Energy-saving control system for linkage of door and window opening and closing state with indoor and outdoor environment

Abstract

The application provides an energy-saving control system for linkage of door and window opening and closing state and indoor and outdoor environment, relates to the field of energy-saving control, and solves the technical problem of low indoor energy-saving control efficiency of the prior art. The system comprises: an environment information acquisition module for acquiring multi-source environment data; a central processing module for outputting a current suitability score based on the multi-source environment data through an environment comfort model, triggering a digital twin model to generate a plurality of environment adjustment candidate strategies when the suitability score is lower than a preset threshold, and predicting suitability score curves corresponding to each candidate strategy; constructing and solving an optimization objective function for maximizing the suitability score curve and meeting an energy consumption constraint to obtain an optimal adjustment strategy; and an environment adjustment execution module for performing adjustment operations on the indoor environment according to the optimal adjustment strategy. The application is used in the environment adjustment process of various indoor scenes such as office spaces, family residences, commercial buildings and the like, which need to consider energy saving and comfort.

Description

Technical Field

[0001] This invention belongs to the field of green energy conservation, specifically an energy-saving control system that links the opening and closing status of doors and windows with the indoor and outdoor environment. Background Technology

[0002] With the in-depth implementation of the "dual-carbon" strategy, building energy conservation has become a key area for achieving the "dual control" targets for total energy consumption and intensity. Most people spend most of their time indoors, and a comfortable indoor environment directly affects human health and work efficiency. Therefore, indoor environment regulation needs to achieve a precise balance between energy consumption control and comfort assurance. This need is particularly prominent in commercial buildings, office spaces, and other scenarios.

[0003] However, traditional energy-saving control technologies often measure comfort based on environmental indicators, neglecting the multi-dimensional influencing factors of human perception. This can easily lead to misjudging comfort levels and prematurely shutting down regulating devices or over-operating high-energy-consuming equipment. Furthermore, because existing energy-saving control technologies are limited to indoor temperature and humidity indicators and lack real-time perception and integration of the outdoor environment, opportunities to utilize natural conditions to improve comfort are missed, thus reducing the efficiency and rationality of indoor energy-saving control. Summary of the Invention

[0004] This application provides an energy-saving control system that links the opening and closing status of doors and windows with the indoor and outdoor environment, solving the technical problem of low energy-saving control efficiency caused by inaccurate judgment of human comfort in the prior art.

[0005] To achieve the above objectives, this application adopts the following technical solution: Firstly, it provides an energy-saving control system that links the opening and closing status of doors and windows with the indoor and outdoor environment, including: The environmental information acquisition module is used to collect indoor environmental parameters, outdoor environmental parameters, and user presence status to obtain multi-source environmental data. The central processing module is used to output a current suitability score based on the multi-source environmental data and an environmental comfort model. When the suitability score is lower than a preset threshold, it triggers a digital twin model to generate multiple candidate environmental adjustment strategies and predicts the suitability score curve corresponding to each candidate strategy; and... An optimization objective function is constructed to maximize the suitability score curve while satisfying energy consumption constraints. The optimal regulation strategy is obtained by solving the optimization objective function. The suitability score curve represents the trajectory of the predicted suitability score at each time point in the future after adopting a certain environmental regulation candidate strategy. The environmental regulation execution module is used to perform regulation operations on the indoor environment according to the optimal regulation strategy.

[0006] Based on the above technical solution, in the energy-saving control system that links the opening and closing status of doors and windows with the indoor and outdoor environment provided in this application, the environmental information acquisition module not only covers indoor and outdoor environmental parameters, but also incorporates the user's presence status, forming multi-dimensional, multi-source environmental data; the central processing module converts the environmental condition into a quantifiable suitability score through an environmental comfort model. When the score is not up to standard, it generates multiple candidate strategies with the help of a digital twin model and predicts the suitability change curve of each strategy. Then, it solves the optimal solution through an optimization objective function with "maximizing the suitability score curve + meeting energy consumption constraints" as the core, thus achieving a synergistic balance between comfort improvement and energy consumption control; the environmental adjustment execution module directly performs adjustment operations based on the optimal strategy, ensuring that actions such as opening and closing doors and windows are highly matched with real-time environmental needs, reducing energy waste caused by ineffective adjustments.

[0007] Furthermore, the process of constructing the environmental comfort model includes: Instantaneous thermal sensation values ​​are calculated based on the user's body surface temperature, ambient air temperature, and airflow speed; these instantaneous thermal sensation values ​​are used to characterize the instantaneous hot and cold sensations directly perceived by the skin. Based on historical ambient temperature sequences and user-defined temperatures, the steady-state deviation value in the body is calculated through convolution integrals. The steady-state deviation value in the body is used to characterize the cumulative thermal or cold stress of the human body core temperature caused by long-term exposure to an environment deviating from the desired temperature. An air quality score is calculated based on indoor CO2 and PM2.5 concentrations; this air quality score is used to characterize the impact of air cleanliness on breathing comfort. The instantaneous thermal sensation value, the body steady-state deviation value, and the air quality score are nonlinearly fused to obtain an initial comfort score; The initial comfort score is corrected based on historical manual adjustment data to obtain the final suitability score.

[0008] Furthermore, the instantaneous thermal sensation value S thermal The formula for calculation is: Among them, T skin This indicates the user's body surface temperature, T. skinideal K represents the ideal body surface temperature. t V represents the temperature sensitivity coefficient, β represents the weight of airflow influence, and V r V represents airflow velocity. rideal T represents the ideal airflow velocity. r Indicates ambient air temperature; The formula for calculating the steady-state deviation value ΔCore in vivo is: Where α represents the temperature difference influence coefficient, T setpoint The preset target temperature for air conditioning is represented by t, the current time is represented by τ, the integral variable is represented by λ, and the time decay constant is represented by λ. The formula for calculating the air quality score is: Among them, C CO2 Indicates CO2 concentration, Th CO2 C represents the CO2 concentration threshold. PM2.5 Indicates PM2.5 concentration, Th PM2.5 k represents the PM2.5 concentration threshold. C02 k PM2.5 This represents the steepness parameter, which controls the rate of change of the sigmoid function near the concentration threshold.

[0009] Furthermore, the initial comfort score is calculated as follows: Among them, ECI raw γ represents the initial comfort score, and γ represents the steady-state weighting coefficient. The formula for calculating the suitability score is: Where ECI represents the suitability score, η represents the adaptive calibration coefficient, and ΔU represents the historical smoothed value of the user's manual adjustment.

[0010] Furthermore, the method for determining the adaptive calibration coefficient includes: After obtaining the user's manual adjustment data each time, the absolute difference between the predicted suitability score and the actual suitability score is calculated, and the average value of the absolute difference over a preset time period is calculated to obtain the mean absolute error. The mean absolute error is mapped to an adaptive calibration coefficient; the mapping relationship uses a negative correlation function to ensure that the smaller the mean absolute error, the larger the adaptive calibration coefficient, and the larger the mean absolute error, the smaller the adaptive calibration coefficient.

[0011] Its mapping relationship can be expressed as: η max is the upper limit of the calibration coefficient, and k is the attenuation coefficient.

[0012] Furthermore, the methods for obtaining the historical smoothing values ​​include: Monitor and record the user's manual adjustment amount u i and adjusting timestamp t i ; A weighted moving average algorithm is used to smooth historical manual adjustments, yielding a smoothed historical value. The calculation formula is as follows: ;in, t represents the weighting coefficient. current Let τ be the current time, and τ be the time decay constant.

[0013] Furthermore, the triggering digital twin model generates multiple environmental regulation strategies, including: Different combinations of device states are generated using a digital twin model to obtain multiple candidate strategies; the combinations of device states include door and window opening / closing status, air conditioner on / off mode, air conditioner on / off temperature, fresh air system on / off mode, fresh air system on / off airflow, fan on / off mode, and fan on / off speed.

[0014] Furthermore, the prediction of the suitability score curves corresponding to each candidate strategy includes: For each candidate strategy, based on building thermal parameters, current indoor and outdoor environmental parameters, and equipment performance parameters, thermodynamic and fluid dynamic equations are solved in a digital twin environment to simulate the environmental parameter sequence of indoor temperature, humidity, CO2 concentration, and PM2.5 concentration over a future period. The simulated environmental parameter sequence is used as input to the environmental comfort model, and the predicted suitability score curve for each candidate strategy in the future is output.

[0015] Furthermore, the optimization objective function satisfies: Among them, ECI desired ECI represents the target suitability score. predicted (τ) represents the fitness score predicted at time τ, P(τ) represents the total system power at time τ, and α represents the energy saving weight coefficient.

[0016] Furthermore, the central processing module includes several edge computing units, each edge computing node is deployed in a region to process multi-source environmental data of a single region and output the optimal adjustment strategy for a single region; The environmental information acquisition module, the environmental regulation execution module, and each edge computing unit are connected via a wireless mesh network; the wireless mesh network is used to establish point-to-point communication links between the edge computing node and the environmental information acquisition module and the environmental regulation execution module of its respective area. Furthermore, the first wireless mesh network is constructed using the Zigbee or Thread protocol; The second communication link is a wireless network (Wi-Fi), Ethernet, or cellular mobile network.

