Traffic signal period duration dynamic adjustment method based on trajectory data

Abstract

The invention provides a traffic signal period duration dynamic adjustment method based on trajectory data. The method comprises the following steps: step 1, determining a data source; step 2, data integration and standardization; 3, traffic flow characteristics are extracted; and 4, constructing a dynamic traffic model, and dynamically adjusting the period duration of the traffic signal. According to the method, the traffic flow efficiency can be improved, the traffic flow change can be more accurately predicted by utilizing real-time data analysis, and the signal period can be dynamically adjusted, so that the vehicle waiting time is shortened, and the overall road traffic capacity is improved. According to the method, big data analysis and an artificial intelligence algorithm are combined, automation and intelligence of traffic signal control are achieved, and dependence on manual intervention is reduced.

Description

Technical Field

[0001] The present invention belongs to the field of emerging information technology, and in particular relates to a method for dynamically adjusting the cycle duration of a traffic signal based on trajectory data. Background Art

[0002] In today's rapidly developing urban environment, traffic congestion has become a prominent problem, especially during peak hours, when a large number of vehicles rush to limited road resources, resulting in a significant decrease in traffic mobility. Traditional traffic signal control methods, due to the lack of real-time data analysis and dynamic response mechanisms, are often unable to effectively cope with instantaneous traffic pressure, resulting in long queues of vehicles at intersections, and even chain reactions leading to traffic paralysis in wider areas. In order to solve these problems, an intelligent method that can respond to traffic conditions in real time and dynamically adjust traffic signal cycles is urgently needed to optimize traffic flow, reduce waiting time, improve road use efficiency, and promote the sustainable development of urban transportation systems. Summary of the invention

[0003] Purpose of the invention: The technical problem to be solved by the present invention is to provide a method for dynamically adjusting the cycle duration of traffic signals based on trajectory data in view of the deficiencies of the prior art. The method can analyze traffic flow based on real-time trajectory data and dynamically adjust the cycle duration of traffic lights to optimize urban traffic flow, reduce congestion, improve road traffic efficiency, and reduce environmental pollution and enhance the driver's travel experience. Through this method, the present invention aims to achieve an intelligent upgrade of the traffic management system and provide an effective technical solution to the problem of urban traffic congestion.

[0004] The method of the present invention comprises the following steps:

[0005] Step 1, determine the data source;

[0006] Step 2: Data integration and standardization;

[0007] Step 3, extracting traffic flow characteristics;

[0008] Step 4: Build a dynamic traffic model and dynamically adjust the traffic signal cycle duration.

[0009] Step 1 includes: obtaining vehicle trajectory data through a traffic data service provider, wherein the vehicle trajectory data includes the real-time position, driving speed and driving direction of the vehicle.

[0010] In step 1, the vehicle trajectory data is anonymized.

[0011] Step 2 includes: integrating vehicle trajectory data obtained from different traffic data service providers to build a unified data pool, formatting the integrated vehicle trajectory data to ensure that timestamps, longitude and latitude, and speed are standardized in a unified format; at the same time, classifying and annotating vehicle trajectory data according to vehicle type, size, and driving status; establishing a metadata management system (establishing a metadata management system usually involves several key steps, including defining metadata standards, designing data models, selecting appropriate technology platforms, implementing data collection and storage strategies, and formulating data management policies) to record the source, collection time, and collection method of the data; implementing data consistency checks to ensure that data between different data sources are logically and temporally consistent, and continuously implementing data security measures and privacy protection strategies. Specific technologies to ensure data consistency include using data verification and validation mechanisms, such as hashing algorithms or digital signatures to ensure data integrity; using timestamps and version control to ensure data temporality; and integrating data from different sources through data fusion algorithms. Data security and privacy protection are achieved through measures such as encrypted storage, transmission encryption, access control, data desensitization, and regular security audits. These techniques are standard practices in the field of data management and can be implemented through custom development or using off-the-shelf data management software.

[0012] Step 3 includes: using data analysis techniques to identify key traffic flow indicators from vehicle trajectory data, including vehicle volume, vehicle density, and average speed.

