CN116665444A - Expressway ramp control and variable speed limit cooperative control method considering accident risk - Google Patents
Expressway ramp control and variable speed limit cooperative control method considering accident risk Download PDFInfo
- Publication number
- CN116665444A CN116665444A CN202310656154.5A CN202310656154A CN116665444A CN 116665444 A CN116665444 A CN 116665444A CN 202310656154 A CN202310656154 A CN 202310656154A CN 116665444 A CN116665444 A CN 116665444A
- Authority
- CN
- China
- Prior art keywords
- control
- time
- segment
- ramp
- cooperative control
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 230000009471 action Effects 0.000 claims abstract description 35
- 238000005457 optimization Methods 0.000 claims abstract description 35
- 230000008569 process Effects 0.000 claims abstract description 30
- 239000013256 coordination polymer Substances 0.000 claims description 30
- 230000002265 prevention Effects 0.000 claims description 29
- 230000035484 reaction time Effects 0.000 claims description 15
- 230000008901 benefit Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000001133 acceleration Effects 0.000 claims description 2
- 230000000903 blocking effect Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 claims description 2
- 230000008676 import Effects 0.000 claims 1
- 230000006872 improvement Effects 0.000 abstract description 4
- 238000005070 sampling Methods 0.000 description 7
- 230000007246 mechanism Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 206010033799 Paralysis Diseases 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000035755 proliferation Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a expressway ramp control and variable speed limit cooperative control method, in particular to an expressway ramp control and variable speed limit cooperative control method considering accident risk. The invention aims to solve the problem that the existing cooperative control method unilaterally pursues the improvement of traffic efficiency and neglects the limitations of accident risks and influences. The process is as follows: 1. acquiring road conditions of a target expressway section; 2. detector layout is carried out on each segment and each ramp; 3. determining a cooperative control action area; 4. establishing a traffic flow model; 5. calibrating parameters of a traffic flow model; 6. acquiring real-time traffic data in each control period; 7. determining whether cooperative control is on; 8. calculating average collision probability of the cooperative control action area and judging a risk state; 9. obtaining optimal ramp control regulation rate and speed limit value; 10. the next control cycle is entered and a new round of optimization control is executed again from 6. The invention belongs to the field of expressway safety control.
Description
Technical Field
The invention belongs to the field of expressway safety control, and particularly relates to an expressway ramp control and variable speed limit cooperative control method considering accident risk.
Background
Expressways are main frameworks of urban road networks, and the running efficiency of the expressways is closely related to the overall traffic efficiency of cities. However, with the proliferation of urban traffic demand, the traffic congestion problem faced by expressways is becoming more severe, and the advantages of rapidity, efficiency and safety are gradually weakened. Therefore, there is a need to fully exploit the potential of existing traffic facilities by better utilizing existing expressway networks by improving traffic management levels. Ramp control and variable speed limit control are main control methods of a expressway, but the single control method has limited effect and is difficult to adapt to continuously increased traffic pressure. The ramp control and the variable speed limit cooperative control are hopeful to combine the control effects of the ramp control and the variable speed limit cooperative control, so that the current situation of traffic jam of the expressway is improved to a greater extent.
The existing cooperative control method is mostly based on foreign expressway control experience, is mainly established for relieving the bottleneck congestion of the expressway, pursues optimization of traffic efficiency unilaterally, and has insufficient attention to road traffic safety. The expressway has more ramp at the entrance and the exit, often forms a plurality of frequent congestion bottlenecks, and under the influence of the frequent congestion bottlenecks, the expressway has complex and changeable traffic environment and outstanding traffic safety problems. In addition, because the expressway has the characteristics of dense ramp distribution, high vehicle entrance and exit frequency and large traffic flow, once a traffic accident happens, a plurality of adjacent ramps are involved, the ramp queuing overflow further affects the connected common urban roads, and the traffic paralysis of the whole road network is caused in severe cases. Therefore, prevention and control of the risk of expressway accidents is a non-negligible point in expressway management.
In summary, aiming at the unilateral pursuit of the improvement of traffic efficiency by the existing cooperative control method and neglecting the limitations of accident risk and influence, it is necessary to establish a expressway ramp control and variable speed limit cooperative control method considering the accident risk.
Disclosure of Invention
The invention aims to solve the problem that the existing cooperative control method unilaterally pursues the improvement of traffic efficiency and neglects the accident risk and influence limitation, and provides a expressway ramp control and variable speed limit cooperative control method considering the accident risk.
The expressway ramp control and variable speed limit cooperative control method considering accident risk is characterized in that: the method comprises the following specific processes:
step 1, obtaining road conditions of a target expressway road section, wherein the road conditions comprise the total length L of the road section, the number m of lanes, and the positions, the number and the intervals of the ramp at the entrance and the exit along the line;
step 2, dividing the target road section into N sections based on the road condition of the target expressway section obtained in the step 1, wherein the numbers of the sections are sequentially 1,2, … and N, and arranging detectors on each section of the main line and each ramp;
step 3, determining a cooperative control action area based on the step 1 and the step 2;
step 4, establishing a traffic flow model adapting to cooperative control based on the step 1, the step 2 and the step 3;
step 5, acquiring data of the flow, the density and the speed of the expressway by using detectors arranged on each section, and calibrating parameters of a traffic flow model;
step 6, in each control period m, acquiring real-time traffic data of each detector on the expressway, including the flow q of each segment i (k) Velocity v i (k) Density ρ i (k) Queuing length w of ramp i (k)；
Wherein q i (k)、v i (k)、ρ i (k) Respectively representing the flow, speed and density of segment i at time k, w i (k) Representing the queuing length of the entrance ramp i at the current moment k;
step 7, calculating the average speed V of the traffic flow of the cooperative control action area determined in the step 3 avg Judging traffic flow congestion state, and determining whether cooperative control is started or not according to the traffic flow congestion state; the specific process is as follows:
calculating the average speed V of traffic flow in the cooperative control area using the detector data avg Judgment of V avg Whether or not the speed threshold V is exceeded threshold The method comprises the steps of carrying out a first treatment on the surface of the If yes, judging the free flow state, and not performing variable speed limiting control in the current period, and recovering the maximum regulation rate by ramp control; otherwise, judging that the traffic is in a congestion state, and entering a step 8;
step 8, calculating average collision probability CP of cooperative control action area avg Judging the risk state, and determining whether accident risk conventional prevention and control or key prevention and control are carried out;
the specific process is as follows:
predicting real-time collision probability of each segment by using collision probability model, and calculating average collision probability CP of cooperative control action area avg As a predictive value of accident risk;
judging average collision probability CP avg Whether or not a preset collision probability threshold value CP has been reached threshold The method comprises the steps of carrying out a first treatment on the surface of the If the risk is judged to be high, constructing a cooperative control optimization model by taking the safety as a unique control target, and performing accident risk important prevention and control; otherwise, judging that the risk is low, constructing a cooperative control optimization model by taking the efficiency and the safety together as control targets, and performing accident risk standardization prevention and control;
step 9, solving the constructed cooperative control optimization model to obtain the optimal ramp control adjustment rate r i (m) and speed limit value VSL i (m) transmitting to the corresponding control device for execution;
and step 10, entering the next control period m+1 after the control period m is finished, and executing a new round of optimization control again from the step 6.