[0017] Secondly, an indoor energy-saving control device is provided, comprising: a communication unit and a processing unit; the communication unit is used to establish a data connection with an environmental information acquisition module to receive multi-source environmental data, and to establish a communication connection with an environmental regulation execution module to receive the optimal regulation strategy; The processing unit is used to output a current suitability score based on the multi-source environmental data and an environmental comfort model. When the suitability score is lower than a preset threshold, it triggers a digital twin model to generate multiple candidate environmental adjustment strategies and predicts the suitability score curve corresponding to each candidate strategy; and... An optimization objective function is constructed to maximize the suitability score curve and satisfy energy consumption constraints. The optimal regulation strategy is obtained by solving the optimization objective function and then transmitted to the communication unit.

[0018] Thirdly, this application provides an indoor energy-saving control device, comprising: a processor and a storage medium; the storage medium includes instructions, and the processor is configured to execute the instructions to implement the method described in the first aspect and any possible implementation thereof. This indoor energy-saving control device may be an electronic device or a chip within an electronic device.

[0019] Fourthly, this application provides an energy-saving control method that links the opening and closing status of doors and windows with the indoor and outdoor environment, including: Collect indoor environmental parameters, outdoor environmental parameters, and user presence status to obtain multi-source environmental data; Based on the multi-source environmental data, the current suitability score is output through the environmental comfort model. When the suitability score is lower than a preset threshold, the digital twin model is triggered to generate multiple environmental adjustment candidate strategies and predict the suitability score curve corresponding to each candidate strategy. Construct an optimization objective function that maximizes the suitability score curve and satisfies energy consumption constraints, and solve the optimization objective function to obtain the optimal regulation strategy; The indoor environment is regulated according to the optimal regulation strategy.

[0020] Fifthly, this application provides a computer-readable storage medium storing instructions that, when executed on an indoor energy-saving control device, cause the indoor energy-saving control device to perform the methods described in the first aspect and any possible implementation thereof.

[0021] In a sixth aspect, this application provides a computer program product containing instructions that, when the computer program product is run on an indoor energy-saving control device, cause the indoor energy-saving control device to perform the methods described in the first aspect and any possible implementation thereof.

[0022] This application provides an energy-saving control system that links the opening and closing status of doors and windows with the indoor and outdoor environment. It uses an environmental information acquisition module to capture indoor and outdoor environmental parameters and user status to form a multi-dimensional data foundation. At its core is an environmental comfort model that integrates instantaneous thermal sensation, body steady-state deviation, and air quality. This model, combined with adaptive correction based on historical manual adjustment data, achieves precise quantification of comfort needs. A digital twin model generates candidate strategies for combining the states of multiple devices such as doors, windows, air conditioning, and fresh air systems, and simulates future environmental parameter sequences to predict suitability curves. An optimization objective function that minimizes the square of the comfort deviation and the weighted sum of system energy consumption balances comfort and energy saving. Furthermore, relying on regionalized edge computing units to process single-region data, this system effectively solves the technical problems of decision-making bias, comfort judgments deviating from actual human sensations, and lack of forward-looking prediction in traditional environmental control systems. Ultimately, it achieves dynamic and precise matching of indoor environmental suitability and effective control of system energy consumption, creating a deeply linked intelligent closed loop between door and window opening and closing and environmental regulation. This provides users with indoor environmental control services that balance comfort and low-carbon energy saving. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 A system architecture diagram of an energy-saving control system that links the opening and closing status of doors and windows with the indoor and outdoor environment, provided in an embodiment of this application. Figure 2 A flowchart illustrating the energy-saving control method for linking the opening and closing status of doors and windows with the indoor and outdoor environment, as provided in an embodiment of this application. Figure 3 A flowchart illustrating another energy-saving control method for linking the opening and closing status of doors and windows with the indoor and outdoor environment, provided in an embodiment of this application; Figure 4 A flowchart illustrating another energy-saving control method for linking the opening and closing status of doors and windows with the indoor and outdoor environment, provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of the indoor energy-saving control device provided in the embodiments of this application; Figure 6 A schematic diagram of the hardware structure of the indoor energy-saving control device provided in the embodiments of this application. Detailed Implementation

[0025] In the description of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. The "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" means one or more, and "multiple" means two or more. The terms "first," "second," etc., do not limit the quantity or order of execution, and "first," "second," etc., do not necessarily imply differences.

[0026] It should be noted that, in this application, the terms "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0027] The energy-saving control method for linking the opening and closing status of doors and windows with the indoor and outdoor environment provided in this application embodiment can be applied to, for example... Figure 1 In the energy-saving control system shown, where the opening and closing status of doors and windows is linked to the indoor and outdoor environment, such as... Figure 1 As shown, the system includes: The environmental information acquisition module is used to collect indoor environmental parameters, outdoor environmental parameters, and user presence status to obtain multi-source environmental data. The central processing module is used to output a current suitability score based on multi-source environmental data and an environmental comfort model. When the suitability score is lower than a preset threshold, it triggers a digital twin model to generate multiple candidate environmental regulation strategies and predicts the suitability score curve corresponding to each candidate strategy; and... Construct an optimization objective function that maximizes the fitness score curve and satisfies energy consumption constraints, and solve the optimization objective function to obtain the optimal regulation strategy; The environmental regulation execution module is used to perform regulation operations on the indoor environment according to the optimal regulation strategy.

[0028] It should be noted that this system adopts a modular connection architecture of "regional edge collaboration + hierarchical communication" to ensure the real-time performance, low power consumption, and regional specificity of data transmission between modules. The specific connection methods and their corresponding functions are as follows: The central processing module contains several edge computing units, each of which is deployed in a physical area (such as partition A of an office area or the living room area of ​​a home), serving as the core node for data processing and strategy generation in that area. The environmental information acquisition module (such as temperature sensor, CO2 sensor, human presence sensor) and the environmental regulation execution module (such as door and window drive device, air conditioner controller, fresh air system switch) both establish point-to-point communication links with the edge computing unit of their respective areas through a wireless mesh network. This wireless mesh network is built using the Zigbee or Thread protocol, both of which have the characteristics of low power consumption, anti-interference, and strong self-organizing network capability. It can adapt to high-frequency data acquisition from sensors (such as environmental parameter transmission once every 2 minutes) and low-latency command reception from actuators (such as door and window opening and closing command response time ≤10 seconds). This avoids the wiring limitations of wired connections and ensures the efficient transmission of multi-source environmental data from the acquisition module to the edge computing unit within the area, as well as the accurate issuance of optimal regulation strategies from the edge computing unit to the execution module.

[0029] In addition, the system is equipped with a second communication link, which uses Wi-Fi, Ethernet or cellular mobile networks (such as 4G / 5G), mainly for global coordination communication between edge computing units and central processing modules: when the adjustment strategy of a single area needs to be associated with other areas (such as the bedroom and living room sharing the same fresh air main pipe in a home, which need to coordinate the control of fresh air volume), or when the edge computing unit needs to upload regional operation data to the central processing module for global energy consumption statistics, cross-regional and cross-level data interaction is realized through this link.

[0030] This layered communication design serves two purposes. First, it uses a wireless mesh network to meet the short-range, low-power data exchange needs of modules within the area, reducing energy waste caused by invalid data transmission. Second, it ensures global coordination through a second communication link, guaranteeing that the central processing module can coordinate strategies across different areas and avoid inter-area adjustment conflicts (such as simultaneous activation of high-energy-consuming devices in adjacent areas leading to total power overload). Simultaneously, the connection methods of each module are adapted to the edge computing capabilities of the central processing module—multi-source data from the environmental information acquisition module can be directly transmitted to the edge computing unit of its respective area, where it can quickly process and generate the optimal adjustment strategy specific to that area. This eliminates the need for centralized transmission to the central processing module for processing, significantly shortening the "data acquisition-strategy generation-execution adjustment" cycle. This further improves the matching accuracy between door / window opening / closing, equipment operation, and real-time environmental requirements, helping the system achieve high energy efficiency while ensuring comfort.

[0031] To address the technical problem of low energy-saving control efficiency due to inaccurate judgment of human comfort in existing technologies, embodiments of this application provide an energy-saving control method that links the opening and closing status of doors and windows with the indoor and outdoor environment. This method includes: Collect indoor environmental parameters, outdoor environmental parameters, and user presence status to obtain multi-source environmental data; Based on multi-source environmental data, the current suitability score is output through the environmental comfort model. When the suitability score is lower than the preset threshold, the digital twin model is triggered to generate multiple environmental adjustment candidate strategies and predict the suitability score curve corresponding to each candidate strategy. Construct an optimization objective function that maximizes the suitability score curve while satisfying energy consumption constraints, solve the optimization objective function to obtain the optimal regulation strategy, and then execute it.

[0032] Based on this, the method ensures the comprehensiveness of the decision-making basis through multi-dimensional data collection, and realizes the scientific generation and optimization of adjustment strategies by relying on intelligent models. While improving the suitability of the indoor environment, it can effectively control energy consumption and solve the problems of strong blindness and difficulty in balancing energy consumption and comfort in traditional adjustment methods.

