Signal intersection traffic flow equalization control method based on real-time detection data

Abstract

The invention discloses a signal intersection traffic flow balance control method based on real-time detection data. The method comprises the following steps: S1, collecting traffic operation data of each entrance lane of an intersection in real time; s2, designing a time-phased basic signal timing scheme; s3, calculating a queuing length imbalance index representing the queuing dispersion degree of each phase; s4, constructing a signal intersection traffic flow balance control algorithm based on real-time detection data; and S5, generating and executing a new signal timing scheme. According to the method, long queuing elimination and traffic pressure balancing are taken as primary targets, high-precision real-time data are utilized, rapid self-adaptive adjustment of signals is realized through an efficient algorithm, dynamic balancing of vehicle queuing at each entrance lane of the signalized intersection is realized, spreading and overflow of traffic congestion are prevented, and the traffic safety is improved. Therefore, the traffic efficiency, the fairness and the anti-congestion capability of the intersection are effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of urban intelligent traffic signal control, and particularly relates to a signal intersection traffic flow balancing control method based on real-time detection data. BACKGROUND

[0002] Urban road signal intersections are the bottleneck of the traffic network, and their operation efficiency directly determines the traffic capacity and service level of the regional road network. With the acceleration of urbanization and the continuous growth of the number of motor vehicles, the uneven distribution of traffic flow in time and space is increasingly prominent, especially during the morning and evening peak hours, the traffic flow of each entrance direction of the intersection is greatly different, and it is easy to form "tidal" congestion. The traditional signal control method has been unable to cope with such dynamic and uneven traffic flow.

[0003] The commonly used intersection signal control methods at present mainly include timing control, induction control and adaptive control. Timing control sets a fixed signal timing scheme according to historical traffic flow data, which cannot adapt to the real-time fluctuations of traffic flow, especially when the traffic flow is unevenly distributed in time and space, which easily leads to long queues of vehicles in some entrance ways, while the green light time of other entrance ways is idle, resulting in waste of resources and traffic congestion. Induction control detects the arrival of vehicles by burying coil detectors near the stop line, and accordingly extends or shortens the green light time, which has a certain real-time, but its control logic is relatively simple, usually only responding to the vehicle request of the current phase, lacking global perception and cooperative optimization of the queuing state of each direction of the whole intersection, which easily leads to green light idle or unfairness between phases. The adaptive control system dynamically adjusts the cycle, green ratio and phase difference according to the detected traffic flow, occupancy and other parameters by establishing a traffic model. However, such systems usually rely on complex models and expensive system architecture, and their response speed and processing capacity for short-term traffic mutations are limited.

[0004] In summary, the existing signal control technology, whether it is basic timing control or more advanced induction and adaptive control, generally has the following core defects when facing dynamic unbalanced traffic flow: (1) Control target deviation: unable to eliminate long queues and achieve balanced traffic pressure on each approach, resulting in control strategies that cannot effectively address the root cause of traffic congestion (Zhao Jing, Guo Kaiqi, Zhang Cheng. Intersection geometric design and signal control co-optimization model based on simulation optimization [J]. China Journal of Highway Engineering, 2025, 38 (06): 295-312.); (2) State perception is one-sided and lagging: the detection data relied on are mostly indirect parameters, or the model calculation is complex, making it difficult to accurately capture the queue length and its dynamic changes that directly reflect traffic pressure (Wang Haizhong, Zhang Dan, Wang Menglin, Tian Ai'ai. Intersection signal and vehicle trajectory fusion control model under heterogeneous traffic flow [J]. Transportation System Engineering and Information, 2025, 25 (04): 96-103.); (3) Control strategy is rigid: lack of a lightweight, fast response, and balanced-oriented feedback control mechanism that can quickly and directly adjust green light time resources from less pressure to more pressure directions after detecting an imbalance (Jiang Mingzhi, Wu Tianjiao, Zhang Lin. Vehicle cooperative control algorithm for unsignalized intersection based on deep reinforcement learning [J]. Journal of Transportation Engineering and Information Science, 2022, 20 (02): 14-24.).

[0005] Therefore, there is an urgent need for a new intelligent control method that can accurately perceive real-time traffic conditions and balance traffic pressure on each approach, to make up for the shortcomings of existing technology and fundamentally improve the operating efficiency and robustness of signalized intersections. The present invention is proposed in this context, aiming to dynamically calculate a queue length imbalance index that accurately represents the traffic pressure difference on each approach based on high-precision real-time detection data, and to build a fast-response feedback control algorithm around this core, with the goal of achieving dynamic balance of vehicle queues on each approach at signalized intersections, effectively eliminating long queues, preventing the occurrence and spread of traffic congestion, and improving the overall operating efficiency and fairness of the intersection. SUMMARY

[0006] To achieve the above purpose, the present invention provides a signalized intersection traffic balancing control method based on real-time detection data.