The beneficial effects of the invention are as follows:
the invention aims to provide a expressway ramp control and variable speed limit cooperative control method considering accident risk, aiming at the limitation that the existing cooperative control technology unilaterally pursues traffic efficiency and does not fully consider the frequent accident of an expressway and involves larger traffic characteristics.
1. According to the invention, the real-time accident risk of the expressway is predicted by introducing the collision probability model, the control target of cooperative control is flexibly determined according to the accident risk of each control period, and the real-time monitoring and flexible prevention and control of the accident risk state can be realized.
2. The invention divides the traffic state according to the average speed and flexibly determines the opening and closing of the cooperative control, accords with the complex and changeable traffic characteristics of the urban expressway, and can better avoid the negative influence caused by meaningless cooperative control when the traffic state is good.
3. The invention fully considers the complex and changeable expressway traffic environment and the dynamic change of accident risk states, actively detects traffic states and predicts risk states by using common coil detectors, and reasonably balances safety and efficiency on a control target according to the traffic states and the risk states. By fully combining ramp control and variable speed limit control advantages, comprehensive improvement of the expressway traffic state can be effectively realized.
Drawings
FIG. 1 is an example of a segment division and detector layout according to the present invention;
FIG. 2 is a schematic representation of a highway cooperative control infrastructure in accordance with the present invention;
fig. 3 is a control flow chart of the expressway ramp control and variable speed limit cooperative control method taking accident risk into consideration.
Detailed Description
The first embodiment is as follows: the expressway ramp control and variable speed limit cooperative control method taking accident risk into consideration in the embodiment comprises the following specific processes:
step 1, obtaining road conditions of a target expressway road section, wherein the road conditions comprise the total length L of the road section, the number m of lanes, the positions, the number, the intervals and the like of the ramp at the entrance and exit along the line;
and determining a target expressway section to be controlled according to the traffic flow congestion condition without control, counting the total length L and the number m of lanes of the target section, and the positions, the number, the intervals and the like of the ramp at the entrance and the exit along the line, so as to prepare for the arrangement of detectors, the installation of control facilities and the establishment of a traffic flow model.
Step 2, based on the road conditions of the target expressway road section obtained in the step 1, the target road section is divided into N sections according to the principle that the roads are continuous and have the same attribute (the whole road section is divided into small sections in sequence, the attribute such as the number of lanes in each small section is unchanged during division) (the dispersion is that the road section with the whole length is divided into small sections), the numbers are 1,2, … and N in sequence, and the detector layout is carried out on each section of a main line (the expressway and the expressway are usually composed of a ramp and a main line) and each ramp, so as to obtain traffic flow data such as the flow q, the density ρ and the speed v of each section and each ramp in real time;
an example of road segment division and detector layout is shown in fig. 1;
step 3, determining a cooperative control action area based on the step 1 and the step 2;
step 4, based on the step 1, the step 2 and the step 3, establishing an expressway macroscopic traffic flow model adapting to cooperative control by considering respective action mechanisms of ramp control and variable speed limit and multi-congestion bottleneck characteristics of an expressway;
based on a classical METANET model, the adaptability is improved by considering the speed limit compliance level, the response time characteristic, the structural characteristics of the multi-congestion bottleneck of the expressway and the action mechanism of ramp control of a driver, and an expressway macroscopic traffic flow model which can be suitable for an expressway cooperative control scene is established.
Step 5, acquiring data of the flow, the density and the speed of the expressway by using detectors arranged on each section, and calibrating parameters of a macroscopic traffic flow model;
step 6, in each control period m, acquiring real-time traffic data of each detector on the expressway, including the flow q of each segment i (k) Velocity v i (k) Density ρ i (k) Queuing length w of ramp i (k) Etc.;
wherein q i (k)、v i (k)、ρ i (k) Respectively representing the flow, speed and density of segment i at time k, w i (k) Representing the queuing length of the entrance ramp i at the current time k, the real-time traffic data will be used for traffic state determination and as an initial state of the traffic flow model.
