An algorithm, system and device for dynamic queue length perception and traffic signal control optimization at signalized intersections based on vehicle-road collaboration

Abstract

The present application relates to the technical field of intelligent traffic correlation, in particular to a signal intersection dynamic queue length sensing and traffic signal control optimization algorithm, system and device based on vehicle-road cooperation. One of the signal intersection dynamic queue length sensing and traffic signal control optimization algorithms based on vehicle-road cooperation comprises: under the condition of obtaining the current queue length of each phase of the intersection, calculating the minimum green light time required for the queue vehicles to be emptied which matches the current queue length of each phase of the intersection; forming an optimal green-to-red ratio adjustment strategy under the condition that the minimum green light time required for the queue vehicles to be emptied does not match the current green light timing; updating the current green light timing according to the optimal green-to-red ratio adjustment strategy.

Description

Technical Field

[0001] The present invention relates to the field of intelligent traffic-related technologies, and in particular to an algorithm, system, and device for dynamic queue length perception and traffic signal control optimization at a signalized intersection based on vehicle-road collaboration. Background Art

[0002] Urban arterial roads, the backbone of the transportation network, provide access for long-distance rapid transit and commuter traffic, yet they are the most frequent and severe congestion. Traffic congestion on urban signal-controlled arterial roads reflects not only the independent properties of the road sections themselves, but also the interplay and interconnectedness between them. In congestion, especially when queues overflow, distinct temporal and spatial characteristics emerge between sections. With the acceleration of urbanization and the continuous increase in the number of motor vehicles, the gap between road resources and traffic demand has become increasingly prominent. Saturated traffic conditions have become a common phenomenon, and traffic congestion has become a focus of public concern.

[0003] To achieve intelligent traffic management, road status data must be acquired. Existing technologies typically use fixed vehicle detectors, such as geomagnetic vehicle detectors, to obtain road condition data. However, fixed vehicle detectors cannot dynamically monitor queue lengths at signalized intersections. This results in traffic signal control optimization methods based on queue length estimation using vehicle detectors being non-adaptive, often leading to wasted green time or queue overflows due to short green time. Summary of the Invention

[0004] In response to the deficiencies of the prior art, the present application provides a dynamic queue length perception and traffic signal control optimization algorithm, system and device for signalized intersections based on vehicle-road collaboration. It aims to calculate the dynamic queue length based on the vehicle-road collaboration system according to the traffic flow perception data of each entrance lane and the timing plan of the traffic signal control system; calculate the minimum green light time required to clear the queued vehicles according to the actual queue length of each entrance lane of the signalized intersection; compare the minimum green light time with the green light time of the current timing plan to determine whether to increase or extend the green light time, and calculate the required extended green light time, so as to minimize the occurrence of secondary stops of queued vehicles and maximize the traffic efficiency of the signalized intersection. Specifically,

[0005] In one aspect, the present invention provides a dynamic queue length perception and traffic signal control optimization algorithm for signalized intersections based on vehicle-road collaboration, which is characterized by including:

[0006] When the current queue lengths at each phase of the intersection are obtained, the minimum green light time required to clear the queued vehicles that matches the current queue lengths at each phase of the intersection is calculated;

[0007] When the minimum green light time required to clear the queue of vehicles does not match the current green light timing, an optimal green light ratio adjustment strategy is formed;

[0008] Update the current green light timing according to the optimal green-to-signal ratio adjustment strategy.

[0009] Preferably, the above-mentioned signalized intersection dynamic queue length perception and traffic signal control optimization algorithm based on vehicle-road collaboration, wherein: when the current queue length of each phase of the intersection is obtained, calculating the minimum green light time required to clear the queued vehicles that matches the current queue length of each phase of the intersection specifically includes:

[0010] The calculation method for the minimum green light time required for the queue of vehicles to be cleared is:

[0011]

[0012] g′ i,k,p The minimum green light time required for the vehicles in the p-th phase of the k-th signal cycle at the i-th intersection to be cleared;

[0013] q i,k,p is the queue length at the pth phase of the kth signal cycle at the i-th intersection when the green light is on;

[0014] s i,k,p is the vehicle exit rate after the green light is turned on in the p-th phase of the k-th signal cycle at the i-th intersection;

[0015] d i,k,p is the arrival rate of vehicles entering the i-th intersection after the green light is turned on in the p-th phase of the k-th signal cycle.

