Air conditioner load identification method and device
By calculating the correlation index of temperature and load data, the air conditioner load identification model is trained, and the problem of inaccurate air conditioner load identification in the existing technology is solved, achieving a more efficient air conditioner load identification effect.
Patent Information
- Application Number
- CN202411065709.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-12
AI Technical Summary
It is difficult for the prior art to accurately identify the air conditioner load in the power grid. Traditional methods can easily lead to incorrect judgments and inaccurate results by simply comparing statistical indicators.
By obtaining historical temperature data and load data, determining the comfort temperature interval, calculating summer and winter load-temperature correlation indicators, training the air conditioner load recognition model, and combining the decision tree classification model to identify the air conditioner load in the target area.
It improves the accuracy and efficiency of air conditioning load identification, is more generalized than traditional methods, and can more accurately determine whether the user has air conditioning load.
Smart Images

Figure CN118935604A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the technical field of power load analysis, and in particular to an air conditioning load identification method and device. Background Art
[0002] As the global climate warms and extreme weather increases, the load of air conditioning cooling or heating in the power grid continues to increase, which puts pressure on power grid regulation. If the air conditioning load in the power grid can be estimated, it will provide a basis for power grid regulation. Monitoring the air conditioning load by installing hardware is costly and distorted in many cases. Estimating the air conditioning load through user historical load data is simple, easy and low-cost.
[0003] The existing method of estimating air conditioning load is to select data from dates without air conditioning load in the user's historical load data, compare it with the data from dates with air conditioning load, and simply compare the statistical indicators (mean, median, etc.) of the two to determine whether there is air conditioning load in the user's historical load. The selection of dates without air conditioning load is done by simply specifying fixed dates in spring and autumn. Since the dates on which users use air conditioning are not fixed in different years, the traditional method is prone to incorrectly classifying dates with and without air conditioning load; at the same time, the comparison method of statistical indicators is relatively rough, resulting in inaccurate judgment of whether there is air conditioning load in the user's historical load. Summary of the invention
[0004] The embodiments of the present application provide an air conditioning load identification method and device to accurately identify whether there is an air conditioning load in the user's historical load.
[0005] This application is implemented through the following technical solutions:
[0006] In a first aspect, an embodiment of the present application provides an air conditioning load identification method, comprising:
[0007] Obtain the historical daily temperature data and corresponding historical daily load data for the target area.
[0008] Determine the comfortable temperature range for the target area based on historical daily temperature data.
[0009] Based on the historical daily temperature data that are higher than the comfortable temperature range and the corresponding historical daily load data, the summer load-temperature correlation index data is calculated.
[0010] Based on the historical daily temperature data below the comfortable temperature range and the corresponding historical daily load data, the winter load-temperature correlation index data is calculated.
[0011] The air conditioning load identification model is trained based on the summer load-temperature correlation index data, winter load-temperature correlation index data and the air conditioning load labels of the historical daily load data.
[0012] The air conditioning load data of target users in the target area is identified according to the air conditioning load identification model.
[0013] In conjunction with the first aspect, in some possible implementations, determining a comfortable temperature range of a target area according to historical daily temperature data includes:
[0014] Based on the historical daily temperature data, determine the historical temperature range.
[0015] Calculate the comfortable temperature range based on the historical temperature range, preset value and preset range.
[0016] In conjunction with the first aspect, in some possible implementations, determining a historical temperature range according to historical daily temperature data includes:
[0017] Based on historical daily temperature data, calculate the average daily temperature.
[0018] Based on the daily average temperature, determine the historical temperature range.
[0019] In combination with the first aspect, in some possible implementations, calculating the comfortable temperature interval based on the historical temperature interval, the preset value, and the preset interval includes:
[0020] The intersection of the historical temperature interval and the preset interval is calculated to obtain the first interval.
[0021] The sum of the maximum value of the first interval and the preset value is taken as the maximum value of the comfortable temperature interval.
[0022] The difference between the minimum value of the first interval and the preset value is taken as the minimum value of the comfortable temperature interval.
[0023] In combination with the first aspect, in some possible implementations, summer load-temperature correlation index data is calculated based on historical daily temperature data that is higher than a comfortable temperature range and corresponding historical daily load data, including:
[0024] The first type correlation coefficient between the historical daily temperature data above the comfortable temperature range and the corresponding historical daily load data is calculated, and the first type correlation coefficient is used as the summer load-temperature correlation indicator data.
[0025] According to the historical daily temperature data below the comfortable temperature range and the corresponding historical daily load data, the winter load-temperature correlation index data are calculated, including:
[0026] The second type correlation coefficient between the historical daily temperature data below the comfortable temperature range and the corresponding historical daily load data is calculated, and the second type correlation coefficient is used as the winter load-temperature correlation indicator data.
