CN115830867A

CN115830867A - Signal intersection lane distribution method and device considering random traffic flow

Info

Publication number: CN115830867A
Application number: CN202211460465.6A
Authority: CN
Inventors: 黄玮; 程浩帆; 黄国煜
Original assignee: Sun Yat Sen University; Sun Yat Sen University Shenzhen Campus
Current assignee: Sun Yat Sen University; Sun Yat Sen University Shenzhen Campus
Priority date: 2022-11-17
Filing date: 2022-11-17
Publication date: 2023-03-21

Abstract

The invention discloses a signalized intersection lane allocation method and device considering random traffic flow, wherein the method comprises the following steps: acquiring a random traffic flow; carrying out random planning processing on the random traffic flow, and carrying out model construction by taking the minimum delay of the traffic flow as a target function to obtain a two-stage random planning model; decoupling the two-stage stochastic programming model according to the reliability of the service level to obtain a first-stage decoupling model and a second-stage decoupling model; performing optimization iterative computation processing on the first-stage decoupling model and the second-stage decoupling model according to a gradient descent algorithm to obtain a service level reliability index combination; and solving the first-stage decoupling model according to the service level reliability index combination to obtain a signalized intersection lane allocation result. The embodiment of the invention can improve the robustness of lane allocation, reduce the calculation complexity and the calculation cost, and can be widely applied to the technical field of road traffic management.

Description

Signal intersection lane distribution method and device considering random traffic flow

Technical Field

The invention relates to the technical field of road traffic management, in particular to a signalized intersection lane distribution method and device considering random traffic flow.

Background

With the rapid development of social economy, the travel demand of people is increasing day by day, and the phenomenon that the road supply is not matched with the travel demand is also becoming serious day by day. The intersection serving as a center for collecting and evacuating traffic flow often becomes a bottleneck road section in a traffic network, and has a key influence on delay conditions. The conventional intersection lane allocation method allocates lanes according to signal control by assuming that the traffic flow at the intersection reaches a fixed value. However, due to the fluctuation and randomness of traffic demands, the number of vehicles arriving at each period is usually different, and the related method has the problems of poor interpretability and high calculation cost.

Disclosure of Invention

In view of this, embodiments of the present invention provide a method and an apparatus for allocating lanes at a signalized intersection in consideration of random traffic flows, so as to improve robustness of lane allocation and reduce computation cost.

In one aspect, the invention provides a signalized intersection lane allocation method considering random traffic flow, which comprises the following steps:

acquiring a random traffic flow;

carrying out stochastic programming processing on the stochastic traffic flow, and carrying out model construction by taking the minimum delay of the traffic flow as a target function to obtain a two-stage stochastic programming model;

decoupling the two-stage stochastic programming model according to the reliability of the service level to obtain a first-stage decoupling model and a second-stage decoupling model;

performing optimization iterative computation processing on the first-stage decoupling model and the second-stage decoupling model according to a gradient descent algorithm to obtain a service level reliability index combination;

and solving the first-stage decoupling model according to the service level reliability index combination to obtain a signalized intersection lane allocation result.

Optionally, the randomly planning the random traffic flow, and performing model construction with a minimum delay of the traffic flow as an objective function to obtain a two-stage random planning model, including:

carrying out random scene division processing on the random traffic flow to obtain a random scene set;

performing traffic flow minimum delay calculation according to the random scene set to obtain the target function;

and constructing a model according to the objective function to obtain a two-stage stochastic programming model.

Optionally, the performing, according to the random scene set, a minimum delay calculation of a traffic flow to obtain the objective function includes:

the objective function comprises a first stage objective function and a second stage objective function;

performing traffic flow minimum delay expectation calculation on all scenes in the random scene set to obtain the first-stage objective function;

and solving the first-stage objective function to obtain a lane allocation scheme, and performing traffic delay calculation on any scene in the random scene set according to the lane allocation scheme to obtain the second-stage objective function.

