Energy consumption estimation method and system of LED lamp and storage medium

Abstract

The invention relates to the technical field of LED energy consumption estimation, in particular to an energy consumption estimation method and system for an LED lamp and a storage medium, and the method comprises the steps: obtaining historical operation data, historical cooking data and historical energy consumption data of the LED lamp at the previous stage, and constructing a comprehensive data set; constructing each historical operation feature sub-function and each user historical cooking feature sub-function based on the comprehensive data set; calculating a historical operation data characteristic function and a user historical cooking characteristic function; and performing nonlinear regression analysis calculation based on the historical operation data feature function, the user historical cooking feature function and the historical energy consumption data to obtain a first energy consumption estimation function, and further calculating the energy consumption of the LED lamp in the next stage. According to the invention, the kitchen LED lamp energy consumption estimation accuracy can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of LED energy consumption estimation, and specifically to an energy consumption estimation method, system and storage medium for an LED lamp. Background Art

[0002] Existing kitchen LED energy consumption estimation methods mainly rely on a simple brightness-power linear relationship for LED energy consumption estimation, without fully considering the influence of historical operation data and user historical cooking data on the energy consumption of the LED lamp, resulting in limited accuracy of kitchen LED lamp energy consumption estimation.

[0003] Therefore, an energy consumption estimation method, system and storage medium for an LED lamp are proposed. Summary of the Invention

[0004] The purpose of the present invention is to provide an energy consumption estimation method, system and storage medium for an LED lamp. By obtaining the historical operation data, user historical cooking data and historical energy consumption data of the LED lamp in the previous stage, and constructing a comprehensive data set; constructing each historical operation feature sub-function and each user historical cooking feature sub-function based on the comprehensive data set; then calculating the historical operation data feature function and the user historical cooking feature function; performing non-linear regression analysis calculation based on the historical operation data feature function, the user historical cooking feature function and the historical energy consumption data, calculating to obtain a first energy consumption estimation function, and then calculating the energy consumption of the LED lamp in the next stage. The present invention can effectively improve the accuracy of kitchen LED lamp energy consumption estimation.

[0005] To achieve the above purpose, the present invention provides the following technical solutions:

[0006] An energy consumption estimation method for an LED lamp, comprising:

[0007] S1. Obtain the historical operation data, user historical cooking data and historical energy consumption data of the LED lamp in the previous stage. The historical operation data includes the brightness data, temperature data, power data and switch state data of the LED lamp; the user historical cooking data includes cooking time node data, cooking type data and cooking duration data, and construct a comprehensive data set;

[0008] S2. Extract the historical operation data feature vector and the user historical cooking feature vector based on the comprehensive data set; calculate each historical operation feature sub-function and each user historical cooking feature sub-function based on these two feature vectors; then calculate the historical operation data feature function and the user historical cooking feature function;

[0009] S3. Perform non-linear regression analysis calculation based on the historical operation data feature function, the user historical cooking feature function and the historical energy consumption data, calculate to obtain a first energy consumption estimation function, and then calculate the energy consumption of the LED lamp in the next stage.

[0010] Preferably, the historical operation data features include switch state features, brightness features, temperature features, and power features; the switch state features include the average daily opening duration and the average daily opening times The brightness features include the average daily opening brightness and the standard deviation of the opening brightness σ B The temperature features include the average daily opening temperature and the temperature-power correlation coefficient ρ T,P The power features include the average daily opening power and the temperature-power correlation coefficient ρ T,P The user's historical cooking features include cooking time distribution features, cooking type features, and cooking duration features; the cooking time distribution features include the average daily cooking frequency and the average daily cooking duration The cooking type features include the average daily time of each cooking type {κ1, κ2,..., κ o} and the average daily lighting time of each cooking type {υ1, υ2,..., υ o}; the cooking duration features include the average daily cooking duration and the correlation coefficient with the average daily opening duration reflecting the relevance between the average daily cooking duration and the average daily opening duration and the average daily opening duration .

