Street lamp dynamic regulation and control method and system based on cloud server

Abstract

The invention relates to the technical field of street lamp control, in particular to a street lamp dynamic regulation and control method and system based on a cloud server. The method comprises the following steps: collecting environment, traffic, street lamp state and time multi-dimensional original data, and performing cleaning, standardization and feature fusion processing to obtain a comprehensive regulation factor of a brightness demand and an emergency degree weight; based on the comprehensive regulation and control factor and the street lamp state data, a cloud server is adopted to generate a single lamp target brightness and a switching instruction, check optimization is carried out cooperatively, and fault maintenance early warning is generated synchronously; presetting a basic regulation and control time window according to historical data, refining regulation and control time granularity in combination with real-time environment, traffic and time segment characteristics, and performing real-time adjustment on regulation and control time; the system comprises a multi-modal data fusion analysis module, a cloud server street lamp regulation and control instruction generation module and a regulation and control time dynamic adjustment module. In this way, energy consumption is reduced, the regulation and control response speed is increased, and the method can be used for multiple scenes such as urban roads, parks and scenic spots.

Description

Technical Field

[0001] This invention relates to the field of street light control technology, and in particular to a method and system for dynamic control of street lights based on a cloud server. Background Technology

[0002] In today's rapidly accelerating urbanization process, streetlights, as a key component of urban infrastructure, have their management efficiency and level of intelligence directly impacting the overall appearance of the city and the quality of life for its residents. Traditional urban streetlight management methods largely rely on manual inspections and simple timed controls. As cities continue to expand and the number of streetlights increases, the drawbacks of this management model become increasingly apparent.

[0003] Traditional urban street light management methods rely on a single data source, such as fixed time periods or light sensor data, to control the switching on and off of lights. This fails to consider dynamic factors, resulting in a mismatch between brightness and actual demand, and causing energy waste. The timing is fixed, and the control time (such as the duration of light illumination and the brightness switching point) is fixed for a long time. Without combining real-time data for dynamic optimization, it cannot adapt to the differentiated needs of different time periods and different areas.

[0004] In conclusion, it is essential to propose a dynamic control method and system for streetlights that can reduce energy consumption and improve control response speed. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for dynamic control of streetlights based on a cloud server, which aims to reduce energy consumption and improve control response speed.

[0006] To achieve the above objectives, the present invention employs a cloud server-based dynamic street light control method, comprising the following steps: Collect raw data from multiple dimensions, including environment, traffic, street light status, and time. After cleaning, standardization, and feature fusion processing, obtain a comprehensive control factor that combines brightness demand and urgency weight. Based on comprehensive control factors and street light status data, a cloud server is used to generate target brightness and switching instructions for a single light, and to collaboratively verify and optimize, and simultaneously generate fault repair early warnings. Based on historical data, a basic control time window is preset, and the control time granularity is refined by combining real-time environmental, traffic and time characteristics, and the control time is adjusted in real time.

[0007] Among the steps involved in collecting raw data from multiple dimensions, including environment, traffic, streetlight status, and time, and then processing this data through cleaning, standardization, and feature fusion to obtain a comprehensive control factor that weights brightness demand and urgency: Environmental data, traffic data, and street light status data are collected separately, and time data is synchronized. The environmental data includes light intensity, weather type, and visibility; the traffic data includes traffic flow, vehicle speed, and pedestrian flow; and the street light status data includes street light power, brightness, current, voltage, and fault information. Standardize the cleaned data and map data from different dimensions to a unified quantization range; The standardized data is fused to extract key features and output a comprehensive control factor that includes brightness demand weight and urgency weight.

[0008] After collecting environmental data, traffic data, and street light status data, and synchronizing time data: The collected multi-dimensional raw data is cleaned to remove outliers caused by sensor malfunctions, and missing data is filled in using interpolation.

[0009] In the steps of feature fusion of standardized data, extraction of key features, and output of a comprehensive control factor including brightness demand weight and urgency weight: Standardized environmental data, traffic data, time data, and street light status data are classified according to data dimensions to construct a multi-source feature matrix; The feature matrix is ​​processed hierarchically to extract local key features from each data dimension and capture time series features.

[0010] After performing hierarchical processing on the feature matrix, extracting local key features from each data dimension, and capturing time series features: The extracted multi-dimensional features are weighted and fused to generate brightness demand weight and urgency weight, which together constitute a comprehensive control factor.

