A holographic adaptive optimization method for calculating delay variation of a four-way intersection

Abstract

The application discloses a kind of holographic adaptive optimization intersection control delay variation calculation method, it is related to traffic signal control technical field, comprising: step 101, signal timing daily plan, real-time signal timing scheme, vehicle passes stop line time are obtained as target data;Step 102, vehicle movement is divided into four phases, according to target data, determine the traffic state corresponding to each phase when vehicle passes;Step 103, according to the traffic state corresponding to current phase, determine the control delay time corresponding to current traffic state;Step 104, according to the control delay time of each phase, determine the control delay variation of current intersection in statistical time;It can realize the accuracy of the control delay time calculation of each phase.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of traffic signal control technology, in particular to a holographic adaptive optimization after intersection control delay change calculation method. BACKGROUND

[0002] With the increase of the number of cars, traffic congestion has become a problem that plagues China's economic development. There are two methods to solve traffic congestion, active and passive. The active method is mainly to improve the traffic infrastructure and develop advanced traffic control systems, while the passive method is to use single and double restrictions, encourage green travel, etc. At present, developing advanced traffic control systems is the best way to operate and has the least impact on people's lives.

[0003] For example, Chinese patent publication No. CN114913685A discloses a kind of intersection traffic signal adaptive control method based on deep reinforcement learning, including three steps: define the algorithm controller based on deep reinforcement learning and convolutional neural network, define state space, action space and reward function;Deep reinforcement learning method is used to train convolutional neural network;According to the trained algorithm controller, the intersection traffic signal control is carried out.The prior art divides the lane into multiple cells, each cell can accommodate multiple vehicles, expresses the state information by vehicle saturation rate, supplements the information of saturation rate by the speed ratio of vehicles in the cell, and comprehensively takes the speed of vehicles in the lane, delay time and the number of changes of vehicles in several sections closest to the stop line as the reward value.

[0004] However, when the prior art controls the traffic signal, the cycle length of the intersection, the green ratio of the selected lane, the saturation, the traffic capacity, and a reward value need to be known, and the corresponding value can be calculated only when these parameters are met;On the other hand, this implementation ignores the overall control delay, resulting in an increase in the overall control delay waiting time of each intersection, and the calculation method is complex;The change of the total control delay of the intersection after the implementation of the holographic adaptive signal control should be calculated based on the signal control daily plan, the signal control actual scheme, and the data of the vehicle passing through the stop line time, so as to optimize the signal control effect. SUMMARY

[0005] The present application provides a holographic adaptive optimization after intersection control delay change calculation method, which solves the problem of large fluctuation range of average delay time of each phase in the prior art, and realizes the accuracy of control delay time calculation.

[0006] The present application provides a holographic adaptive optimization after intersection control delay change calculation method, which includes:

[0007] Step 101, obtaining signal timing plan, real-time signal timing scheme, and time of vehicle passing stop line as target data;

[0008] Step 102, dividing vehicle movement into four phases, and determining traffic state corresponding to each phase when vehicle passes according to target data;

[0009] Step 103, determining control delay time corresponding to current traffic state according to traffic state corresponding to current phase;

[0010] Step 104, determining control delay variation of current intersection in statistical time according to control delay time of each phase.

[0011] The adjustment mode of control delay time is realized by the following content:

[0012] Step 201, determining phase change cycle time, which is total time of four phases according to preset order;

[0013] Step 202, obtaining green light time corresponding to each phase, and difference between green light time of current phase and preset time as first error;

[0014] Step 203, calculating first error of phase change cycle time to determine control delay time caused by each first error;

[0015] Step S204, obtaining control delay variation in current phase change cycle time according to obtained control delay time.

[0016] The control delay variation of one intersection in each statistical period is:

[0017]

[0018] Wherein, C is cycle number in statistical period; I is phase number of each cycle; i is current calculated phase; t i+ is time of current cycle i phase extension, t i+ ≥0; T' is is start time of next cycle i phase; T ie is end time of current cycle i phase; is vehicle number passing from end of current cycle i phase to start of next cycle i phase; V i+ is vehicle number passing after i phase extension; t i- is time of current cycle i phase shortening; a, b, c are variation coefficients, when t i+ >0, a=1, b=1, c=0; when t i-When the green light of phase i is prolonged, a=1, b=1, c=0, when the green light of phase i is reduced, a=0, b=0, c=1.

