Intelligent home carbon emission monitoring and optimizing system based on artificial intelligence

Abstract

The invention relates to the technical field of smart home, and particularly discloses a smart home carbon emission monitoring and optimizing system based on artificial intelligence, and the system comprises a data collection layer which comprises an environment sensor, an energy metering module, a family member sensing module and an external data input module; according to the invention, real-time cleaning, denoising and point-by-point normalization processing are carried out on data acquired by the data acquisition layer through the edge calculation layer, a carbon emission prediction model based on multi-dimensional influence factors is constructed in combination with user historical behavior data and preset parameters, and optimization suggestions are generated through comparison of actual monitoring data, so that the accuracy of carbon emission prediction is improved. According to the invention, high-efficiency and low-consumption data preprocessing is realized, the accuracy of carbon emission prediction is improved, an equipment operation strategy can be dynamically optimized so as to reduce energy consumption, the system has a sensor fault early warning function, and the intelligent level and user experience of smart home energy management are significantly enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of smart home, and particularly to a smart home carbon emission monitoring and optimization system based on artificial intelligence. Background Art

[0002] With the increasingly severe global climate change problem, the low-carbon development of smart home systems has not only become a hot topic in the scientific research field but also an important means to promote sustainable lifestyles and environmental protection.

[0003] Although traditional smart home systems have made certain progress in energy management, such as achieving energy-saving operation of household appliances through intelligent control and using sensors to monitor environmental parameters to optimize energy use, their technical limitations have become increasingly prominent in the face of the urgent need for global carbon emissions reduction. Traditional smart home systems generally have the following technical defects: carbon emission monitoring relies on single-source energy data, lacks multi-source data fusion analysis, and is difficult to comprehensively and accurately reflect the actual carbon emissions of a household, making it impossible to provide users with accurate carbon footprint analysis; no closed-loop feedback mechanism is established between the predicted value and the actual monitored value. In energy management, the predicted value is of great significance for predicting future energy demand and formulating energy-saving strategies. However, due to the lack of an effective feedback mechanism, the predicted value often deviates significantly from the actual monitored value, resulting in the lack of accuracy and effectiveness in the formulation and implementation of energy-saving strategies. The existing technologies cannot meet the needs of users for refined carbon emission management, and there is an urgent need for a new type of monitoring and optimization system integrating artificial intelligence technology. Summary of the Invention

[0004] The purpose of the present invention is to provide a smart home carbon emission monitoring and optimization system based on artificial intelligence to solve the following technical problems:

[0005] How to effectively monitor smart home carbon emissions through multi-dimensional information based on artificial intelligence.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A smart home carbon emission monitoring and optimization system based on artificial intelligence, the system includes:

[0008] A data acquisition layer, including an environmental sensor, an energy metering module, a family member perception module, and an external data input module. The environmental sensor is used to collect indoor and outdoor environmental data, the energy metering module is used to collect electricity consumption and gas consumption, the family member perception module is used to collect the status and location distribution of indoor family members, and the external data input module is used to input various power ratio information corresponding to regional electricity consumption;

[0009] An edge computing layer, used for preprocessing the collected data;

[0010] Cloud analysis layer, which analyzes the preprocessed data, estimates and monitors the carbon emissions of smart homes, and generates corresponding optimization suggestions according to the estimated and actual monitoring results;

[0011] Terminal interaction layer, which is used to display carbon emission data and optimization suggestions, and the user selects whether to execute the optimization suggestions.

[0012] Furthermore, the process of the edge computing layer preprocessing the collected data includes:

[0013] S1. Clean the collected data and remove or correct abnormal data;

[0014] S2. Denoise the data after cleaning;

[0015] S3. Normalize the data after denoising.

[0016] Furthermore, in step S3, the process of normalizing the data after denoising includes:

[0017]

[0018] The normalized value of the i-th collected data is obtained through analysis and calculation by formulas (1)-(3);

[0019] where i is the serial number of the current data point, X i is the i-th original data vector, is the mean value corresponding to the i-th original data, and σ i is the standard deviation corresponding to the i-th original data.

