Central business district low-carbon intelligent traffic management and control system and method based on Internet of Things

Abstract

The invention discloses a central business district low-carbon intelligent traffic management and control system and method based on the Internet of Things, and belongs to the field of intelligent traffic. The invention discloses a central business district low-carbon intelligent traffic management and control system and method based on the Internet of Things. The system comprises a data acquisition unit, a data analysis unit and a collaborative execution unit. The problem that complex and changeable urban traffic demands are difficult to effectively cope with in the prior art is solved, the carbon footprint change trend is predicted by monitoring and analyzing multi-source data in real time in combination with a reinforcement learning algorithm, low-carbon travel suggestions can be generated and pushed to users, and the user experience is improved. Therefore, the user can be guided to reasonably plan the travel mode and time, the travel efficiency is improved, the traffic control instruction is generated based on the prediction result, the traffic signal lamp time sequence is dynamically adjusted, the public traffic scheduling is optimized, and the traffic jam can be effectively relieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a low-carbon intelligent transportation control system and method for a central business district based on the Internet of Things. Background Art

[0002] Traditional traffic control systems mainly rely on fixed signal light timing and simple traffic flow monitoring, lacking the ability to comprehensively analyze and dynamically control multi-source data such as traffic flow, vehicle emissions, and ambient air quality. This single control model is difficult to effectively respond to the complex and ever-changing urban traffic needs; therefore, it does not meet existing needs. To this end, we propose a low-carbon intelligent traffic control system and method for central business districts based on the Internet of Things. Summary of the Invention

[0003] The purpose of the present invention is to provide a low-carbon intelligent traffic control system and method for central business districts based on the Internet of Things. By real-time monitoring and analysis of multi-source data such as traffic flow, vehicle emissions and ambient air quality, combined with reinforcement learning algorithms to predict carbon footprint change trends, it can accurately generate low-carbon travel recommendations, dynamically adjust traffic light timing and optimize public transportation scheduling, and solve the problems raised in the above-mentioned background technology.

[0004] To achieve the above-mentioned object, the present invention provides the following technical solutions: a low-carbon intelligent traffic control system for a central business district based on the Internet of Things, the system comprising a data acquisition unit, a data analysis unit, and a collaborative execution unit;

[0005] The data acquisition unit is configured to deploy monitoring equipment on the central business district road network to collect multi-source data in real time, including traffic flow data, vehicle emission data, ambient air quality data, and public transportation operation data;

[0006] The data analysis unit is configured to use a reinforcement learning algorithm and combine historical data with multi-source data collected in real time to predict the regional carbon footprint change trend within the next hour and generate low-carbon travel recommendations, as well as generate traffic control instructions, dynamically adjust traffic light timing, and optimize public transportation scheduling;

[0007] The collaborative execution unit is configured to push low-carbon travel suggestions to users through mobile applications or information, and execute traffic control instructions.

[0008] Furthermore, the data acquisition unit includes:

[0009] A data acquisition module is configured to deploy various types of monitoring equipment at key nodes of the central business district road network. The various types of monitoring equipment cooperate with each other to collect multi-source data of the central business district road network from different angles in real time, and perform preliminary processing on the multi-source data collected in real time through edge computing nodes.

[0010] The data processing module is configured to further pre-process the multi-source data collected in real time, including data cleaning, data denoising and smoothing, and data standardization, and perform data fusion processing after pre-processing.

[0011] Furthermore, the data acquisition module includes:

[0012] Deploy a planning module configured to collect historical traffic flow data from the central business district road network, analyze the historical traffic flow data through cluster analysis and principal component analysis, and identify key nodes with high traffic flow, frequent congestion, and frequent traffic conflicts;

[0013] A planning execution module is configured to deploy various types of monitoring equipment at the identified key nodes and collect multi-source data in real time through the cooperation of the monitoring equipment;

[0014] The preliminary processing module is configured to deploy edge computing nodes near the deployment location of the monitoring equipment to perform preliminary processing on the collected raw data.