Optionally, the performing traffic delay calculation on any scene in the random scene set according to the lane allocation scheme to obtain the second-stage objective function includes:

carrying out traffic flow cycle division processing on any scene in the random scene set according to the lane allocation scheme to obtain a traffic flow cycle set;

performing lane delay calculation processing on the traffic flow period set to obtain scene lane delay;

and obtaining the second stage objective function according to the scene lane delay and the scene traffic flow.

Optionally, the performing lane delay calculation processing on the traffic flow cycle set to obtain a scene lane delay includes:

acquiring the cycle length, the traffic arrival rate, the lane green light time, the saturation flow rate and the number of remaining queued vehicles of each cycle in the traffic cycle set;

and calculating the cycle length, the traffic flow arrival rate, the lane green light time, the saturated flow rate and the number of the remaining queued vehicles by using a lane delay calculation formula to obtain the scene lane delay.

Optionally, the decoupling processing is performed on the two-stage stochastic programming model according to the service level reliability to obtain a first-stage decoupling model and a second-stage decoupling model, and the method includes:

initializing a service level reliability index;

performing reserve traffic capacity calculation processing on the first stage of the two-stage stochastic programming model through the service level reliability index to obtain a first-stage decoupling model;

and carrying out traffic delay calculation processing on the second stage of the two-stage stochastic programming model according to the first-stage decoupling model to obtain a second-stage decoupling model.

Optionally, the performing, according to a gradient descent algorithm, optimization iterative computation processing on the first-stage decoupling model and the second-stage decoupling model to obtain a service level reliability index combination includes:

initializing a service level reliability set;

inputting the service level reliability set into the first-stage decoupling model to perform lane allocation calculation processing to obtain an allocated lane;

performing expected total delay calculation processing on the second-stage decoupling model according to the distribution lane to obtain a total delay expected difference value;

and updating the service level reliability set according to the total delay expected difference, returning to the step of inputting the service level reliability set into the first-stage decoupling model for lane distribution calculation processing to obtain a distributed lane, and determining the service level reliability set as a service level reliability index combination until the total delay expected difference is less than a preset threshold value.

On the other hand, the embodiment of the invention also provides a signalized intersection lane distribution device considering random traffic flow, which comprises the following components:

the system comprises a first module, a second module and a third module, wherein the first module is used for acquiring random traffic;

the second module is used for carrying out random planning processing on the random traffic flow, and carrying out model construction by taking the minimum delay of the traffic flow as a target function to obtain a two-stage random planning model;

the third module is used for decoupling the two-stage stochastic programming model according to the reliability of the service level to obtain a first-stage decoupling model and a second-stage decoupling model;

the fourth module is used for carrying out optimization iterative computation processing on the first-stage decoupling model and the second-stage decoupling model according to a gradient descent algorithm to obtain a service level reliability index combination;

and the fifth module is used for solving the first-stage decoupling model according to the service level reliability index combination to obtain a signal intersection lane distribution result.

On the other hand, the embodiment of the invention also discloses an electronic device, which comprises a processor and a memory;

the memory is used for storing programs;

the processor executes the program to implement the method as described above.

On the other hand, the embodiment of the invention also discloses a computer readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to realize the method.

In another aspect, an embodiment of the present invention further discloses a computer program product or a computer program, where the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The computer instructions may be read by a processor of a computer device from a computer-readable storage medium, and the computer instructions executed by the processor cause the computer device to perform the foregoing method.

Compared with the prior art, the invention adopting the technical scheme has the following technical effects: the embodiment of the invention carries out random planning processing on the random traffic flow, and carries out model construction by taking the minimum delay of the traffic flow as a target function to obtain a two-stage random planning model; the method can be applied to a scene of random traffic flow arrival, a model is constructed by taking the minimum delay as an optimization target, the expected delay of traffic flow at the intersection is effectively reduced, and the robustness of a lane allocation scheme is improved; in addition, the embodiment of the invention also introduces the concept of the service level reliability, decouples the model, converts the problem into the service level reliability combination which enables the expected total delay to be minimum, reduces the calculation complexity and improves the solving efficiency.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a flowchart of a method for allocating lanes at a signalized intersection in consideration of random traffic flow according to an embodiment of the present disclosure;

fig. 2 is an explanatory diagram of lane delay calculation provided in an embodiment of the present application;

