Intelligent jamming alleviating system based on big data analysis

Abstract

The present application relates to the technical field of road vehicle control, and especially relates to an intelligent congestion alleviating system based on big data analysis. The system comprises: an information collection module, which is used to collect road information, driving information and vehicle information of a characteristic road section through a traffic gantry; a road analysis module, which is used to calculate vehicle density and statistical convergence time of convergence quantity of red light period; a target selection module, which is used to generate vehicle characteristic values to select target vehicles; and a characteristic analysis module, which comprises a congestion analysis unit used to determine whether the characteristic road section is a congestion road section based on vehicle density and the number of target vehicles in a single green light period, and generate a congestion characteristic value, and a congestion prediction unit used to generate a predicted congestion road section based on the congestion characteristic value and the convergence time. The present application utilizes the cooperation of the above modules to effectively improve the efficiency of detecting road congestion, and further improve the accuracy of the intelligent congestion alleviating system based on big data analysis.

Description

Technical Field

[0001] This invention relates to the field of road vehicle control technology, and in particular to an intelligent congestion mitigation system based on big data analysis. Background Technology

[0002] In recent years, most cities around the world have faced the challenge of low vehicle speeds during peak hours. When vehicles approach intersections, traffic light adjustments and the merging or merging of vehicles from different directions can easily lead to congestion. Traditional methods, such as signal timing based on human experience and police intervention, are no longer sufficient to cope with dynamically changing traffic flows. Congestion causes vehicles to frequently start and stop, resulting in CO and HC emission concentrations that are 2-5 times higher than when driving at a constant speed. Traditional governance methods struggle to balance efficiency improvement with environmental goals. Dynamically adjusting the green ratio based on prediction results can reduce the intersection delay index.

[0003] Chinese Patent Application Publication No. CN114512010A discloses a vehicle guidance system and device suitable for easing traffic congestion. This invention includes a big data analysis system for congestion-prone sections, a video monitoring module for easily congested areas, and an automatic traffic control system for congestion-prone sections. The system sets congestion thresholds and calculates the length of the congestion and the average vehicle speed using video data acquired by the camera in the easily congested area video monitoring module. If both the congestion length and average vehicle speed reach the congestion threshold, the automatic traffic control system for the congestion-prone section is activated, sending a command signal to the traffic control system in that area. The traffic control system then causes merging vehicles to stop entering the congested area and vehicles behind to stop and be prompted to turn off their engines until there is a 1-2 kilometer stretch of unobstructed road ahead, at which point merging or following vehicles are gradually allowed to proceed. This effectively avoids the stop-and-go crawling state of vehicles during congestion, reducing exhaust emissions, saving fuel, and increasing braking time.

[0004] However, the above method has the following problems: it fails to accurately identify and effectively regulate congestion in characteristic road sections near traffic intersections that are prone to congestion. Summary of the Invention

[0005] To address this issue, the present invention provides an intelligent congestion mitigation system based on big data analysis, which overcomes the problem in existing technologies that fail to accurately identify and effectively regulate congestion in characteristic road sections near traffic intersections.

[0006] To achieve the above objectives, the present invention provides an intelligent congestion mitigation system based on big data analysis, comprising:

[0007] The information collection module is used to collect road information, driving information and vehicle information of characteristic road sections through the traffic gantry. The road information includes the total number of vehicles and the traffic volume. The driving information includes the average speed of vehicles and the exhaust gas concentration of target vehicles. The vehicle information includes the number of times vehicle taillights flash and the number of times vehicles change lanes.

[0008] The road analysis module, which is connected to the information collection module, is used to divide the vehicle traffic volume into green light cycle traffic volume and red light cycle convergence volume in combination with traffic lights, calculate vehicle density based on the total number of vehicles and the green light cycle traffic volume, and count the convergence time of the red light cycle convergence volume.

[0009] The target selection module is connected to the information acquisition module and is used to generate vehicle feature values ​​based on the number of flashes of the vehicle's taillights and the number of times the vehicle changes lanes to select target vehicles.