[0015] Furthermore, the data processing module includes:

[0016] The preprocessing module is configured to perform a series of preprocessing operations on multi-source data collected in real time, including data cleaning, data denoising and smoothing, and data standardization. Specifically:

[0017] Data cleaning: remove outliers from multi-source data and use filling methods to fill missing values in the original data;

[0018] Data denoising and smoothing: Filtering algorithms, including Kalman filtering and median filtering, are used to denoise the noise and fluctuations in the collected multi-source data.

[0019] Data standardization and normalization: By standardizing multi-source data, different types of multi-source data are converted into a unified format and dimension;

[0020] The data fusion module is configured to use a data fusion algorithm to fuse multi-source data collected in real time. The data fusion algorithm includes Bayesian networks and neural networks, and then uses spatiotemporal analysis technology to establish a correlation model between traffic flow, vehicle emissions and ambient air quality, and to explore the inherent connections and mutual influences between multi-source data.

[0021] Furthermore, the data analysis unit includes:

[0022] A feature extraction module is configured to extract key features from multi-source data collected in real time, including traffic flow features, vehicle emission features, and ambient air quality features. The extracted features will serve as input to the reinforcement learning algorithm to predict future carbon footprint trends;

[0023] The carbon footprint prediction module is configured to build a reinforcement learning model for carbon footprint prediction based on historical data based on a reinforcement learning algorithm. The reinforcement learning model combines the characteristics of multi-source data collected in real time to predict the changing trend of regional carbon footprint in the next hour and generate low-carbon travel recommendations;

[0024] The instruction generation module is configured to formulate an optimization strategy for traffic light timing based on the carbon footprint prediction results and traffic flow data, generate traffic control instructions for adjusting the traffic light timing based on the optimization strategy, and generate traffic control instructions for bus vehicle scheduling based on the carbon footprint prediction results and public transportation operation data. The generated traffic control instructions are used to implement traffic control.

[0025] Furthermore, the features extracted by the feature extraction module are specifically:

[0026] Traffic flow characteristics: Extract the characteristics of road congestion index and average vehicle speed change rate from traffic flow data;

[0027] Vehicle emission characteristics: Extract the characteristics of unit mileage emissions and the emission proportions of different types of vehicles from vehicle emission data;

[0028] Ambient air quality characteristics: Extract characteristics of pollutant concentration change trends and air quality index change rates from ambient air quality data.

[0029] Furthermore, the carbon footprint prediction module performs the following process:

[0030] Based on the reinforcement learning algorithm and historical data, a reinforcement learning model for carbon footprint prediction is constructed;

[0031] The features in the multi-source data are used as the state space, and the carbon footprint change trend in the next hour is used as the objective function. The model is trained through a reward mechanism, where the reward mechanism gives positive rewards for carbon footprint reduction and negative rewards for carbon footprint increase.

[0032] Using the trained reinforcement learning model and combining the multi-source data features collected in real time, we can predict the changing trend of regional carbon footprint in the next hour.

[0033] Low-carbon travel recommendations are generated based on the carbon footprint prediction results. When it is predicted that the carbon footprint of a certain area will increase within the next hour, travelers are given priority to choose public transportation such as subways and buses.

[0034] Furthermore, the collaborative execution unit includes:

[0035] The personalized recommendation module is configured to generate a user profile based on the user's historical travel records, preference settings, and real-time location, analyze the user's travel habits, including frequent travel times, common locations, and travel mode preferences, and provide users with personalized low-carbon travel suggestions based on the user profile and the generated low-carbon travel suggestions. The suggestions are pushed to users through mobile applications or information. Specifically, they are divided into:

[0036] For commuters, it is recommended to choose public transportation or carpooling during peak hours;

[0037] For short trips, walking or cycling is recommended;

[0038] The instruction execution module is configured to receive traffic control instructions generated by the data analysis unit, dynamically adjust the traffic light timing and optimize public transportation scheduling, and provide feedback on the execution results.

