Intelligent collaborative regulation method and system of light and heat equipment considering comfort, health and energy saving

Abstract

The application provides a light and heat equipment intelligent collaborative regulation method and system which takes into account comfort, health and energy saving. The method comprises the following steps: collecting operation state parameters of a to-be-regulated field and first outdoor meteorological data; establishing a target function with the minimum comprehensive energy consumption of the to-be-regulated field as the target, and obtaining an optimization target after the target function is constrained by multiple constraint conditions; taking the operation state parameters of each device at the current time as an individual population and the first outdoor meteorological data as initial input, using a pre-trained prediction model and combining a particle swarm optimization algorithm to iteratively optimize each individual in the population under the constraint of the optimization target, and obtaining an optimal regulation strategy of the comprehensive light environment, the thermal environment and the comprehensive energy consumption; and controlling the operation state of each device in the to-be-regulated field according to the optimal regulation strategy. The application can realize intelligent regulation which takes into account comfort, health and energy saving, and can efficiently create and intelligently operate a low-carbon and healthy environment of a building.

Description

Technical Field

[0001] This application relates to the field of intelligent control technology, and in particular to an intelligent collaborative control method and system for solar thermal equipment that takes into account both comfort and health and energy saving. Background Technology

[0002] Indoor thermal, humidity, and light environments are primarily regulated through terminal controls such as shading systems, air conditioning systems, and lighting systems. Different shading control schemes affect the indoor thermal environment and the energy consumption of lighting and air conditioning. Lighting energy consumption accounts for up to 20% in large office buildings, and the combined energy consumption of lighting and air conditioning reaches 60%. Reducing energy consumption in lighting and air conditioning systems is crucial for energy conservation and emission reduction during building operation. Furthermore, in office buildings, occupants often neglect to adjust shading devices, leading to poor indoor lighting environments and energy waste. Therefore, further research is needed on the coordinated control methods of building thermal and light regulation equipment (such as shading devices, lighting equipment, and air conditioning equipment).

[0003] In related studies, the indicators for evaluating the light environment generally include static indicators (illuminance, daylight factor, daylight uniformity, solar glare coefficient, etc.) and dynamic indicators (autonomous daylight factor, effective solar illuminance percentage, autonomous glare coefficient, etc.). These indicators can evaluate the light environment in different spatial and temporal dimensions. Thermal environment indicators generally use a comprehensive index such as PMV-PPD (Predicted Mean Vote - Predicted Percentage of Dissatisfied), effective temperature (ET), and operating temperature to statistically assess the thermal comfort satisfaction of a given area.

[0004] Related technologies propose different goals for creating photothermal environments and methods for equipment control to improve indoor occupant comfort and enhance user experience. However, conflicts exist among adjusting building shading, artificial lighting, and air conditioning setpoints while ensuring indoor light and thermal comfort. Therefore, how to balance the operating status of various control devices and optimize control strategies to improve the indoor environment and reduce building energy consumption while meeting photothermal comfort requirements has become an urgent technical problem to be solved. Summary of the Invention

[0005] This application provides an improved intelligent coordinated control method and system for solar thermal equipment that balances comfort, health, and energy saving, enabling intelligent control that balances comfort, health, and energy saving.

[0006] In a first aspect, this application provides a method for intelligent coordinated control of solar thermal equipment that balances comfort, health, and energy conservation, including: Collect the operating status parameters of each device at the site to be regulated at the current moment, as well as the first outdoor meteorological data; An objective function is established with the goal of minimizing the overall energy consumption of the site to be regulated. After applying multiple constraints to the objective function, an optimized objective is obtained. The operating status parameters of each device at the current moment are used as individuals to generate a population, and the first outdoor meteorological data is used as the initial input. Using a pre-trained prediction model and combined with the particle swarm optimization algorithm, the individual in the population is iteratively optimized under the constraint of the optimization objective to obtain the optimal control strategy for the comprehensive light environment, thermal environment and comprehensive energy consumption. According to the optimal control strategy and in combination with the operating status parameters of the location to be controlled, the operating status of each corresponding device in the location to be controlled is controlled.

[0007] Secondly, this application provides an intelligent collaborative control system for solar thermal equipment that balances comfort, health, and energy saving, including: Monitoring sensors are used to collect the operating status parameters of each device in the controlled area at the current moment, as well as the first outdoor meteorological data. A cloud platform is used to establish an objective function with the goal of minimizing the comprehensive energy consumption of the site to be regulated. After constraining the objective function with multiple constraints, an optimization objective is obtained. The operating status parameters of each device at the current moment are used as individuals to generate a population, and the first outdoor meteorological data is used as the initial input. Using a pre-trained prediction model and combined with a particle swarm optimization algorithm, each individual in the population is iteratively optimized under the constraints of the optimization objective to obtain the optimal regulation strategy for comprehensive light environment, thermal environment and comprehensive energy consumption. The control module is used to control the operating status of each device in the controlled location according to the optimal control strategy and in combination with the operating status parameters of the controlled location.

[0008] This application provides a method and system for intelligent collaborative control of solar thermal equipment that balances comfort, health, and energy conservation. The method includes: collecting operating status parameters of the controlled environment and first outdoor meteorological data; establishing an objective function with the goal of minimizing the overall energy consumption of the controlled environment, and obtaining an optimization objective by constraining the objective function with multiple constraints; using the operating status parameters of each device at the current moment as an individual to generate a population, and the first outdoor meteorological data as initial input; using a pre-trained prediction model combined with a particle swarm optimization algorithm, iteratively optimizing each individual in the population under the constraints of the optimization objective to obtain the optimal control strategy for the overall light environment, thermal environment, and overall energy consumption; and controlling the operating status of each corresponding device in the controlled environment according to the optimal control strategy. This application can achieve intelligent control that balances comfort, health, and energy conservation, realizing the efficient creation and intelligent operation and maintenance of a low-carbon and healthy building environment. Attached Figure Description

[0009] Figure 1 The diagram shown is a flowchart illustrating the intelligent collaborative control method for solar thermal equipment that balances comfort, health, and energy saving, as provided in an embodiment of this application. Figure 2 The diagram shown is a schematic representation of the conceptual process of coordinated regulation provided in an embodiment of this application. Figure 3 The diagram shown is a detailed schematic of the intelligent collaborative control method for solar thermal equipment that balances comfort, health, and energy saving, provided in an embodiment of this application. Figure 4 The diagram shown is a schematic representation of the optimization process of the particle swarm optimization algorithm provided in an embodiment of this application. Figure 5 The diagram shown is a schematic representation of the room performance simulation process provided in an embodiment of this application. Figure 6 The diagram shown is a schematic representation of the process of deployment and control on a cloud platform according to an embodiment of this application. Detailed Implementation

[0010] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of this specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of one or more embodiments of this specification as detailed in the appended claims.