[0007] The present invention is realized at least by one of the following technical solutions.

[0008] A signalized intersection traffic balancing control method based on real-time detection data, comprising the following steps: S1. Real-time collection of traffic operation data on each approach of the intersection; S2. Design a time-based basic signal timing plan; S3. Calculate a queue length imbalance index representing the queue discrete degree of each phase; S4. Construct a signal intersection traffic flow balancing control algorithm based on real-time detection data; S5. Generate and execute a new signal timing plan.

[0009] Further, the real-time collection of traffic operation data of each approach of the intersection in step S1 includes arranging high-precision detection devices at the intersection signal lights and at a preset distance upstream of the stop line to collect real-time traffic operation data of each approach; the traffic operation data includes traffic flow and queue length of each approach; the queue length refers to the length of the continuous vehicle queue from the stop line back to the last stopped vehicle at the green light time of the phase.

[0010] Further, the design of a time-based basic signal timing plan in step S2 includes traffic period division based on historical traffic flow data, designing a basic signal timing plan for each period as a reference for subsequent adjustment; the basic signal timing plan includes signal cycle length, phase sequence, green time, yellow time, and all-red time of each phase.

[0011] Further, the queue length imbalance index representing the queue discrete degree of each phase in step S3 has the following formula:

[0012] In the formula, is the time step number, is the queue length imbalance index of the th step, is the number of phases, is the average queue length of the th approach of the i th phase in the th step, i is the traffic pressure weight of the th phase.

[0013] The calculation formula of the traffic pressure weight

[0014] In the formula, is the number of approaches included in the i th phase, is the saturation flow rate of each approach of the i th phase.

[0015] Further, the construction of a signal intersection traffic flow balancing control algorithm based on real-time detection data in step S4 includes the following steps: S4.1 sets a time step T. At the end of each time step, based on the real-time data collected in S1 and the calculation formula for the queue length imbalance index described in S3, the current step length is calculated. k Queue length imbalance index for each phase .

[0016] S4.2 Set an imbalance threshold ,like Then the traffic flow at the intersection is in a relatively balanced state, and the next step is long k +1 Use the current step size k The basic signal timing scheme. If If this happens, the traffic flow at the intersection will be severely unbalanced, and the system will switch to S4.3 to optimize the basic signal timing scheme.

[0017] S4.3 For the phase with the largest average queue length, in the next step... k +1 to provide green light time compensation The compensation formula is:

[0018] In the formula, This is the compensation coefficient.

[0019] For the phase with the minimum average queue length, in the next step... k +1 Reduce green light time The calculation formula is:

[0020] In the formula, This is the reduction factor.

[0021] Under the constraints that the signal cycle duration remains constant and the green light time for any phase must not be less than the minimum green light time or more than the maximum green light time, for and Perform normalization processing to ensure + =0.

[0022] Furthermore, step S5, which involves generating and executing a new signal timing scheme, involves adjusting the green light time based on the output of the signalized intersection traffic flow balancing control algorithm based on real-time detection data from step S4. This new signal timing scheme is then transmitted to the intersection's signal controller via the communication network for execution in the next step. k +1 to start execution.

[0023] The application also provides a device comprising a processor and a memory, the memory being used for storing instructions or computer programs, and the processor being used for executing the instructions or computer programs in the memory to enable the device to perform the steps of the method.

[0024] The application also provides a computer readable storage medium having instructions stored therein, which, when executed on a device, enable the device to perform the steps of the method.

[0025] Compared with the prior art, the application can at least achieve the following beneficial effects: 1. The application takes the queuing length imbalance index as the core evaluation index and feedback signal of signal optimization, and the control target is to eliminate the queuing difference between each approach, thereby preventing the intersection lock and regional congestion caused by long queuing in a certain direction from the root.

[0026] 2. The signal intersection traffic balancing control algorithm proposed by the application has stability and flexibility, adopts an optimization method based on rules and a simplified model, has small calculation burden, fast response speed, and can effectively respond to short-term and severe fluctuations of traffic flow.

[0027] 3. The application ensures the relative fairness of the passing right of vehicles in each direction by dynamically reallocating the green light time, avoids long waiting of vehicles in certain directions, realizes traffic balancing, reduces the total delay and parking times of vehicles, and thus improves the overall operation efficiency of the intersection. BRIEF DESCRIPTION OF DRAWINGS

[0028] Figure 1 The signal intersection traffic balancing control method flowchart based on real-time detection data provided for the embodiment of the application.

