Intersection signal control scheme optimization method and device, equipment and storage medium

Abstract

The embodiment of the invention provides an optimization method and device of an intersection signal control scheme, equipment and a storage medium. The method comprises the steps of collecting traffic state data of each flow direction of an intersection; the traffic state data is utilized, the green light time of each flow direction of the intersection is used as a variable, an objective function of the intersection is constructed, and the objective function at least comprises the weighted sum of a plurality of variable functions in the following variable functions: a green light utilization rate function, a travel time function and a waiting time function; and optimizing the target function of the intersection through a gradient descent method to obtain the optimized green light time of each flow direction of the intersection. According to the technical scheme provided by the embodiment of the invention, the target function is constructed by monitoring the traffic state data of the intersection in real time, and the green light time of the signal lamp is adaptively adjusted by optimizing the target function based on gradient descent, so that the green light utilization rate is improved, and the queuing time is reduced, thereby optimizing the traffic signal control.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to an optimization method, device, equipment and storage medium for an intersection signal control solution. Background Art

[0002] Traditional traffic signal control methods often use fixed time cycles, which are difficult to adapt to complex traffic flow changes. The green light utilization rate refers to the ratio of the number of vehicles that actually pass through the green light time to the theoretical maximum number of vehicles that pass through in a signal control cycle. By optimizing the green light utilization rate, the signal light time can be used more effectively and the road capacity can be improved. However, the existing traffic signal optimization methods have the following problems:

[0003] 1. Relying on manual experience and fixed parameters, lacking adaptability.

[0004] 2. Unable to effectively handle dynamically changing traffic flow.

[0005] 3. The optimization process is complex, the amount of calculation is large, and it is difficult to apply in real time. Summary of the invention

[0006] In view of this, the embodiment of the present application provides an optimization method, device, equipment and storage medium for an intersection signal control scheme. The technical solution of the embodiment of the present application monitors the traffic status data of the intersection in real time, constructs an objective function based on the data, and adaptively adjusts the green light time of the signal light based on the objective function based on gradient descent optimization, thereby improving the green light utilization rate, reducing the queuing time and optimizing the traffic signal control. The gradient descent method of the embodiment of the present application simplifies the design of the optimization model, avoids the explosive growth of the optimization parameters, can complete the optimization calculation in a shorter time, requires less computing power, and has the significance of universal application.

[0007] In the first aspect, an embodiment of the present application provides an optimization method for an intersection signal control scheme, comprising: collecting traffic status data for each flow direction of the intersection; utilizing the traffic status data and taking the green light time for each flow direction of the intersection as a variable to construct an objective function of the intersection, wherein the objective function includes at least a weighted sum of several variable functions of the following variable functions: a green light utilization function, a travel time function, and a waiting time function; optimizing the objective function of the intersection by a gradient descent method to obtain the optimized green light time for each flow direction of the intersection.

[0008] From the above, by real-time monitoring of the traffic status data of the intersection, the objective function is constructed based on it. The green light time of the traffic light is adaptively adjusted based on the objective function based on gradient descent optimization, the green light utilization rate is improved, the queuing time is reduced, and the traffic signal control is optimized; and the gradient descent method is used to simplify the design of the optimization model, avoid the explosive growth of the optimization parameters, and be able to complete the optimization calculation in a shorter time, with less computing power requirements, which has universal application significance.

[0009] In a possible implementation of the first aspect, a method for optimizing an intersection signal control scheme further includes: obtaining a signal control cycle of the intersection according to an optimized green light time of each flow direction of the intersection.

[0010] From the above, on the basis of optimizing the green light time of each flow direction at the intersection by the gradient descent method, the signal control cycle of the intersection is also optimized at the same time, further improving the smoothness of the intersection.

[0011] In a possible implementation of the first aspect, the objective function of the intersection is optimized by the gradient descent method to obtain the optimized green light time for each flow direction at the intersection, specifically comprising: in a green light time space with the green light time of each flow direction at the intersection as a dimension, starting from a point with the current green light time of each flow direction at the intersection as a coordinate, optimizing the objective function by the gradient descent method to obtain the optimized green light time for each flow direction at the intersection, wherein the gradient is the gradient of the objective function in the green light time space.

[0012] From the above, the objective function is optimized by gradient descent in the green light time space with the green light time of each flow direction at the intersection as the dimension, and the optimized green light time of each flow direction at the intersection is obtained. This simplifies the design of the optimization model, avoids the explosive growth of optimization parameters, can complete the optimization calculation in a shorter time, requires less computing power, and has universal application significance.

[0013] In a possible implementation of the first aspect, the objective function is optimized by a gradient descent method, specifically including: obtaining the gradient of the current point in the green light time space; changing the green light time of each flow direction according to a set ratio along the gradient direction of the current point, and taking the point corresponding to the green light time of each flow direction after the change in the green light time space as the new current point; comparing the objective function value of the current point before and after the change; when the absolute value of the change in the objective function value is less than a preset threshold or the number of optimization iterations reaches a maximum number of iterations, the green light time of each flow direction at this time is used as the optimized green light time of the flow direction.