[0011] Preferably, each historical operation feature sub-function includes a historical switch state feature sub-function, a historical temperature feature sub-function, a historical brightness feature sub-function, and a historical power feature sub-function; each user's historical cooking feature sub-function includes a cooking time distribution feature sub-function, a cooking type feature sub-function, and a cooking duration feature sub-function.

[0012] Preferably, the historical operation data feature function is as follows:

[0013]

[0014] where H represents the historical operation data feature function; represents the historical brightness feature sub-function; represents the historical temperature feature sub-function; represents the historical switch state feature sub-function; represents the historical power feature sub-function; ω B 、ω B 、ω B and ω B respectively represent the weights of each historical operation data feature sub-function.

[0015] Preferably, the user historical cooking feature function is as follows:

[0016]

[0017] where C represents the user historical cooking feature function; ω t 、ω m and ω d respectively represent the weights of each historical cooking feature sub-function.

[0018] Preferably, the first energy consumption estimation function is as follows:

[0019]

[0020] where E represents the first energy consumption estimation function; θ1 and θ2 represent regression coefficients; ε represents an error term; △T represents the time window of the next stage.

[0021] An energy consumption estimation system for an LED lamp, the system is used to execute the above-mentioned energy consumption estimation method for an LED lamp, including:

[0022] A data acquisition module, which acquires the historical operation data, user historical cooking data, and historical energy consumption data of the LED lamp in the previous stage. The historical operation data includes the brightness data, temperature data, power data, and switch state data of the LED lamp; the historical user kitchen cooking data includes cooking time node data, cooking type data, and cooking duration data, and constructs a comprehensive data set and stores it in the database;

[0023] A feature function construction module, which extracts historical operation data features and user historical cooking features based on the comprehensive data set; constructs each historical operation feature sub-function and each user historical cooking feature sub-function based on these two features; and then constructs a historical operation data feature function and a user historical cooking feature function;

[0024] An energy consumption estimation module, which performs non-linear regression analysis based on the historical operation data feature function, user historical cooking feature function, and historical energy consumption data to obtain the first energy consumption estimation function, and then calculates the energy consumption of the LED lamp in the next stage.

[0025] A computer-readable storage medium, in which there is a program executable by a processor. When the program executable by the processor is executed by the processor, it is used to implement the above-mentioned energy consumption estimation method for an LED lamp.

[0026] Compared with the prior art, the beneficial effects of the present invention are:

[0027] 1. The present invention constructs a comprehensive dataset by obtaining the historical operation data of the LED and the historical cooking data of the user, and can comprehensively estimate the energy consumption of the LED lamp, thereby improving the accuracy of the kitchen LED energy consumption estimation.

[0028] 2. The present invention extracts the historical operation data feature vector and the user historical cooking feature vector based on the comprehensive dataset, and calculates each historical operation feature sub-function and each user historical cooking feature sub-function based on these two feature vectors. Each historical operation feature sub-function includes a historical switch state feature sub-function, a historical temperature feature sub-function, a historical brightness feature sub-function, and a historical power feature sub-function. Each user historical cooking feature sub-function includes a cooking time distribution feature sub-function, a cooking type feature sub-function, and a cooking duration feature sub-function. Then, the historical operation data feature function and the user historical cooking feature function are calculated. Based on the historical operation data feature function and the user historical cooking feature function, it can lay a foundation for the later LED energy consumption estimation, thereby improving the accuracy of the kitchen LED energy consumption estimation.

[0029] 3. The present invention performs non-linear regression analysis calculation based on the historical operation data feature function, the user historical cooking feature function, and the historical energy consumption data, calculates the first energy consumption estimation function, and then calculates the energy consumption of the LED lamp in the next stage, which can improve the accuracy of the kitchen LED energy consumption estimation. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic flow chart of a method for estimating the energy consumption of an LED lamp provided by an embodiment of the present invention;

[0031] Figure 2 It is a schematic structural diagram of a system for estimating the energy consumption of an LED lamp provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0032] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0033] Embodiment 1

[0034] In order to improve the accuracy of the energy consumption estimation of the LED lamp in Kitchen A, a method for estimating the energy consumption of an LED lamp is applied. Refer to Figure 1 It is a schematic flow chart of a method for estimating the energy consumption of an LED lamp provided by an embodiment of the present invention, including:

[0035] S1. Obtain the historical operation data of the LED lights in the previous stage, the user's historical cooking data, and the historical energy consumption data. The historical operation data includes the brightness data, temperature data, power data, and switch status data of the LED lights; the user's historical cooking data includes the cooking time node data, cooking type data, and cooking duration data, and construct a comprehensive data set;

[0036] Further, the switch status data represents the on state and the off state; the brightness data, temperature data, and power data are all data sequences obtained at j moments when the LED lights are in the on state; the brightness data, temperature data, and power data each include j values;

[0037] The comprehensive data set is:

[0038] SD = {B, T, P, S, C t , C m , C d};

[0039] where SD represents the comprehensive data set; B represents the brightness data; T represents the temperature data; P represents the power data; S represents the switch status data; C t represents the cooking time node data; C m represents the cooking type data; C d represents the cooking duration data;

[0040] In this embodiment, by obtaining the historical operation data of the LED and the user's historical cooking data to construct a comprehensive data set, the energy consumption of the LED lights can be comprehensively estimated, thereby improving the accuracy of kitchen LED energy consumption estimation.

[0041] S2. Extract the historical operation data feature vector and the user's historical cooking feature vector based on the comprehensive data set; calculate each historical operation feature sub-function and each user's historical cooking feature sub-function based on these two feature vectors; and then calculate the historical operation data feature function and the user's historical cooking feature function;

[0042] Further, the historical operation data features include switch status features, brightness features, temperature features, and power features; the switch status features include the average daily on duration and the average daily on times The brightness features include the average daily on brightness and the standard deviation of the on brightness σ B ; the temperature features include the average daily on temperature and the temperature-power correlation coefficient ρ T,P ; the power features include the average daily on power and the temperature-power correlation coefficient ρ T,P; The user's historical cooking characteristics include cooking time distribution characteristics, cooking type characteristics, and cooking duration characteristics; the cooking time distribution characteristics include the average daily cooking frequency and the average daily cooking duration The cooking type characteristics include the average daily time of each type of cooking {κ1, κ2,..., κ o} and the average daily lighting time of each cooking type {υ1, υ2,..., υ o}; The cooking duration characteristics include the average daily cooking duration and the correlation coefficient of the average daily opening duration reflecting the correlation between the average daily cooking duration and the average daily opening duration .

[0043] Furthermore, each historical operation characteristic sub - function includes a historical switch state characteristic sub - function, a historical temperature characteristic sub - function, a historical brightness characteristic sub - function, and a historical power characteristic sub - function;

[0044] The historical brightness characteristic sub - function is:

[0045]

[0046] Among them, represents the historical brightness characteristic sub - function; represents the average daily opening brightness on the i - th day; σ B i represents the standard deviation of the opening brightness on the i - th day; β1 and β2 represent the brightness characteristic weight coefficients;

[0047] The historical temperature characteristic sub - function is:

[0048]

[0049] Among them, represents the historical temperature characteristic sub - function; represents the average daily opening temperature on the i - th day; ρ T,P i represents the temperature - power correlation coefficient on the i - th day; ω1 and ω2 represent the temperature characteristic weight coefficients;

[0050] The temperature - power correlation coefficient is:

[0051]

[0052] T i =[T1 i ,T2 i ,T3 i ...T j i ​;

[0053] P i = [P1 i , P2 i , P3 i ...P j i ;

[0054] Where N represents the total number of days; ρ(T i , P i ) represents the Pearson correlation coefficient between the temperature data T i and the power data P i on the i-th day; T i j represents the temperature value at the j-th time point on the i-th day; P i j represents the power value at the j-th time point on the i-th day;

[0055] The historical switch state feature sub-function is:

[0056]

[0057] Where represents the historical switch state feature sub-function; γ1 and γ2 represent the historical switch state feature weights;

[0058] The historical power feature sub-function is:

[0059]

[0060] Where represents the historical power feature sub-function; and represent the historical power feature weights;

[0061] Furthermore, the historical operation data feature function is:

[0062]

[0063] Where H represents the historical operation data feature function; represents the historical brightness feature sub-function; represents the historical temperature feature sub-function; represents the historical switch state feature sub-function; represents the historical power feature sub-function; ω B , ω B , ω B and ω B respectively represent the weights of each historical operation data feature sub-function.