[0033] like Figure 2 As shown in the embodiment of this application, the energy-saving control method that links the opening and closing status of doors and windows with the indoor and outdoor environment includes: S1. Collect indoor environmental parameters, outdoor environmental parameters, and user presence status to obtain multi-source environmental data, and output the current suitability score based on the multi-source environmental data through the environmental comfort model.

[0034] The indoor environmental parameters represent physical or chemical indicators reflecting the indoor spatial environment, such as indoor temperature, indoor humidity, and indoor light intensity. The outdoor environmental parameters represent physical or chemical indicators reflecting the outdoor spatial environment, such as outdoor temperature, outdoor humidity, and outdoor wind speed. User presence status indicates whether there is user activity indoors. These parameters and statuses can be collected by various common sensors, such as indoor and outdoor temperatures through temperature sensors, indoor humidity through humidity sensors, and user presence status through human presence sensors or infrared sensors. The environmental comfort model is used to transform multi-source environmental data into quantifiable indicators that characterize the user's comfort level in the indoor environment. The current suitability score characterizes the degree to which the current indoor environment meets the user's comfort needs in terms of temperature, humidity, and adaptability to user activities, and can typically be expressed using a percentage or ten-point scale.

[0035] In some implementations, indoor environmental parameters may include indoor air circulation speed, while outdoor environmental parameters may include outdoor precipitation and outdoor air quality level. User presence status may also be collected through cameras (with basic human body recognition algorithms), access control system opening and closing records, etc. The data collection devices may use wired connections (such as connecting to the data collection terminal via RS485 bus) or wireless connections (such as transmitting data via Bluetooth, Wi-Fi, etc.) to adapt to different building structures and installation scenarios. The environmental comfort model may be built based on industry-standard comfort evaluation criteria (such as the ASHRAE thermal comfort standard) or may be based on preset evaluation logic that meets the basic comfort needs of the target user group.

[0036] It should be noted that the data acquisition frequency can be set according to actual needs, such as high-frequency acquisition (once every 1 minute) to ensure data real-time performance, or low-frequency acquisition (once every 5 minutes) to reduce device power consumption and data transmission pressure.

[0037] For example, a DS18B20 temperature sensor can be installed in the living room to collect indoor temperature, and an SHT30 humidity sensor can be installed to collect indoor humidity. A BME280 multi-parameter sensor can be installed on the outdoor balcony to collect outdoor temperature, humidity, and wind speed. A PIR infrared human body sensor can be installed at the indoor door to determine the presence of the user. All parameters are collected every 2 minutes and transmitted to the data processing terminal. Through an environmental comfort model built based on the ASHRAE comfort zone standard, the information of the current indoor temperature of 28°C, indoor humidity of 65%, and the presence of the user is converted into a current suitability score of 70 points (out of 100).

[0038] S2. When the suitability score is lower than the preset threshold, the digital twin model is triggered to generate multiple environmental regulation candidate strategies and predict the suitability score curve corresponding to each candidate strategy.

[0039] Among them, the Digital Twin Model (DT Model) refers to a virtual model constructed digitally that is highly similar to the actual indoor space (including building structure, doors and windows, environmental control equipment, etc.) and is used to simulate the changing trend of the indoor environment under different environmental control strategies; the suitability score curve represents the trajectory of the predicted suitability score at each time point in the future after adopting a certain environmental control candidate strategy.

[0040] In some implementations, environmental control candidate strategies can cover different opening and closing states of doors and windows (e.g., fully open, half open, and fully closed), different operating modes of basic indoor environmental control equipment (e.g., air conditioning in cooling mode, air conditioning in ventilation mode, fresh air system in low airflow mode, and fresh air system in high airflow mode), and different combinations of equipment operating parameters (e.g., setting 24℃ in air conditioning cooling mode and setting 26℃ in air conditioning cooling mode). The digital twin model can be built based on basic data such as the actual indoor space dimensions, wall insulation coefficient, and equipment operating parameters (e.g., air conditioning cooling capacity and fresh air system airflow). The simulation process can incorporate physical laws such as heat conduction and air circulation without relying on complex algorithms. The prediction time span of the suitability score curve can be set according to the equipment adjustment response speed. For example, for equipment such as doors and windows and air conditioning, where the environment changes rapidly after adjustment, the prediction time span can be set to the next 30 minutes to 1 hour.

[0041] It should be noted that the preset threshold can be flexibly set according to user needs or application scenarios. For example, for a home scenario, the preset threshold can be set to 60 points (out of 100), and for an office scenario, the preset threshold can be set to 65 points (out of 100). In addition to "suitability score is lower than preset threshold", the conditions for triggering the digital twin model can also include "suitability score is lower than preset threshold for N consecutive times (e.g., 3 consecutive times)" to avoid false triggering due to single data fluctuations.

[0042] For example, if the current indoor temperature is 29℃ and humidity is 70%, and the outdoor temperature is 33℃ and humidity is 65%, the suitability score is 55 points (below the preset threshold of 60 points), triggering the digital twin model; this model is based on the indoor space (20㎡, wall insulation coefficient) Equipment parameters (air conditioning cooling capacity 2500W, maximum air volume of fresh air system 150m³ / h) 3 The system constructs a system ( / h) to generate five logically consistent candidate environmental control strategies: Strategy 1 (all doors and windows closed + air conditioning at 24°C), Strategy 2 (all doors and windows closed + air conditioning at 25°C), Strategy 3 (doors and windows partially open + high airflow of the fresh air system), Strategy 4 (all doors and windows open + high airflow of the fresh air system), and Strategy 5 (all doors and windows closed + air conditioning supply + low airflow of the fresh air system). Simultaneously, it predicts the suitability score every 10 minutes within the next hour, forming a score curve for each strategy. For example, the score curve for Strategy 2 is 55 points → 63 points → 69 points → 73 points → 71 points → 69 points, and the score curve for Strategy 3 is 55 points → 58 points → 61 points → 63 points → 62 points → 61 points.

[0043] S3. Construct an optimization objective function that maximizes the suitability score curve and satisfies energy consumption constraints, solve the optimization objective function to obtain the optimal regulation strategy and execute it.

[0044] Among them, optimizing the objective function is a mathematical expression tool for balancing comfort and energy conservation needs, aiming to find an environmental regulation strategy that maximizes comfort while minimizing energy waste.

[0045] In some implementations, the objective function of "maximizing the suitability score curve" can be specifically defined as "maximizing the arithmetic mean of the suitability scores over a future time period T", "maximizing the peak value of the suitability scores over a future time period T", or "minimizing the cumulative duration of the suitability scores being below a preset threshold over a future time period T". The "energy consumption constraint" can be specifically set as "the total energy consumption of the system does not exceed E kWh over a future time period T", "the real-time operating power of the environmental control equipment does not exceed P watts (W)", or "the cumulative daily control energy consumption does not exceed Etotal kWh". The objective function can be solved using common optimization algorithms in the industry, such as genetic algorithms, particle swarm optimization (PSO), or enumeration (for scenarios with a small number of candidate strategies). The execution of the optimal control strategy can be achieved through common execution components such as relays and intelligent controllers. For example, a relay can control the start and stop of the door and window drive motor to adjust the opening and closing state of the doors and windows, and an intelligent controller can send instructions to the air conditioner to adjust its operating mode and parameters.

[0046] It should be noted that the specific value of the energy consumption constraint can be set according to the user's energy-saving needs, the energy consumption parameters of the equipment, and the building's energy quota. For example, for scenarios with high energy-saving needs, the total energy consumption constraint for the next hour can be set to 1 kWh, and for scenarios prioritizing comfort, the energy consumption constraint can be set to 1.5 kWh. The choice of solution algorithm can be flexibly adjusted according to the number of candidate strategies. When the number of candidate strategies is small (e.g., less than 10), the enumeration method can be used to ensure the solution speed and accuracy. When the number of candidate strategies is large (e.g., more than 20), the genetic algorithm can be used to improve the solution efficiency.

[0047] For example, the objective function is constructed as "maximizing the average suitability score within the next hour, while ensuring that the total energy consumption within the next hour does not exceed 1.2 kWh". The particle swarm optimization algorithm is used to solve the five candidate strategies generated in S2. Considering the energy consumption characteristics of the equipment in an outdoor high-temperature (33℃) scenario (air conditioning energy consumption increases by more than 30% when doors and windows are open, so the combination of open doors and windows + air conditioning operation is prioritized for elimination), the average score and energy consumption of each strategy are calculated: Strategy 1 (all doors and windows closed + air conditioning cooling at 24℃) has an average score of 69 points and an energy consumption of 1.4 kWh (over-constraint); Strategy 2 (all doors and windows closed + air conditioning cooling at 26℃) has an average score of 68 points and an energy consumption of 1.0 kWh (meets the constraint). (Constraints) Strategy 3 (doors and windows half open + high airflow of fresh air system) had an average score of 61 points and energy consumption of 0.3 kWh (satisfies constraints); Strategy 4 (doors and windows fully open + high airflow of fresh air system) had an average score of 59 points and energy consumption of 0.25 kWh (satisfies constraints); Strategy 5 (doors and windows fully closed + air conditioning + low airflow of fresh air system) had an average score of 63 points and energy consumption of 0.5 kWh (satisfies constraints). Finally, Strategy 2 (doors and windows fully closed + air conditioning cooling to 26℃) with the highest average score and meeting the energy consumption constraints was selected as the optimal adjustment strategy. The door and window drive motor is controlled by a relay to adjust the doors and windows to the fully closed state, and the intelligent controller sends a command to the air conditioner to start the cooling mode and set the temperature to 25℃.

