A Smart Traffic Regulation Method and System Based on 5G Cloud Computing Terminal Technology

Abstract

The present application discloses an intelligent traffic regulation method based on 5G cloud computing terminal technology, including: using the 5G network to collect data such as traffic flow parameters, weather condition parameters, and emergency incident parameters in real time; performing fusion processing on the data of traffic flow parameters, weather condition parameters, and emergency incident parameters, and judging the comprehensive traffic state based on the fusion algorithm; and generating and applying a regulation strategy according to the traffic state, controlling traffic lights and electronic signs through 5G terminals, dynamically adjusting the traffic flow, and guiding vehicles to avoid congested areas; synchronously, using a traffic flow prediction algorithm to predict the future traffic flow; when it is predicted that the future traffic flow may exceed the road section carrying capacity, implementing dynamic speed limit adjustment.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation technologies, and more particularly to an intelligent transportation regulation method and system based on 5G cloud computing terminal technology. Background Art

[0002] With the development of urbanization, traffic pressure has been increasing day by day. Traditional traffic regulation means cannot adapt to the rapidly changing traffic conditions in modern cities and cannot quickly respond to dynamically changing traffic flows. Traditional traffic management systems usually rely on local sensors and centralized data processing centers, and there are certain delays in signal light adjustment, traffic flow guidance, etc. For complex and rapidly changing traffic conditions, traditional systems cannot make corresponding decisions within a short enough time. Most of the existing traffic management is based on predetermined rules or static models, such as fixed signal light cycles or simple traffic flow management models, and cannot respond to dynamic factors such as weather and sudden accidents in real time, resulting in a lack of flexibility in traffic control and prone to traffic jams or inefficient traffic flow management.

[0003] Therefore, the emergence of 5G technology, with its characteristics of high bandwidth, low latency, and wide coverage, combined with the super processing power of cloud computing, provides technical support for the implementation of intelligent transportation. Summary of the Invention

[0004] The purpose of this application is to provide an intelligent transportation regulation method and system based on 5G cloud computing terminal technology, through the high-speed transmission of 5G and the distributed data processing architecture of cloud computing terminals, to achieve dynamic monitoring and intelligent regulation of complex traffic conditions, improve traffic management efficiency, and reduce traffic congestion.

[0005] To achieve the above objectives, this application document provides an intelligent transportation regulation method based on 5G cloud computing terminal technology, including: using a 5G network to collect real-time data such as traffic flow parameters, weather condition parameters, and emergency event parameters; performing fusion processing on the data of traffic flow parameters, weather condition parameters, and emergency event parameters, and judging the comprehensive traffic state based on a fusion algorithm; and generating and applying a regulation strategy according to the traffic state, controlling signal lights and electronic signs through 5G terminals, dynamically adjusting traffic flow, and guiding vehicles to avoid congested areas; synchronously, using a traffic flow prediction algorithm to predict future traffic flow; when it is predicted that the future traffic flow may exceed the road section carrying capacity, implementing dynamic speed limit adjustment.

[0006] Further, the traffic flow prediction algorithm is implemented using the following formula: ; where T1 is the real-time traffic flow parameter, T2 is the predicted traffic flow value, T3 is the historical traffic flow parameter, and λ is the balance weight parameter.

[0007] Furthermore, the balance weight parameter is set to balance the influences of the current traffic flow parameter and the historical traffic flow parameter, and the value of the balance weight parameter is adjusted in real time to adapt to the changes in the traffic environment.

[0008] Preferably, the weight parameters α, β, and γ in the fusion algorithm are dynamically adjusted according to the current traffic environment. The α weight is relatively high to reflect the importance of real-time traffic flow. The β weight changes according to the weather conditions, and the γ weight is set according to the severity of emergencies.

[0009] Preferably, when the system predicts that the future traffic state reaches the congestion critical value, it sends path optimization suggestions and traffic warning notifications to vehicle drivers to guide the vehicles to detour and relieve the traffic pressure.