[0011] Among them, in the steps of generating target brightness and switching instructions for a single lamp using a cloud server based on comprehensive control factors and street lamp status data, and collaboratively verifying and optimizing, and synchronously generating fault maintenance early warnings: Acquire comprehensive control factors and street light status data, construct a decision model, and set protection threshold constraints for maximum brightness and minimum power of street lights; The target brightness value and on / off status command for each street light are calculated and output based on the real-time comprehensive control factor. For streetlights that show a fault in the status data, maintenance warning instructions are generated simultaneously, and maintenance priorities are planned.

[0012] After the step of calculating and outputting the target brightness value and on / off status command for each street light based on the real-time comprehensive control factor: Perform collaborative verification of instructions from adjacent streetlights.

[0013] Among them, the steps of setting a basic control time window based on historical data and refining the control time granularity by combining real-time environmental, traffic and time segment characteristics, and adjusting the control time in real time are as follows: Based on historical lighting data and regional work and rest patterns, preset basic control time windows for multiple scenarios; Adjust the switching time of lights based on real-time light intensity data; The duration of the lights is dynamically adjusted based on real-time traffic and pedestrian flow data. Optimize the time granularity of adjustment based on the characteristics of different time periods, refining hourly adjustments to minute-level adjustments.

[0014] In the step of adjusting the switching time of lights based on real-time light intensity data: If the light intensity is below the threshold, the streetlights will be turned on in advance. If the light intensity is higher than the threshold, the streetlights will be turned off later.

[0015] This invention also provides a cloud server-based dynamic street light control system, including a multimodal data fusion and analysis module, a cloud server street light control instruction generation module, and a control time dynamic adjustment module; wherein: The multimodal data fusion and analysis module is used to collect raw data from multiple dimensions, including environment, traffic, street light status, and time. After cleaning, standardization, and feature fusion processing, it obtains a comprehensive control factor for brightness demand and urgency weight. The cloud server street light control instruction generation module is used to generate single-lamp target brightness and on / off instructions based on comprehensive control factors and street light status data, and to collaboratively verify and optimize, and synchronously generate fault maintenance early warnings. The dynamic adjustment module for control time is used to preset a basic control time window based on historical data, and to refine the control time granularity by combining real-time environment, traffic and time characteristics, and to adjust the control time in real time.

[0016] This invention discloses a cloud server-based dynamic street light control method and system, which employs a multimodal data fusion analysis module, a cloud server street light control command generation module, and a dynamic adjustment module for control time to perform the following steps: Collecting multi-dimensional raw data on environment, traffic, street light status, and time; performing cleaning, standardization, and feature fusion processing to obtain a comprehensive control factor with weighted brightness requirements and urgency; based on the comprehensive control factor and street light status data, generating target brightness and on / off commands for individual lights using a cloud server, and collaboratively verifying and optimizing, while simultaneously generating fault repair early warnings; pre-setting a basic control time window based on historical data, and refining the control time granularity by combining real-time environmental, traffic, and time-specific characteristics, and adjusting the control time in real time; through the above methods, reducing energy consumption and improving control response speed, it can be applied to multiple scenarios such as urban roads, parks, and scenic areas. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the steps of the cloud server-based dynamic control method for streetlights according to the present invention.

[0019] Figure 2 This is a flowchart of steps S100 of the present invention.

[0020] Figure 3 This is a flowchart of steps S200 of the present invention.

[0021] Figure 4 This is a flowchart of steps S300 of the present invention.

[0022] Figure 5 This is a schematic diagram of the structural principle of the cloud server-based dynamic control system for streetlights of the present invention.

[0023] Figure 6 This is a schematic diagram of the electronic device of the present invention.

[0024] 401 - Multimodal data fusion analysis module; 402 - Cloud server street light control instruction generation module; 403 - Control time dynamic adjustment module. Detailed Implementation

[0025] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0026] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0027] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0028] Please see Figures 1-4 This invention provides a method for dynamic control of streetlights based on a cloud server, comprising the following steps: S100: Collects raw data from multiple dimensions, including environment, traffic, street light status, and time. After cleaning, standardization, and feature fusion processing, it obtains a comprehensive control factor that weights brightness requirements and urgency.