FIG. 3 is a diagram illustrating a coupling relationship of a two-phase stochastic programming model according to an embodiment of the present disclosure;

fig. 4 is a flowchart of solving a decoupled model according to an embodiment of the present disclosure;

fig. 5 is a schematic diagram of a random traffic flow inlet/outlet lane according to an embodiment of the present disclosure;

fig. 6 is a schematic diagram of a lane assignment adjustment change according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

In the related art, intersection optimization is mainly based on signal control optimization, namely, the passing time and the passing sequence of conflicting traffic flows are controlled through signal timing optimization. The lane allocation of the intersection is used as an important means for allocating the intersection space resources, and the cooperative optimization of the lane allocation and the signal control can further improve the running efficiency of the intersection, so that the lane allocation becomes one of the keys for researching the optimization of the intersection. Most lane function allocation and signal control cooperative optimization methods mostly assume that the traffic flow arrival at the intersection is a fixed value, in fact, traffic demand has volatility and randomness, and the number of arriving vehicles in each period is usually different. In the signal timing optimization, in order to deal with the volatility and the randomness, the intersection can be optimized by adopting a mode of adjusting the signal timing parameters in real time. In the cooperative optimization of lane allocation and signal allocation, in consideration of potential safety hazards and extra delay possibly caused by frequent lane function adjustment in real time, it is often desirable to find a fixed lane allocation scheme within a long period of time, and under the scheme, real-time adjustment is performed on signal allocation so as to obtain a control scheme for minimizing delay. At present, the research on the real-time optimization cooperation of lane function allocation and traffic signal timing, particularly the research on the minimum delay as a target function, is less, and the existing method also has the problems of poor interpretability, high calculation cost and the like.

In view of this, referring to fig. 1, an embodiment of the present invention provides a method for allocating lanes at a signalized intersection in consideration of random traffic flows, including:

s101, acquiring a random traffic flow;

s102, carrying out random planning processing on the random traffic flow, and carrying out model construction by taking the minimum delay of the traffic flow as a target function to obtain a two-stage random planning model;

s103, decoupling the two-stage stochastic programming model according to the reliability of the service level to obtain a first-stage decoupling model and a second-stage decoupling model;

s104, performing optimization iterative computation processing on the first-stage decoupling model and the second-stage decoupling model according to a gradient descent algorithm to obtain a service level reliability index combination;

and S105, solving the first-stage decoupling model according to the service level reliability index combination to obtain a signal intersection lane distribution result.

The method and the device are applied to intersection lane distribution in a random traffic flow scene. The embodiment of the invention firstly obtains the random traffic flow, randomly plans the random traffic flow and constructs a two-stage random planning model taking the minimum delay as a target function. The two-phase stochastic programming model comprises a first-phase model and a second-phase model, and according to the definition of the problem, the two phases of the two-phase stochastic programming problem are determined to meet the following requirements: in the first stage, according to the first-stage model, obtaining a lane allocation scheme which enables total delay under all possible scenes to be minimum and is applied to the time period covered by all the scenes to be kept unchanged; in the second stage, a signal timing scheme with the minimum total delay in a specific scene is obtained under a fixed lane allocation scheme according to the second-stage model, so that the randomness of the arrival of traffic flow is adapted.

And then decoupling the highly-coupled two-stage random programming model by taking the service level reliability as a decoupling index, constructing the decoupled first-stage and second-stage models, solving by a gradient descent algorithm to obtain an optimal reliability index combination, and obtaining a lane distribution scheme corresponding to the reliability index combination, namely a signalized intersection lane distribution result.

It should be noted that, in the process of constructing the two-stage stochastic programming model, constraint conditions of the two-stage stochastic programming model also need to be set:

(1) And (3) lane minimum right of way constraint: i.e. to ensure that each lane has at least one directional right of way (or steer function), can be expressed as

Wherein, delta _i，j，k Indicating whether the driving direction j of the kth lane of the entrance i is permitted or not, and is permitted when the value thereof is 1 and is not permitted when the value thereof is 0.