[0014] From the above, in the green light time space, according to the gradient descent of the objective function to the green light time matrix, the target condition is optimized when the absolute value of the change in the objective function value before and after the gradient descent is less than the preset threshold or reaches the maximum number of iterations, which can both control the objective function and limit the computing power requirements.

[0015] In a possible implementation of the first aspect, the traffic status data is used, and the green light time of each flow direction at the intersection is used as a variable to construct a green light utilization function of the intersection, specifically including: using the average headway time in the traffic status data of each flow direction at the intersection, and taking the green light time of each flow direction as a variable to obtain the maximum flow function of the flow direction at the intersection, and the maximum flow function of each flow direction changes positively with the green light time of the flow direction; using the traffic status data of each flow direction at the intersection, and taking the green light time of each flow direction as a variable to obtain the traffic flow function of the flow direction at the intersection; according to the traffic flow function and the maximum flow function of each flow direction at the intersection, the green light utilization function of the intersection is obtained.

[0016] From the above, the green light utilization function of the intersection is obtained by the ratio of the sum of the traffic flow functions of each flow direction of the intersection to the sum of the maximum flow function, so that the green light utilization function can comprehensively evaluate the green light utilization of the entire intersection and avoid the influence of the flow direction with smaller flow.

[0017] In a possible implementation of the first aspect, the traffic status data is used to construct a travel time function or a waiting time function of the intersection, specifically including: using the traffic status data, taking the green light time of each flow direction as a variable, to construct a first variable function of each flow direction of the intersection, the first variable function being a travel time function or a waiting time function; and constructing the first variable function of the intersection by taking the sum of the first variable functions of each flow direction of the intersection.

[0018] From the above, by accumulating the travel time functions and waiting time functions of each flow direction at the intersection, the travel time function and waiting time function of the intersection are obtained, so that the travel time function of the intersection can comprehensively evaluate the vehicle travel time of the entire intersection, and the waiting time function of the intersection can comprehensively evaluate the vehicle waiting time of the entire intersection.

[0019] In a possible implementation of the first aspect, collecting traffic status data for each flow direction at the intersection specifically includes: collecting the traffic status data at the beginning of each optimization cycle, and each optimization cycle includes at least one signal control cycle; the method also includes: sending the optimized signal control scheme to the traffic light at the intersection at the end of each optimization cycle, and starting the next optimization cycle.

[0020] As described above, by collecting traffic status data at the beginning of each optimization cycle and generating an optimized signal control plan, sending the signal control plan to the traffic light at the intersection at the end of each optimization cycle and starting the next optimization cycle, real-time adaptive adjustment of the signal control plan at the intersection can be achieved.

[0021] In a possible implementation manner of the first aspect, the traffic status data includes at least one of the following data for each flow direction: traffic flow, travel time, waiting time, speed, and headway.

[0022] As shown above, travel time and waiting time are used to compare the signal control schemes before and after optimization, traffic flow and headway are used to generate green light utilization, and traffic flow, speed and headway are also used to construct the optimization objective function.

[0023] In the second aspect, an embodiment of the present application provides an optimization device for an intersection signal control scheme, including: a data acquisition module, used to collect traffic status data of each flow direction of the intersection; a target construction module, used to use the traffic status data, taking the green light time of each flow direction of the intersection as a variable, to construct an objective function of the intersection, wherein the objective function at least includes a weighted sum of several variable functions of the following variable functions: a green light utilization function, a travel time function, and a waiting time function; a signal control optimization module, used to optimize the objective function of the intersection by a gradient descent method to obtain the optimized green light time for each flow direction of the intersection.

[0024] From the above, by real-time monitoring of the traffic status data of the intersection, the objective function is constructed based on it. The green light time of the traffic light is adaptively adjusted based on the objective function based on gradient descent optimization, the green light utilization rate is improved, the queuing time is reduced, and the traffic signal control is optimized; and the gradient descent method is used to simplify the design of the optimization model, avoid the explosive growth of the optimization parameters, and be able to complete the optimization calculation in a shorter time, with less computing power requirements, which has universal application significance.

[0025] In a possible implementation of the second aspect, the signal control optimization module is further used to obtain the signal control cycle of the intersection according to the optimized green light time of each flow direction of the intersection.

[0026] From the above, on the basis of optimizing the green light time of each flow direction at the intersection by the gradient descent method, the signal control cycle of the intersection is also optimized at the same time, further improving the smoothness of the intersection.

[0027] In a possible implementation of the second aspect, when the signal control optimization module optimizes the objective function of the intersection by the gradient descent method to obtain the optimized green light time for each flow direction at the intersection, it is specifically used to include: in the green light time space with the green light time of each flow direction at the intersection as the dimension, starting from the point with the current green light time of each flow direction at the intersection as the coordinate, optimizing the objective function by the gradient descent method to obtain the optimized green light time for each flow direction at the intersection, and the gradient is the gradient of the objective function in the green light time space.

[0028] From the above, the objective function is optimized by gradient descent in the green light time space with the green light time of each flow direction at the intersection as the dimension, and the optimized green light time of each flow direction at the intersection is obtained. This simplifies the design of the optimization model, avoids the explosive growth of optimization parameters, can complete the optimization calculation in a shorter time, requires less computing power, and has universal application significance.