[0016] Preferably, the above-mentioned signalized intersection dynamic queue length perception and traffic signal control optimization algorithm based on vehicle-road collaboration, wherein: forming an optimal green-to-signal ratio adjustment strategy when the minimum green light time required to clear the queued vehicles does not match the current green light timing specifically includes:

[0017] Obtaining queue length data for each phase of each signal cycle at each intersection, and forming a state space based on the queue length data;

[0018] Obtaining action set data for each phase of each signal cycle at each intersection, and forming a workspace based on the action set data;

[0019] Obtaining an average delay at the intersection, and forming a reward function based on the average delay;

[0020] According to the state space, work space and reward function, an intersection traffic control optimization model is formed;

[0021] An optimal green-to-signal ratio adjustment strategy is formed based on the intersection traffic control optimization model.

[0022] Preferably, the above-mentioned signal intersection dynamic queue length perception and traffic signal control optimization algorithm based on vehicle-road collaboration, wherein: the state space is s i,k =[q i,k,1 ,q i,k,2 ,…,q i,k,P ], where q i,k,p The queue length at the p-th phase of the k-th signal cycle at the th intersection;

[0023] The workspace is: a i,k ={a i,k,1 ,a i,k,2 ,…,a i,k,P};a i,k,p is the action set of the pth phase of the kth signal cycle at the i-th intersection, a i,k,p ={extend green light time, keep green light time unchanged, shorten green light time};

[0024] The reward function is formed by taking the average delay at the intersection:

[0025]

[0026] Among them, T i,k,p is the duration of the pth phase of the kth signal cycle at the i-th intersection;

[0027] λ i,k,p (n) is the kth signal cycle pth phase of the i-th intersection. Select action a from the action space. i,k Take the nth action a i,k,p (1) The green letter ratio after

[0028] g′ i,k,p (n) is the kth signal cycle pth phase of the i-th intersection. Select action a from the action space. i,k Take the nth action a i,k,p (n) The length of the green light after, if the action is to extend the green light time, g′ i,k,p (n) = g i,k,p (n)+Δt, if the action is to shorten the green light time, g′ i,k,p (n) = g i,k,p (n)-Δt;

[0029] x i,k,p (n) is the kth signal cycle pth phase of the i-th intersection. Select action a from the action space. i,k Take the nth action a i,k,p (n) after saturation,

[0030] q i,k,p is the maximum queue length of the p-th phase lane in the k-th signal cycle at the i-th intersection;

[0031] s ik,p is the saturation flow rate of the lane with the maximum queue length in the p-th phase of the k-th signal cycle at the i-th intersection.

[0032] γ∈[0,1) is a discount factor, which is used to assign different weights to the delay rewards obtained at different synchronization times;

[0033] r i,k (j) is the reward function.

[0034] Preferably, the above-mentioned signal intersection dynamic queue length perception and traffic signal control optimization algorithm based on vehicle-road collaboration, wherein: forming the optimal green signal ratio adjustment strategy according to the intersection traffic control optimization model specifically includes:

[0035] Q π* =max π* Q(s i,k (0),a i,k (1),a i,k (2),…,a i,k (n))

[0036] π * To determine the optimal green-to-credit ratio adjustment strategy.

[0037] On the other hand, the present application further provides a system for dynamic queue length perception and traffic signal control optimization at a signalized intersection based on vehicle-road collaboration, which includes:

[0038] Collection unit: collects the current queue situation at each phase of the intersection and forms the current queue length of each phase of the intersection for uploading;

[0039] The calculation unit calculates the minimum green light time required to clear the queued vehicles matching the current queue lengths of the respective phases of the intersection after obtaining the current queue lengths of the respective phases of the intersection;

[0040] The adjustment unit forms an optimal green-to-signal ratio adjustment strategy when the minimum green light time required to clear the queued vehicles does not match the current green light timing;

[0041] The update unit updates the current green light timing according to the optimal green-to-signal ratio adjustment strategy.

