An energy output power self-regulation system based on artificial intelligence

By introducing artificial intelligence technology into the energy management system, using PMV-PPD model and linear planning algorithm to dynamically adjust the output power of power equipment, the shortcomings of traditional systems in handling human comfort factors are solved, and energy management and comfort are achieved Dual optimization reduces energy waste and carbon emissions.

CN118655795BActive Publication Date: 2024-11-22SHANDONG TAIWU INFORMATION TECH CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202411147360.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-21
Publication Date
2024-11-22
Estimated Expiration
2044-08-21

AI Technical Summary

Technical Problem

Traditional energy management systems have achieved results in improving energy use efficiency, but they seem unscrupulous when considering the human comfort factor, and cannot analyze the complex relationship between user comfort needs and energy supply in real time, making it difficult to accurately improve user comfort experience. , and there is a problem of energy waste.

Method used

A self-regulating system for energy output power based on artificial intelligence is designed. Through the data acquisition module, indoor environment and personnel activity data are collected in real time, combined with PMV-PPD model and linear planning algorithm, the output power of power equipment is dynamically adjusted, and energy configuration and use are optimized. , ensure indoor environment comfort and energy efficiency.

Benefits of technology

It realizes the rational allocation and efficient utilization of energy, significantly improves user comfort experience and energy use efficiency, reduces energy waste and carbon emissions, and provides a smarter and more convenient living environment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118655795B_ABST
    Figure CN118655795B_ABST
Patent Text Reader

Abstract

The present invention discloses an energy output power self-regulating system based on artificial intelligence, which relates to the technical field of intelligent energy management. The system comprises the following components: a data acquisition module: by deploying various sensors in intelligent buildings, indoor environmental parameters and personnel activities are collected in real time. The present invention comprehensively considers human comfort factors and uses advanced PMV‑PPD models to accurately evaluate human comfort, thereby effectively improving the comfort level of the indoor environment. This innovation not only enables the energy management system to perceive and respond to the actual needs of users in real time, but also brings users a more comfortable and healthy living and working environment while ensuring stable energy supply. Through precise regulation of artificial intelligence, the system can automatically adjust the output power of power equipment, thereby significantly improving the user's comfort experience while ensuring energy utilization efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent energy management, and in particular to an energy output power self-regulation system based on artificial intelligence. Background Art

[0002] With the rapid development of science and technology and the continuous improvement of people's requirements for quality of life, energy management systems are increasingly used in modern buildings, homes and industrial fields. These systems aim to achieve sustainable development by optimizing energy distribution and use, improving energy utilization efficiency and reducing energy consumption costs. As people's requirements for the comfort of living and working environments increase, traditional energy management systems can no longer meet the dual needs of energy efficiency and user comfort through only a single-dimensional energy management. Therefore, it is particularly important to develop a system that can deeply integrate human comfort factors and energy management to achieve intelligent regulation.

[0003] Traditional energy regulation systems have achieved remarkable results in improving energy efficiency. Through precise metering, monitoring and scheduling, they have effectively reduced energy waste. However, when considering human comfort factors, these systems often seem to be powerless. Most of them rely on preset fixed parameters and simple sensor data feedback for adjustment, and lack the ability to dynamically respond to the actual feelings of the human body. In addition, traditional systems are relatively lagging behind in the application of artificial intelligence and cannot analyze the complex relationship between user comfort needs and energy supply in real time. As a result, it is difficult to accurately improve the user's comfort experience while meeting the user's energy needs. This limitation not only affects the user's living and working quality, but also causes unnecessary energy waste.

[0004] Therefore, an energy output power self-regulation system based on artificial intelligence is developed, which uses intelligent algorithms to finely control energy output, realizes the rational allocation and efficient utilization of energy, and achieves the dual effects of energy conservation and emission reduction. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the prior art and to provide an energy output power self-regulation system based on artificial intelligence. It can realize intelligent and precise adjustment of energy output power by deeply integrating human comfort factors and energy management systems. It can not only perceive changes in the indoor environment and personnel activities in real time, but also dynamically adjust key air-conditioning and lighting systems to ensure a constant and comfortable indoor environment and avoid energy waste and decreased comfort. The use of intelligent algorithms realizes the optimization and efficient utilization of energy configuration, effectively reduces carbon emissions, and promotes environmental protection and sustainable development.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an energy output power self-regulation system based on artificial intelligence, the system comprising the following components:

