Adaptive control optimization method for intersection in intelligent network connection environment

Abstract

The invention provides a self-adaptive control optimization method for an intersection in an intelligent network connection environment, and belongs to the technical field of intelligent traffic, and the method comprises the steps: obtaining a signal lamp state and an initial speed when a motorcade enters a speed guide region; according to the signal lamp state and the initial speed, based on a pre-trained signal control model, adopting a signal lamp timing strategy to guide the speed of the motorcade; the training of the signal control model comprises the step of training the signal control model by taking the delay minimization of the vehicle team passing through the intersection as a target. Speed guidance and signal control are performed according to the signal lamp state and the vehicle team condition, and a signal lamp timing strategy is introduced to reduce the pause time of the vehicle at the intersection, so that the vehicle can pass through the intersection without stopping or the stopping time is shortest, and the traffic efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to an adaptive control optimization method for intersections in an intelligent network environment. Background Art

[0002] With the rise of autonomous driving technology, modern transportation is rapidly developing towards intelligence, and the mixture of connected vehicles (CAVs) and human-driven vehicles (HVs) is inevitable. Studies have shown that by 2045, the adoption rate of highly automated driving vehicles (L4 CAVs) is expected to reach 24.8%. Therefore, it is of great significance to study the impact of mixed traffic flow on adaptive control optimization in intelligent connected environments.

[0003] In terms of speed guidance and signal optimization, scholars have proposed various traffic signal optimization algorithms and control models. However, current research mainly focuses on the interaction between fleet intensity and penetration rate, and there is limited research on improving the passing efficiency of vehicles at intersections. Summary of the invention

[0004] The purpose of the present invention is to overcome the deficiencies in the prior art and to provide an adaptive control optimization method for intersections in an intelligent network environment, which can reduce the dwell time of vehicles at intersections, enable vehicles to pass through intersections without stopping or with minimal stopping time, and improve traffic efficiency.

[0005] To achieve the above object, the present invention is implemented by adopting the following technical solutions:

[0006] In one aspect, the present invention provides an adaptive control optimization method for an intersection in an intelligent network environment, comprising:

[0007] Get the signal light status and initial speed when the convoy enters the speed guidance area;

[0008] According to the signal light state and the initial speed, based on a pre-trained signal control model, a signal light timing strategy is adopted to guide the speed of the convoy;

[0009] The training of the signal control model includes:

[0010] The signal control model is trained with the goal of minimizing the delay of a convoy passing through an intersection.

[0011] Optionally, the objective function for minimizing the delay of the convoy passing through the intersection is as follows:

[0012] ;

[0013] ;

[0014] Where D is the minimum total delay time of the convoy; n is the number of vehicles in the convoy; ti is the driving time of a vehicle from the speed guidance area to the stop line of the intersection; vf is the free flow speed; L c represents the length of the guide area; a represents the acceleration; a min Indicates the minimum acceleration; a max represents the maximum acceleration; v0 represents the initial speed when the convoy enters the guidance area; v represents the guidance speed; represents the duration of the green light; T' represents the signal light cycle; v max Indicates the maximum speed of the vehicle; v min Indicates the minimum travel speed for the road limit.

[0015] Optionally, when the traffic light is red and the number of vehicles queuing in front of the stop line is less than a preset number of vehicles, the guide speed satisfies the following formula:

[0016] ;

[0017] Where, L d It represents the length of the convoy; Tr represents the remaining red light time; Tp represents the queue clearance time; t1 represents the vehicle starting loss time.

[0018] Optionally, when the current traffic light is red and the number of vehicles queued in front of the stop line is not less than the preset number of vehicles, the green light is activated in advance. The time for activating the green light in advance is as follows:

[0019] ;

[0020] Where, Tq represents the green light advance time; Tr represents the remaining red light time; Tp represents the queue dissipation time; t1 represents the vehicle start loss time; L d Indicates the length of the convoy.