[0027] In conjunction with the first aspect, in some possible implementations, calculating a first type correlation coefficient between historical daily temperature data above a comfortable temperature range and corresponding historical daily load data includes:
[0028] Take the historical daily load data above the comfortable temperature range and the historical daily average temperature in the historical daily temperature data to calculate the first correlation coefficient.
[0029] The second correlation coefficient is calculated by taking the historical daily load data above the comfortable temperature range and the square root of the difference between the corresponding historical daily average temperature and the maximum value of the comfortable temperature range.
[0030] The third correlation coefficient is calculated by taking the difference between adjacent historical daily load data above the comfortable temperature range and the difference between the corresponding historical daily average temperatures.
[0031] The first correlation coefficient, the second correlation coefficient and the third correlation coefficient are regarded as the first type correlation coefficients.
[0032] In conjunction with the first aspect, in some possible implementations, a calculation formula for the first correlation coefficient is:
[0033]
[0034] Among them, r 1 represents the first correlation coefficient, n represents the number of temperature intervals above the comfortable temperature, X i represents the i-th historical daily load data, Y i represents the historical daily average temperature corresponding to the i-th historical daily load data, Indicates the average of historical daily load data above the comfortable temperature range. Represents the mean of the historical average daily temperatures above the comfort temperature range.
[0035] The calculation formula of the second correlation coefficient is:
[0036]
[0037] Among them, r 2 represents the second correlation coefficient, B i It represents the square root of the difference between the historical daily average temperature corresponding to the i-th historical daily load data and the maximum value of the comfort temperature range. It represents the mean of the square root of the difference between the historical daily average temperature corresponding to the i-th historical daily load data and the maximum value of the comfort temperature range.
[0038] The calculation formula of the third correlation coefficient is:
[0039]
[0040] Among them, r 3 represents the third correlation coefficient, C i represents the difference between the i-th historical daily load data and the i-1-th historical daily load data, represents the mean of the difference between the i-th historical daily load data and the i-1-th historical daily load data, D i represents the difference between the historical daily average temperature corresponding to the i-th historical daily load data and the historical daily average temperature corresponding to the i-1-th historical daily load data, It represents the mean of the difference between the historical daily average temperature corresponding to the i-th historical daily load data and the historical daily average temperature corresponding to the i-1-th historical daily load data.
[0041] In combination with the first aspect, in some possible implementations, calculating a second type correlation coefficient between historical daily temperature data below a comfortable temperature range and corresponding historical daily load data includes:
[0042] The fourth correlation coefficient is calculated by taking the historical daily load data below the comfortable temperature range and the historical daily average temperature in the historical daily temperature data.
[0043] The fifth correlation coefficient is calculated by taking the square root of the difference between the historical daily load data below the comfortable temperature range and the corresponding historical daily average temperature and the minimum value of the comfortable temperature range.
[0044] The sixth correlation coefficient is calculated by taking the difference between adjacent historical daily load data below the comfortable temperature range and the difference between the corresponding historical daily average temperatures.
[0045] The fourth correlation coefficient, the fifth correlation coefficient and the sixth correlation coefficient are regarded as the second type correlation coefficients.
[0046] In combination with the first aspect, in some possible implementations, a calculation formula for the fourth correlation coefficient is:
[0047]
[0048] Among them, r 4 represents the fourth correlation coefficient, m represents the number of intervals below the comfortable temperature, X k represents the kth historical daily load data, Yk represents the historical daily average temperature corresponding to the kth historical daily load data, Represents the average of historical daily load data below the comfortable temperature range, Represents the mean of the historical daily average temperatures that were below the comfort temperature range.
[0049] The calculation formula of the fifth correlation coefficient is:
[0050]
[0051] Among them, r 5 represents the fifth correlation coefficient, B k It represents the square root of the difference between the historical daily average temperature corresponding to the k-th historical daily load data and the minimum value of the comfortable temperature range. It represents the mean of the square root of the difference between the historical daily average temperature corresponding to the kth historical daily load data and the minimum value of the comfortable temperature range.
[0052] The calculation formula of the sixth correlation coefficient is:
[0053]
[0054] Among them, r 6 represents the sixth correlation coefficient, C k represents the difference between the kth historical daily load data and the k-1th historical daily load data, represents the mean of the difference between the kth historical daily load data and the k-1th historical daily load data, D k represents the difference between the historical daily average temperature corresponding to the kth historical daily load data and the historical daily average temperature corresponding to the k-1th historical daily load data, It represents the mean of the difference between the historical daily average temperature corresponding to the k-th historical daily load data and the historical daily average temperature corresponding to the k-1-th historical daily load data.