Step 7, calculating the average speed V of the traffic flow of the cooperative control action area determined in the step 3 avg Judging the traffic flow congestion state, and determining whether the cooperative control is started or not according to the traffic flow congestion state; the specific process is as follows:
calculating the average speed V of traffic flow in the cooperative control area using the detector data avg Judgment of V avg Whether or not the speed threshold V is exceeded threshold The method comprises the steps of carrying out a first treatment on the surface of the If yes, judging the free flow state, and not performing variable speed limiting control in the current period, and recovering the maximum regulation rate by ramp control; otherwise, judging that the traffic is in a congestion state, and entering a step 8;
step 8, calculating average collision probability CP of cooperative control action area avg Judging the risk state, and determining whether accident risk conventional prevention and control or key prevention and control are carried out;
the specific process is as follows:
based on the traffic flow parameters detected in real time, predicting the real-time collision probability of each segment by using a collision probability model, and calculating the average collision probability CP of the cooperative control action area avg As a predictive value of accident risk;
thereafter, the average collision probability CP is determined avg Whether or not a preset collision probability threshold value CP has been reached threshold The method comprises the steps of carrying out a first treatment on the surface of the If the risk is judged to be high, constructing a cooperative control optimization model by taking the safety as a unique control target, and performing accident risk important prevention and control; otherwise, judging that the risk is low, constructing a cooperative control optimization model by taking the efficiency and the safety together as control targets, and performing accident risk standardization prevention and control;
note that whether accident risk emphasis prevention or normalization prevention is based on a Model Predictive Control (MPC) framework, i.e., predicting future traffic flow states under each control scheme using a traffic flow model, and selecting a control scheme that achieves an optimal control objective as an optimal solution.
Step 9, solving the constructed cooperative control optimization model to obtain the optimal ramp control adjustment rate r i (m) and speed limit value VSL i (m) transmitting to corresponding control devices (ramp signal lamps, variable information boards) for execution;
wherein, because of the specificity of the model, the optimization model is simpler to solve. For a given speed limiting scheme, the optimal ramp adjustment rate is determined by itself in the iterative prediction process of the traffic flow model. Thus, the decision variables of the optimization model are essentially the rate limiting values for each control cycle for each segment in the prediction domain. The speed limit value is a series of discrete values and has strict constraints, so that the number of feasible solutions of the optimization model is limited, and the solution can be achieved by a traversal enumeration method.
And step 10, entering the next control period m+1 after the control period m is finished, and executing a new round of optimization control again from the step 6.
The second embodiment is as follows: this embodiment differs from the specific embodiment in that each segment in step 2 includes at most one entrance ramp and one exit ramp;
the segment division should not be too long or too short, and is usually between 300m and 1000 m;
the main line needs to respectively arrange a group of detectors on each section and each lane at the beginning of the road section, as shown by LD 0-LD 8 in figure 1;
the entrance ramp is provided with two groups of detectors, namely a check-in detector and a queuing detector, so as to obtain the actual afflux quantity and the queuing length of the ramp respectively;
the exit ramp is only provided with a group of detectors for acquiring the ramp running-out amount.
Other steps and parameters are the same as in the first embodiment.
And a third specific embodiment: the difference between this embodiment and the first or second embodiment is that, in the step 3, the cooperative control action area is determined based on the step 1 and the step 2; the specific process is as follows:
according to the actual traffic flow running condition, a variable speed limit information board (a display board capable of displaying speed limit information) is arranged on a main line to form a plurality of variable speed limit sections;
setting ramp signal lamps on an entrance ramp (which is selected to be easy to cause main line congestion according to experience of traffic managers) which is easy to cause traffic bottleneck to form a plurality of ramp control nodes;
the road area acted by the speed limiting section and the ramp control node is the cooperative control action area.
Other steps and parameters are the same as in the first or second embodiment.
The specific embodiment IV is as follows: the difference between the embodiment and one to three embodiments is that, in the step 4, based on the step 1, the step 2 and the step 3, the respective action mechanisms of ramp control and variable speed limit and the multi-congestion bottleneck characteristics of the expressway are considered, and an expressway macroscopic traffic flow model adapting to cooperative control is established;
based on a classical METANET model, the adaptability is improved by considering the speed limit compliance level, the response time characteristic, the structural characteristics of the multi-congestion bottleneck of the expressway and the action mechanism of ramp control of a driver, and an expressway macroscopic traffic flow model which can be suitable for an expressway cooperative control scene is established.
The specific process is as follows:
1. the classical meta model is a recursive relation of the flow, speed and density of each segment of the road over time, as follows:
wherein q i (k)、v i (k)、ρ i (k) Respectively representing the flow, speed and density of the segment i at time k; w (w) i (k) Represents the queuing length of the entrance ramp i at time k, h i (k) The entrance ramp inflow of the section i of time k is represented, and the unit is veh/h; s is(s) i (k) The exit ramp flow of the time k segment i is represented, and the unit is veh/h; lambda (lambda) i The number of lanes for segment i; v f The unit is km/h for free flow speed; ρ crit Is critical density, singlyBits veh/(km.ln); μ, η, κ, τ are model parameters; t is the time step; l (L) i Is the length of segment i; v [ rho ] i (k)]Is density ρ i (k) Corresponding desired speed.
2. The METANET model based on 1 is improved from the aspects of the speed limiting compliance level of a driver, the reaction time characteristic, the structural characteristics of a multi-congestion bottleneck of a expressway, the ramp control action mechanism and the like, and a macroscopic traffic flow model (a common composition model of formulas 3-11) which is suitable for cooperative control and is built in a city, is provided with unidirectional double lanes or more and is provided with matched traffic safety and management facilities, wherein the expressway is characterized in that the central separation, the total control access and the control access interval and the pattern are built in the city:
(1) Dynamic density equation:
w i (k)＝w i (k-1)+T·[d i (k-1)-h i (k-1)] (5)
r i (k)＝r i (k-1)+K R [O crit,i -O i (k-1)] (6)
wherein d i (k) And w i (k) Respectively representing ramp arrival flow and ramp queuing vehicle number of the entrance ramp corresponding to the section i at the time k;
Q i maximum traffic capacity for the entrance ramp comprised by segment i;
ρ jam,i and ρ crit,i The blocking density and the critical density of the section i where the ramp is located are respectively;
equation (6) is an alintea ramp control algorithm. Wherein r is i (k) The ramp adjustment rate of the section i at the time k is given by the unit of veh/h;
O crit,i critical occupancy for segment i;
O i (k-1) is the actual occupancy of segment i at time k-1;
K R to adjust parameters;
(2) Dynamic velocity equation:
wherein τ i (k) A reaction time parameter representing the time k of segment i;
τ dec indicating the reaction time in the decelerating state;
τ uni the reaction time in the constant speed state is represented;
τ acc indicating the reaction time in the accelerated state;
(3) The desired velocity equation:
V[ρ i (k)]＝min{v f ·exp{-(1/μ)[ρ i (k)/ρ crit ] μ },(1+α i (k))·u i vsl (k)} (9)
wherein alpha is i (k) The real-time overspeed amplitude of the segment i at the time k is represented to reflect the violation condition of a driver on a given speed limit, and is calculated by adopting a simple moving average method;
representing the displayed speed limit value of segment i at time k-t;
T α the number of time periods being a moving average (simple moving average is to use the past few sampling periodsAs an estimate of the future, i use the average of the speeds of the past 5 sample periods to calculate the future speed, then the "number of time periods of moving average" is 5);
(4) Road segment flow equation:
q i (k)＝λ i ρ i (k)v i (k) (11)。
other steps and parameters are the same as in one to three embodiments.
