An overflow queue prediction and multi-intersection traffic signal coordination control algorithm, system and device based on vehicle-road collaboration
Through real-time data analysis of vehicle-road collaboration system and multi-way traffic signal coordination control, the green signal ratio is optimized, and the high cost and low efficiency caused by relying on manual judgment in the existing technology is solved, and the automatic overflow pre-prevention is realized The evaluation and control improves the efficiency and adaptability of traffic flow management.
Patent Information
- Application Number
- CN202210735302.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-06-27
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2042-06-27
AI Technical Summary
The prior art relies on manual judgment when dealing with the problem of queuing overflow, which is costly and inefficient, making it difficult to effectively avoid increased traffic pressure.
Based on the vehicle-road collaboration system, the vehicle-road sensing data and vehicle driving data are obtained in real time, the vehicle arrival rate and queue length are predicted, and the multi-way traffic signal coordination control model is constructed to optimize the green signal ratio to avoid overflow events.
It realizes automated overflow prediction and control, reduces the cost of manual intervention, improves the efficiency and adaptability of traffic flow management, and avoids traffic deadlocks.
Smart Images

Figure CN115171374B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent transportation technology, and in particular to an overflow queue prediction and multi-intersection traffic signal coordination control algorithm, system and device based on vehicle-road collaboration. Background Art
[0002] When the streets are filled with slow-moving or even stationary vehicles, there is no room for other vehicles to enter, and "queue overflow" often occurs. Sometimes the queued vehicles extend to the upstream intersection to form a serious congestion. At present, every time this problem occurs, the solution usually adopted is to increase the number of traffic order maintenance personnel at the intersections that are prone to queue overflow and related intersections, and through the information communication of increasing the number of traffic order maintenance personnel at the intersections with queue overflow and related intersections, the traffic order maintenance personnel will control the on and off of the red traffic signal lights at the intersections with queue overflow on site. This method requires a large labor cost and has high requirements for the on-site judgment ability of the traffic order maintenance personnel. If the traffic order maintenance personnel are not experienced in handling, it will not only fail to reduce traffic pressure, but increase traffic pressure. Summary of the invention
[0003] In response to the deficiencies of the prior art, the present invention provides an overflow queue prediction and multi-intersection traffic signal coordination control algorithm, system and device based on vehicle-road collaboration. Based on the roadside perception data of upstream and downstream intersections and the real-time driving data of vehicles entering the network acquired in real time by the cloud control basic platform of the vehicle-road collaboration system, the arrival rate of vehicles entering after the upstream intersection traffic light is activated is predicted, and the maximum queue length of vehicles after the downstream intersection prohibition signal light is turned on is estimated, and it is predicted whether the maximum queue length of vehicles exceeds the safe queue length; if it is predicted that an overflow event will occur, the average queue lengths of the upstream and downstream intersections are combined to form an optimization adjustment strategy for the green-signal ratio of the upstream and downstream intersections, so as to actively avoid the occurrence of overflow. Specifically:
[0004] On the one hand, the present application provides an overflow queue prediction and multi-intersection traffic signal coordination control algorithm based on vehicle-road collaboration, which includes:
[0005] Acquire the first reference data and the real-time driving data of the networked vehicles in real time;
[0006] Construct a prediction model for the arrival rate of vehicles entering the upstream intersection after the traffic light is turned on.
[0007] Predict whether overflow queues will occur after the stop signal light at the current intersection is turned on;
[0008] A multi-intersection traffic signal coordination control model is constructed when overflow queuing occurs, and the green-to-signal ratio optimization adjustment strategy for each intersection is determined.
[0009] Preferably, in the above-mentioned overflow queue prediction and multi-intersection traffic signal coordinated control algorithm based on vehicle-road collaboration, the real-time acquisition of the first reference data and the real-time driving data of the target specifically includes:
[0010] Obtain the length of the convoy at different times in different phases of the intersection, and determine the number of vehicles stranded at the intersection at the end of the previous signal cycle in each phase of the intersection through the convoy length;
[0011] The average speed of the vehicles entering the network at the upstream intersection and the current intersection is formed according to the average speed of the vehicles entering the network at the extension of the stop line of the upstream intersection exit;
[0012] The average travel time of the fleet from the upstream intersection to the current intersection is calculated based on the distance between the upstream intersection and the current intersection and the average speed between the upstream intersection and the current intersection.