[0011] It should be noted that the steps of the corresponding methods are not necessarily performed in the order shown and described in this specification in other embodiments. In some other embodiments, the methods may include more or fewer steps than described in this specification. Furthermore, a single step described in this specification may be broken down into multiple steps in other embodiments; and multiple steps described in this specification may be combined into a single step in other embodiments.

[0012] Related technologies propose different methods for creating and controlling photothermal environments to improve indoor occupant comfort and enhance user experience, as detailed below: Related Technology 1: In the field of shading louver control, patent document CN120122432A discloses a method for controlling the visual comfort performance of intelligent shading louvers based on dynamic programming algorithms. This invention comprehensively considers various factors of the light environment and the visual comfort evaluation index sUDI (Useful Daylight Illuminance Duration), simulates typical office building spaces, and constructs a visual comfort dataset for the office space light environment. The dataset is preprocessed using a machine learning model to build a prediction model. Subsequently, an intelligent control system is built using dynamic programming algorithms to achieve intelligent control of the shading louvers based on corresponding outdoor climate conditions. This maximizes the satisfaction of people's visual comfort needs under different light environments and effectively improves the visual comfort of the indoor light environment.

[0013] Related Technology 2: In the field of photothermal equipment control, patent document CN120312074A proposes a segmented louver control method and system based on non-contact measurement of facial physiological indicators. This system uses an infrared camera to collect user facial video data and extracts facial data features; based on these features, it calculates thermal comfort indicators (such as average facial skin temperature S). skin Based on visual comfort indicators (such as eye-opening degree D), the system determines the user's thermal and visual comfort experience and adjusts the louver angle in segments; thereby adjusting the indoor light and heat equipment under that louver state to regulate the indoor light and heat environment. The entire system includes: an information acquisition module, a data processing module, and an execution module.

[0014] Related Technology 3: In the field of lighting control, patent document CN120499906A discloses a face posture recognition method, an anti-glare lighting control method, a lighting fixture, equipment, and a medium. First, this patent provides a face posture recognition method that collects facial data features and uses a CNN (Convolutional Neural Network) model for training to predict facial posture and facial physiological indicators, thereby controlling the brightness and angle of indoor lighting fixtures to prevent light from directly entering people's line of sight. Second, it develops a lighting control system composed of control elements, lighting fixtures, and a camera. This system can detect changes in people's line of sight and can achieve more efficient glare management according to different locations and activities.

[0015] Related Technology 4: In the field of linkage control technology, patent document CN120610474A discloses a method and system for linkage control of intelligent building equipment based on a large model. This system uses high-precision photosensitive and temperature sensors to collect relevant data on the external and internal environment, including indoor and outdoor light intensity and air temperature. The measured data is used to calculate ISPI (Insolation Shielding Performance Index), IAC (Illumination Adjustment Coefficient), TCC (Thermal Comfort Coefficient), and EEC (Energy Efficiency Coefficient) using machine learning algorithms. By assigning weights to each indicator and setting thresholds for evaluation, an optimal sunshade adjustment strategy is generated and control commands are quickly issued. Simultaneously, the system can monitor the execution effect of the sunshade system and continuously adjust the prediction model and thresholds to further optimize performance.

[0016] Related Technology 5: In the field of architectural design, patent document CN190903581A provides a method and system for dynamic light and heat regulation optimization of building external shading based on co-simulation. First, a building model is constructed, building operating parameters are set, and an external shading calculation model is built. Based on historical meteorological data and operating parameters, the Useful Daylight Illuminance (UDI), Daylight Glare Probability (DGP), and Energy Use Intensity (EUI) for lighting and air conditioning are obtained under different shading regulation thresholds. Subsequently, the optimal opening state of the external shading is obtained through multi-objective optimization, improving the user experience.

[0017] Related Technology Six: In the field of intelligent buildings, CN117742166A invented an intelligent energy-saving building system, including an environmental sensing and adaptive adjustment unit. By setting up various sensors, an environmental sensing network is established to monitor indoor and outdoor environmental parameters in real time. The intelligent lighting unit is equipped with a light sensor to sense indoor and outdoor light intensity and adjust the opening and closing of shading devices as needed. It also provides personalized lighting modes (lamp on / off and brightness) according to user needs and habits. In a further optimized solution, a temperature sensor is installed to monitor indoor and outdoor temperatures and automatically adjust the operation of heating and cooling equipment according to a set temperature range, providing a comfortable indoor light and heat environment for office workers.

[0018] Among the aforementioned technologies, some independently control shading / lighting / air conditioning based on different environmental factors (such as outdoor climate, indoor lighting effect, indoor temperature, etc.) and different optimization indicators (such as light intensity, effective solar utilization coefficient, indoor temperature, building energy consumption, etc.). However, there is a lack of comprehensive control strategies and application effect analysis for achieving the goals of comfortable and healthy light and heat environment and energy conservation. Currently, public buildings suffer from low control levels in actual operation and maintenance. On the one hand, the goal of creating a healthy environment is not considered; on the other hand, each environmental control terminal is controlled separately, ignoring the coupling effect of different environmental parameters in the adjustment process, making it difficult to achieve efficient creation of a comprehensive thermal, humidity, and light environment.

[0019] Specifically, in related technologies one, three, four, and five, only a single object is regulated, and the coupling between indoor light and heat equipment results in poor regulation effects. In related technologies two and six, although shading, lighting, and air conditioning are all regulated, there is a coupling between thermal comfort, visual comfort, and energy consumption. To obtain good indoor natural lighting, the light-transmitting area needs to be increased to improve light comfort and reduce lighting energy consumption, but this also leads to increased indoor solar radiation heat gain. Furthermore, if solar radiation shines directly on people, it can cause increased perceived heat gain, requiring adjustment by the air conditioning system.

[0020] To address the technical challenges of related technologies, this application proposes an intelligent collaborative control method for photothermal equipment that balances comfort, health, and energy conservation. This method involves adjusting building shading to prevent glare, adjusting artificial lighting to meet visual and non-visual comfort illuminance requirements, and adjusting air conditioning set temperatures to balance the impact of solar radiation heat gain. In addition to the horizontal illuminance and glare probability considered in related technologies, this application adds a physiologically equivalent illuminance index to evaluate the physiological effects of light on the human body, i.e., non-visual effects, to create a more comprehensive light environment conducive to human health. On the other hand, building designers typically use air temperature and humidity as control indicators when analyzing thermal environments. Even when considering the impact of radiative heat, they often focus on the long-wave radiation from the building's interior surfaces to personnel. However, in actual office spaces, people are frequently exposed to direct sunlight. In such cases, the solar radiation heat absorbed and released by clothing and skin can generate a strong thermal gain, requiring cooler air for thermal comfort offset correction to maintain indoor comfort. This patent considers the impact of radiative heat gain and achieves coordinated thermal comfort control between shading and air conditioning.