[0048] Based on the above technical solutions, the energy-saving control method for linking the opening and closing status of doors and windows with the indoor and outdoor environment provided in this application ensures the universality and adaptability of multi-source environmental data acquisition by using common sensors and data acquisition methods, covering various scenarios such as homes, offices, and businesses; it avoids the blindness of traditional "trial and error" adjustment by using digital twin models to simulate the effects of different adjustment strategies, and improves the scientific nature of strategy generation; by constructing an optimization objective function and solving it using conventional optimization algorithms, it achieves a precise balance between comfort and energy consumption, satisfying both user comfort needs and energy-saving requirements; the overall method does not rely on special or scarce technical means, has strong feasibility and scalability, and can effectively solve the problems of insufficient environmental adjustment decision-making basis and difficulty in balancing comfort and energy consumption in existing technologies.

[0049] In one possible implementation of the embodiments of this application, combined with Figure 2 ,like Figure 3 As shown, the above S1 can be implemented through the following S101, S102 and S103, which are explained in detail below: S101. Collect multi-source environmental data and user-related data required to construct the environmental comfort model.

[0050] The multi-source environmental data includes indoor and outdoor environmental parameters, while user-related data includes user body surface temperature, user status, and historical manual adjustment data. Indoor environmental parameters at least cover ambient air temperature (T). r airflow velocity V r CO2 concentration C CO2 PM2.5 concentration C PM2.5 Outdoor environmental parameters should at least cover outdoor temperature, and user history manual adjustment data should include the adjustment amount u for each adjustment. i and the corresponding adjustment timestamp t i This provides the basic input for subsequent calculation of the sub-indices of the environmental comfort model.

[0051] In some implementations, user body surface temperature is collected using a contact-type temperature sensor. The sensor needs to be installed in a location the user frequently touches, and its surface must be covered with a flexible, thermally conductive material (such as a silicone pad) to improve contact fit. Indoor CO2 and PM2.5 concentrations are collected using a distributed method, with one collection node deployed in each of the different functional areas of the room. Data is collected every 5 minutes and averaged through a local gateway to serve as the overall indoor concentration data. Historical manual adjustment data must be linked to the environmental parameters at the time of adjustment, for example, recording "2024-05-01 19:00, the user adjusted the air conditioner temperature from 26℃ to 24℃ (adjustment amount u)". i =-2℃), at which point the indoor temperature is 27℃ and the humidity is 65%.

[0052] For example, the indoor environment can be treated as a whole, and multiple similar sensors can be deployed to obtain environmental parameters by averaging. Alternatively, the indoor environment can be divided into multiple areas according to function or area, and each area can be equipped with a set of sensors to collect data in different areas.

[0053] S102. Calculate the sub-indicators of the environmental comfort model based on the collected data, including instantaneous thermal sensation value, body steady-state deviation value, and air quality score.

[0054] Among them, the instantaneous thermal sensation value S thermal The instantaneous hot and cold sensations directly perceived by the skin are calculated using the user's body surface temperature, ambient air temperature, and airflow velocity; the steady-state deviation value ΔCore, used to characterize the cumulative thermal or cold stress at the body's core temperature, is calculated through the convolution integral of historical ambient temperature sequences and the user-set temperature; the air quality rating is A. r To characterize the impact of air cleanliness on breathing comfort, the three sub-indicators, calculated using CO2 concentration and PM2.5 concentration, together form the basis for calculating the initial comfort score.

[0055] In some implementations, the instantaneous thermal sensation value S thermalThe formula for calculation is: Among them, T skin This indicates the user's body surface temperature, T. skinideal K represents the ideal body surface temperature. t V represents the temperature sensitivity coefficient, β represents the weight of airflow influence, and V r V represents airflow velocity. rideal T represents the ideal airflow velocity. r Indicates ambient air temperature; The formula for calculating the steady-state deviation ΔCore in vivo is: Where α represents the temperature difference influence coefficient, T setpoint The preset target temperature for air conditioning is represented by t, the current time is represented by τ, the integral variable is represented by λ, and the time decay constant is represented by λ. The formula for calculating the air quality score is: Among them, C CO2 Indicates CO2 concentration, Th CO2 C represents the CO2 concentration threshold. PM2.5 Indicates PM2.5 concentration, Th PM2.5 k represents the PM2.5 concentration threshold. C02 k PM2.5 This represents the steepness parameter, which controls the rate of change of the sigmoid function near the concentration threshold.

[0056] In some implementations, the ideal body surface temperature can be determined through user group testing: the baseline value is set at 33.5℃ for the 20-30 age group, 33.2℃ for the 31-45 age group, and 33.0℃ for the 46-60 age group; the temperature sensitivity coefficient k... t The least squares fitting method was used to determine: different T samples were collected. skin Users' subjective ratings of hot or cold (1-5 points, 1 point is extremely cold, 5 points is extremely hot) are used to establish S thermal The mapping relationship with subjective ratings, and the final calibration of k t =0.75℃; the time decay constant λ was calibrated through 24-hour continuous testing: record T for each hour within 24 hours. r With user-set temperature T setpoint ΔCore was calculated for different λ values ​​and compared with the user's daily subjective fatigue score (1-10 points). The λ value with the highest fit was selected as 10 min. The airflow influence weight β was dynamically adjusted according to the season: 0.3 for summer (June-August), 0.2 for spring and autumn (March-May, September-November), and 0.1 for winter (December-February).

[0057] It should be noted that when calculating ΔCore, the range of the integration variable τ must be limited to the past 24 hours (i.e., t-τ≤24h). The influence of historical temperature data beyond 24 hours on the current human core temperature can be ignored to avoid distortion of the integration results; in the calculation of air quality scores, the CO2 concentration threshold Th CO2 According to the national standard "Indoor Air Quality Standard" (GB / T18883-2022), the PM2.5 concentration threshold is set at 1000 ppm. PM2.5 Set to 75 μg / m 3 The steepness parameter k of the sigmoid function CO2 =500ppm, k PM2.5 =25μg / m 3 This ensures that the score drops rapidly when the concentration approaches the threshold, reflecting the sensitive impact of air quality on comfort.

[0058] For example, the known user is 35-year-old T. skinideal =33.2℃, k t =0.75℃, β=0.3 (summer), V rideal =0.2m / s, T r =26.5℃, substitute S thermal Calculation formula: S thermal =tanh[(33.2-33.2) / 0.75]+0.3×tanh[(0.25-0.2)×(33.2-26.5)]≈0.098; Calculate ΔCore: Temperature difference influence coefficient α=0.001 (determined by fitting user thermal stress perception), T setpoint =25℃ (user-preset air conditioner target temperature), t=2024-05-06 19:00, τ is taken as the past 24 hours, the integral result ΔCore=0.001×∫(26.5-25)×e -(t-τ) / 600 ≈0.9 (the integration range is (t-86400, t)); calculate A r :C CO2 =450ppm, C PM2.5 =32μg / m 3 , then σ[(450-1000) / 500]≈0.249, σ[(32-75) / 25]≈0.157, A r =1-(0.249+0.157) / 2≈0.847.

[0059] S103. The initial comfort score is obtained by integrating the sub-indicators, and the final suitability score is obtained by combining historical manual adjustment data.

[0060] Among them, the initial comfort score (ECI) rawThe comfort score (ECI) is obtained by nonlinearly fusing instantaneous thermal sensation values, steady-state deviation values ​​within the body, and air quality scores. The comfort score is obtained by combining the initial comfort score with the historical smoothed value ΔU of the user's manual adjustment amount and the adaptive calibration coefficient η. The correction process is used to eliminate the deviation between the model's theoretical calculations and the user's actual comfort preferences.

[0061] In some implementations, the initial comfort score is calculated as follows: Among them, ECI raw γ represents the initial comfort score, and γ represents the steady-state weighting coefficient. The formula for calculating the suitability score is: Where ECI represents the suitability score, η represents the adaptive calibration coefficient, and ΔU represents the historical smoothed value of the user's manual adjustment.

[0062] In some implementations, the methods for obtaining historical smoothing values ​​include: Monitor and record the user's manual adjustment amount u i and adjusting timestamp t i ; A weighted moving average algorithm is used to smooth historical manual adjustments, yielding a smoothed historical value. The calculation formula is as follows: ;in, t represents the weighting coefficient. current Let τ be the current time, and τ be the time decay constant.