[0010] The feature analysis module is connected to the road analysis module and the target selection module respectively. It includes a congestion analysis unit for determining whether a feature road segment is a congested road segment based on the vehicle density and the number of target vehicles in a single green light cycle and generating a congestion characterization value, and a congestion prediction unit for generating a predicted congested road segment based on the congestion characterization value and the convergence time.

[0011] The scheduling module is connected to the information acquisition module and the feature analysis module respectively, and includes a first adjustment unit for adjusting the number of vehicles merging into the feature road segment based on the exhaust gas concentration, and a second adjustment unit for adjusting the green light cycle length based on the number of vehicles merging into the predicted congested road segment.

[0012] The characteristic road segment is the road between the traffic gantry and the next intersection in the direction of vehicle travel.

[0013] Furthermore, the target selection module selects target vehicles based on vehicle feature values, wherein,

[0014] Vehicles whose vehicle characteristic value is greater than or equal to a preset characteristic value are set as target vehicles, and the preset characteristic value is positively correlated with the number of lanes in the characteristic road segment.

[0015] Furthermore, the information collection module is used to collect the total number of vehicles and average speed entering the characteristic road segment through the traffic gantry, wherein,

[0016] Used to generate a predicted congestion coefficient based on the total number of vehicles and the average vehicle speed;

[0017] This is used to issue a signal to select a target vehicle based on the predicted congestion coefficient.

[0018] Furthermore, the congestion analysis unit is used to compare the vehicle density with a preset density, and determine the congestion level of the characteristic road segment based on the comparison result, wherein,

[0019] The preset density is positively correlated with the number of lanes in the characteristic road segment, and the congestion level includes a first congestion level and a second congestion level.

[0020] Furthermore, the congestion analysis unit is used to determine whether a characteristic road segment of the second congestion level is a congested road segment based on the number of target vehicles in a single green light cycle.

[0021] Furthermore, the road analysis module is used to calculate vehicle density based on the total number of vehicles and the traffic volume during the green light cycle, wherein,

[0022] Used to obtain the total number of vehicles located in the characteristic road segment at the end of the red light cycle;

[0023] Used to obtain the traffic volume of the green light cycle in the next green light cycle of the red light cycle;

[0024] The percentage of traffic volume during the green light cycle relative to the total number of vehicles is denoted as the vehicle density.

[0025] The green light cycle traffic volume refers to the number of vehicles that pass through the stop line within a single green light cycle.

[0026] Furthermore, the congestion prediction unit compares the congestion characteristic value with a preset congestion value, and determines, based on the comparison result, whether the intersection behind the congested road segment is a congested intersection.

[0027] The intersection behind is the intersection that connects to the blocked section of road along the direction of vehicle travel.

[0028] Furthermore, the congestion prediction unit is used to designate the road segments following the congested intersections where the red light cycle accumulation time is less than or equal to a preset time as predicted congested road segments.

[0029] The convergence time is the time it takes for vehicles to converge to maximum capacity in a characteristic road segment within a single red light cycle.

[0030] Furthermore, the first adjustment unit adjusts the number of vehicles merging into the characteristic road segment based on the ratio of the exhaust gas concentration to a preset concentration.

[0031] The preset concentration is positively correlated with the number of lanes in the characteristic road segment.

[0032] Furthermore, the second adjustment unit is used to adjust the green light cycle length of the congested intersection based on the number of merging vehicles in each predicted congested road segment connected to the congested intersection.

[0033] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention collects vehicle information near intersections prone to congestion by using a traffic gantry system located close to the intersection. Through classification and analysis of traffic volume during different green light cycles and convergence volume during red light cycles, it can effectively characterize the congestion situation at the intersection. The deployment characteristics of the traffic gantry system near the intersection allow it to directly collect core information of vehicles about to enter the intersection. At the same time, the high-frequency acquisition of the gantry system can capture in real time the dynamic process of continuous vehicle convergence during red light cycles and rapid vehicle passage during green light cycles. Based on the analysis of traffic volume during different green light cycles and convergence volume during red light cycles, this invention avoids the mechanical nature of traditional average timing based on historical data and ignores real-time traffic flow fluctuations. This makes the signal optimization of the intelligent congestion mitigation system more closely match the actual state of the intersection. This method can significantly improve the system's prediction accuracy, targeted control, and scenario adaptability for intersection congestion, effectively reduce the duration of congestion, improve intersection traffic efficiency and flow, and effectively improve the accuracy of the intelligent congestion mitigation system based on big data analysis.