[0020] Furthermore, the process of obtaining the estimated value of the carbon emissions of the smart home includes:

[0021]

[0022] α = Σ k R k * ω k (5)

[0023] The estimated value Q of the carbon emissions of the smart home within the preset time period is obtained through analysis and calculation by formulas (4)-(5) pre ;

[0024] where there are N rooms in the user's indoor area, j ∈ [1, N], E j is the estimated electricity consumption in the j-th room within the preset time period, G j is the estimated gas consumption in the j-th room within the preset time period, α is the electricity carbon emission factor, β is the gas carbon emission factor, R k is the proportion of the k-th type of power supply, ωk is the carbon emission benchmark factor corresponding to the k-th type of power supply.

[0025] Furthermore, the process of obtaining the estimated electricity consumption in the j-th room within the preset time period includes:

[0026]

[0027] The estimated electricity consumption E in the j-th room within the preset time period is obtained through analysis and calculation using formulas (6)-(7). j ;

[0028] where M is the number of types of household appliances, l ∈ [1, M], P l is the rated power of the l-th type of household appliance, is the influence coefficient of temperature on the working power of the l-th type of household appliance, t l is the working time of the l-th type of household appliance, τ l is the correction coefficient of the behavior of indoor users on the l-th type of household appliance, a l is the basic power of the l-th type of household appliance, ΔT is the difference in the indoor and outdoor temperature normalization coefficients, ε l is the influence factor of temperature difference on the power of the l-th type of household appliance, L out is the illumination intensity normalization coefficient, δ l is the influence factor of illumination on the power of the l-th type of household appliance.

[0029] Furthermore, the process of obtaining the actual monitored value of the smart home carbon emissions includes:

[0030] Q s = E all *α + G all *β (8)

[0031] The monitored value Q of the smart home carbon emissions within the preset time period is obtained through analysis and calculation using formula (8). s ;

[0032] where E all is the total electricity consumption of all smart homes within the preset time period, G all is the total gas consumption of all smart homes within the preset time period.

[0033] Furthermore, the process of generating the corresponding optimization suggestions includes:

[0034] Comparing the predicted value and the actual monitored value of the smart home carbon emissions;

[0035] If |Q pre - Q s | ≤ μ, no smart home carbon emission optimization suggestions are generated;

[0036] If Q s > Q pre + μ, then optimization suggestions for appropriately reducing the operating power or reducing the operating time of the smart home are generated;

[0037] If Q s <<Q pre , then a warning signal for a fault in the data acquisition layer is generated.

[0038] Furthermore, the system further includes:

[0039] A communication module, configured to transmit the data preprocessed by the edge computing layer to the cloud analysis layer, and transmit the carbon emission data and optimization suggestions generated by the cloud analysis layer to the terminal interaction layer.

[0040] Advantages of the present invention:

[0041] (1) By performing real-time cleaning, denoising, and point-by-point normalization processing on the data collected by the data acquisition layer through the edge computing layer, combining the user's historical behavior data with preset parameters, a carbon emission prediction model based on multi-dimensional influencing factors is constructed, and optimization suggestions are generated by comparing with actual monitoring data, realizing efficient and low-power data preprocessing, improving the accuracy of carbon emission prediction, dynamically optimizing the device operation strategy to reduce energy consumption, and having a sensor fault warning function at the same time, significantly enhancing the intelligent level and user experience of smart home energy management. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The present invention will be further described below with reference to the accompanying drawings.

[0043] Figure 1 is a schematic block diagram of a smart home carbon emission monitoring and optimization system based on artificial intelligence disclosed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] The technical solutions in the embodiments of the present invention will be clearly and completely described below 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 the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0045] Please refer to Figure 1 shown. In one embodiment, a smart home carbon emission monitoring and optimization system based on artificial intelligence is provided. The system includes:

[0046] A data acquisition layer, including an environmental sensor, an energy metering module, a family member perception module, and an external data input module;

[0047] The environmental sensor is used to collect indoor and outdoor environmental data, and the environmental data includes, but is not limited to, environmental parameters such as indoor and outdoor temperature, humidity, light intensity, and CO2 concentration. The energy metering module is used to collect electricity consumption and gas consumption, and the electricity consumption and gas consumption can be recorded and collected through smart meters and gas meters. The family member perception module is used to collect the status and location distribution of indoor family members. The family member perception module includes an infrared sensor, a smart wearable device (such as a smart bracelet), or a camera, which can identify the location distribution of family members and obtain their status (such as sleeping, working, going out). The external data input module is used to input various power proportion information corresponding to regional electricity consumption, such as the proportion of thermal power generation, wind power generation, and photovoltaic power generation in the regional power grid, which can be specifically obtained through the provincial power dispatching center;