[0055] In a second aspect, an embodiment of the present application provides an air conditioning load identification device, comprising:
[0056] The data acquisition module is used to obtain the historical daily temperature data and the corresponding historical daily load data of the target area.
[0057] The interval division module is used to determine the comfortable temperature interval of the target area based on the historical daily temperature data.
[0058] The first calculation module is used to calculate the summer load-temperature correlation index data according to the historical daily temperature data that is higher than the comfortable temperature range and the corresponding historical daily load data.
[0059] The second calculation module is used to calculate winter load-temperature correlation index data based on historical daily temperature data below the comfortable temperature range in the historical daily temperature data and corresponding historical daily load data.
[0060] The model training module is used to train an air conditioning load identification model based on summer load-temperature correlation index data, winter load-temperature correlation index data and air conditioning load labels of historical daily load data.
[0061] The result output module is used to identify the air conditioning load data of the target users in the target area according to the air conditioning load identification model.
[0062] It can be understood that the beneficial effects of the second aspect mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.
[0063] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:
[0064] This application divides the temperature data and corresponding load data of the target area by comfortable temperature interval, and then calculates the summer load-temperature correlation index number and winter load-temperature correlation index data respectively. Then, the air conditioning load identification model is obtained based on the summer load-temperature correlation index number, winter load-temperature correlation index data and air conditioning load label training of historical daily load data. The model uses a variety of correlation indicators, combined with the air conditioning load identification model (decision tree classification model), has a strong generalization ability, enhances the applicability of the present invention, and can accurately identify whether the target area users have air conditioning load. Compared with the traditional method of directly determining whether the user's historical load has air conditioning load based on the date, it is more accurate and efficient.
[0065] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present specification. BRIEF DESCRIPTION OF THE DRAWINGS
[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0067] Figure 1 is a flow chart of an air conditioning load identification method provided in an embodiment of the present application;
[0068] Figure 2It is a structural schematic diagram of an air conditioning load identification device provided in one embodiment of the present application. DETAILED DESCRIPTION
[0069] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.
[0070] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.
[0071] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.
[0072] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.
[0073] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.
[0074] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.
[0075] The present application provides an air conditioning load identification method. Figure 1 is a schematic diagram of the process of the air conditioning load identification method provided by an embodiment of the present application, referring to Figure 1 , the air conditioning load identification method is described in detail as follows:
[0076] Step 101, obtaining historical daily temperature data and corresponding historical daily load data of a target area.
[0077] In some specific embodiments, in order to obtain a more accurate air-conditioning load identification model, it is necessary to preprocess the acquired raw data, interpolate the missing dates in the raw data, and eliminate outliers in the load data and temperature data through the Laida criterion (3 sigma criterion) to obtain data for training the air-conditioning load identification model.
[0078] Step 102, determining a comfortable temperature range for the target area based on historical daily temperature data.
[0079] Exemplarily, step 102 may include:
[0080] Based on the historical daily temperature data, determine the historical temperature range.
[0081] Calculate the comfortable temperature range based on the historical temperature range, preset value and preset range.
[0082] In some specific embodiments, compared with directly selecting a comfortable temperature range, calculating a comfortable temperature range based on historical daily temperature data can make the air conditioning load identification model more suitable for the target area and improve the accuracy of the identification result.
[0083] Exemplarily, determining the historical temperature range based on historical daily temperature data includes:
[0084] Based on historical daily temperature data, calculate the average daily temperature.
[0085] Based on the daily average temperature, determine the historical temperature range.
[0086] In some specific embodiments, in addition to determining the historical temperature interval by calculating the average temperature, the historical temperature interval may also be determined based on the daily maximum temperature or the daily minimum temperature.
[0087] In some specific embodiments, the historical temperature interval is determined based on the daily average temperature. After the daily average temperature is calculated, the maximum and minimum values of the daily average temperature are found. The interval between the maximum and minimum values is the historical temperature interval. The process of determining the historical temperature interval based on the daily maximum temperature and the daily minimum temperature is the same as the logical process of obtaining the historical temperature interval from the daily average temperature.
[0088] Exemplarily, based on the historical temperature interval, the preset value and the preset interval, calculating the comfortable temperature interval includes:
[0089] The intersection of the historical temperature interval and the preset interval is calculated to obtain the first interval.
[0090] The sum of the maximum value of the first interval and the preset value is taken as the maximum value of the comfortable temperature interval.
[0091] The difference between the minimum value of the first interval and the preset value is taken as the minimum value of the comfortable temperature interval.