[0034] Furthermore, this invention selects target vehicles in characteristic road segments by combining vehicle driving characteristics, such as the number of taillight flashes and lane changes. Since some vehicles frequently accelerate and decelerate to overtake and cut in during congestion, monitoring target vehicles can reflect the driving status of vehicles in characteristic road segments. At the same time, by combining the total number of vehicles entering the characteristic road segment and the average vehicle speed, the traffic flow situation in the characteristic road segment can be effectively monitored, avoiding misjudgments caused by intelligent congestion mitigation systems that only look at traffic flow and not behavior. Aggressive driving behaviors of vehicles, such as frequent flashing and lane changes, are signals of congestion spread. When some vehicles start cutting in and frequently decelerating and accelerating, it will trigger a chain reaction of following vehicles, usually forming regional congestion. By monitoring these characteristics of target vehicles, the system can realize congestion warnings. Macro traffic flow data determines the direction of control, while the driving characteristics of target vehicles can refine the control methods, making the control of the intelligent congestion mitigation system more in line with the actual traffic flow situation, further improving the accuracy of the intelligent congestion mitigation system based on big data analysis.

[0035] Furthermore, this invention analyzes vehicle density to classify congestion levels of characteristic road segments, accurately determining whether congestion in a characteristic road segment is a temporary, self-regulating blockage or a severe blockage requiring intervention. Simultaneously, it determines whether a characteristic road segment of the second congestion level is a congested segment based on the number of target vehicles in a single green light cycle. It can assess the congestion situation by observing target vehicles appearing in congested road segments and predict congestion in connecting road segments by analyzing the congestion situation at intersections following congested road segments. Vehicle density is a core indicator reflecting road segment load; analyzing it to classify congestion levels allows for precise differentiation between temporary fluctuations and severe congestion. This density-based classification avoids the limitations of traditional methods relying solely on average vehicle speed, enabling the system to accurately determine whether intervention is necessary, reducing over-regulation or delayed regulation, and further improving the accuracy of intelligent congestion mitigation systems based on big data analysis.

[0036] Furthermore, this invention adjusts the number of vehicles merging into the characteristic road segment based on exhaust gas concentration. The exhaust gas concentration characterizes the vehicle congestion situation on the characteristic road segment, and the number of merging vehicles is adjusted accordingly. Simultaneously, based on the number of merging vehicles, the green light cycle length at congested intersections is adjusted. Frequent vehicle starts and stops during congestion lead to incomplete combustion, thus quantifying and verifying the degree of congestion. Exhaust gas concentration data can serve as an environmental feedback indicator of the control effect, forming a closed loop with traditional efficiency feedback indicators, further improving the accuracy of the intelligent congestion mitigation system based on big data analysis. Attached Figure Description

[0037] Figure 1 This is a structural block diagram of the intelligent congestion mitigation system based on big data analysis of the present invention;

[0038] Figure 2 This is a schematic diagram of the traffic gantry structure according to an embodiment of the present invention;

[0039] Figure 3 A logic diagram of the target vehicle selected for an embodiment of the present invention;

[0040] Figure 4 This is a logic diagram for determining a blocked intersection according to an embodiment of the present invention;

[0041] Among them, 1. Traffic gantry; 2. Blocked intersections; 3. Characteristic road sections; 4. Predicted congested road sections; 5. Vehicle travel direction. Detailed Implementation

[0042] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0043] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0044] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0045] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0046] Please see Figure 1 The diagram shown is a structural block diagram of the intelligent congestion mitigation system based on big data analysis according to the present invention. An embodiment of the present invention provides an intelligent congestion mitigation system based on big data analysis, comprising:

[0047] The information collection module is used to collect road information, driving information and vehicle information of characteristic road sections through the traffic gantry. The road information includes the total number of vehicles and the traffic volume. The driving information includes the average speed of vehicles and the exhaust gas concentration of the target vehicle. The vehicle information includes the number of times the vehicle's taillights flash and the number of times the vehicle changes lanes.