[0029] In a possible implementation of the second aspect, when the signal control optimization module optimizes the objective function in the green light time space by the gradient descent method, it is specifically used to include: obtaining the gradient of the current point in the green light time space; changing the green light time of each flow direction according to a set proportion along the gradient direction of the current point, and taking the point corresponding to the green light time of each flow direction after the change in the green light time space as the new current point; comparing the objective function value of the current point before and after the change; when the absolute value of the change in the objective function value is less than a preset threshold or the number of optimization attempts reaches the maximum number of iterations, the green light time of each flow direction at this time is used as the optimized green light time of the flow direction.

[0030] From the above, in the green light time space, according to the gradient descent of the objective function to the green light time matrix, the target condition is optimized when the absolute value of the change in the objective function value before and after the gradient descent is less than the preset threshold or reaches the maximum number of iterations, which can both control the objective function and limit the computing power requirements.

[0031] In a possible implementation of the second aspect, when the target construction module uses the traffic status data and takes the green light time of each flow direction of the intersection as a variable to construct the green light utilization function of the intersection, it is specifically used to include: using the average headway time in the traffic status data of each flow direction of the intersection and taking the green light time of each flow direction as a variable to obtain the maximum flow function of the flow direction of the intersection, and the maximum flow function of each flow direction changes positively with the green light time of the flow direction; using the traffic status data of each flow direction of the intersection and taking the green light time of each flow direction as a variable to obtain the traffic flow function of the flow direction of the intersection; obtaining the green light utilization function of the intersection based on the traffic flow function and the maximum flow function of each flow direction of the intersection.

[0032] From the above, the green light utilization function of the intersection is obtained by the ratio of the sum of the traffic flow functions of each flow direction of the intersection to the sum of the maximum flow function, so that the green light utilization function can comprehensively evaluate the green light utilization of the entire intersection and avoid the influence of the flow direction with smaller flow.

[0033] In a possible implementation of the second aspect, when the target construction module uses the traffic status data to construct the travel time function or the waiting time function of the intersection, it is specifically used to include: using the traffic status data, taking the green light time of each flow direction as a variable, to construct a first variable function of each flow direction of the intersection, the first variable function being a travel time function or a waiting time function; and constructing the first variable function of the intersection by the sum of the first variable functions of each flow direction of the intersection.

[0034] From the above, by accumulating the travel time functions and waiting time functions of each flow direction at the intersection, the travel time function and waiting time function of the intersection are obtained, so that the travel time function of the intersection can comprehensively evaluate the vehicle travel time of the entire intersection, and the waiting time function of the intersection can comprehensively evaluate the vehicle waiting time of the entire intersection.

[0035] In a possible implementation of the second aspect, the data acquisition module is specifically used to collect the traffic status data at the beginning of each optimization cycle, and each optimization cycle includes at least one signal control cycle; the optimization device also includes: a scheme sending module, which is used to send the optimized signal control scheme to the traffic light at the intersection at the end of each optimization cycle and start the next optimization cycle.

[0036] As described above, by collecting traffic status data at the beginning of each optimization cycle and generating an optimized signal control plan, sending the signal control plan to the traffic light at the intersection at the end of each optimization cycle and starting the next optimization cycle, real-time adaptive adjustment of the signal control plan at the intersection can be achieved.

[0037] In a possible implementation manner of the second aspect, the traffic status data includes at least one of the following data for each flow direction: traffic flow, travel time, waiting time, speed, and headway.

[0038] As shown above, travel time and waiting time are used to compare the signal control schemes before and after optimization, traffic flow and headway are used to generate green light utilization, and traffic flow, speed and headway are also used to construct the optimization objective function.

[0039] In a third aspect, an embodiment of the present application provides a traffic light control device for an intersection, comprising the optimization device described in any implementation manner of the second aspect.

[0040] In a fourth aspect, an embodiment of the present application provides a computing device, including:

[0041] bus;

[0042] A communication interface connected to the bus;

[0043] at least one processor connected to the bus; and

[0044] At least one memory is connected to the bus and stores program instructions, and when the program instructions are executed by the at least one processor, the at least one processor executes the optimization method described in any embodiment of the first aspect of the present application.

[0045] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium having program instructions stored thereon, wherein when the program instructions are executed by a computer, the computer executes the optimization method described in any implementation of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic diagram of a flow chart of a first embodiment of an optimization method for an intersection signal control scheme of the present application;

[0047] Figure 2 A schematic diagram of a flow chart of constructing a green light utilization function of an intersection in Embodiment 1 of an optimization method for an intersection signal control solution of the present application;

[0048] Figure 3 A schematic diagram of a flow chart of constructing a travel time function or a waiting time function of an intersection in Embodiment 1 of an optimization method of an intersection signal control scheme of the present application;

[0049] Figure 4 A schematic diagram of a flow chart of optimizing an intersection objective function using a gradient descent method according to Embodiment 1 of an optimization method for an intersection signal control solution of the present application;

[0050] Figure 5 A schematic diagram of a flow chart of a second embodiment of an optimization method for an intersection signal control solution of the present application;