[0021] To truly realize the technical concept of "human factors environmental engineering", this application is guided by systems theory, establishes a research and development system around the climate-building-human-equipment system, and conducts analysis and verification based on the actual workstation usage in office spaces. The same approach can also be applied to any other architectural space.

[0022] Based on the above technical concept, this application proposes an intelligent collaborative control method and system for solar thermal equipment that balances comfort, health, and energy conservation. This application aims to consider health indicators such as light comfort, non-visual lighting, and thermal comfort, simulate and construct a dataset, and use a random forest algorithm to establish an accurate predictive model of the light environment, thermal environment, and energy consumption. Then, using a particle swarm optimization algorithm, with constraints including horizontal illuminance, m-EDI (modified equivalent daylight illuminance), DGP (Daylight Glare Probability), and PMV (Predicted Mean Vote), and with the comprehensive energy consumption of lighting and air conditioning as the optimization objective, it dynamically solves for the optimal collaborative control strategy of shading, lighting fixtures, and air conditioning equipment. Simultaneously, using low-cost, high-precision thermal, humidity, and light environment monitoring equipment, an integrated solar thermal monitoring-control system is built, disseminating the control strategy to the control terminal in real time, achieving efficient creation and intelligent operation and maintenance of a low-carbon, healthy building environment.

[0023] Combination Figures 1 to 4 This application provides a method for intelligent coordinated control of solar thermal equipment that balances comfort, health, and energy saving, including: S100, collect the operating status parameters of each device in the location to be regulated at the current moment and the first outdoor meteorological data; wherein, the first outdoor meteorological data includes the direct normal radiation intensity of the sun, the diffuse horizontal radiation intensity of the sky, the outdoor temperature and humidity, the solar altitude angle and the solar azimuth angle; the operating status parameters include the shading status, the lighting status and the air conditioning set temperature.

[0024] S200, an objective function is established with the goal of minimizing the overall energy consumption of the location to be regulated. Multiple constraints are applied to the objective function to obtain an optimized objective. The objective function consists of a predicted overall energy consumption value and a penalty term for constraint violation. The penalty term is the product of the penalty function and the number of violated constraints. The multiple constraints include constraints on horizontal illuminance, constraints on physiologically equivalent illuminance, constraints on the probability of sunlight glare, and constraints on the average perceived illuminance.

[0025] The objective function is expressed as: , As decision variables, , =[Sunshade opening level, light fixture on level, air conditioning set temperature]. Indicates overall energy consumption. This indicates a penalty for violating the constraints. This indicates the number of illegal constraints. Constraints include: a constraint on horizontal illuminance (≥300 lx); a constraint on physiologically equivalent illuminance (m-EDI ≥ 200 lx); a constraint on the probability of sunlight glare (DGP ≤ 0.35); and a constraint on the average perceived illuminance (PMV ∈ [-0.5, +0.5]). A penalty term is applied to the optimization objective when any constraint is not met. , As a penalty function, in order to strictly ensure the quality of the built environment, this application may adopt a static penalty function and set it to 1000, so that the static penalty value is much greater than the comprehensive energy consumption value, so as to clarify the search direction of the next iteration.

[0026] The evaluation indicators for the lighting environment include horizontal illuminance at workstations, physiologically equivalent illuminance (also known as melanopic physiologically equivalent daylight illuminance), and DGP (displacement gamut). Horizontal illuminance at workstations is determined according to the "Standard for Lighting Design of Buildings" GB 50034-2013, with a horizontal illuminance of 300 lx at a height of 0.75 m selected as the standard for achieving adequate daylighting, which serves as the constraint condition for the horizontal illuminance.

[0027] m-EDI is defined by the International Commission on Illumination (ICI) based on the evaluation metrics listed in the EML (Enhanced Metrics List). This metric involves different wavelengths in the spectrum. The physiological effects of light on the human body, especially its impact on the biological clock, mainly include the influence of light on human physiological rhythms, including circadian rhythms, neuroendocrine function, and neurobehavioral responses. The calculation formula is as follows: ; In the formula, is the spectral response function of retinin. For spectral power density, These are constants related to the standard daylight source D65.

[0028] Multiplying the vertical eye illuminance value by the non-visual conversion factor indirectly yields the non-visual evaluation index value. The non-visual conversion factor for natural light is 0.852. Based on the additivity of m-EDI, the eye m-EDI value can be obtained by combining lighting environment parameters such as daylight and artificial lighting. According to the Chinese Standard for Healthy Building Evaluation (T / ASC 02-2021), the physiological equivalent illuminance is set at 200 lx as the advanced limit requirement for non-visual effects. This control strategy also selects this index and value as the lighting environment requirement to meet non-visual physiological health.

[0029] DGP is selected as ≤0.35 according to the threshold specified in the European daylighting standard EN17037-2018 to meet the light environment requirements for glare evaluation.

[0030] The thermal environment calculation index uses the predicted mean perceived value (PMV). The analysis employs the radiation calculation method from the ASHRAE-55 standard to rapidly and quantitatively calculate the impact of solar radiation on mean radiant temperature. The mean radiant temperature adjustment (MRT) is calculated using the following formula: ; In the formula, The percentage of body surface exposed to environmental radiation (sitting posture = 0.696, standing posture = 0.725). The radiative heat transfer coefficient is expressed in W / m³. 2 ·K; The effective radiation field is expressed in W / m². 2 ; The air temperature is expressed in °C.

[0031] The effective radiant field (ERF) is calculated using the following formula: ; In the formula, , These are long-wave emissivity and long-wave absorptivity, respectively. The value is usually 0.95; This refers to the amount of shortwave solar radiation emitted by the body surface. It is then divided into scattered solar radiation ( The data consists of two parts: direct solar radiation (Edir) and direct solar radiation (W / m²). 2 .

[0032] Scattered solar radiation (E diff Calculate using the following formula: ; In the formula, The proportion of the sky dome within the field of vision of personnel; The intensity of scattered solar radiation received on a horizontal surface, expressed in W / m². 2 ; The solar radiation transmittance of the window system (integrated window and internal shading roller blind). Calculate using the following formula: ; In the formula, For window height, For window width, The distance between a person and a window is represented by meters for all three units.