[0042] Preferably, in the above-mentioned signal intersection dynamic queue length perception and traffic signal control optimization system based on vehicle-road collaboration, the adjustment unit specifically includes:

[0043] A state space forming device, which obtains queue length data of each phase of each signal cycle at each intersection and forms a state space based on the queue length data;

[0044] The work space forming device obtains the action set data of each phase of each intersection in each signal cycle, and forms a work space according to the action set data;

[0045] The reward function forming device obtains the average delay of the intersection, and forms a reward function according to the average delay;

[0046] The adjustment strategy forming device forms an intersection traffic control optimization model according to the state space, the work space and the reward function;

[0047] An optimal green ratio adjustment strategy is formed according to the intersection traffic control optimization model.

[0048] In another aspect, the application further provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable in the processor, wherein the processor implements the above-mentioned signal intersection dynamic queue length perception and traffic signal control optimization algorithm based on vehicle-road cooperation when executing the computer program.

[0049] Finally, the application further provides a computer program product comprising computer readable code or a readable storage medium carrying computer readable code, wherein the processor in the electronic device executes the computer readable code to implement the above-mentioned signal intersection dynamic queue length perception and traffic signal control optimization algorithm based on vehicle-road cooperation when the computer readable code is executed in the processor of the electronic device.

[0050] Compared with the prior art, the application has the following beneficial effects:

[0051] The above-mentioned embodiment calculates the dynamic queue length based on the vehicle flow perception data of each approach and the timing scheme of the traffic signal control system according to the vehicle-road cooperation system; calculates the minimum green time required to meet the emptying of the queued vehicles according to the actual queue length of each approach of the signal intersection; compares the minimum green time with the current green time of the timing scheme, judges whether to adjust and increase the green time, and calculates the required extended green time, so as to reduce the occurrence of secondary parking of the queued vehicles to the greatest extent and maximize the passing efficiency of the signal intersection. The application does not depend on the position and number of vehicle detectors, has strong adaptability, can reduce or replace the on-site manual control of the police during the morning and evening peak, and saves manpower. BRIEF DESCRIPTION OF DRAWINGS

[0052] Figure 1 A flowchart of a signal intersection dynamic queue length perception and traffic signal control optimization algorithm based on vehicle-road cooperation provided by the embodiment of the application is shown in the figure;

[0053] Figure 2 A flowchart of a signal intersection dynamic queue length perception and traffic signal control optimization algorithm based on vehicle-road cooperation provided by the embodiment of the application is shown in the figure;

[0054] Figure 3 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0056] On the one hand, if Figure 1 As shown, the present invention provides a dynamic queue length perception and traffic signal control optimization algorithm for signalized intersections based on vehicle-road collaboration, which includes:

[0057] Step S110: When the current queue lengths of each phase at the intersection are obtained, the minimum green light time required to clear the queued vehicles matching the current queue lengths of each phase at the intersection is calculated;

[0058] Step S120: When the minimum green light time required to clear the queue does not match the current green light timing, an optimal green-to-signal ratio adjustment strategy is formed. Schematically, the cloud control platform of the vehicle-road cooperative system obtains the signal light timing plan of the intersection in real time, including the green light duration of different phases at different times at the intersection, i.e., g i,k =[g i,k,1 ,g i,k,2 ,...,g i,k,P ], g i,k,p is the green light duration of the p-th phase in the k-th signal cycle at the i-th intersection, p=1,...,P, where P is the number of phases in the k-th signal cycle at the i-th intersection.

[0059] Compare the minimum green light time calculated for each phase of the intersection with the green light time of the current timing plan. The minimum green light time required for the pth phase of the kth signal cycle at the i-th intersection to clear the queued vehicles is g′ i,k,p , the green light duration of the pth phase in the kth signal cycle at the i-th intersection is g i,k,p ,like g′ i,k,p ≤g i,k,p , keep the current timing plan unchanged; otherwise, execute step S120.

[0060] Step S130: Update the current green light timing according to the optimal green light ratio adjustment strategy.

[0061] The above embodiment is based on the vehicle-road cooperation system to calculate the dynamic queue length according to the traffic flow sensing data of each approach and the timing scheme of the traffic signal control system; to calculate the minimum green light time required to meet the emptying of the queued vehicles according to the actual queue length of each approach of the signal intersection; to compare the minimum green light time with the current timing scheme green light time, to judge whether to adjust and increase the green light time, and to calculate the required extended green light time, so as to maximize the traffic efficiency of the signal intersection. It does not depend on the position and number of vehicle detectors, and has strong adaptability; it can reduce or replace the on-site manual control of the police during peak hours, and saves manpower.