[0039] Furthermore, the instruction execution module includes:

[0040] An effectiveness evaluation module, configured to monitor the effectiveness of traffic light adjustments and public transportation scheduling in real time, and to evaluate the long-term effectiveness of traffic control measures based on the monitoring data and provide feedback;

[0041] The strategy adjustment module is configured to adjust the generation strategy of signal light timing and public transportation dispatch instructions based on the feedback of the execution effect of traffic control instructions, and optimize traffic control measures.

[0042] A low-carbon intelligent traffic control method for a central business district based on the Internet of Things is used to implement a low-carbon intelligent traffic control system for a central business district based on the Internet of Things, comprising the following steps:

[0043] Deploy a variety of monitoring equipment at key nodes on the central business district's road network to collect real-time multi-source data, including traffic flow data, vehicle emissions data, ambient air quality data, and public transportation operation data;

[0044] A carbon footprint prediction model is built based on a reinforcement learning algorithm. Based on historical data and combined with real-time feature data, it predicts the carbon footprint change trend within the next hour and generates low-carbon travel recommendations.

[0045] Generate traffic control instructions for adjusting traffic light timing and bus dispatch based on carbon footprint prediction results, traffic flow data, and public transportation operation data;

[0046] Generate user profiles based on users' travel history, preferences, and real-time locations, analyze their travel habits, and provide users with personalized travel plans based on low-carbon travel recommendations. These plans are then pushed through mobile apps or messaging.

[0047] According to traffic control instructions, traffic light timing is dynamically adjusted and public transportation scheduling is optimized, and the execution effect is monitored in real time to optimize the control strategy.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] The present invention monitors and analyzes multi-source data on traffic flow, vehicle emissions, ambient air quality, and public transportation operations in real time, and combines it with reinforcement learning algorithms to predict carbon footprint trends. This can generate low-carbon travel suggestions and push them to users, thereby guiding users to rationally plan travel methods and times, avoid traffic congestion, and improve travel efficiency. At the same time, based on the prediction results, traffic control instructions are generated, traffic signal timing is dynamically adjusted, and public transportation scheduling is optimized, which can effectively alleviate traffic congestion, especially during peak hours and on congested sections. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a schematic diagram of the structure of the low-carbon intelligent traffic control system for central business districts based on the Internet of Things of the present invention;

[0051] Figure 2 This is a flow chart of the low-carbon intelligent traffic control method for central business districts based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0052] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0053] To address the problem that the existing traffic control system mainly relies on fixed signal light timing and simple traffic flow monitoring, lacks the ability to comprehensively analyze and dynamically control multiple sources of data such as traffic flow, vehicle emissions and ambient air quality. This single control model is difficult to effectively respond to the complex and changing needs of urban traffic. Figure 1-Figure 2 , this embodiment provides the following technical solutions:

[0054] A low-carbon intelligent traffic control system for a central business district based on the Internet of Things, the system comprising a data acquisition unit, a data analysis unit, and a collaborative execution unit;

[0055] The data acquisition unit is configured to deploy monitoring equipment on the central business district road network to collect multi-source data in real time, including traffic flow data, vehicle emission data, ambient air quality data, and public transportation operation data;

[0056] The data analysis unit is configured to use a reinforcement learning algorithm and combine historical data with multi-source data collected in real time to predict the regional carbon footprint change trend within the next hour and generate low-carbon travel recommendations, as well as generate traffic control instructions, dynamically adjust traffic light timing, and optimize public transportation scheduling;

[0057] The collaborative execution unit is configured to push low-carbon travel suggestions to users through mobile applications or information, and execute traffic control instructions.