[0033] Direct solar radiation (E) dir Calculate as follows using the formula: ; In the formula, To expose the projection area of ​​people under direct sunlight; Assuming a human body surface area (approximately 1.8 m²) 2 ); Body proportions exposed to direct sunlight; Direct solar radiation, measured in W / m² 2 ; Total solar transmittance is the ratio of incident shortwave radiation to the total shortwave radiation passing through the glass and shading device.

[0034] refer to Figure 2 As shown, this application constructs datasets corresponding to various prediction models through simulation, considering a multi-dimensional health indicator system that includes thermal comfort, visual comfort, and non-visual comfort. Then, it builds prediction models using a random forest algorithm, providing an optimized foundational database for data-driven intelligent decision-making. Considering the interactive effects of the system, a particle swarm optimization algorithm is employed for multi-objective optimization decision-making, enabling coupled and coordinated control of equipment. Finally, a control system is built to achieve coordinated adjustment of shading, lighting, and air conditioning. This system uses wireless transmission and is deployed on a cloud platform, enabling low-cost and efficient deployment.

[0035] S300, the operating status parameters of each device at the current moment are used as an individual to generate a population and the first outdoor meteorological data are used as initial inputs. Using a pre-trained prediction model and combined with the particle swarm optimization algorithm, the individual in the population is iteratively optimized under the constraint of the optimization objective to obtain the optimal control strategy for the comprehensive light environment, thermal environment and comprehensive energy consumption. The optimal control strategy for the integrated light environment, thermal environment, and integrated energy consumption includes the optimal degree of shading opening, the optimal degree of lighting on, and the optimal air conditioning setting temperature.

[0036] It is worth noting that the pre-trained prediction models in this application include a light environment prediction model, a thermal environment prediction model, and an energy consumption prediction model, all of which were trained using corresponding datasets. These three prediction models can employ the random forest prediction model described in relevant technical documents.

[0037] S400, according to the optimal control strategy and in combination with the operating status parameters of the location to be controlled, control the operating status of each corresponding device in the location to be controlled.

[0038] In one specific embodiment of this application, the training process of the pre-trained prediction model includes: a. By simulating the collection of diverse data from any location and second outdoor meteorological data, and combining each type of data into a dataset; The dataset includes a light environment dataset, a thermal environment dataset, and an energy consumption dataset; the light environment data includes the status of shading on and lighting on; the thermal environment data includes the status of shading on and air conditioning set temperature; and the energy consumption data includes the combined energy consumption data under the status of shading on, lighting on, and air conditioning set temperature.

[0039] b. Using the dataset corresponding to each data point and the second outdoor meteorological data, train the corresponding pre-built prediction model to obtain the pre-trained prediction model. The second outdoor meteorological data includes the intensity of direct solar normal radiation, outdoor temperature and humidity, solar altitude angle, and solar azimuth angle.

[0040] In establishing a random forest prediction model, characteristic values ​​that influence the changes in constraint indices (i.e., horizontal illuminance, m-EDI, DGP) and the optimization objective (comprehensive energy consumption) should be selected. (Reference) Figure 3 Factors affecting its changes include the operating status of indoor solar thermal equipment and outdoor meteorological data. Characteristic values ​​related to the operating status of indoor solar thermal equipment include: shading degree, light switch status / operation rate, and air conditioning set temperature; outdoor meteorological data include: direct solar radiation intensity, diffuse horizontal radiation intensity, outdoor temperature and humidity, and seasonal time (solar altitude angle, azimuth angle).

[0041] Predictive models were established for the light environment, thermal environment, and energy consumption respectively. (Reference) Figure 3 The light environment prediction model's prediction results include horizontal illuminance, m-EDI, and DGP for each workstation. Its inputs are direct solar normal radiation intensity, diffuse sky radiation intensity, solar altitude angle / azimuth angle, shading status, and lighting status. The thermal environment prediction model's output is PMV. Its inputs are direct solar normal radiation intensity, diffuse sky radiation intensity, solar altitude angle / azimuth angle, shading status, and air conditioning set temperature. The energy consumption prediction model's inputs are outdoor temperature and humidity, direct solar normal radiation intensity, diffuse sky radiation intensity, solar altitude angle / azimuth angle, shading status, lighting status, and air conditioning set temperature. Its output is the overall energy consumption.

[0042] This application trains a pre-built light environment prediction model using a light environment dataset and second outdoor meteorological data; a pre-built thermal environment prediction model using a thermal environment dataset and outdoor meteorological data; and a pre-built thermal environment prediction model using an energy consumption dataset and outdoor meteorological data. During training, based on the complex correlation between light and thermal environment evaluation indicators, potential energy consumption influencing factors, and indoor and outdoor operating condition data, each dataset is preprocessed and then divided into a test set and a training set. Each prediction model is trained and evaluated. During training, the true labels of the input data can be directly collected, namely, the horizontal illuminance, m-EDI, DGP, PMV, and comprehensive energy consumption at each workstation. These can be used as true labels to generate prediction models for each optimized indicator. The accuracy of each prediction model is verified using a test set. The accuracy parameters for verifying each prediction model can be the mean square error, root mean square error, mean absolute error, and coefficient of determination R. 2 .

[0043] In one specific embodiment of this application, the step of simulating the collection of diverse data from any location and second outdoor meteorological data, and then combining each type of data into a dataset, includes: a1. Establish a spatial model of any location and simulate a second outdoor meteorological data outside the spatial model; In the process of simulating and collecting data on the site to be regulated, the first step is to establish a spatial model of the site.

[0044] a2. Under the spatial model, the light combination, heat combination, and energy consumption combination conditions of different shading positions, lamp on status, and air conditioning set temperature are simulated time-by-time to obtain diverse data at each time point; the diverse data are preprocessed and then combined into a dataset.

[0045] In one specific embodiment of this application, the simulation of light combination conditions, heat combination conditions, and energy consumption combination conditions under different shading positions, lighting fixture on-states, and air conditioning set temperatures is performed time-by-time under the spatial model to obtain diverse data at each time point; the diverse data is preprocessed, and then the dataset is composed of: a21, under the spatial model, the light combination conditions of different shading positions and lamp on states are simulated at the current moment to obtain the light environment data of each light condition combination at the current moment, and these are combined into a light environment dataset. Within the aforementioned spatial model, the operating conditions of shading and lighting fixtures are combined. This includes different shading opening angles / pull-down rates, and the on / off states / brightness of the lighting fixtures. Subsequently, lighting simulations are performed for different light combination conditions to obtain lighting environment data.

