CN115598976A - Building sunshade self-adaptive dynamic control method, system and medium - Google Patents
Building sunshade self-adaptive dynamic control method, system and medium Download PDFInfo
- Publication number
- CN115598976A CN115598976A CN202211187048.9A CN202211187048A CN115598976A CN 115598976 A CN115598976 A CN 115598976A CN 202211187048 A CN202211187048 A CN 202211187048A CN 115598976 A CN115598976 A CN 115598976A
- Authority
- CN
- China
- Prior art keywords
- sunshade
- building
- self
- adaptive
- optimal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention relates to the technical field of buildings, in particular to a building sunshade self-adaptive dynamic control method, a building sunshade self-adaptive dynamic control system and a building sunshade self-adaptive dynamic control medium. The method provided by the invention realizes the self-adaptive dynamic adjustment of various dynamic sun-shading devices by adopting the machine learning to establish the sun-shading self-adaptive control model and combining simulation optimization and the machine learning model, thereby achieving the effects of energy conservation and daylighting adjustment which are nearly optimal. The method provided by the invention also realizes automatic and continuous optimization of the sunshade state by arranging the memory and combining building performance simulation and computer programming, and improves the accuracy of prediction and the general applicability in different use scenes. Compared with other methods, the method provided by the invention has better energy-saving effect and lower comprehensive energy consumption level.
Description
Technical Field
The invention relates to the technical field of buildings, in particular to a building sunshade self-adaptive dynamic control method, a building sunshade self-adaptive dynamic control system and a building sunshade self-adaptive dynamic control medium.
Background
Along with the development of cities, the requirements of people on the building environment are higher and higher, and the problem of accompanying building energy consumption is more severe, for the problem, a dynamic sunshade system is adopted to replace the traditional fixed sunshade scheme, and because a variable mechanism has higher adaptability to the environment, the building energy consumption is expected to be further reduced, and the visual comfort of users is improved. However, the performance of the dynamic sunshade system is largely influenced by the control strategy. Although the control methods for implementing dynamic sunshade of domestic buildings at present are different, the relation between building energy consumption and indoor lighting cannot be balanced well, so that the functions of the dynamic sunshade on building energy conservation and indoor light environment regulation cannot be fully exerted.
Disclosure of Invention
In view of this, a first objective of the present invention is to provide a building sunshade adaptive dynamic control method, which implements adaptive dynamic adjustment on various dynamic sunshade devices through simulation optimization and development of a machine learning model, so as to achieve near-optimal energy-saving and daylighting-adjusting effects.
Based on the same inventive concept, the second purpose of the invention is to provide a building sunshade self-adaptive dynamic control system.
Based on the same inventive concept, a third object of the present invention is to provide a storage medium.
The first purpose of the invention can be achieved by the following technical scheme:
a self-adaptive dynamic control method for building sunshade comprises the following steps:
building a building simulation model;
setting different sunshade state working conditions by using a building performance simulation model according to the use situation and the environmental parameters, calculating a building performance simulation result, and optimizing the building performance simulation result according to an optimization target to obtain an optimal sunshade state annual schedule;
building a building sunshade self-adaptive control model, and training the building sunshade self-adaptive control model by using an optimal sunshade state annual schedule;
and dynamically acquiring environmental parameters by using a sensor, and acquiring the optimal sunshade state working condition by using a building sunshade self-adaptive control model according to the environmental parameters to realize building sunshade self-adaptive dynamic control.
Further, set up different sunshade state operating mode, include: and setting working parameters of the sun-shading equipment according to the control mode of the sun-shading equipment, and generating a sun-shading state working condition parameter set by using a mode of setting at equal intervals.