[0051] Figure 6 A schematic diagram of a flow chart of using a gradient descent method to converge an objective function to adjust the green light time of an intersection in Embodiment 2 of an optimization method for an intersection signal control solution of the present application;

[0052] Figure 7 A schematic diagram of the structure of an embodiment of an optimization device for an intersection signal control solution of the present application;

[0053] Figure 8 A schematic diagram of the structure of the computing device of the present application. DETAILED DESCRIPTION

[0054] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0055] In the following description, the terms "first\second\third, etc." or module A, module B, module C, etc. are not only used to distinguish similar objects, or to distinguish different embodiments, but do not represent a specific ordering of the objects. It can be understood that the specific order or sequence can be interchanged where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0056] In the following description, the numbers representing the steps, such as S110, S120, etc., do not necessarily mean that the steps must be executed in this manner. If permitted, the order of the previous and next steps can be interchanged, or they can be executed simultaneously.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0058] An embodiment of the present application provides an optimization method, device, equipment and storage medium for an intersection signal control scheme, the method comprising: collecting traffic status data for each flow direction at the intersection; utilizing the traffic status data, taking the green light time for each flow direction at the intersection as a variable, the objective function comprising at least a weighted sum of several variable functions among the following variable functions: a green light utilization function, a travel time function and a waiting time function; optimizing the objective function of the intersection by a gradient descent method, and obtaining the optimized green light time for each flow direction at the intersection.

[0059] The technical solution of the embodiment of the present application monitors the traffic status data of the intersection in real time, constructs the objective function based on it, and adaptively adjusts the green light time of the signal light by optimizing the objective function based on gradient descent, thereby improving the green light utilization rate, reducing the queuing time and optimizing the traffic signal control. The gradient descent method of the embodiment of the present application simplifies the design of the optimization model, avoids the explosive growth of the optimization parameters, can complete the optimization calculation in a shorter time, requires less computing power, and has the significance of universal application.

[0060] The following describes various embodiments of the present application in conjunction with the accompanying drawings. Figures 1 to 4 Embodiment 1 of an optimization method for an intersection signal control scheme of the present application is described.

[0061] Figure 1 The flowchart of Embodiment 1 of an optimization method for an intersection signal control scheme is shown, including steps S110 to S130.

[0062] S110: Collect traffic status data of each flow direction at the intersection.

[0063] S120: Using the traffic status data of each flow direction of the intersection, taking the green light time of each flow direction of the intersection as a variable, constructing an objective function of the intersection. The objective function at least includes a weighted sum of several variable functions among the following variable functions: a green light utilization function, a travel time function, and a waiting time function, each variable function being a function of the green light time of the intersection.

[0064] S130: Optimizing the objective function of the intersection by a gradient descent method to obtain the optimized green light time for each flow direction of the intersection. The signal control scheme of the intersection at least includes the green light time for each flow direction of the intersection.

[0065] In step S110 , real-time traffic status data of each flow direction of the intersection is collected by traffic monitoring equipment and sensors at the intersection.

[0066] In some embodiments, the traffic status data includes at least traffic flow, travel time, waiting time, speed, and headway of each flow direction. The travel time and waiting time are used to compare the signal control schemes before and after optimization, the traffic flow and headway are used to generate green light utilization, and the traffic flow, speed, and headway are also used to construct the optimization objective function.

[0067] In step S120, the green light utilization function is a function of how the green light utilization at the intersection changes with the green light time of each flow direction, and the larger the function is, the better; the travel time function is a function of how the total travel time of vehicles at the intersection changes with the green light time of each flow direction, and the smaller the function is, the better; the waiting time function is a function of how the total waiting time of vehicles at the intersection changes with the green light time of each flow direction, and the smaller the function is, the better.

[0068] In some embodiments, Figure 2 The process shown constructs a green light utilization function of an intersection, which includes steps S210 to S230.

[0069] S210: Using the average headway time in the traffic status data of each flow direction of the intersection and taking the green light time of each flow direction as a variable, a maximum flow function of the flow direction of the intersection is obtained.

[0070] For example, the average headway in the traffic status data of each flow direction at the intersection is used to calculate the current actual maximum flow of the flow direction, and then multiplied by the ratio of the changed green light time of the flow direction to the current actual green light time, to obtain the maximum flow function of the flow direction.

[0071] S220: Using the traffic status data of each flow direction of the intersection and taking the green light time of each flow direction as a variable, a traffic flow function of the flow direction of the intersection is obtained.

[0072] The method of constructing the traffic flow function in this step is not limited. The traffic flow corresponding to the traffic flow function of each flow direction is not only related to the actual traffic flow, but also to the vehicle queue of the flow direction. For example, when the green light time of a flow direction becomes longer, its traffic flow can increase, and vehicles in the waiting queue can pass.

[0073] S230: Obtaining a green light utilization rate of the intersection according to the traffic flow function and the maximum flow function of each flow direction of the intersection.

[0074] For example, the green light utilization function of the intersection is equal to the ratio of the sum of the traffic flow functions of each flow direction of the intersection to the sum of the maximum flow functions of each flow direction.