Fifth embodiment: the difference between the embodiment and the one to four embodiments is that in the step 5, the detectors arranged on each segment are utilized to obtain the data of the expressway flow, the density and the speed, and the parameter calibration of the macroscopic traffic flow model is performed; the specific process is as follows:
the macroscopic traffic flow model parameters comprise traffic flow basic parameters and macroscopic traffic flow model global parameters;
(1) Obtaining a flow-density scatter plot using a detector;
obtaining traffic flow basic parameters based on the flow-density scatter diagram, wherein the traffic flow basic parameters comprise free flow speed v f Critical density ρ crit Density ρ of blockage jam Etc.;
(2) Solving a global parameter calibration model with the minimum prediction error of the flow and the speed as a target by utilizing an optimization algorithm to obtain global parameters of a macroscopic traffic flow model;
the specific process is as follows:
the objective function of the global parameter calibration model with the minimum prediction error of the flow and the speed as the objective is:
the constraint conditions of the global parameter calibration model with the minimum prediction error of the flow and the speed as the target are as follows:
σ min ≤σ≤σ max
σ min ＝[0.001,0.001,0.001,10,10]
σ max ＝[0.05,0.05,0.05,60,60]
τ acc -τ dec ＞0
where σ is the global parameter vector of the macroscopic traffic flow model, i.e. [ tau ] dec ,τ uni ,τ acc ,η,κ]，τ dec Indicating the reaction time in the retarded state τ uni Represents the reaction time in the constant speed state, τ acc Represents the reaction time in the acceleration state, eta is a model parameter, kappa is a model parameter, and sigma min Is the global parameter vector minimum value, sigma of the traffic flow model max The global parameter vector maximum value is the traffic flow model;
n is the total number of discrete segments of the road; k is the maximum time step number of time discrete; v i,real (k) The actual average speed of segment i at time k; v i,predict (k|σ) is the macroscopic traffic flow model predicted average speed for segment i under the global parameter vector σ at time k; q i,real (k) The actual flow at time k for segment i; q i,predict (k|σ) is the predicted flow of the macroscopic traffic flow model for segment i under the global parameter vector σ at time k;
and solving the objective function by utilizing intelligent optimization algorithms such as a genetic algorithm and the like to obtain the optimal global parameters of the macroscopic traffic flow model.
Establishing a Model Predictive Control (MPC) -based expressway cooperative control basic framework, and designing basic control parameters including a sampling period T and a predictive time domain N p Control time domain N c Etc.;
the method comprises the following specific steps:
establishing a expressway cooperative control basic framework based on Model Predictive Control (MPC); the specific process is as follows:
the control object of the present invention is a highway system (the whole highway can be regarded as a traffic system), and the cooperative control basic framework shown in fig. 2 is established according to the basic principle and thought of MPC. The control principle is as follows:
(1) When each control period starts, the expressway system acquires the current traffic state including flow, speed, density and the like;
(2) And then, inputting the acquired traffic flow state information into a traffic flow model as an initial condition for predicting future traffic flow states of the expressway system. The process is executed in each rolling optimization, so that feedback correction of the model is realized;
(3) Then, based on a traffic flow model and a self-defined optimization target, carrying out multi-step prediction and calculating an objective function under different control schemes (combination of ramp control signals and variable speed limit values, namely a control scheme), and obtaining an optimal control scheme (ramp adjustment rate and speed limit values) by solving an optimization problem in real time;
(4) Finally, feeding back the optimal control scheme to the METANET model, and taking the optimal control scheme and the traffic flow state as initial conditions of the next control period; and simultaneously, the data is also sent to the expressway system for actual execution.
Designing basic control parameters; the specific process is as follows:
(1) Sampling period T: the time interval for the control system to acquire the state of the controlled object is shown, and in order to ensure the prediction meaning of the prediction model, the sampling period should ensure that when the vehicle runs at the fastest speed, enough time is available for sampling, namely, the following conditions are satisfied:
T≤min(L i /v f ) (1)
(2) Predicting time domain N p : the time length of the prediction model for predicting the controlled object is not too short or too long, and generally, the integer multiple of the sampling period is taken;
(3) Control time domain N c : the time length of the control sequence returned to the system execution by solving the optimal control scheme refers to predicting the future traffic state, and the time length is also an integer multiple of the sampling period. N (N) c The period of each control signal is combined to determine, and at least one ramp control period and variable speed limit period are ensured to be executed;
the cooperative control method provided by the invention is based on an MPC control framework, and under the framework, important control parameters of cooperative control are designed. And then entering an actual control stage, and carrying out cooperative control on the expressway according to the steps 6 to 10, wherein the complete control flow is shown in figure 3.
Other steps and parameters are the same as in one to four embodiments.
