Adaptive Dynamic Control Method, System and Medium for Building Sunshading

Abstract

The present invention relates to the field of building technology, and in particular to a method, system and medium for adaptive dynamic control of building sunshade. The method provided by the present invention establishes a sunshade adaptive control model by adopting machine learning, and combines simulation optimization with machine learning models to achieve adaptive dynamic adjustment of various types of dynamic sunshade equipment, thereby achieving near-optimal energy saving and lighting adjustment effects. The method provided by the present invention also realizes automatic and continuous sunshade state optimization by setting a memory, combining building performance simulation with computer programming, and improving the accuracy of prediction and versatility in different usage scenarios. Compared with other methods, the method provided by the present invention has better energy-saving effects and lower comprehensive energy consumption levels.

Description

Technical Field

[0001] The present invention relates to the field of building technology, and in particular to a building sunshade adaptive dynamic control method, system and medium. Background Art

[0002] With the development of cities, people's requirements for the building environment are becoming increasingly higher, and the accompanying building energy consumption problem is becoming more and more serious. To address this problem, dynamic shading systems are used instead of traditional fixed shading solutions. Because their variable mechanisms have higher adaptability to the environment, they are expected to further reduce building energy consumption and improve users' visual comfort. However, the performance of dynamic shading systems is largely affected by the control strategy. Although the control methods for dynamic shading in domestic buildings currently vary, none of them have been able to effectively balance the relationship between building energy consumption and indoor lighting, resulting in the inability to fully utilize the role of dynamic shading in building energy conservation and regulating the indoor light environment. Summary of the Invention

[0003] In view of this, the first purpose of the present invention is to provide a method for adaptive dynamic control of building shading, which realizes adaptive dynamic adjustment of various dynamic shading equipment through simulation optimization and development of machine learning models, so as to achieve near-optimal energy saving and lighting adjustment effects.

[0004] Based on the same inventive concept, the second object of the present invention is to provide a building sunshade adaptive dynamic control system.

[0005] Based on the same inventive concept, the third object of the present invention is to provide a storage medium.

[0006] The first object of the present invention can be achieved by the following technical solutions:

[0007] A building shading adaptive dynamic control method comprises the following steps:

[0008] Establishing architectural simulation models;

[0009] Based on the usage scenarios and environmental parameters, the building performance simulation model is used to set different shading conditions, calculate the building performance simulation results, and optimize the building performance simulation results according to the optimization goal to obtain the optimal shading status schedule throughout the year;

[0010] Establish a building shading adaptive control model and use the optimal shading state schedule throughout the year to train the building shading adaptive control model;

[0011] Sensors are used to dynamically collect environmental parameters. Based on the environmental parameters, the building shading adaptive control model is used to obtain the optimal shading state conditions to achieve adaptive dynamic control of building shading.

[0012] Furthermore, different sunshade working conditions are set, including: setting working parameters of the sunshade device according to the control method of the sunshade device, and generating a sunshade working condition parameter group using an equal interval setting method.

[0013] Furthermore, according to the usage scenario and environmental parameters, the building performance simulation model is used to set different shading state conditions, calculate the building performance simulation results, and optimize the building performance simulation results according to the optimization goal to obtain the optimal shading state schedule throughout the year, including the following steps:

[0014] Set optimization goals;

[0015] Input usage scenarios and environmental parameter groups, where the environmental parameter groups are sets of multiple environmental meteorological data with a year as the cycle and hourly as the time interval;

[0016] For each piece of environmental meteorological data, different shading conditions are set, and the building performance simulation results corresponding to the shading condition parameter group are simulated and calculated;

[0017] According to the set optimization goal, the shading state working condition parameters corresponding to the optimal building performance simulation result in the environmental meteorological data are selected and recorded as the optimization result corresponding to the environmental meteorological data;

[0018] The optimization results of all environmental meteorological data in the environmental parameter group are traversed and calculated to obtain the optimal shading status schedule throughout the year.