[0048] The road analysis module, which is connected to the information collection module, is used to combine traffic lights to divide vehicle traffic volume into green light cycle traffic volume and red light cycle convergence volume. Based on the total number of vehicles and green light cycle traffic volume, it calculates vehicle density and counts the convergence time of red light cycle convergence volume.

[0049] The target selection module, which is connected to the information acquisition module, is used to generate vehicle feature values ​​based on the number of times the vehicle's taillights flash and the number of times the vehicle changes lanes in order to select target vehicles.

[0050] The feature analysis module is connected to the road analysis module and the target selection module respectively. It includes a congestion analysis unit for determining whether a feature road segment is a congested road segment based on vehicle density and the number of target vehicles in a single green light cycle and generating a congestion characterization value, and a congestion prediction unit for generating a prediction of congested road segments based on the congestion characterization value and the convergence time.

[0051] The scheduling module is connected to the information acquisition module and the feature analysis module respectively. It includes a first adjustment unit for adjusting the number of vehicles merging into the characteristic road segment based on the exhaust gas concentration, and a second adjustment unit for adjusting the green light cycle length based on the predicted number of vehicles merging into the congested road segment.

[0052] Among them, the characteristic road section is the road between the traffic gantry and the next intersection in the direction of vehicle travel.

[0053] It is understandable that the number of times a vehicle's taillights flash is the same as the number of times its brake lights illuminate.

[0054] Please see Figure 2 As shown, it is a structural schematic diagram of a traffic gantry frame according to an embodiment of the present invention, wherein,

[0055] Traffic gantry 1 is set behind the vehicle entering the blocked intersection 2 along the vehicle's direction of travel 5; characteristic road section 3 is located between traffic gantry 1 and blocked intersection 2; predicted blocked road section 4 is located in front of the vehicle exiting the blocked intersection 2 along the vehicle's direction of travel 5.

[0056] Specifically, this invention collects vehicle information near intersections prone to congestion using traffic gantries positioned close to the intersection. By classifying and analyzing traffic volume during different green light cycles and convergence volume during red light cycles, it effectively characterizes intersection congestion. The gantries' close proximity to intersections allows them to directly collect core information about vehicles about to enter the intersection. Simultaneously, the high-frequency acquisition by the gantries captures in real-time the dynamic process of continuous vehicle convergence during red lights and rapid vehicle passage during green lights. Based on the analysis of traffic volume during different green light cycles and convergence volume during red light cycles, this invention avoids the mechanical approach of traditional methods that average historical data for timing, ignoring real-time traffic flow fluctuations. This makes the signal optimization of the intelligent congestion mitigation system more closely aligned with the actual state of the intersection. This method significantly improves the system's accuracy in predicting intersection congestion, its targeted control, and its adaptability to different scenarios, effectively reducing congestion duration, improving intersection efficiency and traffic flow, and significantly enhancing the accuracy of intelligent congestion mitigation systems based on big data analysis.

[0057] Please see Figure 3 As shown, this is a logic diagram of the target vehicle selection in an embodiment of the present invention. The target selection module selects the target vehicle based on vehicle feature values, wherein...

[0058] Vehicles with a characteristic value greater than or equal to a preset characteristic value are set as target vehicles. The preset characteristic value is positively correlated with the number of lanes in the characteristic road segment.

[0059] The target selection module compares the vehicle feature value with the preset feature value. If the vehicle feature value is greater than or equal to the preset feature value, the vehicle corresponding to the vehicle feature value is set as the target vehicle.

[0060] If the vehicle feature value is less than the preset feature value, then the vehicle corresponding to the vehicle feature value is determined to be a non-target vehicle.

