A visual comfort performance regulation method for intelligent sunshade louvers based on dynamic programming algorithm

Abstract

The application provides a visual comfort performance regulation method for intelligent sunshade louvers based on a dynamic programming algorithm.The method comprises the following steps: step 1, collecting potential influencing factors of light environment visual comfort performance and visual comfort evaluation index values, and constructing an office space light environment visual comfort dataset; step 2, training a random forest model algorithm in machine learning by using the dataset in step 1, and completing construction of a light environment visual comfort index prediction model; and step 3, using the light environment visual comfort index prediction model in step 2, constructing a sunshade regulation intelligent agent based on dynamic programming, and completing intelligent sunshade louver visual comfort performance regulation based on the dynamic programming algorithm. The application comprehensively considers various factors of the light environment and visual comfort evaluation indexes, and realizes intelligent regulation of the sunshade louver by means of the dynamic programming algorithm, so that the visual comfort demand of people in different light environments can be met to the greatest extent, and the visual comfort degree of the indoor light environment is effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of building intelligence and light environment regulation, in particular to a visual comfort performance regulation method of intelligent sunshade louver based on dynamic programming algorithm. The method is widely applicable to office building space, and aims to optimize indoor light environment by means of intelligent control of sunshade louver, so as to improve the visual comfort of people in indoor environment. BACKGROUND

[0002] In modern building system, indoor natural lighting environment has a very key influence on people's visual perception, work efficiency and physical and mental health. Suitable natural lighting conditions can effectively reduce visual fatigue and improve work and study efficiency; on the contrary, poor light environment may cause a series of problems such as eye fatigue and headache. Sunshade louver, as a common building sunshade facility, plays an important role in regulating the amount and distribution of light entering the room, and is a key element to improve indoor light environment.

[0003] Traditional sunshade louver regulation methods mainly rely on manual operation or simple timing control, and cannot dynamically adjust according to real-time light environment changes and people's visual comfort needs. Although some existing intelligent sunshade systems can regulate according to single parameters such as light intensity, they lack comprehensive consideration of multi-factor light environment and visual comfort evaluation index, and it is difficult to truly optimize the visual comfort performance.

[0004] Dynamic programming algorithm is a mathematical method for solving optimization problems in multi-stage decision-making process, and has a wide range of applications in resource allocation, path planning and other fields. However, there is no related technology that combines dynamic programming algorithm with light environment visual comfort index prediction model and applies it to intelligent sunshade louver regulation. SUMMARY

[0005] The present application aims to solve the problems in the prior art and proposes a visual comfort performance regulation method of intelligent sunshade louver based on dynamic programming algorithm. The method can comprehensively consider various factors of light environment and visual comfort evaluation index, and realize intelligent regulation of sunshade louver through dynamic programming algorithm, so as to maximize the visual comfort of indoor light environment.

[0006] The present application is realized by the following technical solutions, and the present application proposes a visual comfort performance regulation method of intelligent sunshade louver based on dynamic programming algorithm, which comprises the following steps:

[0007] Step 1: In a selected typical office building space, use data simulation method to collect potential influencing factors of light environment visual comfort performance and visual comfort evaluation index value, and construct office space light environment visual comfort data set;

[0008] Step 2, according to the nonlinear correlation between the potential influencing factors of the visual comfort performance of the light environment and the visual comfort evaluation index value, use the data set of step 1 to train the random forest model algorithm in machine learning, complete the construction of the visual comfort index prediction model of the light environment; the process of model construction includes data preprocessing, test set and training set segmentation, model training and verification;

[0009] Step 3, taking the visual comfort evaluation index as the optimization goal, using the visual comfort index prediction model of the light environment in step 2, combining with the dynamic programming algorithm to develop the intelligent sunshade louver visual comfort performance regulation based on dynamic programming algorithm; specifically, taking the visual comfort index prediction model of the light environment in step 2 as the state model, obtaining the state transition function and the reward function, and constructing the sunshade regulation intelligent agent based on dynamic programming.