[0029] In this embodiment, raw data from multiple dimensions, including environment, traffic, streetlight status, and time, are collected. After cleaning, standardization, and feature fusion processing, a comprehensive control factor is obtained that weights brightness demand and urgency. The specific process is as follows: S101: Collects environmental data, traffic data, and street light status data respectively, and synchronizes time data; among which, environmental data includes light intensity, weather type, and visibility; traffic data includes traffic flow, vehicle speed, and pedestrian flow; and street light status data includes street light power, brightness, current, voltage, and fault information. S102: Clean the collected multi-dimensional raw data, remove abrupt abnormal values ​​caused by sensor malfunctions, and use interpolation to complete missing data; S103: Standardize the cleaned data and map data of different dimensions to a unified quantization range; S104: Perform feature fusion on standardized data, extract key features, and output a comprehensive control factor that includes brightness demand weight and urgency weight.

[0030] Furthermore, in the steps of feature fusion of standardized data, extraction of key features, and output of a comprehensive control factor including brightness demand weight and urgency weight: Standardized environmental data, traffic data, time data, and street light status data are classified according to data dimensions to construct a multi-source feature matrix; The feature matrix is ​​processed hierarchically to extract local key features from each data dimension and capture time series features. The extracted multi-dimensional features are weighted and fused to generate brightness demand weight and urgency weight, which together constitute a comprehensive control factor.

[0031] In the above process, during the data acquisition phase, four types of data are acquired synchronously with the system through distributed sensing devices: Environmental data: Real-time light intensity (unit: lux) is collected using a light sensor, and weather type (such as sunny, rainy, fog) and visibility (unit: m) are obtained through temperature and humidity sensors and the city weather early warning system. Traffic data: Traffic flow (vehicles / minute) and average vehicle speed (km / h) are counted by road cameras and traffic flow sensors per unit time, and pedestrian flow (people / minute) is counted by pedestrian recognition devices. Streetlight status data: Real-time collection of operating parameters for each streetlight using a single-lamp controller, including instantaneous power (W), current brightness (percentage), operating current (A), voltage (V), and fault indicators (such as short circuit, overload, etc.). Time data: Synchronously records the current date (accurate to the day) and time period type (such as weekday / holiday, morning peak / off-peak / evening peak).

[0032] During the data cleaning phase, outliers are filtered out using preset thresholds: for example, if the light sensor data changes by more than 500 lux within 1 minute (far exceeding the range of natural light variation), it is determined to be a sensor malfunction and the data is removed; for missing data caused by network latency, the mean interpolation method within the adjacent 5 minutes is used to fill in the missing data to ensure data continuity.

[0033] During the data standardization phase, data of different dimensions are mapped to a unified quantization range of 0 to 100: for example, light intensity of 0 to 1000 lux corresponds to 0 to 100 (the higher the value, the stronger the light), traffic flow of 0 to 200 vehicles / minute corresponds to 0 to 100 (the higher the value, the busier the traffic), and low visibility weather such as "fog" and "heavy rain" is assigned a value of 80 to 100, while "sunny" is assigned a value of 10 to 30.

[0034] In the feature fusion and regulatory factor generation stage, key features are extracted and comprehensive regulatory factors are output through multi-layer processing: First, the standardized environmental, traffic, time, and street light status data are classified by dimension to construct a multi-source feature matrix of "data type-value-timestamp" (such as each row corresponding to the full-dimensional data at a certain moment). Secondly, convolutional neural networks (CNNs) are used to extract local features: for example, the correlation between "light intensity below 30 and visibility below 500m" and high brightness demand is identified from environmental data, and the correlation between "vehicle flow > 150 vehicles / minute" and extended lighting duration is captured from traffic data; at the same time, recurrent neural networks (RNNs) are used to capture time series features, such as the dynamic impact of "continuous increase in pedestrian flow from 18:00 to 19:00 on weekdays" on brightness demand. Finally, the extracted features are weighted and fused: light intensity and visibility in environmental data account for 40% (directly affecting brightness demand), traffic flow and pedestrian flow in traffic data account for 30% (affecting urgency), peak hour markers in time data account for 20% (assisting adjustment), and current street light brightness accounts for 10% (avoiding over-adjustment). The final output is a brightness demand weight of 0~100 (e.g., 80 indicates high brightness demand) and an urgency weight (e.g., 60 indicates medium priority adjustment), which together constitute a comprehensive control factor.

[0035] S200: Based on comprehensive control factors and street light status data, it uses a cloud server to generate target brightness and switching instructions for a single light, and coordinates verification and optimization, and synchronously generates fault maintenance early warnings.

[0036] In this embodiment, based on comprehensive control factors and street light status data, a cloud server is used to generate target brightness and on / off commands for individual lights, and to collaboratively verify and optimize the data while simultaneously generating fault repair early warnings. The specific process is as follows: S201: Obtain comprehensive control factors and street light status data, construct a decision model, and set the maximum brightness and minimum power protection threshold constraints for street lights; S202: Calculate and output the target brightness value and on / off status command for each street light based on the real-time comprehensive control factor; S203: Perform collaborative verification of instructions for adjacent streetlights; S204: For streetlights that show a fault in the status data, generate maintenance early warning instructions simultaneously and plan maintenance priorities.

[0037] In the above process, during the decision model construction stage, the cloud server receives the comprehensive control factor and street light status data output by step S100, and sets constraints with "lowest energy consumption" and "highest lighting demand satisfaction" as dual objective functions: for example, the maximum brightness of the street light does not exceed 110% of the rated value (to avoid overload), and the minimum power is not less than 30% of the rated value (to ensure basic lighting).

[0038] During the instruction calculation phase, a reinforcement learning algorithm (such as Q-Learning) is used to train the model, and instructions are output based on real-time comprehensive control factors. For example, when the brightness demand weight is 80 and the urgency weight is 70, the target brightness is calculated to be 85% of the rated value, and an "immediately turn on" instruction is generated; when the brightness demand weight is 20 and the urgency weight is 10, the target brightness is output to be 30%, and an "turn off in 30 minutes" instruction is generated.

[0039] During the collaborative verification phase, the consistency of the instructions for three adjacent streetlights is checked: for example, if the target brightness of a streetlight is 80%, the brightness of the adjacent streetlights must be controlled between 65% and 95% to avoid visual discomfort caused by sudden changes in brightness; if the verification fails, the instructions of the adjacent streetlights are fine-tuned to meet the range.

[0040] During the fault warning phase, for streetlights marked "fault" in the status data (such as those with 0 current and abnormal voltage), a maintenance warning instruction is generated simultaneously. This instruction includes the location coordinates of the faulty streetlight, the fault type (such as "short circuit"), and the maintenance priority is planned based on the load of surrounding streetlights (such as faulty streetlights on main roads have higher priority than those on branch roads). The instruction is then pushed to the maintenance terminal.

[0041] S300: Based on historical data, a basic control time window is preset, and combined with real-time environmental, traffic and time period characteristics, the control time granularity is refined to make real-time adjustments to the control time.

[0042] In this implementation, a basic control time window is preset based on historical data, and the control time granularity is refined by combining real-time environmental, traffic, and time segment characteristics, allowing for real-time adjustment of the control time. The specific process is as follows: S301: Based on historical lighting data and regional work and rest patterns, preset basic control time windows for multiple scenarios; S302: Adjust the switching time of streetlights based on real-time light intensity data; if the light intensity is below the threshold, turn on the streetlights in advance; if the light intensity is above the threshold, delay turning off the streetlights. S303: Dynamically adjust the lighting duration based on real-time traffic and pedestrian flow data; S304: Optimize the time granularity of adjustment based on the characteristics of the time period, and refine the hourly adjustment to the minute level.

[0043] In the above process, during the basic time window preset stage, based on the lighting data of the past 12 months and the regional work and rest patterns, the basic time windows for multiple scenarios are divided: for example, the basic lighting time on weekdays is 19:00 to 6:00 the next day, and on holidays it is 20:00 to 5:30 the next day. For roads around schools, the lighting time is extended to 22:30 after evening self-study ends (21:30).

[0044] The time adjustment phase is based on environmental data, with a light intensity of 500 lux as the threshold: if the light intensity is below 500 lux for 10 consecutive minutes (such as in the evening in winter), the basic lighting time will be advanced by 15 to 30 minutes; if the light intensity is above 500 lux for 5 consecutive minutes in the early morning, the shutdown time will be delayed by 10 to 20 minutes; in the event of low visibility weather such as heavy rain or fog, the lighting time will be automatically extended by 2 to 3 hours.

[0045] Based on traffic data, during the time adjustment phase, a vehicle flow threshold of 5 vehicles / minute and a pedestrian flow threshold of 2 people / minute are set. When the vehicle / pedestrian flow is below the threshold for 10 consecutive minutes, the lighting duration is shortened (e.g., from 6 hours to 4 hours) or the brightness duration is reduced (e.g., from maintaining 80% brightness for 3 hours to 2 hours). When a sudden surge in pedestrian traffic is detected (e.g., after a concert, the pedestrian flow suddenly increases to 300 people / minute), the lighting is temporarily extended by 1 hour, and the brightness is simultaneously increased to 80%.

[0046] In the time granularity optimization phase, the traditional hourly adjustment is refined to the minute level: for example, the brightness increase instruction during the weekday morning peak (5:30~7:30) is accurate to "turn on 80% brightness at 5:32 and reduce to 50% at 7:28"; for the off-peak period from 0:00 to 4:00 in the early morning, the brightness is dynamically adjusted at a frequency of monitoring data every 15 minutes to ensure that the lighting matches the demand in real time.

[0047] Corresponding to the aforementioned embodiments of the cloud server-based dynamic control method for streetlights, this application also provides embodiments of a cloud server-based dynamic control system for streetlights.

[0048] Figure 5 This is a block diagram of a cloud server-based dynamic control system for streetlights, according to an exemplary embodiment. (Refer to...) Figure 5 The system may include: a multimodal data fusion and analysis module 401, a cloud server street light control instruction generation module 402, and a control time dynamic adjustment module 403; wherein: The multimodal data fusion analysis module 401 is used to collect multi-dimensional raw data on environment, traffic, street light status and time, and after cleaning, standardization and feature fusion processing, obtain a comprehensive control factor for brightness demand and urgency weight. The cloud server street light control instruction generation module 402 is used to generate single-lamp target brightness and switching instructions based on comprehensive control factors and street light status data, and to collaboratively verify and optimize, and synchronously generate fault maintenance early warnings. The dynamic adjustment module 403 is used to preset a basic control time window based on historical data, and refine the control time granularity by combining real-time environment, traffic and time characteristics, and adjust the control time in real time.

[0049] In this embodiment, the multimodal data fusion and analysis module 401 collects multi-dimensional raw data on environment, traffic, street light status, and time. After cleaning, standardization, and feature fusion processing, it obtains a comprehensive control factor that combines brightness demand and urgency weight. The cloud server street light control instruction generation module 402 generates single-lamp target brightness and switching instructions based on the comprehensive control factor and street light status data, and performs collaborative verification and optimization, while simultaneously generating fault repair early warnings. The dynamic adjustment module 403 presets a basic control time window based on historical data and refines the control time granularity by combining real-time environmental, traffic, and time-specific characteristics, and adjusts the control time in real time. Through the above methods, energy consumption is reduced and control response speed is improved, enabling applications in urban roads, parks, scenic areas, and other scenarios.

[0050] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0051] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0052] Accordingly, this application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; and, when the one or more programs are executed by the one or more processors, causing the one or more processors to implement the above-described cloud server-based dynamic street light control method. Figure 6 The diagram shown is a hardware structure diagram of any device with data processing capabilities in a cloud server-based dynamic street light control system provided by an embodiment of the present invention, except... Figure 6 In addition to the processor, memory, and network interface shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.

[0053] Accordingly, this application also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the aforementioned cloud server-based dynamic street light control method. The computer-readable storage medium can be an internal storage unit of any data processing device as described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any data processing device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the data processing device, and can also be used to temporarily store data that has been output or will be output.

[0054] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0055] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A method for dynamic control of streetlights based on a cloud server, characterized in that, Includes the following steps: Collect raw data from multiple dimensions, including environment, traffic, street light status, and time. After cleaning, standardization, and feature fusion processing, obtain a comprehensive control factor that combines brightness demand and urgency weight. Based on comprehensive control factors and street light status data, a cloud server is used to generate target brightness and switching instructions for a single light, and to collaboratively verify and optimize, and simultaneously generate fault repair early warnings. Based on historical data, a basic control time window is preset, and the control time granularity is refined by combining real-time environmental, traffic and time characteristics, and the control time is adjusted in real time.

2. The street light dynamic control method based on a cloud server as described in claim 1, characterized in that, In the process of collecting raw data from multiple dimensions, including environment, traffic, streetlight status, and time, and then cleaning, standardizing, and fusing feature data to obtain a comprehensive control factor that weights brightness demand and urgency: Environmental data, traffic data, and street light status data are collected separately, and time data is synchronized. The environmental data includes light intensity, weather type, and visibility; the traffic data includes traffic flow, vehicle speed, and pedestrian flow; and the street light status data includes street light power, brightness, current, voltage, and fault information. Standardize the cleaned data and map data from different dimensions to a unified quantization range; The standardized data is fused to extract key features and output a comprehensive control factor that includes brightness demand weight and urgency weight.

3. The street light dynamic control method based on a cloud server as described in claim 2, characterized in that, After collecting environmental data, traffic data, and street light status data separately, and synchronizing time data: The collected multi-dimensional raw data is cleaned to remove outliers caused by sensor malfunctions, and missing data is filled in using interpolation.

4. The street light dynamic control method based on a cloud server as described in claim 2, characterized in that, In the steps of feature fusion of standardized data, extraction of key features, and output of a comprehensive control factor including brightness demand weight and urgency weight: Standardized environmental data, traffic data, time data, and street light status data are classified according to data dimensions to construct a multi-source feature matrix; The feature matrix is ​​processed hierarchically to extract local key features from each data dimension and capture time series features.

5. The street light dynamic control method based on a cloud server as described in claim 4, characterized in that, After performing hierarchical processing on the feature matrix, extracting local key features from each data dimension, and capturing time series features: The extracted multi-dimensional features are weighted and fused to generate brightness demand weight and urgency weight, which together constitute a comprehensive control factor.

6. The street light dynamic control method based on a cloud server as described in claim 1, characterized in that, In the steps of generating target brightness and switching commands for individual lights using a cloud server based on comprehensive control factors and street light status data, and collaboratively verifying and optimizing, and synchronously generating fault maintenance early warnings: Acquire comprehensive control factors and street light status data, construct a decision model, and set protection threshold constraints for maximum brightness and minimum power of street lights; The target brightness value and on / off status command for each street light are calculated and output based on the real-time comprehensive control factor. For streetlights that show a fault in the status data, maintenance warning instructions are generated simultaneously, and maintenance priorities are planned.

7. The street light dynamic control method based on a cloud server as described in claim 6, characterized in that, After calculating and outputting the target brightness value and on / off status command for each street light based on the real-time comprehensive control factor: Perform collaborative verification of instructions from adjacent streetlights.

8. The method for dynamic control of streetlights based on a cloud server as described in claim 1, characterized in that, In the process of setting a basic control time window based on historical data, and refining the control time granularity by combining real-time environmental, traffic, and time segment characteristics, the control time is adjusted in real time: Based on historical lighting data and regional work and rest patterns, preset basic control time windows for multiple scenarios; Adjust the switching time of lights based on real-time light intensity data; The duration of the lights is dynamically adjusted based on real-time traffic and pedestrian flow data. Optimize the time granularity of adjustment based on the characteristics of different time periods, refining hourly adjustments to minute-level adjustments.

9. The street light dynamic control method based on a cloud server as described in claim 8, characterized in that, In the process of adjusting the switching time of lights based on real-time light intensity data: If the light intensity is below the threshold, the streetlights will be turned on in advance. If the light intensity is higher than the threshold, the streetlights will be turned off later.

10. A cloud server-based dynamic street light control system, employing the cloud server-based dynamic street light control method as described in claim 1, characterized in that, This includes a multimodal data fusion and analysis module, a cloud server street light control command generation module, and a control time dynamic adjustment module; among which: The multimodal data fusion and analysis module is used to collect raw data from multiple dimensions, including environment, traffic, street light status, and time. After cleaning, standardization, and feature fusion processing, it obtains a comprehensive control factor for brightness demand and urgency weight. The cloud server street light control instruction generation module is used to generate single-lamp target brightness and on / off instructions based on comprehensive control factors and street light status data, and to collaboratively verify and optimize, and synchronously generate fault maintenance early warnings. The dynamic adjustment module for control time is used to preset a basic control time window based on historical data, and to refine the control time granularity by combining real-time environment, traffic and time characteristics, and to adjust the control time in real time.

Images