A method and system for intelligent operation and maintenance management of smart street light groups in cities based on big data analysis

Abstract

This invention discloses an intelligent operation and maintenance management method and system for urban smart street light groups based on big data analysis. The method includes the following steps: acquiring and classifying smart street lights on various roads into several street light groups based on urban functional zoning information; acquiring information from each street light group to construct a decision model and generate preliminary operation and maintenance strategies for each street light group; obtaining traffic flow prediction information for the roads where each street light group is located based on historical traffic flow information; obtaining weather prediction information for the roads where each street light group is located based on historical meteorological information; inputting the traffic flow prediction information and weather prediction information into the decision model, and optimizing the preliminary operation and maintenance strategies using a multi-objective optimization algorithm with preset values ​​to obtain a target operation and maintenance strategy; and controlling the smart street light groups according to real-time traffic data and meteorological information to achieve more precise and dynamic management of urban smart street light groups, with a dynamic and adaptive effect of precise brightness control.

Description

Technical Field

[0001] This invention relates to the field of smart street light technology, specifically to a method and system for intelligent operation and maintenance management of urban smart street light groups based on big data analysis. Background Technology

[0002] Smart streetlights are modern lighting facilities that integrate advanced information technology, Internet of Things (IoT) technology, sensors, and artificial intelligence. Unlike traditional streetlights, smart streetlights not only provide basic lighting functions but also enable automatic adjustment, remote monitoring, environmental sensing, data collection, and integration with other urban infrastructure systems. Smart streetlights are an important component of smart city construction, aiming to improve urban lighting efficiency, reduce energy consumption, enhance public safety, and provide greater convenience for urban management and residents.

[0003] Modern smart streetlights can automatically adjust their brightness to adapt to changes in the surrounding environment. For example, in areas with no traffic at night, streetlights can reduce their brightness to save energy; while in busy traffic areas, the brightness of the streetlights will automatically increase to ensure road safety.

[0004] Although smart streetlights can automatically adjust their brightness, they often rely on fixed control strategies, such as triggering mechanisms based on time or ambient light, and fail to make full use of real-time traffic data and weather data to dynamically adjust the lighting intensity and on / off status of the streetlights.

[0005] The aforementioned management approach, lacking dynamic adaptability, may lead to:

[0006] During peak traffic hours, if streetlights fail to adjust their illumination based on real-time traffic data, the visibility of drivers and pedestrians will be severely affected. This is especially true in adverse weather conditions such as rain, snow, and fog, where visibility is already reduced, and insufficient lighting may further exacerbate traffic safety risks and increase the probability of traffic accidents. Simultaneously, this lack of dynamic adaptability in management also leads to energy waste during off-peak hours. When traffic is sparse, streetlights may remain brightly lit, consuming large amounts of unnecessary energy and potentially causing light pollution, impacting the quality of life for nearby residents. Therefore, there is an urgent need for an intelligent operation and maintenance management method and system for smart streetlight clusters based on big data analysis to achieve precise brightness control of smart streetlights. Summary of the Invention

[0007] To address the problem of insufficient brightness control of smart streetlights mentioned in the background section, this invention provides an intelligent operation and maintenance management method and system for urban smart streetlight groups based on big data analysis.

[0008] The above-mentioned objective of this application is achieved through the following technical solution:

[0009] A method for intelligent operation and maintenance management of smart street light clusters in cities based on big data analysis includes the following steps:

[0010] The system acquires urban functional zoning information and classifies smart streetlights on each road into several streetlight groups based on this information. It also acquires historical traffic flow information and historical weather information for each streetlight group and the associated roads.

[0011] The system acquires status information and public feedback information for each street light group. Based on urban functional zoning information, historical traffic flow information, historical meteorological information, status information, and public feedback information, a decision model is constructed. The system then uses the decision model to generate preliminary operation and maintenance strategies for each street light group.

[0012] Historical traffic flow information is input into the trained first prediction model to obtain the traffic flow prediction information corresponding to each street light group on the road output by the first prediction model.

[0013] Historical meteorological information is input into the trained second prediction model to obtain the meteorological prediction information corresponding to the roads where each street light group is located, output by the second prediction model.

[0014] Traffic flow forecast information and weather forecast information are input into the decision model, and the preliminary operation and maintenance strategy is optimized by a pre-set multi-objective optimization algorithm to obtain the target operation and maintenance strategy.

[0015] By adopting the above scheme, urban functional zoning information is obtained, and based on this information, smart streetlights on various roads are grouped into several streetlight clusters. Historical traffic flow and weather information of the roads associated with each streetlight cluster are obtained, along with status information and public feedback information for each streetlight cluster. A decision model is constructed based on the urban functional zoning information, historical traffic flow information, historical weather information, status information, and public feedback information. Preliminary operation and maintenance strategies for each streetlight cluster are generated using the decision model. Historical traffic flow information is input into a trained first prediction model to obtain traffic flow prediction information for the roads where each streetlight cluster is located. Historical weather information is input into a trained second prediction model to obtain weather prediction information for the roads where each streetlight cluster is located, including weather conditions such as rain, fog, and clear skies, which affect visibility. Weather conditions that may affect brightness and light transmittance are considered. Traffic flow forecasts and meteorological forecasts are input into a decision model, which then uses a pre-set multi-objective optimization algorithm to optimize the initial operation and maintenance strategy based on these forecasts, resulting in a target operation and maintenance strategy. This application generates an initial operation and maintenance strategy by combining urban functional zoning information, historical traffic flow information, historical meteorological information, status information, and public feedback information. The corresponding forecast information is obtained using a prediction model, and the forecast information is integrated into the initial operation and maintenance strategy through a multi-objective optimization algorithm to obtain the target operation and maintenance strategy. This enables more accurate and dynamic management of smart street light groups. Based on real-time traffic data and meteorological information, the smart street light groups are dynamically and adaptively adjusted, thereby ensuring precise brightness control and improving the energy efficiency and adaptability of the smart street light groups.