[0075] In step S120, in some embodiments, Figure 3 The illustrated process constructs a travel time function or a waiting time function of an intersection, which includes steps S310 to S320 .

[0076] S310: Using the traffic status data of each flow direction of the intersection and taking the green light time of each flow direction as a variable, construct a first variable function of each flow direction of the intersection, where the first variable function is a travel time function or a waiting time function.

[0077] Among them, the travel time function or waiting time function of each flow direction is constructed with the green light time of each flow direction and the traffic status data of the flow direction as input, and the specific construction method is not limited in this application.

[0078] S320: Constructing the first variable function of the intersection by taking the sum of the first variable functions of the flow directions of the intersection.

[0079] The travel time function of the intersection is equal to the sum of the travel time functions of each flow direction of the intersection, and the waiting time function of the intersection is equal to the sum of the waiting time functions of each flow direction of the intersection.

[0080] In step S130, a green light time space is constructed with the green light time of each flow direction of the intersection as the dimension. In the green light time space, starting from the point with the current green light time of each flow direction of the intersection as the coordinate, the objective function of the intersection is optimized by the gradient descent method to obtain the optimized green light time of each flow direction of the intersection. The gradient here is the gradient of the objective function of the intersection in the green light time space. From the above, the objective function value is converged by gradient descent, which simplifies the design of the optimization model, avoids the explosive growth of the optimization parameters, can complete the optimization calculation in a shorter time, requires less computing power, and has the significance of universal application.

[0081] In some embodiments, Figure 4 The process shown optimizes the objective function of the intersection by using the gradient descent method, which includes steps S410 to S450.

[0082] S410: Obtaining the gradient of the current point in the green light time space.

[0083] Among them, the current point starts from the point with the current green light time of each flow direction at the intersection as the coordinate.

[0084] S420: changing the green light time of each flow direction according to a set ratio along the gradient direction of the current point, and taking the point corresponding to the changed green light time of each flow direction in the green light time space as the new current point.

[0085] The setting ratios of the green light time for different flow directions may be the same or different.

[0086] S430: Compare the objective function values ​​of the current point of the intersection before and after the change, and obtain the absolute value of the change of the objective function value of the intersection.

[0087] Among them, the absolute value of the change in the objective function value at the intersection can determine whether the current objective function converges.

[0088] S440: Determine whether the absolute value of the objective function value change is less than a preset threshold or whether the number of optimization attempts reaches a maximum number of iterations.

[0089] If any condition is met, step S450 is executed, otherwise, the process returns to step S410 for iteration.

[0090] S450: The green light time of each flow direction at this time is used as the optimized green light time of the flow direction.

[0091] After this step is executed, the process returns to step S410 to perform the next iteration.

[0092] In some embodiments, the signal control scheme optimization of the intersection also includes the optimization of the signal control cycle of the intersection, and the signal control cycle of the intersection is obtained according to the optimized green light time of each flow direction of the intersection. For example, the optimized green light time of each flow direction is allocated to a corresponding stage or phase, and then combined with the configured yellow light time and red light time to obtain the signal control cycle of the intersection.

[0093] In some embodiments, the signal control optimization of the intersection is repeated in real time, and the traffic status data of each flow direction of the intersection is collected at the beginning of each optimization cycle; at the end of each optimization cycle, the optimized signal control scheme is sent to the signal of the intersection, and the next optimization cycle is started, so that the signal light time can be dynamically adjusted according to the real-time traffic flow data, and the adaptability and flexibility of traffic signal control are improved. Each optimization cycle includes at least one signal control cycle.

[0094] In some embodiments, when optimizing the signal control schemes for each intersection of a road, each intersection is optimized individually, and then the trunk green wave optimization is performed, thereby completing the optimization of the signal control scheme for the entire road.

[0095] In summary, embodiment 1 of an optimization method for an intersection signal control scheme monitors the traffic status data of the intersection in real time, constructs an objective function based on the data, and adaptively adjusts the green light time of the traffic light based on the objective function based on gradient descent optimization, thereby improving the green light utilization rate, reducing the queuing time and optimizing the traffic signal control. The objective function is optimized based on gradient descent, which simplifies the design of the optimization model and avoids the explosive growth of the optimization parameters. It can complete the optimization calculation in a shorter time and has lower requirements on computing power, which has the significance of universal application.

[0096] Combine the following Figure 5 and Figure 6 A second embodiment of an optimization method for an intersection signal control scheme of the present application is described.

[0097] Embodiment 2 of an optimization method for an intersection signal control scheme is a specific implementation method of embodiment 1 of an optimization method for an intersection signal control scheme, and has all its advantages.

[0098] Figure 5 The flowchart of Embodiment 2 of an optimization method for an intersection signal control scheme of the present application is shown, including steps S510 to S560.

[0099] S510: Collect traffic status data of the intersection.

[0100] Among them, various traffic detectors (such as coils, geomagnetic, radar, cameras, etc.) installed at the intersection are used to collect traffic status data at the intersection in real time, including at least traffic flow, travel time, waiting time, speed, headway, etc., and transmitted to the input interface of the optimization system via wired or wireless means.