[0061] Specifically, the vehicle characteristic value is determined by the number of times the vehicle's taillights flash and the number of times the vehicle changes lanes. The vehicle characteristic value is calculated as follows: Vehicle characteristic value = ax = number of times the vehicle's taillights flash + bx = number of times the vehicle changes lanes. Here, a is the weight of the number of flashes and b is the weight of the number of lane changes. Since lane changes have a more significant impact on traffic flow, a = 0.2 and b = 0.8 are generally used. The units for the number of times the vehicle's taillights flash and the number of times the vehicle changes lanes are times per minute. Only the numerical values ​​are used when calculating the above formula.

[0062] In one specific embodiment, a preset feature value is set to 1.8. If the vehicle feature value is 3.4, which is greater than the preset feature value, then it is determined that the vehicle corresponding to the vehicle feature value is set as the target vehicle.

[0063] If the vehicle feature value is 0.9, which is less than the preset feature value, then the vehicle corresponding to the vehicle feature value is determined to be a non-target vehicle.

[0064] It is understandable that the number of lanes in a characteristic road segment refers to the number of one-way lanes adjacent to the intersection on that segment. The more lanes a characteristic road segment has, the more times vehicles will change lanes near the intersection to pass through it as quickly as possible. Therefore, the preset characteristic value is positively correlated with the number of lanes in the characteristic road segment. Preferably, the preset characteristic value ranges from 0.4 to 2.5.

[0065] Specifically, the information collection module is used to collect the total number of vehicles entering the characteristic road segment through the traffic gantry and the average vehicle speed.

[0066] Used to generate a predicted congestion coefficient based on the total number of vehicles and average vehicle speed;

[0067] It is used to send a signal to select a target vehicle based on the predicted congestion coefficient.

[0068] Specifically, the predicted congestion coefficient = c x total number of vehicles + d x average vehicle speed, where the total number of vehicles is in vehicles and the average vehicle speed is in kilometers per hour. c is the weight of the total number of vehicles and d is the weight of the average vehicle speed. Since the total number of vehicles and the average vehicle speed have equally important effects on congestion, c = 0.5 and d = 0.5 are generally taken. Only the numerical values ​​are used when calculating the above formula.

[0069] Specifically, the predicted congestion coefficient is compared with the preset congestion coefficient. If the predicted congestion coefficient is greater than or equal to the preset congestion coefficient, a signal to select the target vehicle is issued.

[0070] If the predicted congestion coefficient is less than the preset congestion coefficient, then it is determined that no signal to select the target vehicle will be issued.

[0071] In one specific embodiment, a preset congestion coefficient is set to 20. If the predicted congestion coefficient is 27, which is greater than the preset congestion coefficient, then a signal to select a target vehicle is issued.

[0072] If the predicted congestion coefficient is 14, which is less than the preset congestion coefficient, then it is determined that no signal to select the target vehicle will be issued.

[0073] Specifically, the preset congestion coefficient is positively correlated with the number of lanes in the characteristic road segment.

[0074] It is understandable that the more lanes a characteristic road segment has, the more vehicles it can accommodate, and the faster the vehicle speed, assuming the segment length is constant. Therefore, the preset congestion coefficient is positively correlated with the number of lanes in the characteristic road segment. Preferably, the preset congestion coefficient ranges from 15 to 25.

[0075] Specifically, this invention selects target vehicles in characteristic road segments by combining vehicle driving characteristics, such as the number of taillight flashes and lane changes. Since some vehicles frequently accelerate and decelerate to overtake and cut in during congestion, monitoring target vehicles can reflect the driving status of vehicles in characteristic road segments. At the same time, by combining the total number of vehicles entering the characteristic road segment and the average speed, the traffic flow situation in the characteristic road segment can be effectively monitored, avoiding misjudgments caused by intelligent congestion mitigation systems that only look at traffic flow and not behavior. Aggressive driving behaviors of vehicles, such as frequent flashing and lane changes, are signals of congestion spread. When some vehicles start cutting in and frequently decelerating and accelerating, it will trigger a chain reaction of following vehicles, usually forming regional congestion. By monitoring these characteristics of target vehicles, the system can realize congestion warnings. Macro traffic flow data determines the direction of control, while the driving characteristics of target vehicles can refine the control methods, making the control of the intelligent congestion mitigation system more in line with the actual traffic flow situation, and further improving the accuracy of the intelligent congestion mitigation system based on big data analysis.