[0013] Preferably, in the above-mentioned overflow queue prediction and multi-intersection traffic signal coordinated control algorithm based on vehicle-road collaboration, constructing a prediction model for the arrival rate of vehicles entering after the upstream intersection traffic signal light is activated specifically includes:
[0014] The prediction model is constructed using the LSTM neural network model.
[0015]
[0016] in, is the arrival rate of vehicles entering the i-1th intersection after the p-th phase traffic signal light is activated in the k+1th signal cycle;
[0017] is the vehicle arrival rate of the p-th phase of the k-th signal cycle at the i-1-th intersection;
[0018] is the historical traffic arrival rate of the p-th phase in the k+1-th signal cycle at the i-1-th intersection.
[0019] Preferably, in the above-mentioned overflow queue prediction and multi-intersection traffic signal coordinated control algorithm based on vehicle-road collaboration, predicting whether an overflow queue phenomenon will occur after the stop signal light at the current intersection is turned on specifically includes:
[0020] Get the length of the queue of vehicles whose stop lights are on in the next signal cycle at the current intersection:
[0021] According to the distance from the upstream intersection to the current intersection, a safe queue length is formed by the average head distance of the queued vehicles when the stop signal light is on;
[0022] Whether overflow will occur at the current intersection is determined based on the length of the vehicle queue and the safe length when the stop signal light is on in the next signal cycle of the current intersection. If overflow does not occur, continue to determine whether overflow will occur in the next signal cycle.
[0023] Preferably, the above-mentioned overflow queue prediction and multi-intersection traffic signal coordinated control algorithm based on vehicle-road collaboration, wherein a multi-intersection traffic signal coordinated control model is constructed when an overflow queue phenomenon occurs, and the green signal ratio optimization adjustment strategy of each intersection is determined specifically including:
[0024] Calculate the adjustment strategy of the green-signal ratio at each intersection;
[0025] When the adjustment strategy is verified, the optimal adjustment strategy is formed. When the adjustment strategy is not verified, k=k+1 is set to continue calculating the adjustment strategy for the green-to-signal ratio of each intersection.
[0026] Preferably, in the above-mentioned overflow queue prediction and multi-intersection traffic signal coordinated control algorithm based on vehicle-road collaboration, the adjustment strategy for calculating the green signal ratio of each intersection specifically includes:
[0027] Calculate and obtain the green-to-signal ratio of the pth phase in the k+1th signal cycle of the current intersection
[0028] According to the green-to-signal ratio of the pth phase of the k+1th signal cycle at the current intersection The green signal ratio λ of the pth phase of the kth signal cycle at the current intersection i,k,p A green-to-signal ratio difference is formed;
[0029] The green-to-signal ratio difference is divided into m levels to form a green-to-signal ratio adjustment amount, and an adjustment strategy for the green-to-signal ratio is determined according to the green-to-signal ratio adjustment amount.
[0030] Preferably, in the above-mentioned overflow queue prediction and multi-intersection traffic signal coordinated control algorithm based on vehicle-road collaboration, forming the optimal adjustment strategy when the adjustment strategy is verified to be passed specifically includes:
[0031] When κ>m, the green signal ratio adjustment strategy for upstream and downstream intersections with the smallest objective function value is the optimal strategy. When κ≤m, let κ=κ+1 to continue calculating the green signal ratio adjustment strategy for each intersection. The green signal ratio adjustment strategy for upstream and downstream intersections with the smallest objective function value is
[0032]
[0033]
[0034] λi,k+1,p ≥λ min ,p=1,…,P,i=1,…,n
[0035] Where n is the number of upstream and downstream intersections;
[0036] P is the phase number of the k+1th signal cycle at the ith intersection;
[0037] The queue length of the pth phase in the k+1th signal cycle at intersection i;
[0038] λ i,k+1,p is the green-to-signal ratio of the pth phase in the k+1th signal cycle of intersection i; L is the total loss time of the signal cycle;
[0039] C is the signal cycle length;
[0040] λ min The green signal ratio corresponding to the minimum traffic light time;
[0041] The control signal of the traffic light at the upstream intersection is turned on according to the phase difference with the current intersection and the adjusted green signal ratio of the current intersection.