[0046] a22, under the space model, simulate the thermal combination conditions of different shading positions and air conditioning set temperature at the current moment, obtain the thermal environment data of each thermal condition combination at the current moment, and compose them into a thermal environment dataset. a23, under the spatial model, simulate the energy consumption combination conditions of different shading positions, lamp on status and air conditioning set temperature at the current moment, obtain the energy consumption data of each energy consumption combination condition at the current moment, and form them into an energy consumption dataset.

[0047] The energy consumption in this application includes lighting energy consumption, cooling energy consumption, and heating energy consumption. The sum of these three energy consumptions is the comprehensive energy consumption. Specifically, the personnel schedule, lighting schedule, air conditioning schedule, and other thermal disturbance factors can be set in the simulation software to calculate the comprehensive energy consumption, obtain energy consumption data under different shading, lighting, and air conditioning combination adjustment conditions throughout the year, and then preprocess the data to form an energy consumption dataset.

[0048] In one specific embodiment of this application, S300 includes: S310, in the initial iteration, the operating state parameters of each device at the current moment are taken as an individual, and multiple sets of motion state parameters are randomly generated as individuals; all individuals are combined into an initial population; S320 takes external meteorological data as the initial input, and then inputs it into the corresponding pre-trained prediction model to obtain the illuminance, comprehensive energy consumption and PMV of the initial iteration. S330, the illuminance, comprehensive energy consumption, and PMV of the initial iteration are fed back into the optimization objective to calculate the fitness value of each individual, and in the subsequent current iteration, the particle swarm optimization algorithm is used to intelligently update the population based on the fitness value to generate the population of the current iteration; the population of the current iteration is input into the pre-trained prediction model to obtain the illuminance, comprehensive energy consumption, and PMV corresponding to each individual; This step calculates the penalty term for violating constraints based on illuminance, comprehensive energy consumption, and PMV, and feeds the comprehensive energy consumption and the penalty term for violating constraints back into the optimization objective.

[0049] S340, the illuminance, comprehensive energy consumption and PMV corresponding to each individual are fed back to the optimization objective, and S330 is repeated to solve the optimization objective until the maximum number of iterations is reached. The operating state parameters corresponding to the individual with the best fitness value from the last generation population are selected as the optimal control strategy for comprehensive light environment, thermal environment and comprehensive energy consumption.

[0050] refer to Figure 4 As shown, the particle swarm optimization algorithm is configured with the following parameters: The input conditions are set as follows: the current solar altitude / azimuth angle, direct solar radiation intensity, diffuse horizontal radiation intensity, outdoor temperature, outdoor relative humidity, and equipment operating parameters. These are the input conditions for the particle swarm optimization algorithm and the prerequisites for performing the optimization search.

[0051] Define the search space: The search space refers to the scope of the population's work, that is, the range of possible decision variables, including the adjustable location of the shading, the availability of lighting fixtures, and the temperature range set by the air conditioner as the set of all possible actions.

[0052] Setting constraints: Comfortable light and thermal environments are prerequisites that the control strategy of this application must meet. Threshold constraints should be imposed on this indicator to ensure that the search conditions in the later optimization process are maintained within the threshold range.

[0053] During the solution process, the population size is set and the proportion of particles of different functions is divided. Then, the number of search iterations is set. The larger the number of iterations, the more stable the optimization result tends to be, but the computation time will increase. The number of iterations can be adjusted according to the target requirements. A global search is performed based on the action space set above to obtain the control strategies of shading, lighting, and air conditioning at that moment as the output result.

[0054] This application also provides an intelligent collaborative control system for solar thermal equipment that balances comfort, health, and energy efficiency, including: Monitoring sensors are used to collect the operating status parameters of each device in the controlled area at the current moment, as well as the first outdoor meteorological data. A cloud platform is used to establish an objective function with the goal of minimizing the comprehensive energy consumption of the site to be regulated. After constraining the objective function with multiple constraints, an optimization objective is obtained. The operating status parameters of each device at the current moment are used as individuals to generate a population, and the first outdoor meteorological data is used as the initial input. Using a pre-trained prediction model and combined with a particle swarm optimization algorithm, each individual in the population is iteratively optimized under the constraints of the optimization objective to obtain the optimal regulation strategy for comprehensive light environment, thermal environment and comprehensive energy consumption. The control module is used to control the operating status of each device in the controlled location according to the optimal control strategy and in combination with the operating status parameters of the controlled location.

[0055] The control module of this application can be set on a cloud platform or on the control system of the location to be controlled, both of which can achieve the control purpose conceived in this application.

[0056] This application provides a method and system for intelligent collaborative control of solar thermal equipment that balances comfort, health, and energy conservation. The method includes: collecting the operating status parameters of each device in the controlled environment at the current moment, as well as first outdoor meteorological data; establishing an objective function with the goal of minimizing the overall energy consumption of the controlled environment, and obtaining an optimization objective by constraining the objective function with multiple constraints; using the operating status parameters of each device at the current moment as individuals to generate a population, and the first outdoor meteorological data as initial inputs; using a pre-trained prediction model combined with a particle swarm optimization algorithm, iteratively optimizing each individual in the population under the constraints of the optimization objective to obtain the optimal control strategy for the overall light environment, thermal environment, and overall energy consumption; and controlling the operating status of the corresponding devices in the controlled environment according to the optimal control strategy and in conjunction with the operating status parameters of the controlled environment. This application can achieve intelligent control that balances comfort, health, and energy conservation, realizing the efficient creation and intelligent operation and maintenance of a low-carbon and healthy building environment.

[0057] See Figure 3 The intelligent collaborative control system for solar thermal equipment that combines comfort, health, and energy saving is deployed on a cloud platform. The pre-trained prediction model files and optimization code are imported into the cloud platform backend to generate control instructions and send them to the terminal to achieve intelligent control.

[0058] To verify the control effect of this application, this application takes a typical office building in Nanjing as an example and selects one south-facing multi-person office for implementation verification. The room was modeled using Rhino software. The room uses knitted material internal sunshade roller blinds, has multiple workstations, and uses multiple LED lights with multiple circuits for on / off control. The Grasshopper plugin was used to set the performance parameters of the room's envelope, furniture arrangement, and roller blinds.

[0059] The simulation process is as follows: Figure 5 As shown, the HB-Radiance plugin was first used to set up analysis grids for the working surfaces and facial positions of each workstation. The annual lighting effect of each workstation under different roller blind pull-down degrees was simulated to obtain the hourly horizontal illuminance, eye vertical illuminance, and DGP value of each workstation over 8760 hours.

[0060] The room's lighting fixtures were configured using Radiance software, and the illuminance supplementation effect under different switching conditions was simulated. When setting the sky condition, a no-sky model (pure darkness) was selected to verify the illuminance under purely artificial lighting. Based on the previously simulated natural lighting effect, the illuminance values ​​under different switching conditions were superimposed to obtain the horizontal illuminance, m-EDI, and DGP values ​​under the shading and lighting fixture adjustment conditions. These values ​​were then used as training data for subsequent lighting environment models.

[0061] Call the LB Indoor Solar MRT calculation module in Grasshopper and input the original long-wave radiation temperature of the building's interior surface, typically taken as the air conditioning temperature commonly set in summer and winter (26°C in summer, 23°C in winter). Set the relevant parameters in the formula proposed for the specific scheme, including f. eff f bes f svv T sol Using tools such as SHARP and linking parameters with epw files in the EnergyPlus meteorological database, this calculator can calculate the MRT (Mean Radiant Temperature) for all times of the year.

[0062] The PMV calculation module is then invoked, inputting relevant calculation parameters including: air temperature (i.e., air conditioner set temperature), relative humidity (60% in summer, 40% in winter), wind speed (0.1 m / s), metabolic rate (1.1 Mt when typing while sitting), and clothing thermal resistance (0.5 clo in summer, 1.0 clo in winter) to calculate the PMV value at the current moment. This module can perform batch calculations throughout the year based on meteorological data and corrected radiation temperature. The PMV results obtained at each air conditioner set temperature are used as training data for subsequent thermal environment prediction models.

[0063] The `Random` module is invoked, which assigns random values ​​to air conditioning, lighting, and blind schedules. This generates random combinations of blind pull-down rates, lighting activation rates, and air conditioning set temperatures at various times, producing a large dataset for energy consumption prediction. Simultaneously, other thermal disturbance factors are set based on room usage, such as natural / mechanical ventilation, occupancy rate, equipment schedules, and heat dissipation from people and equipment. OpenStudio modules are used to calculate energy consumption, reading hourly lighting and air conditioning energy consumption data as training data for subsequent energy consumption prediction models.

[0064] The obtained simulation data were organized into an Excel file, retaining only the data labels and corresponding values. The file was divided into three datasets: a light environment dataset, a thermal environment dataset, and an energy consumption dataset. Each dataset includes feature variables and target values. The light environment dataset's feature variables include direct solar radiation intensity, diffuse horizontal irradiance, solar altitude / azimuth angle, shading status, and lighting status; the predicted values ​​are horizontal illuminance, m-EDI, and DGP for each workstation. The thermal environment dataset's feature variables include direct solar radiation intensity, diffuse horizontal irradiance, solar altitude / azimuth angle, shading status, and air conditioning set temperature; the predicted value is PMV for each workstation. The energy consumption dataset's feature variables include outdoor temperature and humidity, direct solar radiation intensity, diffuse horizontal irradiance, solar altitude / azimuth angle, shading status, lighting status, and air conditioning set temperature; the predicted value is the combined energy consumption for lighting and air conditioning.

[0065] The sklearn package in Python was used, and the Random Forest Regressor algorithm was selected to solve the regression problem. In the light environment prediction model, because multiple dimensions need to be predicted, the Multi Output Regressor wrapper was additionally imported to predict multiple regression values ​​within a single prediction model. Subsequently, the training and test sets were split, and evaluation metrics were set. Three prediction models were obtained by reading three Excel spreadsheets. Furthermore, when the evaluation metrics are within a reasonable range, the model's performance is considered relatively reliable. It should be noted that there are no absolute thresholds for the model's evaluation metrics; they should be determined based on different prediction results.

[0066] An optimization function is established with the goal of minimizing the building's overall energy consumption, while also considering constraints on indoor lighting environment and thermal comfort. The penalty function method is employed to handle the multi-constraint optimization problem, taking into account the actual control characteristics of the equipment, and the continuous optimization variables are discretized and encoded. Roller blinds and lighting fixtures are controlled in stages, and the air conditioning system provides continuous adjustment within a certain temperature range, with an accuracy set to 0.1℃.

[0067] Three pre-trained prediction models were integrated. Input variables included solar altitude / azimuth angle, direct solar radiation intensity, diffuse horizontal radiation intensity, outdoor temperature, outdoor relative humidity, blind pull-down rate, luminaire activation rate, and air conditioning set temperature. Output parameters included illuminance values ​​at each location, m-EDI, DGP, PMV, and room lighting and air conditioning energy consumption.

[0068] Particle swarm optimization (PSO) algorithm parameter settings include population size, variable dimension, search lower bound, search upper bound, and maximum number of iterations. This application exemplifies the dung beetle optimization algorithm to describe the specific process. The dung beetle optimization algorithm is a swarm intelligence optimization algorithm inspired by the natural behaviors of dung beetles, such as rolling balls, foraging, and reproduction. It can be used to solve complex problems such as path planning and parameter optimization. (See reference...) Figure 4 Follow these steps: Population initialization: Randomly generate an initial dung beetle population within the decision space.

[0069] Fitness assessment: Call the objective function for each individual to determine the degree of constraint violation.

[0070] Location update: Individual locations are updated based on four behaviors of dung beetles: rolling balls, breeding, foraging, and stealing.

[0071] Boundary handling: Ensure the new position is within the range of variable constraints.

[0072] Elite preservation: preserving the best individuals of the present generation for the next.

[0073] Iterative convergence: Repeat the above steps until the maximum number of iterations is reached.

[0074] The continuous optimization results are decoded into control commands corresponding to the optimal control strategy and output. The optimal control strategy includes the optimal shutter opening, represented as... The optimal luminaire opening is expressed as: The optimal air conditioning set temperature is expressed as: ;in, This indicates rounding to the nearest integer. This indicates the continuous change in the roller blind's volume. This indicates the continuous change in the quantity of light fixtures. This indicates the continuous change in air conditioning volume. The number of discrete stops for roller shutter control; This represents the discretization step size for lighting control; 1 represents the output precision, retaining one decimal place.

[0075] This application establishes a corresponding intelligent collaborative control system for solar thermal equipment within the building, balancing comfort, health, and energy efficiency. This system includes an indoor solar thermal environment monitoring system, an energy consumption monitoring system, an electric roller shutter control system, a lighting control system, and an air conditioning control system. The indoor solar thermal monitoring system can monitor and store data in real time, including illuminance, color temperature, PM2.5, CO2, temperature, and humidity. The energy consumption monitoring system can monitor office lighting and air conditioning power consumption in real time, performing energy consumption analysis through time and structural comparisons. The electric roller shutter control system allows direct operation of the shutter's opening and closing via a graphical interface on the doorway control panel or through a platform; the shutter opening degree is stored in real time on the platform. The lighting control system enables stepless color and temperature adjustment for single-loop lighting within the office; light switch records, illuminance values, and color temperature values ​​are stored on the platform. The air conditioning control system monitors and controls parameters such as temperature, fan speed, mode, and operation of the air conditioning system.

[0076] Based on the aforementioned intelligent collaborative control system for solar thermal equipment that balances comfort, health, and energy efficiency, this application also establishes an integrated solar thermal monitoring and control platform, as shown in the attached document. Figure 6 As shown, firstly, low-cost, multi-functional environmental sensors are used to collect parameters such as temperature, humidity, illuminance, and physiological equivalent illuminance in the area where people are located. Secondly, the data is wirelessly uploaded to a cloud platform for processing, and then displayed through a web-based user interface. Simultaneously, the monitoring data provides information to various indoor environmental control terminals via API (Application Programming Interface), including air conditioning, shading, and lighting control terminals closely related to the thermal, humidity, and light environment. Considering multiple objectives such as human comfort and health, energy conservation, and carbon reduction, a particle swarm optimization algorithm is used to calculate the optimal control strategy for each control terminal, and the control commands are sent to the terminals for execution, achieving an integrated and efficient creation of a low-carbon, thermal, humidity, and light-healthy building environment.

[0077] This application's intelligent collaborative control system for solar thermal equipment, which balances comfort, health, and energy efficiency, has been applied in two offices in a typical office building in Nanjing. Integrated thermal, humidity, and solar monitoring equipment is placed at each workstation to collect various environmental parameters of the area where personnel are active. Simultaneously, monitoring equipment is placed on the office windowsills, with the probes facing outwards, to collect information on natural illuminance near the windows. The air conditioning, shading, and lighting in the office can all be remotely adjusted via a platform. The air conditioning is a multi-split system, allowing for on / off switching, temperature setting, and fan speed adjustment; the shading uses electric roller blinds with stepless adjustment of opening degree from 0-100%; and the illuminance and correlated color temperature (2900-6500 K) of the lighting fixtures are stepless.

[0078] Based on the aforementioned data monitoring and intelligent control methods, a building information modeling (BIM) platform was further developed. The model displays workstations, monitoring equipment, and control equipment according to the actual office space layout. The main interface displays real-time illuminance, physiological equivalent illuminance, temperature, and humidity information collected by each monitoring device. Users can access the device control interface through the BIM model to adjust air conditioning, shading, and lighting equipment. In addition, personnel sensors, CO2 concentration sensors, and power monitoring sensors are installed in the room; all collected data is integrated into the platform for convenient viewing and downloading.

[0079] As attached Figure 3 As shown, the trained prediction model file and optimized code are imported into the monitoring platform backend to generate control commands, which are then sent to the end-points to achieve intelligent control. Small meteorological monitoring stations are deployed outdoors to measure environmental data such as solar radiation intensity, wind direction, wind speed, temperature, humidity, aerosol concentration, PM2.5, and PM10. The monitoring platform reads the measured direct solar radiation intensity, diffuse horizontal radiation intensity, temperature, and relative humidity at that moment, and makes control responses based on the current outdoor climate conditions. Internally, the system performs a global search and calculation of the roller blind position, lighting fixture opening, and air conditioning set temperature. This ensures that the roller blind position, after prediction, achieves glare-free operation; the lighting fixture opening ensures that each workstation meets the horizontal and m-EDI illuminance requirements; and the air conditioning set temperature meets the thermal comfort requirements of the most unfavorable point near the window (wherein, the most unfavorable thermal comfort point should be the most unfavorable workstation where human adaptive adjustment is impossible under the current cooling / heating demand, such as in summer when cooling demand is high, the workstation near the window receives the strongest solar radiation and cannot further reduce the thermal resistance of clothing). Furthermore, the system internally calculates the adjustment condition with the lowest fitness value in the current iteration using the particle swarm optimization algorithm, repeats the above optimization process until the maximum number of iterations is reached, outputs the optimal control strategy and feeds it back to the control terminal, and the terminal adjustment status is recorded in real time to the air monitoring platform for real-time viewing and download.

[0080] In summary, this application provides an intelligent collaborative control method and system for solar thermal equipment that balances comfort, health, and energy conservation. It considers factors such as shading to prevent glare, artificial lighting to adjust physiologically equivalent illuminance to the eyes and horizontal illuminance at workstations, air conditioning temperature settings, and the effects of solar radiation heat gain. Compared to related technologies, this application is applicable to the control of solar thermal equipment in similar locations. It not only considers conventional visual environment indicators and thermal comfort evaluation indicators but also takes into account the lighting environment requirements under non-visual effects and the corrected PMV after solar radiation heat gain. It flexibly adjusts shading, lighting, and air conditioning temperatures according to workstation usage to ensure a healthy and comfortable environment for indoor occupants. This control method covers more dimensions of health indicators and responds to the technical needs of human factors engineering. This application considers the coupling between healthy environment and energy consumption, and treats shading, lighting and air conditioning as a coupled whole for joint control. It uses the prediction model of random forest algorithm combined with particle swarm optimization algorithm to construct a real-time response to outdoor meteorological conditions for coordinated control of light and heat environment energy-saving optimization strategy. By globally searching different combinations of the three operating conditions and back-deriving the optimal control strategy, real-time dynamic linkage response between equipment is realized. This solution significantly reduces the comprehensive operating energy consumption of lighting and air conditioning systems while simultaneously meeting the multi-dimensional healthy environment requirements of visual comfort, non-visual comfort and thermal comfort, thereby achieving synergistic optimization of healthy environment creation and building energy conservation and consumption reduction.

[0081] The above description is merely a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of protection of this specification.

[0082] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Without further limitation, an element qualified by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for intelligent collaborative control of solar thermal equipment that balances comfort, health, and energy saving, characterized in that: include: Collect the operating status parameters of each device at the site to be regulated at the current moment, as well as the first outdoor meteorological data; An objective function is established with the goal of minimizing the overall energy consumption of the location to be regulated. Multiple constraints are applied to this objective function to obtain an optimized objective. These constraints include constraints on horizontal illuminance, physiologically equivalent illuminance, solar glare probability, and the predicted average perceived value (PMV). The first outdoor meteorological data includes direct solar normal radiation intensity, diffuse horizontal irradiance, outdoor temperature and humidity, solar altitude angle, and solar azimuth angle. The operating status parameters include shading status, lighting status, and air conditioning set temperature. The predicted average perceived value (PMV) is calculated using the radiation calculation method in the ASHRAE 55 standard to determine the impact of solar radiation on the average radiant temperature. The operating status parameters of each device at the current moment are used as individuals to generate a population, and the first outdoor meteorological data is used as the initial input. Using a pre-trained prediction model and combined with the particle swarm optimization algorithm, the individual in the population is iteratively optimized under the constraint of the optimization objective to obtain the optimal control strategy for the comprehensive light environment, thermal environment and comprehensive energy consumption. According to the optimal control strategy and in combination with the operating status parameters of the site to be controlled, the operating status of each corresponding device in the site to be controlled is controlled.

2. The intelligent collaborative control method for solar thermal equipment that balances comfort, health, and energy saving as described in claim 1, characterized in that, The objective function consists of the comprehensive energy consumption prediction value and the constraint violation penalty term, which is the product of the penalty function and the number of constraint violations.

3. The intelligent collaborative control method for solar thermal equipment that balances comfort, health, and energy saving as described in claim 1, characterized in that, The training process of the pre-trained prediction model includes: By simulating the collection of diverse data from any location and second outdoor meteorological data, each data item is combined into a dataset; The pre-built prediction model is trained using the dataset corresponding to each data point and the second outdoor meteorological data to obtain the pre-trained prediction model.

4. The intelligent collaborative control method for solar thermal equipment that balances comfort, health, and energy saving as described in claim 3, characterized in that, The process of simulating the collection of diverse data from arbitrary locations, along with second outdoor meteorological data, and combining each type of data into a dataset includes: Establish a spatial model of any location and simulate a second outdoor meteorological data outside the spatial model; Under the aforementioned spatial model, time-by-time simulations are performed on light combination conditions, heat combination conditions, and energy consumption combination conditions for different shading positions, lighting status, and air conditioning set temperatures to obtain diverse data at each time point; the diverse data are preprocessed and then assembled into a dataset.

5. The intelligent collaborative control method for solar thermal equipment that balances comfort, health, and energy saving as described in claim 4, characterized in that, The simulation is performed time-by-time under the spatial model to obtain diverse data for light combination, heat combination, and energy consumption combination conditions under different shading positions, lamp on status, and air conditioning set temperature. The diverse data are preprocessed and then combined into a dataset, which includes: Under the aforementioned spatial model, the light combination conditions with different shading positions and luminaire on-state are simulated at the current moment to obtain the light environment data of each light combination condition at the current moment, and these data are combined into a light environment dataset. Under the spatial model, the thermal combination conditions of different shading positions and air conditioning set temperature are simulated at the current moment to obtain the thermal environment data of each thermal combination condition at the current moment, and these are combined into a thermal environment dataset. The energy consumption combination conditions of different shading positions, lighting status and air conditioning set temperature are simulated at the current time under the spatial model to obtain the energy consumption data of each energy consumption combination condition at the current time, and these data are combined into an energy consumption dataset.

6. The intelligent collaborative control method for solar thermal equipment that balances comfort, health, and energy saving as described in claim 1, characterized in that, The process involves using the current operating status parameters of each device as an individual to generate a population, along with the first outdoor meteorological data as initial input. Using a pre-trained prediction model and a particle swarm optimization algorithm, iterative optimization is performed on each individual in the population under the constraints of the optimization objective to obtain the optimal control strategy for comprehensive light environment, thermal environment, and comprehensive energy consumption. In the initial iteration, the operating state parameters of each device at the current moment are treated as an individual, and multiple sets of motion state parameters are randomly generated as individuals; all individuals are then combined into an initial population. External meteorological data is used as the initial input, which is then fed into the corresponding pre-trained prediction model to obtain the illuminance, comprehensive energy consumption, and PMV for the initial iteration. The illuminance, comprehensive energy consumption, and PMV of the initial iteration are fed back into the optimization objective to calculate the fitness value of each individual. In the subsequent current iteration, the particle swarm optimization algorithm is used to intelligently update the population based on the fitness value to generate the population of the current iteration. The population of the current iteration is input into the pre-trained prediction model to obtain the illuminance, comprehensive energy consumption, and PMV corresponding to each individual. The illuminance, comprehensive energy consumption, and PMV corresponding to each individual are fed back into the optimization objective, and the optimization objective is solved repeatedly until the maximum number of iterations is reached. The operating state parameters corresponding to the individual with the best fitness value in the last generation population are selected as the optimal control strategy for comprehensive light environment, thermal environment, and comprehensive energy consumption.

7. The intelligent collaborative control method for solar thermal equipment that balances comfort, health, and energy saving as described in claim 6, characterized in that, The step of feeding back the illuminance, comprehensive energy consumption, and PMV of the initial iterations into the optimization objective includes: The penalty term for violating the constraints is calculated based on illuminance, comprehensive energy consumption, and PMV, and the comprehensive energy consumption and the penalty term for violating the constraints are fed back into the optimization objective.

8. The intelligent collaborative control method for solar thermal equipment that balances comfort, health, and energy saving as described in claim 1, characterized in that, The optimal control strategy for the integrated light environment, thermal environment, and overall energy consumption includes the optimal degree of shading activation, the optimal degree of lighting activation, and the optimal air conditioning setting temperature.

9. A smart collaborative control system for solar thermal equipment that balances comfort, health, and energy efficiency, characterized in that: include: Monitoring sensors are used to collect the operating status parameters of each device in the controlled area at the current moment, as well as the first outdoor meteorological data. A cloud platform is used to establish an objective function aimed at minimizing the overall energy consumption of the location to be regulated. Multiple constraints are applied to this objective function to obtain an optimized target. The current operating status parameters of each device are used as individuals to generate a population, along with the first outdoor meteorological data as initial input. A pre-trained prediction model, combined with a particle swarm optimization algorithm, is used to iteratively optimize each individual in the population under the constraints of the optimized target, resulting in the optimal regulation strategy for the overall light environment, thermal environment, and overall energy consumption. The multiple constraints include constraints on horizontal illuminance, physiologically equivalent illuminance, solar glare probability, and the predicted average perceived value (PMV). The first outdoor meteorological data includes direct solar radiation intensity, diffuse horizontal irradiance, outdoor temperature and humidity, solar altitude angle, and solar azimuth angle. The operating status parameters include shading status, lighting status, and air conditioning set temperature. The predicted average perceived value (PMV) is calculated using the radiation calculation method in the ASHRAE 55 standard to determine the impact of solar radiation on the average radiant temperature. The control module is used to control the operating status of each device in the controlled location according to the optimal control strategy and in combination with the operating status parameters of the controlled location.

Images