[0010] This application document also provides an intelligent traffic control system based on 5G cloud computing terminal technology. The system is applicable to the intelligent traffic control method based on 5G cloud computing terminal technology as described in any one of the above. The system includes: a distributed traffic data collection module and a multi-source data fusion and analysis module. Among them, the distributed traffic data collection module collects traffic flow parameters, weather condition parameters, and emergency event parameters of road sections in real time. The multi-source data fusion and analysis module performs real-time fusion processing on traffic flow, weather, and emergency event data based on the fusion algorithm to generate an evaluation result of the comprehensive traffic state.

[0011] Further preferably, the system further includes: an intelligent prediction module and a path guidance module. The intelligent prediction module generates a control plan according to the traffic flow prediction result, controls the signal light allocation duration and dynamically adjusts the signal light duration through the 5G terminal. The path guidance module realizes traffic sign guidance information and completes the speed limit and traffic diversion plan.

[0012] Further preferably, the system further includes: an edge-cloud collaborative computing module. The edge-cloud collaborative computing module dynamically distributes complex computing tasks to the cloud or edge nodes through the distributed cloud computing terminal to improve the computing efficiency of the system under high traffic loads.

[0013] Preferably, the distributed traffic data collection module collects data from multiple road sections in real time through a variety of collection devices, and uses the high-speed transmission function of the 5G network to ensure low-latency transmission of the data to the cloud for analysis and processing.

[0014] Compared with the prior art, the beneficial effects of the present application are as follows: Innovations have been made in the module composition of the system. To distinguish it from the existing traffic systems, this intelligent traffic control system not only makes innovations in hardware, but also introduces brand-new functional modules in module design, and improves the overall control ability of the system through self-developed algorithms. Among them, the distributed traffic data collection module collects data from multiple urban nodes through the 5G network, including road conditions, signal light status, vehicle speed, weather, etc. Different from the existing centralized data collection, this system collects data through multiple cloud terminal nodes in a distributed manner, and the computing load of each node is optimized through dynamic load balancing to ensure the transmission stability of data during peak periods. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic flow chart of the intelligent traffic control method based on 5G cloud computing terminal technology in the present application document. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] Next, in combination with the specific embodiments, the present application will be further described. It should be noted that, on the premise of no conflict, the following-described embodiments or technical features can be combined arbitrarily to form new embodiments.

[0017] In a preferred embodiment, referring to Figure 1 , the present application document provides an intelligent traffic control method based on 5G cloud computing terminal technology, including: Step S10 uses the 5G network to collect data such as traffic flow parameters, weather condition parameters, and emergency event parameters in real time; Step S20 fuses the data of traffic flow parameters, weather condition parameters, and emergency event parameters, and judges the comprehensive traffic state based on the fusion algorithm; Step S31 generates and applies a control strategy according to the traffic state, controls traffic lights and electronic signs through 5G terminals, dynamically adjusts the traffic flow, and guides vehicles to avoid congested areas; Step S32 Synchronously, uses a traffic flow prediction algorithm to predict the future traffic flow; Step S42 When it is predicted that the future traffic flow may exceed the road section carrying capacity, implement dynamic speed limit adjustment.

[0018] Preferably, when the system predicts that the future traffic state reaches the congestion critical value, it sends path optimization suggestions and traffic warning notifications to vehicle drivers to guide vehicles to detour and relieve traffic pressure.

[0019] This application document also provides an intelligent transportation control system based on 5G cloud computing terminal technology. The system is applicable to the intelligent transportation control method based on 5G cloud computing terminal technology as described above. The system includes: a distributed traffic data collection module and a multi-source data fusion and analysis module. Among them, the distributed traffic data collection module collects traffic flow parameters, weather condition parameters, and emergency event parameters of road sections in real time. The multi-source data fusion and analysis module performs real-time fusion processing on traffic flow, weather, and emergency event data based on a fusion algorithm to generate an evaluation result of the comprehensive traffic state.