[0021] Optionally, when the current traffic light is green and there are vehicles queued in the parking lane ahead and are dissipating, the guide speed satisfies the following formula:

[0022] ;

[0023] ;

[0024] Where, L d represents the length of the convoy; Tp represents the queue dissipation time, Lp represents the length of the vehicle queue, and vp represents the dissipation speed of the queued vehicles;

[0025] After the queue is dissipated, when the vehicle is moving at the maximum speed v maxWhen the guiding speed still does not satisfy the formula, the green light time is extended, and the green light extension time satisfies the following formula:

[0026] ;

[0027] Where, Td represents the green light extension time; Tmax G represents the maximum green light time; T g Indicates the remaining green time based on the shortest green duration.

[0028] Optionally, when the current traffic light is green and there is no vehicle queue in the parking lane ahead, the guide speed satisfies the following formula:

[0029] ;

[0030] Where, L d Indicates the length of the convoy; T g Indicates the remaining green time based on the shortest green duration;

[0031] When the vehicle is at maximum speed v max When the guiding speed still does not satisfy the formula, the green light time is extended, and the green light extension time satisfies the following formula:

[0032] ;

[0033] Wherein, Td represents the green light extension time; Tmax G represents the maximum green light time.

[0034] In a second aspect, the present invention provides a computer system, comprising:

[0035] Memory, for storing computer instructions;

[0036] A processor is used to execute the computer instructions to implement the steps of the adaptive control optimization method for intersections in an intelligent network environment described in the first aspect.

[0037] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the adaptive control optimization method for intersections in an intelligent network environment described in the first aspect are implemented.

[0038] Beneficial Effects

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] The present invention fully considers the status of traffic lights and the specific conditions of the fleet, carries out speed guidance and signal control in a targeted manner, introduces a traffic light timing strategy, and minimizes the dwelling time of vehicles at intersections through precise control and reasonable adjustment of the traffic light time, so that vehicles can pass through intersections without stopping as much as possible. Even if it is impossible to pass through without stopping at all, the stopping time of vehicles can be minimized, thereby effectively improving traffic efficiency, alleviating traffic congestion pressure, and bringing great convenience to people's travel. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic diagram of a flow chart of an adaptive control optimization method for an intersection in an intelligent network environment of the present invention in one embodiment;

[0042] Figure 2 The figure shows a comparison of the average delay time of the adaptive control optimization method for intersections in an intelligent network environment of the present invention and the existing method in one embodiment;

[0043] Figure 3 It is a comparison diagram of the number of stops in an embodiment of the adaptive control optimization method for intersections in an intelligent network environment of the present invention and the existing method;

[0044] Figure 4 The figure shows a comparison of the average queuing time of the adaptive control optimization method for intersections in an intelligent network environment of the present invention and the existing method in one embodiment;

[0045] Figure 5 Shown is a comparison chart of speed values ​​under different vehicle fleet intensities in an embodiment of the adaptive control optimization method for intersections in an intelligent network environment of the present invention. DETAILED DESCRIPTION

[0046] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0047] The term "and / or" is only a description of the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " generally indicates that the related objects are in an "or" relationship.

[0048] Example 1

[0049] like Figure 1As shown, this embodiment introduces an adaptive control optimization method for intersections in an intelligent network environment, which specifically includes the following steps:

[0050] Road traffic flow is a mixed traffic flow consisting of CAVs and HVs. According to the relative positions of different vehicle types on the road, it can be divided into four following scenarios:

[0051] (a) Following vehicles are HVs

[0052] If the vehicle ahead is a HV, the following mode name is HV - HV.

[0053] If the vehicle ahead is a CAV, the following mode is named CAV - HV.

[0054] (b) Following vehicles are CAVs

[0055] If the vehicle ahead is a HV, the following mode is named HV - CAV.

[0056] If the vehicle ahead is a CAV, the following mode is named CAV - CAV.

[0057] In these four following scenarios, the aggregation degree of CAVs cooperative driving is called platoon intensity, usually represented by the symbol O, with a value range of [-1,1]. Under the same penetration rate of intelligent connected vehicles, the greater the platoon intensity, the stronger the correlation between intelligent connected vehicles, and the higher the degree of overall platoon driving.

[0058] The closer the platoon strength value is to 1, the larger the platoon size of intelligent connected vehicles is; the closer it is to -1, the smaller the platoon size is. This study sets the maximum platoon size to 5.