[0064] Furthermore, each user historical cooking feature sub-function includes a cooking time distribution feature sub-function, a cooking type feature sub-function, and a cooking duration feature sub-function.

[0065] The cooking time distribution feature sub-function is:

[0066]

[0067] Wherein, represents the cooking time distribution feature sub-function; α1 and α2 represent the cooking time distribution feature weights;

[0068] The cooking type feature sub-function is:

[0069]

[0070] Wherein, C m (κ1, κ2,..., κ o , υ1, υ2,..., υ o ) represents the cooking type feature sub-function; θ v and θ υ represent the cooking type feature weights; κ v represents the average daily cooking time of the νth cooking type; υ ν represents the average daily lighting time of the νth cooking type;

[0071] The cooking duration feature sub-function is:

[0072]

[0073] Wherein, represents the cooking duration feature sub-function;

[0074] Furthermore, the user historical cooking feature function is:

[0075]

[0076] Wherein, C represents the user historical cooking feature function; ω t 、ω m and ω d respectively represent the weights of each historical cooking feature sub-function.

[0077] In this embodiment, historical operation data feature vectors and user historical cooking feature vectors are extracted based on a comprehensive data set, and various historical operation feature sub-functions and various user historical cooking feature sub-functions are calculated based on these two feature vectors; each historical operation feature sub-function includes a historical switch state feature sub-function, a historical temperature feature sub-function, a historical brightness feature sub-function, and a historical power feature sub-function; each user historical cooking feature sub-function includes a cooking time distribution feature sub-function, a cooking type feature sub-function, and a cooking duration feature sub-function; and then a historical operation data feature function and a user historical cooking feature function are calculated; based on the historical operation data feature function and the user historical cooking feature function, it can lay a foundation for later LED energy consumption estimation, thereby improving the accuracy of kitchen LED energy consumption estimation.

[0078] S3. Perform non-linear regression analysis and calculation based on the historical operation data feature function, the user historical cooking feature function, and the historical energy consumption data, calculate the first energy consumption estimation function, and then calculate the energy consumption of the LED lamp in the next stage.

[0079] Further, the first energy consumption estimation function is:

[0080]

[0081] where E represents the first energy consumption estimation function; θ1 and θ2 represent regression coefficients; ε represents an error term; H next and C next respectively represent the historical operation data feature function and the user historical cooking feature function in the next stage; △T represents the time window in the next stage.

[0082] In this embodiment, non-linear regression analysis and calculation are performed based on the historical operation data feature function, the user historical cooking feature function, and the historical energy consumption data, the first energy consumption estimation function is calculated, and then the energy consumption of the LED lamp in the next stage is calculated, which can improve the accuracy of kitchen LED energy consumption estimation.

[0083] A computer-readable storage medium stores a program executable by a processor, and when the program executable by the processor is executed by the processor, it is used to implement the above-mentioned energy consumption estimation method for an LED lamp.

[0084] In this embodiment, historical operation data of the LED lamp, historical user cooking data, and historical energy consumption data in the previous stage are obtained, and a comprehensive data set is constructed. Based on the comprehensive data set, various historical operation feature sub-functions and various historical user cooking feature sub-functions are constructed. Then, the historical operation data feature function and the historical user cooking feature function are calculated. Nonlinear regression analysis and calculation are performed based on the historical operation data feature function, the historical user cooking feature function, and the historical energy consumption data to calculate the first energy consumption estimation function, and then the energy consumption of the LED lamp in the next stage is calculated. The present invention can effectively improve the accuracy of energy consumption estimation of kitchen LED lamps.

[0085] To verify the effectiveness of an energy consumption estimation method for an LED lamp provided in this embodiment, the accuracy of LED energy consumption estimation for Kitchen A is compared using different methods. The different methods include Method 1, Method 2, and Method 3. Method 1 is an energy consumption estimation method for an LED lamp provided in this embodiment. Method 2 does not consider the operation characteristics of the LED lamp based on Method 1. Method 3 does not consider the user cooking characteristics based on Method 1. The specific comparison is shown in Table 1.