[0020] Therefore, preferably, in the traffic data collection stage, the distributed traffic data collection module collects data from multiple road sections in real time through a variety of collection devices, and uses the high-speed transmission function of the 5G network to ensure low-latency transmission of the data to the cloud for analysis and processing.

[0021] The collection devices include monitoring cameras, vehicle-mounted sensors, road surface sensing devices, etc. installed on each road section, which collect traffic flow data, vehicle types, vehicle speeds and other information in real time. Through the low-latency transmission of the 5G network, all the collected data is uploaded to the 5G cloud computing terminal in real time.

[0022] Further preferably, the system further includes: an intelligent prediction module and a path guidance module. The intelligent prediction module generates a control plan according to the traffic flow prediction result, controls the signal light allocation time and dynamically adjusts the signal light time through the 5G terminal. The path guidance module realizes traffic sign guidance information and completes the speed limit and traffic diversion plan.

[0023] Further preferably, the system further includes: an edge-cloud collaborative computing module. The edge-cloud collaborative computing module dynamically distributes complex computing tasks to the cloud or edge nodes through a distributed cloud computing terminal, improving the computing efficiency of the system under high traffic load.

[0024] Therefore, innovation has been made in the module composition of the system. In order to distinguish it from the existing traffic system, this intelligent transportation control system not only makes innovations in hardware, but also introduces brand-new functional modules in module design, and improves the overall control ability of the system through self-developed algorithms. Among them, the distributed traffic data collection module collects data from multiple urban nodes through the 5G network, including road conditions, signal light status, vehicle speed, weather, etc. Different from the existing centralized data collection, this system distributes data collection through multiple cloud terminal nodes, and the computing load of each node is optimized through dynamic load balancing to ensure the transmission stability of data during peak periods.

[0025] The multi-source data fusion and analysis module transmits multi-source data (such as traffic flow, lane occupancy rate, real-time events, weather conditions, etc.) to the cloud server through the 5G network, and performs data cleaning, integration and analysis. It not only simply processes a single data source, but also incorporates complex data such as weather changes and major events into the analysis scope. Combining with the ultra-high-speed data transmission of 5G, the system can fuse these data within milliseconds and generate instant regulation suggestions. Further, in the intelligent prediction and regulation module, through intelligent algorithms based on distributed computing, the future traffic conditions are predicted, and facilities such as traffic lights and electronic billboards are adjusted in real time to guide the traffic flow and reduce traffic jams. Different from traditional regulation methods, the system combines the low-latency characteristics of 5G, can process tens of billions of data points in real time, and based on innovative algorithms, anticipates traffic congestion points and conducts instant regulation. The innovative algorithms include fusion algorithms and traffic flow prediction algorithms.

[0026] In the edge-cloud collaborative computing module, based on the distributed architecture of cloud computing, the system dynamically distributes computing tasks to edge nodes and cloud terminals to achieve faster response. Combining with the edge computing technology of 5G, the system can dynamically determine the best execution location of computing tasks, reducing the computing pressure on the central server, which is particularly effective when the road network scale is large or the data is intensive.

[0027] Further, the fusion algorithm is implemented based on the following formula: ;

[0028] Where D is the traffic state evaluation result, T1 is the real-time traffic flow parameter, W is the weather condition parameter, such as applied to rainfall and temperature, E is the emergency parameter, such as applied to accidents and closed roads, and α, β, γ are weight parameters dynamically adjusted according to traffic conditions.

[0029] Preferably, the weight parameters α, β, γ in the fusion algorithm are dynamically adjusted according to the current traffic environment. The α weight is higher to reflect the importance of real-time traffic flow, the β weight changes according to weather conditions, and the γ weight is set according to the severity of emergencies.