[0007] Data collection module: Through various sensors deployed in smart buildings, indoor environmental parameters and personnel activities are collected in real time;

[0008] Data processing module: receives the raw data transmitted by the data acquisition module, performs preprocessing and cleaning, removes noise and outliers, and passes the processed data to subsequent modules for analysis;

[0009] Comfort analysis module: Based on the preset comfort model, it comprehensively considers the impact of multiple factors on human comfort, analyzes indoor environmental parameters and personnel activities, and evaluates the comfort level of the current indoor environment;

[0010] Intelligent control module: Receive current and historical comfort evaluation results from the comfort analysis module, use linear regression to combine historical data and current trends to predict energy demand in the future, formulate preliminary control strategies based on energy demand and comfort prediction results, and combine energy management goals. Use linear programming algorithms to optimize the preliminary strategies to find the optimal control strategy with the highest energy efficiency and lowest cost while meeting comfort requirements, convert the optimized control strategy into specific control instructions, and send them to the actuator;

[0011] Actuator: According to the instructions of the intelligent control module, the output power of the power equipment is accurately adjusted to ensure the effective implementation of the control strategy and achieve real-time optimization of the indoor environment.

[0012] Furthermore, the data acquisition module deploys a variety of sensors in key areas within the building and constructs a sensor network between the data processing center. The sensors collect indoor environmental parameters and personnel activities in real time according to preset configuration parameters. Before data transmission, the collected raw data is preliminarily processed, and the relevant data is encrypted during transmission and transmitted to the data processing center through the sensor network. The data processing center receives the data and stores it.

[0013] Furthermore, the data processing module receives the raw data transmitted from the data acquisition module, distinguishes the received indoor environmental parameters and personnel activities according to the sensor type and the acquisition location, checks the format of the data, converts the received data into a unified format, adds a timestamp, identifies and removes noise in the raw data, sets reasonable thresholds to detect and eliminate outliers in the raw data, further cleans the data after noise removal and outlier elimination, and stores the cleaned data in a database.

[0014] Furthermore, the comfort analysis module receives the cleaned and pre-processed indoor environmental parameter data and personnel activity data, uses the PMV-PPD model to evaluate the impact of environmental parameters and personnel activity factors on comfort, and conducts a comprehensive evaluation of the factors affecting comfort. Based on the comprehensive evaluation results, the overall comfort score of the current indoor environment is calculated, and the comfort change trend in the future is predicted based on historical data and time series analysis models. According to the actual application effect and user feedback, the comfort analysis model is continuously optimized and adjusted to improve the accuracy of the evaluation.

[0015] Furthermore, the comfort analysis module uses the PMV-PPD model to evaluate the impact of environmental parameters and personnel activity factors on comfort, and obtains the required parameters through measurement and calculation, such as indoor air temperature. , mean radiant temperature , indoor air velocity , relative humidity , human metabolic rate , clothing thermal resistance , calculate the sensible heat exchange between the human body and the environment , the formula is: ,in, is the metabolic rate of the human body, It is the mechanical work done by the human body. is the convective heat transfer between the human body and the surrounding air, and the calculation formula is: , is the clothing area coefficient, is the convective heat transfer coefficient, is the human body surface temperature, calculated as, is the indoor air temperature, is the radiation heat exchange between the human body and the surrounding environment, and the calculation formula is: , is the radiation heat transfer coefficient, is the mean radiant temperature, It is the amount of heat dissipated by the human body through evaporation of the skin surface and breathing. The calculation formula is: , , is the amount of heat dissipated by evaporation from the skin surface. is the evaporative heat dissipation from breathing, is the water vapor partial pressure of the air around the human body, calculated as: ,in, is the air temperature The saturated water vapor partial pressure under the condition of heat storage rate in the human body heat balance equation , PMV and PPD are calculated by the formula.

[0016] Furthermore, the comfort analysis module predicts the comfort change trend in the future based on historical data and the autoregressive moving average model. The general form of the autoregressive moving average model is: ,in, is the backshift operator, yes The order difference operator, It is a comfort-related index of PMV and PPD. It is a white noise sequence. Check the stationarity of the comfort time series. According to the autocorrelation function and partial autocorrelation function graph of the time series, preliminarily determine the parameters (p, d, q) of the autoregressive moving average model. Use historical data to estimate the parameters of the selected autoregressive moving average model. Use the trained autoregressive moving average model to predict the comfort-related indicators in the future. Analyze the changing trend of comfort in the future based on the prediction results.