[0013] In step 3, the traffic conditions are quantified and the changes of the traffic conditions over time are monitored by using the key traffic flow indicators, including:

[0014] By analyzing the data of vehicles passing through a specific road section or intersection, the traffic volume in different time periods is calculated to identify peak and off-peak periods (using classification algorithms in machine learning technology to identify peak and off-peak periods. First, collect traffic volume data for a specific road section or intersection in different time periods, including vehicle counts, timestamps, dates, weather conditions, special events, and other factors that may affect traffic. Then, use this data to train a classification model, such as a support vector machine (SVM), random forest, or gradient boosting machine (GBM). The model will learn to identify the characteristics of peak periods from historical data. Next, the trained model is applied to the real-time data stream to automatically classify whether the current period is peak or off-peak. In addition, the model can be retrained regularly with newly collected data to maintain its accuracy and adaptability);

[0015] By measuring the number of vehicles in a specific area, evaluating vehicle density, and discovering possible congestion points (through the real-time vehicle trajectory data obtained from the traffic data service provider, the average traffic volume of a specific road section or intersection in different time periods can be calculated, and then these data points can be used to compare and analyze with historical data to determine the vehicle density. If the real-time traffic volume is significantly higher than the historical average, and the average distance between vehicles is lower than the preset threshold, the system will automatically identify the area as a high-density area and a possible congestion point. The preset threshold for vehicle density is usually determined based on the historical traffic data and traffic engineering standards of a specific road section. This threshold varies depending on the region, road section type, number of lanes, and traffic flow characteristics. For example, on urban roads, the vehicle density threshold may be set at 150 to 200 vehicles per kilometer, while on highways, this threshold may be higher. The specific threshold needs to be determined by analyzing the traffic flow data of a specific road section, combining traffic flow theory, such as the concepts of free flow, stable flow, and congested flow, and actual traffic conditions);

[0016] Obtain traffic fluidity by calculating the average speed of vehicles on a specific road section (traffic fluidity can be evaluated by calculating the average speed of vehicles on a specific road section. For example, if the average speed is close to or equal to the speed limit of the road section, this usually indicates that traffic fluidity is good and vehicles can flow freely; if the average speed is much lower than the speed limit or there are frequent decelerations and stops, this may mean that traffic fluidity is hindered and there is congestion. By continuously monitoring these speed data, we can identify changing trends in traffic flow, predict possible congestion, and adjust traffic lights or issue traffic guidance accordingly to improve traffic fluidity);

[0017] Analyze the changing patterns of these characteristics in time series;

[0018] By comparing the traffic characteristics of weekdays and weekends (traffic characteristics refer to parameters such as traffic volume, vehicle density and average speed, which show statistical characteristics and trends in different time periods (such as weekdays and weekends). By comparing the changes in these parameters on weekdays and weekends, the periodic pattern of traffic flow can be identified. For example, the traffic volume is higher during the morning and evening rush hours on weekdays, while the traffic peak may occur during specific time periods such as noon or evening on weekends. This periodic pattern is crucial for optimizing the setting of traffic lights and traffic flow management.), a periodic pattern is obtained (a periodic pattern usually refers to the regular changes in traffic flow within a week. For example, the traffic flow on weekdays is Traffic may have two obvious peaks in the morning and evening, which coincide with commuting time, while the traffic is relatively low at other times of the day. In contrast, the traffic peak on weekends may not be so obvious, and the peak period may be postponed to late morning or afternoon, because people may be more inclined to go out for leisure or shopping at these times. In addition, certain specific festivals or seasonal activities may also cause changes in the cyclical pattern of traffic flow, such as increased traffic on the eve of holidays or during the peak summer tourism season. By analyzing these cyclical patterns, traffic management departments can better predict and respond to traffic demand in different time periods, optimize the timing of traffic lights, and improve road use efficiency).