Further, according to the use situation and the environmental parameters, different sunshade state working conditions are set by utilizing the building performance simulation model, the building performance simulation result is calculated, and the optimization is carried out on the building performance simulation result according to the optimization target, so as to obtain the best sunshade state annual schedule, and the method comprises the following steps:
setting an optimization target;
inputting a use scene and a set of environment parameters, wherein the set of environment parameters is a plurality of sets of environment weather data with a year period and an hour interval;
setting different sunshade state working conditions for each environmental meteorological data, and simulating and calculating a building performance simulation result corresponding to a sunshade state working condition parameter set;
selecting a sunshade state working condition parameter corresponding to the optimal building performance simulation result in the environmental meteorological data according to the set optimization target, and recording the sunshade state working condition parameter as the optimization result corresponding to the environmental meteorological data;
and traversing and calculating the optimizing results of all the environmental meteorological data in the environmental parameter group to obtain the annual time schedule of the optimal sunshade state.
Further, the optimization target is as follows: and the parameter set of the working condition of the sun-shading state with smaller building energy consumption is a more optimal value while meeting the condition of avoiding glare.
Further, the method for training the self-adaptive control model for building sunshade by using the annual schedule of the optimal sunshade state comprises the following steps:
selecting a machine learning classification algorithm, and establishing a building sunshade self-adaptive control model;
converting the working condition parameters of the optimal sunshade state into classification labels, setting the classification labels as output of the model, setting the environmental meteorological data and the use situation as characteristic input of the model, and training the building sunshade self-adaptive control model by using the annual time schedule of the optimal sunshade state;
and (4) adjusting parameters and pruning the building sunshade self-adaptive control model to obtain the trained building sunshade self-adaptive control model.
Further, in the step of selecting a machine learning classification algorithm and establishing the building sunshade self-adaptive control model, the selected machine learning classification algorithm is a random forest algorithm or a decision tree algorithm.
Further, the building sunshade self-adaptive dynamic control method further comprises the following steps:
and the storage is used for recording the environmental parameters and the user using habits acquired by the sensor, and the annual schedule of the optimal sunshade state and the building sunshade adaptive control model are updated according to the environmental parameters and the user using habits stored by the storage.
The second purpose of the invention can be achieved by the following technical scheme:
an adaptive dynamic control system for building shading, comprising:
the simulation model module is used for establishing a building simulation model;
the simulation optimizing module is used for setting different sunshade state working conditions by utilizing the building performance simulation model according to the use scene and the environmental parameters, calculating a building performance simulation result, and optimizing the building performance simulation result according to an optimizing target to obtain an optimal sunshade state all-year-round timetable;
the building sunshade self-adaptive control model module is used for establishing a building sunshade self-adaptive control model, training the building sunshade self-adaptive control model by using an optimal sunshade state annual schedule, and acquiring an optimal sunshade state working condition by using the building sunshade self-adaptive control model according to acquired environmental parameters;
the sensor module is used for dynamically acquiring environmental parameters;
and the sunshade equipment is used for realizing the self-adaptive dynamic control of the building sunshade according to the optimal sunshade state working condition output by the self-adaptive control model module of the building sunshade.
Furthermore, the building sunshade self-adaptive dynamic control system also comprises a memory module for recording environmental parameters acquired by the sensor and user use habits; the environmental parameters and the user use habits stored in the memory are used for updating the annual schedule of the optimal sunshade state and the building sunshade adaptive control model.
The third purpose of the invention can be achieved by the following technical scheme:
a storage medium storing a program which, when executed by a processor, implements the building sunshade adaptive dynamic control method as recited in claim.
Compared with the prior art, the invention has the following beneficial effects:
(1) The method greatly improves the effect of the dynamic sunshade device in the aspects of saving energy and adjusting indoor luminous environment by combining simulation optimization and machine learning, realizes flexible and scientific response to the parameters of the sensor, can adapt to indoor and outdoor environment changes and changes of user use habits, and has more pertinence on a control target and can approach an optimization target set by a user compared with the traditional sunshade control method based on a certain fixed numerical value.
(2) According to the invention, through setting the memory and combining building performance simulation and computer programming, automatic and continuous sunshade state optimization is realized, time and energy input by manual control are reduced, a cyclic flow of input → simulation → reading result → optimization → re-input according to the result after optimization is realized, and simulation optimization and model training are carried out by continuously collecting new data, so that the accuracy of prediction and the universality in different use scenes are improved. In addition, through the method and the flow, a user can obtain a near-optimal sunshade self-adaptive control strategy after inputting according to a prompt without having professional knowledge related to building science and computer science.