[0017] Furthermore, the intelligent control module uses linear regression to combine historical data and current trends to predict energy demand in the future, collects historical energy demand data and related influencing factor data, and the basic form of the linear regression model is: ,in, is the energy demand, This is what affects energy demand. are model parameters, is the error term, which represents the part that cannot be explained in the model. The model parameters are estimated by the least squares method using historical data. , the goal of the least squares method is to minimize the residual sum of squares, the formula is: ,in, is the number of data points. The fitting effect of the model is evaluated by calculating the mean square error index. Combined with the current trend, the future values ​​of the independent variables are predicted. The predicted independent variable values ​​are substituted into the linear regression model to calculate the predicted value of energy demand in the future.

[0018] Furthermore, the intelligent control module optimizes the preliminary control strategy using a linear programming algorithm to find the optimal control strategy with the highest energy efficiency and the lowest cost under the premise of meeting the comfort requirements. The adjusted control parameter is set as the decision variable, denoted as , the objective function is the quantity that needs to be minimized during the optimization process. In this scenario, the goal is to minimize the cost while considering energy efficiency. The formula is: ,in, is the unit cost, are the corresponding energy usage and control parameters, is the cost function related to energy efficiency, is the number of cost items related to energy efficiency. The constraints are comfort requirements, equipment capacity limitations, and energy supply limitations. It can be expressed as a linear inequality: , ,in, and About A linear function of and is a constant, and are the number of inequality constraints and equality constraints respectively. The comfort requirements are reflected by setting the upper and lower limits of the temperature range, humidity range, and air flow rate parameters. The above objective function and constraints are converted into the standard form of linear programming problems and solved using the linear programming algorithm. According to the results of linear programming, the optimal value of each decision variable is explained, and specific control strategies are formulated accordingly.

[0019] Furthermore, the actuator receives the control instructions from the intelligent control module, decodes and verifies the received instructions through the parsing unit, establishes a connection with the power equipment and detects the current operating status of each device in real time, and uses a closed-loop control strategy to accurately adjust the equipment output power based on the parsed instructions, collects the equipment operating status and indoor environmental parameter changes before and after the control, and feeds back to the intelligent control module. If equipment failure, data anomalies and safety hazards are detected, the exception handling mechanism will be immediately activated.

[0020] Compared with the prior art, this energy output power self-regulation system based on artificial intelligence has the following beneficial effects:

[0021] 1. The present invention comprehensively considers human comfort factors and uses the advanced PMV-PPD model to accurately evaluate human comfort, thereby effectively improving the comfort level of the indoor environment. This innovation not only enables the energy management system to perceive and respond to the actual needs of users in real time, but also provides users with a more comfortable and healthy living and working environment while ensuring a stable energy supply. Through the precise control of artificial intelligence, the system can automatically adjust the output power of power equipment, thereby significantly improving the user's comfort experience while ensuring energy efficiency.

[0022] 2. The present invention closely combines human comfort with the regulation of energy output power to achieve a dynamic balance between the two. Traditional energy management systems often only focus on energy utilization efficiency and cost control, but ignore the important aspect of user comfort. The present invention introduces a comfort analysis module and an intelligent control module, which can not only further enhance the user's comfort level on the basis of meeting the user's energy needs, but also formulate the optimal control strategy based on the comfort prediction results and energy management goals. This intelligent control method not only reduces energy waste, but also improves the overall efficiency of energy use, bringing users a more intelligent, convenient and comfortable life experience.

[0023] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 It is a process framework diagram of an energy output power self-regulation system based on artificial intelligence;

[0026] Figure 2 The flowchart of an energy output power self-regulation system based on artificial intelligence is shown in FIG. DETAILED DESCRIPTION

[0027] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Embodiment 1

[0028] This embodiment provides an energy output power self-regulation system based on artificial intelligence, which includes data collection, processing, comfort analysis, intelligent control and actuator modules. Sensors deployed in smart buildings collect indoor environmental parameters and personnel activity data in real time, use the PMV-PPD model to evaluate comfort, and combine historical data with the autoregressive moving average model to predict future comfort changes. The intelligent control module formulates control strategies based on comfort and energy demand forecasts through linear programming and optimization algorithms, dynamically adjusts the output power of power equipment, and the actuator accurately executes control instructions to achieve indoor environment optimization and efficient energy utilization.