[0076] Specifically, the congestion analysis unit compares vehicle density with a preset density and determines the congestion level of a characteristic road segment based on the comparison result.

[0077] If the vehicle density is less than the preset density, the congestion level of the characteristic road segment is determined to be the first congestion level.

[0078] If the vehicle density is greater than or equal to the preset density, the congestion level of the characteristic road segment is determined to be the second congestion level.

[0079] In one specific embodiment, the preset density is set to 150%. If the vehicle density is 100%, which is less than the preset density, the congestion level of the characteristic road segment is determined to be the first congestion level.

[0080] If the vehicle density is 240%, which is greater than the preset density, then the congestion level of the characteristic road segment is determined to be the second congestion level.

[0081] The preset density is positively correlated with the number of lanes in the characteristic road segment, and the congestion level includes the first congestion level and the second congestion level.

[0082] It is understandable that, given a constant vehicle speed, the more lanes a characteristic road segment has, the more vehicles can pass through in a single green light cycle. Since the characteristic road segment is relatively short, the number of vehicles passing through is generally greater than the total number of vehicles within that segment, thus preventing congestion. Therefore, the preset density is positively correlated with the number of lanes in the characteristic road segment. Preferably, the preset density ranges from 100% to 200%.

[0083] Specifically, the congestion analysis unit is used to determine whether a characteristic road segment of the second congestion level is a congested road segment based on the number of target vehicles in a single green light cycle.

[0084] Specifically, if the number of target vehicles in a single green light cycle is zero, the congestion analysis unit determines whether the characteristic road segment of the second congestion level is a congested road segment.

[0085] Specifically, the road analysis module is used to calculate vehicle density based on the total number of vehicles and the traffic volume during the green light cycle.

[0086] Used to obtain the total number of vehicles located in the characteristic road segment at the end of the red light cycle;

[0087] Used to obtain the traffic volume during the green light cycle in the next green light cycle of the red light cycle;

[0088] The percentage of traffic during a green light cycle relative to the total number of vehicles is called vehicle density.

[0089] The green light cycle throughput is the number of vehicles that cross the stop line within a single green light cycle.

[0090] Please see Figure 4 As shown, this is a logic diagram for determining a congested intersection according to an embodiment of the present invention. The congestion prediction unit compares the congestion characteristic value with a preset congestion value, and determines whether the intersection behind the congested road segment is a congested intersection based on the comparison result.

[0091] If the congestion indicator value is greater than or equal to the preset congestion value, then the intersection behind the congested road segment is determined not to be a congested intersection.

[0092] If the congestion indicator value is less than the preset congestion value, then the intersection behind the congested road section is determined to be a congested intersection.

[0093] Specifically, the congestion indicator is the ratio of the target number of vehicles to the vehicle density in a single green light cycle.

[0094] Specifically, if the traffic volume during a single green light cycle is greater than or equal to the total number of vehicles, the intersection will not be congested; if the traffic volume during a green light cycle is less than the total number of vehicles, the intersection will be congested. Therefore, the preset congestion value is generally set to 1.

[0095] The intersection behind is the intersection that connects to the congested section of road along the direction of vehicle travel.

[0096] Specifically, the congestion prediction unit is used to define the road segments following the congested intersections where the red light cycle accumulation time is less than or equal to a preset time as predicted congested road segments.

[0097] The convergence time is the time it takes for vehicles to converge to maximum capacity in a characteristic road segment within a single red light cycle.

[0098] In one specific embodiment, a preset time is set to 60 seconds. If the accumulation time of the red light cycle is 34 seconds, which is less than the preset time, then the road segment connected to the corresponding congested intersection is set as the predicted congested road segment.

[0099] Specifically, the preset time is positively correlated with the duration of a single red light cycle.