[0059] The Markov chain model is used to abstract the fleet into a Markov chain to model the relationship between the penetration rate of intelligent connected vehicles and the platoon intensity in different following scenarios. The formula is as follows:

[0060] ;

[0061] in, It indicates the probability of HVs following CAVs; represents the probability of CAVs following CAVs; It indicates the probability of CAVs following HVs; It indicates the probability of HVs following HVs; represents the first random probability; represents the second random probability; is a probability function.

[0062] The intelligent driver model (IDM) is used for HVs, and the formula is as follows:

[0063] ;

[0064] Among them, the parameter meaning and value range of the intelligent driver model (IDM) are shown in Table 1:

[0065] Table 1 Parameter meaning and value range of intelligent driver model (IDM)

[0066]

[0067] Using cooperative adaptive cruise control (CACC) for CAVs, the formula is as follows:

[0068] ;

[0069] The parameter meaning and value range of cooperative adaptive cruise control (CACC) are shown in Table 2:

[0070] Table 2 Parameter meaning and value range of cooperative adaptive cruise control (CACC)

[0071]

[0072] CAVs can quickly obtain real-time traffic information, and traditional timing signal control is not conducive to fully optimizing road traffic capacity. In order to enable vehicles to stop at intersections without stopping or to minimize the stopping time, this study introduces a "demand allocation" signal timing scheme.

[0073] Get the traffic light status and initial speed when the convoy enters the speed guidance area.

[0074] When the convoy arrives at an intersection, there will be a variety of different signal light states, defined as a set of signal light state sets:

[0075] y = {(vi, ti ) | g(i), a(i), r(i)};

[0076] The specific status classification is shown in Table 3 below:

[0077] Table 3 Traffic light status classification

[0078]

[0079] Among them, g(i) represents the number of green light hours remaining when the convoy enters the speed guidance area; a(i) represents the yellow light state when the convoy enters the speed guidance area; r(i) represents the number of red light hours remaining when the convoy enters the speed guidance area; t = ; L c represents the length of the guide area; vf represents the free flow speed; vi represents the speed of the vehicle in case i, ranging from ; ti represents the time when the vehicle is in condition i.

[0080] When g(i) ≥ t or r (i) < t, vehicles can pass through the intersection without stopping, and the convoy speed should be within the range.

[0081] When g(i) < t, a(i) ≥ t or r(i) ≥ t, the vehicle needs to stop and wait, so the convoy speed needs to be guided so that the vehicle passes without stopping before the next green light ends. The speed should be maintained at .

[0082] According to the signal light state and the initial speed, based on a pre-trained signal control model, a signal light timing strategy is adopted to guide the speed of the vehicle fleet.

[0083] Research shows that in complex road conditions such as urban roads, speed fluctuations should be kept within 50% of the initial speed to ensure driving stability; on roads with simple road conditions and wide views such as highways, speed changes can be extended to 60% of the initial speed to improve driving efficiency; in congested areas, speed fluctuations should be limited to within 40% of the initial speed to prioritize driving safety. In summary, it is recommended to keep speed changes within the range of 40% to 60%.

[0084] Under the conditions of adaptive control and vehicle speed guidance, the goal is to minimize the overall delay of the convoy. To achieve this goal, an objective function is formulated to determine the best control optimization result, and the corresponding mathematical model is as follows: The objective function with the goal of minimizing the delay of the convoy passing through the intersection is as follows:

[0085] ;

[0086] ;

[0087] Where D is the minimum total delay time of the convoy; n is the number of vehicles in the convoy; ti is the driving time of a vehicle from the speed guidance area to the stop line of the intersection; vf is the free flow speed; L c represents the length of the guide area; a represents the acceleration; a min Indicates the minimum acceleration; a max represents the maximum acceleration; v0 represents the initial speed when the convoy enters the guidance area; v represents the guidance speed; represents the duration of the green light; T' represents the signal light cycle; v max Indicates the maximum speed of the vehicle; v min Indicates the minimum travel speed for the road limit.

[0088] When the traffic light is red and the number of vehicles queuing in front of the stop line is less than the preset number of vehicles, the guidance speed satisfies the following formula:

[0089] ;

[0090] Where, L d It represents the length of the convoy; Tr represents the remaining red light time; Tp represents the queue clearance time; t1 represents the vehicle starting loss time.