[0092] In some specific embodiments, assuming that the historical temperature interval is 18°C-20°C, assuming that the preset interval is 15°C-25°C, then the first interval is 18°C-20°C. The preset value is a fixed value pre-set considering the fluctuation of the comfortable temperature interval. When the preset value is 1, the comfortable temperature interval in the above example is 17°C-21°C.
[0093] In some specific embodiments, the preset interval can be specifically 15°C-25°C. It is generally believed that the possibility of turning on the air conditioner is small when the temperature is in this range. The preset interval can be adjusted accordingly according to the actual situation of the target area. In order to more accurately identify the air conditioning load, the approximate location of the target area can be first determined according to the latitude and longitude coordinates of the target area, and then the range of the preset interval can be adaptively adjusted according to this position.
[0094] Step 103 , according to the historical daily temperature data that is higher than the comfortable temperature range in the historical daily temperature data and the corresponding historical daily load data, summer load-temperature correlation index data is calculated.
[0095] Exemplarily, step 103 may include:
[0096] The first type correlation coefficient between the historical daily temperature data above the comfortable temperature range and the corresponding historical daily load data is calculated, and the first type correlation coefficient is used as the summer load-temperature correlation indicator data.
[0097] Exemplarily, calculating the first type correlation coefficient between the historical daily temperature data above the comfortable temperature range and the corresponding historical daily load data includes:
[0098] Take the historical daily load data above the comfortable temperature range and the historical daily average temperature in the historical daily temperature data to calculate the first correlation coefficient.
[0099] The second correlation coefficient is calculated by taking the historical daily load data above the comfortable temperature range and the square root of the difference between the corresponding historical daily average temperature and the maximum value of the comfortable temperature range.
[0100] The third correlation coefficient is calculated by taking the difference between adjacent historical daily load data above the comfortable temperature range and the difference between the corresponding historical daily average temperatures.
[0101] The first correlation coefficient, the second correlation coefficient and the third correlation coefficient are regarded as the first type correlation coefficients.
[0102] Exemplarily, the calculation formula of the first correlation coefficient is:
[0103]
[0104] Among them, r 1 represents the first correlation coefficient, n represents the number of temperature intervals above the comfortable temperature, X i represents the i-th historical daily load data, Y i represents the historical daily average temperature corresponding to the i-th historical daily load data, Indicates the average of historical daily load data above the comfortable temperature range. Represents the mean of the historical average daily temperatures above the comfort temperature range.
[0105] The calculation formula of the second correlation coefficient is:
[0106]
[0107] Among them, r 2 represents the second correlation coefficient, B i It represents the square root of the difference between the historical daily average temperature corresponding to the i-th historical daily load data and the maximum value of the comfort temperature range. It represents the mean of the square root of the difference between the historical daily average temperature corresponding to the i-th historical daily load data and the maximum value of the comfort temperature range.
[0108] The calculation formula of the third correlation coefficient is:
[0109]
[0110] Among them, r 3 represents the third correlation coefficient, C i represents the difference between the i-th historical daily load data and the i-1-th historical daily load data, represents the mean of the difference between the i-th historical daily load data and the i-1-th historical daily load data, D i represents the difference between the historical daily average temperature corresponding to the i-th historical daily load data and the historical daily average temperature corresponding to the i-1-th historical daily load data, It represents the mean of the difference between the historical daily average temperature corresponding to the i-th historical daily load data and the historical daily average temperature corresponding to the i-1-th historical daily load data.
[0111] Step 104 , calculating winter load-temperature correlation index data based on the historical daily temperature data below the comfortable temperature range and the corresponding historical daily load data.
[0112] Exemplarily, step 104 may include:
[0113] The second type correlation coefficient between the historical daily temperature data below the comfortable temperature range and the corresponding historical daily load data is calculated, and the second type correlation coefficient is used as the winter load-temperature correlation indicator data.
[0114] Exemplarily, calculating the second type correlation coefficient between the historical daily temperature data below the comfortable temperature range and the corresponding historical daily load data includes:
[0115] The fourth correlation coefficient is calculated by taking the historical daily load data below the comfortable temperature range and the historical daily average temperature in the historical daily temperature data.
[0116] The fifth correlation coefficient is calculated by taking the square root of the difference between the historical daily load data below the comfortable temperature range and the corresponding historical daily average temperature and the minimum value of the comfortable temperature range.
[0117] The sixth correlation coefficient is calculated by taking the difference between adjacent historical daily load data below the comfortable temperature range and the difference between the corresponding historical daily average temperatures.
[0118] The fourth correlation coefficient, the fifth correlation coefficient and the sixth correlation coefficient are regarded as the second type correlation coefficients.
