Building energy-saving management system and method based on Internet of Things

Abstract

The invention relates to the technical field of building energy saving, in particular to a building energy-saving management system and method based on the Internet of Things. The method comprises the following steps: acquiring a target architectural design drawing; building structure feature point recognition is carried out on the target building design drawing, three-dimensional space point cloud modeling is carried out, and a building three-dimensional structure model is constructed; building environment illumination parameters and personnel flow monitoring parameters are collected based on multiple sensor nodes; environment light intensity space distribution analysis is carried out on the building environment illumination parameters, then dynamic light intensity distribution rendering is carried out, and an environment light intensity distribution rendering model is constructed; and according to the building three-dimensional structure model, carrying out regional use scene analysis on the environment light intensity distribution rendering model, and carrying out optimal time sequence illumination demand fitting so as to construct an optimal illumination demand time sequence curve of each region. The energy consumption utilization rate of the building is increased, and accurate equipment regulation and control are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of building energy conservation, and in particular to a building energy conservation management system and method based on the Internet of Things. Background Art

[0002] As the global energy crisis and environmental problems become increasingly severe, improving building energy efficiency has become an important issue in promoting sustainable development. As one of the main areas of energy consumption, the efficiency of building energy management is directly related to the country and society's energy resource utilization and carbon emission control. Traditional building energy-saving management methods mostly rely on manual operation and regular inspections, usually relying on manual recording and adjusting the operating status of equipment one by one. There are problems such as delayed information feedback, untimely data processing, and serious energy waste, making it difficult to achieve efficient, accurate, and real-time energy management and control.

[0003] In recent years, with the rapid development of information technology and Internet of Things technology, many buildings have introduced Internet of Things technology for energy-saving management. Internet of Things technology uses sensors, smart devices and cloud computing to achieve real-time monitoring, data collection and intelligent analysis of energy consumption inside buildings, greatly improving the automation and intelligence level of energy management. Various types of equipment inside the building (such as air conditioning, lighting, elevators, HVAC systems, etc.) are connected to the central control platform through networked sensors, and real-time transmission of operating status and energy consumption data provides more comprehensive and accurate information support for energy-saving management.

[0004] However, although the building energy-saving management technology based on the Internet of Things has gradually matured, it still faces some challenges in practical applications. For example, there are many types of internal equipment in buildings, and their functions are complex. How to achieve efficient coordination between different systems; how to handle huge and multi-dimensional data volumes, conduct effective data analysis and decision support; how to deal with dynamically changing usage environments and emergencies, etc., are all key issues that need to be solved in the current building energy-saving management system. Therefore, how to establish a more intelligent and automated building energy-saving management method on the Internet of Things platform has become a hot topic in current research and application. Summary of the invention

[0005] In order to solve the above technical problems, the present invention proposes a building energy-saving management system and method based on the Internet of Things to solve at least one of the above technical problems.

[0006] To achieve the above object, the present invention provides a building energy-saving management method based on the Internet of Things, comprising the following steps:

[0007] Step S1: obtaining a target building design drawing; identifying building structure feature points of the target building design drawing, performing three-dimensional space point cloud modeling, and constructing a three-dimensional building structure model;

[0008] Step S2: Collect building environment lighting parameters and personnel flow monitoring parameters based on multiple sensor nodes; perform ambient light intensity spatial distribution analysis on the building environment lighting parameters, then perform dynamic light intensity distribution rendering, and construct an ambient light intensity distribution rendering model;

[0009] Step S3: Perform regional usage scenario analysis on the ambient light intensity distribution rendering model according to the three-dimensional structural model of the building, and perform optimal timing lighting demand fitting, so as to construct the optimal lighting demand timing curve for each area;

[0010] Step S4: Calculate the optimal light source compensation in multiple time periods based on the optimal lighting demand time series curve of each area, dynamically control the building lighting equipment, and construct a multi-time regional light source compensation control strategy;

[0011] Step S5: predicting the regional temperature change trend of the personnel flow monitoring parameters according to the three-dimensional structural model of the building, making intelligent temperature control demand decisions, and building a space intelligent temperature control strategy;

[0012] Step S6: Perform intelligent control of building equipment and collaborative reinforcement learning based on the multi-period regional light source compensation control strategy and the space intelligent temperature control strategy, and build an intelligent energy consumption control model to perform building energy-saving management operations.

[0013] The present invention accurately restores the three-dimensional structure of the building through the recognition of building structure feature points and three-dimensional space point cloud modeling, and provides an accurate building model for subsequent energy-saving management. The construction of the three-dimensional structure model of the building is helpful for an in-depth understanding of the spatial layout and structural characteristics of the building, and provides reliable basic data for energy-saving management decisions. The building environment lighting parameters are analyzed and dynamic light intensity distribution rendering is performed to accurately simulate the lighting conditions inside the building, which helps to understand the spatial distribution of light intensity. The construction of the ambient light intensity distribution rendering model helps to optimize the lighting environment inside the building, improve comfort and potentially reduce unnecessary lighting energy consumption. The lighting requirements are analyzed according to the building structure model, and the optimal lighting requirement timing curve for each area is constructed. Personalized lighting plans are formulated according to the functions and requirements of different areas. The construction of the optimal lighting requirement timing curve helps to rationally utilize light source resources, improve lighting efficiency, and meet the lighting requirements of different areas in the building at the same time. Based on the optimal lighting demand time series curve, multi-period light source compensation calculations are performed, and a dynamic control strategy for building lighting equipment is constructed to achieve a balance between lighting demand and energy consumption. A multi-period regional light source compensation control strategy is constructed to help optimize the operation of building lighting equipment, reduce energy waste, and improve energy-saving effects. According to the personnel flow monitoring parameters, the regional temperature change trend is predicted, and a space intelligent temperature control strategy is constructed to adjust the temperature according to real-time demand, improve comfort and save energy. The construction of an intelligent temperature control strategy helps to optimize the internal temperature control of the building, improve energy utilization efficiency, and reduce energy consumption costs. Combined with light source compensation control and intelligent temperature control strategies, intelligent regulation and reinforcement learning of building equipment are carried out, and an intelligent energy consumption regulation model is constructed to achieve dynamic energy-saving management. The construction of an intelligent energy consumption regulation model helps to monitor and adjust the operating status of building equipment in real time, minimize energy consumption, improve energy-saving effects, and achieve building energy-saving management goals.

[0014] Preferably, step S1 comprises the following steps:

[0015] Step S11: Obtaining a target building design drawing;

[0016] Step S12: Identify the architectural structural feature points of the target architectural design drawing and mark a plurality of structural feature points;

[0017] Step S13: performing spatial layout distribution analysis on a plurality of structural feature points to generate spatial layout distribution data;

[0018] Step S14: performing regional geometry calculation on the target building design drawing to generate multiple regional geometry data in the building;

[0019] Step S15: Perform three-dimensional spatial point cloud modeling on the geometric data of multiple areas in the building according to the spatial layout distribution data to construct a three-dimensional structural model of the building.

[0020] The present invention obtains the target building design drawing as the first step in establishing energy-saving management, provides basic data on building structure and design, and provides a basis for subsequent analysis and optimization. By identifying and marking building structure feature points, the key structural information of the building is accurately captured, which helps to understand the structural characteristics and strength distribution of the building, and provides a basis for energy-saving management. The spatial layout distribution of multiple structural feature points is analyzed to reveal the overall characteristics of the internal structure of the building, which helps to understand the impact of the internal layout of the building on energy utilization and lighting. The regional geometry calculation of the building design drawing generates detailed regional geometry data, which provides necessary spatial information for subsequent energy utilization and lighting design. Three-dimensional space point cloud modeling is performed based on the spatial layout distribution data and the regional geometry data. Construction of a three-dimensional structural model of the building helps to accurately present the three-dimensional structure and spatial layout of the building. By establishing an accurate three-dimensional structural model, energy utilization analysis, lighting design and air-conditioning system layout can be better performed, thereby improving the accuracy and efficiency of energy-saving management.

[0021] Preferably, the specific steps of step S2 are:

[0022] Step S21: Collecting building environment lighting parameters and personnel flow monitoring parameters based on multiple sensor nodes;

[0023] Step S22: positioning the multi-sensor nodes in the internal space of the building to generate the spatial position coordinates of each node;

[0024] Step S23: Calculating the illumination intensity of the building environment illumination parameters to generate an ambient illumination intensity value;

[0025] Step S24: performing an ambient light intensity spatial distribution analysis on the ambient light intensity value based on the spatial position coordinates of each node to generate building ambient light intensity spatial distribution data;

[0026] Step S25: Perform dynamic light intensity distribution rendering on the building environment light intensity spatial distribution data to construct an environment light intensity distribution rendering model.

[0027] The present invention collects building environment lighting parameters and personnel flow monitoring parameters through multiple sensor nodes, monitors the state of the building's internal environment in real time, and the collected data can be used to analyze the building's energy utilization and personnel activity patterns, providing basic data for subsequent energy-saving management. Positioning the spatial position coordinates of each sensor node helps to establish an accurate model of the building's internal spatial structure. Position information helps optimize sensor layout and improve the accuracy and coverage of data collection. Through light intensity calculation, the lighting conditions of different areas inside the building are obtained, and the characteristics of light distribution are understood. These data are helpful to evaluate the lighting conditions inside the building and provide a basis for energy-saving improvements and indoor comfort. By performing spatial distribution analysis on ambient light intensity values, the differences and changes in lighting inside the building are revealed. The generated light intensity spatial distribution data can be used to guide the optimal design and adjustment of the building's internal lighting system. Dynamic light intensity distribution rendering intuitively presents the changes and distribution laws of the building's internal lighting conditions. The constructed light intensity distribution rendering model helps building managers better understand the lighting characteristics of the building, and then take corresponding energy-saving measures and optimization strategies.

[0028] Preferably, step S25 specifically comprises the following steps:

[0029] Perform building light orientation analysis on the building's 3D structural model to identify the light orientation characteristics of different areas;

[0030] Perform dynamic ray tracing on the lighting parameters of the building environment to generate dynamic ray tracing trajectories;

[0031] Based on the light direction characteristics of different areas, the dynamic ray tracing trajectory is simulated to simulate the illumination time series change, so as to generate the illumination time series change trajectory of different areas;

[0032] According to the illumination time series variation trajectory of different areas, the illumination time series intensity fluctuation of the spatial distribution data of the building environment light intensity is calculated to generate the time series light intensity fluctuation characteristics of different areas;

[0033] Based on the temporal light intensity fluctuation characteristics of different areas, the three-dimensional structural model of the building is dynamically rendered with light intensity distribution, and an ambient light intensity distribution rendering model is constructed.

