Multi-objective optimization method for variable speed limit control strategy of intelligent expressway

Abstract

The embodiment of the present disclosure provides a kind of intelligent highway variable speed limit control strategy multi-objective optimization method, belong to data processing technical field, specifically include: step 1, based on the theory of meta-cell variable, fusion metastable state, traffic capacity variable and free-flow speed variable, CTM model is improved, the corresponding highway simulation model of target section is obtained;Step 2, according to the preset optimization goal and constraint condition, NSGA-II algorithm and highway simulation model are used to solve, and optimization strategy set is generated.The scheme of the present disclosure, from the space-time characteristics of highway traffic flow under the influence of event, constructs the variable CTM model for highway active control, considers traffic safety, constructs the accident risk calculation method based on the variable CTM model, and proposes the variable speed limit control multi-objective optimization method of occasional bottleneck with safety and efficiency as the goal, which improves the optimization accuracy, adaptability, safety and efficiency.

Description

TECHNICAL FIELD

[0001] The embodiment of the present disclosure relates to the technical field of data processing, in particular to a multi-objective optimization method for variable speed limit control strategy of intelligent expressway. BACKGROUND

[0002] In recent years, with the rapid development of intelligent expressway active control technology, variable speed limit (VSL) has become an effective measure for road dynamic control. VSL is a dynamic speed limit method that dynamically updates the speed limit value according to the road operating conditions, which can effectively control the traffic flow state. It is suitable for both common congestion caused by changes in road conditions and occasional congestion caused by large-scale activities, traffic accidents, and adverse weather. The composition of the VSL system includes inductive coils laid in the bottleneck area, road condition and weather sensors, and variable speed limit signs set at the start of the speed limit, as well as a central control system. Through real-time monitoring of road conditions by inductive devices, traffic flow information such as flow and speed, and environmental information such as weather and road conditions are obtained. The central control system solves the optimal control strategy according to the speed limit starting conditions and updating rules, and finally the variable speed limit sign transmits the speed limit information to the driver, forming an active control logic of "perception-decision-response". Domestic and foreign scholars have done a lot of theoretical research on VSL control. Statistics show that most of the existing research focuses on VSL control optimization under common congestion, and there is less research under traffic event conditions. Moreover, most of the research methods combine the simulation model of the expressway with the VSL control optimization model. Expressway is suitable for macroscopic traffic flow simulation model, among which the CTM (Cell Transmission Model, CTM) model and the METANET model are widely used. Scholars have summarized the macroscopic traffic flow simulation model and its improvement method, and believe that the CTM model has high solving efficiency and is easy to develop, which is more suitable for VSL research on expressway. Moreover, the VSL optimization control algorithm is divided into single-objective optimization based on genetic algorithm or reinforcement learning and multi-objective optimization based on multi-objective genetic algorithm.

[0003] The authenticity of the simulation model is the basis for strategy optimization, therefore, many scholars have improved the basic model. Mainly including according to the traffic flow state of the highway bottleneck area and its upstream and downstream, realizing the improved CTM model of the passing capacity reduction and the variable speed, according to the variable demand of the influence of highway traffic events and traffic control intervention, constructing a variable CTM model for different traffic control. Although scholars have made a lot of improvements to the basic model, the use scene is relatively single, and the existing model still has shortcomings in the face of flexible and variable traffic control under traffic events. In addition, due to the lack of accurate quantitative evaluation index of traffic safety level in the macroscopic simulation model, the existing variable speed limit control strategy optimization method mainly focuses on the efficiency target, and the safety target strategy optimization research is less, which is difficult to consider traffic safety and efficiency at the same time.

[0004] Therefore, there is an urgent need for a smart highway variable speed limit control strategy multi-objective optimization method with high precision and adaptability, which considers safety and efficiency at the same time. SUMMARY

[0005] Therefore, the embodiments of the present disclosure provide a smart highway variable speed limit control strategy multi-objective optimization method, which at least partially solves the problems of poor optimization precision, adaptability, safety and efficiency in the prior art.

