each air-conditioning user.

[0045] Beneficial effects of the present invention:

[0046] The present invention obtains the historical daily electricity load data and historical temperature data of each user in the past year through a user data module; analyzes the historical daily electricity load data of each user through an analysis unit of an analysis module to screen out users with regular electricity usage; analyzes the historical daily electricity load data and historical temperature data of users with regular electricity usage through an identification unit of the analysis module to screen out air-conditioning users; analyzes the historical daily electricity load data and historical temperature data of each air-conditioning user through a quantization unit of the analysis module to calculate the summer air-conditioning load and winter air-conditioning load of each air-conditioning user, so that the power grid company can intuitively obtain the summer air-conditioning load and winter air-conditioning load of each user, and during peak electricity consumption, can communicate with users with higher air-conditioning loads to reduce part of the air-conditioning load to alleviate the power shortage. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The present invention will be further described below in conjunction with the accompanying drawings.

[0048] Figure 1 A method flow chart of an embodiment of the present invention;

[0049] Figure 2 A system module framework diagram of an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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.

[0051] See also Figure 1 As shown, in one embodiment, a method for identifying and quantifying air conditioning load based on data analysis is provided, comprising the following steps:

[0052] S1: Obtain the historical daily power load data and historical temperature data of each user in the past year through the user data module;

[0053] S2: Analyze the historical daily power load data of each user through the analysis unit of the analysis module to screen out users with regular power consumption;

[0054] S3: Analyze the historical daily power load data and historical temperature data of users with regular power consumption through the recognition unit of the analysis module to screen out air-conditioning users;

[0055] S4: Analyze the historical daily power load data and historical temperature data of each air-conditioning user through the quantization unit of the analysis module to calculate the summer air-conditioning load and winter air-conditioning load of each air-conditioning user.

[0056] Through the above technical scheme, this embodiment obtains the historical daily electricity load data and historical temperature data of each user in the past year through the user data module; analyzes the historical daily electricity load data of each user through the analysis unit of the analysis module, and screens out users with regular electricity usage; analyzes the historical daily electricity load data and historical temperature data of users with regular electricity usage through the identification unit of the analysis module, and screens out air-conditioning users; analyzes the historical daily electricity load data and historical temperature data of each air-conditioning user through the quantification unit of the analysis module, and calculates the summer air-conditioning load and winter air-conditioning load of each air-conditioning user, so that the power grid company can intuitively obtain the summer air-conditioning load and winter air-conditioning load of each user. During peak electricity consumption, it can communicate with users with higher air-conditioning loads to reduce part of the air-conditioning load to alleviate the power shortage.

[0057] As an implementation mode of the present invention, the historical daily electricity load data includes a load variation curve of the daily electricity load varying with time;

[0058] The screening process for users with regular electricity consumption is as follows:

[0059] S10: Obtaining a load variation curve of the user's daily electricity load over time in the past year through a user data module;

[0060] S20: By Heaven and Earth The power load of the day is analyzed to obtain the Tianhedi Correlation coefficient of the day; and is any working day in the past year, and ;

[0061] S30: Analyze the correlation coefficient between all working days of each user in the past year and any other working day, and select users with regular electricity consumption according to the analysis results;

[0062] Through the above technical solution, this embodiment obtains the load change curve of the user's daily power load over time in the past year through the user data module; Heaven and Earth The power load of the day is analyzed to obtain the Tianhedi The correlation coefficient of each user’s working day in the past year is analyzed with that of any other working day, and users with regular electricity usage are screened out based on the analysis results. The air conditioning load of users with regular electricity usage is identified and quantified to improve the accuracy of quantification.