[0058] The technical effects of the above content are as follows: the data acquisition unit collects traffic flow data in real time, allowing the system to accurately understand the carbon emissions and traffic conditions of the central business district road network. The data analysis unit, based on a reinforcement learning algorithm, combines historical and real-time data to predict the regional carbon footprint change trend within the next hour and generate traffic control instructions, which can dynamically adjust traffic light timing. For example, during peak traffic hours, this can improve road capacity and alleviate traffic congestion. The collaborative execution unit ensures that low-carbon travel recommendations are pushed to users, and traffic control instructions are accurately conveyed to traffic lights and other equipment, ensuring that traffic flows in different directions can alternate in an orderly manner.

[0059] The data acquisition unit includes:

[0060] A data acquisition module is configured to deploy various types of monitoring equipment at key nodes of the central business district road network. The various types of monitoring equipment cooperate with each other to collect multi-source data of the central business district road network from different angles in real time, and perform preliminary processing on the multi-source data collected in real time through edge computing nodes.

[0061] The data processing module is configured to further pre-process the multi-source data collected in real time, including data cleaning, data denoising and smoothing, and data standardization, and perform data fusion processing after pre-processing.

[0062] The technical effect of the above content is: the data acquisition module cooperates with various types of monitoring equipment to collect multi-source data from different angles, which can effectively reduce the errors that may occur in a single device and improve the accuracy and reliability of the data. At the same time, the edge computing node performs preliminary processing on the multi-source data collected in real time, and can quickly filter out abnormal data or noise data, further improving the data quality. The data processing module further processes the multi-source data, which can further significantly improve the data quality and provide a reliable data foundation for subsequent data analysis and fusion.

[0063] Data acquisition module, including:

[0064] Deploy a planning module configured to collect historical traffic flow data from the central business district road network, analyze the historical traffic flow data through cluster analysis and principal component analysis, and identify key nodes with high traffic flow, frequent congestion, and frequent traffic conflicts;

[0065] Cluster analysis can divide traffic flow data into different clusters based on similarity, thereby identifying areas with similar traffic flows and helping to determine areas with high congestion rates. For example, cluster analysis can reveal that certain intersections or road sections have highly concentrated traffic flows during specific time periods, making them prone to congestion.

[0066] Principal component analysis can extract the main features from traffic flow data, remove redundant information, and further clarify the distribution of key nodes. For example, principal component analysis can help identify which factors (such as traffic volume, speed, time, etc.) have the greatest impact on traffic congestion, thereby more accurately locating key nodes;

[0067] A planning execution module is configured to deploy various types of monitoring equipment at the identified key nodes and collect multi-source data in real time through the cooperation of the monitoring equipment;

[0068] The preliminary processing module is configured to deploy edge computing nodes near the deployment location of the monitoring equipment to perform preliminary processing on the collected raw data.

[0069] The technical effect of the above content is: the deployment planning module collects historical traffic flow data of the central business district road network and uses statistical methods such as cluster analysis and principal component analysis to conduct in-depth analysis of the data. It can accurately identify key nodes with high traffic flow, frequent congestion and many traffic conflict points. By accurately identifying key nodes, the deployment planning module can provide a scientific basis for the deployment of monitoring equipment. Deploying monitoring equipment at these key nodes can ensure that the collected data is more representative and can effectively reflect the overall operating status of the central business district road network. Finally, the preliminary processing module deploys edge computing nodes near the deployment location of the monitoring equipment to perform preliminary processing on the collected raw data. The edge computing nodes can quickly screen and preliminarily analyze the raw data, remove noise data and abnormal data, reduce data transmission volume, and improve data quality and availability.

[0070] Data processing module, including:

[0071] The preprocessing module is configured to perform a series of preprocessing operations on multi-source data collected in real time, including data cleaning, data denoising and smoothing, and data standardization. Specifically:

[0072] Data cleaning: remove outliers from multi-source data and use filling methods to fill missing values in the original data;

[0073] Data denoising and smoothing: Filtering algorithms, including Kalman filtering and median filtering, are used to denoise the noise and fluctuations in the collected multi-source data.

