A Distributed Intelligent Lighting Control Method and System Based on Edge Computing

Abstract

This invention discloses a distributed intelligent lighting control method and system based on edge computing, belonging to the field of intelligent lighting technology. The system includes a distributed lighting node module, an edge computing node module, a cloud collaboration module, a multimodal sensing module, a communication module, and a user interaction module. These modules are deployed in a distributed manner, achieving an organic combination of localized control and cloud-based collaborative management. The multimodal sensing module collects multi-dimensional data such as illumination, personnel, temperature, and humidity within the area. The edge computing node module completes lighting control decisions through localized computation. This invention also discloses the corresponding control method, including steps such as initialization, data acquisition and preprocessing, localized control, distributed collaboration, and cloud optimization. This invention solves the shortcomings of existing systems, such as high response latency, poor fault tolerance, low control accuracy, and high energy consumption, achieving precise, rapid, and energy-saving lighting control, improving system stability and scalability, and adapting to various application scenarios.

Description

Technical Field

[0001] This invention relates to the field of intelligent lighting technology, specifically to a distributed intelligent lighting control method and system based on edge computing. Background Technology

[0002] With the rapid development of smart cities, smart parks, and smart homes, intelligent lighting systems have been widely applied in various scenarios. Their core requirements are to achieve precise lighting control, energy saving, and convenient management. Currently, most existing intelligent lighting systems adopt a centralized control architecture, which collects lighting data and issues control commands through cloud servers or central controllers. This approach suffers from prominent problems such as high response latency, reliance on network bandwidth, poor fault tolerance, and high energy consumption.

[0003] Specifically, in a centralized control architecture, the status data of all lighting nodes must be uploaded to the cloud or central controller, and control commands must also be issued from the cloud / central controller to each node. When there are a large number of lighting nodes (such as in large parks or office buildings), a large amount of data transmission will be generated, consuming a large amount of network bandwidth. Moreover, delays are prone to occur during data transmission, resulting in untimely control and affecting user experience. At the same time, if the cloud server or central controller fails, the entire lighting system will be paralyzed, with extremely poor fault tolerance. In addition, centralized control cannot perform localized adaptive control based on the real-time scene of each area (such as human presence, light intensity, and environmental requirements), and often adopts a uniform lighting strategy, resulting in serious energy waste.

[0004] In existing technologies, some solutions attempt to incorporate edge computing, but these are mostly simple edge node deployments that fail to achieve true distributed collaborative control. There is a lack of efficient data interaction and collaboration mechanisms between edge nodes and the cloud, and between edge nodes themselves, failing to fully leverage the low latency and localized processing advantages of edge computing. Furthermore, control strategies are often based on single-sensor data (such as only light intensity), without integrating multi-dimensional data for precise analysis, resulting in low control accuracy and difficulty in meeting the personalized lighting needs of different scenarios. In addition, existing systems suffer from poor compatibility of lighting nodes, making it difficult to achieve collaborative control of different brands and types of lighting equipment, and lack robust fault monitoring and self-healing mechanisms, leading to high maintenance costs.

[0005] Therefore, developing a distributed intelligent lighting control method and system based on edge computing to achieve localized processing and distributed collaborative control of lighting nodes, improve control response speed, accuracy and system stability, and reduce energy consumption and maintenance costs has become an urgent technical problem to be solved. Summary of the Invention

[0006] (a) Technical problems to be solved To address the shortcomings of existing technologies, this invention provides a distributed intelligent lighting control method and system based on edge computing. By localized data processing and distributed collaboration of edge nodes, combined with multimodal sensing data fusion, it achieves precise, rapid, and energy-saving control of lighting, improves system stability and scalability, and solves the problems of high response latency, reliance on network bandwidth, poor fault tolerance, low control accuracy, and high energy consumption in existing intelligent lighting systems.

[0007] (II) Technical Solution To achieve the above objectives, the present invention provides the following technical solution: a distributed intelligent lighting control system based on edge computing, the system comprising a distributed lighting node module, an edge computing node module, a cloud collaboration module, a multimodal sensing module, a communication module, and a user interaction module; each module is deployed in a distributed manner, the edge computing node module communicates locally with the distributed lighting node module and the multimodal sensing module, and the cloud collaboration module communicates remotely with each edge computing node module, thereby achieving an organic combination of local control and cloud collaborative management.

[0008] Distributed lighting node module: Composed of several intelligent lighting terminals, each with an independent control unit and communication unit, capable of independently receiving control commands and adjusting lighting parameters (brightness, color temperature, on / off status); each intelligent lighting terminal includes an LED light, an intelligent drive module, and a status acquisition unit. The status acquisition unit collects its own operating status data (such as power, temperature, and fault information) and feeds it back to the edge computing node module; each intelligent lighting terminal is divided into regions, with each region corresponding to an edge computing node module, enabling localized control of lighting nodes within the region.

[0009] Edge computing node modules: As the core control unit of the system, they are distributed across various lighting areas. Each edge computing node module controls a corresponding distributed lighting node module and multimodal sensing module in one area. They receive environmental and personnel data collected by the multimodal sensing module, as well as operational status data fed back by the distributed lighting node module, and achieve real-time control of lighting parameters through localized computation. They are also responsible for fault monitoring, data preprocessing, and local storage of lighting nodes within the area, and for collaborative communication with other edge computing node modules to achieve cross-area coordinated lighting control. Lightweight edge computing chips are used, integrating control algorithms and data processing modules to reduce energy consumption and improve response speed.

[0010] Cloud-based collaboration module: Deployed on a cloud server, it establishes remote communication connections with each edge computing node module; it receives aggregated data (such as regional lighting status, energy consumption data, and fault information) uploaded by each edge computing node module, enabling global lighting status monitoring, data statistical analysis, control strategy optimization, and parameter distribution; it supports remote management and configuration of edge computing node modules, and can temporarily take over the lighting control of the area when an edge computing node module fails, ensuring the overall stability of the system; it also stores historical data to provide data support for lighting strategy optimization and energy consumption analysis.

[0011] The communication module is divided into a local communication unit and a remote communication unit. The local communication unit adopts low-power, high-reliability communication protocols such as Zigbee, WiFi, and LoRa to realize local data interaction between edge computing node modules, distributed lighting node modules, and multimodal sensing modules, reducing communication latency. The remote communication unit adopts communication protocols such as 5G and Ethernet to realize remote data transmission between edge computing node modules and cloud collaboration modules, supports encrypted data transmission, and ensures data security. It also supports collaborative communication between edge computing node modules to realize cross-regional data interaction.

[0012] User interaction module: Used to enable interaction between users and the system, including local interaction units (such as touch control panels, voice interaction terminals) and remote interaction units (such as mobile APP, web management platform); users can view the lighting status, energy consumption data, and fault information of each area through the interaction module, customize lighting control parameters (such as brightness threshold, color temperature range), set scene modes (such as office mode, energy-saving mode, emergency mode), and issue manual control commands to achieve convenient management of the lighting system.

[0013] A distributed intelligent lighting control method based on edge computing, implemented based on the aforementioned distributed intelligent lighting control system based on edge computing, includes the following steps: S1. System Initialization Configuration: Start the distributed intelligent lighting control system and complete the self-test and communication connection of each module; divide the edge computing node modules into regions and configure parameters, clarifying the lighting area, number of lighting nodes and layout of sensing modules managed by each edge computing node module; initialize the global control parameters (such as basic energy consumption threshold and emergency lighting parameters) of the cloud collaboration module, initialize the local control strategies (such as light intensity threshold and human presence response threshold) of the edge computing node modules, and initialize each intelligent lighting terminal to the default lighting state (such as brightness 50% and color temperature 4000K) to complete the system initialization.

[0014] S2. Multimodal Data Acquisition and Preprocessing: The multimodal sensing modules in each area collect real-time data on light intensity, personnel presence and location, personnel density, and environmental temperature and humidity within the area. This data is then transmitted to the corresponding edge computing node modules via local communication units. The edge computing node modules preprocess the received raw data, using a moving average algorithm to filter data fluctuations and remove outliers. The data is then converted to a standardized format, and key feature data (such as the presence of personnel and whether the light intensity is below a threshold) is extracted. Simultaneously, the modules receive their own operational status data from the distributed lighting node modules, completing the data aggregation.

[0015] S3. Localized Control Decisions at Edge Nodes: Based on preprocessed multimodal data and combined with local control strategies, the edge computing node module makes localized decisions using a lightweight control algorithm to generate lighting control commands. If people are detected in the area and the light intensity is lower than the preset threshold, the brightness and color temperature of the lighting terminal will be adjusted according to the population density and ambient temperature and humidity (e.g., increase brightness when population density is high and decrease color temperature when temperature and humidity are high). If no one is detected in the area for a preset time (e.g., 5 minutes), a shutdown command is issued to turn off all lighting terminals in the area, thereby saving energy. If an abnormal operating status of the lighting terminal is detected (such as abnormal power or excessive temperature), a stop operation command will be issued immediately, and the fault information will be fed back to the cloud collaboration module. At the same time, the backup lighting terminal in the area will be activated to ensure the continuity of lighting.

[0016] S4. Distributed Collaborative Control: When cross-regional lighting coordination is required (such as continuous areas like corridors and lobbies), each edge computing node module interacts with data through its local communication unit, sharing the sensing data and control status within the region. Based on the collaborative control algorithm, it generates cross-regional linkage control commands to control the coordinated operation of lighting terminals in each region (such as corridor lighting turning on and off sequentially as people move, and the brightness of lobby and corridor lighting being coordinated and matched). The edge computing node module feeds back the collaborative control results to the cloud collaboration module in real time, achieving synchronization between localized collaboration and cloud monitoring.

[0017] S5. Cloud-based Collaborative Optimization and Control: The cloud-based collaborative module receives aggregated data (lighting status, energy consumption data, fault information, and control records) uploaded by each edge computing node module. It analyzes the global lighting status using big data analytics algorithms, optimizes global control strategies (such as adjusting the illumination threshold for each area and optimizing energy-saving parameters), and distributes the optimized strategies to each edge computing node module, enabling dynamic updates of the control strategies. Simultaneously, the cloud-based collaborative module monitors the operational status of each edge computing node module and lighting terminal in real time. If a fault is detected in an edge computing node module, it immediately takes over the lighting control of that area temporarily until the edge node returns to normal. It also regularly generates energy consumption and fault statistics reports to provide decision support for users.

[0018] S6. User Interaction and Manual Control: Users can view the lighting status, energy consumption data, and fault information of each area through the user interaction module, customize lighting control parameters, and set scene modes (such as setting the brightness to 80% and the color temperature to 5000K in office mode, and setting the brightness to 30% and the color temperature to 3000K in energy-saving mode). When manual control is required, the user issues a manual control command, which is transmitted to the corresponding edge computing node module through the local communication unit or the remote communication unit. The edge computing node module executes the command, controls the lighting terminal to adjust to the specified state, and uploads the manual control record to the cloud collaboration module for filing.

[0019] S7. System Maintenance and Self-Healing: The edge computing node module monitors its own and the operating status of the lighting terminals and sensing modules within its control area in real time. If a device failure is detected, it immediately attempts to perform local self-healing (such as restarting the device or switching to a backup communication link). If self-healing fails, the fault information is fed back to the cloud collaboration module and the user interaction module to remind the user to perform maintenance. The cloud collaboration module records fault information and maintenance records to form a fault database, providing support for subsequent system optimization.

[0020] Furthermore, the lightweight control algorithm of the edge computing node module adopts an adaptive algorithm based on reinforcement learning, which can automatically optimize the local control strategy according to user habits and environmental changes (such as differences in illumination caused by seasonal changes), without requiring manual adjustment by the user, thereby further improving the control accuracy and energy-saving effect; at the same time, it integrates an illumination compensation algorithm to solve the problem of uneven illumination in the area and achieve a uniform distribution of lighting brightness.

[0021] Furthermore, the multimodal perception module adds a human motion recognition sensor, which uses image recognition algorithms to identify user actions (such as waving or pausing) to achieve more accurate judgment of human intentions. For example, it can adjust the lighting brightness when a user waves and maintain stable lighting when a user pauses, thus further improving the user experience.

[0022] Furthermore, the communication module adopts a hybrid communication architecture. Local communication prioritizes the LoRa protocol (low power consumption, long distance), which is suitable for scenarios such as large parks. Short-range communication uses the Zigbee protocol (low latency, high reliability) to achieve a balance between communication efficiency and energy consumption. Long-range communication uses 5G narrowband technology to reduce data transmission costs and improve the response speed of remote control.

[0023] Furthermore, the cloud-based collaboration module supports multi-tenant management, enabling it to provide services to multiple users (such as park management, enterprises, and residents) simultaneously. Each user can independently set lighting strategies for their own controlled area, achieving system scalability. It also integrates an energy consumption prediction algorithm to predict future energy consumption based on historical data, providing users with energy-saving suggestions.

[0024] Furthermore, the distributed lighting node module supports hot-swapping, allowing for flexible addition or reduction of lighting terminals according to scenario requirements. The edge computing node module can automatically identify newly added lighting terminals and complete their configuration without system downtime, thus improving the system's flexibility and scalability.

[0025] (III) Beneficial Effects This invention provides a distributed intelligent lighting control method and system based on edge computing. It has the following beneficial effects: 1. Fast response and low latency: This invention adopts edge computing and a distributed architecture. The edge computing node module processes the sensing data and control decisions locally, without having to upload all the data to the cloud, which greatly reduces the amount of data transmission and transmission latency, and realizes real-time response of lighting control (response time ≤100ms). This solves the problem of high latency in centralized control and improves the user experience.

[0026] 2. Strong fault tolerance and high stability: The system adopts a distributed deployment, with each edge computing node module working independently. When a certain edge node fails, the cloud collaboration module can temporarily take over the control, and the lighting system in other areas will not be affected. At the same time, the edge nodes have local self-healing capabilities, which can quickly handle equipment failures, ensure the overall stability of the system, and avoid the defects of "single point of failure" in centralized control.

[0027] 3. Precise control and significant energy saving: By combining multimodal sensing data (light, people, temperature and humidity, etc.), the lighting parameters are precisely controlled through reinforcement learning adaptive algorithms. The lighting status is dynamically adjusted according to people's presence and environmental changes to avoid ineffective lighting and reduce energy consumption by 30%-50%. At the same time, cross-regional collaborative control is achieved to further improve energy saving and lighting comfort.

[0028] 4. Strong compatibility and good scalability: The communication module supports multiple mainstream communication protocols and is compatible with smart lighting terminals and sensing devices of different brands and types, solving the problem of poor compatibility of existing systems; the system supports hot-swapping and multi-tenant management, and can flexibly expand lighting nodes and control areas according to scenario requirements, adapting to application scenarios of different scales (from homes and office buildings to large parks).

[0029] 5. Convenient management and low maintenance costs: Users can achieve comprehensive control of the lighting system through local or remote interactive modules, and view the lighting status, energy consumption data and fault information in real time; the localized fault monitoring and self-healing mechanism of edge nodes reduces the frequency of manual maintenance, and the big data analysis function of the cloud collaboration module provides accurate guidance for maintenance, significantly reducing maintenance costs.

[0030] 6. Low network dependency and wide applicability: The edge computing node module enables localized control, ensuring the normal operation of the lighting system in the area even in the event of a network outage. Only the cloud monitoring and global optimization functions are affected, solving the problem of high network bandwidth dependency of existing systems. It is suitable for scenarios with poor network conditions (such as remote parks and outdoor lighting). Attached Figure Description

[0031] Figure 1 This is a structural block diagram of the distributed intelligent lighting control system based on edge computing according to the present invention; Figure 2 This is a flowchart illustrating the distributed intelligent lighting control method based on edge computing of the present invention. The corresponding numbers in the attached diagram are as follows: 1. Distributed lighting node module; 11. Intelligent lighting terminal; 12. Intelligent drive module; 13. Status acquisition unit; 2. Edge computing node module; 3. Cloud collaboration module; 4. Multimodal perception module; 41. Light sensor; 42. Human infrared sensor; 43. Personnel density sensor; 44. Temperature and humidity sensor; 5. Communication module; 51. Local communication unit; 52. Remote communication unit; 6. User interaction module; 61. Local interaction unit; 62. Remote interaction unit. Detailed Implementation

[0032] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] Example 1: like Figure 1As shown, this embodiment of the invention provides a distributed intelligent lighting control system based on edge computing, including a distributed lighting node module 1, an edge computing node module 2, a cloud collaboration module 3, a multimodal perception module 4, a communication module 5, and a user interaction module 6.

[0034] The distributed lighting node module 1 consists of 20 LED smart lighting terminals 11, divided into 4 areas, with 5 lighting terminals in each area. Each lighting terminal integrates a smart drive module 12 and a status acquisition unit 13. The status acquisition unit 13 collects the power and temperature data of the lighting terminal and feeds it back to the edge computing node module 2 of the corresponding area. The edge computing node module 2 uses an STM32H743 microcontroller as the core chip, integrating lightweight edge computing algorithms and data processing modules. One edge computing node is deployed in each area, responsible for managing the lighting terminals and sensing modules in that area. The cloud collaboration module 3 is deployed on an Alibaba Cloud server, supporting multi-tenant management and big data... Analysis shows that the multimodal sensing module 4 is deployed in one set in each area, including a light sensor 41 (BH1750), a human infrared sensor 42 (HC-SR501), a personnel density sensor 43 (infrared array sensor), and a temperature and humidity sensor 44 (DHT11), with a sampling frequency of 1 time / 30 seconds; the local communication unit 51 of the communication module 5 adopts the LoRa protocol (communication distance ≥ 500 meters), and the remote communication unit 52 adopts 5G narrowband communication, using AES encryption algorithm to ensure data security; the user interaction module 6 includes a touch control panel (TFTLCD touch screen) and a mobile APP (supporting Android and iOS systems).

[0035] Example 2: like Figure 2 As shown, this embodiment of the invention provides a distributed intelligent lighting control method based on edge computing, implemented based on the system in Embodiment 1, including the following steps: S1. System Initialization Configuration: Start the system, each module completes self-test, and communication module 5 establishes local and remote communication connections; divide the four edge computing node modules 2 into regions, specifying that each node manages five lighting terminals, and set local control parameters (light intensity threshold is 100 lux, and no personnel stay time threshold is 5 minutes); cloud collaboration module 3 initializes the global energy consumption threshold and emergency lighting parameters, and each lighting terminal is initialized to 50% brightness and 4000K color temperature, completing the initialization.

[0036] S2. Multimodal data acquisition and preprocessing: Multimodal sensing module 4 in each area acquires data in real time. In area 1, the light intensity is 80 lux, 3 people are detected, and the temperature and humidity are 25℃ / 50%. Status acquisition unit 13 collects data from 5 lighting terminals, all of which are operating normally. Edge computing node module 2 performs filtering and noise reduction on the data, removes outliers, extracts key features (personnel presence, light intensity below the threshold), and completes data aggregation.

[0037] S3. Edge Node Localized Control Decision: Based on preprocessed data, edge computing node module 2 in area 1 generates control instructions through reinforcement learning adaptive algorithms to control the brightness of 5 lighting terminals in the area to 80% and the color temperature to 5000K (adapted to office scenarios); at the same time, it monitors the status of the lighting terminals in real time to ensure normal operation.

[0038] S4. Distributed collaborative control: When a person is detected moving from area 1 to area 2, the edge computing node modules 2 of area 1 and area 2 interact with each other through the LoRa protocol. The edge computing node of area 1 issues a command to reduce the lighting brightness to 30%, and the edge computing node of area 2 issues a command to turn on the lighting (brightness 80%), so as to realize cross-area collaborative control and avoid ineffective lighting.

[0039] S5. Cloud Collaborative Optimization and Control: The cloud collaborative module 3 receives lighting status and energy consumption data uploaded by 4 edge computing nodes. Through big data analysis, it finds that the energy consumption of area 1 is too high. The light threshold of this area is optimized to 120 lux. The optimization strategy is then sent to edge computing node module 2 of area 1 to realize dynamic updates of the control strategy. At the same time, the status of each edge node is monitored in real time to ensure normal operation.

[0040] S6. User Interaction and Manual Control: Users can view the lighting status of each area through a mobile APP, set area 3 to energy-saving mode, and issue a command for brightness of 30% and color temperature of 3000K. The command is transmitted to edge computing node module 2 of area 3 via 5G remote communication. The edge node executes the command, adjusts the lighting status, and uploads the control record to the cloud for filing.

[0041] S7. System Maintenance and Self-Healing: If an abnormal power of a lighting terminal in area 4 is detected, edge computing node module 2 will immediately issue a stop operation command, start the backup lighting terminal in the area, and at the same time feed back the fault information to the cloud and mobile APP to remind the user to maintain it; the edge node will attempt to restart the faulty terminal, and if self-healing fails, record the fault information to the cloud fault database.

[0042] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A distributed intelligent lighting control system based on edge computing, comprising, characterized in that: It includes a distributed lighting node module, an edge computing node module, a cloud collaboration module, a multimodal sensing module, a communication module, and a user interaction module; each module is deployed in a distributed manner, with the edge computing node module communicating locally with the distributed lighting node module and the multimodal sensing module, and the cloud collaboration module communicating remotely with each edge computing node module, thus achieving an organic combination of local control and cloud collaborative management; The distributed lighting node module consists of several intelligent lighting terminals. Each intelligent lighting terminal has an independent control unit and communication unit, which can independently receive control commands and execute lighting parameter adjustments. The intelligent lighting terminal includes an LED lighting lamp, an intelligent driving module, and a status acquisition unit. The status acquisition unit is used to collect its own operating status data and feed it back to the edge computing node module. Each intelligent lighting terminal is divided into regions, and each region corresponds to one edge computing node module. The edge computing node modules are distributed and deployed in each lighting area. Each edge computing node module manages and controls a distributed lighting node module and a multimodal sensing module in a corresponding area. It is used to receive environmental and personnel data collected by the multimodal sensing module and operational status data fed back by the distributed lighting node module. It realizes real-time control of lighting parameters through localized computing, and is also responsible for fault monitoring, data preprocessing and local storage of lighting nodes in the area. It can also communicate collaboratively with other edge computing node modules. The cloud collaboration module is deployed on the cloud server and establishes a remote communication connection with each edge computing node module. It is used to receive the aggregated data uploaded by each edge computing node module, realize global lighting status monitoring, data statistical analysis, control strategy optimization and parameter distribution, support remote management and configuration of edge computing node modules, and can temporarily take over the lighting control of the area when the edge computing node module fails, while storing historical data. The multimodal sensing module is distributed and deployed in each lighting area, and is locally connected to the edge computing node module. It is used to collect multi-dimensional sensing data in the area, including light sensor, human infrared sensor, personnel density sensor, temperature and humidity sensor, and uses filtering and noise reduction algorithm to preprocess the data. The communication module is divided into a local communication unit and a remote communication unit. The local communication unit adopts a low-power, high-reliability communication protocol to realize local data interaction between the edge computing node module, the distributed lighting node module, and the multimodal sensing module. The remote communication unit adopts a long-distance communication protocol to realize remote data transmission between the edge computing node module and the cloud collaboration module, and supports encrypted data transmission and collaborative communication between edge computing node modules. The user interaction module includes a local interaction unit and a remote interaction unit, which are used to realize the interaction between the user and the system, and support lighting status viewing, parameter customization, scene mode setting and manual control command issuance.

2. The distributed intelligent lighting control system based on edge computing according to claim 1, characterized in that: The edge computing node module uses a lightweight edge computing chip and integrates a control algorithm and a data processing module. The control algorithm adopts an adaptive algorithm based on reinforcement learning and also integrates a lighting compensation algorithm. It can automatically optimize the local control strategy according to user habits and environmental changes to solve the problem of uneven lighting in the area.

3. The distributed intelligent lighting control system based on edge computing according to claim 1, characterized in that: The multimodal perception module can be equipped with a human motion recognition sensor, which can identify user actions through image recognition algorithms to accurately determine the user's intentions. The image recognition algorithm can identify actions such as waving and pausing, and trigger corresponding operations such as adjusting lighting brightness and stabilizing lighting.

4. The distributed intelligent lighting control system based on edge computing according to claim 1, characterized in that: The communication module adopts a hybrid communication architecture, prioritizing the LoRa protocol for local communication, the Zigbee protocol for short-range communication, and 5G narrowband technology for long-range communication. It uses the AES encryption algorithm to ensure data transmission security and supports rapid network configuration and automatic identification of devices.

5. A distributed intelligent lighting control system based on edge computing according to claim 1, characterized in that: The cloud-based collaboration module supports multi-tenant management and can provide services to multiple users simultaneously. Each user can independently set the lighting strategy for their own managed area. It also integrates an energy consumption prediction algorithm, which can predict future energy consumption based on historical data and provide energy-saving suggestions.

6. The distributed intelligent lighting control system based on edge computing according to claim 1, characterized in that: The distributed lighting node module supports hot-swapping, and the edge computing node module can automatically identify and configure newly added lighting terminals without requiring system downtime.

7. A distributed intelligent lighting control method based on edge computing, applied to the system described in any one of claims 1-6, characterized in that: Includes the following steps: S1. System Initialization Configuration: Start the system, complete the self-test and communication connection of each module, divide the area and configure the parameters of each edge computing node module, initialize the global control parameters of the cloud collaboration module, initialize the local control strategy of the edge computing node module, initialize each smart lighting terminal to the default lighting state, and complete the system initialization. S2. Multimodal data acquisition and preprocessing: The multimodal sensing modules in each area acquire real-time data on light intensity, personnel location, personnel density, and ambient temperature and humidity within the area, and send it to the edge computing node module in the corresponding area. The edge computing node module performs filtering and noise reduction, outlier removal, and format conversion on the raw data, extracts key feature data, and simultaneously receives the operating status data fed back by the distributed lighting node module to complete the data aggregation. S3. Edge Node Localized Control Decision: Based on preprocessed multimodal data and combined with local control strategies, the edge computing node module makes localized decisions through a lightweight control algorithm, generates lighting control instructions, and sends them to the distributed lighting node module to control the lighting terminal to perform corresponding actions. S4. Distributed collaborative control: When cross-regional lighting coordination is required, each edge computing node module interacts with data through the local communication unit, shares sensing data and control status, generates cross-regional linkage control commands based on the collaborative control algorithm, controls the coordinated operation of lighting terminals in each region, and feeds the collaborative control results back to the cloud collaborative module. S5. Cloud Collaboration Optimization and Control: The cloud collaboration module receives aggregated data uploaded by each edge computing node module, optimizes the global control strategy through big data analysis algorithms and distributes it to each edge computing node module, monitors the operating status of each module and device in real time, temporarily takes over control when the edge computing node module fails, and generates statistical reports regularly. S6. User interaction and manual control: Users can view lighting status, energy consumption data, and fault information through the user interaction module, customize control parameters, set scene modes, and issue manual control commands. The edge computing node module executes the commands and uploads the control records to the cloud collaboration module for filing. S7. System Maintenance and Self-Healing: The edge computing node module monitors its own and the operating status of devices within the controlled area in real time. When a fault is detected, it attempts to self-heal locally. If self-healing fails, it sends the fault information to the cloud collaboration module and the user interaction module. The cloud collaboration module records the fault information and maintenance records to form a fault database.

8. The distributed intelligent lighting control method based on edge computing according to claim 7, characterized in that: In S3, the generation logic of the lighting control command includes: if personnel are detected in the area and the light intensity is lower than a preset threshold, the brightness and color temperature of the lighting terminal are adjusted according to personnel density and ambient temperature and humidity; if no personnel are detected in the area for a preset time, a shutdown command is issued; if the lighting terminal is detected to be in an abnormal operating state, a stop operation command is issued and fault information is fed back, while a backup lighting terminal is started.

9. The distributed intelligent lighting control method based on edge computing according to claim 7, characterized in that: In S4, cross-regional collaborative control includes lighting coordination in connected areas such as corridors and halls, enabling lighting to turn on and off sequentially as people move, or to coordinate and match the brightness of lighting in different areas; in S7, local self-healing attempts include restarting equipment and switching to backup communication links.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the edge computing-based distributed intelligent lighting control method according to any one of claims 7-9.

Images