[0019] Furthermore, the optimization goal is: while satisfying the glare avoidance condition, the sunshade state operating condition parameter group with lower building energy consumption is the more optimal value.

[0020] Furthermore, the building shading adaptive control model is trained using the optimal shading state schedule throughout the year, including the following steps:

[0021] Select a machine learning classification algorithm to establish an adaptive building shading control model;

[0022] The optimal shading state parameters are converted into classification labels and set as the output of the model. The environmental meteorological data and usage scenarios are set as the feature inputs of the model. The building shading adaptive control model is trained using the optimal shading state year-round schedule.

[0023] The building sun shading adaptive control model is adjusted and pruned to obtain the trained building sun shading adaptive control model.

[0024] Furthermore, in the step of selecting a machine learning classification algorithm and establishing a building shading adaptive control model, the selected machine learning classification algorithm is a random forest algorithm or a decision tree algorithm.

[0025] Furthermore, the above-mentioned building shading adaptive dynamic control method further includes the following steps:

[0026] A memory is used to record environmental parameters and user usage habits collected by sensors, and the optimal shading state annual schedule and the building shading adaptive control model are updated based on the environmental parameters and user usage habits stored in the memory.

[0027] The second object of the present invention can be achieved by the following technical solutions:

[0028] An adaptive dynamic control system for building sunshade, comprising:

[0029] Simulation model module, used to establish building simulation model;

[0030] The simulation optimization module is used to set different shading conditions based on usage scenarios and environmental parameters using the building performance simulation model, calculate the building performance simulation results, and optimize the building performance simulation results according to the optimization objectives to obtain the optimal shading status schedule throughout the year;

[0031] The building shading adaptive control model module is used to establish a building shading adaptive control model, and use the optimal shading state full-year schedule to train the building shading adaptive control model, and use the building shading adaptive control model to obtain the optimal shading state working condition based on the collected environmental parameters;

[0032] Sensor module, used to dynamically collect environmental parameters;

[0033] The sunshade equipment is used to realize adaptive dynamic control of building sunshade according to the optimal sunshade state working condition output by the building sunshade adaptive control model module.

[0034] Furthermore, the building shading adaptive dynamic control system also includes a memory module for recording environmental parameters and user usage habits collected by sensors; the environmental parameters and user usage habits stored in the memory are used to update the optimal shading state throughout the year schedule and the building shading adaptive control model.

[0035] The third object of the present invention can be achieved by the following technical solutions:

[0036] A storage medium stores a program, which, when executed by a processor, implements the building sunshade adaptive dynamic control method as claimed in the claim.

[0037] The present invention has the following beneficial effects compared to the prior art:

[0038] (1) The present invention greatly improves the effect of dynamic shading equipment in energy saving and adjusting indoor light environment by combining simulation optimization with machine learning, achieves flexible and scientific response to sensor parameters, and can adapt to changes in indoor and outdoor environments and changes in user usage habits. Compared with traditional shading control methods based on a fixed value, the method of the present invention is more targeted in control objectives and can be closer to achieving the optimization goals set by users.

[0039] (2) The present invention achieves automatic and continuous optimization of shading conditions by providing a memory and combining building performance simulation with computer programming, thus reducing the time and effort required for manual operation. This process implements a cyclical process of input → simulation → result reading → optimization → re-input based on the optimized result. By continuously collecting new data for simulation optimization and model training, the accuracy of predictions and the versatility of the system in different usage scenarios are improved. Furthermore, through this method and process, users do not need to possess professional knowledge in architectural science and computer science. Following the prompts, they can obtain a near-optimal adaptive shading control strategy.