[0016] In a preferred embodiment, this application can be further configured as follows: the steps of obtaining urban functional zoning information, classifying smart streetlights on each road into several streetlight groups based on the urban functional zoning information, and obtaining historical traffic flow information and historical meteorological information of the roads corresponding to each streetlight group, include the following steps:

[0017] The geographical location information of smart streetlights on each road is obtained, and the smart streetlights are divided based on K-means clustering and geographical location information to obtain several preliminary streetlight groups.

[0018] Based on urban functional zoning information, the preliminary street light groups were classified into several groups.

[0019] By adopting the above technical solution, the geographical location information of smart streetlights on each road is obtained, and the smart streetlights are divided based on K-means clustering and geographical location information to obtain several preliminary streetlight groups. Based on urban functional zoning information such as commercial areas, industrial areas and residential areas, the preliminary streetlight groups are further optimized by group classification to obtain several streetlight groups. By initially dividing based on geographical location information and optimizing group classification based on urban functional zoning information, the division of each streetlight group is refined, improving the accuracy and rapid response of controlling smart streetlights.

[0020] In a preferred embodiment, this application can be further configured as follows: the steps of obtaining status information and public feedback information of each street light group, constructing a decision model based on urban functional zoning information, historical traffic flow information, historical meteorological information, status information, and public feedback information, and generating a preliminary operation and maintenance strategy based on each street light group through the decision model include the following steps:

[0021] Obtain public feedback information and match the corresponding street light groups based on the preset identifiers associated with the public feedback information;

[0022] By using pre-set natural language processing rules, sentiment analysis and semantic understanding are performed on public feedback information to extract feedback features;

[0023] A decision-making model is constructed based on urban functional zoning information, historical traffic flow information, historical meteorological information, status information, and feedback characteristics.

[0024] By adopting the above technical solution, public feedback information is obtained, and corresponding street light groups are matched through their associated preset identifiers. Pre-set natural language processing technology is used to conduct in-depth sentiment analysis and semantic understanding of the public feedback information to identify the public's specific opinions on the smart street light groups and capture the emotional tendencies in the public feedback. Then, key feedback features are extracted, and a decision model is constructed based on urban functional zoning information, historical traffic flow information, historical meteorological information, status information, and feedback features. This completes the information association between each input information and the corresponding street light group, enabling the constructed decision model to accurately generate corresponding decisions for each street light group.

[0025] In a preferred embodiment, this application can be further configured as follows: the step of inputting traffic flow prediction information and weather prediction information into a decision model, and optimizing the preliminary operation and maintenance strategy through a pre-set multi-objective optimization algorithm to obtain the target operation and maintenance strategy includes the following steps:

[0026] Based on urban functional zoning information and historical traffic flow information, a first threshold and a second threshold are set in the decision-making model for traffic flow prediction information;

[0027] The decision model divides each street light group into groups based on the first and second thresholds and the corresponding traffic flow prediction information, and generates the first basic control strategy for each street light group based on the group division results.

[0028] The input meteorological forecast information is extracted into meteorological forecast features through the decision model, and a second basic control strategy is generated for each street light group based on the meteorological forecast features.

[0029] The first basic control strategy and the second basic control strategy are integrated into the preliminary operation and maintenance strategy by the decision model based on the pre-set multi-objective optimization algorithm to obtain the target operation and maintenance strategy.

[0030] By adopting the above technical solution, a first threshold and a second threshold for traffic flow prediction information are set in the decision model based on urban functional zoning information and historical traffic flow information. The decision model then groups each street light group according to the corresponding traffic flow prediction information based on the first and second thresholds, and generates a first basic control strategy for each street light group based on the grouping results. The decision model extracts the input meteorological prediction information into meteorological prediction features, and generates a second basic control strategy for each street light group based on the meteorological prediction features. The decision model integrates the first and second basic control strategies into the preliminary operation and maintenance strategy based on a pre-set multi-objective optimization algorithm to obtain the target operation and maintenance strategy. The preliminary operation and maintenance strategy is integrated and optimized based on the traffic flow prediction information and meteorological prediction information associated with each street light group to ensure that the formulated operation and maintenance strategy not only conforms to reality, but also anticipates and adapts to future changes in demand, thereby achieving effective optimization of the preliminary operation and maintenance strategy and making it more suitable for lighting management needs.

[0031] In a preferred embodiment, this application can be further configured as follows: the first basic control strategy includes a real-time light contribution control strategy, a vehicle speed prediction control strategy, and a real-time traffic flow information weight control strategy. The step of grouping the traffic flow prediction information corresponding to each street light group based on a first threshold and a second threshold using a decision model, and generating a preset first basic control strategy for each street light group based on the grouping results, includes the following steps:

[0032] Traffic flow prediction information that is greater than the first threshold is set as the real-time control group, traffic flow prediction information that is less than the second threshold is set as the vehicle speed control group, and traffic flow prediction information that is between the first threshold and the second threshold is set as the weight control group.

[0033] A real-time lighting contribution control strategy is generated for the street light groups associated with the real-time control group;

[0034] A vehicle speed prediction and control strategy is generated for the street light group associated with the vehicle speed control group.

[0035] A weighted control strategy is generated for real-time traffic flow information of the street light groups associated with the weighted control group.