[0042] On the other hand, the present application further provides an overflow queue prediction and multi-intersection traffic signal coordination control system based on vehicle-road collaboration, which includes:
[0043] Data input module: used to obtain the real-time roadside perception data and real-time driving data of connected vehicles from the cloud control platform of the vehicle-road cooperative system;
[0044] Overflow prediction module: predicts the arrival rate of vehicles entering the upstream intersection after the traffic signal light is activated to predict whether overflow queues will occur;
[0045] Coordination control module: used to determine the optimization adjustment strategy of the green-to-signal ratio at multiple intersections for upstream and downstream related intersections where overflow queues are predicted to occur.
[0046] Preferably, the above-mentioned overflow queue prediction and multi-intersection traffic signal coordination control system based on vehicle-road collaboration further includes:
[0047] Strategy output module: used to share the green signal ratio optimization adjustment strategy for multiple intersections to the traffic signal control system of the public security traffic police department through the cloud control basic platform of the vehicle-road cooperative system, and assist the traffic signal control system in timing optimization.
[0048] Finally, the present application further provides an overflow queue prediction and multi-intersection traffic signal coordination control device based on vehicle-road collaboration, which includes a storage medium and a processor, the storage medium is used to store computer programs, and the processor is used to execute the computer program to implement any of the above-mentioned overflow queue prediction and multi-intersection traffic signal coordination control algorithms based on vehicle-road collaboration.
[0049] Compared with the prior art, the present invention has the following beneficial effects:
[0050] The vehicle-road cooperative system provides the feasibility for accurately sensing the traffic flow information of upstream and downstream signalized intersections, which can avoid the cost of large-scale deployment of vehicle detectors in the traditional way;
[0051] To address the overflow queue problem, the system can predict in real time whether overflow queues will occur based on the perception data collected by the vehicle-road cooperative system, and achieve active coordinated control of upstream and downstream related intersections under oversaturated conditions to avoid intersection deadlocks, making the model more adaptable. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] Figure 1 A flowchart of an overflow queue prediction and multi-intersection traffic signal coordination control algorithm based on vehicle-road collaboration provided by an embodiment of the present invention;
[0053] Figure 2 A flowchart of an overflow queue prediction and multi-intersection traffic signal coordination control algorithm based on vehicle-road collaboration provided by an embodiment of the present invention;
[0054] Figure 3 A flowchart of an overflow queue prediction and multi-intersection traffic signal coordination control algorithm based on vehicle-road collaboration provided by an embodiment of the present invention;
[0055] Figure 4 This is a structural schematic diagram of an overflow queue prediction and multi-intersection traffic signal coordination control device based on vehicle-road collaboration. DETAILED DESCRIPTION
[0056] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. In the subsequent description, the use of suffixes such as "module", "component" or "unit" used to represent elements is only to facilitate the description of the present invention and has no specific meaning in itself. Therefore, "module", "component" or "unit" can be used in a mixed manner.
[0057] Embodiment 1
[0058] like Figure 1 As shown, an overflow queue prediction and multi-intersection traffic signal coordination control algorithm based on vehicle-road collaboration includes:
[0059] Step S110: acquiring first reference data and real-time driving data of networked vehicles in real time; specifically:
[0060] Among them, the first reference master data can be, for example, the length of the convoy at different times in different phases of each intersection, especially the length of the convoy at the first reference time, where the first reference time can be the time when the stop signal light is turned on, such as the time when the prohibition signal light is turned on.
[0061] like Figure 2 As shown, step S1101, obtain the length of the vehicle fleet passing through the intersection at different phases at different times, and determine the number of vehicles stranded at the intersection at the end of the previous signal cycle in each phase of the intersection through the length of the vehicle fleet.
[0062] Schematically: The queue lengths of different phases at different times are used to determine the length of the fleet of vehicles stranded at the intersection at the end of the previous traffic light cycle at each phase of the intersection, which is counted as q i,k ;
[0063] q i,k =[q i,k,1 ,q i,k,2 ,…,q i,k,P ]
[0064] Among them, q i,k is the length of the convoy at each phase of the kth signal cycle at the i-th intersection when the signal lights are prohibited from turning on;
[0065] q i,k,p is the queue length at the i-th intersection in the p-th phase of the k-th signal cycle when the traffic lights are prohibited from turning on;
[0066] p=1,…,P, P is the phase number of the i-th k-th signal cycle.