[0062] As a further preferred embodiment, the above-mentioned signal intersection dynamic queue length sensing and traffic signal control optimization algorithm based on vehicle-road cooperation, wherein: step S110, under the condition of obtaining the current queue length of each phase of the intersection, the calculation of the minimum green light time required to form and empty the queued vehicles matching the current queue length of each phase of the intersection specifically includes,

[0063] The calculation method of the minimum green light time required for the queued vehicles to empty is:

[0064]

[0065] g′ i,k,p is the minimum green light time required for the queued vehicles of the pth phase of the kth signal cycle of the ith intersection to empty;

[0066] q i,k,p is the queue length of the pth phase of the kth signal cycle of the ith intersection at the green light opening time;

[0067] s i,k,p is the vehicle exit rate after the green light of the pth phase of the kth signal cycle of the ith intersection is started;

[0068] d i,k,p is the arrival rate of the vehicles entering after the green light of the pth phase of the kth signal cycle of the ith intersection is started.

[0069] Further, the above-mentioned signal intersection dynamic queue length sensing and traffic signal control optimization algorithm based on vehicle-road cooperation, wherein: step S120, under the condition that the minimum green light time required for the queued vehicles to empty does not match the current green light timing, the formation of the optimal green signal ratio adjustment strategy specifically includes: as shown in Figure 2

[0070] Step S1201, obtain the queue length data of each phase of each signal cycle of each intersection, and form a state space according to the queue length data; the state space is si,k = [q i,k,1 , q i,k,2 ​,...,q i,k,P ], where q i,k,p The queue length of the p-th phase in the k-th signal cycle at the i-th intersection;

[0071] Step S1202: Obtain action set data for each phase of each signal cycle at each intersection, and form a workspace based on the action set data; the workspace is: ai,k ={a i,k,1 ,a i,k,2 ,...,a i,k,P};a i,k,p is the action set of the pth phase of the kth signal cycle at the i-th intersection, a i,k,p ={extend green light time, keep green light time unchanged, shorten green light time};

[0072] Step S1203: Obtain the average delay of the intersection, and form a reward function based on the average delay; the reward function:

[0073]

[0074] Among them, T i,k,p is the duration of the pth phase of the kth signal cycle at the i-th intersection;

[0075] λ i,k,p (n) is the kth signal cycle pth phase of the i-th intersection. Select action a from the action space. i,k Take the nth action a i,k,p (1) The green letter ratio after

[0076] g′ i,k,p (n) is the kth signal cycle pth phase of the i-th intersection. Select action a from the action space. i,k Take the nth action a i,k,p (n) The length of the green light after, if the action is to extend the green light time, g′ i,k,p (n) = g i,k,p (n)+Δt, if the action is to shorten the green light time, g′ i,k,p (n) = g i,k,p (n)-Δt;

[0077] x i,k,p (n) is the kth signal cycle pth phase of the i-th intersection. Select action a from the action space. i,k Take the nth action a i,k,p (n) after saturation,

[0078] q i,k,p is the maximum queue length of the p-th phase lane in the k-th signal cycle at the i-th intersection;

[0079] si,k,p is the saturation flow rate of the lane with the maximum queue length in the p-th phase of the k-th signal cycle at the i-th intersection.

[0080] γ∈[0,1) is a discount factor, which is used to assign different weights to the delay rewards obtained at different synchronization times;

[0081] r i,k (j) is the reward function.

[0082] Step S1204: forming an intersection traffic control optimization model based on the state space, workspace, and reward function, wherein the intersection traffic control model is based on Markov decision making and is formed in combination with the state space, workspace, and reward function.

[0083] Step S1205: forming an optimal green-to-signal ratio adjustment strategy based on the intersection traffic control optimization model, specifically including:

[0084] Q π* =max π* Q(s i,k (0),a i,k (1),a i,k (2),...,a i,k (n))

[0085] π * To determine the optimal green-to-credit ratio adjustment strategy.