[0119] Exemplarily, the calculation formula of the fourth correlation coefficient is:
[0120]
[0121] Among them, r 4 represents the fourth correlation coefficient, m represents the number of intervals below the comfortable temperature, X k represents the kth historical daily load data, Y k represents the historical daily average temperature corresponding to the kth historical daily load data, Represents the average of historical daily load data below the comfortable temperature range, Represents the mean of the historical daily average temperatures that were below the comfort temperature range.
[0122] The calculation formula of the fifth correlation coefficient is:
[0123]
[0124] Among them, r 5 represents the fifth correlation coefficient, B k It represents the square root of the difference between the historical daily average temperature corresponding to the k-th historical daily load data and the minimum value of the comfortable temperature range. It represents the mean of the square root of the difference between the historical daily average temperature corresponding to the kth historical daily load data and the minimum value of the comfortable temperature range.
[0125] The calculation formula of the sixth correlation coefficient is:
[0126]
[0127] Among them, r 6 represents the sixth correlation coefficient, C k represents the difference between the kth historical daily load data and the k-1th historical daily load data, represents the mean of the difference between the kth historical daily load data and the k-1th historical daily load data, D k represents the difference between the historical daily average temperature corresponding to the kth historical daily load data and the historical daily average temperature corresponding to the k-1th historical daily load data, It represents the mean of the difference between the historical daily average temperature corresponding to the k-th historical daily load data and the historical daily average temperature corresponding to the k-1-th historical daily load data.
[0128] In some specific embodiments, since the load data in the comfortable temperature range generally does not contain air conditioning load, the load data of the target area is divided into three parts according to the comfortable temperature range, namely, data above the range, data below the range, and data in the range. By fully calculating the correlation coefficient between the load and the temperature in the data above the range, and the correlation coefficient between the load and the temperature in the data below the range, the correlation between the data can be fully calculated, thereby ensuring the accuracy of the air conditioning load identification model.
[0129] In addition, the correlation coefficient may be other correlation coefficients such as the Spearman correlation coefficient and the chi-square correlation coefficient in addition to the Pearson correlation coefficient. When calculating the correlation coefficient, in addition to selecting the correlation coefficients between the above-mentioned different data, the correlation coefficients of other data may also be selected, for example: taking the historical daily load data above the comfortable temperature range and the difference between the corresponding daily average temperature to calculate the correlation coefficient. Or taking the historical daily load data above the comfortable temperature range and the difference between the corresponding daily average temperature and the maximum value of the comfortable temperature range to calculate the correlation coefficient, and so on.
[0130] Step 105 , training an air conditioning load identification model based on the summer load-temperature correlation index data, the winter load-temperature correlation index data, and the air conditioning load labels of the historical daily load data.
[0131] In some specific embodiments, summer load-temperature correlation index data and winter load-temperature correlation index data are used as input features and input into a decision tree algorithm. The label of whether there is air-conditioning load is used as a training target to train the decision tree algorithm and obtain an air-conditioning load identification model.
[0132] The decision tree algorithm may be ID3, C4.5 or CART, etc., which is not limited in this embodiment.
[0133] Step 106: Identify air conditioning load data of target users in the target area according to the air conditioning load identification model.
[0134] The above-mentioned air conditioning load identification method divides the temperature data and corresponding load data of the target area by the comfortable temperature range, and then calculates the summer load-temperature correlation index number and the winter load-temperature correlation index data respectively. Then, the air conditioning load identification model is obtained by training the air conditioning load labels of the summer load-temperature correlation index number, the winter load-temperature correlation index data and the historical daily load data. The model uses a variety of correlation indicators, combined with the air conditioning load identification model (decision tree classification model), has a strong generalization ability, enhances the applicability of the present invention, and can accurately identify whether the target area users have air conditioning load. Compared with the traditional method of directly determining whether the user's historical load has air conditioning load based on the date, it is more accurate and efficient.
[0135] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0136] Corresponding to the air conditioning load identification method described in the above embodiment, Figure 2 A structural block diagram of an air conditioning load identification device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.
[0137] See also Figure 2 The air conditioning load identification device in the embodiment of the present application may include:
[0138] The data acquisition module 201 is used to acquire the historical daily temperature data and the corresponding historical daily load data of the target area.
[0139] The interval division module 202 is used to determine the comfortable temperature interval of the target area based on the historical daily temperature data.
[0140] The first calculation module 203 is used to calculate the summer load-temperature correlation index data according to the historical daily temperature data that is higher than the comfortable temperature range and the corresponding historical daily load data.