[0029] The data acquisition module deploys various types of sensors in key areas of the building according to actual needs. The sensors include but are not limited to temperature and humidity sensors, light sensors, human infrared sensors, and air quality sensors. A sensor network is constructed in a wireless manner to ensure stable communication between the sensors and the data processing center. A network management system is set up to uniformly manage and configure the sensor network. A series of configuration parameters are preset for each sensor when it is deployed. The sensor collects indoor environmental parameters and personnel activities in real time based on the preset configuration parameters. Before data transmission, the sensor will perform preliminary processing on the collected raw data. In order to ensure the security of the data during transmission, the sensor will encrypt the data after preliminary processing. The encrypted data is transmitted to the data processing center through the sensor network. After receiving the data from the sensor network, the data processing center performs decryption operations to restore the original data. The decrypted data will be stored in the database.

[0030] The data processing module receives the raw data transmitted from the data acquisition module through a preset interface. These data include indoor environmental parameters and personnel activities. According to the source of the data, the received data is preliminarily distinguished, and the format of the received data is checked to see if it meets the predefined standards. The data that passes the check is converted into a unified format and a timestamp is added. The noise in the raw data is identified using statistical methods, and the identified noise is removed to improve the accuracy of the data. A reasonable threshold is set, and outlier detection is performed on the processed data. The detected outliers are removed to prevent them from having an adverse effect on subsequent analysis. The data after noise removal and outlier removal is further cleaned, and a suitable database is selected to store the cleaned data according to the system requirements, and the cleaned data is stored in the database according to the predetermined data structure and index.

[0031] The comfort analysis module receives the cleaned and pre-processed indoor environmental parameters and personnel activity data from the data processing module, and ensures that the received data conforms to the predetermined data format and standard for subsequent analysis. PMV and PPD are international standard models for evaluating environmental comfort. PMV represents the predicted average voting value, which is used to quantify the human body's thermal sensation of the environment. PPD represents the predicted percentage of dissatisfaction, which represents the proportion of people who are dissatisfied with the environment. The received environmental parameters and personnel activity data are input into the PMV-PPD model, and the PMV-PPD model is used to calculate the human body's thermal sensation under the current environmental parameters and personnel activities. The predicted value and dissatisfaction percentage, in addition to the PMV-PPD model, considers other factors that affect comfort and conducts a comprehensive evaluation. Different weights are assigned according to the importance of each factor on comfort. Based on the comprehensive evaluation results, the overall comfort score of the current indoor environment is calculated. The time series analysis model is established using historical comfort data and the corresponding environmental parameters and personnel activity data. Based on the time series analysis model, the comfort change trend in the future is predicted. According to the actual application effect and user feedback, the accuracy of the comfort analysis model is evaluated. According to the evaluation results, the model is continuously optimized and adjusted. A user feedback mechanism is established to collect users' feelings and suggestions on the comfort of the indoor environment as an important basis for model optimization.

[0032] The intelligent control module receives the current and historical comfort assessment results from the comfort analysis module, including the overall comfort score and the comfort change trend, performs necessary preprocessing on the received data, and uses a linear regression model to combine historical data and the current comfort change trend to predict the energy demand in the future. Based on the historical energy usage data and the corresponding comfort assessment results, the linear regression model is trained, and the current comfort assessment results and trends are input into the trained linear regression model to obtain the predicted value of energy demand in the future. According to the energy demand prediction results and the comfort prediction results, combined with the energy management goals, a preliminary control strategy is formulated, the preliminary strategy is optimized using a linear programming algorithm, the optimized control strategy is converted into specific control instructions, the control instructions are sent to the corresponding actuators, and feedback information is received after the actuators execute the instructions.