[0086] Table 1 Comparison of the accuracy of LED lamp energy consumption estimation by different methods

[0087] Method Accuracy of energy consumption estimation Method 1 97％ Method 2 91％ Method 3 89％

[0088] As can be seen from Table 1, an energy consumption estimation method for an LED lamp provided in this embodiment has a certain degree of effectiveness.

[0089] Embodiment 2

[0090] To improve the accuracy of energy consumption estimation of the LED lamp in Kitchen B, an energy consumption estimation system for an LED lamp is applied. Refer to Figure 2 which is a schematic structural diagram of an energy consumption estimation system for an LED lamp provided in an embodiment of the present invention, including:

[0091] A data acquisition module that acquires historical operation data of the LED lamp, historical user cooking data, and historical energy consumption data in the previous stage. The historical operation data includes brightness data, temperature data, power data, and switch state data of the LED lamp. The historical user kitchen cooking data includes cooking time node data, cooking type data, and cooking duration data, and constructs a comprehensive data set and stores it in the database.

[0092] Furthermore, the switch state data represents the on state and the off state. The brightness data, temperature data, and power data are all data sequences at j moments acquired when the LED lamp is in the on state. The brightness data, temperature data, and power data each include j values.

[0093] The comprehensive data set is:

[0094] SD = {B, T, P, S, C t , C m , C d};

[0095] Among them, SD represents the comprehensive data set; B represents the brightness data; T represents the temperature data; P represents the power data; S represents the switch state data; C t represents the cooking time node data; C m represents the cooking type data; C d represents the cooking duration data;

[0096] The feature function construction module extracts the historical operation data features and the user's historical cooking features respectively based on the comprehensive data set; constructs each historical operation feature sub-function and each user's historical cooking feature sub-function based on these two features; and then constructs the historical operation data feature function and the user's historical cooking feature function;

[0097] Furthermore, the historical operation data features include the switch state feature, the brightness feature, the temperature feature and the power feature; the switch state feature includes the average daily opening duration and the average daily opening times The brightness feature includes the average daily opening brightness and the standard deviation of the opening brightness σ B ; the temperature feature includes the average daily opening temperature and the temperature-power correlation coefficient ρ T,P ; the power feature includes the average daily opening power and the temperature-power correlation coefficient ρ T,P ; the user's historical cooking features include the cooking time distribution feature, the cooking type feature and the cooking duration feature; the cooking time distribution feature includes the average daily cooking frequency and the average daily cooking duration The cooking type feature includes the average daily time of each type of cooking {κ1, κ2,..., κ o} and the average daily lighting time of each cooking type {υ1, υ2,..., υ o}; the cooking duration feature includes the average daily cooking duration and the correlation coefficient of the average daily opening duration reflecting the relevance between the average daily cooking duration and the average daily opening duration and the average daily opening duration .

[0098] Further, each historical operation characteristic sub - function includes a historical switch - state characteristic sub - function, a historical temperature characteristic sub - function, a historical brightness characteristic sub - function, and a historical power characteristic sub - function; each user historical cooking characteristic sub - function includes a cooking - time distribution characteristic sub - function, a cooking - type characteristic sub - function, and a cooking - duration characteristic sub - function.

[0099] The historical brightness characteristic sub - function is:

[0100]

[0101] Wherein, represents the historical brightness characteristic sub - function; represents the average daily turn - on brightness on the i - th day; σ B i represents the standard deviation of the turn - on brightness on the i - th day; β1 and β2 represent brightness characteristic weight coefficients;

[0102] The historical temperature characteristic sub - function is:

[0103]

[0104] Wherein, represents the historical temperature characteristic sub - function; represents the average daily turn - on temperature on the i - th day; ρ T,P i represents the temperature - power correlation coefficient on the i - th day; ω1 and ω2 represent temperature characteristic weight coefficients;

[0105] The temperature - power correlation coefficient is:

[0106]

[0107] T i =[T1 i ,T2 i ,T3 i ...T j i ;