[0006] The embodiments of the present disclosure provide a smart highway variable speed limit control strategy multi-objective optimization method, which comprises:

[0007] Step 1, based on the variable of metacell, the fusion metastable state theory, the variable of passing capacity and the variable of free flow speed, the CTM model is improved to obtain the corresponding highway simulation model of the target section;

[0008] Step 2, according to the preset optimization target and constraint condition, the NSGA-II algorithm and the highway simulation model are used for solving to generate an optimization strategy set.

[0009] According to a specific implementation mode of the embodiments of the present disclosure, the step 1 specifically comprises:

[0010] Step 1.1, selecting the number of vehicles N i (t) as the characterization variable of the cell, selecting the density k i (t) as the characterization variable of the cell parameter update change, thereby introducing the cell length variable l i , and needs to meet the cell division condition: that is, the cell length is not less than the distance d that the vehicle travels at the free flow speed within a single simulation step, and the updated cell density formula is:

[0011]

[0012] Where, ΔT is the time period, li is the cell length, λ i is the number of lanes in cell i, q i is the flow in cell i in the tth time period, R i,in is the inflow from the on-ramp in cell i in the tth time period, R i,out is the outflow to the off-ramp in cell i in the tth time period, R

[0013] Step 1.2, two critical densities are introduced as the boundaries of traffic state phase transition, denoted as forward phase transition density k a and reverse phase transition density k b , a state variable Z i (t) is introduced to redefine the criterion of traffic state:

[0014]

[0015]

[0016]

[0017] where ω is the traffic flow reverse wave speed, v f is the road free flow speed, k j is the road jam density, Q max represents the maximum road capacity;

[0018] Step 1.3, the traffic flow fundamental diagram in the CTM model is modified according to the statistical law of the target section;

[0019] Step 1.4, the traffic flow fundamental diagram in the CTM model is modified according to the critical density k c and the capacity Q vsl under speed limit control;

[0020] Step 1.5, the expressway simulation model is formed according to steps 1.1 to 1.4.

[0021] According to a specific implementation manner of the embodiment of the present disclosure, the expressions of the critical density k c and the capacity Q vsl under speed limit control are

[0022]

[0023] Q vsl = k c v sl

[0024] where v sl is the speed limit value, k cQ is the critical density of the road vsl Q is the capacity under speed limit control.

[0025] According to a specific implementation manner of the embodiment of the present disclosure, the optimization target comprises an efficiency target and a safety target.

[0026] According to a specific implementation manner of the embodiment of the present disclosure, the efficiency target is a total driving time of vehicles, and an expression of the efficiency target is

[0027]

[0028] wherein T is a number of simulation periods, N is a number of cells, k i (t) is a density of the cell i in the tth simulation period, l i is a length of the cell i, and Δt is a simulation period length.

[0029] According to a specific implementation manner of the embodiment of the present disclosure, the safety target is a risk of total collision of the road in a preset period, and an expression of the safety target is

[0030]

[0031] wherein t' is a t'th 5min simulation period, and T' is a number of 5min periods into which a simulation length is divided.

[0032] According to a specific implementation manner of the embodiment of the present disclosure, the constraint condition is that a speed limit difference in adjacent control periods on a same road section and a speed limit difference on adjacent road sections in a same control period do not exceed a threshold value of speed per hour.

[0033] According to a specific implementation manner of the embodiment of the present disclosure, the step 2 specifically comprises:

[0034] According to expressions corresponding to the efficiency target and the safety target, a target function is obtained, wherein an expression of the target function is

[0035] A variable speed limit control strategy multi-objective optimization algorithm is formed according to the target function and the constraint condition.

[0036] A joint highway simulation model is used to solve the variable speed limit control strategy multi-objective optimization algorithm by using an NSGA-II algorithm to obtain an optimization strategy set.

[0037] The intelligent expressway variable speed limit control strategy multi-objective optimization scheme in the embodiments of the present disclosure includes: step 1, based on the variable metacell, the fusion metastable state theory, the variable traffic capacity and the variable free flow speed, the CTM model is improved to obtain the expressway simulation model corresponding to the target section; step 2, according to the preset optimization target and constraint condition, the NSGA-II algorithm and the expressway simulation model are used for solving to generate an optimization strategy set.