[0033] The actuator receives the control instructions from the intelligent control module. After receiving the instructions, the parsing unit inside the actuator decodes and verifies the instructions. The actuator establishes a connection with the power equipment that needs to be regulated. Before the regulation, the actuator detects the current operating status of each power equipment in real time. According to the formulated regulation plan, the actuator adjusts the control parameters of the power equipment to accurately adjust its output power. During the regulation process, the actuator continuously collects the operating status of the power equipment and changes in indoor environmental parameters. If the actuator detects equipment failure, data anomalies and safety hazards, it will immediately activate the exception handling mechanism. Embodiment 2

[0034] An energy output power self-regulation system based on artificial intelligence in this embodiment particularly emphasizes taking human comfort factors into consideration and regulating energy output power through artificial intelligence.

[0035] Receive indoor environmental parameter data and personnel activity data from sensors and other data sources, clean the data, remove noise and outliers, and perform necessary preprocessing.

[0036] The PMV-PPD model is used to evaluate the impact of environmental parameters and human activity factors on comfort. The required parameters, indoor air temperature, , mean radiant temperature , indoor air velocity , relative humidity , human metabolic rate , clothing thermal resistance , sensible heat exchange between human body and environment ,in, Mechanical work done for the human body, convective heat transfer ,in, is the convective heat transfer coefficient, is the human body surface temperature, radiation heat transfer ,in, is the clothing area coefficient, is the radiation heat transfer coefficient, evaporative heat dissipation , including evaporative heat dissipation from the skin surface and evaporative heat dissipation through breathing ,in, is the ratio of the effective evaporation area to the total surface area, is the saturated water vapor partial pressure at skin temperature, is the water vapor partial pressure of the indoor air, is the evaporation heat transfer coefficient, and the human body heat balance equation is: ,in, is the heat storage rate, For the radiation heat exchange between human body and environment, For the convective heat transfer between the human body and the environment, calculate the PMV using the formula: ,

[0037] To calculate PPD, the formula is: When the PMV value is close to 0, it indicates that the thermal environment is in a thermal neutral state and feels comfortable. When the PMV is a negative value, it means that the environment is cold. When the PMV is a positive value, the environment is hot. The lower the PPD value, the lower the percentage of people who are dissatisfied with the thermal environment, and the higher the comfort of the thermal environment. The overall comfort score is calculated.

[0038] Based on historical data and the autoregressive moving average model, the comfort level change trend in the future is predicted. The indoor environment parameter data, personnel activity data and corresponding comfort-related index data in the past period of time are collected, and the autoregressive moving average (ARIMA) model is used for prediction. The general form of the autoregressive moving average model is: ,in, is the backshift operator, yes The order difference operator, It is a comfort-related index of PMV and PPD. It is a white noise sequence. Check the stationarity of the comfort time series. If it is not stationary, perform differential processing. According to the autocorrelation function (ACF) and partial autocorrelation function (PACF) diagrams of the time series, preliminarily determine the parameters (p, d, q) of the ARIMA model. Use historical data to estimate the parameters of the selected ARIMA model to obtain the autoregressive coefficient and moving average coefficient. Use the trained ARIMA model to predict the comfort-related indicators in the future. According to the predicted PMV and PPD values, analyze the changing trend of comfort in the future. According to the actual application effect and user feedback, continuously optimize and adjust the comfort analysis model and prediction model to improve the accuracy and reliability of the evaluation.

[0039] The intelligent control module collects historical energy demand data and data on related factors that affect energy demand, and uses linear regression to combine historical data and current trends to predict energy demand in the future. The basic form of the linear regression model is: ,in, is the dependent variable (energy demand), is the independent variable (factor affecting energy demand), are model parameters, is the error term, and the model parameters are estimated using the least squares method using historical data. The goal of the least squares method is to minimize the residual sum of squares. The formula is: in, It is the number of data points. Combined with the current trend, the future value of the independent variable is predicted. The predicted independent variable value is substituted into the linear regression model to calculate the predicted value of energy demand in the future period.

[0040] According to the predicted energy demand and comfort prediction results provided by the comfort analysis module, combined with the energy management goals, the intelligent control module formulates a preliminary control strategy.