[0067] It should be noted that the queue lengths at different times in different phases of the intersection can be formed by the data uploaded by the roadside perception system (such as millimeter wave radar, integrated radar and vision device, etc.) obtained by the cloud control basic platform of the vehicle-road cooperative system, or by other systems, and no specific restrictions are made here. The number of vehicles includes the total number of non-networked vehicles and networked vehicles.
[0068] The real-time driving data of the networked vehicle includes at least the ID information of the networked vehicle that has established a connection with the cloud control basic platform, the VIN code of the networked vehicle, the current location information of the networked vehicle (such as the longitude and latitude of the space where the networked vehicle is located), time information, the driving speed information of the networked vehicle, and the heading angle information of the networked vehicle.
[0069] Step S1102: forming an average speed of the network-entering vehicles between the upstream intersection and the current intersection based on the average speed of the network-entering vehicles at the extension of the stop line of the upstream intersection exit.
[0070] In schematic form, when the total number of vehicles entering the network in the vehicle-road cooperative environment reaches a large sample proportion of the road traffic volume, the average speed of each vehicle entering the network passing through the extended line of the stop line at the upstream intersection exit is calculated. Calculate the average speed of vehicles entering the network between the upstream intersection and the current intersection i-1→i,
[0071]
[0072] Where: v i-1→i (l) is the speed of the lth vehicle entering the network from the upstream intersection i-1 to the current intersection i;
[0073] is the average speed of vehicles entering the network from the upstream intersection i-1 to the current intersection i, which can also be understood as the average speed of the queued vehicles from the upstream intersection i-1 to the current intersection i;
[0074] N is the total number of vehicles entering the network from the upstream intersection i-1 to the current intersection i.
[0075] It should be noted that the ratio value of the large sample ratio is determined according to the actual application scenario and is not specifically limited here.
[0076] Step S1103: Calculate the average travel time of the convoy from the upstream intersection to the current intersection based on the distance between the upstream intersection and the current intersection and the average speed between the upstream intersection and the current intersection.
[0077]
[0078] Among them, s i-1→i The distance between the upstream intersection i-1 and the current intersection i is s i-1→i ;
[0079] is the average travel time of the fleet from the upstream intersection i-1 to the current intersection i.
[0080] Step S120: construct a prediction model for the arrival rate of vehicles entering the upstream intersection after the traffic signal light is turned on. Schematically, the prediction model is constructed using an LSTM neural network model.
[0081]
[0082] in, is the arrival rate of vehicles entering the i-1th intersection after the p-th phase traffic signal light is activated in the k+1th signal cycle;
[0083] is the vehicle arrival rate of the p-th phase of the k-th signal cycle at the i-1-th intersection; is the historical vehicle arrival rate of the pth phase of the k+1th signal cycle at the i-1th intersection. The arrival rate can be obtained through the roadside fusion perception traffic data received by the cloud control basic platform. The meaning of traffic is the total number of vehicles passing per hour. Then, the number of vehicles arriving per minute can be calculated based on the traffic, which is the arrival rate.
[0084] Step S130, predicting whether an overflow queue phenomenon occurs after the stop signal light at the current intersection is turned on;
[0085] like Figure 3 As shown, step S1301, obtaining the length of the vehicle queue whose stop signal lights are on in the next signal cycle of the current intersection: schematically,
[0086]
[0087] in, is the predicted queue length during the p-th phase prohibition signal light in the k+1-th signal cycle at the i-th intersection (current intersection);
[0088] q i,k+1,p is the queue length at the start time of the p-th phase prohibition signal light in the k+1-th signal cycle of the i-th intersection,
[0089] is the predicted value of the traffic arrival rate at the pth phase of the k+1th signal cycle at the i-1th intersection (upstream intersection),
[0090] is the duration of the stop signal light at the pth phase of the k+1th signal cycle at the i-th intersection;
[0091] is the average travel time of the fleet from the upstream intersection i-1 to the current intersection i.
[0092] Step S1302: Based on the distance from the upstream intersection to the current intersection, the average headway of the queued vehicles when the stop signal light is on forms a safe queue length:
[0093]
[0094] Among them, s i-1→i is the distance from the upstream intersection i-1 to the current intersection i;
[0095] h (r) The average headway between vehicles when the traffic line is queued without the signal lights on;
[0096] l safe The length of the queue for safety;
[0097] Step S1303: Determine whether overflow will occur at the current intersection based on the length of the vehicle queue and the safety length when the stop signal light is on in the next signal cycle of the current intersection. If overflow does not occur, set k=k+1 and continue to determine whether overflow will occur in the next signal cycle.