[0063] In some implementations, the steady-state weighting coefficient γ is calibrated through long-term user feedback: 50 users are selected for a 30-day test, and ECI is recorded daily. raw Based on user subjective comfort ratings (1-10 points), γ was adjusted using multiple linear regression analysis, ultimately set at γ=0.04; in the calculation of the historical smoothing value ΔU, the time decay constant τ was set to 86400s (1 day), and the weighting coefficients were... Only manually adjusted data from the last 30 days is retained.

[0064] In some implementations, the adaptive calibration coefficients are determined in the following ways: Over the past 7 days, after each instance of user manual adjustment data was obtained, the absolute difference between the predicted suitability score and the actual suitability score was calculated, and the average absolute error was obtained by averaging the absolute differences over a preset time period. The mean absolute error is mapped to an adaptive calibration coefficient; the mapping relationship uses a negative correlation function to ensure that the smaller the mean absolute error, the larger the adaptive calibration coefficient, and the larger the mean absolute error, the smaller the adaptive calibration coefficient.

[0065] Its mapping relationship can be expressed as: ηmax The upper limit of the calibration coefficient is 0.8, and k is the attenuation coefficient with a default value of 0.5. Both values ​​were determined through multiple tests.

[0066] It should be noted that when calculating the historical smoothing value ΔU, the sign of the adjustment amount must be related to environmental parameters, such as "lowering the air conditioning temperature by 2℃" (u i =-2℃) corresponds to "current temperature is too high", and the preference for "cooling demand" needs to be reflected in ΔU; the calculation of MAE needs to ensure that the time nodes of "model prediction score" and "user subjective score" are consistent, that is, the subjective score is recorded within 30 minutes after the user makes the adjustment, to avoid deviation caused by time difference.

[0067] For example, S is known thermal =0.098, ΔCore=0.9, A r =0.847, γ=0.04, calculate ECI raw =[1-(0.098 2 +0.04×0.9 2 )]×0.04×100≈81.14. Calculate ΔU:t current =2024-05-06 19:00, t1=2024-05-01 19:00 (interval 120 hours), t2=2024-05-03 20:30 (interval 68.5 hours), t3=2024-05-05 18:10 (interval 24.8 hours), w1=e -120 / 24 ≈0.0067, w2=e -68.5 / 24 ≈≈0.057, w3=e -24.8 / 24 ≈0.357, ΔU=[0.0067×(-2)+0.057×1+0.0357×(-1)] / [0.0067+0.057+0.357]≈-0.745; Calculate η: MAE for the past 7 days=4.2, η=0.8×e -0.5×4.2 ≈0.098; final .

[0068] Based on the above technical solution, S1 achieves the quantification from objective environmental parameters to subjective comfort scores through "data collection - sub-item calculation - fusion correction": S101 ensures the comprehensiveness and relevance of data collection, providing high-quality input for subsequent calculations; S102 transforms environmental parameters into quantifiable comfort sub-indicators, ensuring the scientific nature of the calculations; S103, through nonlinear fusion and historical data correction, ensures that the scores not only conform to the laws of the objective environment but also match the user's personalized comfort preferences, providing a reliable basis for subsequent judgment on whether to trigger adjustment strategies.

[0069] In one possible implementation of the embodiments of this application, combined with Figure 2,like Figure 3 As shown, the above S2 can be implemented through the following S201, S202 and S203, which are explained in detail below: S201. Collect and import the basic parameters required for the digital twin model to construct a virtual environment consistent with the actual indoor space.

[0070] The basic parameters include building thermal parameters, equipment performance parameters, and current indoor and outdoor environmental parameters, which are the core basis for the digital twin model to accurately simulate the actual environment. Building thermal parameters are used to characterize the heat transfer characteristics of the building structure, including at least the wall insulation coefficient k-value, roof insulation coefficient, window heat transfer coefficient, and indoor space dimensions (length × width × height). Equipment performance parameters are used to define the operating capabilities of environmental control equipment, including at least the rated cooling / heating capacity, minimum / maximum operating power, and temperature control accuracy of air conditioners; the rated airflow range and power of fresh air systems at different airflow levels; the airflow and power corresponding to the fan speed level; the opening / closing response time of doors and windows; and the air infiltration corresponding to different opening angles. The current indoor and outdoor environmental parameters are the latest multi-source data collected by S1, including indoor temperature, humidity, CO2 concentration, PM2.5 concentration, and airflow velocity; outdoor temperature, humidity, and user presence status, ensuring that the virtual environment is synchronized with the actual scene in real time.

[0071] In some implementation methods, the collection of building thermal parameters requires a combination of "extraction from design drawings + on-site measurement and calibration": first, the design insulation coefficients of walls, roofs, and windows are obtained from the building construction drawings (e.g., the design K value for walls is 0.8 W / (㎡·K)); then, a heat flux meter is used to measure the 24-hour heat flux density at different locations on the corresponding building components (e.g., two measuring points are selected for each of the four orientations of the wall: east, west, south, and north). The heat flux density is then calculated using the formula K... 实测 =q / ΔT (where q is the measured heat flux density and ΔT is the indoor-outdoor temperature difference) to calculate the measured K value. Finally, take "design value × 0.9 + measured value × 0.1" as the calibration value for model input. Equipment performance parameters need to be determined through "manufacturer data + on-site load testing": obtain the rated parameters from the equipment manual, and then monitor the actual power of the equipment in different operating modes in an indoor closed environment using a power meter. Combine the temperature change rate to correct the rated parameters (e.g., if the actual cooling capacity of the air conditioner at 25℃ is 2800W, then the cooling capacity of this setting in the model should be input as 2800W). The current environmental parameters are transmitted to the digital twin model in real time through a wireless Mesh network. The transmission frequency is consistent with the S1 data acquisition frequency (e.g., updated once every 2 minutes) to avoid simulation deviation caused by parameter lag.

[0072] It should be noted that the user's presence status must be used as the "dynamic constraint" input for the model. If the user's presence status is "no one", the model will automatically filter out high-energy-consuming equipment status combinations such as "fan high speed" and "air conditioner heating 28℃" to reduce the generation of invalid candidate strategies.

[0073] S202. Based on the virtual environment, multiple sets of device state combinations are generated through a digital twin model to form candidate strategies for environmental regulation.

[0074] Among them, the equipment status combination refers to the arrangement and combination of the operating status of environmental control equipment such as doors and windows, air conditioners, fresh air systems, and fans. Each combination corresponds to one candidate environmental control strategy. The status of doors and windows includes three types: "fully closed", "half open (opening angle 45° / opening area is half)" and "fully open (opening angle 90° / opening area is full)". The status of air conditioners includes three categories and eight types: "off", "cooling (temperature range 22-28℃, one level in 1℃ increments)" and "air supply (low, medium, and high fan speeds)". The status of fresh air systems includes "off", "low air volume (100m³ / h)" and "low air volume (100m³ / h)". 3 / h)""Medium Stroke Volume (200m 3 / h)" "High air volume (300m 3 The fan states include "off", "low speed", "medium speed" and "high speed"; the digital twin model uses the "constraint screening method" to select effective candidate strategies from all theoretical combinations, excluding combinations that have logical contradictions or high energy consumption and low efficiency.

[0075] In some implementations, the generation of candidate strategies requires setting three levels of constraints: The first layer is "environmental adaptation constraints," which eliminate conflicting combinations based on outdoor environmental parameters. For example, if the outdoor temperature is more than 3°C higher than the indoor temperature (e.g., indoor 27°C, outdoor 32°C), the combination of "half-open / fully-open doors and windows + air conditioning" is excluded to avoid heat loss leading to a surge in air conditioning energy consumption. Outdoor PM2.5 concentration must also be above 75 μg / m³. 3 When air quality exceeds the standard, avoid the combination of "doors and windows half open / full open + fresh air closed" to prevent polluted outdoor air from entering; The second layer is "energy consumption threshold constraint", which sets the maximum allowable energy consumption for a single strategy (e.g., the total energy consumption in the next hour shall not exceed 1.5kWh). The theoretical energy consumption is calculated through the power parameters of the equipment, and combinations that exceed the energy consumption limit are excluded (e.g., "all doors and windows closed + air conditioning at 24℃ + high air volume of fresh air" theoretically consumes 1.8kWh in 1 hour, and is excluded if it exceeds the threshold). The third layer is the "basic comfort constraint". The digital twin model quickly predicts the "minimum suitability score" of the combination and excludes combinations with a score of less than 50 (out of 100). For example, "all doors and windows open + air conditioner off + fresh air off" will predict a suitability score of 42 when the outdoor temperature is 32°C and will be directly excluded. The final number of candidate strategies is controlled at 8-12 groups, which ensures strategy diversity while avoiding excessive computational load in subsequent predictions.