[0036] By adopting the above technical solution, traffic flow prediction information exceeding a first threshold is set as a real-time control group, and a real-time lighting contribution control strategy is generated for the street light groups associated with the real-time control group; traffic flow prediction information below a second threshold is set as a vehicle speed control group, and a vehicle speed prediction control strategy is generated for the street light groups associated with the vehicle speed control group; traffic flow prediction information between the first and second thresholds is set as a weighted control group, and a real-time traffic flow information weighted control strategy is generated for the street light groups associated with the weighted control group; based on the differences in traffic flow prediction information, corresponding control strategies are customized for each associated road, thereby achieving refined differentiation and adaptive control for various scenarios, ensuring that appropriate control strategies can be adopted in different situations.

[0037] In a preferred embodiment, this application can be further configured as follows: the step of generating a real-time lighting contribution control strategy for the smart street light group associated with the real-time control group includes the following steps:

[0038] The decision-making model sets a rated brightness contribution value based on urban functional zoning information, status information, and public feedback information;

[0039] The total brightness value of the associated road is obtained in real time by a photosensitive sensor with an interval setting. The total brightness value is the sum of the current vehicle headlight brightness contribution value and the current street light brightness contribution value.

[0040] Calculate the difference between the total brightness value and the rated brightness contribution value, the rate of change of the difference, and the cumulative value of the difference within a preset time range;

[0041] The PID control algorithm adjusts the current street light brightness contribution value based on the calculated difference, the rate of change of the difference, and the cumulative value of the difference.

[0042] By adopting the above technical solution, the decision-making model sets the rated brightness contribution value based on urban functional zoning information, status information, and public feedback information. Based on the photosensitive sensors set at intervals, the total brightness value of the associated roads is obtained in real time. This total brightness value is the sum of the current vehicle light brightness contribution value and the current street light brightness contribution value. The difference between the total brightness value and the rated brightness contribution value, the rate of change of the difference, and the cumulative value of the difference within a preset time range are calculated. The PID control algorithm adjusts the current street light brightness contribution value according to the calculated difference, the rate of change of the difference, and the cumulative value of the difference. Based on the real-time monitoring results of the total brightness value of the roads, the current street light brightness contribution value is dynamically adjusted, thereby realizing the precise implementation of the lighting contribution control strategy for the street light group within the real-time control group.

[0043] In a preferred embodiment, this application can be further configured such that: the decision model includes an RNN model, and the step of generating a vehicle speed prediction and control strategy for the smart street light group associated with the vehicle speed control group includes the following steps:

[0044] The decision-making model sets a base brightness value based on urban functional zoning information, historical traffic flow information, and status information;

[0045] Traffic sensors set at intervals acquire real-time vehicle traffic information on their associated roads. The vehicle traffic information includes vehicle type information, real-time traffic flow, vehicle spacing, and traffic speed information.

[0046] The RNN model takes vehicle type information, real-time traffic flow, vehicle spacing and traffic speed information as inputs and outputs the predicted vehicle speed.

[0047] Calculate the safe distance based on traffic speed information, predicted vehicle speed, and vehicle type information;

[0048] The base brightness value is dynamically adjusted based on the safe distance.

[0049] By adopting the above technical solution, the decision-making model sets a basic brightness value based on urban functional zoning information, historical traffic flow information, and status information. Traffic sensors set at intervals acquire real-time vehicle traffic information on their associated roads. This vehicle traffic information includes vehicle type information, real-time traffic flow, vehicle spacing, and traffic speed information. Using an RNN model with vehicle type information, real-time traffic flow, vehicle spacing, and traffic speed information as input, the model outputs a predicted vehicle speed. Based on the traffic speed information, predicted vehicle speed, and vehicle type information, a safe distance is calculated. The basic brightness value is dynamically adjusted based on the calculated safe distance. By using vehicle traffic information to calculate the required safe distance and dynamically adjusting the basic brightness value accordingly, the basic brightness value of the streetlights associated with the speed control group is effectively controlled based on vehicle speed prediction.

[0050] In a preferred embodiment, this application can be further configured as follows: the step of generating a real-time traffic flow information weight control strategy for the smart street light group associated with the weight control group includes the following steps:

[0051] Traffic sensors set at intervals acquire real-time traffic flow on their associated roads.

[0052] The decision-making model sets a weighting hierarchy between real-time traffic flow information and street light brightness based on urban functional zoning information, historical traffic flow information, status information, and public feedback information.

[0053] The acquired real-time traffic flow is matched with preset weight ratio levels;

[0054] The brightness of the streetlights in the streetlight group is adjusted according to the weight ratio obtained from the matching.

[0055] By adopting the above technical solution, traffic sensors set at intervals acquire real-time traffic flow on their associated roads. The decision model sets a weight ratio level between real-time traffic flow information and street light brightness based on urban functional zoning information, historical traffic flow information, status information, and public feedback information. The acquired real-time traffic flow is matched with the preset weight ratio level, and the brightness of the street lights in the street light group is adjusted according to the matched weight ratio level. By matching real-time traffic flow with the preset weight ratio level and adjusting the brightness setting of the street light group according to the obtained weight ratio, dynamic weight control based on real-time traffic flow information is customized for the street light group under the weight control group, improving the accuracy and efficiency of the brightness control of the smart street light group.

[0056] The second objective of this invention is achieved through the following technical solution:

[0057] A smart operation and maintenance management system for urban smart street light clusters based on big data analytics includes:

[0058] The group classification module obtains urban functional zoning information and classifies the smart streetlights on each road into several streetlight groups based on the urban functional zoning information. It also obtains historical traffic flow information and historical weather information of the roads associated with each streetlight group.

[0059] The strategy generation module obtains the status information of each street light group and public feedback information, builds a decision model based on urban functional zoning information, historical traffic flow information, historical meteorological information, status information and public feedback information, and generates preliminary operation and maintenance strategies based on each street light group through the decision model.

[0060] The traffic flow prediction module inputs historical traffic flow information into the trained first prediction model to obtain the traffic flow prediction information corresponding to each street light group on the road output by the first prediction model.

[0061] The weather forecast module inputs historical weather information into the trained second forecast model to obtain the weather forecast information corresponding to each street light group on the road output by the second forecast model.

[0062] The strategy optimization module inputs traffic flow forecast information and weather forecast information into the decision model, and optimizes the initial operation and maintenance strategy through a pre-set multi-objective optimization algorithm to obtain the target operation and maintenance strategy.

[0063] By adopting the above technical solution, the group classification module is used to obtain urban functional zoning information, and classifies the smart streetlights on each road into several streetlight groups based on the urban functional zoning information, and obtains historical traffic flow information and historical meteorological information of the roads associated with each streetlight group; the strategy generation module is used to obtain the status information and public feedback information of each streetlight group, and constructs a decision model based on urban functional zoning information, historical traffic flow information, historical meteorological information, status information and public feedback information, and generates preliminary operation and maintenance strategies based on each streetlight group through the decision model; the traffic flow prediction module is used to input historical traffic flow information into the trained first prediction model to obtain the traffic flow prediction information corresponding to the roads where each streetlight group is located, output by the first prediction model; the meteorological prediction module is used to input historical meteorological information into the trained second prediction model to obtain the meteorological prediction information corresponding to the roads where each streetlight group is located, output by the second prediction model; the strategy optimization module is used to input traffic flow prediction information and meteorological prediction information into the decision model, and optimizes the preliminary operation and maintenance strategy through a pre-set multi-objective optimization algorithm to obtain the target operation and maintenance strategy.

[0064] In summary, the intelligent operation and maintenance management method and system for urban smart street light groups based on big data analysis proposed in this application includes at least one of the following beneficial technical effects:

[0065] 1. This application classifies smart streetlights on various roads into several streetlight groups based on urban functional zoning information. A decision model is constructed based on urban functional zoning information, historical traffic flow information, historical meteorological information, status information, and public feedback information. The decision model generates preliminary operation and maintenance strategies based on each streetlight group. By managing streetlight groups by group, customized preliminary operation and maintenance strategies can be generated for streetlight groups with different functional areas and different needs. Attached Figure Description

[0066] Figure 1 This is a flowchart of an embodiment of an intelligent operation and maintenance management method for urban smart street light groups based on big data analysis according to this application;

[0067] Figure 2 This is a flowchart illustrating step S20 in an embodiment of the intelligent operation and maintenance management method for smart street light groups based on big data analysis in this application.

[0068] Figure 3 This is a flowchart illustrating step S50 in an embodiment of the intelligent operation and maintenance management method for smart street light groups based on big data analysis in this application.

[0069] Figure 4This is a flowchart illustrating step S52 in an embodiment of the intelligent operation and maintenance management method for smart street light groups based on big data analysis in this application.

[0070] Figure 5 This is a flowchart illustrating step S522 in an embodiment of the intelligent operation and maintenance management method for smart street light groups based on big data analysis in this application. Detailed Implementation

[0071] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0072] In one embodiment, such as Figure 1 As shown, this application discloses an intelligent operation and maintenance management method for urban smart street light groups based on big data analysis, which specifically includes the following steps:

[0073] S10: Obtain urban functional zoning information, and classify the smart streetlights of each road into several streetlight groups based on the urban functional zoning information, and obtain historical traffic flow information and historical weather information of the roads associated with each streetlight group.

[0074] In this embodiment, the smart street light is a street light system that integrates multiple technologies such as intelligent sensing, intelligent control, and network communication. The urban functional zoning information is relevant information based on the different functions of different areas within the city, such as planned commercial areas, industrial areas, and residential areas. The group classification is the classification of smart street lights according to their corresponding geographical location information and urban functional zoning information. The historical traffic flow information is the record information of vehicle traffic conditions on the associated roads over a period of time. The historical meteorological information is the record information of weather conditions on the associated roads over a period of time.

[0075] Specifically, the system obtains urban functional zoning information and classifies smart streetlights into groups based on their corresponding geographical location information and urban functional zoning information, resulting in several streetlight groups. It also obtains records of vehicle traffic and weather conditions on the roads associated with each streetlight group over a period of time.

[0076] S20: Obtain status information and public feedback information for each street light group; construct a decision model based on urban functional zoning information, historical traffic flow information, historical meteorological information, status information and public feedback information; and generate preliminary operation and maintenance strategies based on each street light group through the decision model.

[0077] In this embodiment, the status information refers to data and parameters related to the operation of the street light group, including switch status, status information, and light output intensity. The public feedback information refers to the public's evaluation, complaints, and suggestions regarding a specific street light group. The decision model is a mathematical model based on big data analysis and machine learning technology, used to integrate and process multiple data sources such as urban functional zoning information, historical traffic flow information, historical meteorological information, street light group status information, and public feedback information to generate a preliminary operation and maintenance strategy for the street light group. The preliminary operation and maintenance strategy is a preliminary operation and maintenance management plan for the street light group formulated by the decision model based on the input information.

[0078] Specifically, the system acquires operational data and parameters for each street light group, as well as public evaluations, complaints, and suggestions regarding specific street light groups. Using this information as input, it constructs a decision-making model that can systematically analyze and evaluate the potential impact of various information on the operation and maintenance strategies of street light groups. Based on this decision-making model, it formulates preliminary operation and maintenance strategies for each street light group.

[0079] S30: Input historical traffic flow information into the trained first prediction model to obtain the traffic flow prediction information corresponding to each street light group on the road output by the first prediction model;

[0080] In this embodiment, the first prediction model is a mathematical model that uses historical information to identify potential patterns and trends, and the traffic flow prediction information is the predicted vehicle traffic situation of the associated roads in the future.

[0081] Specifically, historical traffic flow information is input into the trained first prediction model to obtain the traffic flow prediction information corresponding to the roads where each street light group is located, as output by the first prediction model.

[0082] S40: Input historical meteorological information into the trained second prediction model to obtain the meteorological prediction information corresponding to the roads where each street light group is located, output by the second prediction model;

[0083] In this embodiment, the second prediction model is a mathematical model that uses historical information to identify potential patterns and trends, and the meteorological prediction information is the predicted meteorological changes of the associated roads in the future.

[0084] Specifically, historical meteorological information is input into the trained second prediction model to obtain the meteorological prediction information corresponding to the roads where each street light cluster is located, as output by the second prediction model.

[0085] S50: Input traffic flow forecast information and weather forecast information into the decision model, and optimize the preliminary operation and maintenance strategy through a pre-set multi-objective optimization algorithm to obtain the target operation and maintenance strategy;

[0086] In this embodiment, the multi-objective optimization algorithm is an algorithm that finds a set of optimal target operation and maintenance strategies by repeatedly generating new candidate solutions in the search space and evaluating and updating the solution set according to the requirements of multiple information markers. The target operation and maintenance strategy is the control strategy for each road street light group obtained after optimizing the preliminary operation and maintenance strategy by the multi-objective optimization algorithm.

[0087] Specifically, traffic flow forecast information and weather forecast information are input into the decision-making model. Based on the traffic flow forecast information and weather forecast information, the decision-making model optimizes the initial operation and maintenance strategy using a pre-set multi-objective optimization algorithm to obtain the target operation and maintenance strategy. This ensures precise control of brightness and improves the energy efficiency and adaptability of the smart street light group.

[0088] In one embodiment, step S10 includes the following steps:

[0089] S11: Obtain the geographical location information of the smart streetlights on each road, and divide the smart streetlights based on K-means clustering and geographical location information to obtain several preliminary streetlight groups.

[0090] S12: Based on urban functional zoning information, the preliminary street light groups are classified into several groups.

[0091] In this embodiment, the geographic location information refers to the specific geographic location data of the smart streetlights, including their latitude and longitude, street, region, etc. K-means clustering is an algorithm that clusters each smart streetlight based on its geographic location information to obtain multiple preliminary streetlight groups.

[0092] Specifically, the geographical location information of smart streetlights on each road is obtained, and the smart streetlights are divided based on K-means clustering and corresponding geographical location information such as latitude, longitude, street, and region to obtain several preliminary streetlight groups. Based on urban functional zoning information, the preliminary streetlight groups are further classified into several streetlight clusters, thereby ensuring that the smart streetlights contained in each streetlight cluster can be controlled based on the cluster, thus improving the management efficiency of smart streetlights.

[0093] In one embodiment, such as Figure 2 As shown, step S20 includes:

[0094] S21: Obtain public feedback information and match the corresponding street light group based on the preset identifier associated with the public feedback information;

[0095] S22: Perform sentiment analysis and semantic understanding on public feedback information through pre-set natural language processing rules, thereby extracting feedback features;

[0096] S23: Construct a decision-making model based on urban functional zoning information, historical traffic flow information, historical meteorological information, status information, and feedback characteristics;

[0097] In this embodiment, the preset identifier is a pre-defined identifier used to uniquely identify and associate the corresponding street light group; the natural language processing rules are a series of formalized rules, methods and techniques for extracting information from text, analyzing syntax and semantics, and processing and understanding human language; sentiment analysis is for identifying and extracting subjective information in text and analyzing the sentiment tendency of text; semantic understanding is for the computer to understand and interpret the meaning and connotation of words, phrases, sentences and paragraphs in natural language text; and feedback features include feature information such as lighting intensity, street light status, and the geographical location of the street light.

[0098] Specifically, the system acquires public feedback information and matches the corresponding street light groups based on preset identifiers associated with the public feedback information. It then performs sentiment analysis and semantic understanding on the public feedback information based on preset natural language processing rules to extract feedback features. Based on urban functional zoning information, historical traffic flow information, historical meteorological information, status information, and feedback features, the system constructs a decision model. By constructing a decision model with relevant information of each corresponding street light group, the system generates corresponding preliminary operation and maintenance strategies for each street light group.

[0099] In one embodiment, such as Figure 3 As shown, step S50 includes:

[0100] S51: Based on urban functional zoning information and historical traffic flow information, set a first threshold and a second threshold for traffic flow prediction information in the decision-making model;

[0101] S52: Based on the first and second thresholds, the decision model divides each street light group into groups according to the corresponding traffic flow prediction information, and generates the first basic control strategy for each street light group based on the group division results.

[0102] S53: The input meteorological forecast information is extracted into meteorological forecast features through the decision model, and the second basic control strategy corresponding to each street light group is generated based on the meteorological forecast features.

[0103] S54: The first basic control strategy and the second basic control strategy are integrated into the preliminary operation and maintenance strategy by the decision model based on the pre-set multi-objective optimization algorithm to obtain the target operation and maintenance strategy;

[0104] In this embodiment, the first threshold and the second threshold are critical values ​​set in the decision model for grouping streetlights based on traffic flow prediction information. The first basic control strategy is a preliminary streetlight control strategy generated based on traffic flow prediction information and grouping results, including but not limited to adjusting parameters such as streetlight brightness and switching time to adapt to lighting needs under different traffic flow conditions. The second basic control strategy is a preliminary streetlight control strategy generated based on meteorological prediction characteristics, including but not limited to adjusting streetlight brightness, switching time, or enabling special lighting modes according to weather changes to adapt to lighting needs under different weather conditions.

[0105] Specifically, based on urban functional zoning information and historical traffic flow information, a first threshold and a second threshold for traffic flow prediction information are set in the decision model. The decision model then groups each street light group according to the corresponding traffic flow prediction information based on the first and second thresholds, and generates a first basic control strategy for each street light group based on the grouping results. The decision model extracts the input meteorological prediction information into meteorological prediction features, and generates a second basic control strategy for each street light group based on the meteorological prediction features. Finally, the decision model integrates the first and second basic control strategies into the preliminary operation and maintenance strategy based on a pre-set multi-objective optimization algorithm to obtain the target operation and maintenance strategy. This completes the target operation and maintenance strategy of using different optimization methods for roads with different traffic flow prediction information.

[0106] In one embodiment, the first basic control strategy includes a real-time light contribution control strategy, a vehicle speed prediction control strategy, and a real-time traffic flow information weight control strategy, such as... Figure 4 As shown, step S52 includes:

[0107] S521: Traffic flow prediction information that is greater than the first threshold is set as the real-time control group, traffic flow prediction information that is less than the second threshold is set as the vehicle speed control group, and traffic flow prediction information that is between the first threshold and the second threshold is set as the weight control group.

[0108] S522: Generate a real-time lighting contribution control strategy for the street light group associated with the real-time control group;

[0109] S523: Generate vehicle speed prediction and control strategies for street light groups associated with the vehicle speed control group.

[0110] S524: Generate real-time traffic flow information weight control strategy for the street light group associated with the weight control group;

[0111] In this embodiment, the real-time light contribution control strategy is an operation and maintenance strategy that controls the street light group based on the real-time total brightness value of the road corresponding to the street light group; the vehicle speed prediction control strategy is an operation and maintenance strategy that controls the street light group based on the predicted vehicle speed of the road corresponding to the street light group; and the real-time traffic flow information weight control strategy is an operation and maintenance strategy that controls the street light group based on the weight ratio level corresponding to the real-time traffic flow information.

[0112] Specifically, traffic flow prediction information exceeding a first threshold is set as a real-time control group, traffic flow prediction information below a second threshold is set as a speed control group, and traffic flow prediction information between the first and second thresholds is set as a weighted control group. Real-time lighting contribution control strategies are generated for street light groups associated with the real-time control group, speed prediction control strategies are generated for street light groups associated with the speed control group, and real-time traffic flow information weighted control strategies are generated for street light groups associated with the weighted control group. This enables precise control of street light groups under different traffic flow conditions through different operation and maintenance strategies, achieving precise control through grouping.

[0113] Furthermore, when the obtained meteorological forecast information contains abnormal features, indicating that severe weather that will seriously affect vehicle operation will occur, an emergency control strategy will be adopted: the decision model extracts features from the meteorological forecast information to obtain meteorological forecast features, and extracts abnormal features from the meteorological forecast features based on preset feature extraction principles; if the extraction result is not zero, the extracted abnormal features are matched with the street light group associated with the corresponding area through preset identifiers; and the street light group is controlled based on preset emergency operation and maintenance strategies.

[0114] The feature extraction principle involves extracting anomalous features from multiple dimensions of meteorological data (such as time, space, and meteorological variables) that help identify potential meteorological anomalies or trends. Anomalous features are meteorological elements that deviate from the normal range, including temperature anomalies, precipitation anomalies, wind speed anomalies, and air pressure anomalies. The emergency operation and maintenance strategy is a strategy for quickly and effectively responding to and resolving problems when anomalies occur. Specifically, it involves guiding traffic on roads associated with anomalous features by controlling street light groups, and specifically by dynamically adjusting the brightness, flashing, or color change of street lights to guide traffic.

[0115] In one embodiment, such as Figure 5 As shown, step S522 includes:

[0116] S5221: The decision-making model sets the rated brightness contribution value based on urban functional zoning information, status information, and public feedback information;

[0117] S5222: A photosensitive sensor with an interval setting acquires the total brightness value of its associated road in real time, wherein the total brightness value is the sum of the current vehicle headlight brightness contribution value and the current street light brightness contribution value;

[0118] S5223: Calculate the difference between the total brightness value and the rated brightness contribution value, the rate of change of the difference, and the cumulative value of the difference within a preset time range;

[0119] S5224: The current street light brightness contribution value is adjusted based on the calculated difference, the rate of change of the difference, and the cumulative value of the difference using a PID control algorithm;

[0120] In this embodiment, the rated brightness contribution value is the brightness value that each street light group should provide, as set by the decision model based on urban functional zoning information, status information, and public feedback information. The rated brightness contribution value represents the lighting level that the smart street light group should achieve in different areas, at different times, or under different conditions. The current vehicle light brightness contribution value is the contribution of the vehicle lights of vehicles traveling on the corresponding road to the lighting effect and road lighting distribution. The current street light brightness contribution value is the contribution of the street light group on the corresponding road to the lighting effect and road lighting distribution. The PID control algorithm is a feedback control algorithm for adjusting the output.

[0121] Specifically, the decision-making model sets a rated brightness contribution value based on urban functional zoning information, status information, and public feedback information. Based on photosensitive sensors set at intervals, it acquires the total brightness value of its associated roads in real time. The total brightness value is the sum of the current vehicle light brightness contribution value and the current street light brightness contribution value. Then, it calculates the difference between the total brightness value and the rated brightness contribution value, the rate of change of the difference, and the cumulative value of the difference within a preset time range. The PID control algorithm adjusts the current street light brightness contribution value according to the calculated difference, the rate of change of the difference, and the cumulative value of the difference, thereby completing the real-time light contribution control strategy for the smart street light group associated with the control group.

[0122] In one embodiment, step S523 includes:

[0123] S5231: The decision-making model sets a basic brightness value based on urban functional zoning information, historical traffic flow information, and status information;

[0124] S5232: Traffic sensors with interval settings acquire real-time vehicle traffic information on their associated roads, including vehicle type information, real-time traffic flow, vehicle spacing, and traffic speed information;

[0125] S5233: Using an RNN model with vehicle type information, real-time traffic flow, vehicle spacing and traffic speed information as input, the output is a predicted vehicle speed.

[0126] S5234: Calculate the safe distance based on traffic speed information, predicted vehicle speed, and vehicle type information;

[0127] S5235: Dynamically adjusts the base brightness value based on the safe distance.

[0128] In this embodiment, the base brightness value is the base lighting brightness reference value initially set by the decision model. The traffic sensor is a device used to monitor traffic conditions on the road in real time. It can be installed on or near the road to capture vehicle traffic information, including vehicle type, real-time traffic flow, vehicle spacing, and traffic speed. The vehicle type information is the type of vehicle traveling on the road, such as cars, trucks, buses, motorcycles, etc. Different types of vehicles may have different requirements for road lighting. For example, large trucks may need higher lighting brightness to ensure clear visibility for the driver. The vehicle spacing is the distance between two adjacent vehicles on the road. The traffic speed information is the current driving speed of vehicles on the road. The predicted speed is the predicted driving speed of vehicles in the future. The safe distance is the minimum distance that should be maintained between vehicles traveling on the road.

[0129] Specifically, the decision-making model sets a base brightness value based on urban functional zoning information, historical traffic flow information, and status information. Traffic sensors set at intervals acquire real-time vehicle traffic information on their associated roads. This vehicle traffic information includes vehicle type information, real-time traffic flow, vehicle spacing, and traffic speed information. An RNN model takes vehicle type information, real-time traffic flow, vehicle spacing, and traffic speed information as inputs and outputs a predicted vehicle speed. Based on the traffic speed information, predicted vehicle speed, and vehicle type information, a safe distance is calculated. The base brightness value is then dynamically adjusted based on the safe distance. This allows for the control of the streetlights in front of the vehicle according to the predicted vehicle speed, ensuring that drivers have sufficient road conditions to maintain a safe distance for reaction.

[0130] In one embodiment, step S523 includes:

[0131] S5241: Traffic sensors with interval settings acquire real-time traffic flow on their associated roads;

[0132] S5242: The decision-making model sets the weight ratio hierarchy of real-time traffic flow information and street light brightness based on urban functional zoning information, historical traffic flow information, status information and public feedback information.

[0133] S5243: Match the acquired real-time traffic flow with the preset weight ratio levels;

[0134] S5244: Adjust the brightness of streetlights in the streetlight group according to the weight ratio obtained from the matching hierarchy.

[0135] In this embodiment, real-time traffic flow is the number of vehicles on associated roads within a specific time period. The weight ratio level is a parameter set by the decision model based on various information (such as urban functional zoning information, historical traffic flow information, status information, and public feedback information) to determine the relationship between real-time traffic flow information and street light brightness.

[0136] Specifically, traffic sensors set at intervals acquire real-time traffic flow on their associated roads. The decision model sets a weight ratio between real-time traffic flow and street light brightness based on urban functional zoning information, historical traffic flow information, status information, and public feedback information. The acquired real-time traffic flow is matched with the preset weight ratio, and the brightness of the street lights in the street light group is adjusted according to the matched weight ratio, thus generating a corresponding control strategy for the smart street light group associated with the weight control group.

[0137] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0138] In one embodiment, a smart operation and maintenance management system for smart street light groups based on big data analysis is provided. This smart operation and maintenance management system for smart street light groups based on big data analysis corresponds one-to-one with the smart operation and maintenance management method for smart street light groups based on big data analysis in the above embodiment.

[0139] The present invention and its embodiments have been described above. This description is not restrictive. The accompanying drawings are only one embodiment of the present invention. The actual structure is not limited to this. In short, if a person skilled in the art is inspired by this description and designs a similar structure and embodiment without departing from the spirit of the present invention, such design should fall within the protection scope of the present invention.

Claims

1. A method for intelligent operation and maintenance management of smart street light groups in cities based on big data analysis, characterized by: Including the following steps: The system acquires urban functional zoning information and classifies smart streetlights on each road into several streetlight groups based on this information. It also acquires historical traffic flow information and historical weather information for each streetlight group and the associated roads. The system acquires status information and public feedback information for each street light group. Based on urban functional zoning information, historical traffic flow information, historical meteorological information, status information, and public feedback information, a decision model is constructed. The system then uses the decision model to generate preliminary operation and maintenance strategies for each street light group. Historical traffic flow information is input into the trained first prediction model to obtain the traffic flow prediction information corresponding to each street light group on the road output by the first prediction model. Historical meteorological information is input into the trained second prediction model to obtain the meteorological prediction information corresponding to the roads where each street light group is located, output by the second prediction model. Traffic flow forecast information and weather forecast information are input into the decision model, and the preliminary operation and maintenance strategy is optimized by a pre-set multi-objective optimization algorithm to obtain the target operation and maintenance strategy. The steps of inputting traffic flow forecast information and weather forecast information into the decision model, and optimizing the preliminary operation and maintenance strategy through a pre-set multi-objective optimization algorithm to obtain the target operation and maintenance strategy include the following steps: Based on urban functional zoning information and historical traffic flow information, a first threshold and a second threshold are set in the decision-making model for traffic flow prediction information; The decision model divides each street light group into groups based on the first and second thresholds and the corresponding traffic flow prediction information, and generates the first basic control strategy for each street light group based on the group division results. The decision model extracts the input meteorological forecast information into meteorological forecast features, and generates a second basic control strategy for each street light group based on the meteorological forecast features. The first basic control strategy and the second basic control strategy are integrated into the preliminary operation and maintenance strategy by using a decision model based on a pre-set multi-objective optimization algorithm to obtain the target operation and maintenance strategy.