[0038] The beneficial effects of the embodiments of the present disclosure are: through the scheme of the present disclosure, for the simulation model, the present disclosure focuses on the optimization of the expressway variable speed limit control under the influence of traffic events, and the variable CTM model for the active control of the expressway is constructed from the space-time characteristics of the expressway traffic flow under the influence of events. Specifically, it includes the variable CTM model without external intervention by fusing the metastable state theory and the variable cell length, and the variable CTM model with external intervention by considering the decrease of the bottleneck area traffic capacity caused by the influence of traffic events and the variable speed under the traffic control, which together constitute the variable CTM model for traffic control. The use scenario of the variable CTM model is extensive and has expandability. Including the traffic congestion caused by ramp-mainline merging, large-scale activities, traffic accidents and bad weather, the traffic situation simulation can be carried out respectively with or without external intervention, and for the optimization method, due to the uncertainty of the traffic bottleneck under the influence of events, the accidents caused are often serious, and are more likely to cause secondary accidents. Therefore, more safety needs to be considered in actual application, and the road traffic capacity also needs to be fully utilized. Compared with the traditional single-objective optimization method, the present disclosure considers traffic safety, constructs an accident risk calculation method based on the variable CTM model, and proposes a multi-objective optimization method of the occasional bottleneck variable speed limit control with safety and efficiency as the target, which provides more strategy selection for decision makers, and improves the optimization accuracy, adaptability, safety and efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creating any creative labor.

[0040] Figure 1 A flowchart of a smart expressway variable speed limit control strategy multi-objective optimization method provided by the embodiments of the present disclosure is shown in the figure;

[0041] Figure 2 A variable cell length division schematic diagram provided by the embodiments of the present disclosure is shown in the figure;

[0042] Figure 3A flow-density relationship diagram under three-phase alternating current theory provided by an embodiment of the present disclosure;

[0043] Figure 4 A flow-density relationship diagram under variable traffic capacity provided by an embodiment of the present disclosure;

[0044] Figure 5 A flow-density relationship diagram under variable speed provided by an embodiment of the present disclosure;

[0045] Figure 6 An algorithm diagram of a multi-objective optimization method of a variable speed control strategy of an expressway provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0046] The embodiments of the present disclosure will be described in detail below with reference to the drawings.

[0047] The embodiments of the present disclosure will be described in detail below with reference to the drawings.

[0048] It should be noted that various aspects of the embodiments described below are within the scope of the appended claims. It should be apparent that the aspects described herein can be embodied in a wide variety of forms and that any specific structure and / or function described herein is merely illustrative. Based on the teachings provided herein one skilled in the art should be able to contemplate these and similar aspects of the present disclosure. For example, acts recited as being performed in a certain order can be performed in a different order or concurrently. As will be apparent to those skilled in the art, these and other aspects of the present disclosure can be embodied in a wide variety of forms, some of which have been described but all of which will be apparent from this disclosure and can be carried out in various ways. Accordingly, the disclosure should not be limited to the specific examples described herein, but should be given the full scope of the appended claims.

[0049] It is also necessary to explain that the drawings provided in the following embodiments only illustrate the basic concept of the present disclosure in a schematic manner, and only the components related to the present disclosure are shown in the drawings, not the number, shape and size of the components when actually implemented. The actual implementation of each component may be a random change in number, shape and size, and the component layout pattern may also be more complex.

[0050] In addition, in the following description, specific details are provided in order to facilitate a thorough understanding of the examples. However, one skilled in the art will understand that the aspects described can be practiced without these specific details.

[0051] The embodiments of the present disclosure provide a high-speed highway variable speed limit control strategy multi-objective optimization method, which can be applied to the speed limit strategy optimization process of the traffic control scene.

