A multi-scene linkage intelligent energy-saving lighting control method

Abstract

The application discloses a multi-scene linkage intelligent energy-saving lighting control method, comprising the following steps: S1, multi-dimensional scene data real-time acquisition, building a global data acquisition system covering multi-scene dimensions, real-time acquisition of four-dimensional original data of space human settlement scene data, environmental meteorological scene data, building equipment working condition scene data and power grid energy consumption load scene data, breaking the rigid control logic of traditional intelligent lighting single dimension and fixed segmented scene, innovatively constructing a four-dimensional scene coupling linkage model of human settlement, meteorology, equipment and power grid, realizing full-scene continuous dynamic adaptive regulation and control relying on edge computing and machine learning, and completely solving the industry pain points of scene fragmentation, regulation lag and one-sided judgment of the traditional scheme.

Description

Technical Field

[0001] This invention relates to the field of intelligent lighting control related products, specifically a multi-scene linkage intelligent energy-saving lighting control method. Background Technology

[0002] With the rapid advancement of smart city and green building construction, intelligent lighting systems have been widely applied in various building scenarios. As an important component of building energy consumption, intelligent energy-saving control of lighting is one of the core aspects of building energy conservation and consumption reduction. Currently, the intelligent lighting control solutions on the market have relatively simple control logic, mostly relying on a single ambient light sensor, human infrared sensor, or preset fixed timing program to achieve lighting control, and generally adopt a segmented fixed scene switching control mode.

[0003] Existing technologies suffer from several inherent flaws: First, they rely on a single control dimension, depending solely on data such as illumination, human body sensing, or time series to determine control needs, without considering factors related to living experience, building equipment operation, and power grid load. This results in low control accuracy and issues such as lights being on when no one is present, lights being off when someone is present, and poor matching of lighting color temperature and brightness with the scene. Second, scene switching is rigid, employing a fixed segmented scene switching mode that cannot adapt to dynamically changing and complex living and environmental scenarios. Scene switching exhibits lag and limitations, failing to achieve continuous adaptive control. Third, there is an imbalance between energy saving and user experience. Traditional control solutions often prioritize either energy saving or comfort, failing to balance the user experience with optimal overall energy consumption. This often results in sacrificing lighting experience for energy saving or wasting energy for comfort. Fourth, cross-system coordination is poor. Lighting systems operate independently, without linkage with building HVAC, ventilation, and power grid dispatch systems. The fragmented operation of each device easily leads to redundant energy consumption across the entire area, resulting in limited overall energy-saving effects. Summary of the Invention

[0004] The purpose of this invention is to provide a multi-scene linkage intelligent energy-saving lighting control method to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a multi-scene linkage intelligent energy-saving lighting control method, comprising the following steps:

[0006] S1. Real-time collection of multi-dimensional scene data: Build a full-domain data collection system covering multiple scene dimensions, and collect raw data in real time from four dimensions: spatial human settlement scene data, environmental meteorological scene data, building equipment operating condition scene data, and power grid energy consumption load scene data.

[0007] S2. Multi-source data preprocessing and feature fusion: Cleaning, noise reduction, and normalization preprocessing are performed on the collected raw data of the four dimensions to remove abnormal interference data, extract the core feature parameters of each scene dimension, complete the feature-level deep fusion of cross-scene data, and generate a comprehensive scene feature vector.

[0008] S3. Construct a multi-scenario coupled linkage control model, abandon the traditional segmented fixed scene switching logic, build an integrated coupled linkage model of four major scenarios: human settlement, meteorology, equipment, and power grid, and establish a dynamic and continuous mapping relationship between scene parameters and lighting control parameters.

[0009] S4. Dual-constraint objective optimization solution: With optimal human comfort and minimum energy consumption across the entire area as dual-constraint optimization objectives, a multi-objective optimization function is constructed, and the optimal combination of lighting control parameters is solved in real time through edge computing units.