[0019] When the green light of phase i is prolonged, a=1, b=1, c=0, when the green light of phase i is reduced, a=0, b=0, c=1.

[0020] The one or more technical solutions provided in the embodiments of the application have at least the following technical effects or advantages:

[0021] By acquiring the signal timing daily plan, the real-time signal timing scheme, the time of the vehicle passing the stop line and other data, the control delay variation of each phase in the statistical time can be accurately calculated; this provides strong data support for the traffic manager, and helps better understand and optimize the traffic condition of the intersection.

[0022] According to the actual traffic flow, the actual start time and the end time of each phase are dynamically adjusted, so as to realize the optimization of the traffic signal; this helps reduce the waiting time of the vehicle at the intersection, improve the traffic efficiency and reduce the traffic congestion.

[0023] By determining the cycle time of the phase change, the green light time and the first error and other modes, the control delay time corresponding to each phase can be accurately calculated; this helps the traffic manager more accurately understand the influence of each phase on the overall traffic condition, so as to formulate more effective traffic management strategies. BRIEF DESCRIPTION OF DRAWINGS

[0024] Figure 1 A flowchart of an embodiment one of the holographic adaptive optimization after intersection control delay variation calculation method of the application;

[0025] Figure 2 A phase diagram of the holographic adaptive optimization after intersection control delay variation calculation method of the application;

[0026] Figure 3 A flowchart of an embodiment two of the holographic adaptive optimization after intersection control delay variation calculation method of the application. DETAILED DESCRIPTION

[0027] In order to facilitate the understanding of the application, the application will be described more fully below with reference to the related drawings; the preferred embodiments of the application are shown in the drawings, however, the application can be realized in many different forms, and is not limited to the embodiments described herein; on the contrary, the purpose of providing these embodiments is to make the disclosure of the application more thorough and comprehensive.

[0028] It should be noted that the terms "vertical," "horizontal," "up," "down," "left," "right," and similar expressions used in this article are for illustrative purposes only and do not represent the only possible implementation.

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains; the terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to limit the invention; the term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0030] Example 1

[0031] like Figure 1 As shown, the method for calculating the change in intersection control delay after holographic adaptive optimization in this application includes:

[0032] Step 101: Obtain the daily signal timing plan, real-time signal timing scheme, and vehicle passage time through the stop line as target data;

[0033] The signal timing plan refers to a pre-defined intersection signal timing scheme based on historical traffic flow data, road spatial layout, and traffic management needs. This scheme typically includes time period divisions, phase settings, and time settings for each phase, aiming to optimize traffic flow and improve intersection efficiency.

[0034] The real-time signal timing scheme refers to a scheme that dynamically adjusts the signal timing settings at intersections based on real-time traffic flow data. Unlike daily signal timing plans, real-time signal timing schemes are more flexible and can respond to changes in traffic flow in real time.

[0035] The time it takes for a vehicle to cross the stop line refers to the time required from when a vehicle starts moving after waiting for the traffic light to turn green at the intersection until it crosses the stop line. This time is affected by a variety of factors, including vehicle acceleration performance, the length of the queue of vehicles ahead, and traffic light timing settings.

[0036] By obtaining these three elements, we can accurately determine the traffic status of vehicles at the intersection; such as Figure 2 As shown, this application sets four phases for vehicle movement, and the representation of these four phases is consistent with that in the figure.

[0037] When controlling the vehicle corresponding to each phase, the current phase or other direction queue is ended or extended according to the arrival of the vehicle. When a phase is ended in advance, the control delay of all the vehicles waiting for the traffic of other phases will be reduced by the difference between the original release time and the actual release time; when a phase is extended, the control delay of the vehicle arriving subsequently in the current phase will be reduced by one cycle, but at the same time, the control delay of the vehicle of other phases will be increased by the actual extension time. The control delay change is the sum of the control delay of all the vehicles increased or reduced by the holographic self-adaptation.