[0076] For example, a virtual environment for an open office area built based on S201 (indoor temperature 27℃, outdoor temperature 32℃, PM2.5 30μg / m³) 3 With 20 users, the theoretical equipment configuration combinations total 3 doors / windows × 8 air conditioners × 4 fresh air systems × 4 sets of fans = 384 combinations. After a three-layer constraint screening: the first layer eliminated 186 combinations such as "doors / windows half-open / fully open + air conditioner cooling" and "doors / windows fully open + fresh air system closed"; the second layer eliminated 168 combinations such as "doors / windows fully closed + air conditioner cooling 24℃ + fresh air system high airflow" and "doors / windows fully closed + air conditioner cooling 24℃ + fan high speed"; the third layer eliminated 18 combinations such as "doors / windows fully open + air conditioner closed + fresh air system low airflow" and "doors / windows half-open + air conditioner closed + fresh air system closed"; finally, 12 candidate strategies were retained, including Strategy 1 (doors / windows fully closed + air conditioner cooling 25℃ + fresh air system medium airflow + fan closed), Strategy 2 (doors / windows fully closed + air conditioner cooling 26℃ + fresh air system high airflow + fan low speed), and Strategy 3 (doors / windows half-open + air conditioner supply airflow high airflow + fresh air system high airflow + fan medium speed), etc.

[0077] S203. For each candidate strategy, simulate the future environmental parameter sequence in the digital twin model, and input it into the environmental comfort model to output the suitability score curve.

[0078] Among them, the future environmental parameter sequence refers to the indoor temperature, humidity, CO2 concentration, PM2.5 concentration, and airflow velocity data simulated by the digital twin model at each time step (e.g., every 5 minutes) within a future period (e.g., the next 2 hours) after adopting a certain candidate strategy. The simulation process requires solving thermodynamic equations (to calculate temperature changes) and fluid dynamics equations (to calculate airflow velocity, CO2, and PM2.5 diffusion) to ensure that the parameter changes conform to actual physical laws. The suitability score curve is a curve plotted by substituting the environmental parameter sequence obtained at each time step of the simulation into the environmental comfort model in S1, calculating the corresponding suitability score (ECI), and then drawing the change curve of the "time-ECI" data to intuitively reflect the comfort improvement effect of the candidate strategy.

[0079] In some implementations, the thermodynamic equations can be solved using the finite difference method. Taking indoor temperature simulation as an example, the indoor space is divided into 300 grids (10m×10m×3m) of 1m×1m×1m. The temperature change equation for each grid is as follows: Among them, T i,j,k (t) represents the temperature of the grid (i,j,k) at time t, and λ r ρ is the thermal conductivity of air. r For air density, c rΔt is the specific heat capacity of air, Δx is the time step, Δx is the grid side length, Q is the heat / cooling output of the equipment, and V is the specific heat capacity of air. grid For the mesh volume; The fluid dynamics equations can be solved using a simplified k-ε model to determine airflow velocity and pollutant diffusion. The focus is on calculating airflow distribution at air conditioning vents, fresh air inlets, and gaps in doors and windows, as well as CO2 (generated by user respiration, estimated at 0.018 m³ / hour per person). 3 The calculation involves PM2.5 diffusion concentration; the time span of the suitability score curve is set to the next 2 hours, with a time step of 5 minutes, and a total of 24 data points. The ECI calculation for each data point needs to fully incorporate the instantaneous thermal sensation value, the body steady-state deviation value, and the air quality score formula to ensure the accuracy of the score.

[0080] For example, candidate strategy 1 (all doors and windows closed + air conditioning at 25℃ + fresh air volume of 200m³) 3 Taking ( / h+fan off) as an example: The digital twin model simulates the next 2 hours in 5-minute time steps, obtaining a partial sequence of environmental parameters: Minute 5 (indoor temperature 26.5℃, CO2 concentration 530ppm), Minute 10 (26.1℃, 510ppm), Minute 15 (25.8℃, 490ppm), Minute 20 (25.5℃, 470ppm), Minute 25 (25.2℃, 450ppm)... Minute 120 (25.0℃, 420ppm) m); Substitute each set of parameters into the environmental comfort model to calculate ECI: ECI = 62 points at the 5th minute, 65 points at the 10th minute, 68 points at the 15th minute, 71 points at the 20th minute, 73 points at the 25th minute... 75 points at the 120th minute; finally, a suitability score curve is formed, with the inflection point of the curve being "ECI exceeding 60 points for the first time at the 5th minute" and "ECI reaching its peak of 76 points at the 60th minute", which intuitively reflects that this strategy can improve comfort to a qualified level within 5 minutes and reach the optimal comfort level within 1 hour.

[0081] Based on the above technical solutions, S201 constructs a digital twin model consistent with the actual scenario through parameter calibration, providing a reliable foundation for subsequent simulations; S202 filters out invalid strategies through multi-layer constraints, taking into account both diversity and practicality; S203 quantifies the future effect of each strategy through physical equation simulation and comfort model calculation, providing accurate "strategy-effect" correspondence data for S3 to construct the optimization objective function and solve the optimal strategy, ensuring that the optimal strategy solved subsequently can not only match the user's comfort needs but also meet energy-saving requirements.

[0082] In one possible implementation of the embodiments of this application, combined with Figure 2 ,like Figure 3 As shown, the above S3 can be implemented through the following S301, S302 and S303, which are explained in detail below: S301. Clearly define the components and parameter values ​​of the objective function, and construct a mathematical expression that meets the dual objectives of "comfort and energy saving". The objective function for optimization is calculated as "minimizing the weighted sum of comfort deviation and energy consumption": The constituent elements are defined as follows: ECI desired ECI is the target suitability score, i.e., the desired suitability score benchmark. predicted (τ) represents the prediction suitability score of a candidate strategy at time τ, (ECIdesired-ECIpredicted(τ)). 2 The objective function is used to characterize the comfort deviation; the smaller the deviation, the closer the comfort is to the expectation. P(τ) is the total power of the system at time τ, which is the sum of the power of all operating environmental control equipment. α is the energy-saving weighting coefficient, used to balance the priority of comfort and energy consumption. T is the optimization time span, which is the time for evaluating the effect after the strategy is implemented. It can be consistent with the prediction time of the suitability score curve in S203. The integral term represents the cumulative sum of comfort deviation and energy consumption over the entire optimization time span, and the objective function needs to minimize this sum to achieve "optimal synergy between comfort and energy saving".

[0083] In some implementations, the specific methods for determining each parameter need to be designed in conjunction with the characteristics of the scenario and user preferences: 1. Target Suitability Index (ECI) desired The approach, combining scenario categorization and user research, first divides spaces into three types based on function: office, home, and commercial (e.g., shopping mall). Then, a questionnaire survey is conducted among target users for each scenario to collect feedback on their ratings of "acceptable minimum comfort level" and "ideal comfort level." The "85% of the ideal comfort level rating" is taken as the ECI (Employment Capacity Index). desired For example, in an office setting, if user feedback indicates an ideal comfort score of 85 out of 100, then the ECI (Easy Comfort Index) is... desired =85×85%=72.25 points.

[0084] 2. Energy-saving weight coefficient α: Determined through "user preference score mapping". A 7-level preference scale of "comfort priority - energy saving priority" is designed (level 1 is extreme comfort priority, level 7 is extreme energy saving priority). Users select their own preference level, and then α is calculated by the linear mapping formula α=0.1×(preference level-1)+0.1. For example, if the user selects "level 3 (slight energy saving preference)", then α=0.1×(3-1)+0.1=0.3. If the user selects "level 5 (moderate energy saving preference)", then α=0.5, ensuring that the value of α is stable in the range of 0.1-0.7.

[0085] 3. Total system power P(τ): Determined by “equipment power ledger + real-time acquisition”. First, establish a power ledger for all environmental control equipment, such as 1100W for air conditioning at 25℃, 150W for fresh air at medium air volume, and 50W for door and window drive motors. Then, at time τ, based on the operating status of the equipment in the candidate strategy, retrieve the corresponding power values ​​from the ledger and sum them to obtain P(τ).

[0086] For example, taking a 100㎡ open office area as an example: Through research, ECI was determined. desired =72.25 minutes, α=0.3, T=1 hour (3600 seconds), P max =3000W; The P(τ) of a candidate strategy (all doors and windows closed + air conditioning cooling to 25℃ + fresh air volume) is calculated as follows: air conditioning power 1100W + fresh air power 150W = 1250W (≤3000W, satisfying safety constraints); substituting into the objective function, the integral term is obtained as follows: The effectiveness of the strategy needs to be determined by finding the minimum value of this integral.

[0087] S302. Select an appropriate optimization algorithm to solve the objective function, and combine edge computing nodes to improve the solution efficiency and regional specificity. The optimization algorithm is used to find the strategy that minimizes the integral value of the objective function (i.e., the optimal adjustment strategy) from the candidate strategy set generated by S202. Since the central processing module contains several edge computing units, and each edge computing node is deployed in a region (such as area A and area B of the office area), the solution process can adopt a "partitioned parallel solution" mode—each edge computing node only processes the candidate strategies of its own region, ensuring that the strategy matches the characteristics of the regional environment.

[0088] In some implementations, the selection of optimization algorithms and parameter settings need to be combined with the number of candidate strategies and computational resource design: 1. Algorithm selection: When the number of candidate strategies is ≤15, the "enumeration method + precision verification" is used to solve the problem; when the number of candidate strategies is >15, the "Particle Swarm Optimization (PSO)" algorithm is used to solve the problem.