[0086] Here is an example implementation:

[0087] Assume that the initial state before signal control optimization is s i,k (0), select action a from the action space i,k (1), after execution, the state space becomes s i,k (1), get delay reward r i,k (0),

[0088]

[0089] d i,k,p (1)——At the kth signal cycle and the pth phase of the i-th intersection, action a is selected from the action space. i,k Take the first action a i,k,p (1) Delay after; d i,k,p (0)——initial state s of the pth phase in the kth signal cycle of the i-th intersection i,k (0) delay; k p ——The value depends on the traffic flow in the pth phase. The phase weight is set larger when the traffic flow is large, and smaller when the traffic flow is small; p=1,...,P, P is the phase number of the kth signal cycle at the i-th intersection

[0090] Delay d i,k,p (1) as an example, the calculation formula is as follows: Consists of two items.

[0091]

[0092]

[0093]

[0094] Where:

[0095] T i,k,p is the duration of the pth phase of the kth signal cycle at the i-th intersection;

[0096] λ i,k,p (1) Select action a from the action space for the pth phase of the kth signal cycle at the i-th intersection i,k Take the first action a i,k,p (1) The green-to-signal ratio after i,k,p (1) = g′ i,k,p (1) / T i,k,p , g′ i,k,p (1) Select action a from the action space for the pth phase of the kth signal cycle at the i-th intersection i,k Take the first action a i,k,p (1) The green light duration after that, if the action is to extend the green light time, g′ i,k,p (1) = g i,k,p (1)+Δt, if the action is to shorten the green light time, g′ i,k,p (1) = g i,k,p (1)-Δt;

[0097] x i,k,p (1) Select action a from the action space for the pth phase of the kth signal cycle at the i-th intersection i,k Take the first action a i,k,p (1) after saturation, x i,k,p (1) = q i,k,p / (s i,k,p ×λ i,k,p (1)), q i,k,p is the maximum queue length of the p-th phase lane in the k-th signal cycle at the i-th intersection; s i,k,p is the saturation flow rate of the lane with the maximum queue length in the p-th phase of the k-th signal cycle at the i-th intersection.

[0098] Similarly, from the action space through a series of actions {a i,k (1),a i,k (2),...}After execution, the state space becomes si,k (n), the obtained delay reward.

[0099]

[0100] Example two

[0101] In another aspect, the present application provides a signal intersection dynamic queue length perception and traffic signal control optimization system based on vehicle-road cooperation, which comprises:

[0102] The acquisition unit acquires the current queue situation of the intersection in each phase and forms a current queue length upload of each phase of the intersection. The acquisition unit can be a millimeter wave radar, a radar and video integrated machine, etc. The millimeter wave radar and the radar and video integrated machine obtain the traffic flow and queue length of different phases of the signal intersection at different times, especially the queue length of different phases of the intersection at the green light opening time. Therefore, the number of vehicles passing through the intersection during the green light period of each phase of the signal intersection can be known.

[0103] The calculation unit calculates the minimum green light time required for the queue vehicles to be emptied, which matches the current queue length of each phase of the intersection, under the condition of obtaining the current queue length of each phase of the intersection.

[0104] The adjustment unit forms an optimal green-to-signal ratio adjustment strategy under the condition that the minimum green light time required for the queue vehicles to be emptied does not match the current green light timing.

[0105] The update unit updates the current green light timing according to the optimal green-to-signal ratio adjustment strategy.

[0106] As a further preferred embodiment, the above-mentioned signal intersection dynamic queue length perception and traffic signal control optimization algorithm based on vehicle-road cooperation, wherein the adjustment unit specifically comprises:

[0107] The state space forming device obtains the queue length data of each phase of each signal cycle of each intersection, and forms a state space according to the queue length data.

[0108] The working space forming device obtains the action set data of each phase of each signal cycle of each intersection, and forms a working space according to the action set data.

[0109] The reward function forming device calculates the average delay of the intersection to form a reward function.

[0110] The adjustment strategy forming device forms an intersection traffic control optimization model according to the state space, working space and reward function.

[0111] The optimal green-to-signal ratio adjustment strategy is formed according to the intersection traffic control optimization model.