[0010] Further, in the process of data collection and model construction,

[0011] Firstly, collect the data of potential influencing factors of visual comfort performance of light environment and corresponding visual comfort evaluation index value, so as to build the data set;

[0012] Secondly, the data set is preprocessed, including data cleaning, coding and standardization;

[0013] Finally, the preprocessed data set is divided into training set and test set according to certain proportion, the random forest model algorithm is used to train the training set, the visual comfort index prediction model of light environment is constructed, and the accuracy of the model is verified through the test set.

[0014] Further, the problem modeling of the regulation method is as follows:

[0015] Define the state space: the state includes various parameters of the light environment, the current angle of the sunshade louver and the time information, use s to represent the state, and the state space S is the set of all possible states;

[0016] Define the action space: the action refers to adjusting the angle of the sunshade louver, use a to represent the action, and the action space A is the set of all possible actions;

[0017] Determine the optimization goal: the optimization goal is set to maximize the visual comfort evaluation index, and the output of the visual comfort index prediction model of the light environment is taken as the value function V(s).

[0018] Further, the state transition function: taking the visual comfort index prediction model of the light environment as the state model, given the current state s and action a, the prediction value of the next state s' is obtained through the model; if the state transition is deterministic, P(s'|s,a) = 1 if and only if s' is the next state predicted by the model, otherwise P(s'|s,a) = 0.

[0019] Further, the reward function: define the reward function R(s, a) as the change value of the visual comfort evaluation index of state s after taking action a, that is R(s, a) = V(s') - V(s), wherein s' is the next state transferred after taking action a.

[0020] Further, initialization is performed in the process of constructing the sunshade control agent based on dynamic programming, the value function is initialized to zero, which is applicable to all states; the value function represents the expected value of the long-term cumulative reward that can be obtained by following the optimal strategy from the initial state; the initialization strategy is a random strategy, which randomly selects an action for each state; specifically, the value function V(s) is initialized to zero, which is applicable to all states s∈S; the initialization strategy π(s) is initialized as a random strategy, that is, for each state s, a random action a∈A is selected.

[0021] Further, dynamic programming algorithm iteration is performed in the process of constructing the sunshade control agent based on dynamic programming: the value function is calculated according to the current strategy, and the value function is updated for each state using the Bellman equation; when improving the strategy, the strategy is improved according to the current value function; for each state, the action that can maximize the action value function is selected as the new strategy; repeat the strategy evaluation and strategy improvement steps until the strategy converges, that is, the strategy no longer changes.

[0022] Further, the specific process of the intelligent sunshade control implementation is as follows:

[0023] Real-time state monitoring: real-time monitoring of the parameters of the light environment and the current state of the sunshade louver using sensors, and inputting these information as the current state s into the sunshade control agent based on dynamic programming;

[0024] Action decision: according to the current state s, the agent selects an action a through the already converged optimal strategy π(s), that is, determines the best adjustment angle of the sunshade louver;

[0025] Action execution: send the selected action a to the sunshade louver control system to execute the angle adjustment operation of the sunshade louver;

[0026] Loop iteration: repeat the real-time state monitoring, action decision and action execution steps to realize real-time dynamic control of the sunshade louver.

[0027] The application also proposes an electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the intelligent sunshade louver visual comfort performance control method based on the dynamic programming algorithm when executing the computer program.

[0028] The application further provides a computer readable storage medium for storing computer instructions, which are executed by a processor to implement the steps of the intelligent shading louver visual comfort performance regulation method based on a dynamic programming algorithm.

[0029] Advantages of the application:

[0030] 1. Improving visual comfort: The application comprehensively considers various factors of the light environment and visual comfort evaluation indexes, and realizes intelligent regulation of the shading louver by means of the dynamic programming algorithm, which can best meet the visual comfort needs of people in different light environments and effectively improve the visual comfort of the indoor light environment.

[0031] 2. Adaptive dynamic adjustment: The method can dynamically adjust the angle of the shading louver according to real-time changes in the light environment and the state of the shading louver, realize adaptive light environment regulation, and significantly improve the accuracy and flexibility of regulation.

[0032] 3. Energy saving and high efficiency: By reasonably controlling the angle of the shading louver, unnecessary direct sunlight is reduced, and the energy consumption of indoor air conditioners and lighting devices is reduced, achieving the dual goals of energy saving and comfort. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are only a part of the embodiments of the application, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of the provided drawings.