(3) According to the invention, the sunshade self-adaptive control model is established by adopting machine learning, and the output of the sunshade self-adaptive control model is converted into the classification label, so that the prediction efficiency of the model is improved, a better classification effect can be obtained when the number of samples of the sunshade self-adaptive control model is small, and meanwhile, too much burden can not be caused on the performance of the controller.
Drawings
FIG. 1 is a flow chart of a building sunshade self-adaptive dynamic control method in embodiment 1 of the present invention;
FIG. 2 is a schematic diagram of a simulation model of a building in embodiment 1 of the present invention;
FIG. 3 is a flowchart of step S20 in the adaptive dynamic control method for building sunshade according to embodiment 1 of the present invention;
FIG. 4 is a flowchart of step S30 in the adaptive dynamic control method for building sunshade according to embodiment 1 of the present invention;
FIG. 5 is a schematic diagram of machine learning model input in the adaptive dynamic control method for architectural sunshade according to embodiment 1 of the present invention;
FIG. 6 shows the prediction accuracy of the decision tree and random forest classification algorithm of example 1 of the present invention in each orientation;
fig. 7 is a decision tree diagram of an optimal rolling blind sunshade lowering position of the decision tree model of embodiment 1 of the present invention;
FIG. 8 is a comparison graph of annual energy consumption performance of the adaptive dynamic control method for building sunshade of embodiment 1 of the present invention in south-facing rooms with other methods;
FIG. 9 is a comparison graph of annual energy consumption performance of the adaptive dynamic control method for building sunshade of embodiment 1 of the present invention and other methods in the west direction of the room;
FIG. 10 is a comparison graph of the annual UDI (100-2000 lux) proportion of the building sunshade self-adaptive dynamic control method in the south-facing room and other different sunshade control strategies according to embodiment 1 of the present invention;
FIG. 11 is a comparison chart of the annual UDI (100-2000 lux) proportion of the adaptive dynamic control method for building sunshade in the west-oriented room and other different sunshade control strategies according to embodiment 1 of the invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention, it is obvious that the described embodiments are some, but not all, embodiments of the present invention, and all other embodiments obtained by a person of ordinary skill in the art without making creative efforts based on the embodiments of the present invention belong to the protection scope of the present invention.
Example 1:
as shown in fig. 1, the present embodiment provides a building sunshade adaptive dynamic control method, which includes the following steps:
s10, building a building simulation model;
as shown in fig. 2, in this embodiment, the parameters of the room include building characteristic parameters and building thermal parameters, where the building characteristic parameters include space size and environmental shielding, and the building thermal parameters include boundary conditions, internal heat sources, and HVAC parameters; taking a typical office room in Guangzhou city as an example, a full-size room model is established. The room size is 6m wide x 4m deep x 4m high, is located at the central floor of the office building. Only one outer wall of the room is adjacent to the outdoor environment, and a window is arranged in the middle; the thermal parameter setting of the room refers to the general specification GB55015-2021 for building energy conservation and renewable energy utilization.
In this embodiment, in order to better show the optimization of the control model on the lighting energy consumption, a lighting system capable of realizing stepless dimming is adopted in the room, so as to ensure the lighting quality of the room (the illuminance of the working face is greater than 500 lux). And when natural lighting is sufficient, the lighting system will be turned off to save lighting energy. The illumination spots are located 1m and 3m from the window, 0.75m high, respectively.
In this embodiment, the sunshade device is a roller shutter sunshade device disposed outside the external window, and the size of the roller shutter sunshade device is the same as that of the external window.
S20, as shown in the figure 3, setting different sunshade state working conditions by using a building performance simulation model according to the use situation and the environmental parameters, calculating a building performance simulation result, and optimizing the building performance simulation result according to an optimization target to obtain an optimal sunshade state annual schedule; the method comprises the following steps:
s21, setting an optimization target;
in this embodiment, the optimization target is set as: the working condition parameter group of the sunshade state with smaller building energy consumption is a more optimal value when the glare index DGI at the position 1m away from the window is less than 25.