[0041] The linear programming algorithm is used to optimize the preliminary control strategy to find the optimal control strategy with the highest energy efficiency and the lowest cost under the premise of meeting the comfort requirements. The adjusted control parameter is set as the decision variable, denoted as , the objective function is the quantity that needs to be minimized during the optimization process. Here, it is the cost minimization while considering the energy efficiency. The formula is ,in, is the unit cost, are the corresponding energy usage and control parameters, is the cost function related to energy efficiency, is the number of cost items related to energy efficiency. The constraints are: comfort requirements: reflected by setting the upper and lower limits of temperature range, humidity range, and air velocity parameters: , Equipment capability limitation: such as maximum output power and minimum startup time of the equipment, expressed as: ,Energy supply constraints: grid power supply capacity, fuel supply constraints, expressed as: , transform the above objective function and constraints into the standard form of linear programming problem, and use linear programming algorithm to solve it. According to the results of linear programming, explain the optimal value of each decision variable, and formulate specific control strategies accordingly. Convert the optimized control strategies into specific control instructions and send them to the actuators to realize automatic adjustment of energy output power.

[0042] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An energy output power self-regulation system based on artificial intelligence, characterized in that: The system consists of the following components: Data collection module: Through various sensors deployed in smart buildings, indoor environmental parameters and personnel activities are collected in real time; Data processing module: receives the raw data transmitted by the data acquisition module, performs preprocessing and cleaning, removes noise and outliers, and passes the processed data to subsequent modules for analysis; Comfort analysis module: Based on the preset comfort model, it comprehensively considers the impact of multiple factors on human comfort, analyzes indoor environmental parameters and personnel activities, and evaluates the comfort level of the current indoor environment; The intelligent control module receives the current and historical comfort evaluation results from the comfort analysis module, and uses linear regression to combine historical data and current trends to predict energy demand in the future. Based on the energy demand and comfort prediction results, combined with energy management goals, a preliminary control strategy is formulated, and the preliminary strategy is optimized using a linear programming algorithm to find the optimal control strategy with the highest energy efficiency and the lowest cost while meeting the comfort requirements. The optimized control strategy is converted into specific control instructions and sent to the actuator; Actuator: According to the instructions of the intelligent control module, the output power of the power equipment is accurately adjusted to ensure the effective implementation of the control strategy and achieve real-time optimization of the indoor environment.

2. The energy output power self-regulation system based on artificial intelligence according to claim 1 is characterized in that: The data acquisition module deploys a variety of sensors in key areas within the building and builds a sensor network between the data processing center. The sensors collect indoor environmental parameters and personnel activities in real time according to preset configuration parameters. Before data transmission, the collected raw data is preliminarily processed, and the relevant data is encrypted during transmission and transmitted to the data processing center through the sensor network. The data processing center receives the data and stores it.

3. The energy output power self-regulation system based on artificial intelligence according to claim 1 is characterized in that: The data processing module receives the raw data transmitted from the data acquisition module, distinguishes the received indoor environmental parameters and personnel activities according to the sensor type and the acquisition location, checks the format of the data, converts the received data into a unified format, adds a timestamp, identifies and removes noise in the raw data, sets a reasonable threshold to detect and eliminate outliers in the raw data, further cleans the data after noise removal and outlier elimination, and stores the cleaned data in a database.

4. The energy output power self-regulation system based on artificial intelligence according to claim 1 is characterized in that: The comfort analysis module receives cleaned and pre-processed indoor environmental parameter data and personnel activity data, uses the PMV-PPD model to evaluate the impact of environmental parameters and personnel activity factors on comfort, conducts a comprehensive evaluation of the factors affecting comfort, and calculates the overall comfort score of the current indoor environment based on the comprehensive evaluation results. Based on historical data and time series analysis models, the comfort change trend in the future is predicted, and according to actual application effects and user feedback, the comfort analysis model is continuously optimized and adjusted to improve the accuracy of the evaluation.

5. The energy output power self-regulation system based on artificial intelligence according to claim 4 is characterized in that: The comfort analysis module uses the PMV-PPD model to evaluate the impact of environmental parameters and personnel activity factors on comfort, and obtains the required parameters through measurement and calculation, such as indoor air temperature. , mean radiant temperature , indoor air velocity , relative humidity , human metabolic rate , clothing thermal resistance , calculate the sensible heat exchange between the human body and the environment , the formula is: ,in, is the metabolic rate of the human body, It is the mechanical work done by the human body. is the convective heat transfer between the human body and the surrounding air, and the calculation formula is: , is the clothing area coefficient, is the convective heat transfer coefficient, is the human body surface temperature, calculated as, is the indoor air temperature, is the radiation heat exchange between the human body and the surrounding environment, and the calculation formula is: , is the radiation heat transfer coefficient, is the mean radiant temperature, It is the amount of heat dissipated by the human body through evaporation of the skin surface and breathing. The calculation formula is: , , is the amount of heat dissipated by evaporation from the skin surface. is the evaporative heat dissipation from breathing, is the water vapor partial pressure of the air around the human body, calculated as: ,in, is the air temperature The saturated water vapor partial pressure under the condition of heat storage rate in the human body heat balance equation , PMV and PPD are calculated by the formula.