[0038] Step 102, the vehicle movement is divided into four phases, and the traffic state corresponding to each phase when the vehicle passes is determined according to the target data;

[0039] Step 103, the control delay time corresponding to the current traffic state is determined according to the traffic state corresponding to the current phase;

[0040] Step 104, the control delay change of the current intersection in the statistical time is determined according to the control delay time of each phase.

[0041] In the implementation process of the present application, the control delay time required by the whole is controlled by adjusting the time corresponding to each phase, so as to control the signal lamp time to reduce the traffic congestion.

[0042] Preferably, the signal timing daily plan obtains the phase plan of the day, and obtains the preset standard time of each phase and the cycle time of the four phases according to the obtained phase plan.

[0043] Preferably, the real-time signal timing scheme is used to obtain the actual start time and the actual end time of each phase according to the actual traffic flow.

[0044] Preferably, the time of the vehicle passing the stop line is set, the parking waiting area within 5 meters on both sides of the intersection is set, the time of the vehicle passing the parking line is set according to the time required by the vehicle passing the parking waiting area, and the real-time speed is recorded on the running track image.

[0045] Embodiment two

[0046] Preferably, in the embodiment of the present application, as shown in Figure 3 The adjustment mode of the control delay time is realized by the following contents:

[0047] Step 201, the cycle time of phase change is determined, and the phase change cycle time is the total time of the four phases according to the preset order;

[0048] In step 202, the green light time corresponding to each phase is obtained, and the difference between the green light time of the current phase and the preset time is obtained as a first error;

[0049] In step 203, the first error of the period time of the phase change is calculated to determine the control delay time length caused by each first error;

[0050] In step S204, the control delay change amount in the period time of the current phase change is obtained according to the obtained control delay time length.

[0051] Preferably, in step 202, the extension time and the actual end time of each phase are obtained, and the number of vehicles passing through each phase is determined, and the product of the first error and the last four phases of the current phase is taken as the control delay time length of the current phase.

[0052] Preferably, when the first error occurs, the control delay time length of the next phase of the current phase is the product of the number of vehicles passing through the next phase and the difference between the actual start time and the actual end time in the two adjacent times of the next phase.

[0053] The control delay change amount and the control delay time length mentioned in the above steps are illustrated by the following examples:

[0054] Suppose the standard period length of a period is T, there are four phases, and the phase order is A, B, C, and D. The green light time corresponding to the phase A in the daily plan is t A , the phase A ends t A1 seconds in advance; the green light time corresponding to the phase B in the daily plan is t B , the phase B ends t B1 seconds longer, and the actual end time is T B1e . In the extended time, the number of vehicles passing through the phase B is V B延 ; the phases C and D end normally. The number of vehicles passing through the four phases is V A , V B , V C , and V D , respectively. The number of vehicles passing through the next phase A is V A2 , and the actual start time of the next phase B is T B2s .

[0055] Because the phase A ends in advance, all the vehicles of the phases B, C, and D reduce the waiting time t A1 seconds, and the total control delay time length reduced is t A1 * V B + t A1 * V C + t A1 * V D + t A1 * VA2 ; the control delay of phase B is reduced by V B延 *(T B2s -T B1e ); the total number of control delay of phase C and D in the current cycle and phase A in the next cycle is t B1 *(V C +V D +V A2 ), that is, the change of control delay in the current cycle is -(t A1 *V B +t A1 *V C +t A1 *V D )-V B延 *(T B2s -T B1e )+t B1 *(V C +V D +V A2 ). When the result is positive, it means that the holographic control increases the total control delay of vehicles at the intersection, and when the result is negative, it means that the holographic control reduces the total control delay of vehicles at the intersection.

[0056] In the above description process, the first error is the reduced waiting time of the current phase, and the reduced waiting time makes the reduced time of the subsequent phase be the control delay time. At this time, according to the obtained control delay time, the change of control delay in a cycle can be obtained. When the first error occurs, it means that the green light time is increased or reduced. At this time, the increased green light time will affect the green light time of other phases. At this time, the generated control delay amount can be calculated to cope with the occurrence of congestion, how to regulate or improve the traffic setting of the current intersection.