(2) Function constraint of adjacent lanes: i.e. to ensure that the steering functions of adjacent lanes cannot conflict with each other, can be expressed as:

1-δ _t，j，k+1 ≥δ _i，m，k ；

wherein i =0,1, …, i _max ；j＝0，1，…j _max -1；m＝j，j+1，…j _max And k =0,1, … k _max 。

(3) The number of inlet and outlet channels is restricted: i.e. ensuring that the number of outlet channels is not less than the number of inlet channels, can be expressed as

Wherein, A _T(i，j) The number of lanes of the exit lane with the serial number T (i, j) is indicated, and T (i, j) is the serial number of the exit lane to which a traffic stream with the traveling direction j from the entrance i travels.

(4) And (3) period duration constraint: i.e. ensuring that the period duration is within the specified value, can be expressed as

Where ξ is the reciprocal of the signal period duration; c. C _min And c _max The minimum value and the maximum value of the period duration are respectively determined according to actual scenes.

(5) Green light start time and duration constraints: i.e. to ensure that the start time and duration of the green light are within specified values (determined from the actual scene), the constraint of the start time of the green light can be expressed as

The constraint on the duration of the green light can be expressed as

Wherein, theta _i Denotes the green light start time, phi, of entry i _i Green light duration, g, for entry i _min And g _in Respectively, the minimum value of the phase green time and the phase green interval time.

(6) Shared lane signal control constraint: i.e. to ensure that when a lane allows two or more traffic to turn, i.e. the lane is a pool lane, then they must be controlled by one and the same signal phase, which can be expressed as

M(1-δ _i，j，k )≥Θ _i，k -θ _i ≥-M(1-δ _i，j，k )；

M(1-δ _i，j，k )≥Φ _i，k -φ _i ≥-M(1-δ _i，j，k )；

Wherein, theta _i，k Green light start time, phi, representing the i-th lane of entry _i，k Indicating the green duration of the k-th lane at entry i, M is a sufficiently large positive number.

(7) Flow conservation constraint: i.e. to ensure that the allocated flow is able to meet the traffic demand, can be expressed as

Wherein Q _i，j The traffic demand which represents the driving direction j of the inlet i is an input quantity; q. q of _i，j，k Indicating the k-th lane allocated to the entry iThe traffic flow in the traveling direction j is large.

(8) And (4) traffic prohibition constraint: that is, when a lane does not have the right to pass in a certain direction, the traffic flow in the direction cannot be allocated to the lane, which can be expressed as

M·δ _i，j，k ≥q _i，j，k ；

(9) Lane equal flow rate ratio constraint: that is, when the adjacent lanes have the same steering function, their flow rate ratio is equal, which can be expressed as

Wherein r is _i，j，k The turning radius of the traffic flow with the driving direction j of the kth lane of the entrance i,

the straight-going saturation flow rate of the kth lane at the inlet i is represented, and the specific value is usually determined according to the road requirement in the actual scene.

Further as a preferred embodiment, the randomly planning the random traffic flow, and constructing a model by using the minimum delay of the traffic flow as an objective function to obtain a two-stage randomly planning model, includes:

In the embodiment of the invention, the random scene division processing is carried out on the random traffic flow to obtain a random scene set. When random traffic demands meet a specific continuous probability distribution, the expectation of total delay under all scenes can be represented in an integral form, so that a two-stage stochastic programming model

Can be expressed as:

where Dr is the delay obtained in the second stage and P is the probability of this occurring. The objective function D of the first stage represents the objective function Dr of the second stage _k I.e. the expectation of the total delay under each scenario.