[0089] 2. Parallel solution logic for each region: Each edge computing node obtains the candidate strategies and environmental parameters of its region through the wireless Mesh network, completes the solution independently, and uploads the optimal strategy to the central processing module for aggregation. If there is a need for device linkage between strategies in different regions (such as the sharing of the fresh air main pipe between region A and region B), the central processing module will coordinate the strategies, such as prioritizing the fresh air needs of regions with excessive PM2.5.

[0090] For example, if 12 candidate strategies are generated in open office area A (number ≤ 15, using enumeration), with a time step of 5 minutes (72 time points): 1. Calculate the integral value of the objective function for each strategy group. Taking Strategy 1 (all doors and windows closed + air conditioning at 25℃ + medium air volume in fresh air) as an example, calculate using the trapezoidal integral method: =128600 (points) 2 • seconds + W • seconds); 2. The integral value of Strategy 2 (all doors and windows closed + air conditioner at 26℃ + high air volume for fresh air) is 135200, and that of Strategy 3 (half-open doors and windows + high air volume for fresh air + medium fan speed) is 156800. 3. Comparing the integral values ​​of the 12 strategies, strategy 1 has the smallest integral value (128600), and is tentatively designated as the optimal strategy for area A. The edge nodes of area A upload the results to the central processing module. After coordination to ensure there are no regional conflicts, strategy 1 is confirmed as the final optimal strategy.

[0091] S303. Generate equipment control commands and execute the optimal adjustment strategy, and collect environmental parameters after adjustment to verify the effect.

[0092] The equipment control commands translate the optimal adjustment strategy into recognizable operating signals for each environmental control device (such as the "fully closed" signal for door and window drive motors, the "cooling to 25°C" signal for air conditioners, and the "medium airflow" signal for fresh air systems). These signals are then sent to each device via a wireless Mesh network by the environmental control execution module. Post-adjustment effect verification refers to the real-time collection of indoor environmental parameters by the environmental information acquisition module after strategy execution, recalculating the suitability score, and determining whether the ECI (Economic Conditions Index) has been achieved. desired This forms an "execution-verification" closed loop.

[0093] In some implementations, the instruction generation and execution process needs to emphasize priority and fault tolerance. The specific steps are as follows: 1. Command Priority Ranking: Command priorities are set according to the urgency of environmental parameters, from highest to lowest: PM2.5 concentration exceeding the standard (>75μg / m³). 3 → CO2 concentration exceeds the standard (>1000ppm) → Temperature deviates from T setpoint >3℃→humidity deviates from the ideal range (40%-60%)>other parameters; for example, the optimal strategy includes both "high fresh air volume (to solve CO2 exceeding the standard)" and "air conditioning 25℃ (to solve temperature being 2℃ too high)" commands. First, send the high fresh air volume command, and after the CO2 concentration drops to ≤800ppm, send the air conditioning command to avoid excessive instantaneous power caused by the simultaneous start of equipment.

[0094] 2. Command Fault Tolerance Mechanism: After each command is sent, a "10-second confirmation timeout" is set. If the device does not respond with an "execution successful" signal within 10 seconds, the edge computing node resends the command (up to 3 times). If all 3 attempts fail, it automatically switches to the "backup strategy" (e.g., when the air conditioner fails, it switches to "half-open doors and windows + high fresh air volume + high fan speed"). The backup strategy needs to be pre-stored in the edge computing node and is a combination strategy of the second smallest objective function value.

[0095] 3. Effectiveness Verification Process: After the strategy is implemented, environmental parameters are collected according to the rhythm of "5-minute initial check - 30-minute re-check - 1-hour final check": During the initial check, if the suitability score is ≥ ECI... desired A score of 90% or higher (e.g., 90% of 72.25 points = 65.025 points) is considered "preliminary achievement"; a score ≥ ECId during re-examination is required. esired The standard is determined to be "basically up to standard"; the final score is ≥ECI. desired If the fluctuation is ≤2 points, it is judged as "fully compliant"; if the final inspection fails to meet the standard, S2 is triggered again to generate a new candidate strategy to avoid being in an unsuitable environment for a long time.

[0096] It should be noted that equipment control commands must be encapsulated using standardized protocols. For example, door and window drive motors should use the Modbus protocol, air conditioners should use the IR (infrared) protocol, and fresh air systems should use the MQTT protocol to ensure that different brands of equipment can recognize the commands. When verifying the effect, external interference factors (such as sudden window opening or a large influx of people) must be eliminated. If interference is detected, the verification should be paused and restarted after the interference is eliminated (e.g., after 10 minutes of stable personnel). In addition, the energy consumption-comfort ratio for each strategy execution should be recorded, which is the total energy consumption ÷ comfort improvement value during the adjustment process. This is used for the dynamic adjustment of α in the subsequent optimization objective function. If the energy consumption-comfort ratio is too high, α will be increased by 0.1 in the next adjustment to increase the energy saving weight.

[0097] Based on the above technical solutions, S301 can accurately match users' needs for comfort and energy saving by determining scenario-based parameters; S302 combines edge computing with partitioned solution, which not only improves computing efficiency but also ensures that the strategy fits the characteristics of the regional environment; S303's priority instructions and fault tolerance mechanism ensure the stability of strategy execution, balance comfort and energy saving, and achieve the core technical goal of intelligent control of door and window opening and closing and environmental linkage.

[0098] This application embodiment can divide the indoor energy-saving control device into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or software functional units. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0099] When using integrated units, Figure 5 A possible structural schematic diagram of the indoor energy-saving control device (referred to as indoor energy-saving control device 50) involved in the above embodiments is shown. The indoor energy-saving control device 50 includes a processing unit 501 and a communication unit 502, and may also include a storage unit 503. Figure 5 The structural diagram shown can be used to illustrate the structure of the indoor energy-saving control device involved in the above embodiments.

[0100] when Figure 5 The schematic diagram shown illustrates the structure of the indoor energy-saving control device involved in the above embodiments. The processing unit 501 is used to control and manage the operation of the indoor energy-saving control device, the communication unit 502 is used for the indoor energy-saving control device to communicate with other devices, and the storage unit 503 is used to store the program code and data of the indoor energy-saving control device.

[0101] For example, communication unit 502 is used to receive multi-source environmental data such as indoor environmental parameters, outdoor environmental parameters, and user presence status collected by the environmental information acquisition module, and is also used to send the optimal adjustment strategy command generated by processing unit 501 to the environmental adjustment execution module; processing unit 501 is used to output the current suitability score through the environmental comfort model based on the multi-source environmental data received by communication unit 502. When the suitability score is lower than a preset threshold, it triggers the digital twin model to generate multiple environmental adjustment candidate strategies and predicts the suitability score curve corresponding to each candidate strategy. At the same time, it constructs an optimization objective function to maximize the suitability score curve and satisfy energy consumption constraints, and solves the function to obtain the optimal adjustment strategy.

[0102] In one possible implementation, the processing unit 501 is further configured to correct the initial comfort score obtained through the environmental comfort model based on the user's historical manual adjustment data, so as to obtain a final suitability score that is more in line with the user's true comfort preferences and improve the accuracy of comfort judgment.

[0103] In one possible implementation, the communication unit 502 is also used to build a wireless mesh network via the Zigbee or Thread protocol, establishing a point-to-point communication link between the indoor energy-saving control device and the environmental information acquisition module and environmental regulation execution module of the area, ensuring low latency and stability of data transmission; the processing unit 501 is also used as an edge computing unit to process multi-source environmental data of the area independently, generate the optimal regulation strategy specific to the area, avoid response lag caused by centralized data processing, and achieve targeted adaptation of regulation strategies for different areas.

[0104] The processing unit 501 can be a processor or a controller, and the communication unit 502 can be a communication interface, transceiver, transceiver circuit, transceiver device, etc. The term "communication interface" is a general term and may include one or more interfaces. The storage unit 503 can be a memory. When the indoor energy-saving control device 50 is a chip, the processing unit 501 can be a processor or a controller, and the communication unit 502 can be an input interface and / or an output interface, pins, or circuits, etc. The storage unit 503 can be a storage unit within the chip (e.g., a register, cache, etc.) or a storage unit located outside the chip (e.g., read-only memory (ROM), random access memory (RAM, etc.).

[0105] The communication unit can also be called a transceiver unit. The antenna and control circuit with transceiver functions in the indoor energy-saving control device 50 can be considered as the communication unit 502 of the indoor energy-saving control device 50, and the processor with processing functions can be considered as the processing unit 501 of the indoor energy-saving control device 50. Optionally, the device in the communication unit 502 used to implement the receiving function can be considered as a communication unit, which is used to execute the receiving steps in the embodiments of this application. The communication unit can be a receiver, a receiver circuit, etc. The device in the communication unit 502 used to implement the transmitting function can be considered as a transmitting unit, which is used to execute the transmitting steps in the embodiments of this application. The transmitting unit can be a transmitter, a transmitter, a transmitting circuit, etc.

[0106] Figure 5If the integrated units in the process are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. Storage media for storing computer software products include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0107] Figure 5 The units in the process can also be called modules; for example, a processing unit can be called a processing module.

[0108] This application also provides a hardware structure diagram of an indoor energy-saving control device (denoted as indoor energy-saving control device 60), see [link to diagram]. Figure 6 The indoor energy-saving control device 60 includes a processor 601, and optionally, a memory 602 connected to the processor 601.