[0052] Referring to Figure 1 , a flowchart of a high-speed highway variable speed limit control strategy multi-objective optimization method provided by the embodiments of the present disclosure is shown. As Figure 1 shown, the method mainly includes the following steps:

[0053] Step 1, based on the variable metacell, the fusion metastable state theory, the variable traffic capacity and the variable free flow speed, the CTM model is improved to obtain the corresponding high-speed highway simulation model of the target road section;

[0054] Further, the step 1 specifically includes:

[0055] Step 1.1, selecting the number of vehicles N i (t) as the characterization variable of the cell, and selecting the density k i (t) as the characterization variable of the cell parameter update change, thereby introducing the cell length variable l i , and the cell division condition needs to be met, that is, the cell length is not less than the distance d traveled by the vehicle at the free flow speed within a single simulation step. The updated cell density update formula is:

[0056]

[0057] Where, ΔT is the time period, l i is the cell length, λ i is the number of lanes of cell i, q i (t) is the flow of cell i in the tth time period, R i,in (t) is the inflow of the ramp in cell i in the tth time period, R i,out (t) is the outflow of the ramp in cell i in the tth time period.

[0058] Step 1.2, two critical densities are introduced as the boundaries of traffic state phase transition, denoted as forward phase transition density k a and reverse phase transition density k b , a state variable Z i (t) is introduced to redefine the criterion of traffic flow state:

[0059]

[0060]

[0061]

[0062] where ω is the traffic flow reverse wave speed, v f is the road free flow speed, k j is the road jam density, Q max represents the road maximum capacity;

[0063] Step 1.3, the traffic flow fundamental diagram in the CTM model is modified according to the statistical law of the target section;

[0064] Step 1.4, the traffic flow fundamental diagram in the CTM model is modified according to the critical density k c and the capacity Q vsl under speed limit control;

[0065] Step 1.5, the expressway simulation model is formed according to steps 1.1 to 1.4.

[0066] Further, the expressions of the critical density k c and the capacity Q vsl under speed limit control are

[0067]

[0068] Q vsl = k c v sl

[0069] where v sl is the speed limit value, k c is the road critical density, and Q vsl is the capacity under speed limit control.

[0070] The idea of variable speed limit control on expressway was first proposed by Smulders, and then the potential benefits of this idea spread rapidly in Europe and the United States. Combined with a large number of emerging technologies, the variable speed limit control technology has been applied to practical engineering practice in China since the 1990s. Domestic and foreign scholars have done a lot of theoretical research on variable speed limit control. Statistics show that most of the existing research focuses on the optimization of variable speed limit control under recurrent congestion, and there are few studies under traffic incident conditions. Most of the research methods combine the simulation model of expressway with the optimization model of variable speed limit control. Expressway is suitable for macroscopic traffic flow simulation model, among which the CTM (Cell Transmission Model, CTM) model and the METANET model are widely used. Scholars have summarized the macroscopic traffic flow simulation model and its improvement method, and believe that the CTM model has high solving efficiency and is easy to develop, and is more suitable for the study of variable speed limit control on expressway. The optimization control algorithm of variable speed limit is divided into single-objective optimization based on genetic algorithm or reinforcement learning and multi-objective optimization based on multi-objective genetic algorithm.

[0071] In implementation, the expressway section can be divided into four types according to road conditions, i.e. free flow section, congestion section, event section and traffic control section, and different sections have different traffic operation characteristics. A section may have several states described above, which need to be considered respectively when modeling the section simulation. The basic CTM model is difficult to be directly applied to the simulation of expressway traffic control under the influence of events, and the main reasons include the following aspects: first, the length of each simulation section in the model must be equal, but the actual road is not always an equal-length section due to the road conditions such as ramp, tunnel, etc., which leads to the decrease of the applicability of the basic CTM. Second, the basic model only describes two states of free flow and congestion flow, but according to the three-phase traffic flow theory, there is an unstable metastable state between free flow and congestion flow in actual traffic, which needs to be reflected in the model. Third, when the section is affected by traffic incidents, bad weather, road construction and other traffic events, the traffic capacity will decrease sharply, and the traffic flow fundamental diagram will change. The traffic flow fundamental diagram of the basic model is fixed. Fourth, after the section adopts traffic control, the traffic flow fundamental diagram will also change due to the influence of the outside world, and the most direct manifestation is the change of free flow speed and traffic capacity. Considering the above influences, the basic CTM model is improved in four parts to make it more suitable for simulation under the active control of expressway.