[0019] Step 4 includes: the dynamic traffic model includes:

[0020] The formula for traffic flow change is:

[0021]

[0022] Where λ(t) is the average speed of vehicles entering the road section through the green light at time t; μ(t) is the average speed of vehicles leaving the road section at time t; N(t) represents the traffic volume on a specific road section at time t; d represents the integral sign;

[0023] Adjust λ(t) based on the green light duration G(t) at time t: λ(t) = k*G(t), k is a proportional constant; in the context of traffic signal control, the proportional constant k is used to relate the green light duration G(t) to the vehicle entry rate λ(t), that is, λ(t) = k·G(t)λ(t) = k·G(t). The value of this proportional constant k usually depends on a variety of factors, including the width of the road section, the average speed of vehicles, and the expected traffic throughput. There is no uniform standard for the specific value because it is affected by local traffic conditions, road design, traffic rules, and traffic characteristics. For example, in urban traffic, the value of k may be lower to accommodate lower speeds and more frequent stops; on highways or suburban roads, k may be higher to accommodate higher speeds and fewer stops. If a rough range is required, k is generally between 1 and 5;

[0024] The green light duration adjustment formula is:

[0025]

[0026] Among them, G(t) is the green light duration at time t, T cycle represents the duration of the signal light cycle, C is the maximum number of vehicles that the road section can accommodate; f(N(t)) is a function that adjusts the green light duration according to the traffic volume N(t) at time t to ensure that the green light duration is proportional to the traffic volume and does not exceed the road section capacity limit.

[0027] Step 4 also includes: if the traffic volume increases, recalculate the green light duration G(t) at time t according to the following formula:

[0028]

[0029] Among them, T cycle It can be dynamically adjusted according to the traffic flow N(t) at time t to adapt to traffic demand; the min function ensures that even in high traffic conditions, the green light duration will not exceed the signal light cycle duration T cycle ;

[0030] For example, if the basic signal light cycle duration is T cycle is 120 seconds, the traffic flow N(t) at time t is 50 vehicles per minute, and the road section capacity C is 200 vehicles. Then the green light duration G(t) at time t is:

[0031]

[0032] If the traffic flow N(t) increases to 60 vehicles per minute at time t, the green light duration G(t) at time t will increase accordingly while maintaining the same green light cycle duration T cycle , the consistency of road section capacity C.

[0033] In this way, the traffic light control system can flexibly adjust the green light duration and traffic light cycle duration according to real-time traffic conditions to improve traffic efficiency, reduce congestion, and adapt to changing traffic needs.

[0034] Furthermore, the present invention also provides an electronic device, including a processor and a memory, wherein the memory stores program code, and when the program code is executed by the processor, the processor executes the steps of the described method.

[0035] Furthermore, a storage medium stores a computer program or instruction, and when the computer program or instruction is run on a computer, the steps of the method described are executed.

[0036] The present invention can analyze the vehicle trajectory data in the urban traffic network in real time, and dynamically adjust the cycle duration of the traffic lights accordingly. Through in-depth analysis of the vehicle's driving trajectory, the system can identify the pattern and trend of traffic flow, predict the occurrence of traffic congestion, and adjust the phase and duration of the traffic lights in advance to optimize traffic flow distribution, reduce vehicle waiting time, and improve the road's traffic capacity. The method uses a cloud computing platform for data processing, uses big data technology to store and analyze massive trajectory information, and combines artificial intelligence algorithms to predict and support decision-making for traffic flow, thereby realizing the automation and intelligence of traffic signal control. In addition, the system will also take into account special events and unconventional traffic conditions to flexibly adjust the signal light settings to ensure the adaptability and flexibility of traffic management. Through this comprehensive technical solution, it is expected to significantly improve the operating efficiency of urban transportation and reduce the social costs and environmental impacts caused by traffic congestion.

[0037] The present invention has the following beneficial effects:

[0038] 1) Improve traffic flow efficiency: By using real-time data analysis, this method can more accurately predict traffic flow changes and dynamically adjust signal cycles, thereby reducing vehicle waiting time and improving overall road capacity.

[0039] 2) Intelligent traffic management: Combining big data analysis and artificial intelligence algorithms, this method realizes the automation and intelligence of traffic signal control, reducing dependence on human intervention.

[0040] 3) Reduce traffic congestion: By responding to traffic conditions in real time, this method effectively disperses traffic, especially during peak hours, and can reduce traffic pressure on major roads.

[0041] 4) User customized services: Allow local traffic management departments to adjust algorithm parameters according to local traffic characteristics, implement customized traffic management, and meet the specific needs of different regions.

[0042] 5) Data-driven decision support: The data-driven decision support provided by this method helps traffic management departments to formulate and adjust traffic management strategies more scientifically. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments, and the above and / or other advantages of the present invention will become more clear.