[0034] The present invention analyzes the light direction of the building, identifies the lighting characteristics of different areas, and understands which areas are more susceptible to sunlight, which helps to optimize the design and layout of the building, improve the natural lighting effect, reduce dependence on artificial lighting, and thus reduce energy consumption. Through dynamic light tracing, the changes in light inside the building in different time periods are simulated, which helps to understand the dynamic characteristics of lighting inside the building and provide more detailed data support for energy-saving management. By simulating the time-series changes in light, the changing trend of light conditions in different areas over time is predicted, which helps to determine which areas will receive more or less sunlight and when, providing a reference for optimizing indoor lighting and air-conditioning systems. By calculating the intensity fluctuations of light time series and quantifying the degree of change in light intensity in different areas, the present invention helps to identify the regularity of light fluctuations and provide a basis for formulating energy-saving management strategies. Through dynamic light intensity distribution rendering, the changes in light intensity in different areas inside the building are intuitively displayed. The constructed light intensity distribution rendering model helps building managers better understand the impact of light changes on energy consumption, and then take corresponding energy-saving measures and optimization strategies.

[0035] Preferably, step S3 specifically comprises the following steps:

[0036] Step S31: classifying the building three-dimensional structure model into functional areas to obtain a plurality of building functional classifications;

[0037] Step S32: performing regional usage scenario analysis based on multiple building function classifications, thereby generating multiple regional usage scenarios;

[0038] Step S33: performing multi-period usage demand analysis on the usage scenarios of multiple regions to obtain the multi-period usage demand characteristics of each region;

[0039] Step S34: performing dynamic lighting demand analysis on the multi-period usage demand characteristics of each area to generate multi-period dynamic lighting demand characteristics of each area;

[0040] Step S35: fitting the optimal time series lighting demand for the multi-period dynamic lighting demand characteristics of each area, thereby constructing the optimal lighting demand time series curve for each area.

[0041] The present invention classifies the functional areas of buildings to better understand the uses and functions of different areas inside the building, which helps to divide the building space into different functional areas and provide basic data for subsequent energy-saving management. Through regional usage scenario analysis, the specific usage and needs of each functional area are deeply understood, which helps to identify the differences in lighting needs of different areas and provide customized solutions for energy-saving management. Through multi-period usage demand analysis, the changes in lighting needs of different functional areas in different time periods are understood, which helps to determine the time period characteristics of lighting needs inside the building and provide more refined optimization solutions for energy-saving management. Through dynamic lighting demand analysis, the trend of lighting demand changes over time in each area is quantified, which helps to formulate reasonable lighting management strategies for each functional area and improve energy utilization efficiency. Through optimal time-series lighting demand fitting, the optimal lighting demand timing curve is constructed for each area, which helps to accurately control the lighting level of each functional area, achieve effective energy utilization, and improve the energy-saving performance of the building.

[0042] Preferably, the specific steps of step S4 are:

[0043] Step S41: performing regional temporal light intensity evolution based on the ambient light intensity distribution rendering model, and extracting temporal ambient light intensity parameters of different regions;

[0044] Step S42: calculating the time-period light intensity deviation of the ambient time-series light intensity parameters of different areas according to the multi-time period dynamic light demand characteristics of each area, thereby obtaining the time-series light intensity deviation data of different areas;

[0045] Step S43: performing multi-period optimal light source compensation calculation on the time-series light intensity deviation data of different regions based on the optimal light demand time-series curve of each region, thereby generating regional optimal light source compensation parameters for multiple time periods;

[0046] Step S44: dynamically control the building lighting equipment based on the regional optimal light source compensation parameters in multiple time periods, and construct a multi-time period regional light source compensation control strategy.

[0047] The present invention uses an ambient light intensity distribution rendering model to simulate the changes in illumination conditions in different areas over time, and extracts the time-series ambient light intensity parameters of each area. Extracting the time-series ambient light intensity parameters is helpful to understand the illumination conditions in different areas inside the building, and provides data support for subsequent energy-saving management. According to the dynamic illumination demand characteristics of each area, the light intensity deviations of the ambient time-series light intensity parameters of different areas are calculated one by one, and the change trend of the illumination conditions in each area is revealed. Based on the regional optimal illumination demand time-series curve, multi-period optimal light source compensation calculation is performed on the time-series light intensity deviation data, and the optimal light source compensation parameters for each time period are determined. Generating regional optimal light source compensation parameters for multiple time periods is helpful to adjust illumination according to actual needs, improve energy utilization efficiency and comfort, and dynamically control building lighting equipment based on multi-period regional optimal light source compensation parameters to realize intelligent adjustment of illumination, save energy and improve comfort. Constructing a multi-period regional light source compensation control strategy is helpful to optimize the operation of the building lighting system, realize energy-saving management and environmental friendliness, and obtaining the time-series light intensity deviation data is helpful to evaluate the illumination quality of different areas, and provides a basis for optimizing illumination management.

[0048] Preferably, the specific steps of step S5 are:

[0049] Step S51: performing regional activity trajectory analysis on personnel flow monitoring parameters according to the three-dimensional structural model of the building to generate multi-region personnel activity trajectories;

[0050] Step S52: Calculate the regional stay time of the personnel flow monitoring parameters to obtain the stay time in different areas;

[0051] Step S53: quantifying the usage frequency of people in each area based on the activity trajectories of people in multiple areas and the length of stay in different areas, thereby generating the usage frequency characteristics of people in different areas;

[0052] Step S54: performing spatial heat transfer evolution based on multi-region personnel activity trajectories, thereby generating a spatial heat transfer law;

[0053] Step S55: predicting the regional temperature change trend based on the frequency of use of personnel in different areas and the law of spatial heat transfer, thereby generating temperature change trend prediction data for different areas;

[0054] Step S56: Make intelligent temperature control demand decisions based on the temperature change trend prediction data of different areas and build a space intelligent temperature control strategy.

[0055] The present invention analyzes the three-dimensional structural model of the building, monitors the activity trajectory of personnel in the building, and generates multi-region personnel activity trajectories. Generating multi-region personnel activity trajectories helps to understand the movement mode of personnel in the building, and provides a reference for optimizing the building layout and energy-saving management. The regional stay time calculation of the personnel flow monitoring parameters obtains the stay time data of different regions, revealing the stay of personnel in each region. Analyzing the stay time of different regions helps to evaluate the activity hotspots and usage frequency of each region inside the building, and provides a basis for energy-saving management. Combined with the multi-region personnel activity trajectory and stay time data, the personnel use frequency of each region is quantitatively analyzed to generate the personnel use frequency characteristics of different regions. Quantifying the personnel use frequency characteristics of different regions helps to understand the personnel activity pattern inside the building and provide data support for intelligent temperature control demand decision-making. Based on the multi-region personnel activity trajectory, the spatial heat transfer evolution analysis is performed, the spatial heat transfer law is generated, and the heat transfer situation inside the building is understood. Analyzing the spatial heat transfer law helps to optimize the thermal environment of the building and provide guidance for energy-saving management and comfort improvement. Combined with the personnel use frequency characteristics and the spatial heat transfer law, the temperature change trend of different regions is predicted, and a basis for intelligent temperature control demand decision-making is provided. Building intelligent temperature control strategies based on temperature change trend prediction data helps optimize the building's temperature control management and achieve a balance between energy saving, comfort and environmental protection.

[0056] Preferably, the specific steps of step S54 are:

[0057] Acquire building internal temperature monitoring parameters based on multi-sensor nodes;

[0058] Conduct three-dimensional spatial temperature distribution analysis on the temperature monitoring parameters inside the building to generate three-dimensional spatial temperature distribution characteristics;

[0059] Perform temperature propagation analysis on the three-dimensional spatial temperature distribution characteristics to generate spatial temperature propagation characteristics;

[0060] Analyze the impact of local heat propagation on the activity trajectories of people in multiple regions, and generate the local heat propagation law of people flow;

[0061] The spatial heat transfer evolution is carried out on the local heat propagation law of personnel flow and the spatial temperature propagation characteristics, thereby generating the spatial heat transfer law.

[0062] The present invention obtains the internal temperature monitoring parameters of the building through multiple sensor nodes to realize comprehensive monitoring and data collection of the internal temperature of the building. The use of multiple sensor nodes is helpful to obtain accurate temperature data, providing a reliable basis for subsequent analysis and decision-making. The three-dimensional spatial temperature distribution analysis is performed on the internal temperature monitoring parameters of the building to generate comprehensive three-dimensional spatial temperature distribution characteristics of the building. Understanding the spatial distribution characteristics of the internal temperature of the building is helpful to reveal temperature differences and hot spots, and provide a reference for energy-saving management and comfort improvement. By performing temperature propagation analysis on the three-dimensional spatial temperature distribution characteristics, the spatial temperature propagation characteristics of the building are generated. Understanding the propagation law of temperature in the building is helpful to optimize the ventilation, lighting and air-conditioning design of the building and improve energy efficiency. The influence of the activity trajectories of personnel in multiple regions on local heat propagation is analyzed to generate the local heat propagation law of personnel flow. Understanding the influence of personnel activities on heat propagation is helpful to optimize the thermal environment inside the building and improve energy efficiency and comfort. In combination with the local heat propagation law of personnel flow and the spatial temperature propagation characteristics, the spatial heat transfer evolution analysis is performed to generate the spatial heat transfer law. Understanding the spatial heat transfer law is helpful to formulate targeted energy-saving management strategies and optimize the thermal environment and energy efficiency of the building.

[0063] Preferably, the specific steps of step S6 are:

[0064] Step S61: Perform intelligent control of building equipment according to the multi-period regional light source compensation control strategy and the space intelligent temperature control strategy, and collect energy consumption parameters of building equipment;

[0065] Step S62: Calculate the regional energy efficiency of the building equipment energy consumption parameters, thereby generating energy efficiency values ​​for different areas in the building;

[0066] Step S63: identifying high energy consumption areas based on the energy efficiency values ​​of different areas in the building based on the preset equipment energy consumption threshold, thereby extracting equipment high energy consumption areas;

[0067] Step S64: performing energy consumption optimization analysis on the high energy consumption area of ​​the equipment, thereby generating equipment energy consumption optimization data;

[0068] Step S65: Based on the equipment energy consumption optimization data, collaborative reinforcement learning is performed on the multi-period regional light source compensation control strategy and the space intelligent temperature control strategy to build an intelligent energy consumption regulation model to perform building energy-saving management operations.