[0029] Figure 2 The intersection direction historical daily hour flow chart and time period division chart provided for the embodiment of the application.

[0030] Figure 3 The signal intersection traffic balancing control algorithm flowchart based on real-time detection data provided for the embodiment of the application. DETAILED DESCRIPTION

[0031] To make the purpose, technical scheme and advantages of the embodiments of the application clearer, the technical scheme in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the application.

[0032] Please refer to Figure 1 The application provides a signal intersection traffic flow equalization control method based on real-time detection data, which comprises the following steps: S1. Real-time collection of traffic operation data of each approach of the intersection.

[0033] The real-time collection of traffic operation data of each approach of the intersection in step S1 comprises arranging high-precision detection equipment at the intersection signal lamp and at a preset distance upstream of the stop line to collect the traffic operation data of each approach in real time; the traffic operation data comprises the traffic flow and the queue length of each approach; the queue length refers to the length of the continuous vehicle fleet from the stop line back to the last stopped vehicle at the time when the phase green light is on.

[0034] In some embodiments of the application, the intersection has a total of 14 approaches, wherein there are 2 straight approach lanes, 1 left turn approach lane in the east approach, 2 straight approach lanes, 1 left turn approach lane in the west approach, 3 straight approach lanes, 1 left turn approach lane in the south approach, and 3 straight approach lanes, 1 left turn approach lane in the north approach; the intersection adopts a typical four-phase, and the phases are east-west straight, east-west left turn, south-north straight, and south-north left turn. A video vehicle detector is installed on the intersection signal lamp pole and 100 meters upstream of the stop line. The detector detects and uploads the vehicle arrival rate, time occupancy rate and queue length of each lane per second in real time, and the data is transmitted to the regional control center through an optical fiber.

[0035] S2. Design of time-period-based basic signal timing scheme.

[0036] The design of the time-period-based basic signal timing scheme in step S2 comprises dividing a day into multiple time periods based on historical traffic flow data, and designing a basic signal timing scheme for each time period as a reference for subsequent adjustment; the basic signal timing scheme comprises signal cycle length, phase sequence, green light time of each phase, yellow light time, and all-red time.

[0037] In some embodiments of the application, the historical daily hourly traffic flow of each direction of the intersection is shown in the table. Figure 2 According to the flow chart, the K-means clustering algorithm is used for all-day traffic period division, and 24 hours can be divided into 6 time periods, as shown in Table 1.

[0038] Table 1 Time period division table

[0039] The Webster single intersection signal timing method is used for basic signal timing of the 6 time periods, and the basic signal timing schemes of each time period are shown in Table 2.

[0040] Table 2 Time-period-based basic signal timing scheme

[0041] S3. Calculate the queue length imbalance index representing the queueing dispersion degree of each phase.

[0042] In some embodiments of the present application, taking the morning peak period 07:00-09:00 as an example, the signal cycle length is 160s, and the reference green light time of the four phases is respectively: g1 (south-north left turn) = 34s, g2 (east-west straight) = 40s, g3 (east-west left turn) = 40s, and g4 (south-north straight) = 46s, and the rest is yellow light and all red time.

[0043] Set the time step length to be 3 signal cycle lengths, and at the end of the kth time step, the queue lengths of the four phases are detected as: = 85m, = 60m, = 110m, = 40m; and the average queue length of the four phases is .

[0044] According to the calculation formula of the traffic pressure weight, the traffic pressure weights of the four phases are As shown in Table 3.

[0045] Table 3 Traffic pressure weight values

[0046] According to the calculation formula of the queue length imbalance index, the queue length imbalance index is

[0047] S4. Construct a signal intersection traffic flow balancing control algorithm based on real-time detection data.

[0048] In some embodiments of the present application, the flow chart of the signal intersection traffic flow balancing control algorithm based on real-time detection data is as shown in Figure 3 Set the imbalance threshold value Because Therefore, it is necessary to optimize the basic signal timing scheme.

[0049] As known from S3, the g3 (east-west left turn) phase is the phase with the largest average queue length, and the g4 (south-north straight) phase is the phase with the smallest average queue length. Set the compensation coefficient α = 0.15 s / m and the reduction coefficient β = 0.1 s / m, then seconds seconds Normalize and to Adjust to +4 seconds, Adjust to -4 seconds, so that = 0.

[0050] Check that each adjusted phase green time meets the minimum and maximum green time limits, so the final adjustment is: .

[0051] S5. Generate and execute a new signal timing plan.