[0057] Preferably, according to the obtained control delay change amount, the control delay change amount of an intersection in each statistical time period is determined.

[0058] The control delay change amount of an intersection in each statistical time period is:

[0059]

[0060] Wherein, C is the number of cycles in the statistical time period; I is the number of phases in each cycle; i is the current calculated phase; t i+ is the time of phase extension of the current cycle i, t i+ ≥ 0; T' is is the start time of phase i in the next cycle; T ie is the end time of phase i in the current cycle; V represents the number of vehicles that pass through from the end of phase i of the current cycle to the start of phase i of the next cycle; i+ The number of vehicles passing through after phase i is extended; t i- The current period i represents the time during which the phase shortens; a, b, and c are variation coefficients, which are applied when t... i+ When t > 0, a = 1, b = 1, c = 0; when t i- When the value is greater than 0, a = 0, b = 0, and c = 1.

[0061] Preferably, when the green light of phase i is extended, a = 1, b = 1, c = 0; when the green light of phase i is reduced, a = 0, b = 0, c = 1. The calculation of the change in control delay of the entire intersection is adjusted according to the extension or reduction of the green light of phase i, so that the data obtained is more comprehensive and the effect of the traffic plan adopted at an intersection within a fixed time period can be understood.

[0062] This allows us to obtain the required change in control delay within the currently defined time period. Based on this change in control delay, we can clearly understand the impact of the current signal timing schedule and real-time signal timing scheme on traffic light passage, and whether this impact can affect the overall traffic operation.

[0063] Assume a standard cycle duration of T = 120 seconds, with four phases in sequence: A (east-west straight), B (east-west left turn), C (north-south straight), and D (north-south left turn). The green light duration for phase A (east-west straight) on a scheduled day is t. A =25s, phase A east-west straight ahead t A1 =Ends in 5 seconds; Phase B, east-west left turn, corresponds to a green light duration of t in the daily schedule. B =30, phase B extends east-west leftward by t B1 =Ends in 5 seconds, actual end time is T B1e =9:00, during this extended period, the number of vehicles turning left from east to west in phase B is V. B延 = 3 vehicles; Phase C (north-south straight) and Phase D (north-south left turn) ended normally. The number of vehicles passing through the four phases are V respectively. A =10 vehicles, V B =12 vehicles, V C =9 vehicles, V D = 11 vehicles. The number of vehicles passing through east-west in the next phase A is V. A2 =13 vehicles, the actual start time of the next phase B east-west left turn is T B2s =9:01:30.

[0064] Because phase A (east-west straight traffic) ended early, all vehicles in phases B (east-west left turns), C (north-south straight traffic), and D (north-south left turns) experienced reduced waiting times. A1seconds, the total control delay of the vehicles in phase B is reduced by V seconds A1 *V B +t A1 *V C +t A1 *V D +t A1 *V A2 ; because phase B is extended, the total control delay of the vehicles in phase B passing the stop line after the extension is V seconds B延 *(T B2s -T B1e ); the total control delay of the vehicles in phase C and D in the current cycle and phase A in the next cycle is t B1 *(V C +V D +V A2 ), that is, the control delay change of the cycle is -(t A1 *V B +t A1 *V C +t A1 *V D )-V B延 *(T B2s -T B1e )+t B1 *(V C +V D +V A2 ) = -(5*12+5*9+5*11+5*13)-3*(9:01:30-9:00:00)+5*(9+11+13) = -240 seconds. The result is negative, indicating that the holographic control reduces the total control delay of the vehicles at the intersection.

[0065] Preferably, when controlling the control delay time of the intersection, the passing data of different turning vehicles is determined by an electronic camera, and the vehicle type, license plate number, intersection number, detection time, and vehicle speed time in all passing data are detected, the passing vehicles at different intersections are classified according to the vehicle type, the acquired intersections are processed in time sequence, the most frequent time period of the vehicle trajectory in each phase is determined, the traffic condition of the vehicles in the most frequent time period in each phase is determined, and the control delay change of the intersection is calculated.