[0034] Fig. 1 The flowchart of the intelligent shading louver visual comfort performance regulation method based on a dynamic programming algorithm.

[0035] Fig. 2 The regulation process diagram of the intelligent shading louver visual comfort performance regulation method based on a dynamic programming algorithm. DETAILED DESCRIPTION

[0036] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only a part of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the application.

[0037] In combination with Figs. 1-2The application provides an intelligent sunshade louver visual comfort performance regulation method based on a dynamic programming algorithm.

[0038] Step 1: In a selected typical office building space, the potential influencing factors of the light environment visual comfort performance and the visual comfort evaluation index values are collected by using a data simulation method, and an office space light environment visual comfort dataset is constructed.

[0039] In step 1, the data simulation method is selected

[0040] Tools: Professional lighting simulation software (such as Radiance, DIVA, or EnergyPlus) is used to generate light environment data, and a parameterized modeling tool (such as Grasshopper) is used to realize automatic simulation.

[0041] Fixed parameter settings: Covering sky model types, Radiance simulation parameters, building geometric sizes, materials, orientations, window sizes, space layouts and other variables.

[0042] Verification: Real data is collected by field sensors (illuminance meters, glare sensors), and the simulation results are calibrated to ensure that the error is within 10%.

[0043] In step 1, the influencing factors and evaluation indexes

[0044] Input characteristics: Season, date, time of day, climate parameters (outdoor horizontal direct irradiance, outdoor diffuse irradiance, dry bulb temperature) and sunshade louver blade angle.

[0045] Output index: sUDI, i.e. the ratio of measurement points meeting the effective horizontal illuminance to all measurement points at a certain time, or the area ratio meeting the effective horizontal illuminance.

[0046] In step 1, sUDI simulation based on the simulation platform

[0047] Run simulation: Start simulation by traversing the representative dates and time periods throughout the year, which can be for typical summer representative time periods and winter representative time periods.

[0048] Build dataset: Simulate UDI data, form a mapping with feature data, and build a dataset for machine learning training.

[0049] Step 2: According to the nonlinear correlation between the potential influencing factors of the light environment visual comfort performance and the visual comfort evaluation index values, the random forest model algorithm in machine learning is trained with the dataset in step 1 to complete the construction of the light environment visual comfort index prediction model; the process of model construction includes data preprocessing, segmentation of test set and training set, and model training and verification.

[0050] In step 2, data preprocessing

[0051] Data encoding: Convert it into numerical types for machine learning model processing. Specifically, label encoding is required for seasonal and date data.

[0052] Data standardization: Standardize numerical features so that different features have the same scale.

[0053] In step 2, test set and training set segmentation

[0054] Determine the segmentation ratio: Usually divide the dataset into training set and test set according to certain ratio, common ratio is 7:3 or 8:2. Training set is used for model training, test set is used for evaluating model generalization ability.

[0055] Random segmentation: Use random function algorithm to randomly arrange samples, and divide test set and training set according to the set segmentation ratio.

[0056] In step 2, model training and verification

[0057] Model initialization: Call random forest regression algorithm for sUDI, initialize random forest model and set corresponding hyperparameters.

[0058] Model training: Train random forest model using training set data, input feature matrix and target variable of training set.

[0059] Model verification: Use the trained model to predict the test set, call the prediction method of the model and input the feature matrix of the test set.

[0060] Evaluation index calculation: Evaluate the random forest regression model, common evaluation indexes include mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE) and determination coefficient.

[0061] In step 2, model optimization and tuning

[0062] Hyperparameter optimization: Use grid search (Grid Search) or random search (Random Search) to optimize the hyperparameters of random forest model, find the optimal parameter combination and improve the performance of the model.

[0063] Model training under optimal parameters: After solving the optimal parameters, use the optimal parameters to train the model.

[0064] Step 3, using the visual comfort evaluation index as the optimization objective, develop an intelligent shading louver visual comfort performance regulation based on dynamic programming algorithm using the light environment visual comfort index prediction model of step 2 in combination with the dynamic programming algorithm; specifically, use the light environment visual comfort index prediction model of step 2 as the state model, obtain the state transition function and the reward function, and construct a shading regulation intelligent agent based on dynamic programming.