[0063] As an embodiment of the present invention, Tianhedi The process of obtaining the correlation coefficient of the day is:

[0064] Select enough time collection points between 0:00 and 24:00;

[0065] Get a user's Tianhedi The load variation curve of daily electricity load changing with time;

[0066] In the Tianhedi Obtain the corresponding power load at each time point on the load change curve of the daily power load over time;

[0067] Then through the formula Calculate the user's Tianhedi Correlation coefficient of day ;

[0068] in, is the number of collection points, is the serial number of the collection point; For the Day's The power load of each collection point; For the Day's The power load of each collection point;

[0069] Through the above technical solution, this embodiment selects enough time collection points between 0:00 and 24:00 to obtain a user's Tianhedi The load variation curve of daily electricity load over time; Tianhedi The daily electricity load of the day changes with time. The corresponding electricity load is obtained at each time point on the load change curve; then the formula is used to Calculate the user's Tianhedi The correlation coefficient of the day; the formula of the correlation coefficient is the existing technology, and the derivation process is not described in detail; the correlation coefficient The bigger, the Tianhedi The more similar the load change curves of the day are; the correlation coefficient The smaller, the Tianhedi The load variation curves of the days are more dissimilar.

[0070] As an implementation mode of the present invention, in step S30, the process of screening users with regular electricity usage is as follows:

[0071] Calculate the average correlation coefficient of all weekdays of a user in the past year with any other weekday ;

[0072] The average correlation coefficient value With the first preset value Make a comparison;

[0073] when When , the user is a regular electricity user;

[0074] Otherwise, the user is an irregular electricity user;

[0075] Through the above technical solution, this embodiment calculates the average correlation coefficient value of the correlation coefficient of all working days of a user in the past year with any other working day ; In the average correlation coefficient value With the first preset value To compare; when When the user is a regular electricity user, otherwise, the user is an irregular electricity user. The average correlation coefficient value of the correlation coefficient of all working days of a user in the past year with any other working day is Improve the accuracy of the result of judging whether the user has regular electricity usage;

[0076] It should be noted that the first preset value is a preset value, obtained based on experience, the first preset value It can be 0.8; the average correlation coefficient value is obtained by comparing the correlation coefficient of each working day of a user with any other working day in the past year. The method is prior art and will not be described in detail here.

[0077] As an implementation mode of the present invention, in step S3, the screening process of air conditioner users includes the following steps:

[0078] S100: Obtain the daily power load data and temperature data of the i-th user from March to October in the past year as the first analysis data set through the user data module; use the Kmeans clustering algorithm to calculate the power load data of the first analysis data set, and divide it into a first normal temperature day load set and a high temperature day load set;

[0079] S200: Obtain a first judgment index by analyzing the temperature data of the first normal temperature day load set, the high temperature day load set, and the first analysis data set:

[0080] S300: Obtain the daily power load data and temperature data of the user from November to February in the past year as a second analysis data set through the user data module; calculate the power load data of the second analysis data set using the Kmeans clustering algorithm to divide it into a second normal temperature daily load set and a low temperature daily load set;

[0081] S400: Obtain a second judgment index by analyzing the temperature data of the second normal temperature day load set, the low temperature day load set, and the second analysis data set:

[0082] S500: Obtaining a third judgment index by analyzing the daily power load data and temperature data throughout the year;

[0083] S600: Determine whether the user is an air-conditioning user by analyzing the first judgment index, the second judgment index and the third judgment index;

[0084] S700: Make , repeat steps S100-S600; until , proceed to step S800; is the total number of users; is the user's serial number;

[0085] S800: Filter out all users who are determined to be air-conditioning users;

[0086] It should be noted that the Kmeans clustering algorithm is an existing technology, so the method of obtaining the first normal temperature day load set, the high temperature day load set, the second normal temperature day load set and the low temperature day load set will not be described in detail here.