[0040] (3) The present invention establishes a sunshade adaptive control model by adopting machine learning, and converts the output of the sunshade adaptive control model into classification labels, thereby improving the prediction efficiency of the model, so that the sunshade adaptive control model can achieve better classification effect when the number of samples is small, and at the same time will not cause too much burden on the performance of the controller. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a flow chart of the building sunshade adaptive dynamic control method according to Example 1 of the present invention;

[0042] Figure 2 is a schematic diagram of a building simulation model in Example 1 of the present invention;

[0043] Figure 3 is a flowchart of step S20 in the building sunshade adaptive dynamic control method of embodiment 1 of the present invention;

[0044] Figure 4 This is a flowchart of step S30 in the building sunshade adaptive dynamic control method of embodiment 1 of the present invention;

[0045] Figure 5 1. This is a schematic diagram of the input of a machine learning model in the building sunshade adaptive dynamic control method according to Example 1 of the present invention;

[0046] Figure 6 is the prediction accuracy of the decision tree and random forest classification algorithms in each direction according to Example 1 of the present invention;

[0047] Figure 7 This is a decision tree diagram of the optimal roller blind sunshade lowering position of the decision tree model of Example 1 of the present invention;

[0048] Figure 8 This is a comparison chart of the annual energy consumption performance of the building sunshade adaptive dynamic control method of Example 1 of the present invention and other methods in south-facing rooms;

[0049] Figure 9 This is a comparison chart of the annual energy consumption performance of the building sunshade adaptive dynamic control method of Example 1 of the present invention and other methods in west-facing rooms;

[0050] Figure 10 This is a comparison chart of the annual UDI (100-2000 lux) ratio in a south-facing room under the building shading adaptive dynamic control method of Example 1 of the present invention and other different shading control strategies;

[0051] Figure 11 This is a comparison chart of the annual UDI (100-2000 lux) ratio in a west-facing room under the building shading adaptive dynamic control method of Example 1 of the present invention and other different shading control strategies. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0053] Example 1:

[0054] like Figure 1 As shown, this embodiment provides a building shading adaptive dynamic control method, including the following steps:

[0055] S10, establishing a building simulation model;

[0056] like Figure 2 As shown, in this embodiment, the room parameters include architectural characteristic parameters and building thermal parameters. Architectural characteristic parameters include space dimensions and environmental occlusion, while building thermal parameters include boundary conditions, internal heat sources, and HVAC parameters. A full-scale room model was constructed using a typical office room in Guangzhou as an example. The room measures 6m wide, 4m deep, and 4m high and is located on the central floor of an office building. The room has only one exterior wall connected to the outdoors, with a centrally located window. The room's thermal parameters were set according to the General Specification for Energy Conservation and Renewable Energy Utilization in Buildings (GB55015-2021).

[0057] In this example, to better demonstrate the control model's optimization of lighting energy consumption, a stepless dimming system was used to ensure optimal lighting quality (work surface illuminance > 500 lux). When natural light is sufficient, the lighting system is turned off to conserve energy. The lighting points were set 1m and 3m from the window, and 0.75m high.

[0058] In this embodiment, the sunshade device is a roller blind sunshade device arranged outside the outer window, and its size is consistent with that of the outer window.

[0059] S20, such as Figure 3 As shown, according to the usage scenario and environmental parameters, the building performance simulation model is used to set different shading state conditions, calculate the building performance simulation results, and optimize the building performance simulation results according to the optimization goal to obtain the optimal shading state schedule throughout the year; the following steps are included:

[0060] S21. Set optimization goals;

[0061] In this embodiment, the optimization goal is set as: while satisfying the glare index DGI at 1 m away from the window < 25, the shading state operating condition parameter group with lower building energy consumption is the more optimal value.

[0062] S22. Input usage scenario and environmental parameter group;

[0063] In this embodiment, the usage scenarios include HVAC set temperature and occupancy schedule;

[0064] In this embodiment, the environmental parameter group is the meteorological data of a typical meteorological year, which is a collection of multiple environmental meteorological data with a period of one year and a time interval of one hour. Specifically, it is the China Standard Weather Data (CSWD) of Guangzhou. The meteorological data has a period of one year and a time interval of one hour, including outdoor temperature and humidity, solar radiation intensity, and work surface illumination.

