Urban cultural tourism lighting night scene interconnection control method and system based on photovoltaic technology

Abstract

The present invention relates to the field of lighting night scene control technology, and in particular to a method and system for interconnected control of urban cultural and tourism lighting night scene based on photovoltaic technology. The method comprises the following steps: obtaining scenic area crowd monitoring parameters and photovoltaic lighting night scene equipment status data; performing spatial position positioning calculations on all photovoltaic lighting night scene equipment, and performing spatial distribution analysis, thereby obtaining multiple equipment area distribution maps; performing regional power load calculations on multiple equipment area distribution maps based on photovoltaic lighting night scene equipment status data, and performing power load demand forecasting, thereby generating power load demand forecasting data for each area; performing crowd flow distribution calculations on scenic area crowd monitoring parameters based on multiple equipment area distribution maps, and performing short-term crowd flow situation forecasting, thereby generating crowd flow situation forecasting data for different areas. The present invention realizes efficient response and low energy consumption lighting night scene control.

Description

Technical Field

[0001] The present invention relates to the technical field of lighting night scene control, and in particular to a method and system for interconnected control of urban cultural and tourism lighting night scene based on photovoltaic technology. Background Art

[0002] Urban night scene lighting system has become an indispensable and important part of urban construction. Beautiful night scene lighting can not only meet the basic lighting needs of urban residents, but also create a unique urban cultural atmosphere and inject new vitality into the development of urban tourism. However, traditional urban night scene lighting systems usually have high energy consumption and low efficiency in the linkage response of night scene equipment between regions, which makes it difficult to meet the requirements of sustainable development. With the continuous development of urban construction, people have put forward higher requirements on the quality and experience of night city landscape. How to use advanced technical means to create a personalized and intelligent urban cultural tourism lighting system has become a key issue that needs to be solved urgently. Summary of the invention

[0003] In order to solve the above-mentioned technical problems, the present invention proposes a method and system for interconnected control of urban cultural and tourism lighting night scenes based on photovoltaic technology to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above object, the present invention provides a method for interconnecting and controlling urban cultural and tourism lighting night scenes based on photovoltaic technology, comprising the following steps:

[0005] Step S1: Obtain scenic area crowd monitoring parameters and photovoltaic lighting night scene equipment status data; perform spatial position positioning calculations on all photovoltaic lighting night scene equipment, and perform spatial distribution analysis to obtain multiple equipment area distribution maps;

[0006] Step S2: Calculate the regional power load of multiple equipment regional distribution maps based on the photovoltaic lighting night scene equipment status data, and predict the power load demand, so as to generate power load demand prediction data for each area;

[0007] Step S3: Calculate the crowd flow distribution of the scenic spot crowd flow monitoring parameters based on the regional distribution maps of multiple devices, and perform short-term crowd flow situation prediction to generate crowd flow situation prediction data for different areas;

[0008] Step S4: obtaining a night scene lighting operation plan; decomposing the night scene lighting operation plan into multiple time periods, and analyzing the lighting behavior of each device one by one, and generating dynamic lighting behavior characteristics of each device;

[0009] Step S5: dynamically adjusting the lighting brightness of each device according to the power load demand prediction data of each area to generate dynamic lighting brightness adjustment data;

[0010] Step S6: Based on the crowd flow situation prediction data in different areas, the dynamic lighting brightness adjustment data is fine-tuned in real time, and collaborative linkage control optimization is performed to build a collaborative optimization strategy for night scene equipment to execute the lighting night scene interconnection control operation.

[0011] The present invention understands the position distribution of each photovoltaic lighting night scene device through spatial position positioning calculation and distribution analysis, and generates multiple device area distribution maps, which is helpful to intuitively display the distribution of the equipment in the scenic area, and provides a basis for subsequent energy consumption and crowd flow analysis. The power load calculation and demand forecast based on the equipment status data are used to evaluate the power consumption of each area, and the power load demand forecast data generated is helpful to plan the power supply and optimize the energy utilization to meet the power demand of the scenic area. The crowd flow distribution calculation and short-term crowd flow situation forecast are used to understand the crowd flow in different areas of the scenic area, and the crowd flow situation forecast data is helpful to reasonably arrange the brightness of the lighting equipment and energy-saving adjustment, so as to improve Scenic area experience and safety, decomposition of night lighting operation plans and analysis of equipment lighting behavior to gain an in-depth understanding of lighting usage, generation of dynamic lighting behavior characteristics for each device helps to formulate personalized lighting strategies and improve energy efficiency, and adjusts lighting behavior based on power load demand forecast data to achieve a balance between energy conservation and comfortable lighting. Generating dynamic lighting brightness adjustment data helps optimize lighting effects and improve energy efficiency. Lighting brightness adjustment and collaborative linkage control based on crowd flow forecast data optimizes and improves scenic area lighting effects and energy conservation. Building a collaborative optimization strategy for night view equipment helps to achieve intelligent lighting control and improve the quality and management efficiency of scenic area night views.

[0012] Preferably, step S1 comprises the following steps:

[0013] Step S11: Acquire scenic spot crowd monitoring parameters based on multi-dimensional sensors, identify all photovoltaic lighting night scene equipment in the urban cultural and tourism scenic spot, and collect photovoltaic lighting night scene equipment status data;

[0014] Step S12: performing spatial location calculation on all photovoltaic night scene lighting devices to obtain the spatial location coordinates of each device;

[0015] Step S13: performing spatial distribution analysis on the spatial position coordinates of each device, thereby obtaining device spatial distribution data;

[0016] Step S14: performing spatial distribution fitting on the device spatial distribution data to construct a device spatial distribution map;

[0017] Step S15: performing region division processing on the device space distribution map, thereby obtaining a plurality of device region distribution maps.

[0018] The present invention obtains scenic area crowd monitoring parameters and photovoltaic lighting night scene equipment status data through multi-dimensional sensors to fully understand the situation in the scenic area, identifies all equipment and collects status data, which is helpful for real-time monitoring of equipment operation, and provides basic data for subsequent control and optimization. The spatial position positioning calculation of the equipment is performed to determine the precise position of each device in the scenic area, and the spatial position coordinates of the equipment are obtained, which is helpful for subsequent spatial distribution analysis and optimization of equipment layout. The distribution and density of the equipment in the scenic area are understood through spatial distribution analysis, and the spatial distribution data of the equipment is obtained, which is helpful for optimizing the equipment layout and energy utilization efficiency. Spatial distribution fitting and construction of equipment spatial distribution map can intuitively display the distribution of equipment in the scenic area. Construction of equipment spatial distribution map is helpful for visualizing equipment position, which provides a basis for subsequent regional division and control optimization. The equipment spatial distribution map is subjected to regional division processing to divide the scenic area into different functional areas, and multiple equipment regional distribution maps are obtained, which is helpful for realizing lighting control and energy management for different areas, and improving operation efficiency and user experience.

[0019] Preferably, step S2 comprises the following steps:

[0020] Step S21: Calculate the time-series power generation of each device on the status data of the photovoltaic lighting night scene device, and extract the time-series power generation parameters of each device;

[0021] Step S22: performing a time-series variation analysis on the time-series power generation parameters of each device to generate a time-series power generation curve for each device;

[0022] Step S23: Calculate the power load within a cycle for the time-series power generation curve of each device to generate the power load of each device;

[0023] Step S24: performing regional power load calculation on multiple device regional distribution maps based on the power load of each device to generate multiple regional power load data;

[0024] Step S25: performing load trend evolution of multiple regional power load data one by one to generate power load trend characteristics of each region;

[0025] Step S26: forecasting the power load demand based on the power load trend characteristics of each area, thereby generating power load demand forecast data for each area.

[0026] The present invention calculates the time-series power generation of each device to understand the power generation situation of each device. Extracting the time-series power generation parameters is helpful to analyze the power generation efficiency and operating status of the device, analyzing the changes in the time-series power generation parameters to grasp the dynamic situation of the power generation of the device, generating the time-series power generation curve is helpful to visualize the change trend of the power generation of the device, providing a basis for subsequent analysis, calculating the power load in the cycle of the time-series power generation curve to evaluate the power consumption of the device, generating the power load parameters of the device is helpful to understand the energy consumption of the device, providing data support for energy management and optimization, calculating the regional power load based on the power load of each device to comprehensively consider the impact of multiple devices on regional energy consumption, generating multiple regional power load data is helpful for regional energy management and balancing the power demand of each region, analyzing the trend of multiple regional power loads to find the law and characteristics of load changes, extracting regional power load trend characteristics is helpful to predict power demand, optimize energy distribution and energy-saving strategies, and predicting and planning future power demand for the power load trend characteristics of each region, generating regional power load demand forecast data is helpful to reasonably arrange energy supply and optimize energy utilization to meet the power demand of scenic spots.