[0072] In the first part, the length of the cell is variable. In the basic cell transmission model, the length of the cell is required to be equal because the number of vehicles N i (t) is selected as the representation variable of the cell, in order to break the limitation that the cell must be equal in length, the density k i (t) is selected as the representation variable of the cell parameter update and change, thereby introducing the length variable li But also need to meet the cell division conditions: that is, the cell length is not less than the distance d that the vehicle travels at free flow speed within a single simulation step, cell division schematic diagram as shown in Figure 2 The revised cell density update formula is:

[0073]

[0074] The second part, fusion metastable state theory. The invention considers the metastable state between free flow and congestion flow in the congestion state, introduces two critical densities as the boundaries of traffic state phase transition in the traffic flow phase diagram of the basic model, respectively denoted as the forward phase transition density k a And the reverse phase transition density k b , the traffic flow phase diagram is shown in Figure 3 Introduce the state variable Z i (t), redefine the judgment criterion of vehicle flow state, that is:

[0075]

[0076]

[0077]

[0078] When the cell density is less than the forward phase transition density k a , its state is recorded as 0, indicating that the current cell is in free flow state; when the cell density is greater than the reverse phase transition density k b , its state is recorded as 1, indicating that the current cell is in congestion flow state; when the cell density is between the two, define its state to keep consistent with the previous time, indicating that the current cell is in metastable state.

[0079] The third part, variable traffic capacity. Traffic events will cause the road traffic capacity to drop sharply, and the traffic capacity will recover after taking traffic control measures, so the traffic flow phase diagram in the basic model needs to be modified. But in practical application, the degree of decline in traffic capacity often cannot be calculated mathematically, but is obtained according to statistical rules. In the invention, it is assumed that the reverse wave speed is constant, when a traffic event occurs, the road traffic capacity is reduced to Q' max , the forward phase transition density and the reverse phase transition density are reduced to k' a , k' b , and the maximum jam density is also reduced to k j ', the traffic flow phase diagram is shown in Figure 4 .

[0080] Part Four: Variable Free-Flow Speed. The most direct method of traffic control is flow control and speed limits, which alters the free-flow speed of vehicles. With variable speed limits, vehicles in free-flow mode cannot exceed the speed limit, while congested traffic flows remain unaffected. Changing speed indirectly alters road capacity, also achieved by modifying the basic traffic flow graph in the base model. The improved basic traffic flow graph is shown below. Figure 5 As shown. Where the critical density k c Traffic capacity under speed limit control Q vsl The calculation formula is as follows:

[0081]

[0082] Q vsl =k c v sl

[0083] In the formula: ω is the reverse wave velocity of the traffic flow, v f Let k be the free velocity of the road, ΔT be the time period, and k be the free velocity of the road. c k is the critical density of the road. j Where L is the road congestion density, and λ is the cell length. i R represents the number of lanes in cell i. i,in (t represents the inflow traffic volume of the entrance ramp in cell i during the t-th time period, R) i,out (t) represents the outflow of traffic from the exit ramp in cell i during the t-th time period.

[0084] The improvements in Part 1 and Part 2 combine to form a variable CTM model without external intervention, used to simulate traffic conditions in free-flow and congested road sections. The improvements in Part 3 and Part 4 combine to form a variable CTM model with external intervention, used to simulate traffic conditions in event-related and traffic-controlled road sections. Together, these four parts constitute a variable CTM model for proactive management of highways, which is the highway simulation model corresponding to the target road section.

[0085] Step 2: Based on the preset optimization objectives and constraints, solve the problem using the NSGA-II algorithm and the highway simulation model to generate an optimization strategy set.

[0086] Optionally, the optimization objectives include efficiency objectives and safety objectives.