S22, inputting a use scene and an environment parameter group;
in this embodiment, the usage scenarios include HVAC set temperatures and personnel on-room schedules;
in this embodiment, the environmental parameter group is a typical meteorological year meteorological data set, which is a multiple environmental meteorological data set with a year period and an hour interval, specifically, a Chinese Standard Weather Data (CSWD) in guangzhou city, and the meteorological data includes an outdoor temperature and humidity, a solar radiation intensity, and a working surface illuminance, with the year period and the hour interval.
S23, setting different sunshade state working conditions for each piece of environmental meteorological data, and simulating and calculating a building performance simulation result corresponding to the sunshade state working condition parameter set;
in this embodiment, the sun-shading device is a roller blind sun-shading device, and therefore according to the control mode of the sun-shading device, the working parameters of the sun-shading device are set as the lowering height, and the lowering height is divided into five steps at equal intervals, so as to obtain the working condition parameter sets of the sun-shading state [0%,25%,50%,75%, 100%) ]; wherein, 0% and 100% respectively represent the working conditions of no shielding and complete shielding.
In another embodiment of the invention, the sun-shading equipment is a blind window, the working parameters of the sun-shading equipment are set as the angle of the blind window, the angle of the blind window is divided into four grades at equal intervals, and a sun-shading state working condition parameter group [0,30,60 and 90] is obtained;
s24, selecting a sun-shading state working condition parameter corresponding to an optimal building performance simulation result in the environmental meteorological data according to a set optimization target, and recording the sun-shading state working condition parameter as an optimization result corresponding to the environmental meteorological data;
in this embodiment, according to the environmental parameter set input in step S22, all sunshade state conditions are simulated, and the sunshade state with the DGI less than 25 and the minimum energy consumption in each hour is recorded as the optimization result corresponding to the hour.
And S25, traversing and calculating the optimizing results of all the environmental meteorological data in the environmental parameter group to obtain the annual schedule of the optimal sunshade state.
In this embodiment, the Chinese Standard Weather Data (CSWD) in guangzhou city has weather data for 8760 hours in total, so steps S23 to S24 are iterated 8760 times, so that all the environmental weather data have corresponding optimization results, and the optimization results are combined into an optimal sunshade status annual schedule.
S30, as shown in FIG. 4, building a self-adaptive control model of building sunshade, and training the self-adaptive control model of building sunshade by using an optimal sunshade state annual schedule, comprising the following steps:
s31, selecting a machine learning classification algorithm, and establishing a building sunshade self-adaptive control model;
in the embodiment, a random forest algorithm (RF) and a decision tree algorithm (DT) are respectively selected to establish a building sunshade self-adaptive control model, and the two algorithms are both used based on a Sk-learn library of Python.
S32, converting the working condition parameters of the optimal sunshade state into classification labels, setting the classification labels as output of the model, setting environmental meteorological data and use scenes as characteristic input of the model, and training the architectural sunshade self-adaptive control model by using the annual time schedule of the optimal sunshade state obtained in the step S25;
the characteristic inputs of the random forest algorithm (RF) and the decision tree algorithm (DT) are shown in FIG. 5;
wherein, in the feature input of the random forest algorithm (RF), the environment parameters comprise: the system comprises a building facade, a first working surface lighting illumination (daylighting illumination 1) and a third working surface lighting illumination (daylighting illumination 3), wherein the building facade is provided with a solar radiation intensity (Incident solar radiation on the facade), an Outdoor air temperature (Outdoor temperature), a Set-point temperature for starting indoor air conditioner refrigeration, a first working surface lighting illumination (daylighting illumination 1) and a third working surface lighting illumination (daylighting illumination 3);
in the feature input of the decision tree algorithm (DT), the environmental parameters include: the intensity of solar radiation Incident to the building facade (incorporated solar radiation on the facade), the Outdoor air temperature (Outdoor temperature), the Set temperature for starting the indoor air conditioner refrigeration (Set-point temperature for cooling), and the lighting illumination of the second working face (daylighting illumination 2).