[0065] In step 3, the light environment visual comfort problem is modeled

[0066] Define the state space: the state includes season, date, time of day, climate parameters (outdoor horizontal vector direct irradiance, outdoor diffuse irradiance, dry bulb temperature) and shading louver blade angle.

[0067] Define the action space: the action is the operation that the agent can take. For the shading louver, the action is to adjust the angle of the louver.

[0068] Determine the optimization function: the optimization objective is to maximize the visual comfort evaluation index. Use the sUDI of the light environment visual comfort index prediction model obtained in step 2 as the optimization function.

[0069] In step 3, obtain the state transition function and the reward function

[0070] State transition function: the state transition function describes the probability of the system transitioning to the next state s' after taking action a in the current state s. Based on the light environment visual comfort index prediction model of step 2, use it as the state model to obtain the state transition function.

[0071] Since the light environment visual comfort index prediction model of step 2 can predict the future light environment based on the current light environment parameters and the shading louver state, this model can be used as a state model to obtain the reward function.

[0072] In step 3, construct a shading regulation intelligent agent based on dynamic programming

[0073] Initialization: initialize the value function to zero for all states. The value function represents the expected value of the long-term cumulative reward that can be obtained by following the optimal policy from the initial state; while the initial policy is a random policy, randomly selecting an action for each state.

[0074] Dynamic programming algorithm iteration: calculate the value function according to the current policy. Update the value function for each state using the Bellman equation. When improving the policy, improve the policy according to the current value function. For each state, select the action that maximizes the action value function as the new policy. Repeat the policy evaluation and policy improvement steps until the policy converges, i.e. the policy no longer changes.

[0075] The implementation process of the intelligent sunshade louver visual comfort performance regulation and control method based on the dynamic programming algorithm is specifically as follows:

[0076] 1. Data collection and model construction

[0077] 1.1 Collect data of potential influencing factors of light environment visual comfort performance and corresponding visual comfort evaluation index values as much as possible to construct a data set.

[0078] 1.2 Perform preprocessing work on the data set, including data cleaning, coding, standardization and other operation processes.

[0079] 1.3 Divide the preprocessed data set into a training set and a test set according to a certain proportion, train the training set by using a random forest model algorithm, construct a light environment visual comfort index prediction model, and verify the accuracy of the model through the test set.

[0080] 2. Problem modeling

[0081] 2.1 Define the state space: the state includes various parameters of the light environment, the current angle of the sunshade louver, time and other information, and the state is represented by s, and the state space S is the set of all possible states.

[0082] 2.2 Define the action space: the action refers to adjusting the angle of the sunshade louver, and the action is represented by a, and the action space A is the set of all possible actions.

[0083] 2.3 Determine the optimization target: the optimization target is set to maximize the visual comfort evaluation index, and the output of the light environment visual comfort index prediction model is taken as the value function V(s).

[0084] 3. Obtain the state transition function and the reward function

[0085] 3.1 State transition function: take the light environment visual comfort index prediction model as the state model, given the current state s and the action a, obtain the predicted value of the next state s' through the model. If the state transition is deterministic, P(s'|s,a)=1 if and only if s' is the model-predicted next state, otherwise P(s'|s,a)=0.

[0086] 3.2 Reward function: define the reward function R(s,a) as the change value of the visual comfort evaluation index of the state s after taking the action a, that is, R(s,a)=V(s')-V(s), where s' is the next state transferred after taking the action a.

[0087] 4. Construct a sunshade regulation intelligent agent based on dynamic programming

[0088] 4.1 Initialization: Initialize the value function V(s) to zero for all states s∈S; initialize the policy π(s) to a random policy, i.e., for each state s, randomly select an action a∈A.

[0089] 4.2 Iteration of the dynamic programming algorithm, including policy evaluation and policy improvement.

[0090] 4.2.1 Policy evaluation: Calculate the value function V(s) according to the current policy π(s) and update the value function using the Bellman equation: V(s) = Σ a∈A π(a|s)∑ s'∈S P(s'|s,a)[R(s,a) + γV(s')], where γ is the discount factor, usually taking values between [0,1].