[0074] Data standardization and normalization: By standardizing multi-source data, different types of multi-source data are converted into a unified format and dimension;

[0075] The data fusion module is configured to use a data fusion algorithm to fuse multi-source data collected in real time. The data fusion algorithm includes Bayesian networks and neural networks, and then uses spatiotemporal analysis technology to establish a correlation model between traffic flow, vehicle emissions and ambient air quality, and to explore the inherent connections and mutual influences between multi-source data.

[0076] The technical effects of the above content are as follows: the preprocessing module can significantly improve the quality and availability of data through a series of preprocessing operations such as data cleaning, data denoising and smoothing, and data standardization. The data fusion module can generate more comprehensive and accurate decision support information through comprehensive analysis and fusion of multi-source data. By using spatiotemporal analysis technology, a correlation model between traffic flow, vehicle emissions and ambient air quality is established, which can further explore the spatiotemporal relationship between multi-source data, thereby helping the system to more comprehensively understand the interaction between traffic and the environment, and provide a more scientific basis for low-carbon intelligent traffic control.

[0077] Data Analysis Unit, including:

[0078] A feature extraction module is configured to extract key features from multi-source data collected in real time, including traffic flow features, vehicle emission features, and ambient air quality features. The extracted features will serve as input to the reinforcement learning algorithm to predict future carbon footprint trends;

[0079] The extracted features are:

[0080] Traffic flow characteristics: Extract the characteristics of road congestion index and average vehicle speed change rate from traffic flow data;

[0081] Vehicle emission characteristics: Extract the characteristics of unit mileage emissions and the emission proportions of different types of vehicles from vehicle emission data;

[0082] Ambient air quality characteristics: Extract characteristics of pollutant concentration change trends and air quality index change rates from ambient air quality data;

[0083] The carbon footprint prediction module is configured to build a reinforcement learning model for carbon footprint prediction based on historical data based on a reinforcement learning algorithm. The reinforcement learning model combines the multi-source data features collected in real time to predict the changing trend of regional carbon footprint in the next hour and generate low-carbon travel recommendations. The specific process is as follows:

[0084] Based on the reinforcement learning algorithm and historical data, a reinforcement learning model for carbon footprint prediction is constructed;

[0085] The features in the multi-source data are used as the state space, and the carbon footprint change trend in the next hour is used as the objective function. The model is trained through a reward mechanism, where the reward mechanism gives positive rewards for carbon footprint reduction and negative rewards for carbon footprint increase.

[0086] Using the trained reinforcement learning model and combining the multi-source data features collected in real time, we can predict the changing trend of regional carbon footprint in the next hour.

[0087] Generate low-carbon travel recommendations based on carbon footprint prediction results. When it is predicted that the carbon footprint of a certain area will increase in the next hour, travelers are given priority to choose public transportation such as subways and buses.

[0088] The instruction generation module is configured to formulate an optimization strategy for traffic light timing based on the carbon footprint prediction results and traffic flow data, generate traffic control instructions for adjusting the traffic light timing based on the optimization strategy, and generate traffic control instructions for bus vehicle scheduling based on the carbon footprint prediction results and public transportation operation data. The generated traffic control instructions are used to implement traffic control.

[0089] The technical effect of the above content is: the feature extraction module can convert a large amount of raw data into more representative and interpretable feature vectors by extracting key features, providing concise and effective input for subsequent analysis and prediction. The carbon footprint prediction module is based on the reinforcement learning algorithm and constructs a carbon footprint prediction model based on historical data. The reinforcement learning algorithm can learn the patterns and rules in historical data and combine the multi-source data features collected in real time to predict the changing trend of regional carbon footprint in the next 1 hour, thereby generating low-carbon travel recommendations based on the prediction results. The carbon footprint prediction results provide an important decision-making basis for the instruction generation module. By predicting the changing trend of future carbon footprints, the instruction generation module can formulate corresponding traffic control strategies in advance to optimize traffic signal timing and public transportation scheduling, thereby reducing carbon emissions and achieving the goal of low-carbon travel.