[0087] As an embodiment of the present invention, in step S200, by formula Calculate the first judgment index ;

[0088] in, is the judgment function, when hour, ;when hour, ; is a second preset value; is the number of data for the first normal temperature day load set, ; The load concentration for the first normal temperature day is The daily average temperature corresponding to the daily electricity load; is the number of data in the high temperature day load set, ; The load concentration for high temperature days is The daily average temperature corresponding to the daily electricity load;

[0089] Through the above technical solution, this embodiment is the first normal temperature day average value of the first normal temperature day load set; is the high temperature day average value of the high temperature day load set; is the difference between the average value of the high temperature day and the average value of the first normal temperature day; When , it means that the average value of high temperature day is much different from the average value of the first normal temperature day, so the probability of high temperature day load being concentrated in summer air conditioning load is high. ;when When , it means that the difference between the average value of high temperature day and the average value of the first normal temperature day is small, so the probability that the high temperature day load is concentrated in the summer air conditioning load is small. ;

[0090] It should be noted that the second preset value It is a preset value obtained based on experience and will not be described in detail here.

[0091] In step S400, by formula Calculate the second judgment index ;

[0092] in, is the number of data in the first normal temperature day load set, ; The load concentration for the first normal temperature day is The daily average temperature corresponding to the daily electricity load; is the number of data in the high temperature day load set, ; The load concentration for high temperature days is The daily average temperature corresponding to the daily electricity load;

[0093] Through the above technical solution, this embodiment is the second normal temperature day average value of the second normal temperature day load set; is the low temperature daily average value of the low temperature daily load set; is the difference between the second normal temperature daily average and the low temperature daily average; When , it means that the average value of the second normal temperature day is quite different from the average value of the low temperature day, so the probability of the winter air conditioning load being concentrated on the low temperature day load is high. ;when When , it means that the difference between the low temperature daily average value and the second normal temperature daily average value is small, so the probability that the low temperature daily load is concentrated in the summer air conditioning load is small. .

[0094] In step S500, all groups of dates satisfying the condition that the user has two consecutive working days in the past year, one of which has a maximum temperature greater than 30°C and the other of which has a maximum temperature less than 25°C, are selected as the third analysis data set;

[0095] By formula Calculate the third judgment index ;

[0096] in, is the number of data in the third analysis data set, ; For the third analysis data The daily electricity load with low temperature in the group data; For the third analysis data The daily electricity load with high temperature in the group data; is the third preset value;

[0097] In step S600, when When , the user is judged to be an air-conditioning user, otherwise, the user is not an air-conditioning user;

[0098] Through the above technical solution, this embodiment For the third analysis data The ratio of the difference between the daily electricity load at high temperature and the daily electricity load at low temperature in the group data to the daily electricity load at low temperature; for The average ratio of the difference between the daily power load at high temperature and the daily power load at low temperature in the group data to the daily power load at low temperature, the average ratio The larger the In the data of the group, the daily electricity load of high temperature is different from that of low temperature. When , it means that the probability of air conditioning load in the daily power load with high temperature is high. ;when When , it means that the probability of air conditioning load in the daily power load with low temperature and high temperature is small. ;when and When both are 1 or and When both are 1, the user can be judged as an air-conditioning user, which improves the accuracy of the judgment result;

[0099] It should be noted that the third preset value It is a preset value obtained based on experience and will not be described in detail here.

[0100] As an implementation mode of the present invention, the process of obtaining the summer air conditioning load and the winter air conditioning load of the i-th air conditioning user includes the following steps:

[0101] S1000: By analyzing the temperature data of the i-th user in the past year, the typical load sets of four seasons are obtained;

[0102] S2000: Analyze the data of typical load sets in four seasons respectively, and obtain the typical representative daily load change curves of four seasons respectively;

[0103] S3000: By analyzing the typical daily load change curves of the four seasons, the summer air conditioning load and winter air conditioning load are obtained;