The collecting points of the first working surface lighting illumination, the second working surface lighting illumination and the third working surface lighting illumination are set according to the distance from the external window and are collected through the lighting illumination sensor. The number of lighting illumination sensors of a random forest algorithm (RF) and a decision tree algorithm (DT) is increased, the RF obtains the lighting illumination of the first working surface and the lighting illumination of the third working surface by using the two lighting illumination sensors, and the indoor light environment can be adjusted more accurately by controlling the external shading state; and the decision tree algorithm (DT) adopts the data of one lighting illumination sensor, so that the number of the sensors is reduced, and the similar energy-saving effect can be achieved.
It should be noted that the number and the orientation of the data acquisition points of the lighting illuminance (for example, the orientation of the lighting illuminance sensor, which is the horizontal illuminance by default, but is a vertical illuminance in some cases) of the adaptive control model established in different situations are selected and adjusted according to actual needs.
And S33, performing parameter adjustment and pruning on the building sunshade self-adaptive control model to obtain the trained building sunshade self-adaptive control model.
In the embodiment, the prediction accuracy of the building sunshade self-adaptive control model established based on the random forest algorithm (RF) and the decision tree algorithm (DT) in each direction is shown in fig. 6, and it can be seen that the two building sunshade self-adaptive control models can achieve better prediction accuracy in simulation data.
Fig. 7 is a visual optimal rolling blind sunshade lowering position decision tree diagram of the adaptive control model for building sunshade built based on decision tree algorithm (DT) in this embodiment, and it can be seen that the adaptive control model for building sunshade built by using the method of this embodiment has good interpretability.
And S40, dynamically acquiring environmental data (namely environmental parameters) by using a sensor, and acquiring the optimal sunshade state working condition by using a building sunshade self-adaptive control model according to the environmental data to realize building sunshade self-adaptive dynamic control.
And S50, recording the environmental data and the user using habits acquired by the sensors by using a memory, and updating the annual schedule of the optimal sunshade state and the building sunshade adaptive control model according to the environmental data and the user using habits stored by the memory.
Fig. 8 and 9 are graphs showing comparison of annual energy consumption performance of the building sunshade self-adaptive dynamic control method of the embodiment and other methods in west-oriented rooms and south-oriented rooms, respectively. It can be seen that the results for the south and west orientations are not very different and exhibit the same trend. Secondly, it can be obviously observed that the lighting energy consumption and the refrigeration energy consumption under the control of Ctrl-RF and Ctrl-DT obtained by the method are almost the same as the optimization result, and compared with Ctrl-Solar, ctrl-DGI and Ctrl-Work, the method can achieve lower comprehensive energy consumption level. This shows that although there is a certain error in predicting the temporal sun-shading position by the adaptive control model, the energy saving effect is almost the same as that of the optimal sun-shading control and is more energy-saving than that of the general sun-shading strategy.
FIGS. 10 and 11 demonstrate the annual UDI (100-2000 lux) ratio comparison of the building sunshade adaptive dynamic control method of the present embodiment for south oriented rooms and west oriented rooms and different sunshade control strategies. In a south-oriented room, the ratio optimization results of the self-adaptive sun-shading control models (Ctrl-RF and CRTL-DT) provided by the method are basically the same, and the ratio reaches more than 70%. Compared with a reference room (without sunshade), the self-adaptive sunshade control (Ctrl-RF and CRTL-DT) provided by the method can reduce the time ratio of more than 2000lux, increase the UDI (100-2000 lux) ratio, avoid discomfort glare and reduce the illumination requirement at the same time.