[0044] Figure 1 It is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0045] like Figure 1As shown, the present invention provides a method for dynamically adjusting the cycle duration of a traffic signal based on trajectory data, comprising the following steps:

[0046] Step 1, determine the data source;

[0047] The present invention first focuses on establishing the data source, which is the cornerstone of the dynamic traffic signal adjustment method. The present invention plans to establish a cooperative relationship with leading traffic data service providers in the industry, such as Amap, Baidu Map, Didi Chuxing, etc., to obtain rich vehicle trajectory data including real-time vehicle location, driving speed, driving direction, etc. While ensuring that the data accuracy and update frequency meet the real-time analysis needs, the present invention will evaluate and select data sources that can widely cover the main roads and traffic nodes in the target city or region (the process of evaluating and selecting data sources usually combines quantitative analysis and qualitative judgment, relying on automated data quality assessment tools, algorithm models and expert systems, which can objectively analyze the coverage, accuracy, timeliness and stability of data. For example, data quality scorecards can be used to quantify evaluation criteria, machine learning algorithms can be used to predict the performance of data sources, and simulation and historical data analysis can be used to verify their effectiveness in specific traffic scenarios). In addition, the present invention will negotiate with data service providers to establish standardized data interfaces to achieve automated data acquisition and integration, while ensuring compliance with data privacy protection regulations in the process of acquiring data, and anonymizing data.

[0048] The present invention will establish a data quality control mechanism to evaluate and verify the quality of the acquired data to ensure the accuracy and reliability of the data. At the same time, an efficient data storage and management solution will be designed to cope with the storage, indexing and retrieval needs of large-scale data. Signing a data use agreement with a data service provider to clarify the scope, authority and responsibility of data use is the key to ensuring the smooth progress of cooperation. Finally, a data update and maintenance mechanism will be established (a data update and maintenance mechanism usually refers to a set of automated processes for collecting, integrating and updating data sets regularly or in real time. This includes setting up scheduled tasks to automatically pull the latest data from the data source, using data synchronization technology to ensure data timeliness, implementing data version control to track changes, and regularly checking the integrity and consistency of the data. In addition, the maintenance mechanism may also include performance monitoring to optimize the storage system, error detection and repair processes to deal with data corruption or loss, and a logging system to track data update activities. Innovative maintenance mechanisms may integrate machine learning algorithms to predict data change trends, automatically adjust update frequency and resource allocation, or use blockchain technology to enhance the transparency and auditability of data updates) to ensure that the system can receive the latest data to adapt to real-time changes in traffic conditions. Through this series of steps, the present invention aims to build a stable, reliable and diversified data source foundation to provide strong data support for the dynamic adjustment of traffic signal cycle duration.

[0049] Step 2: Data integration and standardization;

[0050] After the data source is established, the next step is data integration and standardization to ensure the consistency and validity of the data. First, the trajectory data obtained from different service providers are integrated to build a unified data pool, which is not only convenient for centralized management, but also the basis for subsequent analysis. Next, data cleaning is performed to remove duplicate, erroneous or incomplete records in the data set to ensure the accuracy of the data. Furthermore, the integrated data is formatted to ensure that key information such as timestamp, latitude and longitude, speed, etc. are standardized in a unified format. At the same time, the data is classified according to characteristics such as vehicle type, size, driving status, and necessary annotations are made, such as traffic events, special weather conditions, etc., to provide rich contextual information for in-depth analysis. In addition, a metadata management system is established to record information such as the source, collection time, and collection method of the data to enhance the traceability of the data. During the data integration process, data consistency checks will also be implemented to ensure that the data between different data sources are logically and temporally coherent, and data security measures and privacy protection strategies will be continuously implemented to ensure the security of user information.