[0104] Through the above technical scheme, this embodiment selects the daily load change curves corresponding to all dates that meet the conditions of daily minimum temperature greater than or equal to 15°C, average temperature greater than 20°C and less than 25°C, and maximum temperature less than 27°C during the working days from January to June of the past year as the typical load set for spring; selects the daily load change curves corresponding to all dates that meet the conditions of daily maximum temperature greater than 34°C during the working days from June to December of the past year as the typical load set for summer; selects the daily load change curves corresponding to all dates that meet the conditions of daily minimum temperature greater than or equal to 15°C, average temperature greater than 20°C and less than 25°C, and maximum temperature less than 27°C during the working days from June to December of the past year as the typical load set for autumn; selects the daily load change curves corresponding to all dates that meet the conditions of daily maximum temperature less than 10°C and average temperature less than 5°C during the working days of the past year as the typical load set for winter; obtains the typical load sets for four seasons; and then selects the daily load change curves corresponding to all dates that meet the conditions of daily maximum temperature less than 10°C and average temperature less than 5°C during the working days of the past year as the typical load set for winter; The data of the typical load set are analyzed to obtain the typical representative daily load change curves of the four seasons; taking the process of obtaining the typical representative daily load change curve in spring as an example, the similarity of every two daily load change curves in the typical load set in spring is calculated, and the daily load change curve with a similarity greater than the third preset value is selected, and then the distance between every two daily load change curves is calculated through the DTW matrix; the one with the smallest distance is selected as the typical representative daily load change curve in spring; similarly, the typical representative daily load change curve in summer, the typical representative daily load change curve in autumn and the typical representative daily load change curve in season are obtained; finally, by analyzing the typical representative daily load change curves of the four seasons, the summer air-conditioning load and winter air-conditioning load of the i-th user are obtained; thus, the power grid company can intuitively obtain the summer air-conditioning load and winter air-conditioning load of each user, and during the peak period of electricity consumption, it can communicate with users with higher air-conditioning loads to reduce part of the air-conditioning load to alleviate the power shortage;

[0105] It should be noted that calculating the similarity of two curves and calculating the distance between each two curves using the DTW matrix are prior arts and will not be described in detail here.

[0106] As an implementation of the present invention, in step S3000, by formula:

[0107]

[0108] Calculate summer air conditioning load ;

[0109] By formula:

[0110]

[0111] Calculate winter air conditioning load ;

[0112] in, This is a typical representative daily load variation curve in spring; This is a typical representative daily load variation curve in summer; This is a typical representative daily load change curve in autumn; This is a typical representative daily load variation curve in winter;

[0113] Through the above technical solution, this embodiment is the accumulated load of a typical day in summer; is the accumulated load on a typical day in spring; The difference between the cumulative load of a typical day in summer and the cumulative load of a typical day in spring is the summer air conditioning load. is the accumulated load of a typical day in winter; is the accumulated load of a typical day in autumn; It is the difference between the cumulative load of a typical day in winter and the cumulative load of a typical day in autumn, which is the winter air-conditioning load.

[0114] See also Figure 2 As shown, an air conditioning load identification and quantification system based on data analysis, the identification and quantification system includes:

[0115] User data module, used to store historical daily power load data and historical temperature data;

[0116] An analysis module, including an analysis unit, an identification unit and a quantification unit;

[0117] The analysis unit is used to analyze the historical daily power load data of each user and screen out users with regular power consumption;

[0118] The identification unit is used to analyze the historical daily power load data and historical temperature data of users with regular power consumption to screen out air-conditioning users;

[0119] The quantification unit is used to analyze the historical daily electricity load data and historical temperature data of each air-conditioning user, and calculate the summer air-conditioning load and winter air-conditioning load of each air-conditioning user.

[0120] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for identifying and quantifying air conditioning load based on data analysis, characterized in that: The identification and quantification method comprises the following steps: S1: Obtain the historical daily power load data and historical temperature data of each user in the past year through the user data module; S2: Analyze the historical daily power load data of each user through the analysis unit of the analysis module to screen out users with regular power consumption; S3: Analyze the historical daily power load data and historical temperature data of users with regular power consumption through the recognition unit of the analysis module to screen out air-conditioning users; S4: Analyze the historical daily power load data and historical temperature data of each air-conditioning user through the quantization unit of the analysis module to calculate the summer air-conditioning load and winter air-conditioning load of each air-conditioning user.