[0048] The edge computing layer is used to preprocess the collected data and transmit the preprocessed data to the cloud analysis layer. The preprocessing process can effectively reduce the transmission load and cloud load and improve the real-time performance;

[0049] The cloud analysis layer analyzes the preprocessed data based on artificial intelligence, estimates and monitors the carbon emissions of smart homes, and generates corresponding optimization suggestions according to the estimated and actual monitoring results;

[0050] The terminal interaction layer is used to display the carbon emission data and optimization suggestions, and the user can choose whether to execute the optimization suggestions.

[0051] Through the above technical solutions, this embodiment provides a smart home carbon emission monitoring and optimization system based on artificial intelligence. The preprocessing of the edge computing layer effectively reduces the transmission load and cloud load, improves the real-time performance and response speed of the system. Through comprehensive data collection, efficient edge computing, intelligent cloud analysis, and intuitive terminal interaction, this system realizes the accurate monitoring of home carbon emissions and optimization suggestions, and has significant beneficial effects.

[0052] The process of the edge computing layer preprocessing the collected data includes:

[0053] S1. Clean the collected data, remove or correct abnormal data. The commonly used method is a statistics-based method, such as the Z-score method. For a set of data, calculate the Z-score of each data point. Generally speaking, if the Z-score of a certain value is greater than 3 or less than -3, it is considered that this value may be an abnormal value caused by sensor failure, transmission interference, etc., and it can be removed or replaced with other reasonable values (such as the mean, median);

[0054] S2. Denoise the cleaned data. The moving average method is commonly used for denoising, which smooths the data by calculating the average value of the data within a certain time window.

[0055] S3. Normalize the denoised data.

[0056] In step S3, the process of normalizing the denoised data includes:

[0057]

[0058] Analyze and calculate the normalized value of the i-th collected data through formulas (1)-(3);

[0059] where i is the serial number of the current data point, X i is the i-th original data vector, is the mean value corresponding to the i-th original data, σ i is the standard deviation corresponding to the i-th original data, is the mean value corresponding to the (i - 1)-th original data, X i-1 is the (i - 1)-th original data vector, σ i-1 is the standard deviation corresponding to the (i - 1)-th original data.

[0060] Through the above technical solution, this embodiment provides a method for preprocessing the collected data in the edge computing layer. First, clean the original collected data by statistical methods, remove or correct abnormal data, then perform smoothing denoising on the cleaned data by the moving average method, and finally normalize the denoised data through formulas (1)-(3). This way of normalization can update the mean value and standard deviation point by point, avoid storing all data in the edge computing layer, reduce memory and computing consumption, thus ensuring the fast and effective processing of the collected data by the edge computing layer.

[0061] The process of obtaining the predicted value of the smart home carbon emission includes:

[0062]

[0063] α = ∑ k R k * ω k (5)

[0064] Analyze and calculate the predicted value Q of the smart home carbon emission within a preset time period through formulas (4)-(5); pre ;

[0065] where there are N rooms in the user's indoor area, j ∈ [1, N], E j is the predicted electricity consumption in the j-th room within the preset time period, G jis the estimated gas consumption in the j-th room within the preset time period, which can be obtained by analyzing the user's historical behavior data. α is the carbon emission factor of electricity, and β is the carbon emission factor of gas. The carbon emission factor of gas is a fixed value, generally taking 0.19 kgCO2 / m3, and R k is the proportion of the k-th type of power source, and ω k is the carbon emission benchmark factor corresponding to the k-th type of power source. The carbon emission benchmark factors corresponding to various power sources are all fixed values and can be obtained through experimental calculations.