[0090] Collaborative execution unit, including:

[0091] The personalized recommendation module is configured to generate a user profile based on the user's historical travel records, preference settings, and real-time location, analyze the user's travel habits, including frequent travel times, common locations, and travel mode preferences, and provide users with personalized low-carbon travel suggestions based on the user profile and the generated low-carbon travel suggestions. The suggestions are pushed to users through mobile applications or information. Specifically, they are divided into:

[0092] For commuters, it is recommended to choose public transportation or carpooling during peak hours;

[0093] For short trips, walking or cycling is recommended;

[0094] The instruction execution module is configured to receive traffic control instructions generated by the data analysis unit, dynamically adjust the traffic light timing and optimize public transportation scheduling, and provide feedback on the execution results.

[0095] The instruction execution module includes:

[0096] An effectiveness evaluation module, configured to monitor the effectiveness of traffic light adjustments and public transportation scheduling in real time, and to evaluate the long-term effectiveness of traffic control measures based on the monitoring data and provide feedback;

[0097] The strategy adjustment module is configured to adjust the generation strategy of signal light timing and public transportation dispatch instructions based on the feedback of the execution effect of traffic control instructions, and optimize traffic control measures.

[0098] The technical effects of the above content are: the personalized suggestion module generates a user portrait by analyzing the user's historical travel records, preference settings and real-time location, and provides personalized low-carbon travel suggestions to the user based on the user portrait through mobile applications or information push. Targeted suggestions can make it easier for users to accept and adopt low-carbon travel methods. The instruction execution module dynamically adjusts the traffic light timing and optimizes public transportation scheduling according to traffic control instructions. Dynamic optimization can adjust traffic control strategies in time according to real-time traffic conditions and carbon footprint prediction results to ensure the efficient operation of the transportation system. At the same time, the instruction execution module monitors the execution effects of traffic light adjustments and public transportation scheduling in real time, and evaluates the long-term effects of traffic control measures. Through real-time monitoring and evaluation, the actual effects of traffic control measures can be evaluated and problems can be discovered in a timely manner.

[0099] Specifically, this embodiment further proposes a low-carbon intelligent traffic control method for a central business district based on the Internet of Things, which is used to implement a low-carbon intelligent traffic control system for a central business district based on the Internet of Things, including the following steps:

[0100] Deploy a variety of monitoring equipment at key nodes on the central business district's road network to collect real-time multi-source data, including traffic flow data, vehicle emissions data, ambient air quality data, and public transportation operation data;

[0101] A carbon footprint prediction model is built based on a reinforcement learning algorithm. Based on historical data and combined with real-time feature data, it predicts the carbon footprint change trend within the next hour and generates low-carbon travel recommendations.

[0102] Generate traffic control instructions for adjusting traffic light timing and bus dispatch based on carbon footprint prediction results, traffic flow data, and public transportation operation data;

[0103] Generate user profiles based on users' travel history, preferences, and real-time locations, analyze their travel habits, and provide users with personalized travel plans based on low-carbon travel recommendations. These plans are then pushed through mobile apps or messaging.

[0104] According to traffic control instructions, traffic light timing is dynamically adjusted and public transportation scheduling is optimized, and the execution effect is monitored in real time to optimize the control strategy.

[0105] Working principle: Through real-time monitoring and analysis of multi-source data on traffic flow, vehicle emissions, ambient air quality and public transportation operations, combined with reinforcement learning algorithms to predict carbon footprint change trends and generate low-carbon travel recommendations, it can guide users to reasonably plan travel methods and times, avoid traffic congestion, and improve travel efficiency. At the same time, based on the prediction results, traffic control instructions are generated, traffic light timing is dynamically adjusted, and public transportation scheduling is optimized, which can effectively alleviate traffic congestion, especially during peak hours and congested sections. By real-time monitoring of the execution effect of traffic light adjustments and public transportation scheduling, the actual effect of traffic control measures can be evaluated, and problems can be discovered in a timely manner, so that the system can continuously adapt to changes in traffic conditions and improve the intelligence level of the system.