[0100] It is understandable that if all vehicles in the characteristic road segment leave during the green light cycle, the longer the red light duration of a single cycle, the longer the accumulation time of the red light cycle. Therefore, the preset time is positively correlated with the red light duration of a single cycle. Preferably, the preset time ranges from 30 seconds to 90 seconds.

[0101] Specifically, this invention analyzes vehicle density to classify congestion levels of characteristic road segments, accurately determining whether congestion is temporary and self-regulating or severe and requiring intervention. It also determines whether a second-level congestion segment is congested based on the number of target vehicles in a single green light cycle. By analyzing the target vehicles present in congested segments, the invention assesses the congestion situation and predicts congestion at connecting intersections by analyzing the congestion status of those intersections. Vehicle density is a core indicator reflecting road segment load; analyzing it allows for precise differentiation between temporary fluctuations and severe congestion. This density-based classification avoids the limitations of traditional methods relying solely on average vehicle speed, enabling the system to accurately determine intervention needs, reducing over-regulation or delayed intervention, and further improving the accuracy of intelligent congestion mitigation systems based on big data analysis.

[0102] Specifically, the first adjustment unit adjusts the number of vehicles merging into the characteristic road segment based on the ratio of exhaust gas concentration to a preset concentration.

[0103] Specifically, if the ratio of exhaust gas concentration to preset concentration is less than or equal to 1, the number of vehicles merging into the characteristic road segment will not be adjusted. If the ratio of exhaust gas concentration to preset concentration is greater than 1, the number of vehicles merging into the characteristic road segment will be reduced by (ratio of exhaust gas concentration to preset concentration - 1) x the amount of vehicles merging in the previous red light cycle.

[0104] The preset concentration is positively correlated with the number of lanes in the characteristic road segment.

[0105] It is understandable that the more lanes a characteristic road segment has, the more vehicles can pass through, resulting in more exhaust emissions. Given a fixed size of the characteristic road segment, the higher the exhaust concentration, the more likely the preset concentration is to be positively correlated with the number of lanes in the characteristic road segment. Preferably, the preset concentration ranges from 20 ppm to 100 ppm.

[0106] Specifically, the concentration of vehicle exhaust gas can be detected by gas sensors or remote sensing equipment. This is prior art for those skilled in the art and will not be elaborated upon here.

[0107] Specifically, the second adjustment unit is used to adjust the green light cycle length of the congested intersection based on the number of merging vehicles in each predicted congested road segment connected to the congested intersection.

[0108] Specifically, the green light cycle length is allocated according to the ratio of the number of vehicles merging into each predicted congested road segment connected to the congested intersection to the total number of vehicles exiting the congested intersection.

[0109] Specifically, this invention adjusts the number of vehicles merging into characteristic road segments based on exhaust gas concentration. It characterizes the traffic congestion on these segments based on exhaust gas concentration, adjusts the number of merging vehicles, and simultaneously adjusts the green light cycle length at congested intersections based on the number of merging vehicles. Frequent vehicle starts and stops during congestion lead to incomplete combustion, thus quantifying the degree of congestion. Exhaust gas concentration data can serve as an environmental feedback indicator of the control effect, forming a closed loop with traditional efficiency feedback indicators, further improving the accuracy of the intelligent congestion mitigation system based on big data analysis.