[0051] In order to standardize the use and sharing of data, a data access protocol will be formulated and a regular data update mechanism will be established to ensure that the data set can reflect the latest traffic conditions in a timely manner. Finally, a data quality monitoring process will be implemented to continuously evaluate the accuracy and reliability of the data and promptly correct any problems found (data access protocol, data update mechanism and data quality monitoring process are three key components to ensure data accuracy and timeliness. The data access protocol defines the rules for data use and sharing, including permission control, data request format, access frequency limit, etc., and may include innovative API gateway technology to manage data flow and ensure secure access. The data update mechanism involves automated data synchronization strategies, such as real-time stream processing or scheduled batch updates, and may use innovative time series databases to optimize the storage and retrieval of high-frequency data. The data quality monitoring process includes data anomaly detection, accuracy verification and user feedback loops, and may integrate advanced data analysis tools and machine learning models to automatically identify and respond to data quality issues. Innovations may include using blockchain technology to enhance the immutability and transparency of data, or developing adaptive algorithms to dynamically adjust data update frequency and monitoring thresholds based on real-time analysis results). Through this series of meticulous and coherent steps, the present invention will build a high-quality, standardized traffic data foundation, provide solid data support for the dynamic adjustment of traffic signal cycle duration, and thus improve the intelligence level and efficiency of traffic management.

[0052] Step 3, extracting traffic flow characteristics;

[0053] On the basis of completing data integration and standardization, step 3 of the present invention focuses on the extraction of traffic flow characteristics. Using data analysis technology, key traffic flow indicators such as vehicle flow, vehicle density and average speed are identified from the data set. Through these indicators, traffic conditions can be quantified and their changes over time can be monitored. First, by analyzing the data of vehicles passing through a specific section or intersection, the vehicle flow in different time periods can be calculated, and then the peak and non-peak periods can be identified. Then, by measuring the number of vehicles in a specific area, the vehicle density can be evaluated and possible congestion points can be found. In addition, by calculating the average speed of vehicles on a specific section of the road, traffic mobility can be understood. Further, the changing patterns of these characteristics in time series will be analyzed, such as the traffic growth trend during the morning and evening peaks, and the traffic reduction during non-peak hours. In addition, by comparing the traffic characteristics of weekdays and weekends, periodic patterns can be found. Through these analyses, the patterns and trends of traffic flow can be identified, providing a basis for the dynamic adjustment of traffic lights. For example, if it is found that the vehicle density of a certain section of the road has increased significantly during a specific time period, the corresponding signal adjustment strategy can be predicted and prepared to alleviate potential congestion.

[0054] In summary, this method aims to provide scientific and accurate data support for the intelligent management of traffic signals by extracting and analyzing the key features of traffic flow, thereby optimizing traffic flow, reducing congestion, and improving road use efficiency.

[0055] Step 4: construct a dynamic traffic model and dynamically adjust the traffic signal cycle duration;

[0056] The name of the constructed model: Dynamic Traffic Signal and Flow Prediction Model (DTSFPM)

[0057] The formula for traffic flow change is:

[0058]

[0059] Among them, λ(t) is the average rate of vehicles entering the road section through the green light at time t; μ(t) is the average speed of vehicles leaving the road section at time t, which affects the vehicle passing time;

[0060] Adjust λ(t) based on the green light duration G(t): λ(t)=k*G(t), where k is a proportional constant;

[0061] In the context of traffic signal control, a proportionality constant k is used to relate the green light duration G(t) to the vehicle entry rate λ(t), i.e., λ(t) = k·G(t)λ(t) = k·G(t). The value of this proportionality constant k usually depends on a variety of factors, including the width of the road section, the average speed of vehicles, and the expected traffic throughput. There is no uniform standard for the specific value because it is affected by local traffic conditions, road design, traffic regulations, and traffic characteristics. For example, in urban traffic, the value of k may be lower to accommodate lower speeds and more frequent stops; while on highways or suburban roads, k may be higher to accommodate higher speeds and fewer stops. If a rough range is needed, k is generally taken between 1 and 5;

[0062] The green light duration adjustment formula is:

[0063]

[0064] Among them, G(t) is the green light duration at time t, T cycle represents the duration of the signal light cycle, C is the maximum number of vehicles that the road section can accommodate; f(N(t)) is a function that adjusts the green light duration according to the traffic volume N(t) at time t to ensure that the green light duration is proportional to the traffic volume and does not exceed the road section capacity limit.