6. The energy output power self-regulation system based on artificial intelligence according to claim 4 is characterized in that: The comfort analysis module predicts the comfort change trend in the future based on historical data and the autoregressive moving average model. The general form of the autoregressive moving average model is: ,in, is the backshift operator, yes The order difference operator, It is a comfort-related index of PMV and PPD. It is a white noise sequence. Check the stationarity of the comfort time series. According to the autocorrelation function and partial autocorrelation function graph of the time series, preliminarily determine the parameters (p, d, q) of the autoregressive moving average model. Use historical data to estimate the parameters of the selected autoregressive moving average model. Use the trained autoregressive moving average model to predict the comfort-related indicators in the future. Analyze the changing trend of comfort in the future based on the prediction results.

7. The energy output power self-regulation system based on artificial intelligence according to claim 6 is characterized in that: The intelligent control module uses linear regression to combine historical data and current trends to predict energy demand in the future, collects historical energy demand data and related influencing factor data, and the basic form of the linear regression model is: ,in, is the energy demand, This is what affects energy demand. are model parameters, is the error term, which represents the part that cannot be explained in the model. The model parameters are estimated by the least squares method using historical data. , the goal of the least squares method is to minimize the residual sum of squares, the formula is: ,in, is the number of data points. The fitting effect of the model is evaluated by calculating the mean square error index. Combined with the current trend, the future values ​​of the independent variables are predicted. The predicted independent variable values ​​are substituted into the linear regression model to calculate the predicted value of energy demand in the future.

8. The energy output power self-regulation system based on artificial intelligence according to claim 6 is characterized in that: The intelligent control module uses a linear programming algorithm to optimize the preliminary control strategy to find the optimal control strategy with the highest energy efficiency and the lowest cost under the premise of meeting the comfort requirements. The adjusted control parameter is set as the decision variable, denoted as , the objective function is the quantity that needs to be minimized during the optimization process. In this scenario, the goal is to minimize the cost while considering energy efficiency. The formula is: ,in, is the unit cost, are the corresponding energy usage and control parameters, is the cost function related to energy efficiency, is the number of cost items related to energy efficiency. The constraints are comfort requirements, equipment capacity limitations, and energy supply limitations. It can be expressed as a linear inequality: , ,in, and About A linear function of and is a constant, and are the number of inequality constraints and equality constraints respectively. The comfort requirements are reflected by setting the upper and lower limits of the temperature range, humidity range, and air flow rate parameters. The above objective function and constraints are converted into the standard form of linear programming problems and solved using the linear programming algorithm. According to the results of linear programming, the optimal value of each decision variable is explained, and specific control strategies are formulated accordingly.

9. The energy output power self-regulation system based on artificial intelligence according to claim 1 is characterized in that: The actuator receives the control instructions from the intelligent control module, decodes and verifies the received instructions through the parsing unit, establishes a connection with the power equipment and detects the current operating status of each device in real time, and uses a closed-loop control strategy to accurately adjust the equipment output power based on the parsed instructions, collects the equipment operating status and indoor environmental parameter changes before and after the control, and feeds back to the intelligent control module. If equipment failure, data anomalies and safety hazards are detected, the exception handling mechanism will be immediately activated.

Citation Information

Patent Citations

  • Comprehensive energy system multi-objective optimization scheduling method considering human body comfort

    CN110889549A

  • Indoor environment comfort degree adjusting method and system based on deep learning

    CN113485498A

  • Integrated thermal management system based on data analysis

    CN117194904A

  • Building environment and energy coupling intelligent regulation and control system and method based on digital twinning

    CN118396780A

  • Combined air conditioning unit power utilization control system and method based on artificial intelligence

    CN118463361A