[0110] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0111] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A smart congestion mitigation system based on big data analysis, characterized in that, include: The information collection module is used to collect road information, driving information and vehicle information of characteristic road sections through the traffic gantry. The road information includes the total number of vehicles and the traffic volume. The driving information includes the average speed of vehicles and the exhaust gas concentration of target vehicles. The vehicle information includes the number of times vehicle taillights flash and the number of times vehicles change lanes. The road analysis module, which is connected to the information collection module, is used to divide the vehicle traffic volume into green light cycle traffic volume and red light cycle convergence volume in combination with traffic lights, calculate vehicle density based on the total number of vehicles and the green light cycle traffic volume, and count the convergence time of the red light cycle convergence volume. The target selection module is connected to the information acquisition module and is used to generate vehicle feature values ​​based on the number of flashes of the vehicle's taillights and the number of times the vehicle changes lanes to select target vehicles. The feature analysis module is connected to the road analysis module and the target selection module respectively. It includes a congestion analysis unit for determining whether a feature road segment is a congested road segment based on the vehicle density and the number of target vehicles in a single green light cycle and generating a congestion characterization value, and a congestion prediction unit for generating a predicted congested road segment based on the congestion characterization value and the convergence time. The scheduling module is connected to the information acquisition module and the feature analysis module respectively, and includes a first adjustment unit for adjusting the number of vehicles merging into the feature road segment based on the exhaust gas concentration, and a second adjustment unit for adjusting the green light cycle length based on the number of vehicles merging into the predicted congested road segment. The characteristic road segment is the road between the traffic gantry and the next intersection in the direction of vehicle travel; The vehicle characteristic value is determined by the number of times the vehicle's taillights flash and the number of times the vehicle changes lanes. The vehicle characteristic value = ax the number of times the vehicle's taillights flash + bx the number of times the vehicle changes lanes, where a is the weight of the number of flashes and b is the weight of the number of lane changes. The road analysis module is used to calculate vehicle density based on the total number of vehicles and the traffic volume during the green light cycle, wherein... Used to obtain the total number of vehicles located in the characteristic road segment at the end of the red light cycle; Used to obtain the traffic volume of the green light cycle in the next green light cycle of the red light cycle; The percentage of traffic volume during the green light cycle relative to the total number of vehicles is denoted as the vehicle density. The green light cycle traffic volume refers to the number of vehicles that pass through the stop line within a single green light cycle.

2. The intelligent congestion mitigation system based on big data analysis according to claim 1, characterized in that, The target selection module selects target vehicles based on vehicle feature values, wherein, Vehicles whose vehicle characteristic value is greater than or equal to a preset characteristic value are set as target vehicles, and the preset characteristic value is positively correlated with the number of lanes in the characteristic road segment.

3. The intelligent congestion mitigation system based on big data analysis according to claim 2, characterized in that, The information collection module is used to collect the total number of vehicles and the average speed of vehicles entering the characteristic road section through the traffic gantry, wherein, Used to generate a predicted congestion coefficient based on the total number of vehicles and the average vehicle speed; This is used to issue a signal to select a target vehicle based on the predicted congestion coefficient.

4. The intelligent congestion mitigation system based on big data analysis according to claim 2, characterized in that, The congestion analysis unit is used to compare the vehicle density with a preset density, and determine the congestion level of the characteristic road segment based on the comparison result. The preset density is positively correlated with the number of lanes in the characteristic road segment, and the congestion level includes a first congestion level and a second congestion level.

5. The intelligent congestion mitigation system based on big data analysis according to claim 3, characterized in that, The congestion analysis unit is used to determine whether a characteristic road segment of the second congestion level is a congested road segment based on the number of target vehicles in a single green light cycle.

6. The intelligent congestion mitigation system based on big data analysis according to claim 5, characterized in that, The congestion prediction unit compares the congestion characterization value with a preset congestion value, and determines whether the intersection behind the congested road segment is a congested intersection based on the comparison result. The intersection behind is the intersection that connects to the blocked section of road along the direction of vehicle travel.

7. The intelligent congestion mitigation system based on big data analysis according to claim 6, characterized in that, The congestion prediction unit is used to designate the road segments following the congested intersections where the red light cycle accumulation time is less than or equal to a preset time as predicted congested road segments. The convergence time is the time it takes for vehicles to converge to maximum capacity in a characteristic road segment within a single red light cycle.

8. The intelligent congestion mitigation system based on big data analysis according to claim 7, characterized in that, The first adjustment unit adjusts the number of vehicles merging into the characteristic road segment based on the ratio of the exhaust gas concentration to a preset concentration. The preset concentration is positively correlated with the number of lanes in the characteristic road segment.

9. The intelligent congestion mitigation system based on big data analysis according to claim 8, characterized in that, The second adjustment unit is used to adjust the green light cycle length of the congested intersection based on the number of merging vehicles in each predicted congested road segment connected to the congested intersection.

Images