[0101] Among them, the traffic status data has been processed using standard vehicles, such as the data of small cars and large cars have been averaged using standard vehicles.

[0102] S520: Calculate the current green light utilization rate at the intersection.

[0103] The current green light utilization rate of the intersection is calculated using formula (1).

[0104]

[0105] Among them, N actual is the number of vehicles that actually pass through in a signal control cycle, obtained based on the traffic status data collected in step S510, N max is the theoretical maximum number of vehicles passing through, which is related to the geometry of the intersection, lanes and design speed. h is the average headway time of continuous passenger car traffic on a lane (seconds / car, recorded as s / pcu).

[0106] In this step, the current total travel time and total waiting time of the intersection are also obtained from the current traffic status data of the intersection.

[0107] S530: Constructing an objective function for intersection optimization.

[0108] The objective function J(G) is defined by equation (2).

[0109] J(G)=ω 1 U(G)+ω 2 T(G)+ω 3 W(G) (2)

[0110] Among them, U(G) is the green light utilization function, T(G) is the travel time function, W(G) is the waiting time function, ω 1 ,ω 2 ,ω 3 is the weight coefficient. G is the green light time matrix, including the green light time of each flow direction at the intersection. U(G), T(G), and W(G) are all constructed using the traffic status data of the intersection and the green light time of each flow direction.

[0111] Among them, the optimization goal is designed to maximize the utilization rate of green lights and reduce the total travel time and waiting time of vehicles at intersections as much as possible.

[0112] Here, referring to formula (1), U(G) is constructed using formula (3).

[0113]

[0114] Among them, G j is the green light time for flow to j, N j (G j ) is the traffic flow function of direction j, and its acquisition steps include: firstly, obtaining the traffic flow and waiting flow (the flow corresponding to the waiting queue) of direction j according to the traffic status data of the intersection, and obtaining the actual total traffic flow of direction j; then, according to the actual total traffic flow of direction j and the green light time G j Get the flow function N of flow direction j j (G j );N jmax (G j ) is the maximum flow function of flow direction j, according to the average headway and green light time G in the traffic status data of flow direction j. j And the current actual green light time is obtained.

[0115] When constructing the travel time function T(G), the travel time function T of flow direction j is first obtained based on the traffic status data of the intersection and the green light time of each flow direction. j (G), the method of this process is not limited; then the travel time function T(G) of the intersection is obtained.

[0116] For example, the travel time function T of flow direction j is obtained j (G) is as follows: first obtain the actual total traffic flow to direction j; then according to the actual total traffic flow to direction j and the green light time G j Get the travel time function T of flow direction j j (G) This step needs to consider the vehicle start time when the green light starts, the time when the vehicle starts to reach the maximum flow speed, and the vehicle deceleration time before the red light arrives. The maximum flow speed is obtained based on the average headway time in the traffic status data of flow direction j.

[0117] When constructing the waiting time function (G), the traffic status data of the intersection and the green light time of each flow direction are used to obtain the waiting time function W of flow direction j. j (G), the method of this process is not limited; then obtain the waiting time function W(G) of the intersection.

[0118] For example, the waiting time function W of flow direction j is obtained j (G) is as follows: first obtain the actual total traffic flow to direction j; then according to the actual total traffic flow to direction j and the green light time G jObtain the waiting queue function for flow direction j; then calculate the waiting time function W of the waiting vehicles corresponding to the waiting queue function for flow direction j according to the green light time and red and yellow light time of each flow direction j (G).

[0119] S540: Adopt the gradient descent method to converge the objective function and adjust the green light time of the intersection.

[0120] Figure 6 The detailed process of this step is shown, including steps S610 to S650.

[0121] S610: Initialization.

[0122] Among them, the current green light time of each flow direction at the intersection is obtained to form the initial green light time matrix G 0 . Set the step size α of the gradient descent, usually a small positive value, such as α = 0.001. Calculate the initial value of the objective function.

[0123] Among them, in the green light time space composed of the green light time of each flow direction, the current green light time of each flow direction is set as the coordinate point as the current point.

[0124] S620: Calculate the gradient of the objective function at the current point.

[0125] In the green light time space composed of the green light time of each flow direction, the objective function is calculated using formula (4), and the gradient of the green light time matrix G is

[0126]

[0127] In order to simplify the calculation, the gradient is approximately calculated using the numerical differentiation method using equation (5):

[0128]

[0129] Here, δ is a very small constant, for example, δ=0.001.

[0130] S630: Update the green light time and current point.

[0131] Among them, the green light time matrix is ​​updated using formula (6) according to the gradient descent method.

[0132]

[0133] Among them, G K is the green light time matrix of the Kth iteration, G K+1 is the green light time matrix of the K+1th iteration, and updates the current point to G K+1 The corresponding point in the green light time space.

[0134] In order to ensure the safety of the intersection, the safety boundary is usually set for the green light time range using formula (7).

[0135] G K+1 =max(min(G K+1 , G max ), G min ) (7)

[0136] Among them, G max and G min They are respectively the matrix consisting of the maximum value and the minimum value of the green light time allowed for each flow direction during the optimization process, min(G K+1 , G max ) means that each element in the green light time matrix of the K+1th iteration must be less than G max The corresponding elements in G also result in a matrix of the same dimension, max(min(G K+1 , G max ), G min ) table min(G K+1 , G max ) must be greater than G min The corresponding elements in .