[0112] The working principle of the above-mentioned signal intersection dynamic queue length perception and traffic signal control optimization system based on vehicle-road collaboration is the same as the working principle of the signal intersection dynamic queue length perception and traffic signal control optimization method based on vehicle-road collaboration provided in Example 1, and will not be repeated here.

[0113] Example 3

[0114] An embodiment of the present application provides an electronic device, into which a control device based on a game running environment provided by an embodiment of the present application can be integrated. Figure 3 Schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3 As shown, this embodiment provides an electronic device 400, which includes: one or more processors 420; a storage device 410 for storing one or more programs. When the one or more programs are executed by the one or more processors 420, the one or more processors 420 implement:

[0115] When the current queue lengths at each phase of the intersection are obtained, the minimum green light time required to clear the queued vehicles that matches the current queue lengths at each phase of the intersection is calculated;

[0116] When the minimum green light time required to clear the queue of vehicles does not match the current green light timing, an optimal green light ratio adjustment strategy is formed;

[0117] Update the current green light timing according to the optimal green-to-signal ratio adjustment strategy.

[0118] like Figure 3 As shown, the electronic device 400 includes a processor 420, a storage device 410, an input device 430, and an output device 440; the number of processors 420 in the electronic device can be one or more. Figure 3 In the figure, a processor 420 is used as an example; the processor 420, the storage device 410, the input device 430 and the output device 440 in the electronic device can be connected via a bus or other means. Figure 3 The connection via bus 450 is taken as an example.

[0119] The storage device 410, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and module units, such as program instructions corresponding to the control method based on the game running environment in the embodiment of the present application.

[0120] The storage device 410 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function; the data storage area may store data created based on the use of the terminal, etc. Furthermore, the storage device 410 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state memory device. In some instances, the storage device 410 may further include a memory remotely located relative to the processor 420, and such remote memory may be connected via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0121] The input device 430 may be used to receive input numbers, character information or voice information, and generate key signal input related to user settings and function control of the electronic device. The output device 440 may include a display screen, a speaker and other devices.

[0122] like Figure 3 As shown, the electronic device 400 includes a processor 420, a storage device 410, an input device 430, and an output device 440; the number of processors 420 in the electronic device can be one or more. Figure 3 In the figure, a processor 420 is used as an example; the processor 420, the storage device 410, the input device 430 and the output device 440 in the electronic device can be connected via a bus or other means. Figure 3 The connection via bus 450 is taken as an example.

[0123] The storage device 410, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and module units, such as program instructions corresponding to the control method based on the game running environment in the embodiment of the present application.

[0124] The storage device 410 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function; the data storage area may store data created based on the use of the terminal, etc. Furthermore, the storage device 410 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state memory device. In some instances, the storage device 410 may further include a memory remotely located relative to the processor 420, and such remote memory may be connected via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0125] The input device 430 may be used to receive input numbers, character information or voice information, and generate key signal input related to user settings and function control of the electronic device. The output device 440 may include a display screen, a speaker and other devices.

[0126] Example 4

[0127] In some embodiments, the methods described above may be implemented as a computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions for executing various aspects of the present disclosure. Specifically:

[0128] When the current queue lengths at each phase of the intersection are obtained, the minimum green light time required to clear the queued vehicles that matches the current queue lengths at each phase of the intersection is calculated;

[0129] When the minimum green light time required to clear the queue of vehicles does not match the current green light timing, an optimal green light ratio adjustment strategy is formed;

[0130] Update the current green light timing according to the optimal green-to-signal ratio adjustment strategy.

[0131] The computer-readable storage medium mentioned above can be a tangible device that can hold and store instructions used by an instruction execution device. The computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. The computer-readable storage medium used herein is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through an electrical wire.