[0069] The present invention realizes intelligent equipment regulation through multi-period regional light source compensation control strategy and space intelligent temperature control strategy, realizes intelligent management of building equipment and optimizes energy efficiency. Collecting building equipment energy consumption parameters is helpful for real-time monitoring and analysis of building equipment energy consumption, providing data support for subsequent energy consumption optimization, analyzing building equipment energy consumption parameters and calculating regional energy consumption efficiency, generating energy consumption efficiency values ​​of different areas in the building, revealing the energy consumption of each area, and understanding the energy consumption efficiency of different areas in the building is helpful to determine energy-saving potential and key optimization areas, providing guidance for energy consumption management, analyzing energy consumption efficiency values ​​of different areas according to preset equipment energy consumption thresholds, and identifying high energy consumption Area, extract equipment high energy consumption areas, determine the optimization focus, determine the equipment high energy consumption areas to help concentrate on energy consumption optimization, improve energy saving effects and reduce energy consumption costs, analyze equipment high energy consumption areas, conduct energy consumption optimization analysis, generate equipment energy consumption optimization data, explore potential solutions to reduce energy consumption, and optimize equipment energy consumption in high energy consumption areas to effectively reduce energy waste and improve the energy efficiency performance of buildings. Based on equipment energy consumption optimization data, collaborative reinforcement learning is carried out to build an intelligent energy consumption control model to realize intelligent energy-saving control of building equipment. Through the intelligent energy consumption control model, the equipment operation mode can be adjusted in real time, the energy consumption configuration can be optimized, and the energy saving effect and building energy efficiency can be improved.

[0070] In this specification, a building energy-saving management system based on the Internet of Things is provided, which is used to execute the building energy-saving management method based on the Internet of Things as described above, including:

[0071] The three-dimensional structure module is used to obtain the target building design drawing; identify the building structure feature points of the target building design drawing, perform three-dimensional space point cloud modeling, and construct a three-dimensional structural model of the building;

[0072] The light intensity distribution module is used to collect building environment lighting parameters and personnel flow monitoring parameters based on multiple sensor nodes; analyze the spatial distribution of ambient light intensity of building environment lighting parameters, and then perform dynamic light intensity distribution rendering to build an ambient light intensity distribution rendering model;

[0073] The optimal lighting demand module is used to analyze the regional usage scenarios of the ambient light intensity distribution rendering model according to the three-dimensional structural model of the building, and to fit the optimal timing lighting demand, so as to construct the optimal lighting demand timing curve for each area;

[0074] The light source compensation control module is used to calculate the optimal light source compensation in multiple time periods based on the optimal lighting demand timing curve of each area, and dynamically control the building lighting equipment to build a multi-time regional light source compensation control strategy;

[0075] The temperature control decision module is used to predict the regional temperature change trend based on the personnel flow monitoring parameters of the building's three-dimensional structural model, make intelligent temperature control demand decisions, and build a space intelligent temperature control strategy;

[0076] The intelligent energy consumption control module is used to perform intelligent control and collaborative reinforcement learning of building equipment based on multi-period regional light source compensation control strategy and space intelligent temperature control strategy, build an intelligent energy consumption control model, and perform building energy-saving management operations.

[0077] The present invention helps to construct an accurate three-dimensional structural model of the building by acquiring the target building design drawing and identifying the characteristic points of the building structure. Through three-dimensional space point cloud modeling, it can provide basic data for subsequent steps to achieve more accurate lighting and temperature control model construction, collect building environment lighting parameters and personnel flow monitoring parameters, which can help analyze the light intensity distribution of the building environment. The construction of a dynamic light intensity distribution rendering model helps to establish a real lighting condition and provide data support for the optimal lighting demand module. By analyzing the three-dimensional structural model of the building and the ambient light intensity distribution rendering model, regional usage scenario analysis and optimal time-series lighting demand fitting are achieved, and the optimal lighting demand time-series curve for each area is constructed, which helps to optimize the operating efficiency of the building lighting system and improve energy utilization. The optimal light source compensation calculation for multiple time periods is performed according to the optimal lighting demand timing curve to realize dynamic control of building lighting equipment, and a multi-time regional light source compensation control strategy is constructed to effectively adjust the light source brightness and time, improve the lighting effect, and reduce energy consumption at the same time. Based on the building structure and personnel flow monitoring parameters, the regional temperature change trend is predicted, and intelligent temperature control demand decision-making is realized. The construction of space intelligent temperature control strategy is helpful to optimize the operation of the building's heating and cooling systems, improve comfort, and reduce energy consumption. Combined with the light source compensation control strategy and the space intelligent temperature control strategy, the intelligent regulation and collaborative reinforcement learning of building equipment are realized, and an intelligent energy consumption regulation model is constructed. The building energy consumption can be monitored and adjusted in real time, the energy utilization efficiency is improved, and the energy-saving management goal is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 A schematic diagram of the steps of a building energy-saving management method based on the Internet of Things of the present invention;

[0079] Figure 2 Detailed implementation flow chart of step S1;

[0080] Figure 3 Detailed implementation flow chart of step S2;

[0081] Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0082] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0083] This application example provides a building energy-saving management system and method based on the Internet of Things. The execution subject of the building energy-saving management system and method based on the Internet of Things includes but is not limited to: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of this application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0084] See also Figures 1 to 4 The present invention provides a building energy-saving management method based on the Internet of Things, and the building energy-saving management method based on the Internet of Things comprises the following steps:

[0085] Step S1: obtaining a target building design drawing; identifying building structure feature points of the target building design drawing, performing three-dimensional space point cloud modeling, and constructing a three-dimensional building structure model;

[0086] Step S2: Collect building environment lighting parameters and personnel flow monitoring parameters based on multiple sensor nodes; perform ambient light intensity spatial distribution analysis on the building environment lighting parameters, then perform dynamic light intensity distribution rendering, and construct an ambient light intensity distribution rendering model;

[0087] Step S3: Perform regional usage scenario analysis on the ambient light intensity distribution rendering model according to the three-dimensional structural model of the building, and perform optimal timing lighting demand fitting, so as to construct the optimal lighting demand timing curve for each area;

[0088] Step S4: Calculate the optimal light source compensation in multiple time periods based on the optimal lighting demand time series curve of each area, dynamically control the building lighting equipment, and construct a multi-time regional light source compensation control strategy;

[0089] Step S5: predicting the regional temperature change trend of the personnel flow monitoring parameters according to the three-dimensional structural model of the building, making intelligent temperature control demand decisions, and building a space intelligent temperature control strategy;

[0090] Step S6: Perform intelligent control of building equipment and collaborative reinforcement learning based on the multi-period regional light source compensation control strategy and the space intelligent temperature control strategy, and build an intelligent energy consumption control model to perform building energy-saving management operations.

[0091] The present invention accurately restores the three-dimensional structure of the building through the recognition of building structure feature points and three-dimensional space point cloud modeling, and provides an accurate building model for subsequent energy-saving management. The construction of the three-dimensional structure model of the building is helpful for an in-depth understanding of the spatial layout and structural characteristics of the building, and provides reliable basic data for energy-saving management decisions. The building environment lighting parameters are analyzed and dynamic light intensity distribution rendering is performed to accurately simulate the lighting conditions inside the building, which helps to understand the spatial distribution of light intensity. The construction of the ambient light intensity distribution rendering model helps to optimize the lighting environment inside the building, improve comfort and potentially reduce unnecessary lighting energy consumption. The lighting requirements are analyzed according to the building structure model, and the optimal lighting requirement timing curve for each area is constructed. Personalized lighting plans are formulated according to the functions and requirements of different areas. The construction of the optimal lighting requirement timing curve helps to rationally utilize light source resources, improve lighting efficiency, and meet the lighting requirements of different areas in the building at the same time. Based on the optimal lighting demand time series curve, multi-period light source compensation calculations are performed, and a dynamic control strategy for building lighting equipment is constructed to achieve a balance between lighting demand and energy consumption. A multi-period regional light source compensation control strategy is constructed to help optimize the operation of building lighting equipment, reduce energy waste, and improve energy-saving effects. According to the personnel flow monitoring parameters, the regional temperature change trend is predicted, and a space intelligent temperature control strategy is constructed to adjust the temperature according to real-time demand, improve comfort and save energy. The construction of an intelligent temperature control strategy helps to optimize the internal temperature control of the building, improve energy utilization efficiency, and reduce energy consumption costs. Combined with light source compensation control and intelligent temperature control strategies, intelligent regulation and reinforcement learning of building equipment are carried out, and an intelligent energy consumption regulation model is constructed to achieve dynamic energy-saving management. The construction of an intelligent energy consumption regulation model helps to monitor and adjust the operating status of building equipment in real time, minimize energy consumption, improve energy-saving effects, and achieve building energy-saving management goals.

[0092] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a building energy-saving management method based on the Internet of Things of the present invention. In this example, the steps of the method include:

[0093] Step S1: obtaining a target building design drawing; identifying building structure feature points of the target building design drawing, performing three-dimensional space point cloud modeling, and constructing a three-dimensional building structure model;

[0094] In this embodiment, design drawings of the target building are obtained from the architectural design unit or relevant department, which usually include floor plans, elevations, and sections, etc., and the obtained drawings are ensured to be in a processable electronic file format (such as PDF, DWG, DXF, etc.) for subsequent use. The integrity and clarity of the design drawings are checked to ensure that all necessary details (such as dimensions, symbols, materials, etc.) are marked, and any special requirements or design changes that affect modeling are recorded. Suitable architectural modeling software or image processing tools (such as AutoCAD, Revit, SketchUp, MATLAB, OpenCV, etc.) are selected to perform feature point recognition and analysis. Image processing techniques (such as edge detection, corner point detection, etc.) are used to identify feature points of the building structure from the design drawings. These feature points include wall intersections, door and window locations, floor heights, etc. If the design drawing is a two-dimensional plan, algorithms (such as Hough transform, Canny edge detection, etc.) can be used to automatically identify straight lines and intersections, and the identified feature points are marked and classified to generate a feature point data set, recording the coordinates and related attributes (such as type, size) of each feature point in a structured format (such as CSV, JSON or database). ) Save the feature point data for subsequent use, convert the identified two-dimensional feature point data into three-dimensional point cloud data, use simple geometric transformations (such as according to the drawing scale and height information) to map the feature points from the two-dimensional plane to the three-dimensional space, if there is laser scanning or photogrammetry data, these data can be combined to generate a more accurate point cloud, use point cloud processing software (such as CloudCompare, MeshLab or other three-dimensional modeling tools) to filter, denoise and reconstruct the surface of the generated point cloud, and eliminate redundant points and fill in missing areas through post-processing of the point cloud to ensure the integrity and accuracy of the point cloud. According to the processed point cloud data, use modeling software (such as Revit, Blender, 3dsMax, etc.) to convert the point cloud into a three-dimensional structural model. In the modeling process, establish different building structural elements (such as walls, floors, roofs, etc.), and assign them material properties and geometric shapes. Verify the constructed three-dimensional structural model to ensure that it meets the requirements of the design drawings, check whether each part of the model is accurate, and optimize the model as needed, such as simplifying unnecessary details, adjusting material and lighting settings, for subsequent analysis and visualization.