Specific embodiment six: the present embodiment differs from one to five of the embodiments in that the average collision probability CP of the cooperative control action region is calculated in the step 8 avg Judging the risk state, and determining whether accident risk conventional prevention and control or key prevention and control are carried out; the specific process is as follows:
step 8.1, calculating real-time collision probability of each segment and average collision probability CP of cooperative control action area avg ；
Step 8.2, judging the current average collision probability CP avg Whether or not the collision probability threshold value CP is exceeded threshold The method comprises the steps of carrying out a first treatment on the surface of the If yes, judging that the risk is high, and executing the step 8.3; if not, judging that the risk is low, and executing the step 8.4;
step 8.3, constructing a cooperative control optimization model (formula 16) by taking safety as a unique control target, and performing accident risk important prevention and control;
and 8.4, constructing a cooperative control optimization model (formula 27) by taking the efficiency and the safety as control targets together, and performing accident risk standardization prevention and control.
Other steps and parameters are the same as in one of the first to fifth embodiments.
Seventh embodiment: the difference between the present embodiment and one to six embodiments is that the real-time collision probability of each segment and the average collision probability CP of the cooperative control area are calculated in the step 8.1 avg The method comprises the steps of carrying out a first treatment on the surface of the The specific process is as follows:
the real-time collision probability of each segment can be calculated according to the flow, speed and occupancy rate data acquired by the detector, and the calculation formula is as follows:
wherein P is collision (SV, AO, SS) represents the probability of a real-time collision for a given traffic feature SV, AO, SS. SV is the flow standard within the time 5-10min before the target momentThe difference, AO, is the average occupancy in the time 0-5min before the target time, and SS is the standard deviation of speed in the time 5-10min before the target time. b 0 ，b 1 ，b 2 ，b 3 The values of the model parameters are-3.694, -1.207,3.149 and 4.028 respectively;
the real-time collision probability CP of each segment i of the cooperative control action area is obtained by utilizing the formula i After that, average collision probability CP avg It can be calculated as:
wherein M is the total number of segments contained in the cooperative control action region, and C is the number set of segments contained in the cooperative control action region.
Other steps and parameters are the same as in one of the first to sixth embodiments.
Eighth embodiment: the difference between the embodiment and one of the first to seventh embodiments is that in the step 8.3, a cooperative control optimization model is built by taking the security as the only control target, so as to perform accident risk important prevention and control; the specific process is as follows:
calculating the sum of the real-time collision probabilities of all the sections of all the time steps in the prediction time domain, and taking the sum as a quantized value of the total accident risk level of the future time step expressway; in particular, the method comprises the steps of,
for any segment i, its real-time collision probability CP at time k i (k) It can be calculated as:
wherein SV is i (k)、AO i (k)、SS i (k) The standard deviation of the flow of segment i in the 5-10min before time k, the average occupancy in the first 0-5min and the standard deviation of the velocity in the first 5-10min are indicated, respectively.
The flow, occupancy and speed required during calculation are predicted values of a METANET model, and if the related time range has no predicted result, the predicted values are supplemented by using corresponding measured values of the detector.
Thus, the sum of collision probabilities TCP for each segment at each time in the prediction domain can be calculated as:
wherein N is p N is the total number of discrete segments of the road for predicting the time domain;
at this time, the expressway is in a high-risk state, so that the lowest sum of collision probabilities is taken as a control target, and the objective function of the constructed cooperative control optimization model is as follows:
J＝minTCP (16)
wherein J is an objective function;
the constraint conditions are as follows:
(1) In the same control period, the speed limiting value of any segment in each time step is unchanged;
wherein VSL i (m) represents the speed limit value, T, of segment i in control period m c Indicating the length of the control period,a speed limit value representing segment i at time k;
(2) The variable speed limit value of any control period does not exceed the highest speed limit standard and is not lower than the lowest speed limit standard;
V min ≤VSL i (m)≤V max (18)
wherein V is min Is the minimum speed limit standard, V max Is the highest speed limit standard;
(3) In order to ensure stable operation of the main line traffic flow, the change of the speed limit value during adjacent control period is not excessive, and the difference of the variable speed limit values of adjacent sections in the same control period is not excessive;
|VSL i (m+1)-VSL i (m)|≤10km/h (19)
|VSL i+1 (m)-VSL i (m)|≤20km/h (20)
wherein VSL i (m+1) represents the speed limit value of segment i in control period m+1, VSL i (m) represents the speed limit value of segment i in control period m, VSL i+1 (m) represents a speed limit value of segment i+1 in control period m;
(4) Considering the operability of a driver on the driving speed, setting the issued variable speed limit value to be a multiple of 10km/h, namely selecting the variable speed limit value from discrete values;
VSL i (m)∈{10km/h,20km/h,……,70km/h,80km/h} (21)
(5) According to the basic traffic flow theory, the flow of each section does not exceed the traffic capacity of a main line;
λ i ρ i (k)v i (k)≤λ i Q max (22)
wherein Q is max Representing main line traffic capacity;
(6) In order to ensure the afflux stability of the ramp traffic flow, the adjustment rate of each ramp should not have too great fluctuation in time;
other steps and parameters are the same as those of one of the first to seventh embodiments.
Detailed description nine: the difference between the embodiment and one to eighth embodiments is that in the step 8.4, efficiency and safety are used as control targets together to construct a cooperative control optimization model to perform accident risk standardization prevention and control; the specific process is as follows:
if the current average collision probability CP avg Does not exceed the collision probability threshold value CP threshold And constructing a cooperative control optimization model by taking the efficiency and the safety as control targets together, and executing accident risk routine prevention and control.
At this time, the expressway is in a low-risk state, and the cooperative control should consider both safety and efficiency, so as to improve the traffic efficiency of the expressway and reduce the collision risk as a control target.
In the aspect of traffic efficiency, taking total travel time TTT and total travel mileage TTD in a prediction time domain as benefit indexes;
the calculation is as follows:
wherein ρ is i (k+j) represents the density, w, of the segment i at the time (k+j) i (k+j) represents the queuing length of the entrance ramp i at the time (k+j), v i (k+j) represents the speed of segment i at time (k+j);
in terms of safety, with the collision probability sum TCP as the benefit index, as shown in step 9.3, it is calculated as:
the goal of the cooperative control is to minimize the total travel time TTT, maximize the total travel distance TTD, and minimize the collision probability sum TCP, so the linear weighted sum of TTT, TTD, and TCP is taken as the objective function, namely:
J＝min(α TTT TTT-α TTD TTD+α TCP TCP) (27)
wherein alpha is TTT ，α TTD And alpha TCP The weight coefficients of TTT, TTD and TCP are respectively;
the constraint conditions of the model are consistent with those in the step 8.3, and are not repeated.