[0108] P i =[P1 i ,P2 i ,P3 i ...P j i ;

[0109] Wherein, N represents the total number of days; ρ(T i ,P i ) represents the Pearson correlation coefficient between the temperature data T i and the power data P i on the i - th day; T ij represents the temperature value at the j-th moment on the i-th day; P i j represents the power value at the j-th moment on the i-th day;

[0110] The historical switch state feature sub-function is:

[0111]

[0112] Among them, represents the historical switch state feature sub-function; γ1 and γ2 represent the historical switch state feature weights;

[0113] The historical power feature sub-function is:

[0114]

[0115] Among them, represents the historical power feature sub-function; and represent the historical power feature weights;

[0116] Furthermore, the historical operation data feature function is:

[0117]

[0118] Among them, H represents the historical operation data feature function; represents the historical brightness feature sub-function; represents the historical temperature feature sub-function; represents the historical switch state feature sub-function; represents the historical power feature sub-function; ω B 、ω B 、ω B and ω B respectively represent the weights of each historical operation data feature sub-function.

[0119] Furthermore, the historical operation data feature function is:

[0120]

[0121] Among them, H represents the historical operation data feature function; represents the historical brightness feature sub-function; represents the historical temperature feature sub-function; represents the historical switch state feature sub-function; represents the historical power feature sub-function; ω B 、ω B 、ω B and ω BRespectively represent the weights of each historical operation data feature sub-function.

[0122] Furthermore, each user's historical cooking feature sub-functions include a cooking time distribution feature sub-function, a cooking type feature sub-function, and a cooking duration feature sub-function.

[0123] The cooking time distribution feature sub-function is:

[0124]

[0125] Among them, represents the cooking time distribution feature sub-function; α1 and α2 represent the cooking time distribution feature weights;

[0126] The cooking type feature sub-function is:

[0127]

[0128] Among them, C m (κ1, κ2,..., κ o , υ1, υ2,..., υ o ) represents the cooking type feature sub-function; θ v and θ υ represent the cooking type feature weights; κ v represents the average daily cooking time of the νth cooking type; υ ν represents the average daily lighting time of the νth cooking type;

[0129] The cooking duration feature sub-function is:

[0130]

[0131] Among them, represents the cooking duration feature sub-function;

[0132] Furthermore, the user's historical cooking feature function is:

[0133]

[0134] Among them, C represents the user's historical cooking feature function; ω t 、ω m and ω d respectively represent the weights of each historical cooking feature sub-function.

[0135] The energy consumption estimation module performs non-linear regression analysis based on the historical operation data feature function, the user's historical cooking feature function, and the historical energy consumption data to obtain the first energy consumption estimation function, and then calculates the energy consumption of the LED lights in the next stage.

[0136] Furthermore, the first energy consumption estimation function is as follows:

[0137]

[0138] where E represents the first energy consumption estimation function; θ1 and θ2 represent regression coefficients; ε represents an error term; and △T represents the time window of the next stage.

[0139] To verify the effectiveness of the energy consumption estimation system for an LED lamp provided in this embodiment, the accuracy of the LED energy consumption estimation for Kitchen B is compared among different systems; the different methods include System 1, System 2, and System 3; System 1 is the energy consumption estimation system for an LED lamp provided in this embodiment; System 2 does not consider the operating characteristics of the LED lamp based on System 1; System 3 does not consider the user cooking characteristics based on System 1; the specific comparison is shown in Table 2;

[0140] Table 2 Comparison table of the accuracy of LED lamp energy consumption estimation by different methods

[0141] System Accuracy of energy consumption estimation System 1 98％ System 2 90％ System 3 86％

[0142] As can be seen from Table 2, the energy consumption estimation system for an LED lamp provided in this embodiment has a certain effectiveness.