[0137] S640: Convergence judgment.

[0138] When one of the following conditions is met, it is determined to be converged, and step S650 is executed to end the optimization; otherwise, it returns to step S620.

[0139] (1) Change of objective function: When the absolute value of the change of objective function |J K+1 -J K |When it is less than the preset threshold ε, the optimization is stopped. K+1 and J K are the objective function values ​​of the Kth and K+1th iterations respectively. For example, ε=0.001 is usually taken.

[0140] (2) Maximum number of iterations: When the number of optimization attempts reaches the maximum number of iterations K max When the optimization is stopped, for example, K is usually taken max =1000.

[0141] S650: Obtain the optimized green light time and signal control cycle for each flow direction.

[0142] Among them, get the current green light time matrix G K+1 The value of the green light time for each flow direction is the optimized green light time for each flow direction, and the signal control cycle is adjusted accordingly.

[0143] S550: Real-time feedback and adjustment.

[0144] At the beginning of each optimization cycle, the optimization model is input into the detected traffic status data and some preset parameters for real-time calculation, and the green light time of the signal control scheme is continuously adjusted to adapt to dynamically changing traffic needs.

[0145] Each optimization cycle includes several signal control cycles. For example, each optimization cycle includes one signal control cycle. For example, the signal timing scheme is updated once in each signal control cycle to ensure the optimization effect.

[0146] S560: Output the optimal signal control solution.

[0147] Among them, the optimized signal control cycle and the calculation results of the green light time for each flow direction are output to the traffic signal control equipment and released, which can achieve more efficient traffic signal control and improve the traffic efficiency of the intersection.

[0148] Combine the following Figure 7 An embodiment of an optimization device for an intersection signal control scheme of the present application is described.

[0149] An embodiment of an optimization device for an intersection signal control scheme executes embodiment 1 of an optimization method for an intersection signal control scheme, and has all the advantages of embodiment 1 of an optimization method for an intersection signal control scheme.

[0150] Figure 7 The structure of an embodiment of an optimization device for an intersection signal control scheme is shown, including: a data acquisition module 710, a target construction module 720 and a signal control optimization module 730.

[0151] The data acquisition module 710 is used to collect traffic status data of each flow direction of the intersection. For its specific working principle and advantages, please refer to step S110 of the first embodiment of an optimization method for intersection signal control scheme.

[0152] The target construction module 720 is used to construct the target function of the intersection by using the traffic status data of each flow direction of the intersection and taking the green light time of each flow direction of the intersection as a variable. For its specific working principle and advantages, please refer to step S120 of the first embodiment of the optimization method of an intersection signal control scheme.

[0153] The signal control optimization module 730 is used to optimize the objective function of the intersection by the gradient descent method to obtain the optimized green light time for each flow direction of the intersection. For its specific working principle and advantages, please refer to step S130 of the first embodiment of the optimization method of the signal control scheme for an intersection.

[0154] An embodiment of the present application also provides a signal light control device for an intersection, including an optimization device as described in an embodiment of an optimization device for an intersection signal control solution.

[0155] The present application embodiment also provides a computing device, Figure 8 Detailed introduction.

[0156] The computing device 800 includes a processor 810 , a memory 820 , a communication interface 830 , and a bus 840 .

[0157] It should be understood that the communication interface 830 in the computing device 800 shown in this figure can be used to communicate with other devices.

[0158] The processor 810 may be connected to a memory 820. The memory 820 may be used to store the program code and data. Therefore, the memory 820 may be a storage unit inside the processor 810, or an external storage unit independent of the processor 810, or a component including a storage unit inside the processor 810 and an external storage unit independent of the processor 810.

[0159] Optionally, the computing device 800 may further include a bus 840. The memory 820 and the communication interface 830 may be connected to the processor 810 via the bus 840. The bus 840 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus 840 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the figure is represented by only one line, but it does not mean that there is only one bus or one type of bus.

[0160] It should be understood that in the embodiment of the present application, the processor 810 can adopt a central processing unit (CPU). The processor can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. Or the processor 810 uses one or more integrated circuits to execute related programs to implement the technical solutions provided in the embodiments of the present application.

[0161] The memory 820 may include a read-only memory and a random access memory, and provides instructions and data to the processor 810. A portion of the processor 810 may also include a nonvolatile random access memory. For example, the processor 810 may also store information on the device type.

[0162] When the computing device 800 is running, the processor 810 executes the computer-executable instructions in the memory 820 to perform the operation steps of each method embodiment.

[0163] It should be understood that the computing device 800 according to the embodiment of the present application can correspond to the corresponding subjects in the methods according to the embodiments of the present application, and the above-mentioned and other operations and / or functions of each module in the computing device 800 are respectively for implementing the corresponding processes of each method of the present embodiment. For the sake of brevity, they will not be repeated here.

[0164] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0165] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0166] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0167] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0168] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0169] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0170] The embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, it is used to execute the operating steps of each method embodiment.