[0132] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0133] The computer program instructions for performing the disclosed operation can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data or source code or the object code written in any combination of one or more programming languages, wherein the programming languages ​​include object-oriented programming languages, and conventional procedural programming languages.Computer-readable program instructions can be performed completely on the user's computer, partially on the user's computer, performed as an independent software package, partly on the user's computer and partly on a remote computer, or performed completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer by any type of network-including local area network (LAN) or wide area network (WAN), or can be connected to an external computer (such as utilizing an Internet service provider to connect by the Internet). In certain embodiments, by utilizing the state information of computer-readable program instructions to carry out personalized customization electronic circuits, such as programmable logic circuits, field programmable gate arrays (FPGAs) or programmable logic arrays (PLA), this electronic circuit can perform computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0134] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0135] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0136] The flow diagrams and the block diagrams in the drawings are presented to illustrate the architecture, functionality, and operation of possible implementations of devices, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flow diagrams and the block diagrams can represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logic functions. In some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and

[0137] Embodiments of the present disclosure have been described above, and the description is intended to be illustrative of the embodiments and not restrictive. Many modifications and variations of the described embodiments are possible and are within the scope of the disclosure. The selection of terms is intended to best describe the principles of the embodiments, practical application, or technical improvements over the technology found in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A dynamic queue length perception and traffic signal control optimization algorithm for signalized intersections based on vehicle-road collaboration, characterized by: include: When the current queue lengths at each phase of the intersection are obtained, the minimum green light time required to clear the queued vehicles that matches the current queue lengths at each phase of the intersection is calculated; Forming an optimal green-to-signal ratio adjustment strategy when the minimum green light time required to clear queued vehicles does not match the current green light timing, including: obtaining queue length data for each phase of each signal cycle at each intersection, and forming a state space based on the queue length data; obtaining action set data for each phase of each signal cycle at each intersection, and forming a workspace based on the action set data; obtaining the average delay of the intersection, and forming a reward function based on the average delay; forming an intersection traffic control optimization model based on the state space, workspace, and reward function; and forming an optimal green-to-signal ratio adjustment strategy based on the intersection traffic control optimization model. The state space is s i,k =[q i,k, 1,q i,k, 2,…,q i,k, P], where q i,k,p The queue length of the p-th phase in the k-th signal cycle at the i-th intersection; The workspace is: a i,k ={a i,k,1 ,a i,k,2 ,…,a i,k,P };a i,k,p is the action set of the pth phase of the kth signal cycle at the i-th intersection, a i,k,p ={extend green light time, keep green light time unchanged, shorten green light time}; The reward function is formed by taking the average delay at the intersection: Among them, T i,k,p is the duration of the pth phase of the kth signal cycle at the i-th intersection; λ i,k,p (n) is the kth signal cycle pth phase of the i-th intersection. Select action a from the action space. i,k Take the nth action a i,k,p (1) The green letter ratio after g′ i,k,p (n) is the kth signal cycle pth phase of the i-th intersection. Select action a from the action space. i,k Take the nth action a i,k,p (n) The length of the green light after, if the action is to extend the green light time, g′ i,k,p (n) = g i,k,p (n)+Δt, if the action is to shorten the green light time, g′ i,k,p (n) = g i,k,p (n)-Δt; x i,k,p (n) is the kth signal cycle pth phase of the i-th intersection. Select action a from the action space. i,k Take the nth action a i,k,p (n) after saturation, q i,k,p is the maximum queue length of the p-th phase lane in the k-th signal cycle at the i-th intersection; s i,k,p is the saturation flow rate of the lane with the largest queue length in the p-th phase of the k-th signal cycle at the i-th intersection; γ∈[0,1) is the discount factor; r i,k (j) is the reward function; Update the current green light timing according to the optimal green-to-signal ratio adjustment strategy.

2. The algorithm for dynamic queue length perception and traffic signal control optimization at signalized intersections based on vehicle-road collaboration according to claim 1 is characterized by: When the current queue length of each phase of the intersection is obtained, the minimum green light time required to clear the queued vehicles that matches the current queue length of each phase of the intersection is calculated, specifically including: The calculation method for the minimum green light time required for the queue of vehicles to be cleared is: g′ i,k,p The minimum green light time required for the vehicles in the p-th phase of the k-th signal cycle at the i-th intersection to be cleared; q i,k,p is the queue length at the pth phase of the kth signal cycle at the i-th intersection when the green light is on; s i,k,p is the vehicle exit rate after the green light is turned on in the p-th phase of the k-th signal cycle at the i-th intersection; d i,k,p is the arrival rate of vehicles entering the i-th intersection after the green light is turned on in the p-th phase of the k-th signal cycle.