2. The method for identifying and quantifying air conditioning load based on data analysis according to claim 1, characterized in that: The historical daily electricity load data includes a load change curve of the daily electricity load changing over time; The screening process for users with regular electricity consumption is as follows: S10: Obtaining a load variation curve of the user's daily electricity load over time in the past year through a user data module; S20: By Heaven and Earth The power load of the day is analyzed to obtain the Tianhedi day correlation coefficient; and is any working day in the past year, and ; S30: Analyze the correlation coefficient between all working days of each user in the past year and any other working day, and screen out users with regular electricity usage according to the analysis results.

3. The method for identifying and quantifying air conditioning load based on data analysis according to claim 2, characterized in that: By formula , calculate the user's Tianhedi Correlation coefficient of day ; in, is the number of collection points, is the serial number of the collection point; For the Day's The power load of each collection point; For the Day's The power load of each collection point.

4. The method for identifying and quantifying air conditioning load based on data analysis according to claim 3 is characterized in that: In step S30, the process of screening users with regular electricity usage is as follows: Calculate the average correlation coefficient of all weekdays of a user in the past year with any other weekday ; The average correlation coefficient value With the first preset value Make a comparison; when When , the user is a regular electricity user; Otherwise, the user is an irregular electricity user.

5. The method for identifying and quantifying air conditioning load based on data analysis according to claim 4 is characterized in that: By formula Calculate the first judgment index ; in, is the judgment function, when hour, ;when hour, ; is a second preset value; is the number of data in the first normal temperature day load set, ; The load concentration for the first normal temperature day is The daily average temperature corresponding to the daily electricity load; is the number of data in the high temperature day load set, ; The load concentration for high temperature days is The daily average temperature corresponding to the daily electricity load.

6. The method for identifying and quantifying air conditioning load based on data analysis according to claim 5, characterized in that: By formula Calculate the second judgment index ; in, is the number of data in the first normal temperature day load set, ; The load concentration for the first normal temperature day is The daily average temperature corresponding to the daily electricity load; is the number of data in the high temperature day load set, ; The load concentration for high temperature days is The daily average temperature corresponding to the daily electricity load.

7. The method for identifying and quantifying air conditioning load based on data analysis according to claim 6, characterized in that: By formula Calculate the third judgment index ; in, is the number of data in the third analysis data set, ; For the third analysis data The daily electricity load with low temperature in the group data; For the third analysis data The daily electricity load with high temperature in the group data; is the third preset value.

8. The method for identifying and quantifying air conditioning load based on data analysis according to claim 7, characterized in that: In step S3000, by formula: ； Calculate summer air conditioning load ; By formula: ； Calculate winter air conditioning load ; in, This is a typical representative daily load variation curve in spring; This is a typical representative daily load variation curve in summer; This is a typical representative daily load change curve in autumn; This is a typical representative daily load variation curve in winter.

9. An air conditioning load identification and quantification system based on data analysis, applicable to an air conditioning load identification and quantification method based on data analysis according to any one of claims 1 to 8, characterized in that: The identification and quantification system comprises: User data module, used to store historical daily power load data and historical temperature data; An analysis module, including an analysis unit, an identification unit and a quantification unit; The analysis unit is used to analyze the historical daily power load data of each user and screen out users with regular power consumption; The identification unit is used to analyze the historical daily power load data and historical temperature data of users with regular power consumption to screen out air-conditioning users; The quantification unit is used to analyze the historical daily electricity load data and historical temperature data of each air-conditioning user, and calculate the summer air-conditioning load and winter air-conditioning load of each air-conditioning user.

Images