[0065] S23. For each piece of environmental meteorological data, set different shading state conditions, and simulate and calculate the building performance simulation results corresponding to the shading state condition parameter group;

[0066] In this embodiment, the sunshade device is a roller blind sunshade device. Therefore, according to the control method of the sunshade device, the working parameter of the sunshade device is set as the lowering height, and the lowering height is divided into five levels at equal intervals to obtain a sunshade state working condition parameter group [0%, 25%, 50%, 75%, 100%]; among them, 0% and 100% represent unobstructed and completely obstructed working conditions, respectively.

[0067] In another embodiment of the present invention, the sunshade device is a blind, and the working parameter of the sunshade device is set to be a blind angle. The blind angle is divided into four levels at equal intervals to obtain a sunshade state working condition parameter group [0, 30, 60, 90];

[0068] S24. According to the set optimization goal, select the shading state working condition parameter corresponding to the optimal building performance simulation result in the environmental meteorological data, and record it as the optimization result corresponding to the environmental meteorological data;

[0069] In this embodiment, all shading conditions are simulated according to the environmental parameter group input in step S22, and the shading state with DGI less than 25 and minimum energy consumption in each hour is recorded as the optimization result corresponding to that hour.

[0070] S25. Traverse and calculate the optimization results of all environmental meteorological data in the environmental parameter group to obtain the optimal shading state schedule for the whole year.

[0071] In this embodiment, the China Standard Weather Data (CSWD) for Guangzhou has a total of 8760 hours of meteorological data, so steps S23-S24 are iterated 8760 times so that all environmental meteorological data have corresponding optimization results, and the optimization results are combined into an optimal sunshade status schedule for the entire year.

[0072] S30, such as Figure 4 As shown, a building shading adaptive control model is established, and the building shading adaptive control model is trained using the optimal shading state schedule throughout the year, including the following steps:

[0073] S31. Select a machine learning classification algorithm to establish a building shading adaptive control model;

[0074] In this embodiment, the random forest algorithm (RF) and the decision tree algorithm (DT) are respectively selected to establish the building shading adaptive control model, and the use of the two algorithms is based on the Sk-learn library of Python.

[0075] S32, converting the optimal shading state working condition parameters into classification labels and setting them as the output of the model, setting the environmental meteorological data and usage scenarios as the feature inputs of the model, and using the optimal shading state full-year schedule obtained in step S25 to train the building shading adaptive control model;

[0076] The feature inputs of the random forest algorithm (RF) and decision tree algorithm (DT) are as follows Figure 5 As shown;

[0077] Among them, the environmental parameters in the feature input of the random forest algorithm (RF) include: incident solar radiation intensity on the building facade (Incident solar radiation on the facade), outdoor air temperature (Outdoor temperature), set-point temperature for indoor air conditioning and cooling (Set-point temperature for cooling), daylight illuminance on the first working surface (Daylight illuminance 1), and daylight illuminance on the third working surface (Daylight illuminance 3);

[0078] The environmental parameters in the feature input of the decision tree algorithm (DT) include: incident solar radiation intensity on the building facade (Incident solar radiation on the facade), outdoor air temperature (Outdoor temperature), set-point temperature for indoor air conditioning and cooling (Set-point temperature for cooling), and daylight illuminance 2 on the second working surface (Daylight illuminance 2).

[0079] The collection points for the daylighting illuminance of the first, second, and third working surfaces are set based on their distance from the exterior windows, and are all collected using daylighting sensors. The number of daylighting sensors used by the random forest algorithm (RF) and the decision tree algorithm (DT) differs. RF uses two daylighting sensors to collect the daylighting illuminance of the first and third working surfaces, enabling more precise adjustment of the indoor lighting environment by controlling the external shading state. The decision tree algorithm (DT) uses data from a single daylighting sensor, reducing the number of sensors while still achieving similar energy savings.