But considering that this form of solution is difficult to obtain, in this type of problem, the expectation is typically estimated using scene simulation. Assume that the number of scenes to be generated is l. A set of scenes may be represented as S = {1,2. Each scene occurs with equal probability. Two-phase stochastic programming model

Further expressed as:

wherein D represents the first stage objective function,

representing the minimum expected total delay of the traffic flow when only adjusting the lane distribution, E representing the expectation, dr representing the second stage of the stochastic programming model, G representing the signal control parameters of the stochastic traffic flow, delta representing the lane distribution scheme, Q representing the traffic demand of the stochastic traffic flow, kappa representing the kth scene in the stochastic scene set, kappa representing the traffic demand of the stochastic scene set _max Representing the total number of sets of random scenes, P _κ Denotes the probability of occurrence of the k-th scene, Q _κ Represents the traffic demand of the kth scenario, dr _k Representing the second stage objective function, G _κ Signal control parameters representing the kth scene.

Further as a preferred embodiment, the performing the minimum delay calculation of the traffic flow according to the random scene set to obtain the objective function includes:

In the embodiment of the invention, under the scene of random traffic arrival, a two-stage stochastic programming model taking minimum delay as an objective function is constructed. The two-stage stochastic programming model solves the fixed lane allocation scheme which enables all scenes to have minimum delay in the first stage, so that the first-stage objective function is the traffic flow minimum delay expectation obtained by calculating all scenes in the stochastic scene set; the model solves a signal timing scheme which enables delay of each specific scene to be minimum under the fixed lane distribution scheme in the second stage, and further obtains the minimum value of total expected delay of all scenes under the lane distribution scheme, so that the second-stage objective function is the traffic delay calculated for any scene in the random scene set according to the fixed lane distribution scheme obtained by the first-stage solution.

Further as a preferred embodiment, the performing traffic delay calculation on any scene in the random scene set according to the lane assignment scheme to obtain the second-stage objective function includes:

In an embodiment of the invention, the second stage objective function Dr _κ Can be used forExpressed as:

wherein i represents the serial number of the intersection approach, j represents the driving direction of random traffic flow, k represents the serial number of the lane, n represents the traffic flow period, q represents the traffic flow, d represents the lane delay,

representing the minimum value of delay in a particular scenario that can be achieved by adjusting the signal timing alone.

Further, as a preferred embodiment, the performing lane delay calculation processing on the traffic flow cycle set to obtain a scene lane delay includes:

In the embodiment of the invention, the lane delay calculation formula is as follows:

the constraint condition of (1) in the formula is

The constraint condition of (2) in the formula is

Where C denotes the cycle length, q denotes the arrival rate of the traffic flow, phi denotes the green duration of the lane, and s denotes the saturation flow rate, e.g.

Indicating the saturation flow rate on the kth lane of the ith entrance lane for the nth cycle of the kth scenario.

And H represents the number of remaining in-line vehicles, expressed as:

in the formula (I), the compound is shown in the specification,

indicating the number of remaining queued vehicles on the ith lane of the ith entrance lane for the nth cycle of the kth scenario.

It should be noted that, the method for deriving lane delay and the number of remaining queued vehicles is shown in fig. 2, and the delay values of both undersaturation and oversaturation types can be calculated by separately calculating the areas of the shaded portions in the figure. And the number of remaining vehicles is obtained by calculating the relationship between the upper and lower portions of the hatched portion.

Further as a preferred embodiment, the decoupling processing is performed on the two-stage stochastic programming model according to the service level reliability to obtain a first-stage decoupling model and a second-stage decoupling model, and the method includes:

initializing a service level reliability index;

In the embodiment of the present invention, as shown in fig. 3, in the two-stage stochastic programming model, solving the second-stage problem requires obtaining in advance a lane function allocation scheme that minimizes the total delay in the first stage, and the objective function in the second stage is used as a component of the objective function in the first stage to affect the result of the lane function allocation scheme, and these two problems have coupling property, and solving the delay is a nonlinear programming problem, which also makes the difficulty in solving significantly increased.

To decouple the two-phase stochastic programming model described above, the concept of service level reliability is introduced. The service level reliability refers to the probability that a certain direction of an entrance lane of an intersection can meet a specific service level grade, and is numerically equal to the proportion of all possible scenes of the scenes that traffic demands can be met under the specific service level. Wherein, the service level grade division of a certain direction of the entrance way is consistent with the service grade division of the national highway section.