[0141] The second calculation module 204 is used to calculate winter load-temperature correlation index data according to the historical daily temperature data below the comfortable temperature range in the historical daily temperature data and the corresponding historical daily load data.
[0142] The model training module 205 is used to train an air conditioning load identification model according to the summer load-temperature correlation index data, the winter load-temperature correlation index data and the air conditioning load labels of the historical daily load data.
[0143] The result output module 206 is used to identify the air conditioning load data of the target users in the target area according to the air conditioning load identification model.
[0144] Exemplarily, the interval division module 202 may also be used for:
[0145] Based on the historical daily temperature data, determine the historical temperature range.
[0146] Calculate the comfortable temperature range based on the historical temperature range, preset value and preset range.
[0147] Exemplarily, the interval division module 202 may also be used for:
[0148] Based on historical daily temperature data, calculate the average daily temperature.
[0149] Based on the daily average temperature, determine the historical temperature range.
[0150] Exemplarily, the interval division module 202 may also be used for:
[0151] The intersection of the historical temperature interval and the preset interval is calculated to obtain the first interval.
[0152] The sum of the maximum value of the first interval and the preset value is taken as the maximum value of the comfortable temperature interval.
[0153] The difference between the minimum value of the first interval and the preset value is taken as the minimum value of the comfortable temperature interval.
[0154] Exemplarily, the first calculation module 203 may also be used for:
[0155] The first type correlation coefficient between the historical daily temperature data above the comfortable temperature range and the corresponding historical daily load data is calculated, and the first type correlation coefficient is used as the summer load-temperature correlation indicator data.
[0156] Exemplarily, the second calculation module 204 may also be used for:
[0157] The second type correlation coefficient between the historical daily temperature data below the comfortable temperature range and the corresponding historical daily load data is calculated, and the second type correlation coefficient is used as the winter load-temperature correlation indicator data.
[0158] Exemplarily, the first calculation module 203 may also be used for:
[0159] Take the historical daily load data above the comfortable temperature range and the historical daily average temperature in the historical daily temperature data to calculate the first correlation coefficient.
[0160] The second correlation coefficient is calculated by taking the historical daily load data above the comfortable temperature range and the square root of the difference between the corresponding historical daily average temperature and the maximum value of the comfortable temperature range.
[0161] The third correlation coefficient is calculated by taking the difference between adjacent historical daily load data above the comfortable temperature range and the difference between the corresponding historical daily average temperatures.
[0162] The first correlation coefficient, the second correlation coefficient and the third correlation coefficient are regarded as the first type correlation coefficients.
[0163] Exemplarily, the calculation formula of the first correlation coefficient is:
[0164]
[0165] Among them, r 1 represents the first correlation coefficient, n represents the number of temperature intervals above the comfortable temperature, X i represents the i-th historical daily load data, Y i represents the historical daily average temperature corresponding to the i-th historical daily load data, Indicates the average of historical daily load data above the comfortable temperature range. Represents the mean of the historical average daily temperatures above the comfort temperature range.
[0166] The calculation formula of the second correlation coefficient is:
[0167]
[0168] Among them, r 2 represents the second correlation coefficient, B i It represents the square root of the difference between the historical daily average temperature corresponding to the i-th historical daily load data and the maximum value of the comfort temperature range. It represents the mean of the square root of the difference between the historical daily average temperature corresponding to the i-th historical daily load data and the maximum value of the comfort temperature range.
[0169] The calculation formula of the third correlation coefficient is:
[0170]
[0171] Among them, r 3 represents the third correlation coefficient, C i represents the difference between the i-th historical daily load data and the i-1-th historical daily load data, represents the mean of the difference between the i-th historical daily load data and the i-1-th historical daily load data, D i represents the difference between the historical daily average temperature corresponding to the i-th historical daily load data and the historical daily average temperature corresponding to the i-1-th historical daily load data, It represents the mean of the difference between the historical daily average temperature corresponding to the i-th historical daily load data and the historical daily average temperature corresponding to the i-1-th historical daily load data.
[0172] Exemplarily, the second calculation module 204 may also be used for:
[0173] The fourth correlation coefficient is calculated by taking the historical daily load data below the comfortable temperature range and the historical daily average temperature in the historical daily temperature data.
[0174] The fifth correlation coefficient is calculated by taking the square root of the difference between the historical daily load data below the comfortable temperature range and the corresponding historical daily average temperature and the minimum value of the comfortable temperature range.
[0175] The sixth correlation coefficient is calculated by taking the difference between adjacent historical daily load data below the comfortable temperature range and the difference between the corresponding historical daily average temperatures.
[0176] The fourth correlation coefficient, the fifth correlation coefficient and the sixth correlation coefficient are regarded as the second type correlation coefficients.