[0091] When the current traffic light is red and there are no fewer than the preset number of vehicles in the queue in front of the stop line, even if the vehicle is traveling at the lowest speed, it must continue to queue and wait, and activate the green light in advance. The time to activate the green light in advance is as follows:

[0092] ;

[0093] Where, Tq represents the green light advance time; Tr represents the remaining red light time; Tp represents the queue dissipation time; t1 represents the vehicle start loss time; a represents the acceleration; L d Indicates the length of the convoy.

[0094] When the current traffic light is green and there are vehicles queuing in the parking lane ahead and they are dissipating, if the convoy continues to drive at the initial speed, it may stop again due to the influence of the vehicles queuing ahead. To avoid this situation, the guidance speed satisfies the following formula:

[0095] ;

[0096] ;

[0097] Where, L d represents the length of the convoy; Tp represents the queue dissipation time, Lp represents the length of the vehicle queue, and vp represents the dissipation speed of the queued vehicles;

[0098] After the queue is dissipated, when the vehicle is moving at the maximum speed v max When the guiding speed still does not satisfy the formula, the green light time is extended, and the green light extension time satisfies the following formula:

[0099] ;

[0100] Where, Td represents the green light extension time; Tmax G represents the maximum green light time; T g Indicates the remaining green time based on the shortest green duration.

[0101] When the current traffic light is green and there are no vehicles queued in the parking lane ahead, if the convoy continues to travel at the current speed, the traffic light will turn red when the convoy reaches the intersection. In order to ensure that the convoy passes the intersection within the remaining green light time, the speed of the convoy needs to be adjusted accordingly. The guide speed satisfies the following formula:

[0102] ;

[0103] Where, L d Indicates the length of the convoy; T g Indicates the remaining green time based on the shortest green duration;

[0104] When the vehicle is at maximum speed v max When the guiding speed still does not satisfy the formula, the green light time is extended, and the green light extension time satisfies the following formula:

[0105] ;

[0106] Wherein, Td represents the green light extension time; Tmax G represents the maximum green light time.

[0107] Example 2

[0108] like Figure 2-5 As shown, this embodiment introduces an experimental example of an adaptive control optimization method for an intersection in an intelligent network environment, and the steps are as follows:

[0109] This study focuses on the intersection of Kunlunshan South Road and Weihe Road in Huangdao District, Qingdao. The intersection is surrounded by diverse areas, including industrial parks, higher education institutions, and residential areas. Due to the high traffic volume, congestion is a frequent problem. The survey was conducted over a three-day period during peak working hours from 13:00 to 15:00. The body length of large trucks ranges from 8 to 12 meters, the body length of medium trucks ranges from 6 to 8 meters, and the body length of small cars ranges from 2 to 5 meters. The intersection of Kunlunshan South Road and Weihe Road currently uses traditional timed signal control. The intersection has four phases: north-south straight, north-south left turn, east-west straight, and east-west right turn, with a signal period of 134 seconds. The adaptive signal control adopted in this paper uses traffic sensors (such as ground induction loops, cameras) to obtain real-time traffic flow data and dynamically adjust the green light duration according to the current traffic conditions. Studies have shown that in adaptive signal control systems, the maximum green time is usually set to 120% to 150% of the traditional green time to accommodate peak traffic flows.

[0110] Instead, the minimum green time is usually set to 50% to 80% of the conventional green time to ensure safe passage of vehicles. The unit green extension time is fixed at 3 seconds, which means the end of the green phase. If no vehicle is detected passing during this extension time, the system will switch to the next phase.

[0111] This study used Python and SUMO simulation platform to conduct simulation experiments, and set the experimental duration between 600 and 1800 seconds with a step size of 10. In the simulation process, different following models were used, using the intelligent driving model (IDM) for human-driven vehicles (HVs) and the collaborative adaptive cruise control model (CACC) for autonomous vehicles (CAVs).

[0112] like Figure 2-5 As shown in the figure, the results show that as the penetration rate and convoy intensity increase, the intersection capacity will also increase. Higher penetration rate and convoy intensity will lead to faster vehicle speeds, shorter queues and delays, and fewer stops, ultimately improving the traffic efficiency of the intersection. Comparative analysis with traditional signal control systems shows that the proposed adaptive signal control method has considerable advantages. Compared with traditional signal control, the adaptive signal control system reduces the average delay by 20%, the number of stops by 4.2%, and the average queue time by 21.5%.