In conclusion, the embodiment greatly improves the effect of the dynamic sunshade device in the aspects of saving energy and adjusting the indoor luminous environment by combining simulation optimization and machine learning, flexibly and scientifically responds to environmental parameters acquired by a sensor, can adapt to indoor and outdoor environmental changes and changes of user use habits, and has better pertinence on a control target and better approach to an optimization target set by a user compared with the traditional sunshade control method based on a certain fixed numerical value; according to the embodiment, the automatic and continuous sunshade state optimization is realized by arranging the memory and combining building performance simulation and computer programming, the time and energy input by manual control are reduced, the cyclic flow of input → simulation → reading result → optimization → re-input according to the result after optimization is realized, and the simulation optimization and model training are performed by continuously collecting new data, so that the accuracy of prediction and the universality in different use scenes are improved. In addition, through the method and the flow, a user does not need to have professional knowledge related to building science and computer science, and a near-optimal sunshade self-adaptive control strategy can be obtained after input according to prompts; according to the method, the sunshade self-adaptive control model is established by adopting machine learning, the output of the sunshade self-adaptive control model is converted into the classification label, the prediction efficiency of the model is improved, the sunshade self-adaptive control model can obtain a good classification effect when the number of samples is small, and meanwhile, too large burden can not be caused on the performance of the controller.
Example 2:
based on the same inventive concept as embodiment 1, this embodiment provides an adaptive dynamic control system for building sunshade, including:
the simulation model module is used for establishing a building simulation model;
the simulation optimizing module is used for setting different sunshade state working conditions by utilizing the building performance simulation model according to the use scene and the environmental parameters, calculating a building performance simulation result, and optimizing the building performance simulation result according to an optimizing target to obtain an optimal sunshade state all-year-round timetable;
the building sunshade self-adaptive control model module is used for establishing a building sunshade self-adaptive control model, training the building sunshade self-adaptive control model by using an optimal sunshade state annual schedule, and acquiring an optimal sunshade state working condition by using the building sunshade self-adaptive control model according to acquired environmental data (namely environmental parameters);
the sensor module is used for dynamically acquiring environmental data;
and the sunshade equipment is used for realizing the self-adaptive dynamic control of the building sunshade according to the optimal sunshade state working condition output by the self-adaptive control model module of the building sunshade.
The memory module is used for recording the environmental data acquired by the sensor and the use habits of the user; the environmental data and the user use habits stored in the memory are used for updating the annual schedule of the optimal sunshade state and the building sunshade adaptive control model.
That is to say, in the above 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 adaptive control model module for building sunshade is used to implement step S30 of embodiment 1, and the sensor module and the sunshade device work together to implement step S40 of embodiment 1; the memory module is used for realizing the step S50 of the embodiment 1; since steps S10 to S50 have been described in detail in embodiment 1, for brevity of description of the specification, the detailed implementation process of each module in this embodiment is referred to in embodiment 1, and is not described again.
Example 3:
the present embodiment provides a storage medium storing a program, where when the program is executed by a processor, the method for adaptive dynamic control of building sunshade according to embodiment 1 of the present invention is implemented, specifically including:
building a building simulation model;
setting different sunshade state working conditions by using a building performance simulation model according to the use situation and the environmental parameters, calculating a building performance simulation result, and optimizing the building performance simulation result according to an optimization target to obtain an optimal sunshade state annual schedule;
building a self-adaptive control model for building sunshade, and training the self-adaptive control model for building sunshade by using an optimal sunshade state annual schedule;
the method comprises the following steps of dynamically acquiring environmental data (namely environmental parameters) by using a sensor, and acquiring the optimal sunshade state working condition by using a building sunshade self-adaptive control model according to the environmental data to realize building sunshade self-adaptive dynamic control;
and the storage is used for recording the environmental data and the user use habits acquired by the sensor, and the annual schedule of the optimal sunshade state and the architectural sunshade self-adaptive control model are updated according to the environmental data and the user use habits stored by the storage.
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 of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
In the present embodiment, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this embodiment, however, a computer readable signal medium may include a propagated data signal with a computer readable program embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable storage medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program embodied on the computer readable storage medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer-readable storage medium may be written with a computer program for performing the present embodiments in one or more programming languages, including an object oriented programming language such as Java, python, C + +, and conventional procedural programming languages, such as C, or similar programming languages, or combinations thereof. The program may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may 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 the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be understood that the embodiments described above are only a few embodiments of the present invention, rather than all embodiments, and that the present invention is not limited to the details of the above embodiments, and that any suitable changes or modifications thereof, which may occur to those skilled in the art, are deemed to be within the scope of the present invention.