[0080] It should be noted that the number and orientation of the lighting illumination data collection points in the adaptive control model established for different scenarios (for example, the orientation of the lighting illumination sensor, which defaults to horizontal illumination, but in some cases is vertical illumination) are selected and adjusted according to actual needs.

[0081] S33, adjusting and pruning the building sun shading adaptive control model to obtain a trained building sun shading adaptive control model.

[0082] In this embodiment, the prediction accuracy of the building shading adaptive control model based on the random forest algorithm (RF) and the decision tree algorithm (DT) in each direction is as follows: Figure 6 As shown in the figure, it can be seen that both building shading adaptive control models can achieve good prediction accuracy in the simulation data.

[0083] Figure 7 This is a visualized optimal roller blind lowering position decision tree diagram of the building sunshade adaptive control model established based on the decision tree algorithm (DT) of this embodiment. It can be seen that the building sunshade adaptive control model established using the method of this embodiment has good interpretability.

[0084] S40. Use sensors to dynamically collect environmental data (i.e., environmental parameters), and use a building shading adaptive control model to obtain optimal shading state conditions based on the environmental data, thereby achieving building shading adaptive dynamic control.

[0085] S50: Using a memory to record environmental data collected by sensors and user usage habits, and updating an optimal shading state annual schedule and a building shading adaptive control model based on the environmental data and user usage habits stored in the memory.

[0086] Figure 8 and Figure 9 The following are comparison graphs of the annual energy consumption performance of the building shading adaptive dynamic control method of this embodiment and other methods in west-facing rooms and south-facing rooms. It can be seen that the results for the south and west directions are not much different and show the same trend. Secondly, it can be clearly observed that the lighting energy consumption and cooling energy consumption under the Ctrl-RF and Ctrl-DT shading control obtained by this method are almost the same as the optimization results. Compared with Ctrl-Solar, Ctrl-DGI and Ctrl-Work, a lower comprehensive energy consumption level can be achieved. This shows that although there is a certain error in the prediction of the hourly shading position through the adaptive control model, its energy-saving effect is almost the same as that of the optimal shading control, and it is more energy-efficient than the general shading strategy.

[0087] Figure 10 and Figure 11 The adaptive dynamic control method for building shading of this embodiment is compared with the annual UDI (100-2000 lux) ratio under different shading control strategies in south-facing rooms and west-facing rooms. In south-facing rooms, the adaptive shading control models (Ctrl-RF and CRTL-DT) proposed by this method are basically the same as the optimization results, with a ratio of more than 70%. Compared with the benchmark room (without shading), the adaptive shading control (Ctrl-RF and CRTL-DT) proposed by this method can reduce the proportion of time >2000 lux, increase the proportion of UDI (100-2000 lux), avoid uncomfortable glare and reduce lighting needs.

[0088] In summary, this embodiment greatly improves the effect of dynamic shading equipment in energy saving and adjusting indoor light environment by combining simulation optimization with machine learning, realizes flexible and scientific response to environmental parameters collected by sensors, and can adapt to changes in indoor and outdoor environments and changes in user usage habits. Compared with traditional shading control methods based on a fixed value, the method of the present invention is more targeted in control objectives and can be closer to achieving the optimization objectives set by users; this embodiment realizes automatic and continuous shading state optimization by setting up a memory, combining building performance simulation with computer programming, reducing the time and energy invested in human control, and realizing a cyclic process of input → simulation → reading results → optimization → re-input according to the results after optimization. By continuously collecting new data for simulation optimization and model training, the accuracy of prediction and versatility in different usage scenarios are improved. In addition, through this method and process, users do not need to have professional knowledge related to architectural science and computer science, and can obtain a nearly optimal shading adaptive control strategy by following the prompts. This embodiment uses machine learning to establish a shading adaptive control model and converts the output of the shading adaptive control model into classification labels, thereby improving the prediction efficiency of the model, so that the shading adaptive control model can achieve good classification effects even when the number of samples is small, and at the same time will not impose too much burden on the performance of the controller.

[0089] Example 2:

[0090] Based on the same inventive concept as Example 1, this embodiment provides a building sunshade adaptive dynamic control system, including:

[0091] Simulation model module, used to establish building simulation model;

[0092] The simulation optimization module is used to set different shading conditions based on usage scenarios and environmental parameters using the building performance simulation model, calculate the building performance simulation results, and optimize the building performance simulation results according to the optimization objectives to obtain the optimal shading status schedule throughout the year;

[0093] The building shading adaptive control model module is used to establish a building shading adaptive control model, and use the optimal shading state full-year schedule to train the building shading adaptive control model, and use the building shading adaptive control model to obtain the optimal shading state working condition based on the collected environmental data (i.e., environmental parameters);

[0094] Sensor module, used to dynamically collect environmental data;

[0095] The sunshade equipment is used to realize adaptive dynamic control of building sunshade according to the optimal sunshade state working condition output by the building sunshade adaptive control model module.

[0096] The memory module is used to record the environmental data and user usage habits collected by sensors; the environmental data and user usage habits stored in the memory are used to update the optimal shading state throughout the year schedule and the building shading adaptive control model.

[0097] That is to say, among the above-mentioned modules of this embodiment, the simulation model module is used to implement step S10 of embodiment 1, the simulation optimization module is used to implement step S20 of embodiment 1, the building shading adaptive control model module is used to implement step S30 of embodiment 1, the sensor module and the shading device work together to implement step S40 of embodiment 1; the memory module is used to implement step S50 of embodiment 1; since steps S10-S50 have been described in detail in embodiment 1, in order to make the description of the specification concise, the detailed implementation process of the above-mentioned modules in this embodiment refers to embodiment 1 and will not be repeated.

[0098] Example 3:

[0099] This embodiment provides a storage medium storing a program. When the program is executed by a processor, the method for adaptive dynamic control of building sun shading according to embodiment 1 of the present invention is implemented, specifically including:

[0100] Establishing architectural simulation models;

[0101] Based on the usage scenarios and environmental parameters, the building performance simulation model is used to set different shading conditions, calculate the building performance simulation results, and optimize the building performance simulation results according to the optimization goal to obtain the optimal shading status schedule throughout the year;

[0102] Establish a building shading adaptive control model and use the optimal shading state schedule throughout the year to train the building shading adaptive control model;

[0103] Use sensors to dynamically collect environmental data (i.e., environmental parameters). Based on the environmental data, use the building shading adaptive control model to obtain the optimal shading state and achieve adaptive dynamic control of building shading.

[0104] A memory is used to record environmental data collected by sensors and user usage habits, and based on the environmental data and user usage habits stored in the memory, an optimal shading state annual schedule and a building shading adaptive control model are updated.

[0105] It should be noted that the computer-readable storage medium of the present embodiment may be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0106] In this embodiment, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. Furthermore, in this embodiment, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable storage medium other than a computer-readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on a computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0107] The computer readable storage medium can be written in one or more programming languages or a combination thereof to execute the computer program for performing the present embodiment, including object-oriented programming languages such as Java, Python, C++, and conventional procedural programming languages such as C or similar programming languages. The program can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect via the Internet).

[0108] Obviously, the embodiments described above are only part of the embodiments of the present invention, rather than all the embodiments. The present invention is not limited to the details of the above embodiments. Any appropriate changes or modifications made by ordinary technicians in the relevant technical field are deemed to be within the patent scope of the present invention.