[0177] Exemplarily, the calculation formula of the fourth correlation coefficient is:
[0178]
[0179] Among them, r 4 represents the fourth correlation coefficient, m represents the number of intervals below the comfortable temperature, X k represents the kth historical daily load data, Y k represents the historical daily average temperature corresponding to the kth historical daily load data, Represents the average of historical daily load data below the comfortable temperature range, Represents the mean of the historical daily average temperatures that were below the comfort temperature range.
[0180] The calculation formula of the fifth correlation coefficient is:
[0181]
[0182] Among them, r 5 represents the fifth correlation coefficient, B k It represents the square root of the difference between the historical daily average temperature corresponding to the k-th historical daily load data and the minimum value of the comfortable temperature range. It represents the mean of the square root of the difference between the historical daily average temperature corresponding to the kth historical daily load data and the minimum value of the comfortable temperature range.
[0183] The calculation formula of the sixth correlation coefficient is:
[0184]
[0185] Among them, r 6 represents the sixth correlation coefficient, C k represents the difference between the kth historical daily load data and the k-1th historical daily load data, represents the mean of the difference between the kth historical daily load data and the k-1th historical daily load data, D k represents the difference between the historical daily average temperature corresponding to the kth historical daily load data and the historical daily average temperature corresponding to the k-1th historical daily load data, It represents the mean of the difference between the historical daily average temperature corresponding to the k-th historical daily load data and the historical daily average temperature corresponding to the k-1-th historical daily load data.
[0186] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.
[0187] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0188] Those of ordinary skill in the art will appreciate that the templates, units, and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0189] If the module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned various air-conditioning load identification method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal and software distribution medium, etc.
[0190] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.
Claims
1. A method for identifying air conditioning load, characterized in that: include: Obtain historical daily temperature data and corresponding historical daily load data for the target area; Determining a comfortable temperature range for a target area based on the historical daily temperature data; Calculate summer load-temperature correlation index data according to historical daily temperature data that is higher than the comfortable temperature range and corresponding historical daily load data; Calculating winter load-temperature correlation index data according to historical daily temperature data below the comfortable temperature range and corresponding historical daily load data in the historical daily temperature data; An air conditioning load identification model is obtained by training according to the summer load-temperature correlation index data, the winter load-temperature correlation index data and the air conditioning load label of the historical daily load data; The air conditioning load data of target users in the target area is identified according to the air conditioning load identification model.
2. The air conditioning load identification method according to claim 1, characterized in that: Determining the comfortable temperature range of the target area according to the historical daily temperature data includes: Determining a historical temperature range based on the historical daily temperature data; The comfortable temperature interval is calculated based on the historical temperature interval, the preset value and the preset interval.
3. The air conditioning load identification method according to claim 2, characterized in that: Determining the historical temperature range according to the historical daily temperature data includes: Calculating the daily average temperature based on the historical daily temperature data; Based on the daily average temperature, a historical temperature range is determined.
4. The air conditioning load identification method according to claim 2, characterized in that: The calculating the comfortable temperature interval based on the historical temperature interval, the preset value and the preset interval includes: Calculate the intersection of the historical temperature interval and the preset interval to obtain a first interval; Taking the sum of the maximum value of the first interval and the preset value as the maximum value of the comfortable temperature interval; The difference between the minimum value of the first interval and the preset value is used as the minimum value of the comfortable temperature interval.
5. The air conditioning load identification method according to claim 1, characterized in that: The summer load-temperature correlation index data is calculated based on the historical daily temperature data that is higher than the comfortable temperature range and the corresponding historical daily load data, including: Calculate the first type correlation coefficient between the historical daily temperature data above the comfortable temperature range and the corresponding historical daily load data, and use the first type correlation coefficient as the summer load-temperature correlation index data; The winter load-temperature correlation index data is calculated based on the historical daily temperature data that is lower than the comfortable temperature range and the corresponding historical daily load data, including: The second type of correlation coefficient between the historical daily temperature data below the comfortable temperature range and the corresponding historical daily load data is calculated, and the second type of correlation coefficient is used as the winter load-temperature correlation indicator data.
6. The air conditioning load identification method according to claim 5, characterized in that: The calculating of the first type correlation coefficient between the historical daily temperature data above the comfortable temperature range and the corresponding historical daily load data comprises: Take the historical daily load data and the historical daily temperature data that are higher than the comfortable temperature range and calculate the first correlation coefficient; Take the historical daily load data above the comfortable temperature range and the square root of the difference between the corresponding historical daily average temperature and the maximum value of the comfortable temperature range to calculate the second correlation coefficient; Taking the difference between adjacent historical daily load data above the comfortable temperature range and the difference between corresponding historical daily average temperatures, calculate the third correlation coefficient; The first correlation coefficient, the second correlation coefficient and the third correlation coefficient are used as the first type of correlation coefficients.