Wherein, the service level reliability index rho of the I direction j of the entrance way _i，j Can be expressed as:

wherein represents P _r The condition in parentheses is the likelihood of true, and θ is determined by the service level class. In the method, four levels of service levels are generally selected, the definition of the service level grade of the road section is referred, and the traffic flow is in the lower limit of the stable flow range at the moment, and can also be adjusted according to the actual road condition. And when the service level grade is four grades, theta is 0.9, and the value is taken by referring to the value of V/C in the service grade of the road section. Where V denotes the maximum service traffic volume and C denotes the basic traffic capacity.

Introducing the service level reliability index can provide a decoupling method for processing the uncertainty problem of high coupling and large calculation amount:

with service level reliability, the demand can be divided into two parts: the first part is to obtain a lane allocation scheme which is fixed for a long time in a certain time period based on the reliability of the service level; the minimum expected total delay based on the fixed lane assignment scheme can then be derived by adjusting the signal control scheme for each scene.

As a further preferred embodiment, the performing optimization iterative computation processing on the first-stage decoupling model and the second-stage decoupling model according to a gradient descent algorithm to obtain a service level reliability index combination includes:

initializing a service level reliability set;

In the embodiment of the present invention, as shown in fig. 4, the decoupled model may solve the original problem by using the service level reliability index:

firstly, a set formed by the service level reliability of all the current entrance lanes is used as input, a lane allocation scheme is calculated according to a model in a first stage, and then expected total delay is obtained by solving a problem in a second stage under the lane allocation scheme. And then observing the change condition of the expected total delay, adjusting the reliability set, and continuously iterating the optimization process to obtain a group of service level reliability index combinations capable of minimizing the expected total delay. The lane allocation scheme obtained based on the index combination is the lane allocation scheme which needs to minimize the expected total delay, namely the signal intersection lane allocation result.

To further simplify the calculations, in this embodiment reserve capacity is introduced to replace delays in the objective function of the decoupled first stage model. The reserve capacity describes, among other things, the relationship between the traffic supply and the traffic demand.

It should be particularly noted that, in the solution, certain accuracy of solution is sacrificed, and if higher calculation accuracy is to be ensured, a method of enumerating a lane assignment scheme may be used instead of the method of solving the decoupled first-stage model in this embodiment, but the calculation efficiency is lower.

The objective function after introducing reserve capacity as an alternative can be expressed as:

where μ represents reserve traffic capacity. ρ is the service level reliability of all the turns of all the inlet roads of the actual intersection.

It should be noted that, in addition to the original constraints (1) - (6), (8), (9) of the two-stage stochastic programming model, the following constraint conditions need to be satisfied for the decoupled problem:

(10) Number of service vehicles constraint: namely, the relation among the number of arriving vehicles, the traffic capacity of the road and the reliability of the service level in the definition of the reliability of the service level is ensured to be satisfied.

(11) Reserve flow conservation constraint: i.e. to ensure that the allocated flow and reserve capacity can meet traffic demands.

The number constraint of passing vehicles is used for ensuring the smooth passing of traffic flow, and the reserve flow constraint is used for describing the relation between reserve passing capacity, traffic demand and lane flow.

The second-stage model is consistent with the second-stage model in the original two-stage stochastic programming model.

In this embodiment, the optimal reliability indicator combination is solved by a gradient descent algorithm comprising the steps of:

step 1. Based on the given rho ₀ Calculating an initial expected total delay D _origin And let D = D _origin Where ρ is ₀ Refers to the initial solution of the service level reliability combination p. While each p in the initial solution _i，j The value of (2) can be obtained by substituting a scheme without considering volatility into the definition of the reliability of the service level, or different initial solutions can be continuously introduced in an experiment to find a group with higher solving efficiency and better solving effect;

step 2, judging | D-D _origin If yes, stopping calculation, otherwise entering step 3, wherein the epsilon represents a preset threshold value which is a minimum value close to 0, in the embodiment, 0.01 is selected, and the method can be adjusted according to the situation in the actual operation;

step 3, judging D-D _origin If < 0 is true, let D = D _origin ，ρ ₀ = ρ, otherwise go to step 4;