[0066] The above only describes the preferred embodiments of the present application and is not used to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for calculating the change in intersection control delay after holographic adaptive optimization, characterized in that, include: Step 101: Obtain the daily signal timing plan, real-time signal timing scheme, and vehicle passage time through the stop line as target data; Step 102: Divide vehicle movement into four phases, and determine the traffic state corresponding to each phase when the vehicle passes through, based on the target data. Step 103: Determine the control delay time corresponding to the current traffic state based on the traffic state corresponding to the current phase; Step 104: Determine the change in control delay at the current intersection within the statistical time period based on the control delay time of each phase; Changes in control delay at an intersection within each statistical period: Where C is the number of periods within the statistical period; I is the number of phases per period; i is the currently calculated phase; t i+ t is the time extension of the current period i phase. i+ ≥0; T ' is T is the start time of phase i in the next cycle; ie This represents the end time of phase i in the current period; V represents the number of vehicles that pass through from the end of phase i in the current cycle to the beginning of phase i in the next cycle, and its meaning is consistent in both phase extension and phase shortening scenarios; i+ The number of vehicles passing through after the current period i phase is extended; t i- The current period i represents the time during which the phase shortens; a, b, and c are variation coefficients, which are applied when t... i+ When t > 0, a = 1, b = 1, c = 0; when t i- When the value is greater than 0, a = 0, b = 0, and c = 1.

2. The method for calculating the change in intersection control delay after holographic adaptive optimization as described in claim 1, characterized in that, The aforementioned method for adjusting delay time is achieved through the following: Step 201: Determine the period of phase change, wherein the period of phase change is the total time for the four phases to be executed in a preset order; Step 202: Obtain the green light time corresponding to each phase, and obtain the difference between the green light time of the current phase and the preset time as the first error; Step 203: Calculate the first error of the period time of the phase change and determine the control delay duration caused by each first error; Step S204: Based on the obtained control delay duration, obtain the change in control delay within the current phase change period.

3. The method for calculating the change in intersection control delay after holographic adaptive optimization as described in claim 1, characterized in that, The signal timing daily plan obtains the phase plan for the day and, based on the obtained phase plan, obtains the preset standard time for each phase and the periodic time for the four phases.

4. The method for calculating the change in intersection control delay after holographic adaptive optimization as described in claim 2, characterized in that, The real-time signal timing scheme is used to obtain the actual start time and actual end time of each phase based on the actual traffic flow.

5. The method for calculating the change in intersection control delay after holographic adaptive optimization as described in claim 1, characterized in that, The time for a vehicle to pass the stop line is set as follows: a 5-meter area within the stop line on both sides of the intersection is designated as a waiting area. The time for a vehicle to pass the stop line is set according to the time required for the vehicle to pass through the waiting area, and the time is recorded on the trajectory image according to the real-time speed.

6. The method for calculating the change in intersection control delay after holographic adaptive optimization as described in claim 4, characterized in that, In step 202, the extension time and actual end time of each phase are obtained, and the number of vehicles passing through each phase is determined. The product of the sum of the number of vehicles in the last three phases of the current phase and the first error is used as the control delay time of the current phase.

7. The method for calculating the change in intersection control delay after holographic adaptive optimization as described in claim 6, characterized in that, When the first error occurs, the control delay time of the next phase of the current phase is the product of the number of vehicles passing through the next phase and the difference between the actual start time and the actual end time of two adjacent time intervals of the next phase.

8. The method for calculating the change in intersection control delay after holographic adaptive optimization as described in claim 1, characterized in that, When the green light of phase i is extended, a = 1, b = 1, c = 0; when the green light of phase i is reduced, a = 0, b = 0, c = 1.

9. The method for calculating the change in intersection control delay after holographic adaptive optimization as described in claim 2, characterized in that, When controlling the control delay time at intersections, electronic cameras are used to determine the vehicle passing data of vehicles turning different directions. The vehicle type, license plate number, intersection number, detection time, and vehicle speed time are detected in all passing data. Vehicles passing through different intersections are classified according to vehicle type. The obtained intersections are processed in chronological order to determine the time period in which vehicle trajectories appear most frequently in each phase. The traffic situation of vehicles in each phase during the most frequent time period is determined, and the change in control delay at the intersection is calculated.

Images