[0030] Among them, in a specific application scenario, the traffic state within a unit time t is evaluated. The unit time t can be set differently according to different actual application scenarios, preferably ranging from 30 minutes to 60 minutes. Therefore, within a unit time t, the unit time t is preferably 60 minutes. In a traffic management system in a certain city, the following data is collected: the current traffic flow parameter T1 is 500 vehicles per hour, the weather state parameter W is 0.8, the value range of the weather state parameter is from 0 to 1, and 0.8 represents moderate rainfall. The emergency event parameter E is 1, and a value of 1 indicates that an accident has occurred. Therefore, according to the above situation, the system sets the weight parameters as α = 0.6, β = 0.2, γ = 0.2. According to the fusion algorithm formula, the current traffic state evaluation result D is then 0.6×500 + 0.2×0.8 + 0.2×1 = 300 + 0.16 + 0.2 = 300.36. Therefore, the current traffic flow is relatively high, and there are bad weather and accidents, and traffic congestion is expected to occur.

[0031] Among them, it should be noted that traffic flow, weather, and traffic accidents are the main factors affecting traffic conditions. Therefore, the value of α is set to 0.6 because traffic flow is the most important factor affecting traffic conditions and has a higher proportion. The value of β is 0.2, representing the influence of the weather. Although the weather has a greater impact on traffic, its weight is slightly lower compared to traffic flow. The value of γ is 0.2, representing the influence of emergency events (such as traffic accidents). Although severe emergencies may cause congestion, their occurrence frequency is relatively low, so the weight is set to 20%. Dynamic adjustment means that the system can flexibly adjust these parameters according to different traffic conditions. For example, in extreme weather (such as heavy rain), the weight of β may increase, while in sunny weather, the weight of α may increase, reflecting the system's adaptability to actual environmental changes. Therefore, in a preferred embodiment, when W takes the value of 0, it means that the weather condition is ideal and has no negative impact on traffic. When W takes the value of 0.5, it means slight rainfall and has a certain impact on traffic flow. When the weather is extremely bad and has a great impact on traffic flow and safety, W takes the value of 1. Regarding the above traffic state evaluation result D, the calculated result of 300.36 represents the current comprehensive traffic state, which takes into account the comprehensive influence of traffic flow, weather, and emergency events. This result indicates that the traffic condition of this section has reached a relatively high load level and may face traffic congestion. Generally, if the calculated value of the traffic state evaluation result D exceeds a certain critical value, preferably 300 in this embodiment, it indicates that the traffic volume carried by the section is relatively large, and combined with the current weather and accident impacts, the system predicts that congestion may occur in a short time. The system will make a further judgment in combination with the traffic flow prediction algorithm.

[0032] Furthermore, the traffic flow prediction algorithm is implemented using the following formula: ; where, T1 is the real-time traffic flow parameter, which is also the real-time traffic flow within a unit time t as described above. t is preferably 60 minutes. T2 is the predicted traffic flow value, and T3 is the historical traffic flow parameter, representing the traffic flow at the same historical moment, preferably the traffic flow 60 minutes ago. λ is the balance weight parameter.

[0033] Furthermore, the balance weight parameter is set to balance the influence of the current traffic flow parameter and the historical traffic flow parameter, and the value of the balance weight parameter is adjusted in real time to adapt to the changes in the traffic environment.

[0034] Among them, when the real-time traffic flow parameter T1 within a unit time t is detected to be 500 vehicles per hour and the historical traffic flow parameter T3 is 450 vehicles per hour, the balance weight parameter is preferably set to 0.7, indicating that the system is more inclined to use the current real-time traffic flow for prediction, and the importance of historical data is relatively low.

[0035] Therefore, the predicted traffic flow value for the next 60 minutes is calculated as T2 = 0.7×500 + (1 - 0.7)×450 = 485 vehicles per hour, indicating that the future traffic flow will decrease.

[0036] Among them, when λ is set to 0.7, it means that the current traffic flow is more important for future traffic flow prediction than historical data. For example, in the previous unit time, λ was set to 0.3 corresponding to historical data. The setting of λ reflects the balance of the system between real-time and historical rules. For example, during peak hours when real-time traffic flow dominates, the system is more inclined to make predictions based on the current traffic flow; while during off-peak hours or relatively stable periods, the weight of historical traffic flow data may be higher. The system uses λ to determine whether to rely more on current real-time data or historical data. A larger value of λ indicates that real-time data is the main reference, and a lower value of λ indicates that the system refers to historical trends.