[0098] Indicatively, In the state, let k = k + 1 and continue to predict whether overflow occurs in the next signal cycle, that is, execute step S1301. In this state, it is determined that an overflow queue state is formed.
[0099] Step S140: construct a multi-intersection traffic signal coordination control model when overflow queuing occurs, determine the green signal ratio optimization adjustment strategy for each intersection, and further, schematically:
[0100] Step S1401: Calculate the adjustment strategy of the green-to-signal ratio of each intersection; specifically, calculate and obtain the green-to-signal ratio of the pth phase of the k+1th signal cycle of the current intersection According to the green-to-signal ratio of the pth phase of the k+1th signal cycle at the current intersection The green signal ratio λ of the pth phase of the kth signal cycle at the current intersection i,k,p A green-to-signal ratio difference is formed, the green-to-signal ratio difference is divided into m levels to form a green-to-signal ratio adjustment amount, and adjustment information of the green-to-signal ratios of other phases of the k+1th signal cycle of the intersection i is formed according to the green-to-signal ratio adjustment amount in a state where an optimal adjustment strategy is formed;
[0101] Step S1402: When κ>m, the green signal ratio adjustment strategy for upstream and downstream intersections with the smallest objective function value is the optimal strategy. When κ≤m, set κ=κ+1 to execute step S1401.
[0102] The green signal ratio adjustment strategy for upstream and downstream intersections with the smallest objective function value is:
[0103]
[0104]
[0105] λ i,k+1,p ≥λ min ,p=1,…,P,i=1,…,n
[0106] Where n is the number of upstream and downstream intersections;
[0107] P is the phase number of the k+1th signal cycle at the ith intersection;
[0108] The queue length of the pth phase in the k+1th signal cycle at intersection i;
[0109] λ i,k+1,p is the green-to-signal ratio of the pth phase in the k+1th signal cycle of intersection i; L is the total loss time of the signal cycle;
[0110] C is the signal cycle length;
[0111] λ min It is the green signal ratio corresponding to the minimum traffic light time.
[0112] Step S1403: forming a control signal for the traffic light at the upstream intersection according to the phase difference with the current intersection and the adjusted green-to-signal ratio of the current intersection.
[0113] An overflow queue prediction and multi-intersection traffic signal coordination control algorithm, system and device based on vehicle-road collaboration. Based on the roadside perception data of upstream and downstream intersections and the real-time driving data of vehicles entering the network acquired in real time by the cloud control basic platform of the vehicle-road collaboration system, the arrival rate of vehicles entering after the upstream intersection traffic signal is activated is predicted, the maximum queue length of vehicles after the downstream intersection prohibition signal is turned on is estimated, and whether the maximum queue length of vehicles exceeds the safe queue length is predicted; if an overflow event is predicted to occur, the average queue lengths of the upstream and downstream intersections are combined to form an optimization adjustment strategy for the green signal ratio of the upstream and downstream intersections, so as to actively avoid the occurrence of overflow.
[0114] Embodiment 2
[0115] On the other hand, the present application further provides an overflow queue prediction and multi-intersection traffic signal coordination control system based on vehicle-road collaboration, which includes:
[0116] Data input module: used to obtain the real-time roadside perception data and real-time driving data of connected vehicles from the cloud control platform of the vehicle-road cooperative system;
[0117] Overflow prediction module: predicts the arrival rate of vehicles entering the upstream intersection after the traffic signal light is activated to predict whether overflow queues will occur;
[0118] Coordination control module: used to determine the optimization adjustment strategy of the green-to-signal ratio at multiple intersections for upstream and downstream related intersections where overflow queues are predicted to occur.
[0119] Furthermore, it also includes:
[0120] Strategy output module: used to share the green signal ratio optimization adjustment strategy for multiple intersections to the traffic signal control system of the public security traffic police department through the cloud control basic platform of the vehicle-road cooperative system, and assist the traffic signal control system in timing optimization.
[0121] The above-mentioned overflow queue prediction and multi-intersection traffic signal coordination control system based on vehicle-road collaboration has the same working principle as the overflow queue prediction and multi-intersection traffic signal coordination control algorithm based on vehicle-road collaboration provided in Example 1, which will not be repeated here.