[0065] Step 4 also includes: if the traffic volume increases, recalculate the green light duration G(t) at time t according to the following formula:

[0066]

[0067] Among them, T cycle It can be dynamically adjusted according to the traffic flow N(t) at time t to adapt to traffic demand; the min function ensures that even in high traffic conditions, the green light duration will not exceed the signal light cycle duration T cycle ;

[0068] For example, if the basic signal light cycle duration is T cycle is 120 seconds, the traffic flow N(t) at time t is 50 vehicles per minute, and the road section capacity C is 200 vehicles. Then the green light duration G(t) at time t is:

[0069]

[0070] If the traffic flow N(t) increases to 60 vehicles per minute at time t, the green light duration G(t) at time t will increase accordingly while maintaining the same green light cycle duration T cycle , the consistency of road section capacity C.

[0071] In this way, the traffic light control system can flexibly adjust the green light duration and traffic light cycle duration according to real-time traffic conditions to improve traffic efficiency, reduce congestion, and adapt to changing traffic needs.

[0072] The above parameters and formulas together constitute a dynamic traffic signal and flow prediction model, which enables the model to dynamically respond and optimize traffic signal control to adapt to changing traffic conditions.

[0073] The model can be applied to real-time traffic signal control systems to respond to changes in traffic flow by dynamically adjusting the duration of traffic lights, thereby reducing congestion and improving road traffic efficiency.

[0074] The dynamic traffic signal and flow prediction model (DTSFPM) further integrates the key traffic flow features extracted in step 3, such as vehicle density and possible congestion points. In the traffic flow change formula, vehicle density is used as a regulating factor to indirectly adjust the green light duration by affecting the value of the proportional constant k. When the system detects that the vehicle density exceeds the preset threshold, the model automatically reduces the k value, thereby shortening the green light duration and reducing the influx of vehicles in the congested area. In addition, the model uses the information of possible congestion points to adjust the green light duration of relevant intersections in advance to alleviate the upcoming traffic pressure. For example, if a certain intersection is predicted to become a congestion point in the next time period, the model will increase the green light duration of the intersection to speed up vehicle circulation and prevent congestion. Through this real-time data analysis and signal light adjustment, the model can respond to the dynamic changes of traffic flow more effectively, optimize traffic flow distribution, reduce vehicle waiting time, and improve the traffic capacity of the road.

[0075] Through these steps, the present invention aims to provide a flexible and efficient method for dynamically adjusting the cycle duration of traffic signals to cope with ever-changing traffic conditions, reduce traffic congestion, and improve road traffic efficiency.

[0076] In a specific embodiment of the present invention, a method for dynamically adjusting the traffic signal cycle duration based on trajectory data is provided. After the implementation of the method of the present invention, it is expected that congestion can be alleviated by increasing the green light duration during peak hours. Although the traffic volume increases, the average speed and congestion index are improved.

[0077] (1) During off-peak hours, the green light duration should be appropriately increased to accommodate moderate traffic flow and improve road use efficiency.

[0078] (2) During nighttime, the green light duration is reduced to accommodate smaller traffic volumes and keep roads open.

[0079] The experimental prediction data are shown in Table 1.

[0080] Table 1

[0081]

[0082]

[0083] Among them, N 1 (t) represents the reference vehicle flow before the implementation of the method of the present invention; N 2 (t) represents the predicted traffic flow after optimization by the method of the present invention. According to the model prediction, the traffic flow during peak hours increases slightly, but the overall mobility is improved by optimizing the signal cycle;

[0084] G 1 (t) represents the reference green light duration before the implementation of the method of the present invention, G2 (t) represents the green light duration after optimization by the method of the present invention. According to the change of traffic flow, the green light duration increases during peak hours and decreases during night hours.

[0085] Traffic light cycle duration T cycle Remain unchanged to demonstrate the adaptability of the cycle duration to traffic changes.

[0086] The congestion index includes a baseline congestion index and an optimized congestion index. The method of the present invention is expected to reduce the congestion index and improve traffic conditions;

[0087] The average speed includes the baseline average speed and the optimized average speed. The optimized average speed is expected to increase, reflecting the improvement in traffic fluidity.

[0088] In this embodiment, the road section length L is 1 km, and the road section capacity C is 3500 vehicles (set as the traffic volume benchmark value during peak hours), then:

[0089] During peak hours, the baseline congestion index is The optimized congestion index is The average speed is The average speed after optimization is

[0090] The same method is used to calculate the congestion index and average speed for off-peak hours and night time:

[0091] During off-peak hours: the base congestion index is The optimized congestion index is The baseline average speed is 1 km / h, and the optimized average speed is about 0.96 km / h.