[0037] Furthermore, the future traffic conditions are predicted based on the predicted traffic flow value, and control suggestions are given. For example, if the predicted traffic flow value far exceeds the current traffic flow value, the system will take measures in advance, such as diverting vehicles.

[0038] Therefore, in this embodiment, when λ is set to 0.7, it means that the system focuses more on the influence of current traffic data and the influence of historical data is relatively small. If λ is set to 0.5 in another implementation, it means that the system regards the current traffic flow and historical traffic flow as equally important. The predicted result of future traffic flow can be used for signal light control schemes and guiding driver route planning to prevent traffic congestion.

[0039] Furthermore, in order to implement a more intelligent traffic control system, the present application further introduces a traffic congestion risk assessment method. The traffic congestion risk assessment method comprehensively relies on the calculation results of the above-mentioned traffic state fusion formula and traffic flow prediction formula, and is then used to evaluate the congestion risk of a specific road section, and further determine the signal light duration adjustment and traffic flow guidance strategy.

[0040] The traffic congestion risk assessment formula is as follows: , where R represents the predicted traffic congestion risk assessment value per unit time period. The reference value of R is preferably set to 350. If the calculation result is greater than the reference value, it indicates that the traffic assessment per unit time period is not congested. If the calculation result is less than the reference value, it indicates that the traffic is congested during the unit time period. κ represents the sensitivity factor of the traffic control system, which is used to adjust the amplification or reduction effect of the assessment result. D represents the comprehensive traffic state at the current moment, which is calculated by the preposed fusion algorithm. T2 is the predicted future traffic flow, which is obtained from the preposed traffic flow prediction formula. C represents the designed carrying capacity of the road section, that is, the maximum traffic volume that the road section can withstand per unit time. E represents the severity parameter of the current unexpected event, such as the impact of a traffic accident, and its value range is from 0 to 1. A higher value indicates that the unexpected event is more serious. ε represents the adjustment factor for amplifying the impact of the unexpected event, which amplifies the impact of the event on the traffic risk. In a specific embodiment, D takes the value of 300.36, T2 takes the value of 485 vehicles per hour, the designed carrying capacity C of the road section takes the value of 600 vehicles per hour, indicating the maximum passing capacity of the road section. The current unexpected event parameter E takes the value of 0.3, indicating that there is a construction situation on a certain road section. The adjustment factor ε takes the value of 1.1, and the accident impact is small. The sensitivity factor κ takes the value of 1.2. Substituting into the calculation, we get 1.2×300.36×485 / 600×(1 + 0.3×1.1), and the calculated value of R is approximately 219. Therefore, the calculation result indicates that the traffic congestion risk of this road section after 60 minutes is relatively high, and a relatively high congestion situation may occur. Therefore, since the assessment result shows that the road section will be congested in a short time, based on this assessment result, the system will immediately take measures, such as adjusting the signal light timing, guiding vehicles to avoid this road section through dynamic traffic signs, diverting the traffic flow, and reducing the congestion risk. Therefore, based on the current risk assessment result, the system decides to further optimize the signal light timing and reduce the green light time of the road section to reduce the number of new vehicle flows entering. The traffic flow guidance can send path adjustment suggestions in real time through the 5G network, suggesting that drivers detour to other road sections and reducing the traffic volume entering the road section. The early warning release can send an early warning to the municipal management department through the system using the 5G network, prompting for early intervention to prevent the aggravation of potential congestion.

[0041] The basic principles, main features and advantages of the present application have been described above. Those skilled in the art should understand that the present application is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present application. Without departing from the spirit and scope of the present application, various changes and improvements will occur to the present application, and these changes and improvements all fall within the scope of the present application claimed. The scope of protection required by the present application is defined by the appended claims and their equivalents.