Other steps and parameters are the same as in one to eight of the embodiments.
The present invention is capable of other and further embodiments and its several details are capable of modification and variation in light of the present invention, as will be apparent to those skilled in the art, without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (9)
1. The expressway ramp control and variable speed limit cooperative control method considering accident risk is characterized in that: the method comprises the following specific processes:
step 1, obtaining road conditions of a target expressway road section, wherein the road conditions comprise the total length L of the road section, the number m of lanes, and the positions, the number and the intervals of the ramp at the entrance and the exit along the line;
step 2, dividing the target road section into N sections based on the road condition of the target expressway section obtained in the step 1, wherein the numbers of the sections are sequentially 1,2, … and N, and arranging detectors on each section of the main line and each ramp;
step 3, determining a cooperative control action area based on the step 1 and the step 2;
step 4, establishing a traffic flow model adapting to cooperative control based on the step 1, the step 2 and the step 3;
step 5, acquiring data of the flow, the density and the speed of the expressway by using detectors arranged on each section, and calibrating parameters of a traffic flow model;
step 6, in each control period m, acquiring real-time traffic data of each detector on the expressway, including the flow q of each segment i (k) Velocity v i (k) Density ρ i (k) Queuing length w of ramp i (k)；
Wherein q i (k)、v i (k)、ρ i (k) Respectively representing the flow, speed and density of segment i at time k, w i (k) Representing the queuing length of the entrance ramp i at the current moment k;
step 7, calculating the average speed V of the traffic flow of the cooperative control action area determined in the step 3 avg Judging traffic flow congestion state, and determining whether cooperative control is started or not according to the traffic flow congestion state; the specific process is as follows:
calculating a cooperative control action region using detector dataIs the average speed V of the traffic flow avg Judgment of V avg Whether or not the speed threshold V is exceeded threshold The method comprises the steps of carrying out a first treatment on the surface of the If yes, judging the free flow state, and not performing variable speed limiting control in the current period, and recovering the maximum regulation rate by ramp control; otherwise, judging that the traffic is in a congestion state, and entering a step 8;
step 8, calculating average collision probability CP of cooperative control action area avg Judging the risk state, and determining whether accident risk conventional prevention and control or key prevention and control are carried out;
the specific process is as follows:
predicting real-time collision probability of each segment by using collision probability model, and calculating average collision probability CP of cooperative control action area avg As a predictive value of accident risk;
judging average collision probability CP avg Whether or not a preset collision probability threshold value CP has been reached threshold The method comprises the steps of carrying out a first treatment on the surface of the If the risk is judged to be high, constructing a cooperative control optimization model by taking the safety as a unique control target, and performing accident risk important prevention and control; otherwise, judging that the risk is low, constructing a cooperative control optimization model by taking the efficiency and the safety together as control targets, and performing accident risk standardization prevention and control;
step 9, solving the constructed cooperative control optimization model to obtain the optimal ramp control adjustment rate r i (m) and speed limit value VSL i (m) transmitting to the corresponding control device for execution;
and step 10, entering the next control period m+1 after the control period m is finished, and executing a new round of optimization control again from the step 6.
2. The expressway ramp control and variable speed limit cooperative control method considering accident risk according to claim 1, wherein: each segment in the step 2 comprises at most one entrance ramp and one exit ramp;
a group of detectors are respectively arranged on each section and each lane at the beginning end of the road section;
the entrance ramp is provided with two groups of detectors, namely a check-in detector and a queuing detector, so as to respectively acquire the actual import quantity and the queuing length of the ramp;
and a group of detectors are arranged on the exit ramp to obtain the ramp running-out quantity.
3. The expressway ramp control and variable speed limit cooperative control method considering accident risk according to claim 2, wherein: in the step 3, a cooperative control action area is determined based on the step 1 and the step 2; the specific process is as follows:
a variable speed limit information board is arranged on the main line to form a plurality of variable speed limit sections;
arranging ramp signal lamps on the entrance ramp to form a plurality of ramp control nodes;
the road area acted by the speed limiting section and the ramp control node is the cooperative control action area.