[0087] Furthermore, the efficiency target is the total vehicle travel time, and the expression for the efficiency target is:

[0088]

[0089] Wherein, T is the number of simulation periods, N is the number of cells, k i (t) is the density of cell i in the tth simulation period, l i is the length of cell i, and Δt is the simulation period length.

[0090] Further, the safety target is the risk of total collision on the road in a preset period, and the expression of the safety target is

[0091]

[0092] Wherein, t' is the t'th 5min simulation period, and T' is the number of 5min periods divided by the simulation length.

[0093] Further, the constraint condition is that the speed limit difference in adjacent control periods on the same road section and the speed limit difference on adjacent road sections in the same control period does not exceed the threshold of speed per hour.

[0094] Further, the step 2 specifically comprises:

[0095] According to the expressions corresponding to the efficiency target and the safety target, the objective function is obtained, wherein the expression of the objective function is

[0096] According to the objective function and the constraint condition, a variable speed control strategy multi-objective optimization algorithm is formed;

[0097] The joint highway simulation model is used to solve the variable speed control strategy multi-objective optimization algorithm by using the NSGA-II algorithm to obtain the optimization strategy set.

[0098] In specific implementation, when performing variable speed control strategy multi-objective optimization, two parts can be included, which are as follows:

[0099] 2.1 Objective function

[0100] Traffic events on highways are prone to cause traffic congestion and form occasional bottlenecks. Due to its uncertainty, once a traffic accident occurs, the consequences are extremely serious and easy to cause secondary accidents. Therefore, when traffic control is performed, the road safety level is often considered to take corresponding strategies. However, due to the difficulty of accurately evaluating safety in macro simulation models, previous studies usually take efficiency as the main optimization target, and safety is considered less. The present application proposes a variable speed control strategy multi-objective optimization method considering safety and efficiency, which is as follows:

[0101] (1) Efficiency target

[0102] The present application uses the total travel time of vehicles as the efficiency target, which is calculated in the variable CTM model as follows:

[0103]

[0104] where T is the number of simulation periods, N is the number of cells, k i (t) is the density of cell i in the tth simulation period, l i is the length of cell i, and Δt is the length of simulation period.

[0105] (2) Safety objective

[0106] The present application adopts a variable CTM model for active control of expressway, and the core is the update of cell flow, density and speed. Therefore, the present application uses logistic regression to model the relationship between speed, density, flow and conflict probability within 5 minutes before the conflict in the macroscopic model. Based on the public traffic data set, the model is corrected, and it is found that only the speed has a significant impact on the conflict probability. The conflict risk of cell i in the t'+1 period is calculated as follows:

[0107]

[0108] The total collision risk of the road within the simulation time is calculated as follows:

[0109]

[0110] where t' is the t'th 5-minute simulation period, and T' is the number of 5-minute periods divided by the simulation time.

[0111] The objective function of the multi-objective optimization method of variable speed limit control strategy is as follows:

[0112]

[0113] 2.2 Constraint conditions

[0114] In order to facilitate the expressway traffic control, the variable speed limit control usually needs to set the speed limit value to an integer multiple of 10. At the same time, in order to ensure traffic safety, the speed limit value needs to be within a reasonable speed limit range, the minimum speed limit value is not lower than the minimum speed limit of the road, and the maximum speed limit value is not higher than the free flow speed on the road.

[0115] In addition, in order to make the driver adapt to the new speed limit value as soon as possible, the speed limit difference between adjacent control periods on the same section is not more than 20km / h, and the speed limit difference between adjacent sections in the same control period is also not more than 20km / h.