[0122] Embodiment 3
[0123] A device for predicting overflow queues and coordinating and controlling traffic signals at multiple intersections based on vehicle-road collaboration, comprising a storage medium and a processor, wherein the storage medium is used to store a computer program, and the processor is used to execute the computer program to implement the algorithm for predicting overflow queues and coordinating and controlling traffic signals at multiple intersections based on vehicle-road collaboration of the first embodiment, specifically comprising: acquiring first reference data and real-time driving data of a target in real time;
[0124] Construct a prediction model for the arrival rate of vehicles entering the upstream intersection after the traffic signal light is activated.
[0125] Predict the overflow queue status after the stop signal light at the current intersection is turned on;
[0126] A multi-intersection traffic signal coordination control model is constructed under the overflow queue state, and the green-to-signal ratio optimization adjustment strategy of each intersection is determined.
[0127] The control device specifically includes: one or more processors 410, Figure 4 In the example, a processor 410 is used; the memory 420 is used to store one or more programs. When the one or more programs are executed by one or more processors 410, the one or more processors 410 implement the mixed reality interaction method described in any embodiment of the present invention. The processor 410 and the memory 420 can be connected via a bus or other means. Figure 4 The example of connecting through bus is taken in the following.
[0128] The memory 420, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions corresponding to the mixed reality interaction method in the embodiment of the present invention (for example, the reception of signals in each direction and the measurement of field strength, the determination of one-way delay and the collection of TA information). The processor 410 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 420, that is, realizing the above-mentioned mixed reality interaction method.
[0129] The memory 420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the device, etc. In addition, the memory 420 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 420 may further include a memory remotely arranged relative to the processor 410, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0130] Embodiment 4
[0131] Finally, the present application further provides a computer-readable storage medium, on which is stored a program for overflow queue prediction and coordinated control of traffic signals at multiple intersections based on vehicle-road collaboration. When the program for overflow queue prediction and coordinated control of traffic signals at multiple intersections based on vehicle-road collaboration is executed by a processor, an overflow queue prediction and coordinated control algorithm for traffic signals at multiple intersections based on vehicle-road collaboration of the first embodiment is implemented, specifically including:
[0132] Acquire the first reference data and the real-time driving data of the target in real time;
[0133] Construct a prediction model for the arrival rate of vehicles entering the upstream intersection after the traffic signal light is activated.
[0134] Predict the overflow queue status after the stop signal light at the current intersection is turned on;
[0135] A multi-intersection traffic signal coordination control model is constructed under the overflow queue state, and the green-to-signal ratio optimization adjustment strategy of each intersection is determined.
[0136] Of course, the computer-readable storage medium provided by an embodiment of the present invention, whose computer executable instructions are not limited to the method operations described above, can also execute related operations in the mixed reality interaction method provided by any embodiment of the present invention.
[0137] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.
[0138] It is worth noting that in the embodiment of the above-mentioned search device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.
[0139] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims
1. A method for overflow queue prediction and coordinated control of multi-intersection traffic signals based on vehicle-road collaboration, characterized in that: include: Acquire the first reference data and the real-time driving data of the networked vehicles in real time; Construct a prediction model for the arrival rate of vehicles entering the upstream intersection after the traffic signal light is turned on, including: The prediction model is constructed using the LSTM neural network model. in, is the arrival rate of vehicles entering the i-1th intersection after the p-th phase traffic signal light is activated in the k+1th signal cycle; is the vehicle arrival rate of the p-th phase of the k-th signal cycle at the i-1-th intersection; is the historical vehicle arrival rate of the pth phase of the k+1th signal cycle at the i-1th intersection; Predict whether overflow queues will occur after the stop signal light at the current intersection is turned on; A multi-intersection traffic signal coordination control model is constructed when overflow queues occur, and the green signal ratio optimization adjustment strategy for each intersection is determined, including: Calculate the adjustment strategy of the green-signal ratio at each intersection; When the adjustment strategy is verified, the optimal adjustment strategy is formed; when the adjustment strategy is not verified, k=k+1 is set to continue to calculate the adjustment strategy for the green-to-signal ratio of each intersection; The adjustment strategies for calculating the green-signal ratio at each intersection include: Calculate and obtain the green-to-signal ratio of the pth phase in the k+1th signal cycle of the current intersection According to the green-to-signal ratio of the pth phase of the k+1th signal cycle at the current intersection The green signal ratio λ of the pth phase of the kth signal cycle at the current intersection i,k,p A green-to-signal ratio difference is formed; Dividing the green-to-signal ratio difference into m levels to form a green-to-signal ratio adjustment amount, and forming a green-to-signal ratio adjustment strategy according to the green-to-signal ratio adjustment amount; When the adjustment strategy is verified, forming the optimal adjustment strategy specifically includes: When κ>m, the green signal ratio adjustment strategy for upstream and downstream intersections with the smallest objective function value is the optimal strategy. When κ≤m, let κ=κ+1 to continue calculating the green signal ratio adjustment strategy for each intersection. The green signal ratio adjustment strategy for upstream and downstream intersections with the smallest objective function value is λ i,k+1,p ≥λ min ,p=1,…,P,i=1,…,n Where n is the number of upstream and downstream intersections; P is the phase number of the k+1th signal cycle at the ith intersection; The queue length of the pth phase in the k+1th signal cycle at intersection i; λ i,k+1,p is the green-to-signal ratio of the pth phase in the k+1th signal cycle of intersection i; L is the total loss time of the signal cycle; C is the signal cycle length; λ min The green signal ratio corresponding to the minimum traffic light time; The control signal of the traffic light at the upstream intersection is turned on according to the phase difference with the current intersection and the adjusted green signal ratio of the current intersection.
2. The overflow queue prediction and multi-intersection traffic signal coordination control method based on vehicle-road collaboration according to claim 1 is characterized in that: Real-time acquisition of the first reference data and the real-time driving data of the target specifically includes: Obtain the length of the convoy at different times in different phases of the intersection, and determine the number of vehicles stranded at the intersection at the end of the previous signal cycle in each phase of the intersection through the convoy length; The average speed of the vehicles entering the network at the upstream intersection and the current intersection is formed according to the average speed of the vehicles entering the network at the extension of the stop line of the upstream intersection exit; The average travel time of the fleet from the upstream intersection to the current intersection is calculated based on the distance between the upstream intersection and the current intersection and the average speed between the upstream intersection and the current intersection.
3. The overflow queue prediction and multi-intersection traffic signal coordination control method based on vehicle-road collaboration according to claim 1 is characterized in that: Predicting whether overflow queues will occur after the stop signal light at the current intersection is turned on specifically includes: Get the length of the queue of vehicles whose stop lights are on in the next signal cycle at the current intersection: According to the distance from the upstream intersection to the current intersection, a safe queue length is formed by the average head distance of the queued vehicles when the stop signal light is on; Whether overflow will occur at the current intersection is determined based on the length of the vehicle queue and the safety length when the stop signal light is on in the next signal cycle of the current intersection. If overflow does not occur, continue to determine whether overflow will occur in the next signal cycle.
4. A vehicle-road collaboration-based overflow queue prediction and multi-intersection traffic signal coordination control system, realizing a vehicle-road collaboration-based overflow queue prediction and multi-intersection traffic signal coordination control method as described in any one of claims 1-3, characterized in that: include: Data input module: used to obtain the real-time roadside perception data and real-time driving data of connected vehicles from the cloud control platform of the vehicle-road cooperative system; Overflow prediction module: predicts the arrival rate of vehicles entering the upstream intersection after the traffic signal light is activated to predict whether overflow queues will occur; Coordination control module: used to determine the optimization adjustment strategy of the green-to-signal ratio at multiple intersections for upstream and downstream related intersections where overflow queues are predicted to occur.
5. The overflow queue prediction and multi-intersection traffic signal coordination control system based on vehicle-road collaboration according to claim 4 is characterized in that: Also includes: Strategy output module: used to share the green signal ratio optimization adjustment strategy for multiple intersections to the traffic signal control system of the public security traffic police department through the cloud control basic platform of the vehicle-road cooperative system, and assist the traffic signal control system in timing optimization.
6. A device for predicting overflow queues and coordinating traffic signal control at multiple intersections based on vehicle-road collaboration, characterized in that: It includes a storage medium and a processor, the storage medium is used to store a computer program, and the processor is used to execute the computer program to implement the overflow queue prediction and multi-intersection traffic signal coordination control method based on vehicle-road collaboration as described in any one of claims 1 to 3.