[0091] 4.2.2 Policy improvement: Improve the policy π(s) according to the current value function V(s), for each state s, select the action a that maximizes the action value function Q(s,a) as the new policy, i.e.

[0092]

[0093] 4.2.3 Repeat the steps of policy evaluation and policy improvement until the policy converges, that is, the policy no longer changes.

[0094] 5. Intelligent sunshade control implementation

[0095] 5.1 Real-time state monitoring: Use sensors to monitor the parameters of the light environment and the current state of the sunshade louvers in real time, and input these information as the current state s into the sunshade control agent based on dynamic programming.

[0096] 5.2 Action decision: According to the current state s, the agent selects an action a through the optimal policy π(s) that has been converged, i.e., determines the best adjustment angle of the sunshade louvers.

[0097] 5.3 Action execution: Send the selected action a to the sunshade louver control system to perform the angle adjustment operation of the sunshade louvers.

[0098] 5.4 Loop iteration: Repeat the steps of real-time state monitoring, action decision and action execution to realize real-time dynamic control of the sunshade louvers.

[0099] Embodiment

[0100] The present application proposes a visual comfort performance control method for intelligent sunshade louvers based on dynamic programming algorithm, which comprises:

[0101] Step 1: Data collection and model construction

[0102] 1.1 Data Collection: Based on the specified typical office building space, parametric modeling is conducted using Rhinoceros + Grasshopper + Ladybug + Honeybee, and natural lighting environment simulation is conducted. The parametric correlation between fixed variables (building geometric parameters, building material parameters), adjustable behavior variables (shading louver rotation angle), time parameters (year, month, day), climate parameters (sky model, meteorological EPW data), and indoor effective natural lighting illumination matrix ratio or area ratio sUDI is constructed. Record these data during simulation to build the corresponding sample data set.

[0103] 1.2 Data Preprocessing: Data encoding and data standardization.

[0104] 1.2.1 Data Encoding: If the data set contains categorical variables (such as lighting type, space type, etc.), it needs to be converted to numerical type for machine learning model processing. Specifically, the LabelEncoding function in the machine learning toolkit scikit-learn is called to convert string character information to numerical values.

[0105] 1.2.2 Data Standardization: For input feature variables with different variation amplitudes, data dimension and distribution need to be normalized and standardized to make different features have the same scale and avoid affecting the accuracy of result prediction due to data amplitude difference. Numerical features are processed by z-score standardization. Common standardization methods include Min-Max Scaling and Standard Scaling.

[0106] 1.3 Model Training and Validation: The preprocessed data set is divided into training set and test set according to the ratio of 8:2 using Python's scikit-learn library. Initialize the random forest regression model and set appropriate parameters (such as n_estimators = 100, max_depth = 10, etc.). Use the training set to train the model. Use the test set to validate the trained model, calculate the mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE) and determination coefficient (R 2 ) and other evaluation indexes to evaluate the accuracy of the model.

[0107] Step 2: Problem modeling

[0108] 2.1 State space definition: State is a description of the current situation of the system. In the problem of visual comfort performance regulation of intelligent shading louvers, the state includes season, date, time of day, climate parameters (outdoor horizontal vector direct irradiance, outdoor diffuse irradiance, dry-bulb temperature) and louver blade angle. These information are combined into a multi-dimensional vector as state s. For example, s = [season, date, time of day, climate parameters, louver blade angle]. State space S is the set of all possible state vectors.

[0109] 2.2 Action space definition: The adjustment angle range of the shading louver is divided into several discrete values (such as 0°, 10°, 20°, … 90°), which constitute the action space A.

[0110] Step 3: Obtain state transition function and reward function

[0111] 3.1 State transition function: Encapsulate the trained light environment visual comfort index prediction model as a function, input the current state s and action a, output the predicted value of the next state s'. According to the prediction result, determine the state transition probability P(s'|s,a).

[0112] 3.2 Reward function: Implement the reward function R(s,a) in the code, according to the state s and action a, calculate the value function V(s') of the next state s' and the value function V(s) of the current state, the difference between the two is the reward value.