[0116]

[0117] In summary, the two optimization objectives of safety and efficiency, together with the related constraints of speed limit values, constitute the multi-objective optimization method of the variable speed limit control strategy. The application jointly improves the variable CTM model, uses the NSGA-II algorithm to solve the multi-objective optimization model of the variable speed limit control strategy, and generates an optimization strategy set. In actual application scenarios, the traffic management department can adjust the speed limit of the target road section according to the generated optimization strategy set. The specific process of the algorithm is as shown in Figure 6

[0118] The multi-objective optimization method of the intelligent expressway variable speed limit control strategy provided in this embodiment focuses on the optimization of the expressway variable speed limit control under the influence of traffic events by targeting the simulation model. Starting from the space-time characteristics of the expressway traffic flow under the influence of events, the variable CTM model for active control of the expressway is constructed. Specifically, it includes the variable CTM model without external intervention that integrates the metastable state theory and the variable cell length, and the variable CTM model with external intervention that considers the decline of the bottleneck area traffic capacity caused by the influence of traffic events and the variable speed under traffic control. Together, they constitute the variable CTM model for traffic control. The variable CTM model has a wide range of application scenarios and is expandable. It can simulate traffic situations caused by ramp-mainline merging, large-scale activities, traffic accidents, and adverse weather, and can be used for traffic situations with or without external intervention. For the optimization method, the traffic bottleneck under the influence of events has uncertainty, and the accidents caused by it are often serious, which may further cause secondary accidents. Therefore, more safety needs to be considered in actual applications, and the road traffic capacity also needs to be fully utilized. Compared with the traditional single-objective optimization method, the application considers traffic safety, constructs an accident risk calculation method based on the variable CTM model, and proposes a multi-objective optimization method of the occasional bottleneck variable speed limit control with safety and efficiency as the objectives, which provides more strategy options for decision-makers and improves the optimization accuracy, adaptability, safety, and efficiency.

[0119] The units described in the embodiments of the present disclosure can be implemented in the form of software or hardware.

[0120] It should be understood that various parts of the present disclosure can be implemented in hardware, software, firmware, or a combination thereof.

[0121] The above is only a specific implementation of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any changes or replacements within the technical range disclosed in the present disclosure can be easily thought of by those skilled in the art, which should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.​

Claims

1. A method for multi-objective optimization of intelligent highway variable speed limit control strategy, characterized in that, The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. Step 1.1, select the number of vehicles N i (t) as the characterization variable of the cell, select the density k i (t) as the characterization variable of the cell parameter update change, thereby introducing the cell length variable l i , and need to meet the cell division condition: that is, the cell length is not less than the distance d that the vehicle travels at the free flow speed within a single simulation step, and the revised cell density update formula is: where ΔT is the time period, l i is the cell length, λ i is the number of lanes in cell i, q i (t) is the flow in cell i in the tth time period, R i,in (t) is the inflow from the on-ramp in cell i in the tth time period, R i,out (t) is the outflow to the off-ramp in cell i in the tth time period. Step 1.2, Introduce two critical densities as the boundaries of traffic phase transition, denoted as forward phase transition density k a and reverse phase transition density k b , Introduce state variable Z i (t), redefine the criterion of traffic flow state: where ω is the traffic flow counter wave speed, v f is the road free flow speed, k j is the road jam density, Q max denotes the road maximum capacity; The application relates to a variable speed limit control strategy multi-objective optimization method and device. Step 1.4, according to the critical density k c and the capacity Q under speed limit control vsl The basic graph of traffic flow in the CTM model is modified; The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device.

2. The method of claim 1, wherein , the critical density k c and the capacity Q vsl under speed limit control is given by Q vsl = k c v sl where v sl is the speed limit value, k c is the road critical density, Q vsl is the capacity under speed limit control.

3. The method of claim 2, wherein The application relates to a variable speed limit control strategy multi-objective optimization method and device.

4. The method of claim 3, wherein The application relates to a variable speed limit control strategy multi-objective optimization method and device. where T is the number of simulation periods, N is the number of cells, k i (t) is the density of cell i in the tth simulation period, l i is the length of cell i, and Δt is the simulation period length.

5. The method of claim 4, wherein The application relates to a variable speed limit control strategy multi-objective optimization method and device. where t ' is the t ' th 5 min simulation period, T ' is the number of 5 min periods into which the simulation duration is divided.

6. The method of claim 5, wherein The application relates to a variable speed limit control strategy multi-objective optimization method and device.

7. The method of claim 6, wherein The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization method and device. The application relates to a variable speed limit control strategy multi-objective optimization

Images