[0143] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An energy consumption estimation method for an LED lamp, characterized in that, Including: S1. Obtain the historical operation data of the LED lamp in the previous stage, the historical cooking data of the user, and the historical energy consumption data. The historical operation data includes the brightness data, temperature data, power data, and switch state data of the LED lamp; the historical cooking data of the user includes the cooking time node data, cooking type data, and cooking duration data, and construct a comprehensive data set; S2. Extract the historical operation data feature vector and the historical cooking feature vector of the user based on the comprehensive data set; calculate each historical operation feature sub-function and each historical cooking feature sub-function of the user based on these two feature vectors; and then calculate the historical operation data feature function and the historical cooking feature function of the user; S3. Perform non-linear regression analysis and calculation based on the historical operation data feature function, the historical cooking feature function of the user, and the historical energy consumption data, calculate the first energy consumption estimation function, and then calculate the energy consumption of the LED lamp in the next stage.

2. The energy consumption estimation method of an LED lamp according to claim 1, characterized in that: The historical operation data features include switch state features, brightness features, temperature features, and power features; The switch state features include the average daily opening duration and the average daily opening times The brightness features include the average daily opening brightness and the standard deviation σ of the opening brightness B ; The temperature features include the average daily opening temperature and the temperature-power correlation coefficient ρ T,P ; The power features include the average daily opening power and the temperature-power correlation coefficient ρ T,P ; The user's historical cooking features include the cooking time distribution feature, the cooking type feature, and the cooking duration feature; The cooking time distribution characteristics include the average daily cooking frequency and the average daily cooking duration The cooking type characteristics include the average daily time of each type of cooking {κ1, κ2,..., κ o} and the average daily lighting time of each cooking type {υ1, υ2,..., υ o}; The cooking duration characteristics include the average daily cooking duration and the correlation coefficient with the average daily opening duration reflecting the correlation between the average daily cooking duration and the average daily opening duration 3. The energy consumption estimation method of an LED lamp according to claim 1, characterized in that: Each historical operation feature sub-function includes a historical switch state feature sub-function, a historical temperature feature sub-function, a historical brightness feature sub-function, and a historical power feature sub-function; each historical cooking feature sub-function of the user includes a cooking time distribution feature sub-function, a cooking type feature sub-function, and a cooking duration feature sub-function.

4. The energy consumption estimation method of an LED lamp according to claim 1, characterized in that: The historical operation data feature function is: Among them, H represents the historical operation data feature function; represents the historical brightness feature sub-function; represents the historical temperature feature sub-function; represents the historical switch state feature sub-function; represents the historical power feature sub-function; ω B 、ω B 、ω B and ω B respectively represent the weights of each historical operation data feature sub-function.

5. A method for estimating the energy consumption of an LED lamp according to claim 1, characterized in that: The historical cooking feature function of the user is: Among them, C represents the user's historical cooking feature function; ω t , ω m and ω d respectively represent the weights of each historical cooking feature sub-function.

6. The energy consumption estimation method of an LED lamp according to claim 1, characterized in that: The first energy consumption estimation function is: where E represents the first energy consumption estimation function; and represent regression coefficients; ε represents the error term; △T represents the time window of the next stage.

7. An energy consumption estimation system for an LED lamp, the system being used to execute an energy consumption estimation method for an LED lamp as described in any one of claims 1 to 6, characterized in that, Including: A data acquisition module that obtains the historical operation data of the LED lamp in the previous stage, the historical cooking data of the user, and the historical energy consumption data. The historical operation data includes the brightness data, temperature data, power data, and switch state data of the LED lamp; the historical cooking data of the user in the kitchen includes the cooking time node data, cooking type data, and cooking duration data, and constructs a comprehensive data set and stores it in the database; A feature function construction module that extracts the historical operation data features and the historical cooking features of the user based on the comprehensive data set; constructs each historical operation feature sub-function and each historical cooking feature sub-function of the user based on these two features; and then constructs the historical operation data feature function and the historical cooking feature function of the user; An energy consumption estimation module that performs non-linear regression analysis based on the historical operation data feature function, the historical cooking feature function of the user, and the historical energy consumption data to obtain the first energy consumption estimation function, and then calculates the energy consumption of the LED lamp in the next stage.

8. A computer-readable storage medium, characterized in that, It stores a program executable by a processor, and when the program executable by the processor is executed by the processor, it is used to implement an energy consumption estimation method for an LED lamp as described in any one of claims 1 to 6.

Images