[0113] Step 4: Construct shading regulation agent based on dynamic programming

[0114] 4.1 Initialization: Use Python array to initialize the value function V(s) to zero, and the policy π(s) to randomly selected actions.

[0115] 4.2 Dynamic programming algorithm iteration

[0116] 4.2.1 Policy evaluation: Write a function to implement the iterative update of Bellman equation until the value function converges.

[0117] 4.2.2 Policy improvement: Write a function to calculate the action value function Q(s,a) according to the current value function, and select the action that maximizes Q(s,a) as the new policy.

[0118] 4.2.3 Repeat the policy evaluation and policy improvement steps until the policy no longer changes.

[0119] Step 5: Intelligent shading regulation implementation

[0120] 5.1 Real-time state monitoring: Before use, install light sensors, angle sensors and other devices to collect real-time parameters of the light environment and the current angle of the sunshade louvers. The data is transmitted to the control system to obtain the required observation state of the intelligent agent.

[0121] 5.2 Action decision: Input the real-time collected state information into the sunshade control intelligent agent based on dynamic programming, and select the adjustment angle of the sunshade louvers according to the converged optimal strategy.

[0122] 5.3 Action execution: The control system sends the selected action instruction to the driving device of the sunshade louvers to perform the angle adjustment operation.

[0123] 5.4 Loop iteration: Set a timer to repeat the above real-time state monitoring, action decision and action execution steps every certain time (such as 5 minutes) to realize real-time dynamic control of the sunshade louvers.

[0124] The application also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the intelligent sunshade louver visual comfort performance control method based on the dynamic programming algorithm when executing the computer program.

[0125] The application also provides a computer readable storage medium for storing computer instructions, wherein the computer instructions implement the steps of the intelligent sunshade louver visual comfort performance control method based on the dynamic programming algorithm when executed by a processor.

[0126] The memory in the embodiments of the present application can be a volatile memory or a nonvolatile memory, or can include both volatile and nonvolatile memory. Among them, the nonvolatile memory can be a read only memory (ROM), a programmable ROM (PROM), an erasable programmable ROM (EPROM), an electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, and not limitation, many forms of RAM can be used, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous dynamic RAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DRRAM). It is noted that the memory of the methods described herein is intended to include, but not be limited to, these and any other suitable types of memory.

[0127] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be magnetic media (such as floppy disk, hard disk, magnetic tape), optical media (such as high-density digital video disc (digital video disc, DVD)), or semiconductor media (such as solid state disc (solid state disc, SSD)) and the like.

[0128] In the implementation process, each step of the above method can be completed by integrated logic circuit of hardware in the processor or instruction in the form of software. The steps of the method disclosed in the embodiments of the present application can be directly embodied as hardware processor execution or combined execution by hardware and software modules in the processor. The software module can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, register and other mature storage media in the art. The storage medium is located in the memory, and the processor reads the information in the memory and combines the hardware to complete the steps of the above method. To avoid repetition, it will not be described in detail here.

[0129] It should be noted that the processor in the embodiments of the present application can be an integrated circuit chip with processing capability of signals. In the implementation process, each step of the method embodiments can be completed by integrated logic circuits or instructions in the form of software of the hardware in the processor. The processor mentioned above can be a general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as hardware code processing for execution, or executed by a combination of hardware and software modules in the code processing. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, and other mature storage media in the art. The storage medium is located in the storage, and the processor reads the information in the storage, and combines the hardware to complete the steps of the above method.