Claims (10)
1. A building sunshade self-adaptive dynamic control method is characterized by comprising the following steps:
building a building simulation model;
setting different sunshade state working conditions by utilizing a building performance simulation model according to the use situation and the environmental parameters, calculating a building performance simulation result, and optimizing the building performance simulation result according to an optimization target to obtain an optimal sunshade state annual schedule;
building a self-adaptive control model for building sunshade, and training the self-adaptive control model for building sunshade by using an optimal sunshade state annual schedule;
and dynamically acquiring environmental parameters by using a sensor, and acquiring the optimal sunshade state working condition by using a building sunshade self-adaptive control model according to the environmental parameters to realize building sunshade self-adaptive dynamic control.
2. The adaptive dynamic control method for building sunshade according to claim 1, wherein different sunshade status conditions are set, including: and setting working parameters of the sun-shading equipment according to the control mode of the sun-shading equipment, and generating a sun-shading state working condition parameter set by using a mode of setting at equal intervals.
3. The adaptive dynamic control method for building sunshade according to claim 2, wherein different sunshade status conditions are set by using a building performance simulation model according to the use situation and environmental parameters, the building performance simulation result is calculated, and the optimization is performed on the building performance simulation result according to the optimization target to obtain the best sunshade status annual schedule, comprising the following steps:
setting an optimizing target;
inputting a use scene and a set of environment parameters, wherein the set of environment parameters is a plurality of sets of environment weather data with a year period and an hour interval;
setting different sunshade state working conditions for each piece of environmental meteorological data, and simulating and calculating a building performance simulation result corresponding to a sunshade state working condition parameter set;
selecting a sunshade state working condition parameter corresponding to the optimal building performance simulation result in the environmental meteorological data according to the set optimization target, and recording the sunshade state working condition parameter as the optimization result corresponding to the environmental meteorological data;
and traversing and calculating the optimizing results of all the environmental meteorological data in the environmental parameter group to obtain the annual time schedule of the optimal sunshade state.
4. The adaptive dynamic control method for building sunshade according to claim 3, wherein the optimizing targets are: and the sunlight shading state working condition parameter set with smaller building energy consumption is a better value while meeting the condition of avoiding glare.
5. The adaptive dynamic control method for building sunshade according to claim 3, wherein training the adaptive control model for building sunshade using the annual schedule of optimal sunshade status comprises the steps of:
selecting a machine learning classification algorithm, and establishing a building sunshade self-adaptive control model;
converting the working condition parameters of the optimal sunshade state into classification labels, setting the classification labels as the output of the model, setting the environmental meteorological data and the use situation as the characteristic input of the model, and training the self-adaptive control model of the building sunshade by using the annual time schedule of the optimal sunshade state;
and (4) adjusting parameters and pruning the building sunshade self-adaptive control model to obtain the trained building sunshade self-adaptive control model.
6. The adaptive dynamic control method for building sunshade according to claim 5, wherein in the step of selecting a machine learning classification algorithm and establishing the adaptive control model for building sunshade, the selected machine learning classification algorithm is a random forest algorithm or a decision tree algorithm.
7. The adaptive dynamic control method for building sunshade according to any one of claims 1 to 6, further comprising the steps of:
and the storage is used for recording the environmental parameters and the user using habits acquired by the sensor, and the annual schedule of the optimal sunshade state and the building sunshade adaptive control model are updated according to the environmental parameters and the user using habits stored by the storage.