[0106] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0107] While the embodiments of the present invention have been shown and described, it will be apparent to those skilled in the art that various changes, modifications, substitutions, and alterations can be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. A low-carbon intelligent traffic control system for central business districts based on the Internet of Things, characterized by: The system includes a data acquisition unit, a data analysis unit and a collaborative execution unit; The data acquisition unit is configured to deploy monitoring equipment on the central business district road network to collect multi-source data in real time, including traffic flow data, vehicle emission data, ambient air quality data, and public transportation operation data; The data analysis unit is configured to use a reinforcement learning algorithm and combine historical data with multi-source data collected in real time to predict the regional carbon footprint change trend within the next hour and generate low-carbon travel recommendations, as well as generate traffic control instructions, dynamically adjust traffic light timing, and optimize public transportation scheduling; The collaborative execution unit is configured to push low-carbon travel suggestions to users through mobile applications or information, and execute traffic control instructions.

2. The low-carbon intelligent traffic control system for a central business district based on the Internet of Things according to claim 1 is characterized by: The data acquisition unit includes: A data acquisition module is configured to deploy various types of monitoring equipment at key nodes of the central business district road network. The various types of monitoring equipment cooperate with each other to collect multi-source data of the central business district road network from different angles in real time, and perform preliminary processing on the multi-source data collected in real time through edge computing nodes. The data processing module is configured to further pre-process the multi-source data collected in real time, including data cleaning, data denoising and smoothing, and data standardization, and perform data fusion processing after pre-processing.

3. The low-carbon intelligent traffic control system for a central business district based on the Internet of Things according to claim 2 is characterized by: The data acquisition module includes: Deploy a planning module configured to collect historical traffic flow data from the central business district road network, analyze the historical traffic flow data through cluster analysis and principal component analysis, and identify key nodes with high traffic flow, frequent congestion, and frequent traffic conflicts; A planning execution module is configured to deploy various types of monitoring equipment at the identified key nodes and collect multi-source data in real time through the cooperation of the monitoring equipment; The preliminary processing module is configured to deploy edge computing nodes near the deployment location of the monitoring equipment to perform preliminary processing on the collected raw data.

4. The low-carbon intelligent traffic control system for a central business district based on the Internet of Things according to claim 2 is characterized by: The data processing module includes: The preprocessing module is configured to perform a series of preprocessing operations on multi-source data collected in real time, including data cleaning, data denoising and smoothing, and data standardization. Specifically: Data cleaning: remove outliers from multi-source data and use filling methods to fill missing values in the original data; Data denoising and smoothing: Filtering algorithms, including Kalman filtering and median filtering, are used to denoise the noise and fluctuations in the collected multi-source data. Data standardization and normalization: By standardizing multi-source data, different types of multi-source data are converted into a unified format and dimension; The data fusion module is configured to use a data fusion algorithm to fuse multi-source data collected in real time. The data fusion algorithm includes Bayesian networks and neural networks, and then uses spatiotemporal analysis technology to establish a correlation model between traffic flow, vehicle emissions and ambient air quality, and to explore the inherent connections and mutual influences between multi-source data.

5. The low-carbon intelligent traffic control system for a central business district based on the Internet of Things according to claim 1 is characterized by: The data analysis unit comprises: A feature extraction module is configured to extract key features from multi-source data collected in real time, including traffic flow features, vehicle emission features, and ambient air quality features. The extracted features will serve as input to the reinforcement learning algorithm to predict future carbon footprint trends; The carbon footprint prediction module is configured to build a reinforcement learning model for carbon footprint prediction based on historical data based on a reinforcement learning algorithm. The reinforcement learning model combines the characteristics of multi-source data collected in real time to predict the changing trend of regional carbon footprint in the next hour and generate low-carbon travel recommendations; The instruction generation module is configured to formulate an optimization strategy for traffic light timing based on the carbon footprint prediction results and traffic flow data, generate traffic control instructions for adjusting the traffic light timing based on the optimization strategy, and generate traffic control instructions for bus vehicle scheduling based on the carbon footprint prediction results and public transportation operation data. The generated traffic control instructions are used to implement traffic control.