3. The algorithm for dynamic queue length perception and traffic signal control optimization at signalized intersections based on vehicle-road collaboration according to claim 1 is characterized by: The optimal green-to-signal ratio adjustment strategy formed according to the intersection traffic control optimization model specifically includes: Q π* =max π* Q(s i,k (0),a i,k (1),a i,k (2),…,a i,k (n)) π * To determine the optimal green-to-credit ratio adjustment strategy.

4. A signal intersection dynamic queue length perception and traffic signal control optimization system based on vehicle-road collaboration, characterized by: include: Collection unit: collects the current queue situation at each phase of the intersection and forms the current queue length of each phase of the intersection for uploading; The calculation unit calculates the minimum green light time required to clear the queued vehicles matching the current queue lengths of the respective phases of the intersection after obtaining the current queue lengths of the respective phases of the intersection; An adjustment unit forms an optimal green-to-signal ratio adjustment strategy when the minimum green light time required to clear the queued vehicles does not match the current green light timing, including: obtaining queue length data for each phase of each signal cycle at each intersection, and forming a state space based on the queue length data; obtaining action set data for each phase of each signal cycle at each intersection, and forming a workspace based on the action set data; obtaining an average delay at the intersection, and forming a reward function based on the average delay; forming an intersection traffic control optimization model based on the state space, workspace, and reward function; and forming an optimal green-to-signal ratio adjustment strategy based on the intersection traffic control optimization model. The state space is s i,k =[q i,k, 1,q i,k, 2,…,q i,k, P], where q i,k,p The queue length of the p-th phase in the k-th signal cycle at the i-th intersection; The workspace is: a i,k ={a i,k,1 ,a i,k,2 ,…,a i,k,P };a i,k,p is the action set of the pth phase of the kth signal cycle at the i-th intersection, a i,k,p ={extend green light time, keep green light time unchanged, shorten green light time}; The reward function is formed by taking the average delay at the intersection: Among them, T i,k,p is the duration of the pth phase of the kth signal cycle at the i-th intersection; λ i,k,p (n) is the kth signal cycle pth phase of the i-th intersection. Select action a from the action space. i,k Take the nth action a i,k,p (1) The green letter ratio after g′ i,k,p (n) is the kth signal cycle pth phase of the i-th intersection. Select action a from the action space. i,k Take the nth action a i,k,p (n) The length of the green light after, if the action is to extend the green light time, g′ i,k,p (n) = g i,k,p (n)+Δt, if the action is to shorten the green light time, g′ i,k,p (n) = g i,k,p (n)-Δt; x i,k,p (n) is the kth signal cycle pth phase of the i-th intersection. Select action a from the action space. i,k Take the nth action a i,k,p (n) after saturation, q i,k,p is the maximum queue length of the p-th phase lane in the k-th signal cycle at the i-th intersection; s i,k,p is the saturation flow rate of the lane with the largest queue length in the p-th phase of the k-th signal cycle at the i-th intersection; γ∈[0,1) is the discount factor; r i,k (j) is the reward function; The update unit updates the current green light timing according to the optimal green-to-signal ratio adjustment strategy.

5. The system for dynamic queue length perception and traffic signal control optimization at signalized intersections based on vehicle-road collaboration according to claim 4 is characterized by: The adjustment unit specifically includes: A state space forming device, which obtains queue length data of each phase of each signal cycle at each intersection and forms a state space according to the queue length data; A workspace forming device, which obtains action set data of each phase of each signal cycle of each intersection and forms a workspace according to the action set data; a reward function forming device for obtaining an average delay at the intersection and forming a reward function based on the average delay; An adjustment strategy forming device forms an intersection traffic control optimization model based on the state space, workspace, and reward function; An optimal green-to-signal ratio adjustment strategy is formed based on the intersection traffic control optimization model.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein: When the processor executes the computer program, it implements a signal intersection dynamic queue length perception and traffic signal control optimization algorithm based on vehicle-road collaboration as described in any one of claims 1-3.

7. A computer program product, characterized in that It includes computer-readable code, or a readable storage medium carrying computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes an algorithm for implementing a dynamic queue length perception and traffic signal control optimization algorithm for a signalized intersection based on vehicle-road collaboration as described in any one of claims 1 to 3.

Images