step 4, let rho _i，j And + Δ ρ, determining whether the result is less than 1, and if the result is less than 1, entering step 5. Otherwise, go to step 6. Wherein, Δ ρ is a small disturbance value, generally 0.05, and can be adjusted according to actual conditions;

step 5, let ρ _i，j - Α ρ, go to step 6;

step 6, the current rho is processed _i，j Substituting into the first phase problem, a lane function assignment scheme is calculated. Judging whether the lane scheme is changed, if not, entering a step 4, otherwise, entering a step 7;

step 7, calculating expected D (rho) of all getting-off delay of the current lane function distribution scheme _i，j ) If D (ρ) _i，j )-D _origin When the value is less than or equal to 0, the number is recorded

D (rho i, j), otherwise, marking as 0;

step 8, judging whether j is equal to j _max If not equal to j _max Then let j = j +1, go back to step 4, if j is equal to _max Entering a step 9;

step 9, judging whether i is equal to i _max If not equal to i _max Then let i = i +1, j =1, go back to step 4, if it is equal to i _max Entering step 10;

step 10. Calculating the descent gradient

Wherein λ and γ need to be determined experimentally;

step 11, for all i and j, order

Substituting the calculated expected delay D (ρ);

step 12, if D (rho) -D _origin > 0 or D (rho) -D _origin < sigma, go to step 2, otherwise order

Then go to step 10, where σ represents a minimum value close to 0, in the embodiment 0.01, and it can be adjusted according to the situation in the actual operation.

In a feasible implementation manner of the embodiment of the invention, fig. 5 is a schematic diagram of an entrance/exit lane of a single-point intersection of the embodiment. In the embodiment, four branches of east, south and north are arranged at the intersection, and each inlet is provided with an intersection which controls three lanes in the south and north and four lanes in the east and west of the vehicle under the control of a signal lamp. The intersection traffic signal has two phases which are connected by the full red time. The vehicle arrival rate varies between different periods and scenarios and follows a known probability distribution. Meanwhile, the vehicle arrival rate per cycle is constant. Wherein fluctuations between scenes may be interpreted as daily changes in real-life scenarios. In an embodiment, the minimum green time in all directions is 10 seconds. The minimum and maximum periods are 40 seconds and 120 seconds, respectively. For simplicity, the saturation flow was set to 1965 pcu/h/lane. All turning radii are set at 12m. The service level is four, so the saturation level of all lanes is 90%, the initial solution ρ ₀ Each of p in (1) _i，j Directly by bringing the solution of the reference scheme into the definition of the service level reliability. The random traffic demand follows normal distribution, and the mean value Q of the random demand _κ As shown in table 1 below.

TABLE 1 mean observed traffic demand (pcu/h)

To represent different random fluctuation cases, we set the standard deviation α of the normal distribution to three levels: 0.1Q _κ ，0.3Q _κ ，0.5Q _κ The larger the standard deviation, the larger the traffic flow random fluctuation. In addition, the number of random demand scenes used in the present embodiment is 50 scenes, and 20 cycles are calculated for each scene.

For comparison, the lane allocation scheme with the largest reserve traffic capacity, which does not consider traffic demand fluctuation in the first stage, is used as a reference scheme, and compared with the scheme provided by the present invention, on the premise that the second stage is controlled by real-time signals, the expected total delay result is shown in table 2.

TABLE 2 comparison of results

Also, a comparison of gap results is shown in table 2. It can be seen that traffic flow has a significant impact on delay when traffic demand is high. Even with real-time signal control, a larger ripple average results in a larger delay. Fig. 6 shows when α =0.3Q _κ And (5) obtaining a lane function adjusting scheme. As shown in fig. 6, although the adjustment only occurs on three lanes, a 7.15% reduction in total delay is expected, significantly reducing the on-board delay. As shown in the embodiment, in the aspect of delay performance, the lane distribution plan calculated by the proposed two-stage random planning method is compared with a reference method, so that delay at an intersection can be reduced to a certain extent, and the traffic running effect is obviously improved.