4. The expressway ramp control and variable speed limit cooperative control method considering accident risk according to claim 3, wherein: in the step 4, based on the step 1, the step 2 and the step 3, a traffic flow model adapting to cooperative control is established; the specific process is as follows:
the traffic flow model adapted for cooperative control is as follows:
(1) Dynamic density equation:
w i (k)＝w i (k-1)+T·[d i (k-1)-h i (k-1)] (5)
r i (k)＝r i (k-1)+K R [O crit,i -O i (k-1)] (6)
wherein q is i (k)、ρ i (k) Respectively represent the time of the segment iFlow rate and density of k; h is a i (k) The entrance ramp inflow of the section i of time k is represented, and the unit is veh/h; s is(s) i (k) The exit ramp flow of the time k segment i is represented, and the unit is veh/h; lambda (lambda) i The number of lanes for segment i; l (L) i Is the length of segment i; t is the time step; ρ crit The critical density is expressed as veh/(km.ln);
d i (k) And w i (k) Respectively representing ramp arrival flow and ramp queuing vehicle number of the entrance ramp corresponding to the section i at the time k;
Q i maximum traffic capacity for the entrance ramp comprised by segment i;
ρ jam,i and ρ crit,i The blocking density and the critical density of the section i where the ramp is located are respectively;
r i (k) The ramp adjustment rate of the section i at the time k is given by the unit of veh/h;
O crit,i critical occupancy for segment i;
O i (k-1) is the actual occupancy of segment i at time k-1;
K R to adjust parameters;
(2) Dynamic velocity equation:
wherein τ i (k) A reaction time parameter representing the time k of segment i;
τdec represents the reaction time in the decelerating state;
τ uni the reaction time in the constant speed state is represented;
τ acc indicating the reaction time in the accelerated state;
v i (k) Representing the speed of segment i at time k;
V[ρ i (k)]is density ρ i (k) A corresponding desired speed; η and κ are model parameters;
(3) The desired velocity equation:
V[ρ i (k)]＝min{v f ·exp{-(1/μ)[ρ i (k)/ρ crit ] μ },(1+α i (k))·u i vsl (k)} (9)
wherein alpha is i (k) Representing the real-time overspeed amplitude of segment i at time k;
representing the displayed speed limit value of segment i at time k-t;
T α the number of time periods being a moving average;
v f the unit is km/h for free flow speed; μ is a model parameter;
(4) Road segment flow equation:
q i (k)＝λ i ρ i (k)v i (k) (11)。
5. the expressway ramp control and variable speed limit cooperative control method considering accident risk according to claim 4, wherein: in the step 5, the detectors arranged on each segment are utilized to acquire the data of the expressway flow, density and speed, and the parameter calibration of the traffic flow model is carried out; the specific process is as follows:
the traffic flow model parameters comprise traffic flow basic parameters and traffic flow model global parameters;
(1) Obtaining a flow-density scatter plot using a detector;
obtaining traffic flow basic parameters based on the flow-density scatter diagram, wherein the traffic flow basic parameters comprise free flow speed v f Critical density ρ crit Density ρ of blockage jam ；
(2) Solving a global parameter calibration model with the minimum prediction error of the flow and the speed as a target by utilizing an optimization algorithm to obtain global parameters of the traffic flow model;
the specific process is as follows:
the objective function of the global parameter calibration model with the minimum prediction error of the flow and the speed as the objective is:
the constraint conditions of the global parameter calibration model with the minimum prediction error of the flow and the speed as the target are as follows:
σ min ≤σ≤σ max
σ min ＝[0.001,0.001,0.001,10,10]
σ max ＝[0.05,0.05,0.05,60,60]
τ acc -τ dec ＞0
where σ is the global parameter vector of the traffic flow model, i.e. [ tau ] dec ,τ uni ,τ acc ,η,κ]；
τ dec Indicating the reaction time in the retarded state τ uni Represents the reaction time in the constant speed state, τ acc Represents the reaction time in the acceleration state, eta is a model parameter, kappa is a model parameter, and sigma min Is the global parameter vector minimum value, sigma of the traffic flow model max The global parameter vector maximum value is the traffic flow model;
n is the total number of discrete segments of the road; k is the maximum time step number of time discrete; v i,real (k) The actual average speed of segment i at time k; v i,predict (k|σ) is the traffic flow model predicted average speed for segment i under the global parameter vector σ at time k; q i,real (k) The actual flow at time k for segment i; q i,predict (k|σ) is the predicted flow of the traffic flow model for segment i under the global parameter vector σ at time k;
and solving the objective function by using an optimization algorithm to obtain the optimal global parameter of the traffic flow model.
6. The expressway ramp control and variable speed limit cooperative control method considering accident risk according to claim 5, wherein: the average collision probability CP of the cooperative control action area is calculated in the step 8 avg Judging the risk state, and determining whether accident risk conventional prevention and control or key prevention and control are carried out; the specific process is as follows:
step 8.1, calculating real-time collision probability of each segment and average collision probability CP of cooperative control action area avg ；
Step 8.2, judging the current average collision probability CP avg Whether or not the collision probability threshold value CP is exceeded threshold The method comprises the steps of carrying out a first treatment on the surface of the If yes, judging that the risk is high, and executing the step 8.3; if not, judging that the risk is low, and executing the step 8.4;
step 8.3, constructing a cooperative control optimization model by taking safety as a unique control target, and performing accident risk important prevention and control;
and 8.4, constructing a cooperative control optimization model by taking the efficiency and the safety together as control targets, and performing accident risk routine prevention and control.
7. The expressway ramp control and variable speed limit cooperative control method considering accident risk according to claim 6, wherein: calculating real-time collision probability of each segment and average collision probability CP of cooperative control action area in the step 8.1 avg The method comprises the steps of carrying out a first treatment on the surface of the The specific process is as follows:
the real-time collision probability of each segment can be calculated according to the flow, speed and occupancy rate data acquired by the detector, and the calculation formula is as follows:
wherein P is collision (SV, AO, SS) represents the probability of a real-time collision for a given traffic feature SV, AO, SS. SV is before the target timeThe flow standard deviation in the time of 5-10min, AO is the average occupancy in the time of 0-5min before the target time, SS is the speed standard deviation in the time of 5-10min before the target time; b 0 ，b 1 ，b 2 ，b 3 Is a model parameter;
the real-time collision probability CP of each segment i of the cooperative control action area is obtained by utilizing the formula i After that, average collision probability CP avg It can be calculated as:
wherein M is the total number of segments contained in the cooperative control action region, and C is the number set of segments contained in the cooperative control action region.