8. A building sunshade self-adaptation dynamic control system is characterized by comprising:
the simulation model module is used for establishing a building simulation model;
the simulation optimizing module is used for setting different sunshade state working conditions by utilizing the building performance simulation model according to the use scene and the environmental parameters, calculating a building performance simulation result, and optimizing the building performance simulation result according to an optimizing target to obtain an optimal sunshade state all-year-round timetable;
the building sunshade self-adaptive control model module is used for establishing a building sunshade self-adaptive control model, training the building sunshade self-adaptive control model by using an optimal sunshade state annual schedule, and acquiring an optimal sunshade state working condition by using the building sunshade self-adaptive control model according to the acquired environmental parameters;
the sensor module is used for dynamically acquiring environmental parameters;
and the sunshade equipment is used for realizing the self-adaptive dynamic control of the building sunshade according to the optimal sunshade state working condition output by the self-adaptive control model module of the building sunshade.
9. The adaptive dynamic control system for building sunshade according to claim 8, further comprising a memory module for recording environmental parameters and user's usage habits collected by the sensors; the environmental parameters and the user use habits stored in the memory are used for updating the annual schedule of the optimal sunshade state and the building sunshade adaptive control model.
10. A storage medium storing a program, wherein the program, when executed by a processor, implements the adaptive dynamic control method for building sunshade according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211187048.9A CN115598976A (en) | 2022-09-28 | 2022-09-28 | Building sunshade self-adaptive dynamic control method, system and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211187048.9A CN115598976A (en) | 2022-09-28 | 2022-09-28 | Building sunshade self-adaptive dynamic control method, system and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115598976A true CN115598976A (en) | 2023-01-13 |
Family
ID=84845261
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211187048.9A Pending CN115598976A (en) | 2022-09-28 | 2022-09-28 | Building sunshade self-adaptive dynamic control method, system and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115598976A (en) |
-
2022
- 2022-09-28 CN CN202211187048.9A patent/CN115598976A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10448483B2 (en) | Predictive daylight harvesting system | |
| Tabadkani et al. | A review of automatic control strategies based on simulations for adaptive facades | |
| Baloch et al. | Simulation tools application for artificial lighting in buildings | |
| Rapone et al. | Optimisation of curtain wall façades for office buildings by means of PSO algorithm | |
| CN113325762B (en) | Intelligent building personalized energy consumption control method, system, device and equipment | |
| Kurian et al. | Robust control and optimisation of energy consumption in daylight—artificial light integrated schemes | |
| CN109162619B (en) | Intelligent outer window optimization regulation and control method based on energy conservation | |
| KR20130114965A (en) | Design system of building having high energy efficiency using simulation and design process thereof | |
| Al-Obaidi et al. | Assessing the allowable daylight illuminance from skylights in single-storey buildings in Malaysia: a review | |
| Kamaruzzaman et al. | Achieving energy and cost savings through simple daylighting control in tropical historic buildings | |
| CN116258239B (en) | Intelligent control energy carbon-grid management integrated system and carbon-grid management method | |
| Elhelw | Analysis of energy management for heating, ventilating and air-conditioning systems | |
| CN112507439A (en) | Optimization design method for improving building site and building indoor environment performance | |
| US20100131110A1 (en) | Controlling method and system for saving energy of building | |
| CN112668081A (en) | Method for improving indoor environment performance of building based on sun-shading design of building external window | |
| CN115598976A (en) | Building sunshade self-adaptive dynamic control method, system and medium | |
| CN116305464A (en) | Multi-objective optimization method based on solar photovoltaic utilization and natural lighting coupling | |
| CN115795635A (en) | Sunshade setting method, device, equipment and storage medium for transformer substation building | |
| Gehbauer et al. | An evaluation of the demand response potential of integrated dynamic window and HVAC systems | |
| TWI742985B (en) | Intelligent electronic sunblind control system | |
| CN107990514A (en) | A kind of sunshade regulating system based on environment induction | |
| Al-Obaidi et al. | Toplighting systems for improving indoor environment: a review | |
| Agheb et al. | Model predictive control of integrated room automation considering occupants preference | |
| Fumagalli | Energy Space Layout: Designing space layout with optimised energy performance | |
| Intarungsee et al. | Intelligent Internet of Things using artificial neural networks and Kalman filters for energy management systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |