Intelligent street lamp system based on renewable energy sources and control method

Abstract

The invention discloses an intelligent street lamp system based on renewable energy and a control method, the system comprises a street lamp, a renewable energy power generation module, an energy storage module and an intelligent control unit, and the intelligent control unit comprises an intelligent sensing layer, an intelligent application layer and a cloud platform management layer; the intelligent sensing layer comprises a high-precision environment sensor, a human body / traffic flow detection sensor, an equipment state detection module and a controller; the cloud platform management layer comprises an adaptive dimming control module, an equipment management module, a data analysis module, an AI decision module and a visual monitoring module; the intelligent application layer comprises an intelligent operation and maintenance module, a multi-energy coupling module and a city data service module. By the adoption of the system, the management efficiency, the energy utilization rate and the operation and maintenance intelligent level of urban lighting facilities are improved, renewable energy sources such as solar energy and wind energy are combined, energy is collected through multi-energy coupling, regional cooperative control is optimized, and passive power utilization is achieved in the environment with sufficient natural energy.

Description

Technical Field

[0001] This invention belongs to the field of smart city construction, and specifically relates to a smart street light system and control method based on renewable energy. Background Technology

[0002] With the acceleration of urbanization, traditional street lighting systems face problems such as low management efficiency, energy waste, and high operation and maintenance costs. Most existing street lighting systems rely on manual inspections for maintenance, which cannot monitor the streetlights' status in real time or automatically adjust brightness based on ambient light intensity and time of day, resulting in significant energy waste. Furthermore, traditional street lighting systems have limited functionality and cannot meet the needs of smart city construction. With the development of technologies such as artificial intelligence, the Internet of Things, cloud platforms, and intelligent control, there is an urgent need for a highly intelligent and energy-efficient smart light pole system to facilitate urbanization. Summary of the Invention

[0003] The technical problem this invention aims to solve is to address the shortcomings of existing technologies by providing a rationally designed, highly intelligent, and energy-efficient smart street light system based on renewable energy. This system significantly improves the management efficiency, energy utilization rate, and intelligent operation and maintenance level of urban lighting facilities through intelligent information technology. Combining renewable energy sources such as solar and wind power, it collects energy through multi-energy coupling and employs reinforcement learning to optimize regional collaborative control, resulting in a high overall energy saving rate. In environments with abundant natural energy, it can achieve passive power consumption.

[0004] Another technical problem to be solved by the present invention is to provide a reasonably designed control method for a smart street light system based on renewable energy, which addresses the shortcomings of the prior art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A smart street light system based on renewable energy is characterized in that the system includes a street light, a renewable energy power generation module, an energy storage module, and a smart control unit. The smart control unit includes a smart sensing layer, a smart application layer, and a cloud platform management layer. The renewable energy power generation module, the energy storage module, and the smart sensing layer are installed on the street light.

[0007] The intelligent sensing layer includes high-precision environmental sensors, human / vehicle flow detection sensors, equipment status detection modules, and a controller. The high-precision environmental sensors, human / vehicle flow detection sensors, and equipment status detection modules are connected to the controller. The controller communicates with the cloud platform management layer and the intelligent application layer through an efficient communication layer. The equipment status detection module includes a lighting status monitoring module, a voltage and current monitoring module, and a fault detection module. The intelligent sensing layer integrates high-precision environmental sensors (light, temperature, humidity, PM2.5, noise, etc.), human / vehicle flow detection sensors (millimeter-wave radar, infrared sensing), and equipment status monitoring modules (voltage, current, fault detection), etc. Furthermore, the various sensors integrated in the intelligent sensing layer can work collaboratively through specific data fusion algorithms, automatically adjusting the data acquisition frequency and accuracy according to preset rules and scenario requirements to achieve more accurate environmental monitoring and more efficient energy consumption management.

[0008] The high-efficiency communication layer adopts a multi-mode heterogeneous network (NB-IoT, LoRa, 4G / 5G, ZigBee Mesh, etc.) and has a dynamic switching mechanism. It can automatically select the optimal communication mode according to the real-time network status, data transmission requirements and energy consumption, so as to ensure the stability and low latency of data transmission, while reducing communication energy consumption.

[0009] The intelligent application layer includes an intelligent operation and maintenance module, a multi-functional coupling module, and an urban data service module.

[0010] The intelligent operation and maintenance module adopts AI fault diagnosis (ResNet18) and predictive maintenance (Cox risk model) technologies, which can provide early warning of equipment anomalies and automatically adjust equipment parameters or execute repair commands through remote repair functions, thereby reducing manual intervention and improving operation and maintenance efficiency.

[0011] The multi-energy coupling module has intelligent energy management functions. By monitoring the power generation efficiency and energy storage status of solar panels and wind turbines in real time, and combining environmental data (such as light intensity and wind speed), it dynamically adjusts the energy distribution strategy to ensure efficient energy utilization and stable energy supply under different weather conditions.

[0012] The urban data service module features data encryption and secure transmission mechanisms. It utilizes blockchain technology to ensure the immutability and traceability of data, guaranteeing the security and reliability of data such as environmental monitoring, traffic flow statistics, and security monitoring. Furthermore, the system supports seamless integration with other urban systems, providing standardized API interfaces to enable data sharing and collaborative work.

[0013] The cloud platform management layer is based on a microservice architecture and includes an adaptive dimming control module, a device management module, a data analysis module, an AI decision-making module, and a visualization monitoring module.

[0014] The adaptive dimming control module uses the Q-learning algorithm to perform energy-saving optimization strategy control, and dynamically adjusts the brightness and operating time of the streetlights according to real-time environmental data and traffic flow prediction results.

[0015] The device management module centrally manages all street light equipment, including device registration, configuration, monitoring, and maintenance.

[0016] The data analysis module analyzes the collected environmental data and equipment operation data to generate a visual report;

[0017] The AI ​​decision-making module uses artificial intelligence algorithms to predict traffic flow and optimize energy-saving control strategies.

[0018] The visualization monitoring module monitors the operating status of the street light system in real time through a graphical interface, facilitating remote operation by management personnel.

[0019] The technical problem to be solved by the present invention can also be achieved through the following technical solutions: the high-precision environmental sensor includes a light sensor, a temperature and humidity sensor, a PM2.5 sensor, and a noise sensor.

[0020] The technical problem to be solved by the present invention can also be achieved through the following technical solution: the human body / vehicle flow detection sensor includes millimeter-wave radar and infrared sensor.

[0021] The technical problem to be solved by the present invention can also be achieved through the following technical solution: the renewable energy power generation module includes a solar power generation module and a wind power generation module.

[0022] The technical problem to be solved by the present invention can also be achieved through the following technical solution: the street light is equipped with a standardized interface to achieve seamless connection with a third-party system.

[0023] A control method for a smart street light system based on renewable energy, characterized in that the control method is as follows:

[0024] (1) First, the above-mentioned smart street light system is seamlessly connected to the urban traffic management system, urban smart security system, and urban environmental monitoring system through a standardized API interface;

[0025] (2) The working process of the cloud platform management layer is as follows: through the high-precision environmental sensors and human / vehicle flow detection sensors of the intelligent perception layer, environmental data and traffic flow information are collected in real time and uploaded to the cloud platform management layer. The data analysis module of the cloud platform management layer analyzes the collected environmental data and traffic flow information and generates a visualization report. The adaptive dimming control module of the cloud platform management layer dynamically adjusts the street light brightness according to the analyzed environmental data. The AI ​​decision module uses artificial intelligence algorithms to predict traffic flow and optimize energy-saving control strategies based on the analyzed traffic flow information. The visualization monitoring module monitors the street light operation status in the system in real time through a graphical interface.

[0026] (3) The working process of the intelligent application layer is that the intelligent operation and maintenance module monitors the equipment status of the street light in real time through the equipment status detection module of the intelligent perception layer, and promptly detects and handles faults to improve operation and maintenance efficiency.

[0027] The multi-energy coupling module dynamically adjusts the energy distribution strategy by monitoring the power generation efficiency of the renewable energy generation module and the energy storage status of the energy storage module in real time, combined with environmental data collected by high-precision environmental sensors, to ensure efficient energy utilization and stable supply under different weather conditions.