8. The expressway ramp control and variable speed limit cooperative control method considering accident risk according to claim 7, wherein: in the step 8.3, a cooperative control optimization model is built by taking safety as a unique control target, and accident risk important prevention and control are carried out; the specific process is as follows:
real-time collision probability CP at time k for arbitrary segment i i (k) The calculation is as follows:
wherein SV is i (k)、AO i (k)、SS i (k) Respectively representing the standard deviation of the flow of the segment i in 5-10min before the time k, the average occupancy in the first 0-5min and the speed standard deviation in the first 5-10 min;
thus, the sum of collision probabilities TCP for each segment at each time in the prediction domain can be calculated as:
wherein N is p N is the total number of discrete segments of the road for predicting the time domain;
at this time, the expressway is in a high-risk state, so that the lowest sum of collision probabilities is taken as a control target, and the objective function of the constructed cooperative control optimization model is as follows:
J＝minTCP (16)
wherein J is an objective function;
the constraint conditions are as follows:
(1) In the same control period, the speed limiting value of any segment in each time step is unchanged;
wherein VSL i (m) represents the speed limit value, T, of segment i in control period m c Indicating the length of the control period,a speed limit value representing segment i at time k;
(2) The variable speed limit value of any control period does not exceed the highest speed limit standard and is not lower than the lowest speed limit standard;
V min ≤VSL i (m)≤V max (18)
wherein V is min Is the minimum speed limit standard, V max Is the highest speed limit standard;
(3) To ensure stable operation of the main traffic flow;
|VSL i (m+1)-VSL i (m)|≤10km/h (19)
|VSL i+1 (m)-VSL i (m)|≤20km/h (20)
wherein VSL i (m+1) represents the speed limit value of segment i in control period m+1, VSL i (m) represents the speed limit value of segment i in control period m, VSL i+1 (m) represents a speed limit value of segment i+1 in control period m;
(4) The variable speed limit value is selected from discrete values;
VSL i (m)∈{10km/h,20km/h,……,70km/h,80km/h} (21)
(5) The flow of each section does not exceed the traffic capacity of the main line;
λ i ρ i (k)v i (k)≤λ i Q max (22)
wherein Q is max Representing main line traffic capacity;
(6) To ensure the stability of the ramp traffic flow;
9. the expressway ramp control and variable speed limit cooperative control method considering accident risk according to claim 8, wherein: in the step 8.4, efficiency and safety are used as control targets together to construct a cooperative control optimization model, and accident risk routine prevention and control are carried out; the specific process is as follows:
in the aspect of traffic efficiency, taking total travel time TTT and total travel mileage TTD in a prediction time domain as benefit indexes;
the calculation is as follows:
wherein ρ is i (k+j) represents the density of the segment i at the time (k+j);
w i (k+j) represents the queuing length of the entrance ramp i at the time (k+j);
v i (k+j) represents the speed of segment i at time (k+j);
in terms of safety, the collision probability sum TCP is used as a benefit index, and is calculated as follows:
the goal of the cooperative control is to minimize the total travel time TTT, maximize the total travel distance TTD, and minimize the collision probability sum TCP, so the linear weighted sum of TTT, TTD, and TCP is taken as the objective function, namely:
J＝min(α TTT TTT-α TTD TTD+α TCP TCP) (27)
wherein alpha is TTT ，α TTD And alpha TCP The weight coefficients of TTT, TTD and TCP are respectively;
the constraints are identical to those in step 8.3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310656154.5A CN116665444A (en) | 2023-06-05 | 2023-06-05 | Expressway ramp control and variable speed limit cooperative control method considering accident risk |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310656154.5A CN116665444A (en) | 2023-06-05 | 2023-06-05 | Expressway ramp control and variable speed limit cooperative control method considering accident risk |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116665444A true CN116665444A (en) | 2023-08-29 |
Family
ID=87725782
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310656154.5A Pending CN116665444A (en) | 2023-06-05 | 2023-06-05 | Expressway ramp control and variable speed limit cooperative control method considering accident risk |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116665444A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117975737A (en) * | 2024-04-02 | 2024-05-03 | 北京中交华安科技有限公司 | Vehicle active guidance and intelligent control method for highway interweaving area |
-
2023
- 2023-06-05 CN CN202310656154.5A patent/CN116665444A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117975737A (en) * | 2024-04-02 | 2024-05-03 | 北京中交华安科技有限公司 | Vehicle active guidance and intelligent control method for highway interweaving area |
| CN117975737B (en) * | 2024-04-02 | 2024-05-31 | 北京中交华安科技有限公司 | Vehicle active guidance and intelligent control method for highway interweaving area |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cheng et al. | Research on travel time prediction model of freeway based on gradient boosting decision tree | |
| CN113327416A (en) | Urban area traffic signal control method based on short-term traffic flow prediction | |
| CN113299107B (en) | Multi-target fusion intersection dynamic vehicle internet speed guiding control method | |
| CN110363255B (en) | Highway speed-limiting and current-limiting method based on deep learning algorithm | |
| CN109345832B (en) | Urban road overtaking prediction method based on deep recurrent neural network | |
| Pamuła | Road traffic parameters prediction in urban traffic management systems using neural networks | |
| CN111145544B (en) | Travel time and route prediction method based on congestion spreading dissipation model | |
| CN116665444A (en) | Expressway ramp control and variable speed limit cooperative control method considering accident risk | |
| CN115063990A (en) | Dynamic speed limit control method for bottleneck section of highway in mixed traffic flow environment | |
| CN113053120B (en) | Traffic signal lamp scheduling method and system based on iterative learning model predictive control | |
| CN110490365B (en) | Method for predicting network car booking order quantity based on multi-source data fusion | |
| Chen et al. | Adaptive ramp metering control for urban freeway using large-scale data | |
| CN115691138A (en) | Road network subregion division and subregion boundary flow control method | |
| CN112258856B (en) | Method for establishing regional traffic signal data drive control model | |
| CN117351734A (en) | Intelligent regulation and control method and system for vehicle delay | |
| Deshmukh et al. | Machine Learning Algorithm Comparison for Traffic Signal: A Design Approach | |
| CN114463978B (en) | Data monitoring method based on track traffic information processing terminal | |
| CN107886192B (en) | Data and information fusion method based on fixed and mobile vehicle detection data | |
| CN116596126A (en) | Bus string prediction method and system | |
| CN113628455B (en) | Intersection signal optimization control method considering number of people in vehicle under Internet of vehicles environment | |
| Lin et al. | Multiple emergency vehicle priority in a connected vehicle environment: A cooperative method | |
| Kamal et al. | Early detection of a traffic flow breakdown in the freeway based on dynamical network markers | |
| CN106530689B (en) | A kind of real-time predictor method of bus arrival time based on genetic algorithm and running data | |
| CN116434575B (en) | Bus green wave scheme robust generation method considering travel time uncertainty | |
| CN117834136B (en) | Quantum key dynamic management method in Internet of vehicles communication process |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |