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

Abstract

The present application relates to the technical field of LED energy consumption estimation, in particular to a kind of LED lamp's energy consumption estimation method, system and storage medium, comprising: the present application obtains the historical operation data of last stage LED lamp, user historical cooking data and historical energy consumption data, and constructs comprehensive dataset;Each historical operation characteristic subfunction and each user historical cooking characteristic subfunction are constructed based on comprehensive dataset;Further, historical operation data characteristic function and user historical cooking characteristic function are calculated;Based on historical operation data characteristic function, user historical cooking characteristic function and historical energy consumption data, nonlinear regression analysis calculation is carried out, and first energy consumption estimation function is calculated, and then the energy consumption of next stage LED lamp is calculated.The present application can effectively improve the accuracy of kitchen LED lamp energy consumption estimation.

Description

Technical Field

[0001] This invention relates to the field of LED energy consumption estimation technology, specifically to a method, system, and storage medium for estimating the energy consumption of LED lamps. Background Technology

[0002] Existing methods for estimating kitchen LED energy consumption mainly rely on a simple linear relationship between brightness and power, without fully considering the impact of historical operating data and user's historical cooking data on LED light energy consumption, thus limiting the accuracy of kitchen LED light energy consumption estimation.

[0003] To address this, a method, system, and storage medium for estimating the energy consumption of LED lights are proposed. Summary of the Invention

[0004] The purpose of this invention is to provide a method, system, and storage medium for estimating the energy consumption of LED lights. This involves acquiring historical operating data of the LED lights from the previous stage, historical cooking data from users, and historical energy consumption data, and constructing a comprehensive dataset. Based on this comprehensive dataset, various historical operating characteristic functions and user historical cooking characteristic functions are constructed. Then, the historical operating data characteristic functions and user historical cooking characteristic functions are calculated. Based on these functions and historical energy consumption data, nonlinear regression analysis is performed to calculate a first energy consumption estimation function, which is then used to calculate the energy consumption of the LED lights in the next stage. This invention can effectively improve the accuracy of energy consumption estimation for kitchen LED lights.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A method for estimating the energy consumption of LED lights, comprising:

[0007] S1. Obtain historical operating data of LED lights from the previous stage, historical cooking data of users, and historical energy consumption data. Historical operating data includes LED light brightness data, temperature data, power data, and on / off status data; historical cooking data of users includes cooking time node data, cooking type data, and cooking duration data, and construct a comprehensive dataset.

[0008] S2. Extract historical operation data feature vectors and user historical cooking feature vectors from the comprehensive dataset; 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. Based on the historical operation data characteristic function, the user's historical cooking characteristic function, and historical energy consumption data, a nonlinear regression analysis is performed to calculate the first energy consumption estimation function, and then the energy consumption of the LED lights in the next stage is calculated.

[0010] Preferably, the historical operating data features include switch status features, brightness features, temperature features, and power features; the switch status features include average daily operating time. and average number of times opened per day The brightness characteristics include the average daily on / off brightness. and the standard deviation of the on-state brightness σ B Temperature characteristics include average daily operating temperature. Correlation coefficient ρ with temperature and power T,P The power characteristics include average daily operating power. Correlation coefficient ρ with temperature and power T,P User historical cooking characteristics include cooking time distribution characteristics, cooking type characteristics, and cooking duration characteristics; the cooking time distribution characteristics include average daily cooking frequency. and average daily cooking time The cooking type characteristics include the average daily time for each type of cooking {κ1,κ2,,...κ} o} and the average daily lighting time for each cooking type {υ1,υ2,,...υ o The cooking duration characteristics include the average daily cooking time. and the average daily operating time correlation coefficient Reflects average daily cooking time With the average daily operating time The correlation.

[0011] Preferably, each historical operation feature subfunction includes a historical on / off state feature subfunction, a historical temperature feature subfunction, a historical brightness feature subfunction, and a historical power feature subfunction; each user's historical cooking feature subfunction includes a cooking time distribution feature subfunction, a cooking type feature subfunction, and a cooking duration feature subfunction.

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

[0013]

[0014] Where H represents the characteristic function of historical operating data; Represents the historical brightness feature sub-function; Represents the characteristic sub-function of historical temperature; Sub-functions representing historical switch states; Represents the historical power characteristic function; ω B ω B ω B and ω B These represent the weights of the feature sub-functions for each historical running data.

[0015] Preferably, the user's historical cooking feature function is:

[0016]

[0017] Where C represents the user's historical cooking feature function; ω t ω m and ω d These represent the weights of each historical cooking feature sub-function.

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

[0019]

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

[0021] An energy consumption estimation system for LED lights, the system being used to execute the aforementioned energy consumption estimation method for LED lights, comprising:

[0022] The data acquisition module acquires historical operating data of LED lights from the previous stage, historical cooking data of users, and historical energy consumption data. Historical operating data includes brightness data, temperature data, power data, and on / off status data of LED lights; historical user kitchen cooking data includes cooking time node data, cooking type data, and cooking duration data, and constructs a comprehensive dataset to store in the database.

[0023] The feature function construction module extracts historical operation data features and user historical cooking features from the comprehensive dataset; it then constructs various historical operation feature sub-functions and various user historical cooking feature sub-functions based on these two features; and finally, it constructs historical operation data feature functions and user historical cooking feature functions.

[0024] The energy consumption estimation module performs nonlinear regression analysis based on historical operating data characteristic functions, user historical cooking characteristic functions, and historical energy consumption data to obtain the first energy consumption estimation function, and then calculates the energy consumption of LED lights in the next stage.

[0025] A computer-readable storage medium storing a processor-executable program, which, when executed by a processor, is used to implement the above-described method for estimating the energy consumption of an LED lamp.

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

[0027] 1. This invention constructs a comprehensive dataset by acquiring historical operating data of LEDs and historical cooking data of users; it can comprehensively estimate the energy consumption of LED lights, thereby improving the accuracy of kitchen LED energy consumption estimation.

[0028] 2. This invention extracts historical operation data feature vectors and user historical cooking feature vectors from a comprehensive dataset. Based on these two feature vectors, it calculates various historical operation feature sub-functions and various user historical cooking feature sub-functions. The historical operation feature sub-functions include historical on / off status feature sub-functions, historical temperature feature sub-functions, historical brightness feature sub-functions, and historical power feature sub-functions. The user historical cooking feature sub-functions include cooking time distribution feature sub-functions, cooking type feature sub-functions, and cooking duration feature sub-functions. Furthermore, it calculates historical operation data feature functions and user historical cooking feature functions. Based on these historical operation data feature functions and user historical cooking feature functions, it lays the foundation for subsequent LED energy consumption estimation, thereby improving the accuracy of kitchen LED energy consumption estimation.

[0029] 3. This invention uses nonlinear regression analysis based on historical operating data characteristic functions, user historical cooking characteristic functions, and historical energy consumption data to calculate the first energy consumption estimation function, and then calculates the energy consumption of LED lights in the next stage, which can improve the accuracy of kitchen LED energy consumption estimation. Attached Figure Description

[0030] Figure 1 A schematic flowchart of an energy consumption estimation method for LED lamps provided in an embodiment of the present invention;

[0031] Figure 2 This is a schematic diagram of an energy consumption estimation system for LED lights provided in an embodiment of the present invention. Detailed Implementation

[0032] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] Example 1

[0034] To improve the accuracy of energy consumption estimation for LED lights in kitchen A, an energy consumption estimation method for LED lights was applied; (Refer to...) Figure 1 A flowchart illustrating an energy consumption estimation method for LED lamps provided in this embodiment of the invention includes:

[0035] S1. Obtain historical operating data of LED lights from the previous stage, historical cooking data of users, and historical energy consumption data. Historical operating data includes LED light brightness data, temperature data, power data, and on / off status data; historical cooking data of users includes cooking time node data, cooking type data, and cooking duration data, and construct a comprehensive dataset.

[0036] Furthermore, the switch state data represents the on and off states; the brightness data, temperature data, and power data are all data sequences obtained at j time points when the LED light is on; each of the brightness data, temperature data, and power data includes j values.

[0037] The comprehensive dataset is as follows:

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

[0039] Wherein, SD represents the comprehensive dataset; B represents brightness data; T represents temperature data; P represents power data; S represents switch status data; C t Represents cooking time point data; C m Represents cooking type data; C d This indicates the duration of cooking.

[0040] This embodiment constructs a comprehensive dataset by acquiring historical LED operating data and user historical cooking data; it can comprehensively estimate the energy consumption of LED lights, thereby improving the accuracy of kitchen LED energy consumption estimation.

[0041] S2. Extract historical operation data feature vectors and user historical cooking feature vectors from the comprehensive dataset; 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.

[0042] Furthermore, the historical operating data features include on / off status features, brightness features, temperature features, and power features; the on / off status features include average daily on / off duration. and average number of times opened per day The brightness characteristics include the average daily on / off brightness. and the standard deviation of the on-state brightness σ B Temperature characteristics include average daily operating temperature. Correlation coefficient ρ with temperature and power T,P The power characteristics include average daily operating power. Correlation coefficient ρ with temperature and power T,PUser historical cooking characteristics include cooking time distribution characteristics, cooking type characteristics, and cooking duration characteristics; the cooking time distribution characteristics include average daily cooking frequency. and average daily cooking time The cooking type characteristics include the average daily time for each type of cooking {κ1,κ2,,...κ} o} and the average daily lighting time for each cooking type {υ1,υ2,,...υ o The cooking duration characteristics include the average daily cooking time. and the average daily operating time correlation coefficient Reflects average daily cooking time With the average daily operating time The correlation.

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

[0044] The historical brightness feature function is:

[0045]

[0046] in, Represents the historical brightness feature sub-function; σ represents the average daily brightness on day i; B i β1 and β2 represent the standard deviation of the brightness on day i; β1 and β2 represent the brightness feature weighting coefficients.

[0047] The historical temperature feature function is:

[0048]

[0049] in, Represents the characteristic sub-function of historical temperature; ρ represents the average daily operating temperature on day i; T,P i ω1 and ω2 represent the temperature-power correlation coefficient for day i; ω1 and ω2 represent the temperature characteristic weighting 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 temperature data T on day i. i and power data P i Pearson correlation coefficient; T i j P represents the temperature value at the j-th time point on day i; i j This represents the power value at the j-th time point on day i;

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

[0056]

[0057] in, The γ1 and γ2 represent the feature sub-functions of historical switch states; γ1 and γ2 represent the feature weights of historical switch states.

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

[0059]

[0060] in, Represents the historical power characteristic sub-function; and Indicates the weight of historical power characteristics;

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

[0062]

[0063] Where H represents the characteristic function of historical operating data; Represents the historical brightness feature sub-function; Represents the characteristic sub-function of historical temperature; Sub-functions representing historical switch states; Represents the historical power characteristic function; ω B ω B ω B and ω B These represent the weights of the feature sub-functions for each historical running data.

[0064] Furthermore, 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.

[0065] The characteristic sub-function for the cooking time distribution is:

[0066]

[0067] in, α1 and α2 represent the characteristic sub-functions of the cooking time distribution; α1 and α2 represent the characteristic weights of the cooking time distribution.

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

[0069]

[0070] Among them, C m (κ1,κ2,,...κ o ,υ1,υ2,,...υ o ) represents the characteristic sub-function of cooking type; θ v and θ υ Indicates the feature weight of cooking type; κ v Indicates the average daily cooking time for the νth cooking type; υ ν This represents the average daily lighting time for the νth cooking type;

[0071] The cooking duration feature function is:

[0072]

[0073] in, The feature function representing the duration of cooking;

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

[0075]

[0076] Where C represents the user's historical cooking feature function; ω t ω m and ω d These represent the weights of each historical cooking feature sub-function.

[0077] This embodiment extracts historical operation data feature vectors and user historical cooking feature vectors from a comprehensive dataset. Based on these two feature vectors, it calculates various historical operation feature sub-functions and user historical cooking feature sub-functions. The historical operation feature sub-functions include historical on / off status feature sub-functions, historical temperature feature sub-functions, historical brightness feature sub-functions, and historical power feature sub-functions. The user historical cooking feature sub-functions include cooking time distribution feature sub-functions, cooking type feature sub-functions, and cooking duration feature sub-functions. Furthermore, it calculates historical operation data feature functions and user historical cooking feature functions. Based on these historical operation data feature functions and user historical cooking feature functions, it lays the foundation for subsequent LED energy consumption estimation, thereby improving the accuracy of kitchen LED energy consumption estimation.

[0078] S3. Based on the historical operation data characteristic function, the user's historical cooking characteristic function, and historical energy consumption data, a nonlinear regression analysis is performed to calculate the first energy consumption estimation function, and then the energy consumption of the LED lights in the next stage is calculated.

[0079] Furthermore, 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 the error term; H next and C next These represent the historical operation data feature function and the user's historical cooking feature function for the next stage, respectively; △T represents the time window for the next stage.

[0082] This embodiment uses nonlinear regression analysis based on historical operating data characteristic functions, user historical cooking characteristic functions, and historical energy consumption data to calculate the first energy consumption estimation function, and then calculates the energy consumption of LED lights in the next stage, which can improve the accuracy of kitchen LED energy consumption estimation.

[0083] A computer-readable storage medium storing a processor-executable program, which, when executed by a processor, is used to implement the above-described method for estimating the energy consumption of an LED lamp.

[0084] This embodiment acquires historical operating data of LED lights from the previous stage, user historical cooking data, and historical energy consumption data, and constructs a comprehensive dataset. Based on the comprehensive dataset, it constructs various historical operating feature functions and user historical cooking feature functions. Then, it calculates the historical operating data feature function and the user historical cooking feature function. Based on the historical operating data feature function, the user historical cooking feature function, and the historical energy consumption data, it performs nonlinear regression analysis to calculate the first energy consumption estimation function, and then calculates the energy consumption of the LED lights in the next stage. This invention can effectively improve the accuracy of kitchen LED light energy consumption estimation.

[0085] To verify the effectiveness of the LED light energy consumption estimation method provided in this embodiment, the accuracy of different methods for estimating LED energy consumption in kitchen A was compared. The different methods include method 1, method 2, and method 3. Method 1 is the LED light energy consumption estimation method provided in this embodiment. Method 2 is based on method 1 but does not consider the operating characteristics of LEDs. Method 3 is based on method 1 but does not consider the user's cooking characteristics. Specific comparisons are shown in Table 1.

[0086] Table 1 Comparison of Accuracy of LED Lamp Energy Consumption Estimation Using Different Methods

[0087] method Energy consumption estimation accuracy Method 1 97％ Method 2 91％ Method 3 89％

[0088] As shown in Table 1, the energy consumption estimation method for LED lights provided in this embodiment has a certain degree of effectiveness.

[0089] Example 2

[0090] To improve the accuracy of energy consumption estimation for LED lights in Kitchen B, an LED light energy consumption estimation system was applied; (Refer to...) Figure 2 A schematic diagram of an energy consumption estimation system for LED lights provided in an embodiment of the present invention includes:

[0091] The data acquisition module acquires historical operating data of LED lights from the previous stage, historical cooking data of users, and historical energy consumption data. Historical operating data includes brightness data, temperature data, power data, and on / off status data of LED lights; historical user kitchen cooking data includes cooking time node data, cooking type data, and cooking duration data, and constructs a comprehensive dataset to store in the database.

[0092] Furthermore, the switch state data represents the on and off states; the brightness data, temperature data, and power data are all data sequences obtained at j time points when the LED light is on; each of the brightness data, temperature data, and power data includes j values.

[0093] The comprehensive dataset is as follows:

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

[0095] Wherein, SD represents the comprehensive dataset; B represents brightness data; T represents temperature data; P represents power data; S represents switch status data; C t Represents cooking time point data; C m Represents cooking type data; C d This indicates the duration of cooking.

[0096] The feature function construction module extracts historical operation data features and user historical cooking features from the comprehensive dataset; it then constructs various historical operation feature sub-functions and various user historical cooking feature sub-functions based on these two features; and finally, it constructs historical operation data feature functions and user historical cooking feature functions.

[0097] Furthermore, the historical operating data features include on / off status features, brightness features, temperature features, and power features; the on / off status features include average daily on / off duration. and average number of times opened per day The brightness characteristics include the average daily on / off brightness. and the standard deviation of the on-state brightness σ B Temperature characteristics include average daily operating temperature. Correlation coefficient ρ with temperature and power T,P The power characteristics include average daily operating power. Correlation coefficient ρ with temperature and power T,P User historical cooking characteristics include cooking time distribution characteristics, cooking type characteristics, and cooking duration characteristics; the cooking time distribution characteristics include average daily cooking frequency. and average daily cooking time The cooking type characteristics include the average daily time for each type of cooking {κ1,κ2,,...κ} o} and the average daily lighting time for each cooking type {υ1,υ2,,...υ o The cooking duration characteristics include the average daily cooking time. and the average daily operating time correlation coefficient Reflects average daily cooking time With the average daily operating time The correlation.

[0098] Furthermore, each historical operation feature sub-function includes a historical on / off 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.

[0099] The historical brightness feature function is:

[0100]

[0101] in, Represents the historical brightness feature sub-function; σ represents the average daily brightness on day i; B i β1 and β2 represent the standard deviation of the brightness on day i; β1 and β2 represent the brightness feature weighting coefficients.

[0102] The historical temperature feature function is:

[0103]

[0104] in, Represents the characteristic sub-function of historical temperature; ρ represents the average daily operating temperature on day i; T,P i ω1 and ω2 represent the temperature-power correlation coefficient for day i; ω1 and ω2 represent the temperature characteristic weighting 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] Where N represents the total number of days; ρ(T) i ,P i () represents the temperature data T on day i. i and power data P i Pearson correlation coefficient; T ij P represents the temperature value at the j-th time point on day i; i j This represents the power value at the j-th time point on day i;

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

[0111]

[0112] in, The γ1 and γ2 represent the feature sub-functions of historical switch states; γ1 and γ2 represent the feature weights of historical switch states.

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

[0114]

[0115] in, Represents the historical power characteristic sub-function; and Indicates the weight of historical power characteristics;

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

[0117]

[0118] Where H represents the characteristic function of historical operating data; Represents the historical brightness feature sub-function; Represents the characteristic sub-function of historical temperature; Sub-functions representing historical switch states; Represents the historical power characteristic function; ω B ω B ω B and ω B These represent the weights of the feature sub-functions for each historical running data.

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

[0120]

[0121] Where H represents the characteristic function of historical operating data; Represents the historical brightness feature sub-function; Represents the characteristic sub-function of historical temperature; Sub-functions representing historical switch states; Represents the historical power characteristic function; ω B ω B ω B and ω BThese represent the weights of the feature sub-functions for each historical running data.

[0122] Furthermore, 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.

[0123] The characteristic sub-function for the cooking time distribution is:

[0124]

[0125] in, α1 and α2 represent the characteristic sub-functions of the cooking time distribution; α1 and α2 represent the characteristic weights of the cooking time distribution.

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

[0127]

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

[0129] The cooking duration feature function is:

[0130]

[0131] in, The feature function representing the duration of cooking;

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

[0133]

[0134] Where C represents the user's historical cooking feature function; ω t ω m and ω d These represent the weights of each historical cooking feature sub-function.

[0135] The energy consumption estimation module performs nonlinear regression analysis based on historical operating data characteristic functions, user historical cooking characteristic functions, and historical energy consumption data to obtain the first energy consumption estimation function, and then calculates the energy consumption of LED lights in the next stage.

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

[0137]

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

[0139] To verify the effectiveness of the LED light energy consumption estimation system provided in this embodiment, the accuracy of different systems in estimating LED energy consumption in kitchen B was compared. The different methods include System 1, System 2, and System 3. System 1 is the LED light energy consumption estimation system provided in this embodiment. System 2 is based on System 1 but does not consider the operating characteristics of LED lights. System 3 is based on System 1 but does not consider the user's cooking characteristics. Specific comparisons are shown in Table 2.