[0092] Nighttime: Baseline congestion index is The optimized congestion index is The baseline average speed is 1 km / h, and the optimized average speed is about 1.11 km / h.

[0093] Experimental conclusion:

[0094] Based on model variables and expected data, intelligent traffic signal optimization strategies can effectively adapt to traffic demands in different time periods, improve traffic fluidity, reduce congestion, and improve overall traffic efficiency.

[0095] Please note that these data and expected results are hypothetical and are used to illustrate the application of the model. In actual applications, detailed experimental design and data analysis are required according to specific circumstances.

[0096] The present invention provides a method for dynamically adjusting the cycle duration of a traffic signal based on trajectory data. There are many methods and ways to implement the technical solution. The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention. All components not specified in this embodiment can be implemented using existing technologies.

Claims

1. A method for dynamically adjusting the cycle duration of a traffic signal based on trajectory data, characterized in that: The following steps are involved: Step 1, determine the data source; Step 2: Data integration and standardization; Step 3, extracting traffic flow characteristics; Step 4: Build a dynamic traffic model and dynamically adjust the traffic signal cycle duration.

2. The method according to claim 1, characterized in that Step 1 includes: obtaining vehicle trajectory data through a traffic data service provider, wherein the vehicle trajectory data includes the real-time position, driving speed and driving direction of the vehicle.

3. The method according to claim 2, characterized in that In step 1, the vehicle trajectory data is anonymized.

4. The method according to claim 3, characterized in that Step 2 includes: integrating the vehicle trajectory data obtained from different traffic data service providers to build a unified data pool, formatting the integrated vehicle trajectory data to ensure that the timestamp, longitude and latitude, and speed are standardized in a unified format; at the same time, classifying and labeling the vehicle trajectory data according to vehicle type, size, and driving status; establishing a metadata management system to record the source, collection time, and collection method of the data; implementing data consistency checks to ensure that the data between different data sources are logically and temporally consistent, and continuously implementing data security measures and privacy protection strategies.

5. The method according to claim 4, characterized in that Step 3 includes: using data analysis techniques to identify key traffic flow indicators from vehicle trajectory data, including vehicle volume, vehicle density, and average speed.

6. The method according to claim 5, characterized in that In step 3, the traffic conditions are quantified and the changes of the traffic conditions over time are monitored by using the key traffic flow indicators, including: By analyzing the data of vehicles passing through a specific road section or intersection, the traffic volume in different time periods is calculated to identify peak and non-peak hours; By measuring the number of vehicles in a specific area, the vehicle density can be assessed and possible congestion points can be found; Obtain traffic mobility by calculating the average speed of vehicles on a specific road section; By comparing the traffic characteristics on weekdays and weekends, periodic patterns are obtained.

7. The method according to claim 6, characterized in that Step 4 includes: the dynamic traffic model includes: The formula for traffic flow change is: Where λ(t) is the average speed of vehicles entering the road section through the green light at time t; μ(t) is the average speed of vehicles leaving the road section at time t; N(t) represents the traffic volume on a specific road section at time t; d represents the integral sign; Adjust λ(t) based on the green light duration G(t) at time t: λ(t)=k*G(t), where k is a proportional constant; the proportional constant k is used to relate the green light duration G(t) to the vehicle entry rate λ(t), i.e., λ(t)=k·G(t)λ(t)=k·G(t); The green light duration adjustment formula is: Among them, G(t) is the green light duration at time t, T cycle represents the duration of the traffic light cycle, C is the maximum number of vehicles that the road section can accommodate; f(N(t)) is a function that adjusts the green light duration according to the traffic flow N(t) at time t.

8. The method according to claim 7, characterized in that Step 4 also includes: if the traffic volume increases, recalculate the green light duration G(t) at time t according to the following formula: Among them, T cycle It can be dynamically adjusted according to the traffic flow N(t) at time t to adapt to traffic demand.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores program codes, and when the program codes are executed by the processor, the processor executes the steps of the method according to any one of claims 1 to 8.

10. A storage medium, characterized in that: A computer program or instruction is stored, and when the computer program or instruction is run on a computer, the steps of the method according to any one of claims 1 to 8 are executed.

Images