[0171] The computer storage medium of the embodiment of the present application can adopt any combination of one or more computer-readable media.Computer-readable media can be computer-readable signal media or computer-readable storage media.Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above.More specific examples (non-exhaustive lists) of computer-readable storage media include, electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.In this document, computer-readable storage media can be any tangible medium containing or storing programs, which can be used by instruction execution systems, devices or devices or used in combination with them.

[0172] Computer-readable signal media may include data signals transmitted in baseband or as part of a carrier wave, which carry computer-readable program code. Such transmitted data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, transmit, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0173] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0174] Computer program code for performing the operation of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0175] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application 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 application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may also include more other equivalent embodiments without departing from the concept of the present application, all of which belong to the scope of protection of the present application.

Claims

1. A method for optimizing an intersection signal control scheme, characterized in that: include: Collecting traffic status data of each flow direction of the intersection; Using the traffic status data, taking the green light time of each flow direction of the intersection as a variable, constructing an objective function of the intersection, wherein the objective function at least includes a weighted sum of several variable functions among the following variable functions: a green light utilization function, a travel time function, and a waiting time function; The objective function of the intersection is optimized by the gradient descent method to obtain the optimized green light time for each flow direction of the intersection.

2. The optimization method according to claim 1, characterized in that: Also includes: The signal control cycle of the intersection is obtained according to the optimized green light time of each flow direction of the intersection.

3. The optimization method according to claim 1, characterized in that: The objective function of the intersection is optimized by a gradient descent method to obtain the optimized green light time for each flow direction of the intersection, specifically including: In the green light time space with the green light time of each flow direction at the intersection as the dimension, starting from the point with the current green light time of each flow direction at the intersection as the coordinate, the objective function is optimized by the gradient descent method to obtain the optimized green light time for each flow direction at the intersection, and the gradient is the gradient of the objective function in the green light time space.

4. The optimization method according to claim 3, characterized in that: Optimizing the objective function in the green light time space by a gradient descent method includes: In the green light time space, obtaining the gradient of the current point; Changing the green light time of each flow direction according to a set ratio along the gradient direction of the current point, and taking the point corresponding to the changed green light time of each flow direction in the green light time space as the new current point; Comparing the objective function value of the current point before and after the change; When the absolute value of the change in the objective function value is less than a preset threshold or the number of optimization attempts reaches a maximum number of iterations, the green light time of each flow direction at this time is used as the optimized green light time of the flow direction.

5. The optimization method according to claim 1, characterized in that: Using the traffic status data and taking the green light time of each flow direction of the intersection as a variable, a green light utilization function of the intersection is constructed, including: Using the average headway of vehicles in the traffic status data of each flow direction of the intersection, taking the green light time of each flow direction as a variable, a maximum flow function of the flow direction of the intersection is obtained, and the maximum flow function of each flow direction changes positively with the green light time of the flow direction; Using the traffic status data of each flow direction of the intersection, taking the green light time of each flow direction as a variable, obtaining the traffic flow function of the flow direction of the intersection; According to the traffic flow function and the maximum flow function of each flow direction of the intersection, the green light utilization function of the intersection is obtained.

6. The optimization method according to claim 1, characterized in that: Using the traffic status data, constructing a travel time function or a waiting time function of the intersection, including: Using the traffic status data, taking the green light time of each flow direction as a variable, constructing a first variable function of each flow direction of the intersection, wherein the first variable function is a travel time function or a waiting time function; The first variable function of the intersection is constructed by taking the sum of the first variable functions of the flow directions of the intersection.

7. The optimization method according to claim 2, characterized in that: Collecting the traffic status data of each flow direction of the intersection, specifically including: collecting the traffic status data at the beginning of each optimization cycle, each optimization cycle including at least one signal control cycle; The method further comprises: sending the optimized signal control scheme to the signal machine at the intersection at the end of each optimization cycle, and starting the next optimization cycle.

8. The optimization method according to claims 1 to 7, characterized in that: The traffic status data includes at least one of the following data for each flow direction: traffic flow, travel time, waiting time, speed, and headway.

9. An optimization device for an intersection signal control scheme, characterized in that: include: A data collection module, used for collecting traffic status data of each flow direction of the intersection; A target construction module is used to construct a target function of the intersection by using the traffic status data and taking the green light time of each flow direction of the intersection as a variable, wherein the target function at least includes a weighted sum of several variable functions of the following variable functions: a green light utilization function, a travel time function, and a waiting time function; The signal control optimization module is used to optimize the objective function of the intersection by using a gradient descent method to obtain the optimized green light time for each flow direction of the intersection.

10. A signal light control device for an intersection, characterized in that: Includes the optimization device as described in claim 9.

11. A computing device, characterized in that: include, bus; A communication interface connected to the bus; at least one processor connected to the bus; as well as At least one memory is connected to the bus and stores program instructions, and when the program instructions are executed by the at least one processor, the at least one processor executes the optimization method according to any one of claims 1 to 8.

12. A computer-readable storage medium, characterized in that: Program instructions are stored thereon, and when the program instructions are executed by a computer, the computer is caused to execute the optimization method according to any one of claims 1 to 8.

Images