[0140] Table 2 Comparison of Accuracy of LED Lamp Energy Consumption Estimation Using Different Methods

[0141] system Energy consumption estimation accuracy System 1 98％ System 2 90％ System 3 86％

[0142] As shown in Table 2, the energy consumption estimation system for LED lights provided in this embodiment has a certain degree of effectiveness.

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

Claims

1. A method of estimating energy consumption of an LED lamp, characterized by, Comprising: S1. Obtain the historical running data of the previous stage LED lamp, the historical cooking data of the user and the historical energy consumption data, the historical running data including the brightness data, temperature data and power data and switching state data of the LED lamp; the historical cooking data of the user including cooking time node data, cooking type data and cooking duration data, and constructing a comprehensive data set data; S2. Extract the historical running data feature vector and the user historical cooking feature vector based on the comprehensive data set; calculate each historical running feature sub-function and each user historical cooking feature sub-function based on the two feature vectors; and then calculate the historical running data feature function and the user historical cooking feature function; the historical running data feature function is: ； wherein represents a historical operating data characteristic function; represents a historical brightness characteristic sub-function; represents a historical temperature characteristic sub-function; represents a historical switch state characteristic sub-function; represents a historical power characteristic sub-function; , , and respectively represent a weight of each historical operating data characteristic sub-function; The user historical cooking feature function is: ； wherein, represents a user history cooking characteristic function; , and respectively represent respective history cooking characteristic sub-function weights; S3. Perform nonlinear regression analysis based on the historical running data feature function, the user historical cooking feature function and the historical energy consumption data to calculate a first energy consumption estimation function, and then calculate the energy consumption of the next stage LED lamp.

2. The method of claim 1, wherein: The historical running data features include switching state features, brightness features, temperature features and power features; Switch state features include daily average on duration and daily average on count ; the brightness features include daily average on brightness and on brightness standard deviation ; temperature features include daily average on temperature and temperature power correlation coefficient ; the power features include daily average on power and temperature power correlation coefficient ; the user historical cooking features include cooking time distribution feature, cooking type feature, and cooking duration feature; The cooking time distribution feature includes daily average cooking frequency and daily average cooking time length The cooking type feature includes daily average time of each type of cooking and daily average lighting time of each cooking type The cooking duration feature includes a daily average cooking duration and a correlation coefficient of the daily average cooking duration and the daily average on duration , reflecting the relevance of the daily average cooking duration and the daily average on duration .

3. The method of claim 1, wherein: Each historical running feature sub-function includes a historical switching 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.

4. The method of claim 1, wherein: The first energy consumption estimation function is: ： wherein, represents a first energy consumption estimation function; and represents a regression coefficient; represents an error term; represents a time window for the next stage.

5. A system for estimating energy consumption of an LED lamp, the system being configured to perform a method for estimating energy consumption of an LED lamp according to any one of claims 1 to 4, wherein Comprising: A data acquisition module that acquires the historical running data of the previous stage LED lamp, the historical cooking data of the user and the historical energy consumption data, the historical running data including the brightness data, temperature data and power data and switching state data of the LED lamp; the historical user kitchen cooking data including cooking time node data, cooking type data and cooking duration data, and constructing a comprehensive data set and storing it in a database; A feature function construction module that extracts historical running data features and user historical cooking features based on the comprehensive data set; constructs each historical running feature sub-function and each user historical cooking feature sub-function based on the two features; and then constructs the historical running data feature function and the user historical cooking feature function; An energy consumption estimation module that performs nonlinear regression analysis based on the historical running data feature function, the user historical cooking feature function and the historical energy consumption data to obtain a first energy consumption estimation function, and then calculates the energy consumption of the next stage LED lamp.

6. A computer-readable storage medium, characterized in that, The processor executable program stored therein is executed by the processor to implement the LED lamp energy consumption estimation method of any one of claims 1 to 4.

Images