[0052] In some embodiments of the application, a new plan is generated: g1 (north-south left turn) = 34 seconds, g2 (east-west through) = 40 seconds, g3 (east-west left turn) = 44 seconds, g4 (north-south through) = 42 seconds, signal cycle length 160s unchanged. This plan is immediately issued to the signal machine and executed in the next cycle.

[0053] The queue lengths before and after the implementation of the new plan are evaluated, and the evaluation results are shown in Table 4. As can be seen from the table, after applying the optimization algorithm of the present patent, the queue lengths of each approach are reduced, and certain optimization effect is achieved.

[0054] Table 4 Optimization evaluation of queue length of each approach at the intersection

[0055] The above description of the disclosed embodiments enables those skilled in the art to carry out or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for balanced traffic flow control at signalized intersections based on real-time detection data, characterized in that, Includes the following steps: S1. Real-time collection of traffic operation data for each approach lane at the intersection; S2. Design a time-segmented basic signal timing scheme; S3. Calculate the queue length imbalance index, which characterizes the degree of queue dispersion in each phase; S4. Construct a traffic flow balancing control algorithm for signalized intersections based on real-time detection data; S5. Generate and execute a new signal timing scheme.

2. The signalized intersection traffic flow balancing control method based on real-time detection data according to claim 1, characterized in that, Step S1 involves real-time collection of traffic operation data for each approach lane at the intersection, including deploying high-precision detection equipment at the intersection traffic lights and at a preset distance upstream of the stop line to collect traffic operation data for each approach lane in real time.

3. The signalized intersection traffic flow balancing control method based on real-time detection data according to claim 2, characterized in that, The traffic operation data mentioned in step S1 includes traffic flow and queue length at each entrance lane; the queue length refers to the length of the continuous queue from the stop line to the last stopped vehicle when the green light is turned on.

4. The signalized intersection traffic flow balancing control method based on real-time detection data according to claim 1, characterized in that, Step S2 involves designing a time-segmented basic signal timing scheme, which includes dividing traffic periods based on historical traffic flow and designing a basic signal timing scheme for each period as a benchmark for subsequent adjustments. The basic signal timing scheme includes signal cycle duration, phase, phase sequence, green light time, yellow light time, and all-red light time for each phase.

5. The signalized intersection traffic flow balancing control method based on real-time detection data according to claim 1, characterized in that, The queue length imbalance index, which characterizes the degree of queuing dispersion in each phase as described in step S3, is calculated using the following formula: In the formula, Number the time steps. For the first Queue length imbalance index per step length The number of phases in one signal cycle. For the first The first step i Average queue length of each inlet lane in each phase For the first i Traffic pressure weights for each phase.

6. The signalized intersection traffic flow balancing control method based on real-time detection data according to claim 5, characterized in that, In step S3, the traffic pressure weight The calculation formula is: In the formula, For the first i The number of inlet lanes included in each phase. For the first i The saturation flow rate of each inlet channel in each phase.

7. The signalized intersection traffic flow balancing control method based on real-time detection data according to claim 1, characterized in that, Step S4, which describes constructing a signalized intersection traffic flow balancing control algorithm based on real-time detection data, includes the following steps: S4.1 sets a time step T. At the end of each time step, based on the real-time data collected in S1 and the calculation formula for the queue length imbalance index described in S3, the current step length is calculated. k Queue length imbalance index for each phase ; S4.2 Set an imbalance threshold ,like Then the traffic flow at the intersection is in a relatively balanced state, and the next step is long k +1 Use the current step size k The basic signal timing scheme; if If this happens, the traffic flow at the intersection will be severely unbalanced, so we will switch to S4.3 and optimize the basic signal timing scheme. S4.3 For the phase with the largest average queue length, in the next step... k +1 to provide green light time compensation The compensation formula is: In the formula, This is the compensation coefficient; For the phase with the minimum average queue length, in the next step... k +1 Reduce green light time The calculation formula is: In the formula, This is the reduction factor; Under the constraints that the signal cycle duration remains constant and the green light time for any phase must not be less than the minimum green light time or more than the maximum green light time, for and Perform normalization processing to ensure + =0.

8. The signalized intersection traffic flow balancing control method based on real-time detection data according to claim 1, characterized in that, Step S5, which involves generating and executing a new signal timing scheme, involves adjusting the green light time based on the output of the signalized intersection traffic flow balancing control algorithm based on real-time detection data from step S4. This new signal timing scheme is then transmitted to the intersection's signal controller via the communication network for the next step. k +1 to start execution.

9. A device, characterized in that, The device includes a processor and a memory for storing instructions or computer programs, and the processor for executing the instructions or computer programs in the memory to cause the device to perform the steps of the method according to any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on the device, cause the device to perform the steps of the method according to any one of claims 1-8.

Images