[0027] Preferably, the specific steps of step S26 are:

[0028] Extracting the power load trend feature of the first area of ​​the power load trend feature;

[0029] Perform multi-time point feature analysis on the power load trend feature of the first area to obtain the power load trend features at multiple time points;

[0030] Identify the peak and valley values ​​of the power load trend characteristics at multiple time points to mark the peak and valley time points of the power load;

[0031] Mining the periodic evolution characteristics of the peak and valley time points of the power load to generate the periodic evolution characteristics of the power load;

[0032] Conduct deep modeling and learning on the characteristics of the power load cycle evolution to generate the power load cycle evolution law;

[0033] Based on the evolution law of the power load cycle, the power load demand of the first area is predicted based on the power load trend characteristics, so as to generate the power load demand prediction data of the first area;

[0034] The power load demand forecasting operation is repeated to generate power load demand forecasting data for each area.

[0035] The present invention extracts the trend characteristics of the power load in the first area to understand the energy consumption patterns and characteristics of the area, and conducts multi-time point feature analysis to reveal the changing trends and patterns of the power load at different time points, providing a basis for more sophisticated power load management. Identifying the peak and valley time points of the power load is helpful to determine the peaks and valleys of energy consumption, providing important information for energy scheduling and optimization. Mining the periodic evolution characteristics of the power load discovers the periodic changes in energy consumption, helping to understand the long-term laws of energy utilization. Through deep modeling, the periodic evolution laws of the power load are learned to establish a more accurate prediction model, improve the accuracy and reliability of the power load demand, and conduct demand forecasting based on the periodic evolution laws of the power load to effectively plan future power demand and optimize energy distribution and management.

[0036] Preferably, step S3 specifically comprises the following steps:

[0037] Step S31: Performing a crowd flow fluctuation analysis on the crowd flow monitoring parameters of the scenic spot to generate crowd flow fluctuation data of the scenic spot;

[0038] Step S32: Based on the regional distribution diagrams of multiple equipment, regional crowd flow fluctuation identification is performed on the scenic area crowd flow fluctuation data to generate crowd flow fluctuation characteristics for each area;

[0039] Step S33: performing regional crowd flow interaction analysis on the floating characteristics of the crowd flow in each area, so as to obtain the crowd flow interaction logic between different areas;

[0040] Step S34: Calculate the flow distribution of people based on the floating characteristics of the flow of people in each area to obtain regional flow distribution data;

[0041] Step S35: Perform short-term crowd flow situation prediction on the regional crowd flow distribution data according to the crowd flow interaction logic between different areas, so as to generate crowd flow situation prediction data for different areas.

[0042] The present invention helps to understand the fluctuation law and trend of the scenic spot flow by analyzing the crowd flow fluctuation of the crowd flow monitoring parameters, generates the scenic spot flow fluctuation data to provide data support for the subsequent crowd flow management and planning, performs regional crowd flow floating identification on the scenic spot flow fluctuation data based on the equipment area distribution map to determine the crowd flow changes in different areas, generates the crowd flow floating characteristics of each area, helps to distinguish the characteristics of crowd flow activities in different areas in the scenic area, performs regional crowd flow interaction analysis on the crowd flow floating characteristics of each area to reveal the crowd flow interaction law between different areas, obtains the crowd flow interaction logic between different areas, helps to optimize the scenic area planning and improve the crowd flow guidance strategy, performs crowd flow distribution calculation according to the crowd flow floating characteristics of each area to determine the crowd flow distribution of each area, obtains the regional crowd flow distribution data, helps to understand the crowd density and distribution in different areas in the scenic area, performs short-term crowd flow situation prediction on the regional crowd flow distribution data according to the crowd flow interaction logic between different areas to predict the future crowd flow distribution of the scenic area, and generates the crowd flow situation prediction data of different areas, helps to carry out reasonable crowd flow guidance and lighting control, and improves the experience and management efficiency of the urban cultural tourism lighting night scene.

[0043] Preferably, the specific steps of step S4 are:

[0044] Step S41: Obtaining a night scene lighting operation plan;

[0045] Step S42: Decomposing the night scene lighting operation plan into multiple time periods to obtain lighting operation plans for multiple time periods;

[0046] Step S43: performing lighting operation behavior characteristic analysis on the lighting operation schemes of multiple time periods to obtain lighting behavior characteristics of different time periods;

[0047] Step S44: matching the lighting behaviors of multiple device area distribution maps one by one according to the lighting behavior characteristics of different time periods, thereby generating lighting behavior data for each device;

[0048] Step S45: Perform dynamic lighting behavior analysis on the lighting behavior data of each device to generate dynamic lighting behavior characteristics of each device.

[0049] The present invention can provide a basis for lighting system design by obtaining a night scene lighting operation plan to ensure that the overall lighting system operates as planned. The lighting operation plan can be decomposed into multiple time periods to adjust the lighting plan according to the needs of different time periods, thereby improving the flexibility and adaptability of the lighting system. Obtaining lighting operation plans for multiple time periods helps to optimize energy utilization efficiency and reduce energy waste. Analyzing the behavioral characteristics of the lighting operation plan helps to understand the lighting needs of different time periods and provide guidance for lighting control. Obtaining the lighting behavior characteristics of different time periods can help optimize the lighting plan and improve energy utilization efficiency. Matching the lighting behavior of each device can ensure that each device operates according to the lighting behavior characteristics and improve the overall efficiency of the lighting system. Generating lighting behavior data for each device helps to monitor and adjust the lighting effect of the device and reduce energy waste. Analyzing the dynamic lighting behavior of each device monitors the lighting status of the device in real time to ensure efficient energy utilization. Generating dynamic lighting behavior characteristics of the device helps to optimize the operation mode of the device, improve the energy utilization efficiency of the lighting device and reduce energy costs.

[0050] Preferably, the specific steps of step S43 are:

[0051] Extracting lighting operation instruction features based on lighting operation plans for multiple time periods, wherein the lighting operation instruction features include equipment lighting brightness, color temperature, lighting duration, and color features;

[0052] Calculate the average lighting brightness of the equipment to obtain average lighting brightness data;

[0053] Identify the regional color temperature variation range of color temperature and generate the color temperature variation range of different time periods;

[0054] Perform device-by-device distribution statistics on the duration of lighting, so as to obtain the distribution data of the duration of lighting of different devices;

[0055] Performing device dynamic color change evolution on the color feature to generate device dynamic color change features;

[0056] The lighting operation behavior characteristics are analyzed by the average lighting brightness data, the color temperature variation range in different time periods, the lighting time distribution data of different devices and the dynamic color change characteristics of the devices to obtain the lighting operation behavior characteristics in different time periods.

[0057] The present invention helps to adjust the lighting plan according to the needs of different time periods by decomposing the lighting operation plan into multiple time periods, thereby improving the adaptability of the lighting system. The lighting operation plans for multiple time periods provide a detailed data basis for subsequent analysis, promoting the improvement of the energy efficiency of lighting equipment. Analyzing the behavioral characteristics of the lighting operation plan helps to understand the lighting needs and characteristics of different time periods, and provide guidance for lighting control. Through the analysis of lighting behavior characteristics, the lighting plan is optimized, and the energy efficiency of lighting equipment is improved. The lighting behavior of each device is matched to ensure that the lighting behavior of each device meets expectations, thereby improving the overall efficiency of the lighting system. The generation of lighting behavior data for each device helps to monitor and adjust the lighting effect of the device, reduce energy waste, and maximize energy efficiency. The dynamic lighting behavior of each device is analyzed to monitor the lighting status of the device in real time to ensure efficient energy utilization. The generation of dynamic lighting behavior characteristics of the device helps to optimize the operation mode of the device, improve the energy efficiency of the lighting equipment, reduce energy costs, and realize interconnected control of urban cultural and tourism lighting night scenes.

[0058] Preferably, the specific steps of step S5 are:

[0059] Step S51: Calculate the load demand peak value for the power load demand forecast data of each area to obtain the load demand peak value;

[0060] Step S52: Predict the peak time of the load demand peak and generate the load demand peak time point for each area;

[0061] Step S53: dynamically adjust the lighting brightness of each device based on the load demand peak time point of each area to generate dynamic lighting brightness adjustment data.

[0062] The present invention calculates the load demand peak value for the electricity load demand forecast data of each area, which helps to determine the maximum load demand of each area. The load demand peak value helps to reasonably plan energy supply and distribution, improve energy utilization efficiency, and ensure the stable operation of the urban cultural and tourism lighting night scene. The peak time prediction for the load demand peak value predicts the time point when the load demand peak value of each area will help to reasonably arrange energy supply. The generation of load demand peak time point data helps to optimize energy scheduling, improve energy utilization efficiency, and ensure that sufficient energy support can be provided during peak demand periods. The lighting brightness is adjusted for the dynamic lighting behavior characteristics of the equipment based on the load demand peak time point of each area, and the lighting brightness is adjusted in real time according to demand to improve energy utilization efficiency. The generation of dynamic lighting brightness adjustment data helps to adjust the lighting system according to the load demand situation, realize dynamic energy distribution, ensure the best lighting effect during high load periods, and realize coordinated control of the urban cultural and tourism lighting night scene.

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

[0064] Step S61: performing real-time progressive fine-tuning on the dynamic lighting brightness adjustment data based on the crowd flow situation prediction data of different areas to generate real-time fine-tuning night scene lighting data;

[0065] Step S62: performing regional linkage response analysis on the real-time fine-tuning night scene lighting data to generate regional linkage response data;

[0066] Step S63: Calculate the response delay of the regional linkage response data to obtain inter-regional response delay data;

[0067] Step S64: All photovoltaic lighting night scene equipment are coordinated and linked to control optimization according to the inter-regional response delay data, and a night scene equipment coordinated optimization strategy is constructed to execute the lighting night scene interconnection control operation.

[0068] The present invention performs real-time progressive fine-tuning based on the predicted data of human flow situation to dynamically adjust the lighting brightness according to the actual situation, thereby improving the lighting effect and energy-saving effect. The generation of real-time fine-tuning night scene lighting data helps to adapt to the changing needs of urban cultural and tourism lighting night scenes, and provides a more comfortable and safe lighting environment. The real-time fine-tuning night scene lighting data is subjected to regional linkage response analysis to realize coordinated control between different regions, thereby improving the overall efficiency and flexibility of the lighting system. The generation of regional linkage response data helps to optimize the lighting scheme, making the lighting system more intelligent and responsive. The calculation of the response delay data between regions helps to determine the response speed between different regions, helps to optimize the response strategy, and improves the response efficiency and accuracy of the lighting system. The acquisition of the inter-regional response delay data helps to establish a more accurate regulation mechanism, realizes the rapid response and coordinated control of the lighting system, and performs coordinated linkage control optimization on all photovoltaic lighting night scene devices according to the inter-regional response delay data to realize the coordinated work between devices, thereby improving the overall efficiency and energy utilization efficiency of the system. The construction of a coordinated optimization strategy for night scene devices helps to improve the management level of urban cultural and tourism lighting night scenes, and realizes the intelligent and efficient operation of the interconnected control of lighting night scenes.

[0069] In this specification, a photovoltaic-based urban cultural tourism lighting night scene interconnection control system is provided, which is used to execute the photovoltaic-based urban cultural tourism lighting night scene interconnection control method as described above, including:

[0070] The equipment spatial distribution module is used to obtain the scenic area crowd monitoring parameters and photovoltaic lighting night scene equipment status data; perform spatial location calculations on all photovoltaic lighting night scene equipment, and perform spatial distribution analysis to obtain multiple equipment area distribution maps;

[0071] The load demand prediction module is used to calculate the regional power load of multiple equipment regional distribution maps based on the status data of photovoltaic lighting night scene equipment, and to predict the power load demand, so as to generate the power load demand prediction data for each area;

[0072] The crowd flow situation prediction module is used to calculate the crowd flow distribution of the scenic area crowd flow monitoring parameters based on the regional distribution maps of multiple devices, and to perform short-term crowd flow situation prediction to generate crowd flow situation prediction data for different areas;

[0073] The lighting behavior module is used to obtain the night scene lighting operation plan; decompose the night scene lighting operation plan into multiple time periods, and analyze the lighting behavior of each device to generate the dynamic lighting behavior characteristics of each device;

[0074] A dynamic brightness adjustment module, used to dynamically adjust the lighting brightness of each device according to the power load demand prediction data of each area, so as to generate dynamic lighting brightness adjustment data;

[0075] The collaborative control module is used to make real-time progressive fine-tuning of dynamic lighting brightness adjustment data based on the crowd flow situation prediction data in different areas, and to perform collaborative linkage control optimization, build a collaborative optimization strategy for night view equipment, and execute lighting night view interconnection control operations.

[0076] The present invention helps to understand the real-time situation in the scenic area by acquiring scenic spot crowd monitoring parameters and equipment status data, and provides basic data for subsequent decision-making. Spatial location positioning and distribution analysis can help achieve a reasonable layout of equipment, optimize lighting effects and energy utilization efficiency, and regional power load calculation and demand forecasting based on equipment status data help to reasonably plan energy supply and ensure the stable operation of the lighting system. Generating power load demand forecast data helps to optimize energy scheduling and improve energy utilization efficiency. Obtaining night scene lighting operation plans and performing lighting behavior analysis helps to optimize lighting plans and improve lighting effects. Dynamic lighting behavior characteristics are analyzed to adjust lighting brightness according to demand to achieve intelligent lighting control. The lighting behavior of the equipment is dynamically adjusted according to the power load demand forecast data, which helps to save energy and reduce emissions and improve lighting effects. Dynamic lighting brightness adjustment data is generated to adjust the lighting brightness in real time according to actual conditions to adapt to different demand scenarios. Real-time progressive fine-tuning and collaborative linkage control optimization improve the flexibility and response speed of the lighting system, ensure the efficient operation of the lighting system, and construct a night scene equipment collaborative optimization strategy to help achieve intelligent management of lighting night scenes and improve the quality and efficiency of urban cultural and tourism lighting night scenes. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1 A schematic flow chart of the steps of a photovoltaic technology-based urban cultural and tourism lighting night scene interconnection control method of the present invention;

[0078] Figure 2 Detailed implementation flow chart of step S1;

[0079] Figure 3 Detailed implementation flow chart of step S2;

[0080] Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0081] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0082] The example of this application provides a method and system for interconnected control of urban cultural and tourism lighting night scenes based on photovoltaic technology. The execution subjects of the method and system for interconnected control of urban cultural and tourism lighting night scenes based on photovoltaic technology include but are not limited to: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of this application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0083] See also Figures 1 to 4 The present invention provides a photovoltaic technology-based urban cultural tourism lighting night scene interconnection control method, the photovoltaic technology-based urban cultural tourism lighting night scene interconnection control method comprising the following steps:

[0084] Step S1: Obtain scenic area crowd monitoring parameters and photovoltaic lighting night scene equipment status data; perform spatial position positioning calculations on all photovoltaic lighting night scene equipment, and perform spatial distribution analysis to obtain multiple equipment area distribution maps;

[0085] Step S2: Calculate the regional power load of multiple equipment regional distribution maps based on the photovoltaic lighting night scene equipment status data, and predict the power load demand, so as to generate power load demand prediction data for each area;

[0086] Step S3: Calculate the crowd flow distribution of the scenic spot crowd flow monitoring parameters based on the regional distribution maps of multiple devices, and perform short-term crowd flow situation prediction to generate crowd flow situation prediction data for different areas;

[0087] Step S4: obtaining a night scene lighting operation plan; decomposing the night scene lighting operation plan into multiple time periods, and analyzing the lighting behavior of each device one by one, and generating dynamic lighting behavior characteristics of each device;

[0088] Step S5: dynamically adjusting the lighting brightness of each device according to the power load demand prediction data of each area to generate dynamic lighting brightness adjustment data;

[0089] Step S6: Based on the crowd flow situation prediction data in different areas, the dynamic lighting brightness adjustment data is fine-tuned in real time, and collaborative linkage control optimization is performed to build a collaborative optimization strategy for night scene equipment to execute the lighting night scene interconnection control operation.

[0090] The present invention understands the position distribution of each photovoltaic lighting night scene device through spatial position positioning calculation and distribution analysis, and generates multiple device area distribution maps, which is helpful to intuitively display the distribution of the equipment in the scenic area, and provides a basis for subsequent energy consumption and crowd flow analysis. The power load calculation and demand forecast based on the equipment status data are used to evaluate the power consumption of each area, and the power load demand forecast data generated is helpful to plan the power supply and optimize the energy utilization to meet the power demand of the scenic area. The crowd flow distribution calculation and short-term crowd flow situation forecast are used to understand the crowd flow in different areas of the scenic area, and the crowd flow situation forecast data is helpful to reasonably arrange the brightness of the lighting equipment and energy-saving adjustment, so as to improve Scenic area experience and safety, decomposition of night lighting operation plans and analysis of equipment lighting behavior to gain an in-depth understanding of lighting usage, generation of dynamic lighting behavior characteristics for each device helps to formulate personalized lighting strategies and improve energy efficiency, and adjusts lighting behavior based on power load demand forecast data to achieve a balance between energy conservation and comfortable lighting. Generating dynamic lighting brightness adjustment data helps optimize lighting effects and improve energy efficiency. Lighting brightness adjustment and collaborative linkage control based on crowd flow forecast data optimizes and improves scenic area lighting effects and energy conservation. Building a collaborative optimization strategy for night view equipment helps to achieve intelligent lighting control and improve the quality and management efficiency of scenic area night views.

[0091] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a method for interconnecting and controlling urban cultural and tourism lighting night scenes based on photovoltaic technology of the present invention. In this example, the steps of the method include:

[0092] Step S1: Obtain scenic area crowd monitoring parameters and photovoltaic lighting night scene equipment status data; perform spatial position positioning calculations on all photovoltaic lighting night scene equipment, and perform spatial distribution analysis to obtain multiple equipment area distribution maps;

[0093] In this embodiment, crowd monitoring data is obtained from a monitoring system in the scenic area (such as video surveillance, infrared sensors or crowd counters). These data generally include: timestamp: the time when the crowd flow is recorded, area ID: the specific area where the crowd flow is located, crowd flow: the number of people passing through the monitoring point in each time period, and the status data of all night scene lighting equipment is extracted from the photovoltaic lighting control system, including: equipment ID: the unique identifier of each device, current brightness level: the current lighting intensity of the device, switch status: whether the device is turned on or off, battery status: the battery charging status of the photovoltaic device, and device fault status: whether there is a fault or maintenance requirement. The extracted crowd monitoring parameters and photovoltaic lighting equipment status data are integrated into a unified data structure, such as using PandasDataFrame to ensure that the data fields are consistent, including timestamp, area ID, equipment ID and corresponding monitoring data, and the spatial location of each photovoltaic lighting device is obtained using GPS, Bluetooth positioning or indoor positioning system. If the equipment has been pre-installed in a specific location, ensure that there is a location database support, record the geographic coordinates of each device, use geographic information system (GIS) software or data visualization tools (such as Matplotlib or Folium) to visualize the spatial location of the equipment, generate a device distribution map, and display the distribution of equipment in the scenic area by drawing a scatter plot or heat map to identify the relative position relationship between devices. If it is necessary to further analyze the distribution characteristics of the equipment, use a clustering algorithm (such as K-Means or DBSCAN) to group the equipment and identify the concentrated or dispersed areas of the equipment. Through cluster analysis, generate a more specific equipment area distribution map to help subsequent lighting control and crowd management, and store crowd monitoring data, photovoltaic equipment status data, and equipment spatial distribution data in a database (such as MySQL, PostgreSQL, or MongoDB) to provide basic data support for subsequent analysis and decision-making.

[0094] Step S2: Calculate the regional power load of multiple equipment regional distribution maps based on the photovoltaic lighting night scene equipment status data, and predict the power load demand, so as to generate power load demand prediction data for each area;

[0095] In this embodiment, the power load of each area is calculated according to the power and working status of the equipment. The specific steps are as follows: create a dictionary with the key as the area ID and the value as the corresponding total load (initial value is 0), traverse each device and check its working status: if the device status is "on", add the power value (W) of the device to the load value of the corresponding area. After the traversal is completed, the total power load of each area is obtained. The power load data in the past period of time is collected to ensure that the data contains the timestamp and the corresponding load value. Select a suitable prediction model for load demand prediction. Commonly used models include: time series analysis (such as ARIMA, SARIMA) machine learning models (such as linear regression) The historical load data are divided into training set and test set (such as regression, decision tree, random forest), and the selected model is trained with the training set. The specific steps include: smoothing and standardizing the data, constructing feature variables according to time characteristics (such as hours, days, weeks) and external influencing factors (such as weather and pedestrian flow), fitting the model with the training set, adjusting the model parameters to improve the prediction accuracy, and using the trained model to predict the future power load and generate the power load demand data for each region in the future. The prediction results should include the load demand value of each region in a specific time period in the future (such as hours and days), and organize the prediction results into a structured data format, including information such as region ID, prediction time, and predicted load value.

[0096] Step S3: Calculate the crowd flow distribution of the scenic spot crowd flow monitoring parameters based on the regional distribution maps of multiple devices, and perform short-term crowd flow situation prediction to generate crowd flow situation prediction data for different areas;

[0097] In this embodiment, computer vision and machine learning algorithms, such as target detection and tracking technologies, are used to analyze and model the monitoring data. The crowd distribution of the entire scenic area is calculated based on the crowd flow and density data of each area. Time series analysis and neural network prediction models are used in combination with historical crowd flow data to predict the crowd flow situation in the short term (such as 1-2 hours) in the future. The prediction results include the expected crowd flow and crowd density change trends in each area. The calculated crowd distribution and predicted situation data are presented through intuitive data visualization methods such as maps and heat maps, providing scenic area managers with real-time crowd monitoring and prediction data to support subsequent intelligent control decisions.

[0098] Step S4: obtaining a night scene lighting operation plan; decomposing the night scene lighting operation plan into multiple time periods, and analyzing the lighting behavior of each device one by one, and generating dynamic lighting behavior characteristics of each device;

[0099] In this embodiment, an existing night scene lighting operation plan is extracted from a lighting control system or a database, and the plan includes: the start and end time of each time period (such as 6 pm to 12 midnight), the lighting brightness, mode (such as constant light, gradual change, flashing) and the on / off status of the device in different time periods, the lighting device configuration of each area and the corresponding control instructions. According to the extracted operation plan, multiple time periods (such as hours, half hours) are defined to analyze the lighting behavior in each time period, and the lighting behavior data of each device is traversed to extract the following features: brightness change: the change of brightness value in different time periods, working status: the on / off status of the device in each time period, lighting mode: the lighting mode adopted by the device in each time period (such as gradual change, flashing, etc.), and a detailed behavior analysis is performed on each device to generate dynamic lighting behavior features, which specifically include: average brightness: calculate the average brightness of each device in all time periods, change frequency: count the frequency of device brightness changes, analyze the activity of the device in different time periods, mode usage: record the different lighting modes used by the device and their duration, and organize the analyzed dynamic lighting behavior features of the device into structured data, including device ID, area ID, and each feature value (such as average brightness, change frequency, mode usage).

[0100] Step S5: dynamically adjusting the lighting brightness of each device according to the power load demand prediction data of each area to generate dynamic lighting brightness adjustment data;

[0101] In this embodiment, brightness adjustment rules are defined based on the power load demand and the dynamic lighting behavior characteristics of the device. If the predicted load demand is higher than a certain threshold, the brightness of the device is increased. If the predicted load demand is lower than a certain threshold, the brightness of the device is reduced to save energy. A proportional relationship is set, for example, the average brightness of the current device is compared with the predicted load value to determine the adjustment range. The brightness is dynamically adjusted according to the flow of people and the use of the device, for example, the brightness is increased when the flow of people is high and the brightness is reduced when the flow of people is low. Each device is traversed to check the power load demand prediction data and dynamic lighting behavior characteristics of its area. According to the defined adjustment strategy, a new brightness value of each device is calculated, for example: new brightness = current average brightness × (predicted load / maximum load of the device) × adjustment coefficient, wherein the adjustment coefficient is dynamically adjusted according to historical data and real-time feedback to ensure the smoothness of the brightness adjustment, and a lighting control system (such as a DMX or DALI controller) is used to update the brightness value of each device in real time.

[0102] Step S6: Based on the crowd flow situation prediction data in different areas, the dynamic lighting brightness adjustment data is fine-tuned in real time, and collaborative linkage control optimization is performed to build a collaborative optimization strategy for night scene equipment to execute the lighting night scene interconnection control operation.

[0103] In this embodiment, fine-tuning rules for dynamic lighting brightness are defined according to changes in human flow, for example: incremental adjustment: when the predicted human flow increases, the brightness of the device is appropriately increased (for example, increased by 10%), reduction adjustment: when the predicted human flow decreases, the brightness of the device is appropriately reduced (for example, reduced by 10%), threshold setting: a threshold for brightness fine-tuning is set to ensure that the brightness remains stable when the human flow changes insignificantly, and to reduce the impact of frequent adjustments. Each area is traversed to check the human flow situation prediction data and the dynamic lighting brightness adjustment data, and a new brightness value is calculated according to the set fine-tuning rules, for example: new brightness = current brightness × (1 + adjustment ratio) where the adjustment ratio is dynamically adjusted according to changes in human flow, and a lighting control system (such as a DMX or DALI controller) is used to update the brightness of each device in real time. value to ensure that the adjustment instructions can be delivered to the equipment in time. During the fine-tuning process, analyze the lighting linkage relationship between different areas. For example, when the brightness of one area is adjusted, whether other areas also need to be adjusted accordingly? According to the linkage analysis results, formulate a collaborative optimization strategy for night view equipment. While increasing the brightness in high-flow areas, appropriately increase the brightness of adjacent areas to ensure the overall lighting effect. According to the level of traffic, divide the area into different control levels, formulate different lighting strategies, and apply the formulated collaborative optimization strategy to the lighting control system to ensure that each device is adjusted according to the new control strategy. During the execution process, monitor the lighting effects and traffic changes in each area in real time, collect feedback data, and further optimize the fine-tuning rules and collaborative control strategies based on the feedback data to ensure the flexibility and adaptability of the system.

[0104] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0105] Step S11: Acquire scenic spot crowd monitoring parameters based on multi-dimensional sensors, identify all photovoltaic lighting night scene equipment in the urban cultural and tourism scenic spot, and collect photovoltaic lighting night scene equipment status data;

[0106] Step S12: performing spatial location calculation on all photovoltaic night scene lighting devices to obtain the spatial location coordinates of each device;

[0107] Step S13: performing spatial distribution analysis on the spatial position coordinates of each device, thereby obtaining device spatial distribution data;

[0108] Step S14: performing spatial distribution fitting on the device spatial distribution data to construct a device spatial distribution map;

[0109] Step S15: performing region division processing on the device space distribution map, thereby obtaining a plurality of device region distribution maps.

[0110] In this embodiment, according to the environment and needs of the scenic area, suitable sensors such as infrared sensors, cameras and lidar are selected. The selection of these sensors takes into account the accuracy, cost and feasibility of installation of monitoring. Sensors are installed at key locations in the urban cultural and tourism scenic area (such as entrances, main passages, near photovoltaic equipment, etc.), and the field of view of the sensors is ensured to be unobstructed. Sensor parameters (such as sensitivity and sampling frequency) are configured to optimize the monitoring effect. Sensors are used to monitor the flow of people in the scenic area in real time, and image processing technology (such as computer vision algorithm) is combined to identify photovoltaic lighting night scene equipment in the scenic area. Deep learning models (such as convolutional neural networks) are used for equipment identification, and the status data of each photovoltaic lighting night scene equipment is recorded, including Including switch status (on / off), working time, energy consumption (such as voltage, current), etc. This data is obtained through the device's own sensors or through a centralized control system. The status data of all photovoltaic night lighting devices are extracted from the database, including unique identifiers such as device IDs, and prepared for location positioning. GPS positioning, RFID, or positioning methods based on image recognition are used. For outdoor environments, GPS positioning is the most commonly used, while in indoor environments, RFID or image processing technology is more effective. The spatial position positioning calculation is performed on each photovoltaic night lighting device to obtain its spatial position coordinates (such as longitude and latitude or plane coordinates). For example, the longitude and latitude are obtained using a GPS module, and the triangulation method is used to locate the known coordinate points. Determine the exact location of the equipment, extract the spatial location coordinates of all photovoltaic lighting night scene equipment from the database, form a location coordinate data set, use geographic information system (GIS) tools (such as ArcGIS, QGIS) or statistical analysis software (such as R or Python's Pandas, NumPy library) to perform spatial distribution analysis, identify the spatial distribution pattern of the equipment through spatial clustering analysis (such as K-means algorithm, DBSCAN), determine the concentrated area and sparse area of ​​the equipment, record the analysis results, and form a device spatial distribution data set, including the number of equipment in each cluster, distribution center and distribution range, and use spatial interpolation methods (such as Kriging interpolation, inverse distance weighted method) to perform spatial distribution analysis of the equipment. The distribution data is fitted to generate a continuous device distribution model. According to the spatial distribution data of the equipment, interpolation calculation is performed to generate a device spatial distribution map to show the distribution of the equipment in the geographic space. The fitting results are saved as a spatial distribution map and stored in the database to form a visual distribution model. The spatial distribution map is divided into regions using regional partitioning algorithms (such as Voronoi diagram and clustering-based regional partitioning). The Voronoi diagram generates the service area of ​​each device according to the location of the device, while the clustering method divides the region according to the spatial density. According to the spatial distribution of the equipment, the device spatial distribution map is divided into regions to generate multiple device regional distribution maps, and each region represents the range served by a specific device.

[0111] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0112] Step S21: Calculate the time-series power generation of each device on the status data of the photovoltaic lighting night scene device, and extract the time-series power generation parameters of each device;

[0113] Step S22: performing a time-series variation analysis on the time-series power generation parameters of each device to generate a time-series power generation curve for each device;

[0114] Step S23: Calculate the power load within a cycle for the time-series power generation curve of each device to generate the power load of each device;

[0115] Step S24: performing regional power load calculation on multiple device regional distribution maps based on the power load of each device to generate multiple regional power load data;

[0116] Step S25: performing load trend evolution of multiple regional power load data one by one to generate power load trend characteristics of each region;

[0117] Step S26: forecasting the power load demand based on the power load trend characteristics of each area, thereby generating power load demand forecast data for each area.

[0118] In this embodiment, the status data of all photovoltaic lighting night scene devices are extracted from the database, including parameters such as light intensity, working hours, and device power. The time-series power generation (P) = device power (W) × working hours (h) × light effectiveness coefficient (considering the influence of light intensity). This coefficient can be obtained through historical data analysis or estimated according to environmental conditions. The time-series power generation is calculated for each photovoltaic lighting device one by one, and the power generation in each time period is recorded. Data analysis tools (such as Python's Pandas and Matplotlib libraries) are used to perform time-series change analysis. The time-series power generation changes of each device are displayed through time series charts, and the peaks and troughs of the power generation are identified. The power load (L) = time-series power generation (P) / time period (h). The average power load in each cycle is calculated. The time-series power generation data of each device is analyzed one by one to calculate the power load of each device. The power load data and regional distribution map of all devices are extracted to prepare for regional power load calculation. The regional power load (R) = Σ (power load of each device), that is, the power load of the devices in each region is summed up. According to the regional division, the power load of the devices in each region is summed up to obtain the total power load of each region. The load trend analysis is performed using time series analysis methods (such as moving average, exponential smoothing) or statistical analysis tools (such as linear regression). The power load data of each region is analyzed one by one to identify the changing trend of the power load and generate load trend characteristics (such as growth rate, fluctuation amplitude). The power load demand is predicted using time series prediction models (such as ARIMA, SARIMA, LSTM) or machine learning models (such as random forest, support vector machine). According to the trend feature data, the future power load demand of each region is predicted to generate power load demand forecast data.

[0119] In this embodiment, the specific steps of step S26 are:

[0120] Extracting the power load trend feature of the first area of ​​the power load trend feature;

[0121] Perform multi-time point feature analysis on the power load trend feature of the first area to obtain the power load trend features at multiple time points;

[0122] Identify the peak and valley values ​​of the power load trend characteristics at multiple time points to mark the peak and valley time points of the power load;

[0123] Mining the periodic evolution characteristics of the peak and valley time points of the power load to generate the periodic evolution characteristics of the power load;

[0124] Conduct deep modeling and learning on the characteristics of the power load cycle evolution to generate the power load cycle evolution law;

[0125] Based on the evolution law of the power load cycle, the power load demand of the first area is predicted based on the power load trend characteristics, so as to generate the power load demand prediction data of the first area;

[0126] The power load demand forecasting operation is repeated to generate power load demand forecasting data for each area.

[0127] In this embodiment, the power load data of the first area is extracted from the database to ensure that the data includes complete time series records, such as date, time, load value, etc. Interpolation methods (such as linear interpolation or polynomial interpolation) are used to fill missing values ​​to ensure data continuity. The interpolate() method in the Pandas library in Python is used to smooth the data using a sliding average method or a median filter to remove outliers and noise and improve data quality. The mean, maximum, minimum, standard deviation and other statistical features of each time period are calculated to fully understand the changes in power load, determine the time period for analysis (such as day, week, month), and select multiple key time points within the time period (such as hourly and daily peak and valley values). For each selected time point, extract the relevant features of the power load. Use the groupby() method in Python to group by time dimension and calculate the required features. Store the power load features of multiple time points in a data frame (such as PandasDataFrame) and mark each time point with a timestamp for subsequent analysis and visualization. Use the find_peaks function in the SciPy library to identify the peak of the power load data, and use custom conditions to identify the valley (such as the load value is below a certain threshold). Perform peak and valley value recognition on the power load data at multiple time points, mark the load peak and valley values ​​at each time point, and use conditional expressions to filter out the peak and valley values. The peak and valley time points (including timestamps and corresponding load values) are stored in the database to form a peak and valley time point data set for subsequent analysis. Based on historical data analysis, the periodic characteristics of the power load (such as daily cycle, weekly cycle, seasonal cycle) are defined, and the length of the analysis cycle (such as 24 hours) is determined. Time series analysis tools (such as Fourier transform, wavelet transform, or seasonal decomposition) are used to mine the periodic evolution characteristics, and the peak and valley time points are analyzed periodically to extract the periodic evolution characteristics of the power load, such as the load fluctuation amplitude and phase change within the cycle. Appropriate deep learning models are selected, such as long short-term memory networks (LSTM) or gated recurrent units (GRU). These models are used in processing It performs well in time series data, organizes the periodic evolution characteristics into a training data set, including input features (such as historical load data) and target outputs (such as future power load values), uses the training data set to train the selected deep learning model, adjusts hyperparameters (such as learning rate, batch size) to optimize model performance, uses Keras or TensorFlow to build and train the model, uses cross-validation or holdout method to evaluate the prediction performance of the model, calculates indicators such as root mean square error (RMSE) or mean absolute error (MAE) for performance evaluation, extracts the power load trend feature data of the first area from the database, prepares to input it into the trained model, and inputs the data to be predicted into the trained deep learning model.Generate future power load demand forecast data, store the forecast results (including timestamp and forecast load value) in the database, form the power load demand forecast data set for the first region, repeat the above steps for each region, from extracting power load trend characteristics to demand forecasting, ensure a comprehensive analysis of the power load in each region, store the power load demand forecast data for each region in the database, and form the power load demand forecast data set for each region for subsequent analysis and decision-making.

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

[0129] Step S31: Performing a crowd flow fluctuation analysis on the crowd flow monitoring parameters of the scenic spot to generate crowd flow fluctuation data of the scenic spot;

[0130] Step S32: Based on the regional distribution diagrams of multiple equipment, regional crowd flow fluctuation identification is performed on the scenic area crowd flow fluctuation data to generate crowd flow fluctuation characteristics for each area;

[0131] Step S33: performing regional crowd flow interaction analysis on the floating characteristics of the crowd flow in each area, so as to obtain the crowd flow interaction logic between different areas;

[0132] Step S34: Calculate the flow distribution of people based on the floating characteristics of the flow of people in each area to obtain regional flow distribution data;

[0133] Step S35: Perform short-term crowd flow situation prediction on the regional crowd flow distribution data according to the crowd flow interaction logic between different areas, so as to generate crowd flow situation prediction data for different areas.

[0134] In this embodiment, time series analysis methods (such as moving average and standard deviation calculation) are used to identify fluctuations in passenger flow, and the daily average, standard deviation and coefficient of variation of passenger flow are calculated to identify fluctuations in different time periods. The rolling() method of the Pandas library is used to calculate the moving average and standard deviation. According to the calculation results, scenic area passenger flow fluctuation data is generated, including the fluctuation amplitude and trend within the time period. Different areas are divided according to the equipment area distribution map, and the ID of each area is marked. Cluster analysis (such as K-means or DBSCAN) is used to identify the area of ​​passenger flow fluctuation data, and the passenger flow fluctuation data in each area is aggregated to calculate the average fluctuation amplitude and fluctuation frequency of the area, mark the floating characteristics of passenger flow, extract the floating characteristic data of passenger flow in each area from the database, prepare for interactive analysis, and use correlation analysis and interactive network analysis methods (such as Pearson correlation coefficient or graph theory analysis) to identify the passenger flow interaction between areas. Mutual features, analyze whether there is a correlation between the fluctuations of passenger flow in different areas, identify the logical relationship of passenger flow interaction, and form an interaction map. Extract the floating feature data of passenger flow in each area from the database, prepare for distribution calculation, use probability distribution models (such as normal distribution, Poisson distribution) to calculate the distribution of passenger flow in the area, perform distribution fitting on the passenger flow data in each area, determine the mean, standard deviation and other distribution characteristics of each area, store the calculated regional passenger flow distribution data in the database for subsequent prediction and analysis, use time series prediction models (such as ARIMA, SARIMA) or machine learning methods (such as random forest, XGBoost) to predict short-term passenger flow trends, build and train prediction models based on the extracted features and interaction logic, use the StatsModels library in Python to train the ARIMA model, predict the passenger flow trend in each area in the future, and generate prediction results.

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

[0136] Step S41: Obtaining a night scene lighting operation plan;

[0137] Step S42: Decomposing the night scene lighting operation plan into multiple time periods to obtain lighting operation plans for multiple time periods;

[0138] Step S43: performing lighting operation behavior characteristic analysis on the lighting operation schemes of multiple time periods to obtain lighting behavior characteristics of different time periods;

[0139] Step S44: matching the lighting behaviors of multiple device area distribution maps one by one according to the lighting behavior characteristics of different time periods, thereby generating lighting behavior data for each device;

[0140] Step S45: Perform dynamic lighting behavior analysis on the lighting behavior data of each device to generate dynamic lighting behavior characteristics of each device.

[0141] In this embodiment, the operation plan of night scene lighting is extracted from the central control system or database. The data should include the opening time, closing time, lighting intensity, mode (such as constant light, flashing, gradient, etc.) of each lighting device, and the relevant timestamp. The extracted data is converted into a standard format, such as JSON or CSV. This format should contain the device ID, time period and related lighting parameters. The sorted night scene lighting operation plan is stored in a temporary database for quick access in subsequent steps. SQLite or an in-memory database (such as PandasDataFrame) is used for temporary storage. The decomposed time period is determined, for example, every 30 minutes. or every hour. These time periods should cover the entire operating time of nighttime lighting. Traverse the obtained lighting operation plan and split it based on the preset time period. Use a loop structure to check the lighting parameters in each time period. Record the lighting status of each time period. Store the lighting plan for each time period as a new data structure, including the time period identifier, device ID and corresponding lighting parameters. Use data analysis tools (such as Python's Pandas and NumPy libraries) for feature extraction and analysis. Analyze the lighting operation plan for each time period and calculate the following features: On / off frequency: Count the number of times the device is turned on and off in each time period, the average lighting status, and the average lighting status. Lighting intensity: calculate the average brightness of lighting equipment in each time period. Lighting mode usage frequency: analyze the usage frequency of different lighting modes (such as constant light, flashing), use Pandas' groupby() method to group time periods, and calculate the corresponding statistical characteristics. Use rule-based matching algorithms or machine learning classification models (such as KNN, decision trees) to match lighting behavior with equipment, determine the lighting status of each device in a specific time period, and for each device, check the lighting behavior characteristics of its area and time period, match them, use conditional statements or model predictions to determine the behavior of the device in the time period, and generate lighting behavior data for each device, including Including time period, device ID and lighting status (on / off, mode, etc.), extract the lighting behavior data of each device from the database, ensure that the data is complete and can reflect the actual use of the device, use time series analysis methods or dynamic system modeling methods (such as state space model, dynamic time warping (DTW)) to analyze dynamic lighting behavior, dynamically analyze the lighting behavior data of each device, and extract features, such as: Change frequency: analyze the frequency of changes in lighting status, such as the rate at which lights are turned on and off, dynamic mode: identify the mode of lighting changes, such as periodic flickering, gradual change, etc., use Fourier transform or wavelet transform to identify frequency characteristics.

[0142] In this embodiment, the specific steps of step S43 are:

[0143] Extracting lighting operation instruction features based on lighting operation plans for multiple time periods, wherein the lighting operation instruction features include equipment lighting brightness, color temperature, lighting duration, and color features;

[0144] Calculate the average lighting brightness of the equipment to obtain average lighting brightness data;

[0145] Identify the regional color temperature variation range of color temperature and generate the color temperature variation range of different time periods;

[0146] Perform device-by-device distribution statistics on the duration of lighting, so as to obtain the distribution data of the duration of lighting of different devices;

[0147] Performing device dynamic color change evolution on the color feature to generate device dynamic color change features;

[0148] The lighting operation behavior characteristics are analyzed by the average lighting brightness data, the color temperature variation range in different time periods, the lighting time distribution data of different devices and the dynamic color change characteristics of the devices to obtain the lighting operation behavior characteristics in different time periods.

[0149] In this embodiment, the lighting operation plans for multiple time periods are extracted from the database or central control system. The data should include the brightness value, color temperature, lighting duration and color status of each device. The extracted data is converted into a structured format (such as PandasDataFrame) to ensure that each data row represents the lighting status of a device in a specific time period. The following lighting operation instruction features are extracted: device lighting brightness: record the brightness value of each device in each time period, color temperature: record the color temperature value of each device in each time period, lighting duration: calculate the lighting duration of each device in a specific time period, color features: record the color status of the device (such as RGB value or hue), use Pandas' groupby() method to group the device brightness data by time period, calculate the average device brightness value in each time period, and average the device color temperature data by time period. Grouping, calculate the maximum and minimum values ​​of the color temperature data for each time period to identify the range of changes, use conditional statements or data filtering, calculate the lighting time of each device in a specific time period, group and count the lighting time by device ID, calculate the lighting time distribution of each device, extract the color status data of the device, record its changes (such as changes in RGB values), use time series analysis technology (such as dynamic time warping (DTW)) to analyze the change pattern of device color, identify dynamic color change characteristics, integrate the average lighting brightness data, color temperature change range, lighting time distribution data and dynamic color change characteristics into a data frame, use statistical analysis methods (such as principal component analysis (PCA) or cluster analysis) to comprehensively analyze the integrated data to identify the lighting operation behavior characteristics of different time periods, calculate the correlation between each feature, and identify the key factors affecting lighting behavior.

[0150] In this embodiment, the specific steps of step S5 are:

[0151] Step S51: Calculate the load demand peak value for the power load demand forecast data of each area to obtain the load demand peak value;

[0152] Step S52: Predict the peak time of the load demand peak and generate the load demand peak time point for each area;

[0153] Step S53: dynamically adjust the lighting brightness of each device based on the load demand peak time point of each area to generate dynamic lighting brightness adjustment data.

[0154] In this embodiment, a statistical analysis tool (such as Python's Pandas and NumPy libraries) is used to calculate the load peak, the electricity load demand data of each area is traversed, the max() function is used to calculate the maximum load demand value of each area, the load demand peak is determined, the load demand peak of each area and its corresponding timestamp are recorded to form a new data structure (such as DataFrame), including the area ID, load peak and time point, the calculated load demand peak of each area and its time point are stored in a database to form a load demand peak data set for subsequent analysis, the load demand peak data of each area is extracted from the database to ensure that it contains the peak value and the corresponding timestamp, the load demand peak time point is predicted using a time series prediction model (such as ARIMA, SARIMA or LSTM), the historical load demand data and the corresponding timestamp are used to construct a training data set, the features (such as historical peak value, time features) and the target (i.e., the future peak time point) are set, and the load demand peak data is used. The selected prediction model is used to train the training data, optimize the model parameters, and use the trained model to predict the next load demand peak time point for each area. The prediction results are recorded, and the load demand peak time point and prediction results of each area are stored in the database to form a load demand peak time point data set. The dynamic lighting behavior characteristic data of each device is extracted from the database, including brightness, mode, change frequency and other information. According to the load demand peak and the characteristics of the device, a dynamic lighting brightness adjustment strategy is defined. For example, when the load demand peak is about to come, the light brightness is gradually increased. When the load demand peak occurs, the light is kept at a specific brightness level. For each device, based on the load demand peak time point in its area, the defined brightness adjustment strategy is applied. A control system or dimmer (such as DALI, DMX controller) is used to achieve dynamic brightness adjustment. According to the predicted peak time point, the brightness value of the device is gradually adjusted. The brightness change and timestamp of each device during the adjustment process are recorded to form dynamic lighting brightness adjustment data.

[0155] In this embodiment, the specific steps of step S6 are:

[0156] Step S61: performing real-time progressive fine-tuning on the dynamic lighting brightness adjustment data based on the crowd flow situation prediction data of different areas to generate real-time fine-tuning night scene lighting data;

[0157] Step S62: performing regional linkage response analysis on the real-time fine-tuning night scene lighting data to generate regional linkage response data;

[0158] Step S63: Calculate the response delay of the regional linkage response data to obtain inter-regional response delay data;

[0159] Step S64: All photovoltaic lighting night scene equipment are coordinated and linked to control optimization according to the inter-regional response delay data, and a night scene equipment coordinated optimization strategy is constructed to execute the lighting night scene interconnection control operation.

[0160] In this embodiment, the crowd flow situation prediction data of different areas are extracted from the database, including the expected crowd flow changes in each area in the next period of time. The data should contain a timestamp and the corresponding crowd flow value. The previously generated dynamic lighting brightness adjustment data is extracted from the database. The data should include the current brightness of the device, the adjustment time point, the preset maximum and minimum brightness values, etc. According to the changes in the crowd flow, a fine-tuning strategy is formulated, for example: Incremental adjustment: For areas with increased crowd flow, an increment (such as 10%) is set, and the brightness is gradually increased in each time period. Reduction adjustment: When the crowd flow decreases, a reduction (such as 10%) is set, and the brightness is gradually reduced to save energy. For each area, its crowd flow situation prediction data and The current dynamic lighting brightness adjustment data, compare the current flow of people with the preset thresholds (such as high, medium, and low), use a control system (such as DMX or DALI controller) to update the lighting brightness of each area in real time, and gradually adjust the brightness value of the equipment according to the changes in the flow of people. Use loops and conditional statements in the implementation process to ensure that the brightness adjustment is triggered when specific conditions are met. Record the real-time fine-tuned night scene lighting data, including timestamps, area IDs, and adjusted brightness values ​​to form a new data set. Extract the real-time fine-tuned night scene lighting data from the database to ensure data integrity, especially focusing on timestamps and corresponding brightness values. Use data analysis tools (such as Python's Pandas and NumPy) to respond to regional linkages Analysis will be combined with visualization tools (such as Matplotlib or Seaborn) for data display, analyze the changes in lighting data in different areas, and identify the linkage response relationship between areas. For example, when the brightness of one area is adjusted, check whether the lighting changes in other areas are adjusted accordingly, calculate the intensity and direction of the linkage response, use correlation analysis methods (such as Pearson correlation coefficient) to quantify the linkage effect between areas, generate a regional linkage response data set, including area ID, brightness change amplitude, response time and other information, extract the previously generated regional linkage response data from the database, ensure that it contains timestamps and brightness change information, use time series analysis methods (such as cross-correlation analysis) to calculate the response delay between areas, and use P The correlate function in the SciPy library of Python is used for calculation. A cross-correlation analysis is performed on the linkage response data of each pair of regions to determine the response delay time of one region to the lighting adjustment of another region. The delay value between each pair of regions is recorded to form a delay data set. For example, a threshold is set to determine whether the delay is within an acceptable range. The calculated response delay results are organized into a structured data format, including information such as region ID pairs and delay time. The response delay data between regions are extracted from the database to ensure data integrity. Based on the response delay data, a collaborative linkage control strategy is formulated. For example, for areas with large response delays, the lighting brightness is adjusted in advance to achieve better linkage effects. According to the delay time,Adjust the sending time of lighting control commands in each area to ensure the synchronization of equipment in each area. Use a centralized control system (such as an intelligent lighting control system or IoT platform) to manage all photovoltaic lighting night scene equipment to ensure information sharing and unified control instructions between devices. According to the formulated control strategy, adjust the lighting status of each device in real time to ensure that lighting equipment in different areas work together. For example, use an intelligent controller to send control commands to each device, monitor lighting effects and energy consumption in real time, ensure the effectiveness of collaborative control strategies, and establish a feedback mechanism to record device responses and adjustment results for subsequent optimization.

[0161] In this embodiment, a photovoltaic-based urban cultural tourism lighting night scene interconnection control system is provided, which is used to execute the photovoltaic-based urban cultural tourism lighting night scene interconnection control method as described above, including:

[0162] The equipment spatial distribution module is used to obtain the scenic area crowd monitoring parameters and photovoltaic lighting night scene equipment status data; perform spatial location calculations on all photovoltaic lighting night scene equipment, and perform spatial distribution analysis to obtain multiple equipment area distribution maps;

[0163] The load demand prediction module is used to calculate the regional power load of multiple equipment regional distribution maps based on the status data of photovoltaic lighting night scene equipment, and to predict the power load demand, so as to generate the power load demand prediction data for each area;

[0164] The crowd flow situation prediction module is used to calculate the crowd flow distribution of the scenic area crowd flow monitoring parameters based on the regional distribution maps of multiple devices, and to perform short-term crowd flow situation prediction to generate crowd flow situation prediction data for different areas;

[0165] The lighting behavior module is used to obtain the night scene lighting operation plan; decompose the night scene lighting operation plan into multiple time periods, and analyze the lighting behavior of each device to generate the dynamic lighting behavior characteristics of each device;

[0166] A dynamic brightness adjustment module, used to dynamically adjust the lighting brightness of each device according to the power load demand prediction data of each area, so as to generate dynamic lighting brightness adjustment data;

[0167] The collaborative control module is used to make real-time progressive fine-tuning of dynamic lighting brightness adjustment data based on the crowd flow situation prediction data in different areas, and to perform collaborative linkage control optimization, build a collaborative optimization strategy for night view equipment, and execute lighting night view interconnection control operations.

[0168] The present invention helps to understand the real-time situation in the scenic area by acquiring scenic spot crowd monitoring parameters and equipment status data, and provides basic data for subsequent decision-making. Spatial location positioning and distribution analysis can help achieve a reasonable layout of equipment, optimize lighting effects and energy utilization efficiency, and regional power load calculation and demand forecasting based on equipment status data help to reasonably plan energy supply and ensure the stable operation of the lighting system. Generating power load demand forecast data helps to optimize energy scheduling and improve energy utilization efficiency. Obtaining night scene lighting operation plans and performing lighting behavior analysis helps to optimize lighting plans and improve lighting effects. Dynamic lighting behavior characteristics are analyzed to adjust lighting brightness according to demand to achieve intelligent lighting control. The lighting behavior of the equipment is dynamically adjusted according to the power load demand forecast data, which helps to save energy and reduce emissions and improve lighting effects. Dynamic lighting brightness adjustment data is generated to adjust the lighting brightness in real time according to actual conditions to adapt to different demand scenarios. Real-time progressive fine-tuning and collaborative linkage control optimization improve the flexibility and response speed of the lighting system, ensure the efficient operation of the lighting system, and construct a night scene equipment collaborative optimization strategy to help achieve intelligent management of lighting night scenes and improve the quality and efficiency of urban cultural and tourism lighting night scenes.

[0169] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0170] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for interconnecting and controlling urban cultural and tourism lighting night scenes based on photovoltaic technology, characterized in that: The following steps are involved: Step S1: Obtain scenic area crowd monitoring parameters and photovoltaic lighting night scene equipment status data; perform spatial position positioning calculations on all photovoltaic lighting night scene equipment, and perform spatial distribution analysis to obtain multiple equipment area distribution maps; Step S2: Calculate the regional power load of multiple equipment regional distribution maps based on the photovoltaic lighting night scene equipment status data, and predict the power load demand, so as to generate power load demand prediction data for each area; Step S3: Calculate the crowd flow distribution of the scenic spot crowd flow monitoring parameters based on the regional distribution maps of multiple devices, and perform short-term crowd flow situation prediction to generate crowd flow situation prediction data for different areas; Step S4: Obtaining a night scene lighting operation plan; Decompose the night scene lighting operation plan into multiple time periods, analyze the lighting behavior of each device, and generate dynamic lighting behavior characteristics for each device; Step S5: dynamically adjusting the lighting brightness of each device according to the power load demand prediction data of each area to generate dynamic lighting brightness adjustment data; Step S6: Based on the crowd flow situation prediction data in different areas, the dynamic lighting brightness adjustment data is fine-tuned in real time, and collaborative linkage control optimization is performed to build a collaborative optimization strategy for night scene equipment to execute the lighting night scene interconnection control operation.

2. The method for interconnecting and controlling urban cultural and tourism lighting night scenes based on photovoltaic technology according to claim 1 is characterized in that: The specific steps of step S1 are: Step S11: Acquire scenic spot crowd monitoring parameters based on multi-dimensional sensors, identify all photovoltaic lighting night scene equipment in the urban cultural and tourism scenic spot, and collect photovoltaic lighting night scene equipment status data; Step S12: performing spatial location calculation on all photovoltaic night scene lighting devices to obtain the spatial location coordinates of each device; Step S13: performing spatial distribution analysis on the spatial position coordinates of each device, thereby obtaining device spatial distribution data; Step S14: performing spatial distribution fitting on the device spatial distribution data to construct a device spatial distribution map; Step S15: performing region division processing on the device space distribution map, thereby obtaining a plurality of device region distribution maps.

3. The method for interconnecting and controlling urban cultural and tourism lighting night scenes based on photovoltaic technology according to claim 1 is characterized in that: The specific steps of step S2 are: Step S21: Calculate the time-series power generation of each device on the status data of the photovoltaic lighting night scene device, and extract the time-series power generation parameters of each device; Step S22: performing a time-series variation analysis on the time-series power generation parameters of each device to generate a time-series power generation curve for each device; Step S23: Calculate the power load within a cycle for the time-series power generation curve of each device to generate the power load of each device; Step S24: performing regional power load calculation on multiple device regional distribution maps based on the power load of each device to generate multiple regional power load data; Step S25: performing load trend evolution of multiple regional power load data one by one to generate power load trend characteristics of each region; Step S26: forecasting the power load demand based on the power load trend characteristics of each area, thereby generating power load demand forecast data for each area.

4. The method for interconnecting and controlling urban cultural and tourism lighting night scenes based on photovoltaic technology according to claim 3 is characterized in that: The specific steps of step S26 are: Extracting the power load trend feature of the first area of ​​the power load trend feature; Perform multi-time point feature analysis on the power load trend feature of the first area to obtain the power load trend features at multiple time points; Identify the peak and valley values ​​of the power load trend characteristics at multiple time points to mark the peak and valley time points of the power load; Mining the periodic evolution characteristics of the peak and valley time points of the power load to generate the periodic evolution characteristics of the power load; Conduct deep modeling and learning on the characteristics of the power load cycle evolution to generate the power load cycle evolution law; Based on the evolution law of the power load cycle, the power load demand of the first area is predicted based on the power load trend characteristics, so as to generate the power load demand prediction data of the first area; The power load demand forecasting operation is repeated to generate power load demand forecasting data for each area.

5. The method for interconnecting and controlling urban cultural and tourism lighting night scenes based on photovoltaic technology according to claim 1 is characterized in that: The specific steps of step S3 are: Step S31: Performing a crowd flow fluctuation analysis on the crowd flow monitoring parameters of the scenic spot to generate crowd flow fluctuation data of the scenic spot; Step S32: Based on the regional distribution diagrams of multiple equipment, regional crowd flow fluctuation identification is performed on the scenic area crowd flow fluctuation data to generate crowd flow fluctuation characteristics for each area; Step S33: performing regional crowd flow interaction analysis on the floating characteristics of the crowd flow in each area, so as to obtain the crowd flow interaction logic between different areas; Step S34: Calculate the flow distribution of people based on the floating characteristics of the flow of people in each area to obtain regional flow distribution data; Step S35: Perform short-term crowd flow situation prediction on the regional crowd flow distribution data according to the crowd flow interaction logic between different areas, so as to generate crowd flow situation prediction data for different areas.

6. The method for interconnecting and controlling urban cultural and tourism lighting night scenes based on photovoltaic technology according to claim 1 is characterized in that: The specific steps of step S4 are: Step S41: Obtaining a night scene lighting operation plan; Step S42: Decomposing the night scene lighting operation plan into multiple time periods to obtain lighting operation plans for multiple time periods; Step S43: performing lighting operation behavior characteristic analysis on the lighting operation schemes of multiple time periods to obtain lighting behavior characteristics of different time periods; Step S44: matching the lighting behaviors of multiple device area distribution maps one by one according to the lighting behavior characteristics of different time periods, thereby generating lighting behavior data for each device; Step S45: Perform dynamic lighting behavior analysis on the lighting behavior data of each device to generate dynamic lighting behavior characteristics of each device.

7. The method for interconnecting and controlling urban cultural and tourism lighting night scenes based on photovoltaic technology according to claim 6 is characterized in that: The specific steps of step S43 are: Extracting lighting operation instruction features based on lighting operation plans for multiple time periods, wherein the lighting operation instruction features include equipment lighting brightness, color temperature, lighting duration, and color features; Calculate the average lighting brightness of the equipment lighting brightness to obtain average lighting brightness data; Identify the regional color temperature variation range of color temperature and generate the color temperature variation range of different time periods; Perform device-by-device distribution statistics on the duration of lighting, so as to obtain the distribution data of the duration of lighting of different devices; Performing device dynamic color change evolution on the color feature to generate device dynamic color change features; The lighting operation behavior characteristics are analyzed by the average lighting brightness data, the color temperature variation range in different time periods, the lighting time distribution data of different devices and the dynamic color change characteristics of the devices to obtain the lighting operation behavior characteristics in different time periods.

8. The method for interconnecting and controlling urban cultural and tourism lighting night scenes based on photovoltaic technology according to claim 1 is characterized in that: The specific steps of step S5 are: Step S51: Calculate the load demand peak value for the power load demand forecast data of each area to obtain the load demand peak value; Step S52: Predict the peak time of the load demand peak and generate the load demand peak time point for each area; Step S53: dynamically adjust the lighting brightness of each device based on the load demand peak time point of each area to generate dynamic lighting brightness adjustment data.

9. The method for interconnecting and controlling urban cultural and tourism lighting night scenes based on photovoltaic technology according to claim 1 is characterized in that: The specific steps of step S6 are: Step S61: performing real-time progressive fine-tuning on the dynamic lighting brightness adjustment data based on the crowd flow situation prediction data of different areas to generate real-time fine-tuning night scene lighting data; Step S62: performing regional linkage response analysis on the real-time fine-tuning night scene lighting data to generate regional linkage response data; Step S63: Calculate the response delay of the regional linkage response data to obtain inter-regional response delay data; Step S64: All photovoltaic lighting night scene equipment are coordinated and linked to control optimization according to the inter-regional response delay data, and a night scene equipment coordinated optimization strategy is constructed to execute the lighting night scene interconnection control operation.

10. An urban cultural tourism lighting night scene interconnection control system based on photovoltaic technology, characterized in that: The method for executing the photovoltaic technology-based urban cultural tourism lighting night scene interconnection control method as claimed in claim 1 comprises: The equipment spatial distribution module is used to obtain the scenic area crowd monitoring parameters and photovoltaic lighting night scene equipment status data; perform spatial location calculations on all photovoltaic lighting night scene equipment, and perform spatial distribution analysis to obtain multiple equipment area distribution maps; The load demand prediction module is used to calculate the regional power load of multiple equipment regional distribution maps based on the status data of photovoltaic lighting night scene equipment, and to predict the power load demand, so as to generate the power load demand prediction data for each area; The crowd flow situation prediction module is used to calculate the crowd flow distribution of the scenic area crowd flow monitoring parameters based on the regional distribution maps of multiple devices, and to perform short-term crowd flow situation prediction to generate crowd flow situation prediction data for different areas; The lighting behavior module is used to obtain the night scene lighting operation plan; decompose the night scene lighting operation plan into multiple time periods, and analyze the lighting behavior of each device to generate the dynamic lighting behavior characteristics of each device; A dynamic brightness adjustment module, used to dynamically adjust the lighting brightness of each device according to the power load demand prediction data of each area, so as to generate dynamic lighting brightness adjustment data; The collaborative control module is used to make real-time progressive fine-tuning of dynamic lighting brightness adjustment data based on the crowd flow situation prediction data in different areas, and to perform collaborative linkage control optimization, build a collaborative optimization strategy for night view equipment, and execute lighting night view interconnection control operations.

Images