[0028] The city data service module acquires actual environmental data from the city environmental monitoring system, the city traffic management system, and actual traffic flow information, and uploads the acquired actual environmental data and actual traffic flow information to the cloud platform management layer. The cloud platform management layer uses the data analysis module to compare the actual environmental data with the data collected by high-precision environmental sensors to verify the accuracy of the high-precision environmental sensors and human / vehicle flow detection sensors. By comparing the actual traffic flow information with the data collected by human / vehicle flow detection sensors, the accuracy of the human / vehicle flow detection sensors is verified.

[0029] The technical problem to be solved by this invention can also be achieved through the following technical solution: the cloud platform management layer adaptive dimming control uses a Q-learning algorithm for energy-saving optimization strategy control, dynamically adjusting the brightness and development time of streetlights based on real-time environmental data and traffic flow prediction results. The specific steps are as follows:

[0030] 1) Initialize the Q-table: Set the Q-value of all state-action pairs to zero.

[0031] 2) Observe the current state: At each time step, the Agent observes the current state s t This includes the current time, ambient light intensity, traffic flow, status of adjacent streetlights, weather conditions, and equipment status.

[0032] 3) Select an action: Based on the Q-table and the ∈-greedy strategy, select an action a. tThe greedy strategy balances exploration (randomly selecting an action) and exploitation (selecting the action with the highest Q value).

[0033] 4) Execution of actions: The Agent executes action a t And observe the new state of environmental feedback. t+1 and reward r t+1 .

[0034] 5) Update the Q-table: Based on the Q-learning update formula, update the Q-values ​​of the corresponding state-action pairs in the Q-table:

[0035]

[0036] Where α is the learning rate and γ is the discount factor.

[0037] 6) Repeat steps 2-5 until the system reaches a stable state or meets the preset energy-saving target.

[0038] The technical problem to be solved by the present invention can also be achieved through the following technical solution: the multiple sensors integrated in the intelligent sensing layer adopt a Bayesian data fusion algorithm to improve the data acquisition frequency and accuracy, so as to achieve more accurate environmental monitoring and more efficient energy consumption management.

[0039] Compared with the prior art, the present invention has the following technical effects:

[0040] (1) High reliability: Supports network interruption resume, device self-test, and redundant backup to ensure stable system operation (availability ≥ 99.99%).

[0041] (2) Energy saving and high efficiency: Combining solar and wind energy, energy is collected through multi-energy coupling, and regional collaborative control is optimized by reinforcement learning (Q-learning). The overall energy saving rate is high, and passive power consumption can be realized in an environment with abundant natural energy.

[0042] (3) Adaptive lighting control: Based on the Q-learning algorithm, energy-saving optimization strategy control is implemented. The brightness and development time of street lights are dynamically adjusted according to real-time environmental data and traffic flow prediction results.

[0043] (4) Intelligent operation and maintenance: Combine blockchain technology to realize device identity authentication, and use AR remote operation and maintenance to reduce labor costs;

[0044] (5) Open ecosystem: Provides standardized APIs to support seamless integration with urban systems such as traffic management, smart security, and environmental monitoring. Attached Figure Description

[0045] Figure 1 This is an architecture diagram of a smart street light system based on renewable energy according to the present invention;

[0046] Figure 2 This is a schematic diagram of a smart street light system based on renewable energy according to the present invention;

[0047] Figure 3 This is a schematic diagram of a smart street light system and smart light pole system based on renewable energy according to the present invention. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, 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.

[0049] Reference Figure 1-3 This invention relates to a smart street lighting system based on renewable energy. By integrating cloud computing, the Internet of Things (IoT), big data analytics, artificial intelligence (AI), and intelligent control technologies, it constructs an efficient, energy-saving, and scalable urban lighting management system. The system adopts a modular design, supports flexible functional expansion, and can realize functions such as remote intelligent control, dynamic energy-saving dimming, environmental data monitoring, fault early warning, and automated operation and maintenance.

[0050] The smart street light system based on renewable energy described in this invention is divided into an intelligent sensing layer, a high-efficiency communication layer, a cloud platform management layer, and a smart application layer according to its function; and into a software and hardware component according to its hardware and software composition. The software component is used to realize business functions such as data processing, remote management, intelligent decision-making, and user interaction, while the hardware component provides the physical foundation to realize data acquisition, lighting control, street light energy consumption, and communication transmission, providing material support for system operation.

[0051] (a) The implementation of the intelligent perception layer is as follows:

[0052] 1. The integrated intelligent sensing layer for environmental sensors integrates multiple high-precision environmental sensors for real-time environmental data acquisition. Specifically, it includes:

[0053] • Light sensor: Installed on the street light pole, it detects the current ambient light intensity. When the light intensity is below a preset threshold, the system automatically adjusts the street light brightness to ensure effective illumination.

[0054] • Temperature and humidity sensor: Used to monitor ambient temperature and humidity, providing data support for urban environmental monitoring.

[0055] PM2.5 sensor: Monitors air quality in real time, and uploads the data to a cloud platform for city managers to analyze and make decisions.

[0056] Noise sensors: detect environmental noise levels and provide a basis for urban noise pollution control.

[0057] 2. Human / vehicle flow detection sensor

[0058] • Millimeter-wave radar: Installed on streetlight poles, it detects pedestrian and vehicle traffic flow. Based on the detected traffic data, the system dynamically adjusts the streetlight brightness to achieve energy savings.

[0059] • Infrared sensor: Used to detect human activity. When a pedestrian is detected, it automatically turns on nearby streetlights to improve lighting efficiency.

[0060] 3. Equipment Status Monitoring Module

[0061] • Lighting status monitoring: Real-time monitoring of street light operation status, including whether the lights are on, off, high-intensity lighting, or energy-saving lighting.

[0062] • Voltage and current monitoring: Real-time monitoring of the voltage and current status of streetlights to ensure normal equipment operation.

[0063] • Fault detection: By monitoring the operating parameters of the equipment, faults can be detected in a timely manner and alarms can be issued, facilitating rapid repair.

[0064] (II) The implementation method of the high-efficiency communication layer is as follows:

[0065] 1. Construction of multimodal heterogeneous networks

[0066] The high-efficiency communication layer employs multiple communication technologies to ensure stable data transmission and low latency. Specifically, it includes:

[0067] ·NB-IoT: Suitable for low-power, wide-coverage IoT devices, ideal for remote monitoring of street light systems.

[0068] • LoRa: Provides long-range wireless communication capabilities, suitable for data transmission within urban areas.

[0069] • 4G / 5G: Used for high-speed data transmission, supporting high-bandwidth applications such as high-definition video surveillance.

[0070] • ZigBee Mesh: Build self-organizing, self-healing wireless networks to improve the reliability and stability of communication.

[0071] 2. Adaptive Routing Algorithm

[0072] The communication layer employs an adaptive routing algorithm to dynamically select the optimal communication path based on network conditions. When a communication link fails, the system automatically switches to another available link to ensure continuous data transmission.

[0073] (III) The implementation method of the cloud platform management layer is as follows:

[0074] 1. Microservice architecture

[0075] The cloud platform management layer, based on a microservices architecture, provides the following functionalities:

[0076] • Equipment Management: Centralized management of all street lighting equipment, including equipment registration, configuration, monitoring and maintenance.

[0077] • Data Analysis: Analyze the collected environmental data and equipment operation data to generate visual reports.

[0078] AI Decision Making: Utilizing artificial intelligence algorithms (such as LSTM models) to predict traffic flow and optimize energy-saving control strategies.

[0079] • Visual monitoring: Real-time monitoring of the street light system's operating status through a graphical interface, facilitating remote operation by management personnel;

[0080] • System Management: The system management module enables functions such as user permission management, data backup and recovery, and system parameter configuration.

[0081] 2. Edge computing

[0082] To optimize real-time response capabilities, the cloud platform management layer employs edge computing technology. Edge computing nodes are deployed on streetlight poles to perform preliminary processing and analysis of the collected data, reducing data transmission volume and improving system response speed.