[0113] Example 3

[0114] This embodiment introduces a computer system, including:

[0115] Memory, for storing computer instructions;

[0116] A processor is used to execute the computer instructions to implement the steps of the adaptive control optimization method for intersections in an intelligent network environment described in Example 1 or 2.

[0117] Example 4

[0118] This embodiment introduces a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the adaptive control optimization method for intersections in an intelligent network environment described in Embodiment 1 or 2 are implemented.

[0119] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0120] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0121] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0122] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0123] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. An adaptive control optimization method for intersections in an intelligent network environment, characterized in that: include: Get the signal light status and initial speed when the convoy enters the speed guidance area; According to the signal light state and the initial speed, based on a pre-trained signal control model, a signal light timing strategy is adopted to guide the speed of the convoy; The training of the signal control model includes: The signal control model is trained with the goal of minimizing the delay of a convoy passing through an intersection.

2. The adaptive control optimization method for intersections in an intelligent network environment according to claim 1 is characterized in that: The objective function for minimizing the delay of the convoy passing through the intersection is as follows: ； ； Where D is the minimum total delay time of the convoy; n is the number of vehicles in the convoy; ti is the driving time of a vehicle from the speed guidance area to the stop line of the intersection; vf is the free flow speed; L c represents the length of the guide area; a represents the acceleration; a min Indicates the minimum acceleration; a max represents the maximum acceleration; v0 represents the initial speed when the convoy enters the guidance area; v represents the guidance speed; Indicates the duration of the green light; T' represents the signal light cycle; v max Indicates the maximum speed of the vehicle; v min Indicates the minimum travel speed for the road limit.

3. The adaptive control optimization method for intersections in an intelligent network environment according to claim 2 is characterized in that: When the traffic light is red and the number of vehicles queuing in front of the stop line is less than the preset number of vehicles, the guidance speed satisfies the following formula: ； Where, L d It represents the length of the convoy; Tr represents the remaining red light time; Tp represents the queue clearance time; t1 represents the vehicle starting loss time.

4. The adaptive control optimization method for intersections in an intelligent network environment according to claim 2 is characterized in that: When the current traffic light is red and there are no fewer than the preset number of vehicles in the queue ahead of the stop line, the green light is activated in advance. The time for activating the green light in advance is as follows: ； In the formula, Tq represents the green light advance time; Tr represents the remaining red light time; Tp represents the queue clearance time; t1 represents the vehicle start loss time; L d Indicates the length of the convoy.

5. The adaptive control optimization method for intersections in an intelligent network environment according to claim 2, characterized in that: When the current traffic light is green and there are vehicles queued in the parking lane ahead and are dissipating, the guidance speed satisfies the following formula: ； ； Where, L d represents the length of the convoy; Tp represents the queue dissipation time, Lp represents the length of the vehicle queue, and vp represents the dissipation speed of the queued vehicles; After the queue is dissipated, when the vehicle is moving at the maximum speed v max When the guiding speed still does not satisfy the formula, the green light time is extended, and the green light extension time satisfies the following formula: ； In the formula, Td represents the green light extension time; Tmax G represents the maximum green light time; T g Indicates the remaining green time based on the shortest green duration.

6. The adaptive control optimization method for intersections in an intelligent network environment according to claim 2 is characterized in that: When the current traffic light is green and there is no vehicle queue in the parking lane ahead, the guidance speed satisfies the following formula: ； Where, L d Indicates the length of the convoy; T g Indicates the remaining green time based on the shortest green duration; When the vehicle is at maximum speed v max When the guiding speed still does not satisfy the formula, the green light time is extended, and the green light extension time satisfies the following formula: ； Wherein, Td represents the green light extension time; Tmax G represents the maximum green light time.

7. A computer system, characterized in that: include: Memory, for storing computer instructions; A processor is used to execute the computer instructions to implement the steps of the adaptive control optimization method for intersections in an intelligent network environment according to any one of claims 1 to 7.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the adaptive control optimization method for intersections in an intelligent network environment described in any one of claims 1 to 7 are implemented.

Images