[0130] The above describes in detail the intelligent sunshade louver visual comfort performance regulation method based on the dynamic programming algorithm. The principles and implementation manners of the present application are described by using specific examples. The above embodiment is only used to help understand the method of the present application and its core idea. Meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manner and application range will be changed. In summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method for regulating the visual comfort performance of intelligent shading louvers based on dynamic programming algorithm, characterized in that, The method for regulating the visual comfort performance of intelligent shading louvers includes the following steps: Step 1: In the selected typical office building space, use data simulation methods to collect potential influencing factors and visual comfort evaluation index values ​​of the light environment, and construct a visual comfort dataset of the office space light environment. Step 2: Based on the nonlinear relationship between potential influencing factors of visual comfort performance of the light environment and visual comfort evaluation index values, train the random forest model algorithm in machine learning using the dataset from Step 1 to complete the construction of the visual comfort index prediction model for the light environment; the model construction process includes dataset preprocessing, splitting the test set and training set, and model training and validation. Step 3: Using the visual comfort evaluation index value as the optimization target, the visual comfort index prediction model of the light environment in Step 2 is used to develop a dynamic programming algorithm-based intelligent shading louver visual comfort performance regulation; specifically, the visual comfort index prediction model of the light environment in Step 2 is used as the state model to obtain the state transition function and reward function, and a shading regulation intelligent agent based on the dynamic programming algorithm is constructed. During the data acquisition and model building process First, data on potential factors affecting the visual comfort performance of the lighting environment and their corresponding visual comfort evaluation index values ​​were collected to construct a dataset. Secondly, preprocessing work is carried out on the dataset, including data cleaning, encoding, and standardization; Finally, the preprocessed dataset is divided into training and test sets according to a certain ratio. The random forest model algorithm is used to train the training set to build a prediction model for visual comfort index of light environment. The accuracy of the model is verified by the test set. Also includes: Define the state space: The state contains various parameters of the light environment, the current angle and time information of the shading louvers, and is represented by s. The state space S is the set of all possible states. Define the action space: An action refers to adjusting the angle of the sunshade louvers, denoted by 'a'. The action space A is the set of all possible actions. Determine the optimization objective: The optimization objective is set as maximizing the visual comfort evaluation index value, and the output of the light environment visual comfort index prediction model is used as the value function V(s); State transition function: Treating the visual comfort index prediction model of the light environment as a state model, given the current state s and action a, the predicted value of the next state s' is obtained through the state model; if the state transition is deterministic, P(s'|s, a) = 1 if and only if s' is the next state predicted by the state model, otherwise P(s'|s, a) = 0; Reward function: Define the reward function R(s, a) In order to take action a Post-state s The change in the visual comfort evaluation index value, i.e. ,in s' It is to take action a The state is then transitioned to.

2. The method for regulating the visual comfort performance of intelligent shading louvers according to claim 1, characterized in that, Initialization is performed during the construction of a shading control agent based on a dynamic programming algorithm. The initial value function is set to zero, which is applicable to all states. The value function represents the expected long-term cumulative reward obtained by following the optimal policy starting from the initial state; the optimal policy is a stochastic policy that randomly selects an action for each state; specifically, the value function... V(s) Initialize to zero, applicable to all states. ; the optimal strategy Initialize to a random policy, that is, for each state s Randomly select an action .

3. The method for regulating the visual comfort performance of intelligent shading louvers according to claim 2, characterized in that, In the process of constructing a shading control agent based on dynamic programming, dynamic programming algorithm iteration is performed: the value function is calculated according to the current policy, and the value function is updated using the Bellman equation for each state; when improving the policy, the policy is improved according to the current value function. For each state, select the action that maximizes the action value function as the new strategy; Repeat the policy evaluation and policy improvement steps until the policy converges, that is, the policy no longer changes.

4. The method for regulating the visual comfort performance of intelligent shading louvers according to claim 3, characterized in that, The specific process for achieving visual comfort performance regulation of intelligent shading louvers is as follows: Real-time status monitoring: Sensors are used to monitor various parameters of the light environment and the current status of the shading louvers in real time, and this information is used as the current status. The input is fed into a shading control agent based on a dynamic programming algorithm; Action decision: based on the current state The agent uses the already converged optimal policy Choose an action This means determining the optimal adjustment angle for the sunshade louvers; Action execution: Select the action Send the command to the shading louver control system to perform the angle adjustment operation of the shading louvers; Iterative loop: Repeated real-time status monitoring, action decision-making, and action execution steps to achieve real-time dynamic control of the shading louvers.

5. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the intelligent shading louver visual comfort performance control method according to any one of claims 1-4.

6. A computer-readable storage medium for storing computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the steps of the visual comfort performance control method for intelligent shading louvers as described in any one of claims 1-4.

Images