[0066] The process of obtaining the estimated electricity consumption in the j-th room within the preset time period includes:

[0067]

[0068] The estimated electricity consumption E in the j-th room within the preset time period is obtained through analytical calculations using formulas (6)-(7) j ;

[0069] where M is the number of types of household appliances, l ∈ [1, M], and P l is the rated power of the l-th type of household appliance, obtained from the nameplate data of smart home appliances or the standard specification library is the influence coefficient of temperature on the working power of the l-th type of household appliance, and t l is the working time of the l-th type of household appliance, which can be obtained by analyzing the user's historical behavior data, and τ l is the correction coefficient of the behavior of indoor users on the l-th type of household appliance, which can be preset according to experience. For example, the correction coefficients of the behavior of users in different states such as sleep, work, and fitness on various types of household appliances are different. a l is the basic power of the l-th type of household appliance, which can be preset according to experience or obtained through experiments. ΔT is the difference in the indoor and outdoor temperature normalization coefficients, which can be obtained by preprocessing the data collected by the edge computing module. ε l is the influence factor of temperature difference on the power of the l-th type of household appliance, preset according to experience. The influence factors of the power of different types of household appliances are different. For example, the influence factor of the air conditioner can be preset to 1, the influence factor of the refrigerator can be preset to 0.5, and the influence factor of the lamp can be preset to 0. L out is the light intensity normalization coefficient, which can be obtained by preprocessing the data collected by the edge computing layer. δ l is the influence factor of light on the power of the l-th type of household appliance, preset according to experience. The influence factors of the power of different types of household appliances are different. For example, the influence factor of the lamp can be preset to 0.7, and the influence factor of the TV can be preset to 0.2.

[0070] The process of obtaining the actual monitored value of the carbon emissions of the smart home includes:

[0071] Q s = E all *α + G all *β (8)

[0072] The monitored value Q of the carbon emissions of the smart home within the preset time period is obtained through analytical calculation using formula (8). s ;

[0073] Among them, E all is the total electricity consumption of all smart homes within the preset time period, and G all is the total gas consumption of all smart homes within the preset time period. Both E all and G all can be obtained by collecting through the energy metering module.

[0074] The process of generating the corresponding optimization suggestions includes:

[0075] Comparing the predicted value and the actual monitored value of the carbon emissions of the smart home;

[0076] If |Q pre - Q s | ≤ μ, it indicates that the system is operating normally and no optimization suggestions for smart home carbon emissions are generated;

[0077] If Q s > Q pre + μ, it indicates that the optimization of smart home carbon emissions is poor, and optimization suggestions for appropriately reducing the operating power or operating time of the smart home are generated, such as lowering the water heater temperature and reducing the air conditioner usage time;

[0078] If Q s <<Q pre , it indicates that the sensor may malfunction, and a warning signal for data acquisition layer failure is generated.

[0079] Through the above technical solution, this embodiment provides a smart home carbon emissions monitoring and optimization method based on artificial intelligence. This technical solution performs real-time cleaning, denoising, and point-by-point normalization processing on the data collected by the data acquisition layer through the edge computing layer, constructs a carbon emissions prediction model based on multi-dimensional influencing factors in combination with the user's historical behavior data and preset parameters, and generates optimization suggestions through comparison with actual monitoring data, realizing efficient and low-power data preprocessing, improving the accuracy of carbon emissions prediction, dynamically optimizing the device operation strategy to reduce energy consumption, and having a sensor failure warning function at the same time, significantly enhancing the intelligent level and user experience of smart home energy management.

[0080] The system further includes:

[0081] The communication module is used to transmit the data preprocessed by the edge computing layer to the cloud analysis layer, and transmit the carbon emission data and optimization suggestions generated by the cloud analysis layer to the terminal interaction layer. It uses the MQTT protocol to achieve efficient data transmission between the edge and the cloud, supports resuming data transmission after network disconnection, and uses the AES-256 algorithm for data encryption to protect user privacy.

[0082] The above has described an embodiment of the present invention in detail, but the content described is only the preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. An intelligent home carbon emission monitoring and optimization system based on artificial intelligence, characterized in that, The system includes: A data acquisition layer, including an environmental sensor, an energy metering module, a family member perception module, and an external data input module. The environmental sensor is used to collect indoor and outdoor environmental data. The energy metering module is used to collect electricity consumption and gas consumption. The family member perception module is used to collect the status and location distribution of indoor family members. The external data input module is used to input various power proportion information corresponding to regional electricity consumption; An edge computing layer, which is used to preprocess the collected data; A cloud analysis layer, which analyzes the preprocessed data, estimates and monitors the carbon emissions of the smart home, and generates corresponding optimization suggestions according to the estimated and actual monitoring results; A terminal interaction layer, which is used to display the carbon emission data and optimization suggestions, and the user selects whether to execute the optimization suggestions.