Corresponding to the method of fig. 1, an embodiment of the present invention further provides an electronic device, including a processor and a memory; the memory is used for storing programs; the processor executes the program to implement the method as described above.

Corresponding to the method of fig. 1, the embodiment of the present invention also provides a computer-readable storage medium, which stores a program, and the program is executed by a processor to implement the method as described above.

The embodiment of the invention also discloses a computer program product or a computer program, which comprises computer instructions, and the computer instructions are stored in a computer readable storage medium. The computer instructions may be read by a processor of a computer device from a computer-readable storage medium, and executed by the processor, causing the computer device to perform the method illustrated in fig. 1.

In summary, the embodiments of the present invention have the following advantages: aiming at the randomness of traffic flow, the invention firstly constructs a two-stage random planning model of lane distribution and signal control cooperative optimization, wherein the first stage hopes to search a lane function distribution scheme which can cause the vehicle getting-off delay to be the minimum in all scenes, and the second stage is to solve the signal control parameter which causes the vehicle delay to be the minimum in the determined scenes, namely the determined traffic demand and lane function distribution scheme. Introducing a concept of service level reliability in the process of solving the model, decoupling the problem, and converting the problem into a problem of finding a reliability index combination to minimize the expected total delay; finally, we adopt a gradient descent algorithm to obtain the final solution. On one hand, the two-stage stochastic programming model constructed by the method can find a lane allocation scheme which minimizes delay and has higher traffic system robustness. On the other hand, by introducing the concept of the reliability of the service level, the method reduces the computational complexity of the method and improves the solving efficiency.

In alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flow charts of the present invention are provided by way of example in order to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed, and in which sub-operations described as part of larger operations are performed independently.

Furthermore, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise indicated to the contrary, one or more of the described functions and/or features may be integrated in a single physical device and/or software module, or one or more functions and/or features may be implemented in separate physical devices or software modules. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be understood within the ordinary skill of an engineer given the nature, function, and interrelationships of the modules. Accordingly, those skilled in the art can, using ordinary skill, practice the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative of and not intended to limit the scope of the invention, which is defined by the appended claims and their full scope of equivalents.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Further, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.

It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.

In the description of the specification, reference to the description of "one embodiment," "some embodiments," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims

1. A method for signalized intersection lane assignment in consideration of random traffic flow, the method comprising:

acquiring a random traffic flow;

carrying out random planning processing on the random traffic flow, and carrying out model construction by taking the minimum delay of the traffic flow as a target function to obtain a two-stage random planning model;

and solving the first-stage decoupling model according to the service level reliability index combination to obtain a signal intersection lane allocation result.

2. The method according to claim 1, wherein the stochastic programming of the stochastic traffic flow is modeled with a minimum delay of traffic flow as an objective function, and the two-stage stochastic programming model is obtained by:

3. The method according to claim 2, wherein the performing traffic flow minimum delay calculation according to the random scene set to obtain the objective function comprises:

4. The method according to claim 3, wherein the performing a traffic delay calculation on any scene in the random scene set according to the lane assignment scheme to obtain the second-stage objective function comprises:

5. The method according to claim 4, wherein the performing lane delay calculation processing on the traffic flow cycle set to obtain a scene lane delay comprises:

6. The method of claim 1, wherein the decoupling the two-stage stochastic programming model according to the service level reliability to obtain a first-stage decoupling model and a second-stage decoupling model comprises:

initializing a service level reliability index;

7. The method according to claim 1, wherein the performing optimization iterative computation processing on the first stage decoupling model and the second stage decoupling model according to a gradient descent algorithm to obtain a service level reliability index combination comprises:

initializing a service level reliability set;

performing expected total delay calculation processing on the second-stage decoupling model according to the assigned lanes to obtain a total delay expected difference value;

8. A signalized intersection lane assignment device considering random traffic flow, the device comprising:

9. An electronic device, comprising a memory and a processor;

the memory is used for storing programs;

the processor executing the program implements the method of any one of claims 1 to 7.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method of any one of claims 1 to 7.