7. The air conditioning load identification method according to claim 6, characterized in that: The calculation formula of the first correlation coefficient is: Wherein, r1 represents the first correlation coefficient, n represents the number of temperature ranges above the comfortable temperature range, and X i represents the i-th historical daily load data, Y i represents the historical daily average temperature corresponding to the i-th historical daily load data, Indicates the average of historical daily load data above the comfort temperature range. Represents the mean of the historical daily average temperatures above the comfort temperature range; The calculation formula of the second correlation coefficient is: Among them, r2 represents the second correlation coefficient, B i It represents the square root of the difference between the historical daily average temperature corresponding to the i-th historical daily load data and the maximum value of the comfort temperature range. represents the mean of the square root of the difference between the historical daily average temperature corresponding to the i-th historical daily load data and the maximum value of the comfort temperature range; The calculation formula of the third correlation coefficient is: Wherein, r3 represents the third correlation coefficient, C i represents the difference between the i-th historical daily load data and the i-1-th historical daily load data, represents the mean of the difference between the i-th historical daily load data and the i-1-th historical daily load data, D i represents the difference between the historical daily average temperature corresponding to the i-th historical daily load data and the historical daily average temperature corresponding to the i-1-th historical daily load data, It represents the mean of the difference between the historical daily average temperature corresponding to the i-th historical daily load data and the historical daily average temperature corresponding to the i-1-th historical daily load data.
8. The air conditioning load identification method according to claim 5, characterized in that: The calculating of the second type correlation coefficient between the historical daily temperature data below the comfortable temperature range and the corresponding historical daily load data comprises: Take the historical daily load data and the historical daily temperature data that are lower than the comfortable temperature range and calculate the fourth correlation coefficient; Take the historical daily load data below the comfortable temperature range and the square root of the difference between the corresponding historical daily average temperature and the minimum value of the comfortable temperature range to calculate the fifth correlation coefficient; Taking the difference between adjacent historical daily load data below the comfortable temperature range and the difference between corresponding historical daily average temperatures, calculate the sixth correlation coefficient; The fourth correlation coefficient, the fifth correlation coefficient and the sixth correlation coefficient are used as the second type correlation coefficients.
9. The air conditioning load identification method according to claim 8, characterized in that: The calculation formula of the fourth correlation coefficient is: Wherein, r4 represents the fourth correlation coefficient, m represents the number of temperatures below the comfortable temperature range, and X k represents the kth historical daily load data, Y k represents the historical daily average temperature corresponding to the k-th historical daily load data, Represents the average of the historical daily load data below the comfort temperature range. Represents the mean of the historical daily average temperatures below the comfort temperature range; The calculation formula of the fifth correlation coefficient is: Wherein, r5 represents the fifth correlation coefficient, B k It represents the square root of the difference between the historical daily average temperature corresponding to the k-th historical daily load data and the minimum value of the comfortable temperature range. It represents the mean of the square root of the difference between the historical daily average temperature corresponding to the k-th historical daily load data and the minimum value of the comfortable temperature range; The calculation formula of the sixth correlation coefficient is: Wherein, r6 represents the sixth correlation coefficient, C k represents the difference between the kth historical daily load data and the k-1th historical daily load data, represents the mean of the difference between the kth historical daily load data and the k-1th historical daily load data, D k represents the difference between the historical daily average temperature corresponding to the kth historical daily load data and the historical daily average temperature corresponding to the k-1th historical daily load data, It represents the mean of the differences between the historical daily average temperature corresponding to the k-th historical daily load data and the historical daily average temperature corresponding to the k-1-th historical daily load data.
10. An air conditioning load identification device, characterized in that: include: A data acquisition module, used to acquire historical daily temperature data and corresponding historical daily load data of a target area; An interval division module, used for determining a comfortable temperature interval of a target area according to the historical daily temperature data; A first calculation module is used to calculate summer load-temperature correlation index data according to historical daily temperature data that is higher than the comfortable temperature range in the historical daily temperature data and corresponding historical daily load data; A second calculation module is used to calculate winter load-temperature correlation index data according to historical daily temperature data below the comfortable temperature range in the historical daily temperature data and corresponding historical daily load data; A model training module, used for training an air conditioning load identification model according to the summer load-temperature correlation index data, the winter load-temperature correlation index data and the air conditioning load label of the historical daily load data; The result output module is used to identify the air conditioning load data of the target users in the target area according to the air conditioning load identification model.