2. The intelligent home carbon emission monitoring and optimization system based on artificial intelligence according to claim 1, characterized in that, The process of the edge computing layer preprocessing the collected data includes: S1. Perform data cleaning on the collected data, and remove or correct abnormal data; S2. Perform denoising processing on the data after cleaning; S3. Perform normalization processing on the data after denoising.

3. The intelligent home carbon emission monitoring and optimization system based on artificial intelligence according to claim 2, characterized in that, In step S3, the process of performing normalization processing on the data after denoising includes: Obtain the normalized value of the i-th collected data through analysis and calculation using formulas (1)-(3); Among them, i is the serial number of the current data point, and X i is the i-th original data vector, is the mean corresponding to the i-th original data, and σ i is the standard deviation corresponding to the i-th original data.

4. An intelligent home carbon emission monitoring and optimization system based on artificial intelligence according to claim 3, characterized in that, The process of obtaining the estimated value of the smart home carbon emissions includes: ɑ = ∑ k R k * ω k (5) The estimated value Q of the carbon emissions of the smart home within a preset time period is obtained through analytical calculation using formulas (4)-(5). pre ; Among them, there are N rooms in the user's indoor area, where j ∈ [1, N], and E j is the estimated electricity consumption in the j-th room during the preset time period, and G j is the estimated gas consumption in the j-th room during the preset time period. α is the electricity carbon emission factor, β is the gas carbon emission factor, and R k is the proportion of the k-th type of power source, and ω k is the carbon emission benchmark factor corresponding to the k-th type of power source.

5. The intelligent home carbon emission monitoring and optimization system based on artificial intelligence according to claim 4, characterized in that, The process of obtaining the estimated electricity consumption in the j-th room within the preset time period includes: The estimated power consumption E in the j-th room within a preset time period is obtained through analysis and calculation using formulas (6)-(7). j ; Among them, M is the number of types of home appliances, l ∈ [1, M], P l is the rated power of the l-th type of home appliance, is the influence coefficient of temperature on the working power of the l-th type of home appliance, t l is the working time of the l-th type of home appliance, τ l is the correction coefficient of the influence of the behavior of indoor users on the l-th type of home appliance, a l is the basic power of the l-th type of home appliance, ΔT is the difference of the indoor and outdoor temperature normalization coefficients, ε l is the influence factor of temperature difference on the power of the l-th type of home appliance, L out is the normalization coefficient of light intensity, δ l is the influence factor of light on the power of the l-th type of home appliance.

6. The intelligent home carbon emission monitoring and optimization system based on artificial intelligence according to claim 5, characterized in that The process of obtaining the actual monitoring value of the smart home carbon emissions includes: Q s = E all * α + G all * β (8) The monitoring value Q of the carbon emissions of the smart home within the preset time period is obtained through analysis and calculation by formula (8). s ; Among them, E all is the total electricity consumption of all smart homes within a preset time period, and G all is the total gas consumption of all smart homes within a preset time period.

7. An intelligent home carbon emission monitoring and optimization system based on artificial intelligence according to claim 6, characterized in that, The process of generating the corresponding optimization suggestions includes: Compare the estimated value and the actual monitoring value of the smart home carbon emissions; If |Q pre -Q s | ≤ μ, no smart home carbon emission optimization suggestions will be generated; If Q s >Q pre + μ, then optimization suggestions for appropriately reducing the operating power or the operating time of the smart home are generated; If Q s <<Q pre , a warning signal for the failure of the data acquisition layer is generated.

8. The intelligent home carbon emission monitoring and optimization system based on artificial intelligence according to claim 7, characterized in that, The system further includes: A communication module, which is used to transmit the data preprocessed by the edge computing layer to the cloud analysis layer, and transmit the carbon emission data and optimization suggestions analyzed and generated by the cloud analysis layer to the terminal interaction layer.

Images