[0010] S5. Dynamic adaptive lighting control closed-loop execution: Based on the optimal control parameters obtained through iterative solution, the brightness, color temperature, and start / stop status of lighting equipment are dynamically and adaptively adjusted in real time. The system continuously monitors changes in scene data, iterates and updates the control strategy in a closed loop, and achieves dynamic energy-saving control across the entire domain.

[0011] As a preferred embodiment of the present invention, the specific acquisition parameters of the four dimensions of raw data in step S1 include:

[0012] The spatial living scene data includes spatial personnel distribution density, personnel activity status, personnel stay duration, perceived temperature of the living space, user lighting preference parameters, and spatial usage function status;

[0013] The environmental meteorological scene data includes ambient light intensity, ambient temperature and humidity, rain and snow weather conditions, day and night time periods, and air quality parameters;

[0014] The building equipment operating condition scenario data includes air conditioning operating conditions, fresh air system operating status, building door and window opening and closing status, building space ventilation status, and load parameters of supporting electrical equipment.

[0015] The power grid energy consumption load scenario data includes real-time power grid load, power grid peak and valley periods, regional energy consumption quotas, power grid voltage fluctuation parameters, and real-time electricity consumption data.

[0016] As a preferred embodiment of the present invention, step S2 is specifically implemented as follows:

[0017] Median filtering algorithm is used to remove abrupt and abnormal data collected by the sensor, thus completing data noise reduction and cleaning;

[0018] By using a linear normalization algorithm, scene data of different magnitudes and dimensions are uniformly mapped to the 0-1 standard range, eliminating differences in data dimensions.

[0019] Based on the influence weight of each scene dimension on lighting control, a dynamic weighted fusion algorithm is used to dynamically allocate weight coefficients and extract the fused comprehensive scene feature vector.

[0020] As a preferred embodiment of the present invention, the multi-scene coupling and linkage control model described in step S3 establishes a continuous coupling and association mechanism for the entire scene. It uses four-dimensional scene features as model input variables and lighting brightness, color temperature, and start / stop status as model output control variables. The model is trained by machine learning algorithm to dynamically associate scene features with lighting parameters, abandoning the fixed scene level switching mode, realizing uninterrupted and adaptive scene linkage control, and eliminating the defects of scene switching lag and rigid control.

[0021] As a preferred embodiment of the present invention, the method for constructing and solving the dual-constraint optimization objective in step S4 includes:

[0022] A human living comfort evaluation model is constructed, and the lighting comfort score is quantified based on the characteristics of human visual vision and the parameters of the tactile environment to achieve the quantitative evaluation of the optimal human living comfort.

[0023] Construct a full-domain energy consumption calculation model to statistically analyze the real-time energy consumption of lighting equipment, the collaborative energy consumption of building supporting equipment, and the energy consumption loss of power grid load, so as to achieve quantitative statistics of the target of minimum energy consumption across the entire domain.

[0024] By using a multi-objective genetic algorithm to perform weighted optimization on the dual-constraint objectives, the system dynamically balances the living lighting experience with the energy-saving requirements of the entire area, and outputs the optimal combination of lighting control parameters.

[0025] As a preferred embodiment of the present invention, the specific logic of the edge computing real-time iterative update strategy in step S5 is as follows: the edge computing unit independently completes multi-source scene data processing and model calculation locally, avoids remote transmission delay in the cloud, and sets a regular iteration cycle of 1-5 seconds to complete scene data updates and control parameter iterations; when the scene data fluctuation exceeds the preset threshold, the control strategy is immediately triggered for emergency dynamic update, realizing millisecond-level adaptive adjustment of the lighting state.

[0026] As a preferred embodiment of the present invention, it also includes a model self-learning optimization step: the system collects massive amounts of scene control data, energy consumption data and user manual adjustment feedback data over a long period of time, and continuously iterates and optimizes the weight parameters and dual-objective optimization function coefficients of the multi-scene coupled linkage model through deep learning algorithms, so as to adaptively adapt to the personalized lighting control needs of different building spaces and different user groups, and realize the model's autonomous iterative upgrade.

[0027] Preferably, the present invention further includes a cross-system collaborative linkage step across the entire region: Based on the result of deep integration of multi-scenario data, real-time collaborative linkage control of the lighting system, the building HVAC system, the fresh air system, and the power grid dispatching system is achieved, and the lighting strategy is adjusted synchronously by matching the working conditions of building equipment and the load status of the power grid, avoiding energy consumption waste and scenario adaptation conflicts caused by independent control of multiple devices, and improving the intelligent collaborative management and energy-saving level of the entire building region.

[0028] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0029] The present invention breaks the rigid control logic of traditional intelligent lighting in a single dimension and fixed segmented scenarios, innovatively constructs a coupling and linkage model for scenarios in four dimensions: human settlement, meteorology, equipment, and power grid, and realizes full-scenario continuous dynamic adaptation control relying on edge computing and machine learning, completely solving the industry pain points of scenario fragmentation, control lag, and one-sided judgment in traditional solutions; at the same time, it is equipped with a deep learning self-learning mechanism, which can adapt to the personalized lighting needs of different building spaces and populations, has high adaptability and scalability, and greatly improves the control accuracy and intelligent level of the intelligent lighting system.

[0030] The present invention first creates a comfort experience and overall energy consumption dual-constraint optimization control mechanism, solves the core problem of the imbalance between traditional lighting energy conservation and human settlement experience, maximizes the reduction of building energy consumption on the basis of ensuring a high-quality lighting experience; at the same time, it breaks through the collaborative barriers between the lighting system and the building HVAC, fresh air, and power grid dispatching systems, realizes multi-device and cross-system linkage control, effectively reduces overall energy consumption redundancy, meets the overall energy conservation and intelligent management needs of green buildings and smart buildings, and has significant comprehensive application benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 is a schematic flow chart of a multi-scenario linkage intelligent energy-saving lighting control method of the present invention;

[0032] Figure 2 is a schematic diagram of the construction and solution method of the dual-constraint optimization objective of a multi-scenario linkage intelligent energy-saving lighting control method of the present invention;

[0033] Figure 3 is a schematic diagram of the edge computing real-time iterative update strategy of a multi-scenario linkage intelligent energy-saving lighting control method of the present invention;

[0034] Figure 4 is a schematic diagram of the self-learning optimization process of the edge model of a multi-scenario linkage intelligent energy-saving lighting control method of the present invention;

[0035] Figure 5 is a schematic diagram of the cross-system collaborative linkage process across the entire region of a multi-scenario linkage intelligent energy-saving lighting control method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0036] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0037] In the description of this invention, it should be noted that the terms "upper," "lower," "inner," "outer," "front end," "rear end," "both ends," "one end," and "the other end," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0038] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installed," "equipped with," "connected," etc., should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0039] Please see Figure 1-5 This invention provides an embodiment of a multi-scene linkage intelligent energy-saving lighting control method, comprising the following steps: Step 1, multi-dimensional data collection across the entire area. Human body sensing sensors, light sensors, temperature and humidity sensors, and meteorological data collection terminals are deployed in various functional spaces of the office building. Simultaneously, the system connects to the building equipment management system and the power grid energy consumption monitoring system to collect real-time data on four dimensions of scenarios: personnel distribution, activity status, occupancy comfort, ambient light, temperature and humidity, rain and snow weather, air conditioning and fresh air operation status, door and window status, real-time power grid load, and peak and off-peak periods. The data collection frequency is 1 second / time.

[0040] Step 2: Multi-source data preprocessing and fusion. The collected real-time data undergoes outlier removal, noise reduction, and normalization, mapping all scene data to the 0-1 range. Based on the characteristics of the office scene, data weights are assigned to each dimension: 0.4 for residential scenes, 0.3 for environmental meteorology, 0.15 for building equipment operating conditions, and 0.15 for power grid load. A weighted fusion algorithm is then used to generate a comprehensive scene feature vector.

[0041] Step 3: Construction and Training of Multi-Scene Coupling Model. Based on historical data and real-time fusion features of office scenarios, a multi-scene coupling and linkage control model is built. Through machine learning training, the dynamic mapping relationship between scene features and lighting brightness, color temperature, and start / stop parameters is trained, eliminating the traditional fixed segmented scene levels such as office, rest, and lunch break, and realizing continuous and uninterrupted matching control of scenes.

[0042] Step 4: Dual-Constraint Objective Optimization Solution. With the optimal visual and physical comfort for office workers as the experience objective, and the lowest overall energy consumption for office lighting, building equipment, and power grid load as the energy-saving objective, a multi-objective genetic algorithm iteratively solves for the optimal lighting parameters. During weekdays with sufficient natural light, the lighting brightness is dynamically reduced based on occupant activity levels to adapt to the natural light environment; on cloudy or rainy days and at night, the lighting brightness is automatically increased and the color temperature optimized to ensure office comfort; during peak power grid load periods, lighting energy consumption is moderately optimized without affecting the living experience, reducing the pressure on the power grid load.

[0043] Step 5: Edge Computing Dynamic Control Execution. Data processing and model calculations are completed locally through the on-site edge computing gateway, iterating the control strategy every 2 seconds. When people enter or leave the office area, the weather changes, air conditioning equipment starts or stops, or the power grid load fluctuates, the system updates the control parameters in real time, dynamically adjusting the lighting on / off, brightness, and color temperature. For example, when there are many people in the office, it automatically adjusts to a high-brightness, neutral color temperature office mode; when there is sporadic activity, the brightness is appropriately reduced to balance comfort and energy saving; during off-peak hours, priority is given to ensuring a comfortable lighting experience; during peak hours, refined energy-saving control is implemented.

[0044] Step 6: Self-learning and cross-system collaborative optimization. The system stores daily office scenario control data, energy consumption data, and user manual adjustment feedback, and performs model parameter self-optimization weekly. Simultaneously, it collaborates with air conditioning and fresh air systems to match appropriate lighting color temperature and brightness when building ventilation, temperature, and humidity conditions change, ensuring overall spatial comfort and achieving intelligent collaborative energy saving throughout the building.

[0045] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A multi-scene linkage intelligent energy-saving lighting control method, characterized in that, Includes the following steps: S1. Real-time collection of multi-dimensional scene data: Build a full-domain data collection system covering multiple scene dimensions, and collect raw data in real time from four dimensions: spatial human settlement scene data, environmental meteorological scene data, building equipment operating condition scene data, and power grid energy consumption load scene data. S2. Multi-source data preprocessing and feature fusion: Cleaning, noise reduction, and normalization preprocessing are performed on the collected raw data of the four dimensions to remove abnormal interference data, extract the core feature parameters of each scene dimension, complete the feature-level deep fusion of cross-scene data, and generate a comprehensive scene feature vector. S3. Construct a multi-scenario coupled linkage control model, abandon the traditional segmented fixed scene switching logic, build an integrated coupled linkage model of four major scenarios: human settlement, meteorology, equipment, and power grid, and establish a dynamic and continuous mapping relationship between scene parameters and lighting control parameters. S4. Dual-constraint objective optimization solution: With optimal human comfort and minimum energy consumption across the entire area as dual-constraint optimization objectives, a multi-objective optimization function is constructed, and the optimal combination of lighting control parameters is solved in real time through edge computing units. S5. Dynamic adaptive lighting control closed-loop execution: Based on the optimal control parameters obtained through iterative solution, the brightness, color temperature, and start / stop status of lighting equipment are dynamically and adaptively adjusted in real time. The system continuously monitors changes in scene data, iterates and updates the control strategy in a closed loop, and achieves dynamic energy-saving control across the entire domain.

2. The intelligent energy-saving lighting control method with multi-scene linkage according to claim 1, characterized in that, In step S1, the specific collection parameters for the four dimensions of raw data include: The spatial living scene data includes spatial personnel distribution density, personnel activity status, personnel stay duration, perceived temperature of the living space, user lighting preference parameters, and spatial usage function status; The environmental meteorological scene data includes ambient light intensity, ambient temperature and humidity, rain and snow weather conditions, day and night time periods, and air quality parameters; The building equipment operating condition scenario data includes air conditioning operating conditions, fresh air system operating status, building door and window opening and closing status, building space ventilation status, and load parameters of supporting electrical equipment. The power grid energy consumption load scenario data includes real-time power grid load, power grid peak and valley periods, regional energy consumption quotas, power grid voltage fluctuation parameters, and real-time electricity consumption data.

3. The intelligent energy-saving lighting control method with multi-scene linkage according to claim 1, characterized in that, The specific implementation methods of step S2 include: Median filtering algorithm is used to remove abrupt and abnormal data collected by the sensor, thus completing data noise reduction and cleaning; By using a linear normalization algorithm, scene data of different magnitudes and dimensions are uniformly mapped to the 0-1 standard range, eliminating differences in data dimensions. Based on the influence weight of each scene dimension on lighting control, a dynamic weighted fusion algorithm is used to dynamically allocate weight coefficients and extract the fused comprehensive scene feature vector.

4. The intelligent energy-saving lighting control method with multi-scene linkage according to claim 1, characterized in that, The multi-scene coupling and linkage control model described in step S3 establishes a continuous coupling and association mechanism for the entire scene. It uses four dimensions of scene features as model input variables and lighting brightness, color temperature, and start / stop status as model output control variables. The model is trained by machine learning algorithm to dynamically associate scene features with lighting parameters, abandoning the fixed scene level switching mode, realizing uninterrupted and adaptive scene linkage control, and eliminating the defects of scene switching lag and rigid control.

5. The intelligent energy-saving lighting control method with multi-scene linkage according to claim 1, characterized in that, The construction and solution methods for the dual-constraint optimization objective in step S4 include: A human living comfort evaluation model is constructed, and the lighting comfort score is quantified based on the characteristics of human visual vision and the parameters of the tactile environment to achieve the quantitative evaluation of the optimal human living comfort. Construct a full-domain energy consumption calculation model to statistically analyze the real-time energy consumption of lighting equipment, the collaborative energy consumption of building supporting equipment, and the energy consumption loss of power grid load, so as to achieve quantitative statistics of the target of minimum energy consumption across the entire domain. By using a multi-objective genetic algorithm to perform weighted optimization on the dual-constraint objectives, the system dynamically balances the living lighting experience with the energy-saving requirements of the entire area, and outputs the optimal combination of lighting control parameters.

6. The intelligent energy-saving lighting control method with multi-scene linkage according to claim 1, characterized in that, The specific logic of the edge computing real-time iterative update strategy in step S5 is as follows: the edge computing unit independently completes multi-source scene data processing and model calculation locally, avoiding remote transmission delays in the cloud, and sets a regular iteration cycle of 1-5 seconds to complete scene data updates and control parameter iterations; when the scene data fluctuation exceeds the preset threshold, the control strategy is immediately triggered for emergency dynamic update, realizing millisecond-level adaptive adjustment of the lighting status.

7. The intelligent energy-saving lighting control method with multi-scene linkage according to claim 1, characterized in that, It also includes a model self-learning optimization step: the system collects massive amounts of scene control data, energy consumption data and user manual adjustment feedback data over a long period of time, and continuously iterates and optimizes the weight parameters and dual-objective optimization function coefficients of the multi-scene coupled linkage model through deep learning algorithms, so as to adaptively adapt to the personalized lighting control needs of different building spaces and different user groups, and realize the model's autonomous iterative upgrade.

8. The intelligent energy-saving lighting control method with multi-scene linkage according to claim 1, characterized in that, It also includes a cross-system collaborative linkage step: based on the deep fusion results of multi-scenario data, it realizes real-time collaborative linkage control of the lighting system with the building HVAC system, fresh air system, and power grid dispatching system, and synchronously matches the building equipment operating conditions and power grid load status to adjust the lighting strategy, avoids energy waste and scenario adaptation conflicts caused by independent control of multiple devices, and improves the intelligent collaborative management and energy-saving level of the entire building.

Images