2. The intelligent operation and maintenance management method for smart street light groups based on big data analysis according to claim 1, characterized in that: The steps of obtaining urban functional zoning information, classifying smart streetlights on each road into several streetlight groups based on the urban functional zoning information, and obtaining historical traffic flow information and historical weather information of the roads corresponding to each streetlight group include the following steps: The geographical location information of smart streetlights on each road is obtained, and the smart streetlights are divided based on K-means clustering and geographical location information to obtain several preliminary streetlight groups; Based on urban functional zoning information, the preliminary street light groups were classified into several groups.

3. The intelligent operation and maintenance management method for smart street light groups based on big data analysis according to claim 1, characterized in that: The steps of acquiring status information and public feedback information for each street light group, constructing a decision model based on urban functional zoning information, historical traffic flow information, historical meteorological information, status information, and public feedback information, and generating preliminary operation and maintenance strategies for each street light group through the decision model include the following steps: Obtain public feedback information and match the corresponding street light groups based on the preset identifiers associated with the public feedback information; By using pre-set natural language processing rules, sentiment analysis and semantic understanding are performed on public feedback information to extract feedback features; A decision-making model is constructed based on urban functional zoning information, historical traffic flow information, historical meteorological information, status information, and feedback characteristics.

4. The intelligent operation and maintenance management method for smart street light groups based on big data analysis according to claim 1, characterized in that: The first basic control strategy includes a real-time light contribution control strategy, a vehicle speed prediction control strategy, and a real-time traffic flow information weight control strategy. The step of grouping traffic flow prediction information corresponding to each street light group using a decision model based on a first threshold and a second threshold, and generating a preset first basic control strategy for each street light group based on the grouping results, includes the following steps: Traffic flow prediction information that is greater than the first threshold is set as the real-time control group, traffic flow prediction information that is less than the second threshold is set as the vehicle speed control group, and traffic flow prediction information that is between the first threshold and the second threshold is set as the weight control group. A real-time lighting contribution control strategy is generated for the street light groups associated with the real-time control group; A vehicle speed prediction and control strategy is generated for the street light group associated with the vehicle speed control group. A weighted control strategy is generated for real-time traffic flow information of the street light groups associated with the weighted control group.

5. The intelligent operation and maintenance management method for smart street light groups based on big data analysis according to claim 4, characterized in that: The step of generating a real-time lighting contribution control strategy for the smart street light group associated with the real-time control group includes the following steps: The decision-making model sets a rated brightness contribution value based on urban functional zoning information, status information, and public feedback information; The total brightness value of the associated road is obtained in real time by a photosensitive sensor with an interval setting. The total brightness value is the sum of the current vehicle light brightness contribution value and the current street light brightness contribution value. Calculate the difference between the total brightness value and the rated brightness contribution value, the rate of change of the difference, and the cumulative value of the difference within a preset time range; The PID control algorithm adjusts the current street light brightness contribution value based on the calculated difference, the rate of change of the difference, and the cumulative value of the difference.

6. The intelligent operation and maintenance management method for smart street light groups based on big data analysis according to claim 4, characterized in that: The decision model includes an RNN model, and the step of generating a vehicle speed prediction and control strategy for the smart street light group associated with the vehicle speed control group includes the following steps: The decision-making model sets a base brightness value based on urban functional zoning information, historical traffic flow information, and status information; Traffic sensors set at intervals acquire real-time vehicle traffic information on their associated roads. The vehicle traffic information includes vehicle type information, real-time traffic flow, vehicle spacing, and traffic speed information. The RNN model takes vehicle type information, real-time traffic flow, vehicle spacing and traffic speed information as inputs and outputs the predicted vehicle speed. Calculate the safe distance based on traffic speed information, predicted vehicle speed, and vehicle type information; The base brightness value is dynamically adjusted based on the safe distance.

7. The intelligent operation and maintenance management method for smart street light groups based on big data analysis according to claim 4, characterized in that: The steps for generating a real-time traffic flow information weight control strategy for the smart street light group associated with the weight control group include the following steps: Traffic sensors set at intervals acquire real-time traffic flow on their associated roads. The decision-making model sets a weighting hierarchy between real-time traffic flow information and street light brightness based on urban functional zoning information, historical traffic flow information, status information, and public feedback information. The acquired real-time traffic flow is matched with preset weight ratio levels; The brightness of the streetlights in the streetlight group is adjusted according to the weight ratio obtained from the matching.

8. A smart city street light group intelligent operation and maintenance management system based on big data analysis, used to execute the steps of the smart city street light group intelligent operation and maintenance management method based on big data analysis as described in any one of claims 1-7, characterized in that, include: The group classification module obtains urban functional zoning information and classifies the smart streetlights on each road into several streetlight groups based on the urban functional zoning information. It also obtains historical traffic flow information and historical weather information of the roads associated with each streetlight group. The strategy generation module obtains the status information of each street light group and public feedback information, builds a decision model based on urban functional zoning information, historical traffic flow information, historical meteorological information, status information and public feedback information, and generates preliminary operation and maintenance strategies based on each street light group through the decision model. The traffic flow prediction module inputs historical traffic flow information into the trained first prediction model to obtain the traffic flow prediction information corresponding to each street light group on the road output by the first prediction model. The weather forecast module inputs historical weather information into the trained second forecast model to obtain the weather forecast information corresponding to the roads where each street light group is located, output by the second forecast model. The strategy optimization module inputs traffic flow forecast information and weather forecast information into the decision model, and optimizes the initial operation and maintenance strategy through a pre-set multi-objective optimization algorithm to obtain the target operation and maintenance strategy.

Images