Claims

1. A smart traffic control method based on 5G cloud computing terminal technology, characterized in that, Including: Collecting data on traffic flow parameters, weather condition parameters, and emergency incident parameters in real time using a 5G network; Fusing the data of the traffic flow parameters, the weather condition parameters, and the emergency incident parameters, and judging the comprehensive traffic state based on a fusion algorithm; The fusion algorithm is implemented based on the following formula: ; where D is the comprehensive traffic state at the current moment, T1 is the real-time traffic flow parameter, and W is the weather condition parameter; the weight parameters α, β, and γ in the fusion algorithm are dynamically adjusted according to the current traffic environment. The α weight is relatively high to reflect the importance of real-time traffic flow. The β weight changes according to the weather condition, and the γ weight is set according to the severity of emergencies; Generating and applying a control strategy according to the traffic state, controlling traffic lights and electronic signs through 5G terminals, dynamically adjusting the traffic flow, and guiding vehicles to avoid congested areas; Synchronously, a future traffic flow is predicted using a traffic flow prediction algorithm; the traffic flow prediction algorithm is implemented using the following formula: ; Among them, T1 is the real-time traffic flow parameter, T2 is the predicted future traffic flow, T3 is the historical traffic flow parameter, and λ is the calculation of the balance weight parameter; When it is predicted that the future traffic flow exceeds the road section's carrying capacity, dynamic speed limit adjustment is implemented; Adopt a traffic congestion risk assessment method to evaluate the congestion risk of a specific section, and further determine the signal light duration adjustment and traffic flow guidance strategy. The traffic congestion risk assessment formula is as follows: , where R represents the predicted traffic congestion risk assessment value per unit time period; κ represents the sensitivity factor of the traffic control system, which is used to adjust the amplification or reduction effect of the assessment result, C represents the designed carrying capacity of the section, that is, the maximum traffic volume that the section can bear per unit time, and E represents the severity parameter of the current emergency event.

2. The intelligent traffic control method based on 5G cloud computing terminal technology according to claim 1, characterized in that The setting of the balance weight parameter is to balance the influence of the real-time traffic flow parameter and the historical traffic flow parameter, and the value of the balance weight parameter is adjusted in real time to adapt to the change of the traffic environment.

3. The intelligent traffic control method based on 5G cloud computing terminal technology according to claim 2, characterized in that When the system predicts that the future traffic state reaches the congestion critical value, a path optimization suggestion and a traffic warning notice are sent to vehicle drivers to guide the vehicles to bypass and relieve the traffic pressure.

4. A smart traffic control system based on 5G cloud computing terminal technology, characterized in that, The system is applicable to the intelligent traffic control method based on 5G cloud computing terminal technology as described in any one of claims 1-3. The system includes: A distributed traffic data collection module and a multi-source data fusion and analysis module; Among them, the distributed traffic data collection module collects traffic flow parameters, weather condition parameters, and emergency incident parameters of road sections in real time; The multi-source data fusion and analysis module performs real-time fusion processing on traffic flow, weather, and emergency incident data based on a fusion algorithm to generate an evaluation result of the comprehensive traffic state.

5. The intelligent transportation control system based on 5G cloud computing terminal technology according to claim 4, characterized in that, The system further includes: An intelligent prediction module and a path guidance module. The intelligent prediction module generates a control plan according to the traffic flow prediction result, controls the signal light matching duration and dynamically adjusts the signal light duration through 5G terminals, and the path guidance module realizes traffic sign guidance information to complete the speed limit and traffic diversion plan.

6. The intelligent transportation control system based on 5G cloud computing terminal technology according to claim 5, characterized in that, The system further includes: An edge-cloud collaborative computing module. The edge-cloud collaborative computing module dynamically distributes complex computing tasks to the cloud or edge nodes through a distributed cloud computing terminal to improve the computing efficiency of the system under high traffic load.

7. The intelligent traffic control system based on 5G cloud computing terminal technology according to claim 4, characterized in that The distributed traffic data collection module collects data from multiple road sections in real time through a variety of collection devices, and uses the high-speed transmission function of the 5G network to ensure low-latency transmission of the data to the cloud for analysis and processing.

Images