[0095] Step S2: Collect building environment lighting parameters and personnel flow monitoring parameters based on multiple sensor nodes; perform ambient light intensity spatial distribution analysis on the building environment lighting parameters, then perform dynamic light intensity distribution rendering, and construct an ambient light intensity distribution rendering model;

[0096] In this embodiment, a variety of sensors are arranged inside the building, including ambient light intensity sensors (such as photoresistors or light sensors) and personnel flow monitoring sensors (such as infrared sensors, cameras or intelligent access control systems), ensuring that the sensors cover all key areas in the building, such as offices, corridors, conference rooms and public areas, to obtain comprehensive data, configure the sensors to regularly collect ambient light parameters (such as light intensity) and personnel flow parameters (such as the number of people and flow paths), set a suitable collection frequency, such as once every minute or every 5 minutes, to ensure the timeliness and accuracy of the data, transmit the collected data to a central database or cloud storage via a wireless network or wired network to ensure the security and accessibility of the data, and perform preliminary processing on the data, such as time. Stamp synchronization and data format unification to form a structured data set, clean the collected ambient lighting parameters, remove outliers and noise, ensure data accuracy, organize the lighting data into a format suitable for analysis, usually including light intensity, location coordinates and timestamps, use spatial analysis tools (such as GIS software, Python's Pandas and NumPy libraries) to perform spatial distribution analysis on ambient lighting data, use interpolation methods (such as Kriging interpolation, inverse distance weighted method, etc.) to calculate the light intensity of each area, generate a spatial distribution map of light intensity, visualize the analysis results, use charts or heat maps to show the light intensity distribution of different areas, help identify areas with strong or weak light, and choose appropriate rendering software or framework ( js, etc.) to render dynamic light intensity distribution, set dynamic rendering conditions according to lighting parameters and environmental changes (such as time, weather, etc.), create a 3D model of the building in the rendering software, and import the previously generated light intensity data, use real-time lighting calculation or global illumination algorithms (such as ray tracing, photon mapping, etc.) to render the model, dynamically adjust the light intensity and distribution according to time changes or personnel flow data, simulate real lighting changes, show the changes of light inside the building through animation effects, help analyze the lighting effects in different time periods, and optimize the performance of the rendering model, such as reducing the number of polygons and using LOD (level of detail) technology to ensure that the model is in different settings. Ensure that the model runs smoothly on the equipment, conduct tests to ensure the accuracy and real-time performance of dynamic light intensity rendering, adjust rendering parameters to meet the needs, integrate the dynamic light intensity distribution rendering results with the building 3D model to form a complete ambient light intensity distribution rendering model, ensure that the model can reflect the actual lighting changes and meet the needs of analysis and visualization, save the constructed ambient light intensity distribution rendering model and related parameters to the database or file system for subsequent use and analysis, record the model's version information and parameter settings for subsequent modification and updating, verify the constructed rendering model to ensure that it accurately reflects the lighting conditions inside the building, and compare it with the actual measurement results, make necessary adjustments and optimizations based on the verification results, and improve the reliability and practicality of the model.

[0097] Step S3: Perform regional usage scenario analysis on the ambient light intensity distribution rendering model according to the three-dimensional structural model of the building, and perform optimal timing lighting demand fitting, so as to construct the optimal lighting demand timing curve for each area;

[0098] In this embodiment, the usage scenarios of different areas in the building are determined, such as offices, conference rooms, corridors, public areas, and leisure areas, and the usage characteristic data of each area is collected, including usage time, activity type, personnel flow pattern, etc. The regional usage scenario data is integrated with the previous lighting parameters and personnel flow data to form a comprehensive analysis basis. Data analysis tools (such as Python's Pandas, R, or Excel) are used to organize and clean the data to ensure data consistency and accuracy. Based on the usage scenarios of each area, the lighting requirements in different time periods are analyzed. For example, the conference room requires higher lighting during meetings, while the corridor only requires basic lighting. The lighting standards in different scenarios (such as work environment, leisure environment, etc.) are considered to provide preparation for subsequent needs. Provide a basis for fitting. According to the regional usage scenarios and lighting requirements, establish a lighting demand model. Use linear regression, time series analysis or machine learning algorithms (such as random forests, support vector machines, etc.) for modeling. Determine input variables (such as time, activity type, and personnel density) and output variables (light intensity) for fitting analysis. Collect historical lighting data and corresponding usage scenario data as model training sets to ensure that the data covers different time periods and scenarios to improve the generalization ability of the model. Perform data preprocessing, such as normalization, missing value processing, and feature selection, to optimize model input. Use the selected lighting demand model to train the data. Improve the accuracy and stability of the model through cross-validation and hyperparameter tuning. Record the performance indicators of the model (such as mean square error, R 2 values, etc.) to ensure that the model can accurately predict the lighting demand. After the model training is completed, the model is used to predict the lighting demand of each area and generate the optimal lighting demand time series curve. The time series curve should reflect the changes in lighting demand in different time periods. Considering the peak and trough periods of building use, the generated optimal time series lighting demand curve is visualized, and chart tools (such as Matplotlib, Seaborn or Excel) are used to display the changes in lighting demand in different areas. Through the visualization analysis results, the rules and trends of lighting demand are identified to assist in the formulation of subsequent lighting control strategies. The generated optimal lighting demand time series curve is compared with the actual measured lighting data to verify the accuracy of the model. The user's opinions are collected through the feedback mechanism to evaluate whether the lighting demand meets the actual usage. According to the verification results, necessary adjustments are made to the model, such as retraining the model, optimizing feature selection or modifying input parameters. The lighting conditions and usage scenarios in the building are continuously monitored to ensure that the model always reflects the actual needs.

[0099] Step S4: Calculate the optimal light source compensation in multiple time periods based on the optimal lighting demand time series curve of each area, dynamically control the building lighting equipment, and construct a multi-time regional light source compensation control strategy;

[0100] In this embodiment, the light source compensation strategy is defined according to the optimal lighting demand timing curve of each area. The goal is to dynamically adjust the light intensity according to the ambient light, internal light source and personnel activities. Determine the basis for compensation, such as: current ambient light intensity, personnel density in the area, time period, etc. Install an ambient light intensity sensor to monitor the changes in light intensity inside and outside the building in real time. Compare the real-time light intensity data with the optimal lighting demand timing curve to calculate the required light source compensation. Calculate the light source compensation amount for each area to ensure that the compensated light intensity is a positive value. If it is a negative value, it means that the current light has met the demand and no additional compensation is required. Integrate the calculated compensated light intensity with the usage scenario and light source status of each area to form a comprehensive light source compensation data set. Design and configure an intelligent lighting control system to ensure that it can receive the lighting demand, ambient light intensity and compensation calculation results in real time. Select appropriate control protocols (such as DALI, Zigbee, LON, etc.) and hardware (such as smart lamps, dimmers) for system integration. Develop a dynamic control algorithm to adjust the output of the lighting equipment according to the real-time light source compensation calculation results. The algorithm should be able to automatically adjust according to the preset logic (such as linear regulation, PID control, etc.). Consider the response characteristics and adjustment range of different devices to avoid over-adjustment. Implement dynamic control of lighting equipment in the building, including adjusting the brightness, switch status, etc. of lamps. Send instructions through the control system to adjust the lighting equipment in each area in real time to meet the lighting needs. Establish a feedback mechanism to monitor the actual output of the lighting equipment to ensure that it is consistent with the calculated compensation light intensity. Monitor the lighting effect through sensors and continuously adjust the control strategy based on feedback information to optimize the lighting effect and energy consumption. Integrate the light source compensation calculation and dynamic control strategy of all areas to form a comprehensive multi-period regional light source compensation control strategy. Ensure that the strategy can adapt to changes in different time periods and usage scenarios, such as different needs during weekdays and weekends, daytime and nighttime. Test the constructed light source compensation control strategy in the actual environment to evaluate its effectiveness and stability under different conditions. Make necessary optimizations based on the test results, such as adjusting the compensation algorithm, improving the control logic, etc. Develop a user-friendly interface for managers to monitor and adjust the light source compensation control strategy in real time. The interface should provide data visualization functions to display the current lighting status, compensation needs and equipment operation status. Establish a long-term monitoring mechanism to regularly evaluate the effectiveness of the light source compensation control strategy and the lighting quality in the building. Based on actual usage and feedback, control strategies are continuously optimized and updated to cope with different usage requirements and environmental changes.

[0101] Step S5: predicting the regional temperature change trend of the personnel flow monitoring parameters according to the three-dimensional structural model of the building, making intelligent temperature control demand decisions, and building a space intelligent temperature control strategy;

[0102] In this embodiment, the temperature monitoring data in the building is collected to ensure that the data covers different time periods and different areas for analysis, and the personnel flow monitoring parameters, including the number of personnel, flow path and residence time, are integrated as the influencing factors of temperature change. A suitable temperature change model is selected, and linear regression, time series analysis (such as ARIMA model) or machine learning algorithm (such as random forest, support vector machine, etc.) is used to predict regional temperature changes, determine input variables (such as current temperature, personnel flow parameters, ambient light intensity, etc.) and output variables (regional temperature changes), build a model, and use historical temperature data and personnel flow data to train the model to ensure that the model can accurately reflect the temperature change trend. Through cross-validation, The performance of the model is evaluated by indicators such as mean square error, and the model parameters are adjusted to improve the prediction accuracy. Real-time data is input into the trained model to predict the regional temperature change trend. The prediction range can be set to the next few hours or days. The prediction results, including the temperature change trend and change range of each area, are recorded to provide a basis for subsequent intelligent temperature control decisions. According to the temperature change prediction results of each area, the temperature control needs in different time periods are analyzed. For example, when the flow of people increases, the regional temperature rises, and cooling measures need to be strengthened. The temperature control threshold is set to determine when heating or cooling is needed to maintain a comfortable indoor environment. According to the temperature control needs, an intelligent temperature control strategy is designed. The strategy should include dynamic adjustment of air conditioners, heaters and ventilation systems. Working status, consider the usage scenarios and comfort standards of different areas, ensure that the temperature control strategy meets actual needs, develop an intelligent decision-making system that can receive temperature predictions, personnel flow and environmental data in real time, automatically generate temperature control decisions, use decision trees, fuzzy logic or reinforcement learning algorithms to realize intelligent decision-making functions, transmit the temperature control instructions generated by the intelligent decision-making system to the actual temperature control equipment (such as air conditioners and heaters), realize automatic adjustment, monitor the working status of the equipment in real time through the control system, and adjust the temperature control strategy according to the feedback information, integrate the temperature control needs, temperature change trends and intelligent decision-making results of all areas, form a comprehensive space intelligent temperature control strategy, and ensure that the strategy can adapt to changes in different time periods, regions and usage scenarios. ization to improve flexibility and effectiveness, test the constructed intelligent temperature control strategy in the actual environment, evaluate its effectiveness, response speed and comfort under different conditions, and make necessary optimizations based on the test results, such as adjusting the temperature control threshold, improving the decision-making algorithm, etc. Develop a user-friendly interface for managers to monitor and adjust the temperature control strategy in real time. The interface should provide real-time data visualization, including temperature distribution, personnel flow and temperature control status, allowing managers to manually adjust the temperature control settings according to actual needs, ensure flexibility, establish a long-term monitoring mechanism, regularly evaluate the effect of the intelligent temperature control strategy and the temperature comfort in the building, and continuously optimize and update the control strategy based on actual usage and feedback to cope with different usage needs and environmental changes.

[0103] Step S6: Perform intelligent control of building equipment and collaborative reinforcement learning based on the multi-period regional light source compensation control strategy and the space intelligent temperature control strategy, and build an intelligent energy consumption control model to perform building energy-saving management operations.

[0104] In this embodiment, the multi-period regional light source compensation control strategy and the space intelligent temperature control strategy are integrated into a central control system to ensure that the system can receive data from light sensors, temperature sensors and personnel flow monitoring equipment in real time, design the system architecture so that it can handle the needs of light and temperature control at the same time, ensure the efficiency and accuracy of the decision-making process, develop intelligent control algorithms, automatically generate control instructions based on real-time data and preset light source compensation and temperature control strategies, use rule engines, fuzzy logic or machine learning models to formulate control logic, ensure that the equipment status can be flexibly adjusted according to environmental changes and usage needs, and implement the generated control instructions to the lighting and temperature control equipment in the building, such as automatically adjusting lamps Brightness, air conditioning temperature setting, etc., through intelligent control systems, real-time monitoring of equipment response, further optimization of control strategies based on feedback information, design a reinforcement learning framework, define state space, action space and reward mechanism, the state space should include the current light intensity, temperature, personnel flow, etc.; the action space includes different operations for adjusting lighting and temperature control equipment, the reward mechanism should be based on energy efficiency and comfort target setting to ensure that the system maintains the comfort of the indoor environment while optimizing energy consumption, collect historical data, including energy consumption, light intensity, temperature changes and personnel flow, as training data for the reinforcement learning model, use the collected data to train the reinforcement learning model, and simulate the environment Evaluate and optimize different strategies to improve the decision-making ability of the model. Integrate the trained model into the intelligent control system so that it can update and optimize the decision-making process in real time. According to real-time data feedback and environmental changes, adjust the strategy to adapt to different usage situations. Through continuous learning, the model can be continuously improved to adapt to dynamic changes in the building and optimize energy consumption management. Integrate light source compensation control, temperature control strategy and reinforcement learning model to form a comprehensive intelligent energy consumption control model to ensure that the model can handle the needs of lighting and temperature control at the same time to achieve the best energy consumption management. Optimize the model to ensure its efficient operation, reduce decision-making delays, and improve response speed. In the actual environment, the constructed intelligent energy consumption control The model is simulated and tested to evaluate its performance in different scenarios, including energy efficiency under high and low load conditions. Adjustments and optimizations are made based on the test results to ensure that the model can be effectively executed under various conditions. The intelligent energy consumption control model is formally implemented into the building management system, and real-time energy consumption management operations are started. A monitoring mechanism is established to regularly evaluate the effectiveness of the model, including energy consumption reduction, comfort feedback, and equipment operating status. Based on feedback data from long-term operations, the intelligent energy consumption control model is continuously optimized, and the model is updated with new data and technologies to adapt to changing usage requirements and environmental conditions. The model is evaluated and updated regularly to ensure its effectiveness and reliability in energy-saving management.

[0105] In this embodiment, refer to Figure 2, is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0106] Step S11: Obtaining a target building design drawing;

[0107] Step S12: Identify the architectural structural feature points of the target architectural design drawing and mark a plurality of structural feature points;

[0108] Step S13: performing spatial layout distribution analysis on a plurality of structural feature points to generate spatial layout distribution data;

[0109] Step S14: performing regional geometry calculation on the target building design drawing to generate multiple regional geometry data in the building;

[0110] Step S15: Perform three-dimensional spatial point cloud modeling on the geometric data of multiple areas in the building according to the spatial layout distribution data to construct a three-dimensional structural model of the building.

[0111] In this embodiment, after obtaining authorization from relevant personnel, the source of the design drawings of the target building is confirmed, including the architectural design company and the online architectural database, to ensure that the acquired design drawings are the latest version and contain complete building information, to obtain the format of the design drawings, usually in CAD file (such as DWG, DXF) or PDF format, to ensure that the drawings are available for subsequent processing and analysis, and to perform format conversion when necessary, to import the acquired design drawings into architectural design software (such as AutoCAD, Revit) or image processing software for subsequent processing, to pre-process the design drawings, including image denoising, contrast enhancement and edge detection, to improve the accuracy of feature point recognition, to process the drawings using image processing tools (such as OpenCV), and to apply feature point detection algorithms (such as Harris corner detection or SIFT) to identify architectural design points. The key structural feature points in the design map, such as wall intersections, column positions, door and window frames, etc., are identified to ensure that the extracted feature points are representative and can reflect the overall structure of the building. The multiple identified structural feature points are marked to form a list of structural feature points for subsequent analysis and modeling. The marked structural feature point data are integrated into a unified database to ensure consistent data format. GIS software or building analysis tools (such as Rhino or Grasshopper) are used for data processing. Spatial analysis methods (such as Voronoi diagrams or cluster analysis) are used to analyze multiple structural feature points to generate spatial layout distribution data for each part of the building, identify the relationship between different areas, analyze space utilization and functional zoning, generate spatial layout distribution data, record the spatial characteristics and relationships of each area, and store them in the database.

[0112] Extract geometric data of each area from the architectural design drawing, including wall thickness, room area, space height, etc. Use the measurement tools or scripts of the CAD software to automatically extract geometric information, calculate the geometric form of multiple areas in the building, including plane outline, volume calculation and area analysis, use mathematical modeling methods (such as polygon area calculation, volume formula) to calculate geometric form, organize the calculated geometric form data of each area, and record them in the database for subsequent modeling. According to the spatial layout distribution data and regional geometric form data, prepare the parameters required to build a 3D point cloud model, select a suitable 3D modeling tool (such as Blender, SketchUp or Revit), convert the regional geometric form data into a 3D point cloud, generate a 3D model of each area of ​​the building, use computer graphics technology (such as mesh generation and surface reconstruction) to construct a 3D space point cloud, and optimize the point cloud model, including denoising, resolution adjustment and texture mapping, to improve the visualization effect of the model and ensure that the generated 3D structural model has good details and realism. Save the constructed 3D structural model of the building in a standard format (such as OBJ, FBX or STL) for subsequent use and sharing, and display the 3D model in a visualization tool for display and evaluation.

[0113] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0114] Step S21: Collecting building environment lighting parameters and personnel flow monitoring parameters based on multiple sensor nodes;

[0115] Step S22: positioning the multi-sensor nodes in the internal space of the building to generate the spatial position coordinates of each node;

[0116] Step S23: Calculating the illumination intensity of the building environment illumination parameters to generate an ambient illumination intensity value;

[0117] Step S24: performing an ambient light intensity spatial distribution analysis on the ambient light intensity value based on the spatial position coordinates of each node to generate building ambient light intensity spatial distribution data;

[0118] Step S25: Perform dynamic light intensity distribution rendering on the building environment light intensity spatial distribution data to construct an environment light intensity distribution rendering model.

[0119] In this embodiment, appropriate sensor nodes are selected, mainly including: light sensors: used to measure the ambient light intensity (such as LDR or photoelectric sensors), personnel flow sensors: used to monitor personnel flow (such as PIR sensors, infrared sensors or cameras), sensors are installed at appropriate locations inside the building to ensure that all key areas can be covered, the sensor collection frequency and parameters are set, and the light and personnel flow data are collected in real time. The collected data is sent to the central processing system through a wireless network or a wired network, and the collected light parameters and personnel flow monitoring parameters are integrated into a database for subsequent analysis. Fixed spatial position coordinates (such as x, y, and z coordinates) are assigned to each sensor node. These coordinates are based on the building plan or three-dimensional model, and the position is calibrated using a laser rangefinder or architectural design software (such as AutoCAD or Revit). The spatial position coordinates of each node are recorded in the database to ensure that the position data corresponds to the data collected by the sensor one by one. The ambient light parameter data is extracted from the database, and data cleaning is performed to remove outliers and noise. The data collected by the light sensor is converted into units to ensure that all data are unified into a standard unit (such as lux). The Light intensity value, considering the changes in light in different time periods, generate ambient light intensity values, use statistical methods (such as mean, standard deviation) for analysis to obtain more accurate light intensity data, organize the spatial position coordinates of each sensor node and the corresponding light intensity value to form a structured data set, use spatial interpolation methods (such as Kriging interpolation, inverse distance weighted method, etc.) to analyze the spatial distribution of light intensity values, generate ambient light intensity spatial distribution data, show the changes in light inside the building, and generate light intensity data through data visualization tools (such as Python's Matplotlib or GIS software). A spatial distribution diagram of light intensity is prepared to facilitate analysis and understanding. Appropriate 3D modeling and rendering software (such as Blender, Unity or UnrealEngine) is selected for light intensity distribution rendering. The 3D model of the building and the spatial distribution data of light intensity are imported. The intensity and position of the light source are set according to the spatial distribution data of light intensity. The rendering parameters are adjusted to reflect the actual lighting conditions to achieve dynamic rendering effects. The light intensity can be updated in real time over time. The rendering results are evaluated to ensure that they are consistent with the actual lighting conditions. The model and rendering parameters are adjusted according to the evaluation results to improve the realism and accuracy of the rendering effect.

[0120] In this embodiment, the specific steps of step S25 are:

[0121] Perform building light orientation analysis on the building's 3D structural model to identify the light orientation characteristics of different areas;

[0122] Perform dynamic ray tracing on the lighting parameters of the building environment to generate dynamic ray tracing trajectories;

[0123] Based on the light direction characteristics of different areas, the dynamic ray tracing trajectory is simulated to simulate the illumination time series change, so as to generate the illumination time series change trajectory of different areas;

[0124] According to the illumination time series variation trajectory of different areas, the illumination time series intensity fluctuation of the spatial distribution data of the building environment light intensity is calculated to generate the time series light intensity fluctuation characteristics of different areas;

[0125] Based on the temporal light intensity fluctuation characteristics of different areas, the three-dimensional structural model of the building is dynamically rendered with light intensity distribution, and an ambient light intensity distribution rendering model is constructed.