Claims

1. A building shading adaptive dynamic control method, characterized in that: The following steps are involved: S10, establishing a building simulation model; S20. Using a building simulation model, different shading conditions are set according to usage scenarios and environmental parameters, and building performance simulation results are calculated. The building performance simulation results are optimized according to the optimization goal to obtain an optimal shading state schedule for the entire year. S30, establishing a building shading adaptive control model, and using the optimal shading state full-year schedule to train the building shading adaptive control model; S40, using sensors to dynamically collect environmental parameters, and using a building shading adaptive control model to obtain optimal shading state conditions based on the environmental parameters, thereby achieving building shading adaptive dynamic control; Setting different sunshade working conditions in step S20 includes: setting the working parameters of the sunshade device according to the control method of the sunshade device, and generating a sunshade working condition parameter group using an equal interval setting method; Step S20 includes the following steps: Setting an optimization goal; the optimization goal is: while meeting the glare avoidance condition, the shading state working condition parameter group with lower building energy consumption is the best value; Input usage scenarios and environmental parameter groups, where the usage scenarios include HVAC set temperatures and occupancy schedules, and the environmental parameter groups are a collection of multiple environmental meteorological data sets with a yearly cycle and hourly intervals. For each piece of environmental meteorological data, different shading conditions are set, and the building performance simulation results corresponding to the shading condition parameter group are simulated and calculated; According to the set optimization goal, the shading state parameters corresponding to the optimal building performance simulation result in the environmental meteorological data are selected and recorded as the optimization result corresponding to the environmental meteorological data; according to the input environmental parameter group, all shading state conditions are simulated, and the shading state with a DGI less than 25 and the lowest energy consumption in each hour is recorded as the optimization result corresponding to that hour; Traverse and calculate the optimization results of all environmental meteorological data in the environmental parameter group to obtain the optimal shading status schedule for the whole year; In step S30, the optimal shading state annual schedule is used to train the building shading adaptive control model, including the following steps: Select a machine learning classification algorithm to establish an adaptive building shading control model; The optimal shading state parameters are converted into classification labels and set as the output of the model. The environmental meteorological data and usage scenarios are set as the feature inputs of the model. The building shading adaptive control model is trained using the optimal shading state year-round schedule. The building sun shading adaptive control model is adjusted and pruned to obtain the trained building sun shading adaptive control model.

2. The building shading adaptive dynamic control method according to claim 1, characterized in that: In the step of selecting a machine learning classification algorithm and establishing a building shading adaptive control model, the selected machine learning classification algorithm is a random forest algorithm or a decision tree algorithm.

3. The building shading adaptive dynamic control method according to claim 1 or 2, characterized in that: The following steps are also included: S50: Using a memory to record environmental parameters and user usage habits collected by sensors, and updating an optimal shading state year-round schedule and a building shading adaptive control model based on the environmental parameters and user usage habits stored in the memory.

4. A building sunshade adaptive dynamic control system, characterized in that: The dynamic control method according to any one of claims 1 to 3 is implemented, and the dynamic control system includes: Simulation model module, used to establish building simulation model; The simulation optimization module is used to set different shading conditions based on usage scenarios and environmental parameters using a building simulation model, calculate building performance simulation results, and optimize the building performance simulation results according to the optimization objectives to obtain the optimal shading status schedule throughout the year; The building shading adaptive control model module is used to establish a building shading adaptive control model, and use the optimal shading state full-year schedule to train the building shading adaptive control model, and use the building shading adaptive control model to obtain the optimal shading state working condition based on the collected environmental parameters; Sensor module, used to dynamically collect environmental parameters; The sunshade equipment is used to realize adaptive dynamic control of building sunshade according to the optimal sunshade state working condition output by the building sunshade adaptive control model module.

5. The building sunshade adaptive dynamic control system according to claim 4, characterized in that: It also includes a memory module for recording environmental parameters and user usage habits collected by sensors; the environmental parameters and user usage habits stored in the memory are used to update the optimal shading state throughout the year schedule and the building shading adaptive control model.

6. A storage medium storing a program, characterized in that: When the program is executed by a processor, the building sunshade adaptive dynamic control method according to any one of claims 1 to 3 is implemented.

Images