[0083] (iv) The intelligent application layer includes the following:

[0084] 1. Adaptive dimming control

[0085] The cloud platform's adaptive dimming control, based on the Q-learning algorithm, employs energy-saving optimization strategies to dynamically adjust streetlight brightness and operating time according to real-time environmental data and traffic flow predictions. The specific steps are as follows:

[0086] 1) Initialize the Q-table: Set the Q-value of all state-action pairs to zero.

[0087] 2) Observe the current state: At each time step, the Agent observes the current state s t This includes the current time, ambient light intensity, traffic flow, status of adjacent streetlights, weather conditions, and equipment status.

[0088] 3) Select an action: Based on the Q-table and the ∈-greedy strategy, select an action a. t The greedy strategy balances exploration (randomly selecting an action) and exploitation (selecting the action with the highest Q value).

[0089] 4) Execution of actions: The Agent executes action a t And observe the new state of environmental feedback. t+1 and reward r t+1 .

[0090] 5) Update the Q-table: Based on the Q-learning update formula, update the Q-values ​​of the corresponding state-action pairs in the Q-table:

[0091]

[0092] Where α is the learning rate and γ is the discount factor.

[0093] 6) Repeat steps 2-5 until the system reaches a stable state or meets the preset energy-saving target.

[0094] 2. Intelligent Operation and Maintenance Module

[0095] • AI Fault Diagnosis: The ResNet18 deep learning model is used to diagnose equipment faults. By analyzing equipment operation data, the cause of the fault can be quickly located.

[0096] • Predictive maintenance: Using the Cox risk model to predict equipment failure risks, maintenance plans can be arranged in advance, reducing equipment downtime and lowering manual inspection costs.

[0097] 3. Combination of solar and wind energy

[0098] Based on geographical and climatic conditions, solar power generation modules and wind power generation modules should be rationally arranged to maximize energy collection.

[0099] • Solar energy: Install solar power generation modules to absorb solar energy during the day and convert it into electrical energy stored in batteries. Use the stored electrical energy to supply power at night or on cloudy days.

[0100] • Wind power: Equipped with micro wind power generation modules, it generates and stores wind power, complementing solar power, especially providing additional electricity at night or on cloudy days.

[0101] By combining solar power generation modules and wind power generation modules, a complementary energy supply system is formed to improve energy utilization efficiency and stability, ensuring a continuous and stable power supply for smart streetlights under different weather conditions.

[0102] 4. City Data Services

[0103] • Environmental monitoring: Collected environmental data such as temperature, humidity, PM2.5, and noise are uploaded to the cloud platform to provide data support for urban environmental governance.

[0104] Traffic flow statistics: Traffic flow data collected through millimeter-wave radar and infrared sensors provides a basis for urban traffic planning and management.

[0105] • Security monitoring: Combining high-definition cameras and intelligent analysis algorithms, the street light system can be used for security monitoring, thereby improving urban safety.

[0106] The control method for the smart street light system based on renewable energy described in this invention is as follows:

[0107] 1. System Integration

[0108] By integrating the intelligent sensing layer, high-efficiency communication layer, cloud platform management layer, and smart application layer, a complete smart street light system is constructed. Through standardized API interfaces, seamless integration with other urban systems, such as traffic management systems, smart security systems, and environmental monitoring systems, is achieved.

[0109] 2. System Testing

[0110] The system was tested in an urban environment to verify its functionality and performance. The tests included:

[0111] • Accuracy of environmental data acquisition: Verify the accuracy of the sensors by comparing actual environmental data with the data acquired by the sensors.

[0112] • Communication stability: Test the stability of the communication layer under different network environments to ensure the continuity of data transmission.

[0113] • Energy saving effect: The energy consumption data of traditional street light systems and smart street light systems are compared to verify the energy saving effect of the system.

[0114] • Operation and maintenance efficiency: By simulating equipment failure, the response time and repair efficiency of the intelligent operation and maintenance system are tested.

[0115] Divided by hardware and software components, the hardware part includes cloud platform, multi-mode heterogeneous network, high-precision environmental sensor, human / vehicle flow detection sensor, equipment status detection module, solar power generation module, wind power generation module and energy storage module, etc. The software part includes functional modules such as visual monitoring, equipment management, lighting control, data analysis, AI decision making, intelligent operation and maintenance and system management.

[0116] Examples of applications in urban and industrial parks will be provided:

[0117] 1. Application of Smart Streetlight Systems in Cities

[0118] Smart streetlight systems based on renewable energy are deployed on major city streets and squares. Sensors in the intelligent sensing layer collect environmental data and traffic flow information in real time and upload them to a cloud platform. Based on the data analysis results, the cloud platform dynamically adjusts the streetlight brightness to achieve energy savings. Simultaneously, an intelligent operation and maintenance system monitors equipment status in real time, promptly identifying and handling faults to improve operational efficiency.

[0119] 2. Application of Smart Streetlight Systems in Industrial Parks

[0120] Deploying smart streetlight systems in industrial parks, combined with environmental monitoring functions, allows for real-time monitoring of environmental indicators such as air quality and noise levels. By integrating with the park's security system, the streetlights can also be monitored for security. This makes lighting management in the park more intelligent, improves energy efficiency, enhances environmental quality, and provides strong support for the park's sustainable development.

[0121] The smart street light system based on renewable energy described in this invention achieves functions such as environmental data monitoring, remote intelligent control, dynamic energy-saving dimming, fault early warning, and automated operation and maintenance through the collaborative work of the intelligent sensing layer, high-efficiency communication layer, cloud platform management layer, and intelligent application layer. Meanwhile, the system demonstrates excellent performance in energy saving, operation and maintenance efficiency, and environmental improvement, and has broad application prospects and promotional value.

[0122] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A smart street light system based on renewable energy sources, characterized by, The system comprises a street lamp, a renewable energy power generation module, an energy storage module and a smart control unit, the smart control unit comprises a smart sensing layer, a smart application layer and a cloud platform management layer, the renewable energy power generation module, the energy storage module and the smart sensing layer are installed on the street lamp; The smart sensing layer comprises a high-precision environment sensor, a human / vehicle flow detection sensor, a device state detection module and a controller, the high-precision environment sensor, the human / vehicle flow detection sensor, the device state detection module and the controller are connected, the controller is in communication connection with the cloud platform management layer and the smart application layer through an efficient communication layer, the device state detection module comprises a lighting state monitoring module, a voltage and current monitoring module and a fault detection module; The efficient communication layer is provided with a multi-mode heterogeneous network, the multi-mode heterogeneous network supports the communication protocols of NB-IoT, LoRa, 4G / 5G and ZigBee Mesh, has a dynamic switching mechanism, can automatically select the optimal communication mode according to the real-time network state, data transmission demand and energy consumption condition, ensure the stability and low delay of data transmission, and reduce the communication energy consumption; The smart application layer comprises a smart operation and maintenance module, a multi-energy coupling module and a city data service module; The smart operation and maintenance module adopts AI fault diagnosis and predictive maintenance technology, early warns device abnormities, and automatically adjusts device parameters or executes repair instructions through a remote repair function; The multi-energy coupling module has an intelligent energy management function, dynamically adjusts energy distribution strategies by real-time monitoring of the power generation efficiency of the renewable energy power generation module and the energy storage state, and combining the environmental data provided by the high-precision environment sensor, to ensure efficient utilization and stable supply of energy under different weather conditions; The city data service module has a data encryption and secure transmission mechanism, realizes data non-tamperability and traceability through blockchain technology; The cloud platform management layer is based on a micro-service architecture and comprises an adaptive dimming control module, a device management module, a data analysis module, an AI decision module and a visual monitoring module; The adaptive dimming control module controls energy-saving optimization strategies based on a Q-learning algorithm, dynamically adjusts the brightness and development time of the street lamp according to real-time environmental data and traffic flow prediction results; The device management module centrally manages all street lamp devices, including device registration, configuration, monitoring and maintenance; The data analysis module analyzes the collected environmental data and device operation data to generate a visual report; The AI decision module uses artificial intelligence algorithms to optimize traffic flow prediction and energy-saving control strategies; The visual monitoring module real-time monitors the running state of the street lamp system through a graphical interface, facilitating remote operation of management personnel.

2. A smart street light system based on renewable energy as claimed in claim 1 wherein, The high-precision environment sensor comprises an illumination sensor, a temperature and humidity sensor, a PM2.5 sensor and a noise sensor.

3. A smart street light system based on renewable energy as claimed in claim 1 wherein, The human / vehicle flow detection sensor comprises a millimeter wave radar and an infrared sensor.

4. The smart street light system based on renewable energy source as claimed in claim 1 wherein, The renewable energy power generation module comprises a solar power generation module and a wind power generation module.

5. A smart street light system based on renewable energy as claimed in claim 1, wherein, The street lamp is provided with a standardized interface to realize seamless connection with a third-party system.

6. A control method of the smart street light system based on renewable energy according to any one of claims 1-5, characterized in that, The control method is, (1) first, the intelligent street lamp system according to any one of claims 1-5 is connected with a city traffic management system, a city intelligent security system and a city environment monitoring system through a standardized API interface; (2) the working process of the cloud platform management layer is that environment data and traffic flow information are collected in real time by high-precision environment sensors and human / vehicle flow detection sensors of the intelligent sensing layer, uploaded to the cloud platform management layer, analyzed by a data analysis module of the cloud platform management layer, and visual reports are generated; an adaptive light adjustment control module of the cloud platform management layer dynamically adjusts the brightness of the street lamp according to the analyzed environment data; an AI decision module uses artificial intelligence algorithms to predict traffic flow and optimize energy-saving control strategies according to the analyzed traffic flow information, and a visual monitoring module monitors the running state of the street lamp in the system in real time through a graphical interface; (3) the working process of the intelligent application layer is that an intelligent operation and maintenance module monitors the equipment state of the street lamp in real time through an equipment state detection module of the intelligent sensing layer, discovers and handles faults in a timely manner, and improves operation and maintenance efficiency; The multi-energy coupling module dynamically adjusts the energy distribution strategy by monitoring the power generation efficiency of the renewable energy power generation module and the energy storage state of the energy storage module in real time, and combining the environment data collected by the high-precision environment sensor, to ensure efficient use and stable supply of energy under different weather conditions; The city data service module obtains actual environment data of the city environment monitoring system and actual traffic flow information of the city traffic management system, and uploads the obtained actual environment data and actual traffic flow information to the cloud platform management layer; the cloud platform management layer compares the actual environment data with the data collected by the high-precision environment sensor through the data analysis module to verify the accuracy of the high-precision environment sensor and the human / vehicle flow detection sensor, and compares the actual traffic flow information with the data collected by the human / vehicle flow detection sensor to verify the accuracy of the human / vehicle flow detection sensor.

7. The control method according to claim 6, characterized in that: The adaptive light adjustment control module of the cloud platform management layer controls the energy-saving optimization strategy based on the Q-learning algorithm, dynamically adjusts the brightness and development time of the street lamp according to the real-time environment data and traffic flow prediction results; The specific steps are as follows: 1) initialize the Q table: set the Q value of all state-action pairs to zero, 2) Observe current state: At each time step, the Agent observes the current state s t including the current time, ambient light intensity, traffic flow, neighboring streetlight status, weather conditions, and device status, 3) Select action: select an action a according to the Q-table and the ε-greedy policy t The ε-greedy policy balances between exploration, which means randomly selecting an action, and exploitation, which means selecting the action with the highest Q-value. 4) Perform action: Agent performs action a t and observes the new state of the environment s t+1 and reward r t+1 , 5) update the Q table: update the Q value of the corresponding state-action pair in the Q table according to the Q-learning update formula: where, alpha is the learning rate, gamma is the discount factor, 6) repeat steps 2)-5): until the system reaches a stable state or meets the preset energy-saving target.

8. The control method according to claim 6, characterized by, The multiple sensors integrated in the intelligent sensing layer use the Bayesian data fusion algorithm to improve the data acquisition frequency and accuracy, so as to realize more accurate environment monitoring and more efficient energy consumption management.

Images