6. The low-carbon intelligent traffic control system for a central business district based on the Internet of Things according to claim 5 is characterized by: The features extracted by the feature extraction module are specifically: Traffic flow characteristics: Extract the characteristics of road congestion index and average vehicle speed change rate from traffic flow data; Vehicle emission characteristics: Extract the characteristics of unit mileage emissions and the emission proportions of different types of vehicles from vehicle emission data; Ambient air quality characteristics: Extract characteristics of pollutant concentration change trends and air quality index change rates from ambient air quality data.

7. The low-carbon intelligent traffic control system for a central business district based on the Internet of Things according to claim 5 is characterized by: The carbon footprint prediction module performs the following process: Based on the reinforcement learning algorithm and historical data, a reinforcement learning model for carbon footprint prediction is constructed; The features in the multi-source data are used as the state space, and the carbon footprint change trend in the next hour is used as the objective function. The model is trained through a reward mechanism, where the reward mechanism gives positive rewards for carbon footprint reduction and negative rewards for carbon footprint increase. Using the trained reinforcement learning model and combining the multi-source data features collected in real time, we can predict the changing trend of regional carbon footprint in the next hour. Low-carbon travel recommendations are generated based on the carbon footprint prediction results. When it is predicted that the carbon footprint of a certain area will increase within the next hour, travelers are given priority to choose public transportation such as subways and buses.

8. The low-carbon intelligent traffic control system for a central business district based on the Internet of Things according to claim 1 is characterized by: The collaborative execution unit includes: The personalized recommendation module is configured to generate a user profile based on the user's historical travel records, preference settings, and real-time location, analyze the user's travel habits, including frequent travel times, common locations, and travel mode preferences, and provide users with personalized low-carbon travel suggestions based on the user profile and the generated low-carbon travel suggestions. The suggestions are pushed to users through mobile applications or information. Specifically, they are divided into: For commuters, it is recommended to choose public transportation or carpooling during peak hours; For short trips, walking or cycling is recommended; The instruction execution module is configured to receive traffic control instructions generated by the data analysis unit, dynamically adjust the traffic light timing and optimize public transportation scheduling, and provide feedback on the execution results.

9. The low-carbon intelligent traffic control system for a central business district based on the Internet of Things according to claim 8, characterized in that: The instruction execution module includes: An effectiveness evaluation module, configured to monitor the effectiveness of traffic light adjustments and public transportation scheduling in real time, and to evaluate the long-term effectiveness of traffic control measures based on the monitoring data and provide feedback; The strategy adjustment module is configured to adjust the generation strategy of signal light timing and public transportation dispatch instructions based on the feedback of the execution effect of traffic control instructions, and optimize traffic control measures.

10. A low-carbon intelligent traffic control method for a central business district based on the Internet of Things, used to implement a low-carbon intelligent traffic control system for a central business district based on the Internet of Things according to any one of claims 1 to 9, characterized in that: The following steps are involved: Deploy a variety of monitoring equipment at key nodes on the central business district's road network to collect real-time multi-source data, including traffic flow data, vehicle emissions data, ambient air quality data, and public transportation operation data; A carbon footprint prediction model is built based on a reinforcement learning algorithm. Based on historical data and combined with real-time feature data, it predicts the carbon footprint change trend within the next hour and generates low-carbon travel recommendations. Generate traffic control instructions for adjusting traffic light timing and bus dispatch based on carbon footprint prediction results, traffic flow data, and public transportation operation data; Generate user profiles based on users' travel history, preferences, and real-time locations, analyze their travel habits, and provide users with personalized travel plans based on low-carbon travel recommendations. These plans are then pushed through mobile apps or messaging. According to traffic control instructions, traffic light timing is dynamically adjusted and public transportation scheduling is optimized, and the execution effect is monitored in real time to optimize the control strategy.

Images