[0126] In this embodiment, the three-dimensional structural model of the building is imported into architectural design software (such as Rhino, Revit or SketchUp) to ensure that the model contains detailed geometric information and material properties for light analysis.

[0127] Use ray tracing algorithms (such as RayTracing) to calculate the interaction between light from different light sources (such as sunlight) and the building surface, set different times and dates to analyze the orientation characteristics of light in different areas of the building model, identify different areas inside the building (such as offices, corridors, public areas, etc.), and record the light orientation characteristics of each area, generate light orientation characteristic data, record the lighting direction angle, incident angle and illuminated area of ​​each area, set the dynamic properties of the light source, such as the movement trajectory of the sun, including changes in altitude and azimuth, confirm the time span (such as light changes within a day) and sampling frequency (such as every hour or every minute), use ray tracing technology to dynamically track the light, generate the dynamic path of the light inside the building, record the area, incident angle and intensity of the light at each time point, generate dynamic ray tracing trajectory data, and form a complete path record of the light in the building. Based on the light orientation characteristics and dynamic ray tracing trajectories of different areas, build a lighting time series change model to determine the law of light intensity change over time in each area, and use time series analysis methods (such as time series Prediction or interpolation method) simulates the time-series change of illumination in different areas, records the change of illumination intensity in each area at different time points, generates the trajectory data of time-series change of illumination in different areas, records the change trend of illumination over time, analyzes the trajectory of time-series change of illumination, calculates the fluctuation of illumination intensity, uses statistical methods (such as standard deviation, mean, etc.) to evaluate the light intensity fluctuation characteristics of each area, generates time-series light intensity fluctuation characteristic data of different areas, records the light intensity fluctuation range and frequency of each area, imports the three-dimensional structural model of the building and the time-series light intensity fluctuation characteristic data into rendering software (such as Blender, Unity or UnrealEngine), ensures that the model has appropriate material and illumination properties for realistic rendering, sets dynamic light sources according to the time-series light intensity fluctuation characteristics of different areas, adjusts the intensity and position of the light source, realizes dynamic rendering effect, updates the illumination intensity in real time with time, generates visualization effect of dynamic light intensity distribution, displays the time-series change of illumination in various areas inside the building, conducts effect evaluation, ensures that the rendering result meets the actual illumination conditions and has good visual performance.

[0128] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0129] Step S31: classifying the building three-dimensional structure model into functional areas to obtain a plurality of building functional classifications;

[0130] Step S32: performing regional usage scenario analysis based on multiple building function classifications, thereby generating multiple regional usage scenarios;

[0131] Step S33: performing multi-period usage demand analysis on the usage scenarios of multiple regions to obtain the multi-period usage demand characteristics of each region;

[0132] Step S34: performing dynamic lighting demand analysis on the multi-period usage demand characteristics of each area to generate multi-period dynamic lighting demand characteristics of each area;

[0133] Step S35: fitting the optimal time series lighting demand for the multi-period dynamic lighting demand characteristics of each area, thereby constructing the optimal lighting demand time series curve for each area.

[0134] In this embodiment, the three-dimensional structural model of the building is imported into the architectural design software (such as Revit, AutoCAD or ArchiCAD), and it is ensured that the model contains all necessary structural details and functional information. According to the architectural design drawings and functional requirements, the model is classified into functional areas, such as offices, conference rooms, public areas, rest areas, etc., and the partition tool of the architectural software is used to manually or automatically mark different functional areas. The classified data records are recorded, and the name, area, location and related attributes of each functional area are recorded, and the records are stored in the database for subsequent analysis and use. According to the purpose of use and user needs of different functional areas, multiple usage scenarios are defined, such as: work scenarios in office areas, meeting scenarios in conference rooms, and social scenarios in rest areas. The scenario analysis method selects the scenario analysis method (Scenario Analysis) or the user interview method to collect the actual usage and needs of users in each functional area. According to the analysis results, a specific usage scenario description is generated for each functional area, and the usage frequency, duration and user type of the scenario are recorded. The historical usage data corresponding to each area is collected, including the usage period, usage frequency and number of users, which are obtained through sensor data, user surveys or management system records, and statistical analysis (such as time series analysis, frequency analysis, etc.) is applied. The multi-period usage demand is analyzed by using the rate analysis method, and the usage demand characteristics of each functional area in different time periods are determined. The multi-period usage demand characteristics of each area are recorded to form a structured data set, including peak hours, valley hours and their corresponding usage demand. The multi-period usage demand characteristics of each area are integrated with the corresponding lighting demand, and the relationship between the usage demand and the lighting demand is analyzed. Based on the regional usage demand, the dynamic lighting demand is calculated, and the factors considered include: the number of users in each area, the lighting standards in different scenes (such as the lighting requirements of work scenes and rest scenes), and the multi-period dynamic lighting demand characteristic data of each area is generated. According to the data, record the light intensity required in different time periods, organize the multi-period dynamic light demand characteristic data of each area to form a time series data set, select a suitable time series fitting model, such as ARIMA, exponential smoothing or polynomial regression, to fit the light demand time series data, use the historical light demand data to train the selected fitting model, generate the optimal light demand time series curve for each area, evaluate the fitting effect of the model, adjust the model parameters to improve the fitting accuracy, record the optimal light demand time series curve for each area, and use visualization tools (such as Matplotlib, Excel) to generate charts for easy analysis and display.

[0135] In this embodiment, step S4 includes the following steps:

[0136] Step S41: performing regional temporal light intensity evolution based on the ambient light intensity distribution rendering model, and extracting temporal ambient light intensity parameters of different regions;

[0137] Step S42: calculating the time-period light intensity deviation of the ambient time-series light intensity parameters of different areas according to the multi-time period dynamic light demand characteristics of each area, thereby obtaining the time-series light intensity deviation data of different areas;

[0138] Step S43: performing multi-period optimal light source compensation calculation on the time-series light intensity deviation data of different regions based on the optimal light demand time-series curve of each region, thereby generating regional optimal light source compensation parameters for multiple time periods;

[0139] Step S44: dynamically control the building lighting equipment based on the regional optimal light source compensation parameters in multiple time periods, and construct a multi-time period regional light source compensation control strategy.

[0140] In this embodiment, the ambient light intensity distribution rendering model is used to ensure that the model contains the latest light intensity distribution data and regional information, the building three-dimensional model and its light intensity distribution data are imported into the rendering software (such as Blender, Unity or special architectural lighting analysis software), the evolution parameters are set, including the evolution time range (such as different time periods of a day) and the light source type (natural light, artificial light), the lighting simulation is implemented, the light intensity evolution algorithm (such as ray tracing or global illumination) is run, the ambient light intensity data of each area at different time periods is generated, the time series ambient light intensity parameters of different areas are extracted, and the time series ambient light intensity parameters of each area at different time periods are recorded. The light intensity value of the time period is obtained, and the extracted time-series ambient light intensity parameters are stored in the database for subsequent use. From the previous analysis, the multi-time period dynamic lighting demand characteristic data and time-series ambient light intensity parameters of each area are obtained to ensure that these data can correspond one to one. The light intensity deviation of each area is calculated one by one. Light intensity deviation = dynamic lighting demand - ambient light intensity parameter. The time-series light intensity deviation data of each area is recorded to identify which time periods need compensation. The calculated time-series light intensity deviation data is sorted and stored for subsequent analysis and compensation calculation. The optimal lighting demand time-series curve for each area generated previously is imported to ensure data The format is compatible with the deviation data. A suitable compensation calculation method is selected, such as linear interpolation, proportional compensation or model-based compensation algorithm. The time-series light intensity compensation parameters of each area are calculated. The compensation parameters = light intensity deviation + optimal lighting demand. The compensation parameters are ensured to be within a reasonable range to prevent uneven lighting caused by over-compensation. The regional optimal light source compensation parameters of each area in different time periods are recorded and stored in the database. According to the regional optimal light source compensation parameters of multiple time periods, a dynamic control strategy for building lighting equipment is formulated, and the types of lighting equipment in different areas (such as LED lights, fluorescent lights, etc.) and their adjustment ranges are determined. A control algorithm is developed, and PID control, fuzzy logic control or rule-based control system is used to dynamically adjust the lighting equipment to achieve the required light level, ensuring that the system can respond to changes in ambient light intensity and fluctuations in usage demand in real time. The control algorithm is integrated into the building management system to ensure that the system can receive data and feedback control instructions in real time. System testing is performed to verify the effectiveness of the dynamic control strategy, and adjustments and optimizations are made based on the test results. A monitoring mechanism is established to track the status and lighting effects of lighting equipment in real time, collect user feedback, and continuously optimize the control strategy based on the feedback information to ensure that the lighting effects inside the building meet usage requirements.

[0141] In this embodiment, step S5 includes the following steps:

[0142] Step S51: performing regional activity trajectory analysis on personnel flow monitoring parameters according to the three-dimensional structural model of the building to generate multi-region personnel activity trajectories;

[0143] Step S52: Calculate the regional stay time of the personnel flow monitoring parameters to obtain the stay time in different areas;

[0144] Step S53: quantifying the usage frequency of people in each area based on the activity trajectories of people in multiple areas and the length of stay in different areas, thereby generating the usage frequency characteristics of people in different areas;

[0145] Step S54: performing spatial heat transfer evolution based on multi-region personnel activity trajectories, thereby generating a spatial heat transfer law;

[0146] Step S55: predicting the regional temperature change trend based on the frequency of use of personnel in different areas and the law of spatial heat transfer, thereby generating temperature change trend prediction data for different areas;

[0147] Step S56: Make intelligent temperature control demand decisions based on the temperature change trend prediction data of different areas and build a space intelligent temperature control strategy.

[0148] In this embodiment, personnel flow monitoring parameters from sensors are collected, including information such as location, timestamp, and personnel ID. The data is organized into a structured format to ensure that each record contains the necessary fields. Based on the personnel's mobile data, a trajectory analysis algorithm (such as trajectory reconstruction based on time series) is used to generate the personnel activity trajectory of each area. Use GIS software or data analysis tools (such as Python's Pandas and Matplotlib) for visualization to help identify personnel activity patterns. Integrate the activity trajectories of each area to form a multi-region personnel activity trajectory data set, and record the activity density and movement path of each area. Define the calculation rules for the length of stay, for example: the time in a certain area exceeds a certain threshold (such as 5 minutes) and is considered to be a stay. Analyze the personnel activity trajectory of each area and count the length of stay of each user in different areas. Use statistical analysis tools (such as R language or Python) for data processing to calculate the total length of stay in each area. Record the length of stay in different areas to form a regional length of stay data set for subsequent analysis. Determine the calculation method for the frequency of use of personnel, for example: frequency of use = number of people staying / total monitoring time. Based on the multi-region personnel activity trajectory and length of stay data, calculate the frequency of use of each area. Use statistical methods to quantify each area and generate personnel usage frequency characteristic data. Store the calculated personnel usage frequency characteristics in the database to provide basic data for subsequent analysis. Based on the physical principle of heat conduction, build a spatial heat transfer model, taking into account factors such as building materials, personnel activities and ambient temperature. Use numerical simulation methods (such as finite element analysis or finite difference method) to analyze spatial heat transfer. Generate spatial heat transfer laws by simulating the impact of personnel activities on regional temperature in different time periods. Record the evolution of spatial heat transfer to form a heat transfer data set for subsequent use. Integrate the personnel usage frequency characteristics of different areas with the spatial heat transfer law as the basic data for temperature change analysis. Select a suitable time series prediction model (such as ARIMA, linear regression or machine learning model) to predict temperature change trends. Use the selected model to predict the temperature change trends in different areas and generate temperature change trend prediction data. Record the future temperature change trends of each area to support intelligent temperature control decisions. Based on the temperature change trend prediction data of different areas, build an intelligent temperature control decision model, taking into account personnel activities, usage frequency and external environmental factors. Design multiple temperature control strategies, such as active regulation based on predictive models, passive regulation (such as natural ventilation), and intelligent lighting and temperature control linkage. Integrate intelligent temperature control strategies into building management systems to ensure that the system can monitor and adjust temperature control devices in real time. Conduct system tests to verify the effectiveness of temperature control decisions and optimize based on test results. Establish a feedback mechanism for the temperature control system to monitor indoor temperature changes and user feedback in real time, and adjust temperature control strategies to improve comfort and energy efficiency.

[0149] In this embodiment, the specific steps of step S54 are:

[0150] Acquire building internal temperature monitoring parameters based on multi-sensor nodes;

[0151] Conduct three-dimensional spatial temperature distribution analysis on the temperature monitoring parameters inside the building to generate three-dimensional spatial temperature distribution characteristics;

[0152] Perform temperature propagation analysis on the three-dimensional spatial temperature distribution characteristics to generate spatial temperature propagation characteristics;

[0153] Analyze the impact of local heat propagation on the activity trajectories of people in multiple regions, and generate the local heat propagation law of people flow;

[0154] The spatial heat transfer evolution is carried out on the local heat propagation law of personnel flow and the spatial temperature propagation characteristics, thereby generating the spatial heat transfer law.

[0155] In this embodiment, multiple temperature sensors are arranged in key areas inside the building (such as offices, conference rooms, corridors, etc.) to ensure that all important spaces are covered, and suitable temperature sensors (such as digital thermometers, thermocouples or infrared sensors) are selected to ensure that their accuracy and response time meet the requirements. The sensors are configured to regularly collect indoor temperature data and send the data to a central database through a wireless network or a wired network. The data collection frequency is ensured to be appropriate (such as once per minute) so as to obtain time series data. The collected temperature monitoring parameters are sorted and stored in the database to form a structured data set for subsequent analysis. The temperature monitoring parameters are cleaned to remove outliers and noise to ensure the accuracy of the data. The data is converted into three 3D coordinate system to ensure that each temperature value corresponds to its spatial position. Use 3D modeling software (such as MATLAB, Python's Matplotlib, or 3D visualization tools) to perform spatial interpolation (such as Kriging interpolation or inverse distance weighted method) on the temperature data to generate a 3D temperature distribution map to show the temperature differences and distribution characteristics of different regions. Record the generated 3D spatial temperature distribution characteristic data, including the temperature range, mean, and standard deviation of each region, to facilitate subsequent analysis. Select a suitable heat propagation model, such as the Fourier heat conduction equation, to describe the temperature propagation process in space. Consider factors such as the thermal conductivity, convection, and radiation of building materials, and construct a comprehensive temperature propagation model. Based on the three-dimensional temperature distribution map, the temperature distribution characteristics of the building materials are analyzed. dimensional temperature distribution data, simulate temperature changes in different time periods, generate spatial temperature propagation characteristics, use numerical simulation methods (such as finite element analysis) to calculate the evolution of temperature over time, record the temperature change rate and propagation path, record the spatial temperature propagation characteristic data in the database, form a temperature propagation model that can be analyzed, collect multi-region personnel activity trajectory data, including the movement path and residence time of personnel in each region, use sensor data or user behavior analysis tools to obtain accurate activity trajectory information, analyze the impact of personnel flow on the temperature and heat of the local area according to the personnel activity trajectory, use the heat transfer model to calculate the local impact of personnel activities on the surrounding environment temperature, identify the heat source of personnel activities and its The propagation path is recorded, and the local heat propagation law of the generated personnel flow is recorded, including the scope and intensity of the heat impact, to form a data set for subsequent analysis. The local heat propagation law and spatial temperature propagation characteristics are integrated to build a comprehensive heat transfer model. The influence of heat sources in different regions (such as personnel, equipment, natural light, etc.) on the overall temperature is considered. Numerical simulation methods (such as computational fluid dynamics CFD) are used to analyze the evolution of spatial heat transfer, observe the temperature distribution and heat flow under time changes, simulate the heat transfer effects under different scenarios (such as different numbers of personnel, equipment operating status), and record the generated spatial heat transfer law, including heat distribution, propagation rate and impact range, to form a comprehensive heat transfer data set.

[0156] In this embodiment, step S6 includes the following steps:

[0157] Step S61: Perform intelligent control of building equipment according to the multi-period regional light source compensation control strategy and the space intelligent temperature control strategy, and collect energy consumption parameters of building equipment;

[0158] Step S62: Calculate the regional energy efficiency of the building equipment energy consumption parameters, thereby generating energy efficiency values ​​for different areas in the building;

[0159] Step S63: identifying high energy consumption areas based on the energy efficiency values ​​of different areas in the building based on the preset equipment energy consumption threshold, thereby extracting equipment high energy consumption areas;

[0160] Step S64: performing energy consumption optimization analysis on the high energy consumption area of ​​the equipment, thereby generating equipment energy consumption optimization data;

[0161] Step S65: Based on the equipment energy consumption optimization data, collaborative reinforcement learning is performed on the multi-period regional light source compensation control strategy and the space intelligent temperature control strategy to build an intelligent energy consumption regulation model to perform building energy-saving management operations.

[0162] In this embodiment, the multi-period regional light source compensation control strategy and the space intelligent temperature control strategy are integrated into the building management system to ensure that the system can automatically adjust the lighting and temperature control equipment, configure the control system so that it can receive data from temperature sensors, light sensors and activity sensors to adjust the equipment settings in real time, install energy consumption monitoring equipment (such as smart meters) on the building equipment to ensure that the energy consumption data of each device can be collected in real time, set the collection frequency, such as collecting energy consumption parameters every hour or in real time, and transmit the data to the central database, organize and store the collected building equipment energy consumption parameters in the database to form a structured energy consumption data set for subsequent analysis to determine the calculation formula of energy consumption efficiency, energy consumption efficiency = effective energy output / Total energy consumption, define the standard of effective energy output according to the function and usage of the building, analyze the energy consumption parameters of each area, calculate the energy efficiency value in the area, use statistical software (such as Python, R or Excel) to process the data, record the energy efficiency of each area, record the calculated energy efficiency values ​​in the database, and form a regional energy efficiency data set. According to industry standards or historical data, set thresholds for equipment energy consumption to identify high-energy consumption areas, ensure that the thresholds are in line with the actual situation and energy-saving goals of the building, analyze the energy efficiency values ​​of different areas in the building, identify areas with energy efficiency below the preset threshold, and record the names, locations and energy consumption values ​​of these high-energy consumption areas for subsequent optimization Analyze, organize and record the data of identified high-energy consumption areas to form a high-energy consumption area data set, determine the goals of energy consumption optimization, such as reducing energy consumption in specific areas, improving energy efficiency, etc., formulate standards and methods for optimization analysis, such as simulation-based optimization algorithms, select appropriate energy consumption analysis tools (such as EnergyPlus, eQuest or custom models), conduct detailed analysis of high-energy consumption areas, calculate potential energy savings and the feasibility of optimization measures, and generate equipment energy consumption optimization data based on the analysis results, including recommended optimization measures, expected energy-saving effects and implementation costs. Record these data in the database for subsequent use, and design a collaborative reinforcement learning framework that can be combined with multi-period regional light source compensation Compensation control strategy and space intelligent temperature control strategy, define states, actions and reward mechanisms so that the model can learn and self-optimize, use historical energy consumption data and optimization data to train the intelligent energy consumption regulation model, optimize its decision-making ability, adjust model parameters through simulation and actual operation data to ensure that it can adapt to different operating environments, verify the constructed intelligent energy consumption regulation model to ensure its effectiveness in practical applications, continuously optimize the model according to feedback results, improve its intelligent decision-making ability and energy consumption management efficiency, integrate the trained intelligent energy consumption regulation model into the building management system, realize real-time energy consumption regulation and energy-saving management, set up a monitoring interface in the system, and facilitate managers to monitor and adjust energy consumption management strategies in real time.

[0163] In this embodiment, a building energy-saving management system based on the Internet of Things is provided, which is used to execute the building energy-saving management method based on the Internet of Things as described above, including:

[0164] The three-dimensional structure module is used to obtain the target building design drawing; identify the building structure feature points of the target building design drawing, perform three-dimensional space point cloud modeling, and construct a three-dimensional structural model of the building;

[0165] The light intensity distribution module is used to collect building environment lighting parameters and personnel flow monitoring parameters based on multiple sensor nodes; analyze the spatial distribution of ambient light intensity of building environment lighting parameters, and then perform dynamic light intensity distribution rendering to build an ambient light intensity distribution rendering model;

[0166] The optimal lighting demand module is used to analyze the regional usage scenarios of the ambient light intensity distribution rendering model according to the three-dimensional structural model of the building, and to fit the optimal timing lighting demand, so as to construct the optimal lighting demand timing curve for each area;

[0167] The light source compensation control module is used to calculate the optimal light source compensation in multiple time periods based on the optimal lighting demand timing curve of each area, and dynamically control the building lighting equipment to build a multi-time regional light source compensation control strategy;

[0168] The temperature control decision module is used to predict the regional temperature change trend based on the personnel flow monitoring parameters of the building's three-dimensional structural model, make intelligent temperature control demand decisions, and build a space intelligent temperature control strategy;

[0169] The intelligent energy consumption control module is used to perform intelligent control and collaborative reinforcement learning of building equipment based on multi-period regional light source compensation control strategy and space intelligent temperature control strategy, build an intelligent energy consumption control model, and perform building energy-saving management operations.

[0170] The present invention helps to construct an accurate three-dimensional structural model of the building by acquiring the target building design drawing and identifying the characteristic points of the building structure. Through three-dimensional space point cloud modeling, it can provide basic data for subsequent steps to achieve more accurate lighting and temperature control model construction, collect building environment lighting parameters and personnel flow monitoring parameters, which can help analyze the light intensity distribution of the building environment. The construction of a dynamic light intensity distribution rendering model helps to establish a real lighting condition and provide data support for the optimal lighting demand module. By analyzing the three-dimensional structural model of the building and the ambient light intensity distribution rendering model, regional usage scenario analysis and optimal time-series lighting demand fitting are achieved, and the optimal lighting demand time-series curve for each area is constructed, which helps to optimize the operating efficiency of the building lighting system and improve energy utilization. The optimal light source compensation calculation for multiple time periods is performed according to the optimal lighting demand timing curve to realize dynamic control of building lighting equipment, and a multi-time regional light source compensation control strategy is constructed to effectively adjust the light source brightness and time, improve the lighting effect, and reduce energy consumption at the same time. Based on the building structure and personnel flow monitoring parameters, the regional temperature change trend is predicted, and intelligent temperature control demand decision-making is realized. The construction of space intelligent temperature control strategy is helpful to optimize the operation of the building's heating and cooling systems, improve comfort, and reduce energy consumption. Combined with the light source compensation control strategy and the space intelligent temperature control strategy, the intelligent regulation and collaborative reinforcement learning of building equipment are realized, and an intelligent energy consumption regulation model is constructed. The building energy consumption can be monitored and adjusted in real time, the energy utilization efficiency is improved, and the energy-saving management goal is achieved.

[0171] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0172] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A building energy-saving management method based on the Internet of Things, characterized in that: The following steps are involved: Step S1: Obtain a target building design drawing; Identify the building structure feature points of the target building design drawing, perform three-dimensional space point cloud modeling, and construct a three-dimensional structural model of the building; Step S2: Collecting building environment lighting parameters and personnel flow monitoring parameters based on multiple sensor nodes; Perform spatial distribution analysis of ambient light intensity on building environment lighting parameters, then perform dynamic light intensity distribution rendering to build an ambient light intensity distribution rendering model; Step S3: Perform regional usage scenario analysis on the ambient light intensity distribution rendering model according to the three-dimensional structural model of the building, and perform optimal timing lighting demand fitting, so as to construct the optimal lighting demand timing curve for each area; Step S4: Calculate the optimal light source compensation in multiple time periods based on the optimal lighting demand time series curve of each area, dynamically control the building lighting equipment, and construct a multi-time regional light source compensation control strategy; Step S5: predicting the regional temperature change trend of the personnel flow monitoring parameters according to the three-dimensional structural model of the building, making intelligent temperature control demand decisions, and building a space intelligent temperature control strategy; Step S6: Perform intelligent control of building equipment and collaborative reinforcement learning based on the multi-period regional light source compensation control strategy and the space intelligent temperature control strategy, and build an intelligent energy consumption control model to perform building energy-saving management operations.

2. The building energy-saving management method based on the Internet of Things according to claim 1 is characterized in that: The specific steps of step S1 are: Step S11: Obtaining a target building design drawing; Step S12: Identify the architectural structural feature points of the target architectural design drawing and mark a plurality of structural feature points; Step S13: performing spatial layout distribution analysis on a plurality of structural feature points to generate spatial layout distribution data; Step S14: performing regional geometry calculation on the target building design drawing to generate multiple regional geometry data in the building; Step S15: Perform three-dimensional spatial point cloud modeling on the geometric data of multiple areas in the building according to the spatial layout distribution data to construct a three-dimensional structural model of the building.

3. The building energy-saving management method based on the Internet of Things according to claim 1 is characterized in that: The specific steps of step S2 are: Step S21: Collecting building environment lighting parameters and personnel flow monitoring parameters based on multiple sensor nodes; Step S22: positioning the multi-sensor nodes in the internal space of the building to generate the spatial position coordinates of each node; Step S23: Calculating the illumination intensity of the building environment illumination parameters to generate an ambient illumination intensity value; Step S24: performing an ambient light intensity spatial distribution analysis on the ambient light intensity value based on the spatial position coordinates of each node to generate building ambient light intensity spatial distribution data; Step S25: Perform dynamic light intensity distribution rendering on the building environment light intensity spatial distribution data to construct an environment light intensity distribution rendering model.

4. The building energy-saving management method based on the Internet of Things according to claim 3 is characterized in that: The specific steps of step S25 are: Perform building light orientation analysis on the building's 3D structural model to identify the light orientation characteristics of different areas; Perform dynamic ray tracing on the lighting parameters of the building environment to generate dynamic ray tracing trajectories; Based on the light direction characteristics of different areas, the dynamic ray tracing trajectory is simulated to simulate the illumination time series change, so as to generate the illumination time series change trajectory of different areas; According to the illumination time series variation trajectory of different areas, the illumination time series intensity fluctuation of the spatial distribution data of the building environment light intensity is calculated to generate the time series light intensity fluctuation characteristics of different areas; Based on the temporal light intensity fluctuation characteristics of different areas, the three-dimensional structural model of the building is dynamically rendered with light intensity distribution, and an ambient light intensity distribution rendering model is constructed.

5. The building energy-saving management method based on the Internet of Things according to claim 1 is characterized in that: The specific steps of step S3 are: Step S31: classifying the building three-dimensional structure model into functional areas to obtain a plurality of building functional classifications; Step S32: performing regional usage scenario analysis based on multiple building function classifications, thereby generating multiple regional usage scenarios; Step S33: performing multi-period usage demand analysis on the usage scenarios of multiple regions to obtain the multi-period usage demand characteristics of each region; Step S34: performing dynamic lighting demand analysis on the multi-period usage demand characteristics of each area to generate multi-period dynamic lighting demand characteristics of each area; Step S35: fitting the optimal time series lighting demand for the multi-period dynamic lighting demand characteristics of each area, thereby constructing the optimal lighting demand time series curve for each area.

6. The building energy-saving management method based on the Internet of Things according to claim 1 is characterized in that: The specific steps of step S4 are: Step S41: performing regional temporal light intensity evolution based on the ambient light intensity distribution rendering model, and extracting temporal ambient light intensity parameters of different regions; Step S42: calculating the time-period light intensity deviation of the ambient time-series light intensity parameters of different areas according to the multi-time period dynamic light demand characteristics of each area, thereby obtaining the time-series light intensity deviation data of different areas; Step S43: performing multi-period optimal light source compensation calculation on the time-series light intensity deviation data of different regions based on the optimal light demand time-series curve of each region, thereby generating regional optimal light source compensation parameters for multiple time periods; Step S44: dynamically control the building lighting equipment based on the regional optimal light source compensation parameters in multiple time periods, and construct a multi-time period regional light source compensation control strategy.

7. The building energy-saving management method based on the Internet of Things according to claim 1 is characterized in that: The specific steps of step S5 are: Step S51: performing regional activity trajectory analysis on personnel flow monitoring parameters according to the three-dimensional structural model of the building to generate multi-region personnel activity trajectories; Step S52: Calculate the regional stay time of the personnel flow monitoring parameters to obtain the stay time in different areas; Step S53: quantifying the usage frequency of people in each area based on the activity trajectories of people in multiple areas and the length of stay in different areas, thereby generating the usage frequency characteristics of people in different areas; Step S54: performing spatial heat transfer evolution based on multi-region personnel activity trajectories, thereby generating a spatial heat transfer law; Step S55: predicting the regional temperature change trend based on the frequency of use of personnel in different areas and the law of space heat transfer, thereby generating temperature change trend prediction data for different areas; Step S56: Make intelligent temperature control demand decisions based on the temperature change trend prediction data of different areas and build a space intelligent temperature control strategy.

8. The building energy-saving management method based on the Internet of Things according to claim 7 is characterized in that: The specific steps of step S54 are: Acquire building internal temperature monitoring parameters based on multi-sensor nodes; Conduct three-dimensional spatial temperature distribution analysis on the temperature monitoring parameters inside the building to generate three-dimensional spatial temperature distribution characteristics; Perform temperature propagation analysis on the three-dimensional spatial temperature distribution characteristics to generate spatial temperature propagation characteristics; Analyze the impact of local heat propagation on the activity trajectories of people in multiple regions, and generate the local heat propagation law of people flow; The spatial heat transfer evolution is carried out on the local heat propagation law of personnel flow and the spatial temperature propagation characteristics, thereby generating the spatial heat transfer law.

9. The building energy-saving management method based on the Internet of Things according to claim 1 is characterized in that: The specific steps of step S6 are: Step S61: Perform intelligent control of building equipment according to the multi-period regional light source compensation control strategy and the space intelligent temperature control strategy, and collect energy consumption parameters of building equipment; Step S62: Calculate the regional energy efficiency of the building equipment energy consumption parameters, thereby generating energy efficiency values ​​for different areas in the building; Step S63: identifying high energy consumption areas based on the energy efficiency values ​​of different areas in the building based on the preset equipment energy consumption threshold, thereby extracting equipment high energy consumption areas; Step S64: performing energy consumption optimization analysis on the high energy consumption area of ​​the equipment, thereby generating equipment energy consumption optimization data; Step S65: Based on the equipment energy consumption optimization data, collaborative reinforcement learning is performed on the multi-period regional light source compensation control strategy and the space intelligent temperature control strategy to build an intelligent energy consumption regulation model to perform building energy-saving management operations.

10. A building energy-saving management system based on the Internet of Things, characterized in that: The method for executing the building energy-saving management method based on the Internet of Things as claimed in claim 1 comprises: The three-dimensional structure module is used to obtain the target building design drawing; identify the building structure feature points of the target building design drawing, perform three-dimensional space point cloud modeling, and construct a three-dimensional structural model of the building; The light intensity distribution module is used to collect building environment lighting parameters and personnel flow monitoring parameters based on multiple sensor nodes; analyze the spatial distribution of ambient light intensity of building environment lighting parameters, and then perform dynamic light intensity distribution rendering to build an ambient light intensity distribution rendering model; The optimal lighting demand module is used to analyze the regional usage scenarios of the ambient light intensity distribution rendering model according to the three-dimensional structural model of the building, and to fit the optimal timing lighting demand, so as to construct the optimal lighting demand timing curve for each area; The light source compensation control module is used to calculate the optimal light source compensation in multiple time periods based on the optimal lighting demand timing curve of each area, and dynamically control the building lighting equipment to build a multi-time regional light source compensation control strategy; The temperature control decision module is used to predict the regional temperature change trend based on the personnel flow monitoring parameters of the building's three-dimensional structural model, make intelligent temperature control demand decisions, and build a space intelligent temperature control strategy; The intelligent energy consumption control module is used to perform intelligent control and collaborative reinforcement learning of building equipment based on multi-period regional light source compensation control strategy and space intelligent temperature control strategy, build an intelligent energy consumption control model, and perform building energy-saving management operations.

Images