[0109] In the first possible implementation, see Figure 6 The indoor energy-saving control device 60 also includes a transceiver 603. The processor 601, memory 602, and transceiver 603 are connected via a bus. The transceiver 603 is used to communicate with other devices or communication networks. Optionally, the transceiver 603 may include a transmitter and a receiver. The device in the transceiver 603 that implements the receiving function can be considered as a receiver, which is used to perform the receiving steps in the embodiments of this application. The device in the transceiver 603 that implements the transmitting function can be considered as a transmitter, which is used to perform the transmitting steps in the embodiments of this application.

[0110] Based on the first possible implementation method Figure 6 The structural diagram shown can be used to illustrate the structure of the indoor energy-saving control device involved in the above embodiments.

[0111] in, Figure 6 The diagram can also illustrate the system chip in the indoor energy-saving control device. In this case, the actions performed by the aforementioned indoor energy-saving control device can be implemented by this system chip; the specific actions performed can be found above and will not be repeated here.

[0112] In implementation, each step of the method provided in this embodiment can be completed by integrated logic circuits in the processor or by instructions in software form. The steps of the method disclosed in the embodiments of this application can be directly manifested as being executed by a hardware processor, or being executed by a combination of hardware and software modules in the processor.

[0113] The processor in this application may include, but is not limited to, at least one of the following: a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a microcontroller unit (MCU), or an artificial intelligence processor, etc., and other computing devices that run software. Each computing device may include one or more cores for executing software instructions to perform calculations or processing. The processor may be a standalone semiconductor chip or integrated with other circuits into a single semiconductor chip. For example, it may form a System-on-a-Chip (SoC) with other circuits (such as encoding / decoding circuits, hardware acceleration circuits, or various bus and interface circuits), or it may be integrated as a built-in processor within an ASIC. The ASIC with the integrated processor may be packaged separately or together with other circuits. In addition to the cores for executing software instructions to perform calculations or processing, the processor may further include necessary hardware accelerators, such as field-programmable gate arrays (FPGAs), programmable logic devices (PLDs), or logic circuits that implement dedicated logic operations.

[0114] The memory in the embodiments of this application may include at least one of the following types: read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions; random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions; or electrically erasable programmable-only memory (EEPROM). In some scenarios, the memory may also be a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures that can be accessed by a computer, but is not limited thereto.

[0115] This application also provides a computer-readable storage medium including instructions that, when run on a computer, cause the computer to perform any of the methods described above.

[0116] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform any of the methods described above.

[0117] This application also provides a chip including a processor and an interface circuit. The interface circuit is coupled to the processor. The processor is used to run computer programs or instructions to implement the above-described method. The interface circuit is used to communicate with other modules outside the chip.

[0118] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks (SSDs)).

[0119] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0120] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and modifications.

Claims

1. An energy-saving control system that links the opening and closing status of doors and windows with the indoor and outdoor environment, characterized in that, include: The environmental information acquisition module is used to collect indoor environmental parameters, outdoor environmental parameters, and user presence status to obtain multi-source environmental data. The central processing module is used to output the current suitability score based on the multi-source environmental data through the environmental comfort model. When the suitability score is lower than a preset threshold, it triggers the digital twin model to generate multiple environmental adjustment candidate strategies and predicts the suitability score curve corresponding to each candidate strategy. as well as, Construct an optimization objective function that maximizes the suitability score curve and satisfies energy consumption constraints, and solve the optimization objective function to obtain the optimal regulation strategy; The environmental regulation execution module is used to perform regulation operations on the indoor environment according to the optimal regulation strategy; The formula for calculating the suitability score is as follows: Where ECI represents the suitability score, η represents the adaptive calibration coefficient, and ΔU represents the historical smoothed value of the user's manual adjustment. This represents the initial comfort score; The formula for calculating the initial comfort score is: Where γ represents the steady-state weighting coefficient; This is the instantaneous thermal sensation value, used to characterize the instantaneous hot and cold sensations directly perceived by the skin. The calculation formula is: , Indicates the user's body surface temperature. This represents the ideal body surface temperature. This represents the temperature sensitivity coefficient, and β represents the weight of the airflow effect. Indicates airflow velocity. This represents the ideal airflow velocity. Indicates ambient air temperature; This is the steady-state deviation value within the body, used to characterize the cumulative thermal or cold stress in the human body's core temperature caused by prolonged exposure to an environment deviating from the desired temperature. The calculation formula is: α represents the influence coefficient of temperature difference. The preset target temperature for air conditioning is represented by t, the current time is represented by τ, the integral variable is represented by λ, and the time decay constant is represented by λ. An air quality score is used to characterize the impact of air cleanliness on breathing comfort. The calculation formula is: , Indicates CO2 concentration. Indicates the CO2 concentration threshold. Indicates PM2.5 concentration. This indicates the PM2.5 concentration threshold. , This represents the steepness parameter, used to control the rate of change of the sigmoid function near the concentration threshold; The optimization objective function satisfies: Among them, ECI desired ECI represents the target suitability score. predicted (τ) represents the fitness score predicted at time τ, P(τ) represents the total system power at time τ, and α represents the energy saving weight coefficient.

2. The energy-saving control system for linking the opening and closing status of doors and windows with the indoor and outdoor environment as described in claim 1, characterized in that, The process of constructing the environmental comfort model includes: Instantaneous thermal sensation values ​​are calculated based on the user's body surface temperature, ambient air temperature, and airflow speed; these instantaneous thermal sensation values ​​are used to characterize the instantaneous hot and cold sensations directly perceived by the skin. Based on historical ambient temperature sequences and user-defined temperatures, the steady-state deviation value in the body is calculated through convolution integrals. The steady-state deviation value in the body is used to characterize the cumulative thermal or cold stress of the human body core temperature caused by long-term exposure to an environment deviating from the desired temperature. An air quality score is calculated based on indoor CO2 and PM2.5 concentrations; this air quality score is used to characterize the impact of air cleanliness on breathing comfort. The instantaneous thermal sensation value, the body steady-state deviation value, and the air quality score are nonlinearly fused to obtain an initial comfort score; The initial comfort score is corrected based on historical manual adjustment data to obtain the final suitability score.

3. The energy-saving control system for linking the opening and closing status of doors and windows with the indoor and outdoor environment as described in claim 1, characterized in that, The method for determining the adaptive calibration coefficient includes: After obtaining the user's manual adjustment data each time, the absolute difference between the predicted suitability score and the actual suitability score is calculated, and the average value of the absolute difference over a preset time period is calculated to obtain the mean absolute error. The mean absolute error is mapped to an adaptive calibration coefficient; the mapping relationship uses a negative correlation function to ensure that the smaller the mean absolute error, the larger the adaptive calibration coefficient, and the larger the mean absolute error, the smaller the adaptive calibration coefficient. The mapping relationship is expressed as follows: η max is the upper limit of the calibration coefficient, k is the attenuation coefficient, and MAE is the mean absolute error.

4. The energy-saving control system for linking the opening and closing status of doors and windows with the indoor and outdoor environment according to claim 2, characterized in that, The methods for obtaining the historical smoothing values ​​include: Monitor and record the user's manual adjustment amount u i and adjusting timestamp t i ; A weighted moving average algorithm is used to smooth historical manual adjustments, yielding a smoothed historical value. The calculation formula is as follows: ;in, t represents the weighting coefficient. current Let τ be the current time, and τ be the time decay constant.

5. The energy-saving control system for linking the opening and closing status of doors and windows with the indoor and outdoor environment according to claim 1, characterized in that, The triggering digital twin model generates multiple environmental regulation strategies, including: Different combinations of device states are generated using a digital twin model to obtain multiple candidate strategies; the combinations of device states include door and window opening / closing status, air conditioner on / off mode, air conditioner on / off temperature, fresh air system on / off mode, fresh air system on / off airflow, fan on / off mode, and fan on / off speed.

6. The energy-saving control system for linking the opening and closing status of doors and windows with the indoor and outdoor environment according to claim 1, characterized in that, The prediction of the suitability score curves for each candidate strategy includes: For each candidate strategy, based on building thermal parameters, current indoor and outdoor environmental parameters, and equipment performance parameters, thermodynamic and fluid dynamic equations are solved in a digital twin environment to simulate the environmental parameter sequence of indoor temperature, humidity, CO2 concentration, and PM2.5 concentration over a future period. The simulated environmental parameter sequence is used as input to the environmental comfort model, and the predicted suitability score curve for each candidate strategy in the future is output.

7. The energy-saving control system for linking the opening and closing status of doors and windows with the indoor and outdoor environment according to claim 1, characterized in that, The central processing module includes several edge computing units. Each edge computing node is deployed in a region to process multi-source environmental data in a single region and output the optimal adjustment strategy for that single region. The environmental information acquisition module, the environmental regulation execution module, and each edge computing unit are connected via a wireless mesh network; the wireless mesh network is used to establish point-to-point communication links between the edge computing node and the environmental information acquisition module and the environmental regulation execution module of its respective area.

Images