CN117523823A - Regional traffic signal control optimization method based on quantum genetic algorithm - Google Patents
Regional traffic signal control optimization method based on quantum genetic algorithm Download PDFInfo
- Publication number
- CN117523823A CN117523823A CN202311312534.3A CN202311312534A CN117523823A CN 117523823 A CN117523823 A CN 117523823A CN 202311312534 A CN202311312534 A CN 202311312534A CN 117523823 A CN117523823 A CN 117523823A
- Authority
- CN
- China
- Prior art keywords
- time
- vehicle
- intersection
- genetic algorithm
- quantum
- 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
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 166
- 230000002068 genetic effect Effects 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000005457 optimization Methods 0.000 title claims abstract description 19
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 239000003086 colorant Substances 0.000 claims description 4
- 230000035772 mutation Effects 0.000 claims description 4
- 230000000737 periodic effect Effects 0.000 claims description 4
- 210000000349 chromosome Anatomy 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 17
- 230000002787 reinforcement Effects 0.000 description 11
- 125000004122 cyclic group Chemical group 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 238000004088 simulation Methods 0.000 description 7
- 230000002457 bidirectional effect Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000011160 research Methods 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 3
- 229910003460 diamond Inorganic materials 0.000 description 2
- 239000010432 diamond Substances 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000002096 quantum dot Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012358 sourcing Methods 0.000 description 1
- 230000003068 static effect Effects 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
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
- G08G1/0145—Measuring and analyzing of parameters relative to traffic conditions for specific applications for active traffic flow control
-
- 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
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of 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
- 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
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a regional traffic signal control optimization method based on a quantum genetic algorithm. The invention combines the road models of the two-way crossroad, the two-way annular crossroad and the diamond-type crossroad, and optimizes the passing efficiency of vehicles from three aspects of average waiting time, standard deviation and collision percentage of the vehicles. Compared to other algorithms, quantum genetic algorithms search the solution space more efficiently due to their special performance and have a faster convergence speed. The method can quickly find the optimal solution and update the population through quantum rotation gate technology so as to guide the evolution process more effectively. Compared with the traditional swarm intelligence algorithm, the quantum genetic algorithm is easier to find the best solution of the current result.
Description
Technical Field
The invention belongs to the technical field of traffic signal control, and particularly relates to a regional traffic signal control optimization method based on a quantum genetic algorithm, which aims to solve the problem of traffic intersection congestion under the existing infrastructure condition.
Background
Traffic signal control is widely applied to traffic flow management as an important tool, and research shows that the traffic signal control is one of the most effective methods at present, and can obviously reduce traffic jam and improve traffic efficiency. With the rapid development of sensors and intelligent networking automobiles, research on signal control of complex traffic intersections is still necessary.
At present, two main modes are adopted for solving the urban traffic problem in China, one mode is to continuously increase the investment and construction of urban infrastructure traffic facilities, and the other mode is to improve the urban road network traffic management and control efficiency. However, the building speed of the urban infrastructure cannot catch up with the increasing speed of people on traffic demands, and the capacity of the road cannot load traffic pressure, so that the method cannot effectively solve the traffic problem. The other method is to optimize traffic signal timing by utilizing computer application technology and real-time information integration, thereby realizing more efficient vehicle circulation and providing a feasible solution for urban traffic systems.
Urban traffic signal control is a well developed and important research area aimed at shortening the average waiting time per vehicle by coordinating the movement of vehicles at intersections. Traffic signal control studies began in the 60 s of the last century, and several periodic optimization models have been developed, including the TRRL method in the united kingdom, the ARRB method in australia, the HCM method in the united states, and the like. At the end of the 20 th century to the beginning of the 21 st century, traffic students began to reduce the problem of urban traffic congestion while improving the vehicle passing efficiency by fusing control theory with intelligent algorithms. As heuristic algorithms have evolved in the 10 s of the 20 th century, it has become an algorithm to solve the combinatorial optimization problem, with one feasible solution for each instance. Because of its unique features and capabilities, heuristic algorithms are widely used in solving intelligent traffic control problems.
The above studies, although having achieved great success, still have the following problems: (1) In the prior art, an algorithm is proposed mainly aiming at a crossroad, other crossroad conditions are not introduced into an algorithm model, and application expansion is difficult to carry out; (2) The traffic capacity varies from road to road, but this is not considered in the existing models. In summary, there are many researches on the optimization control of regional traffic signals, in recent years, quantum theory has been rapidly developed, and the quantum theory is widely applied in the aspects of intelligent traffic system, complex system model, optimization and the like.
Disclosure of Invention
The invention aims to provide a regional traffic signal control optimization method based on a quantum genetic algorithm aiming at the problem of traffic intersection vehicle congestion.
The invention is realized by the following technical scheme, and provides a regional traffic signal control optimization method based on a quantum genetic algorithm, which comprises the following steps:
step1: initializing a system, and determining population quantity, chromosome length and iteration times;
step2: generating an initial population by utilizing the quantum probability amplitude;
step3: calculating a fitness value;
step4: selection operation: calculating the fitness, and selecting individuals with large fitness values to be transmitted to the next generation;
step5: crossover and mutation operations: generating new individuals through quantum revolving doors to meet the requirement of the total number of the groups;
step6: judging whether the maximum evolution algebra is reached, if not, turning to Step3 operation; otherwise, step7 is performed;
step7: calculating signal phase parameters of all intersections; in a signal period, one or more traffic flows acquire the display of the identical signal light color at any time, and then the continuous time sequence of acquiring different light colors is called a signal phase;
step8: the algorithm ends and the procedure exits.
Further, in the quantum genetic algorithm, the signal phase timing calculation formula with the largest number of vehicles passing in unit time is as follows:
wherein Y represents the sum of the maximum flow ratios of all the periodic phases, i.e
Y i Is the maximum flow ratio of the ith phase, i.e
Wherein q is i For the real-time flow of the ith phase at a certain moment, s i The maximum number of lanes is fully occupied for the i-th phase vehicle.
Further, in the quantum genetic algorithm, a calculation formula of no vehicle passing time in one cycle of signal phase is as follows:
wherein l is the starting time of the vehicle, I is the adjacent time difference of two green lights, A is the time for the signal lamp at the intersection to continuously be yellow, and n is the phase number; the calculation formula of A is as follows:
wherein v is 0 To be on the roadThe speed of a running vehicle, f is the friction coefficient on a road, g is gravity, c is the length of the vehicle, D is the width of an intersection, and T is the feedback time of a driver;
i is the time of the adjacent time difference of the two green lights, and the calculation formula is as follows:
where z is the distance between the stop line and the conflict point, u a Indicating the speed of the vehicle when entering the intersection, t s Is the time required for braking the vehicle.
Further, in the quantum genetic algorithm, the maximum traffic volume calculation formula of the lane fully occupied by the vehicle is as follows:
in the middle ofIn the timing period of the signal phase, the number of vehicles passing through an mth intersection and an nth entrance in unit time is counted; />The flow rate of the nth crossing at the highest 15 minutes in the peak time is the flow rate of the nth crossing in the unit period; without the flow rate of up to 15 minutes during peak hours, the estimation is performed using the following formula:
q in mn In the signal phase timing time period, the traffic flow of the mth intersection and the nth entrance within one hour of the peak time period is calculated; (PHF) mn In the signal phase timing time period, the mth intersection and the nth entrance are coefficients within one hour of the peak time period.
Further, in the quantum genetic algorithm, the total time allowed to pass the vehicle in the signal phase is:
G e ＝S c -L。
further, in the quantum genetic algorithm, the time that can pass through the vehicle per unit time is:
further, in the quantum genetic algorithm, the proportional time available for vehicle traffic is:
further, the average residence time of all vehicles at the entrance of the road intersection is:
d in i,j,k The average delay time of the vehicle in the kth lane of the jth entrance of the ith intersection; n (N) i,j The number of lanes for the j-th entrance of the i-th intersection; n (N) i The number of entrance ways for the i-th intersection; n is the number of intersections; q (Q) i,j,k The number of vehicles in the kth lane of the jth entrance of the ith intersection; wherein d is i,j,k The solution formula of (2) is:
wherein Q represents real-time flow at a certain moment; t is t r Representing the time that the signal lamp of the crossing is continuously red; s represents the maximum number of vehicles that fully occupy the lane.
The invention provides electronic equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the regional traffic signal control optimization method based on a quantum genetic algorithm when executing the computer program.
The invention provides a computer readable storage medium for storing computer instructions which when executed by a processor implement the steps of the regional traffic signal control optimization method based on a quantum genetic algorithm.
The invention aims at reducing the average waiting time of the vehicle and optimizes the algorithm from multiple directions by taking the collision rate and standard deviation as optimization factors on the basis. Compared with the traditional crowd-sourcing algorithm, the method realizes better effect and mainly contributes to:
(1) Constructing a regional traffic signal lamp control strategy based on three typical intersection road models;
(2) In the aspect of experimental results, the better performance and the effectiveness of the experimental results are highlighted by comparing with four traditional signal timing methods of a fixed timing algorithm, a longest queue priority algorithm, a reinforcement learning algorithm and a genetic algorithm;
(3) In the aspect of optimizing effect, the algorithm is reduced in three aspects of vehicle average waiting time, collision rate and standard deviation under three typical intersection road models compared with other algorithms, and the traffic efficiency and safety of the road network are further improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a regional traffic signal control optimization method based on a quantum genetic algorithm.
Fig. 2 is a schematic diagram of a 3D model of a two-way intersection.
Fig. 3 is a schematic diagram of a 3D model of a bidirectional loop-type intersection.
Fig. 4 is a schematic diagram of a diamond-type intersection 3D model.
Fig. 5 is a schematic diagram of average vehicle waiting times per five algorithms for a two-way intersection.
Fig. 6 is a standard deviation diagram of five algorithms for a two-way intersection.
Fig. 7 is a schematic diagram of average wait times per vehicle for five algorithms for a two-way loop intersection.
Fig. 8 is a schematic view of collision rates for five algorithms for a two-way loop intersection.
Fig. 9 is a standard deviation schematic diagram of five algorithms of a bidirectional annular intersection.
Fig. 10 is a graph showing average waiting times of each vehicle for five algorithms at a diamond-type intersection.
Fig. 11 is a schematic diagram of collision rates of five algorithms at a diamond-type intersection.
Fig. 12 is a standard deviation diagram of five algorithms of diamond-type crossing.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Correlation definition
Definition 1 Signal phase
In a signal cycle, one or several traffic flows get the same signal light color display at any time, then the sequential timing of their getting different light colors (green, yellow, full red) is called a signal phase.
Definition 2 Green letter ratio
The green-to-blue ratio refers to the proportional time available for a vehicle to pass within one cycle of the traffic light. I.e. the ratio of the effective green time to the period duration of a certain phase.
Definition of 3 Quantum states
Quantum states are a group of quantum characterizations used to represent states of quantum mechanical isolation systems. Quantum states include pure states and mixed states.
The pure state may be represented by a complex vector defined on the hilbert space, the dimensions of which are determined by the dimensions of the quantum system. Such as for a qubit (dimension 2) quantum state, can be expressed as
Where α and β are two amplitude constants, also known as probability amplitude, while α and β satisfy
|α| 2 +|β| 2 ＝1
The mixture is a probabilistic mixture of a series of pure states, which can be represented by a density matrix ρ
Wherein the method comprises the steps ofAnd p i Representing the pure state and its corresponding probability. The probability distribution satisfies the normalized Σp i Relation=1 and density matrix satisfies Tr { ρ 2 Equal sign holds when ρ is pure.
Referring to fig. 1-12, according to three typical intersections, by comparing three evaluation parameters of average waiting time, standard deviation and collision percentage, the quantum genetic algorithm has certain advantages in solving the problem of intersection congestion compared with other four algorithms, and specifically, the invention provides a regional traffic signal control optimization method based on the quantum genetic algorithm, which comprises the following steps:
step1: initializing a system, and determining population quantity, chromosome length and iteration times;
step2: generating an initial population by utilizing the quantum probability amplitude;
step3: calculating a fitness value;
step4: selection operation: calculating the fitness, and selecting individuals with large fitness values to be transmitted to the next generation;
step5: crossover and mutation operations: generating new individuals through quantum revolving doors to meet the requirement of the total number of the groups;
step6: judging whether the maximum evolution algebra is reached, if not, turning to Step3 operation; otherwise, step7 is performed;
step7: calculating signal phase parameters of all intersections; in a signal period, one or more traffic flows acquire the display of the identical signal light color at any time, and then the continuous time sequence of acquiring different light colors is called a signal phase;
step8: the algorithm ends and the procedure exits.
According to the flow of the quantum genetic algorithm, the time complexity of generating the parent population is O (n 2 ) The time complexity of the select crossover operation is O (n 2 ) The time complexity of the mutation operation is O (n), and the time complexity of the fitness function calculation is O (n). The time complexity of the present invention is max (O (n), O (n) 2 ))＝O(n 2 )。
The quantum genetic algorithm is used for constructing traffic signal control and vehicle travel related formulas on three typical intersection road models;
in the quantum genetic algorithm, the signal phase timing calculation formula with the largest number of vehicles passing in unit time is as follows:
wherein Y represents the sum of the maximum flow ratios of all the periodic phases, i.e
Y i Is the maximum flow ratio of the ith phase, i.e
Wherein q is i For the real-time flow of the ith phase at a certain moment, s i The maximum number of lanes is fully occupied for the i-th phase vehicle.
In the quantum genetic algorithm, the calculation formula of no vehicle passing time in one cycle of signal phase is as follows:
wherein l is the starting time of the vehicle, I is the adjacent time difference of two green lights, A is the time for the signal lamp at the intersection to continuously be yellow, and n is the phase number; the calculation formula of A is as follows:
wherein v is 0 For the speed of the vehicle running on the road, f is the friction coefficient on the road, g is gravity, c is the length of the vehicle, D is the width of the intersection, and T is the feedback time of the driver;
i is the time of the adjacent time difference of the two green lights, and the calculation formula is as follows:
where z is the distance between the stop line and the conflict point, u a Indicating the speed of the vehicle when entering the intersection, t s Is the time required for braking the vehicle.
In the quantum genetic algorithm, the maximum traffic volume calculation formula of the lane fully occupied by the vehicle is as follows:
in the middle ofIn the timing period of the signal phase, the number of vehicles passing through an mth intersection and an nth entrance in unit time is counted; />The flow rate of the nth crossing at the highest 15 minutes in the peak time is the flow rate of the nth crossing in the unit period; without the flow rate of up to 15 minutes during peak hours, the estimation is performed using the following formula:
q in mn In the signal phase timing time period, the traffic flow of the mth intersection and the nth entrance within one hour of the peak time period is calculated; (PHF) mn In the signal phase timing time period, the mth intersection and the nth entrance are coefficients within one hour of the peak time period.
In the quantum genetic algorithm, the total time allowed to pass the vehicle in the signal phase is:
G e ＝S c -L。
in the quantum genetic algorithm, the time that can pass through the vehicle in a unit time is:
in the quantum genetic algorithm, the proportional time available for vehicle traffic is:
the average residence time of all vehicles at the entrance of the road intersection is as follows:
d in i,j,k The average delay time of the vehicle in the kth lane of the jth entrance of the ith intersection; n (N) i,j The number of lanes for the j-th entrance of the i-th intersection; n (N) i The number of entrance ways for the i-th intersection; n is the number of intersections; q (Q) i,j,k The number of vehicles in the kth lane of the jth entrance of the ith intersection; wherein d is i,j,k The solution formula of (2) is:
wherein Q represents real-time flow at a certain moment; t is t r Representing the time that the signal lamp of the crossing is continuously red; s represents the maximum number of vehicles that fully occupy the lane.
Specific models of the bidirectional crossroad, the bidirectional annular crossroad, and the diamond-type crossroad shown in fig. 2, 3, and 4 will be described below as examples.
Two-way crossroad model description
Step 1/call simulation module introduces vehicle road information, and introduces parameter maximum vehicle quantity
Function Simulation(max_gen)
Step 2/adding crossroad roads, introducing crossroad road parameters:/and
Function add_roads(roads)
specific parameters of the crossroad are as follows:
Inbound in four directions:east,west,north and south；
Outbound in four directions:east,west,north and south
Straight from east to west and north to south
Left turns in four directions:east,west,north and south
Right turns in four directions:east,west,north and south
step 3/add vehicle information, introduce parameters vehicle speed and vehicle path
Function add_generator(vehicle_rate,paths)
Step 4/adding traffic signal control function, introducing parameters of road signal position, signal cycle period, slow distance, slow factor and vehicle stopping distance +.
Function add_traffic_signal(signal_roads,cycle,slow_distance,slow_factor,stop_distance)。
Bidirectional annular intersection model description
Step 1/call simulation module introduces vehicle road information, and introduces parameter maximum vehicle quantity
Function Simulation(max_gen)
Step 2/adding ring-shaped intersection roads, and introducing ring-shaped intersection road parameters × +.
Function add_roads(roads)
The specific parameters of the annular intersection are as follows:
Inbound in four directions:east,west,north and south；
Outbound in four directions:east,west,north and south
Left turns in four directions:east,west,north and south
Right turns in four directions:east,west,north and south
Construct four directions:east,west,north and south
step 3/add vehicle information, introduce parameters vehicle speed and vehicle path
Function add_generator(vehicle_rate,paths)
Step 4/adding traffic signal control function, introducing parameters of road signal position, signal cycle period, slow distance, slow factor and vehicle stopping distance +.
Function add_traffic_signal(signal_roads,cycle,slow_distance,slow_factor,stop_distance)。
Diamond type intersection 3D model description
Step 1/call simulation module introduces vehicle road information, and introduces parameter maximum vehicle quantity
Function Simulation(max_gen)
Step 2/adding diamond-type intersection roads, and introducing diamond-type intersection road parameters × +.
Function add_roads(roads)
The specific parameters of the diamond-type intersection are as follows:
The right side ofthe north-south direction starts；
Right turns inboth directions；
Left turns inboth directions；
The left side ofthe north-south direction starts；
Right in side ofthe north-south direction；
Straight road from north to south；
Right out side ofthe north-south direction；
North-south straight right
Left in side ofthe north-south direction；
Straight road from north to south；
Left out side ofthe north-south direction；
North-south straight left
The north-south road goes straight to the middle ofthe road
step 3/add vehicle information, introduce parameters vehicle speed and vehicle path
Function add_generator(vehicle_rate,paths)
Step 4/adding traffic signal control function, introducing parameters of road signal position, signal cycle period, slow distance, slow factor and vehicle stopping distance +.
Function add_traffic_signal(signal_roads,cycle,slow_distance,slow_factor,stop_distance)。
In order to further clarify the superiority of the invention, the invention is compared with a traffic signal control model based on a fixed timing control algorithm, a traffic signal control model based on a longest queue priority algorithm, a traffic signal control model based on a reinforcement learning algorithm and a traffic signal control model based on a genetic algorithm, and experimental results show that the invention has stronger advantages in reducing the waiting time of vehicles and improving the traffic efficiency of road networks.
In the two-way crossroad study, five different control algorithms are used, and the average waiting time of the motor vehicle at each run is shown by fig. 5 for each algorithm. The abscissa in the figure represents the number of times the algorithm is executed, and the ordinate represents the waiting time. Experimental data show that the red broken line represents a fixed timing control algorithm, the minimum waiting time is 3.18, the maximum waiting time is 4.36, and the average total waiting time after 100 times of cyclic iteration is 3.8713; the blue broken line represents the longest queue priority control algorithm, the minimum waiting time is 3.18, the maximum waiting time is 4.63, and the average total waiting time after 100 times of loop iteration is 3.8938; the green broken line represents a reinforcement learning algorithm, the minimum waiting time is 3.42, the maximum waiting time is 4.38, and the average total waiting time after 100 times of cyclic iteration is 3.83; the purple broken line represents a genetic algorithm, the minimum waiting time is 3.29, the maximum waiting time is 4.14, and the average total waiting time after 100 cyclic iterations is 3.86; orange broken lines represent the quantum genetic algorithm, the minimum waiting time is 2.61, the maximum waiting time is 4.02, and the average total waiting time after 100 cyclic iterations is 3.38. From these line graphs, it is clear that the trend of five different algorithms at the bi-directional intersection changes at the same time.
Five different control algorithms were used for the experiments to manage the bi-directional intersection and the standard deviation of each algorithm after 100 runs was compared. The standard deviation results of these algorithms are shown in fig. 6. The fixed timing control algorithm is represented by orange, and the standard deviation is 0.169; the longest queue priority control algorithm is represented in blue with a standard deviation of 0.272; the reinforcement learning algorithm is represented by green, and the standard deviation is 0.2278; genetic algorithm is represented by yellow with standard deviation of 0.197; quantum genetic algorithm is represented by dark blue with standard deviation of 0.157. The difference between the average waiting time per group of each vehicle and its group average over 100 cycles for these five algorithms is clearly demonstrated using a dot plot. The higher the standard deviation is the larger the difference between the numerical value and the average value, and the lower the standard deviation is the smaller the difference is.
Five control algorithms are adopted to study the bidirectional annular intersection. From fig. 7, it can be seen that each algorithm averages each vehicle waiting time. The average minimum waiting time of the fixed timing control algorithm is 2.81, the maximum waiting time is 3.98, and the average total waiting time after 100 times of loop iteration is 3.4524; the average minimum waiting time of the longest queue priority control algorithm is 2.58, the maximum waiting time is 4.13, and the average total waiting time after 100 times of loop iteration is 3.4188; the average minimum waiting time of the reinforcement learning algorithm is 2.61, the maximum waiting time is 4.29, and the average total waiting time after 100 times of loop iteration is 3.4002; the average minimum waiting time of the genetic algorithm is 3, the maximum waiting time is 3.99, and the average total waiting time after 100 times of loop iteration is 3.4478; the average minimum waiting time of the quantum genetic algorithm is 2.06, the maximum waiting time is 3.74, and the average total waiting time after 100 cyclic iterations is 3.18. These data show the trend of five different algorithms on the two-way annular intersection at the same time with a line graph.
In this experiment, five different control algorithms were used to manage the bi-directional annular intersection, and the collision rate for each algorithm was recorded. From fig. 8, it can be seen that the collision rate of the fixed timing control algorithm is 9%; the collision rate of the longest queue priority control algorithm is 7%; the collision rate of the reinforcement learning algorithm is 8%; the collision rate of the genetic algorithm is 7%; the collision rate of the quantum genetic algorithm is the lowest and is only 3%. To more clearly show the collision rate ratio of these five algorithms in the same time period, a three-dimensional pie chart is used for representation.
Experiments were performed in the study of two-way annular intersections and five different control algorithms were employed. After 100 runs, the standard deviation of the results for each algorithm was calculated. The results of these standard deviations are shown in fig. 9. According to the color representation in the figure, orange represents a fixed timing control algorithm, and the standard deviation is 0.33; blue represents the longest queue priority control algorithm, which is executed for a time of 0.36; green represents the reinforcement learning algorithm with a standard deviation of 0.417; yellow represents the genetic algorithm with a standard deviation of 0.32; the dark blue color represents the quantum genetic algorithm with a standard deviation of 0.26. The difference between the average vehicle waiting time per group and the average value of its group over 100 loop iterations for each algorithm is shown by a dot plot. The higher the standard deviation is, the larger the difference between the numerical value and the average value is, and the lower the standard deviation is, the smaller the difference between the numerical value and the average value is.
Fig. 10 shows the average vehicle waiting time per algorithm when five control algorithms are used at the diamond-type intersection. The red broken line represents a fixed timing control algorithm, the minimum value is 3.65, the maximum value is 5.54, and the average total waiting time after 100 times of cyclic iteration is 4.5171; the blue broken line represents the longest queue priority control algorithm, the minimum value is 3.86, the maximum value is 5.59, and the average total waiting time after 100 loop iterations is 4.628; the green broken line represents a reinforcement learning algorithm, the minimum value is 2.4, the maximum value is 14.96, and the average total waiting time after 100 times of cyclic iteration is 4.8783; the purple broken line represents a genetic algorithm, the minimum value is 3.63, the maximum value is 5.6, and the average total waiting time after 100 times of cyclic iteration is 4.5618; the orange broken line represents the quantum genetic algorithm, the minimum value is 2.82, the maximum value is 4.1, and the average total waiting time after 100 cyclic iterations is 3.49. The diamond-type intersection adopts the variation trend of different algorithms, and can be clearly displayed through the line graph in the same time period.
Fig. 11 shows the collision rate results after five control algorithms are applied at the diamond-type intersection. From the color correspondence in the graph, the following can be concluded: the collision rate of the fixed timing control algorithm is 10%; the collision rate of the longest queue priority control algorithm is 9%; the collision rate of the reinforcement learning algorithm is 19.4%; the collision rate of the genetic algorithm is 12%; the collision rate of the quantum genetic algorithm is 8.76%. To better compare the effects of these five algorithms, a three-dimensional pie chart was used to show their impact rate versus time.
Five different control algorithms were used at the diamond-type intersection and compared by standard deviation after 100 runs of each algorithm. Fig. 12 shows the standard deviation after the algorithm is run. Wherein, orange represents a fixed timing control algorithm, and the standard deviation is 0.368; blue represents the longest queue priority control algorithm, which is executed for a time of 0.75; green represents a reinforcement learning algorithm with a standard deviation of 2.42; yellow represents the genetic algorithm with a standard deviation of 0.637; and the dark blue represents the quantum genetic algorithm with a standard deviation of 0.358. By using a dot plot to show the difference of the average vehicle waiting time of each group over 100 iterations of the loop for each of the five algorithms, the effect of each algorithm can be more intuitively understood. Higher standard deviation means that the values differ more from the average values, while lower standard deviation means that the values differ less from the average values.
According to experimental result analysis, the average waiting time of each motor vehicle can be reduced by 12.7%, 13.2%, 11.7% and 12.4% respectively by using a quantum genetic algorithm compared with a fixed timing algorithm, a longest queue priority algorithm, a reinforcement learning algorithm and a genetic algorithm on the two-way intersection. Furthermore, the quantum genetic algorithm can reduce the standard deviation by 1.2%, 11.5%, 7.08% and 4%, respectively, compared to the four algorithms described above in terms of standard deviation. At the two-way circular intersection, the waiting time of the motor vehicle can be obviously reduced by using a quantum genetic algorithm. Compared with four algorithms such as a fixed timing algorithm, the quantum genetic algorithm reduces the waiting time of the motor vehicle by 7.9%, 7%, 6.5% and 7.8% on average. In addition, quantum genetic algorithms can also reduce collision rate. Compared with other four algorithms, the quantum genetic algorithm reduces the collision rate by 6%, 4%, 5% and 4% respectively. In addition, the performance of the quantum genetic algorithm is improved in terms of standard deviation, and the performance is respectively reduced by 7%, 10%, 15.7% and 6%. At diamond-type intersections, quantum genetic algorithms can reduce the waiting time of each vehicle by 22.7%, 24.6%, 28.5%, 23.5% on average, as compared to these four algorithms. In terms of collision rate, compared with the four algorithms, the quantum genetic algorithm can be reduced by 1.24%, 0.24%, 10.64% and 3.24% respectively. Compared with four algorithms such as a fixed timing algorithm, the quantum genetic algorithm can be reduced by 1%, 39.2%, 206.2% and 27.9% respectively in terms of standard deviation.
The quantum genetic algorithm provided by the invention can search the solution space of the problem more effectively and has a faster convergence speed than other algorithms. The method can quickly find the optimal solution and update the population by utilizing the quantum rotation gate technology, thereby guiding the evolution process more effectively. Compared with the other four algorithms, the quantum genetic algorithm is easier to find the best solution of the current result. Therefore, the quantum genetic algorithm has certain advantages over other algorithms in solving the traffic jam problem.
The invention builds signal lamp control models of three traffic intersections including an intersection, an annular intersection and a diamond intersection by utilizing a quantum genetic algorithm for the first time based on Pygame experimental simulation. Experimental results show that the traffic light signal control model based on the quantum genetic algorithm achieves better effects in optimizing traffic light timing strategies and reducing vehicle queuing time. The model is very helpful for improving the overall vehicle passing efficiency, provides a new thought for solving the traffic jam problem, and has certain theoretical and practical significance.
The invention provides electronic equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the regional traffic signal control optimization method based on a quantum genetic algorithm when executing the computer program.
The invention provides a computer readable storage medium for storing computer instructions which when executed by a processor implement the steps of the regional traffic signal control optimization method based on a quantum genetic algorithm.
The memory in embodiments of the present application may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a Read Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. The volatile memory may be random access memory (random access memory, RAM) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous DRAM (SLDRAM), and direct memory bus RAM (DRRAM). It should be noted that the memory of the methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the processes or functions described in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a high-density digital video disc (digital video disc, DVD)), or a semiconductor medium (e.g., a Solid State Disk (SSD)), or the like.
In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or by instructions in the form of software. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in the processor for execution. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method. To avoid repetition, a detailed description is not provided herein.
It should be noted that the processor in the embodiments of the present application may be an integrated circuit chip with signal processing capability. In implementation, the steps of the above method embodiments may be implemented by integrated logic circuits of hardware in a processor or instructions in software form. The processor may be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, or discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in hardware, in a decoded processor, or in a combination of hardware and software modules in a decoded processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.
The invention provides a regional traffic signal control optimization method based on a quantum genetic algorithm, and specific examples are applied to illustrate the principle and the implementation mode of the invention, and the illustration of the above examples is only used for helping to understand the method and the core idea of the invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (10)
1. A regional traffic signal control optimization method based on a quantum genetic algorithm is characterized by comprising the following steps of: the method comprises the following steps:
step1: initializing a system, and determining population quantity, chromosome length and iteration times;
step2: generating an initial population by utilizing the quantum probability amplitude;
step3: calculating a fitness value;
step4: selection operation: calculating the fitness, and selecting individuals with large fitness values to be transmitted to the next generation;
step5: crossover and mutation operations: generating new individuals through quantum revolving doors to meet the requirement of the total number of the groups;
step6: judging whether the maximum evolution algebra is reached, if not, turning to Step3 operation; otherwise, step7 is performed;
step7: calculating signal phase parameters of all intersections; in a signal period, one or more traffic flows acquire the display of the identical signal light color at any time, and then the continuous time sequence of acquiring different light colors is called a signal phase;
step8: the algorithm ends and the procedure exits.
2. The method according to claim 1, characterized in that: in the quantum genetic algorithm, the signal phase timing calculation formula with the largest number of vehicles passing in unit time is as follows:
wherein Y represents the sum of the maximum flow ratios of all the periodic phases, i.e
Y i Is the maximum flow ratio of the ith phase, i.e
Wherein q is i For the real-time flow of the ith phase at a certain moment, s i The maximum number of lanes is fully occupied for the i-th phase vehicle.
3. The method according to claim 2, characterized in that: in the quantum genetic algorithm, the calculation formula of no vehicle passing time in one cycle of signal phase is as follows:
wherein l is the starting time of the vehicle, I is the adjacent time difference of two green lights, A is the time for the signal lamp at the intersection to continuously be yellow, and n is the phase number; the calculation formula of A is as follows:
wherein v is 0 For the speed of the vehicle running on the road, f is the friction coefficient on the road, g is gravity, c is the length of the vehicle, D is the width of the intersection, and T is the feedback time of the driver;
i is the time of the adjacent time difference of the two green lights, and the calculation formula is as follows:
where z is the distance between the stop line and the conflict point, u a Indicating the speed of the vehicle when entering the intersection, t s Is the time required for braking the vehicle.
4. A method according to claim 3, characterized in that: in the quantum genetic algorithm, the maximum traffic volume calculation formula of the lane fully occupied by the vehicle is as follows:
in the middle ofIn the timing period of the signal phase, the number of vehicles passing through an mth intersection and an nth entrance in unit time is counted; />The flow rate of the nth crossing at the highest 15 minutes in the peak time is the flow rate of the nth crossing in the unit period; without the flow rate of up to 15 minutes during peak hours, the estimation is performed using the following formula:
q in mn In the signal phase timing time period, the traffic flow of the mth intersection and the nth entrance within one hour of the peak time period is calculated; (PHF) mn In the signal phase timing time period, the mth intersection and the nth entrance are coefficients within one hour of the peak time period.
5. The method according to claim 4, wherein: in the quantum genetic algorithm, the total time allowed to pass the vehicle in the signal phase is:
G e ＝S c -L。
6. the method according to claim 5, wherein: in the quantum genetic algorithm, the time that can pass through the vehicle in a unit time is:
7. the method according to claim 6, wherein: in the quantum genetic algorithm, the proportional time available for vehicle traffic is:
8. the method according to claim 7, wherein: the average residence time of all vehicles at the entrance of the road intersection is as follows:
d in i,j,k The average delay time of the vehicle in the kth lane of the jth entrance of the ith intersection; n (N) i,j The number of lanes for the j-th entrance of the i-th intersection; n (N) i The number of entrance ways for the i-th intersection; n is the number of intersections; q (Q) i,j,k The number of vehicles in the kth lane of the jth entrance of the ith intersection; wherein d is i,j,k The solution formula of (2) is:
wherein Q represents real-time flow at a certain moment; t is t r Representing the time that the signal lamp of the crossing is continuously red; s represents the maximum number of vehicles that fully occupy the lane.
9. An electronic device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1-8 when the computer program is executed.
10. A computer readable storage medium storing computer instructions which, when executed by a processor, implement the steps of the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311312534.3A CN117523823A (en) | 2023-10-11 | 2023-10-11 | Regional traffic signal control optimization method based on quantum genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311312534.3A CN117523823A (en) | 2023-10-11 | 2023-10-11 | Regional traffic signal control optimization method based on quantum genetic algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117523823A true CN117523823A (en) | 2024-02-06 |
Family
ID=89759532
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311312534.3A Pending CN117523823A (en) | 2023-10-11 | 2023-10-11 | Regional traffic signal control optimization method based on quantum genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117523823A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809889A (en) * | 2015-04-19 | 2015-07-29 | 北京工业大学 | Traffic signal timing optimization method based on principal component analysis improvement genetic algorithm |
| CN107610487A (en) * | 2017-08-23 | 2018-01-19 | 南京邮电大学 | Area Traffic Control System and method based on the dynamic random wagon flow phase difference coordination system |
| CN108898857A (en) * | 2018-06-13 | 2018-11-27 | 同济大学 | A kind of intersection motor vehicle green light interval setting method considering security reliability |
| CN109887274A (en) * | 2019-01-23 | 2019-06-14 | 南京邮电大学 | A kind of regional traffic coordination optimizing control system and method based on vehicles average delay |
| US20190347933A1 (en) * | 2018-05-11 | 2019-11-14 | Virtual Traffic Lights, LLC | Method of implementing an intelligent traffic control apparatus having a reinforcement learning based partial traffic detection control system, and an intelligent traffic control apparatus implemented thereby |
| CN110517510A (en) * | 2019-08-27 | 2019-11-29 | 华侨大学 | Based on the Intersections timing designing method for improving Webster function and genetic algorithm |
| CN111739284A (en) * | 2020-05-06 | 2020-10-02 | 东华大学 | Traffic signal lamp intelligent timing method based on genetic algorithm optimization fuzzy control |
| CN113012449A (en) * | 2021-03-11 | 2021-06-22 | 华南理工大学 | Smart city signal lamp timing optimization method based on multi-sample learning particle swarm |
| JP2021128771A (en) * | 2020-02-11 | 2021-09-02 | ベイジン バイドゥ ネットコム サイエンス テクノロジー カンパニー リミテッドBeijing Baidu Netcom Science Technology Co., Ltd. | Control method of traffic light signal, device, apparatus and storage medium |
| US20210375129A1 (en) * | 2017-09-28 | 2021-12-02 | Weiping Meng | Traffic Signal Pan-String Control Method and Its System |
-
2023
- 2023-10-11 CN CN202311312534.3A patent/CN117523823A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809889A (en) * | 2015-04-19 | 2015-07-29 | 北京工业大学 | Traffic signal timing optimization method based on principal component analysis improvement genetic algorithm |
| CN107610487A (en) * | 2017-08-23 | 2018-01-19 | 南京邮电大学 | Area Traffic Control System and method based on the dynamic random wagon flow phase difference coordination system |
| US20210375129A1 (en) * | 2017-09-28 | 2021-12-02 | Weiping Meng | Traffic Signal Pan-String Control Method and Its System |
| US20190347933A1 (en) * | 2018-05-11 | 2019-11-14 | Virtual Traffic Lights, LLC | Method of implementing an intelligent traffic control apparatus having a reinforcement learning based partial traffic detection control system, and an intelligent traffic control apparatus implemented thereby |
| CN108898857A (en) * | 2018-06-13 | 2018-11-27 | 同济大学 | A kind of intersection motor vehicle green light interval setting method considering security reliability |
| CN109887274A (en) * | 2019-01-23 | 2019-06-14 | 南京邮电大学 | A kind of regional traffic coordination optimizing control system and method based on vehicles average delay |
| CN110517510A (en) * | 2019-08-27 | 2019-11-29 | 华侨大学 | Based on the Intersections timing designing method for improving Webster function and genetic algorithm |
| JP2021128771A (en) * | 2020-02-11 | 2021-09-02 | ベイジン バイドゥ ネットコム サイエンス テクノロジー カンパニー リミテッドBeijing Baidu Netcom Science Technology Co., Ltd. | Control method of traffic light signal, device, apparatus and storage medium |
| CN111739284A (en) * | 2020-05-06 | 2020-10-02 | 东华大学 | Traffic signal lamp intelligent timing method based on genetic algorithm optimization fuzzy control |
| CN113012449A (en) * | 2021-03-11 | 2021-06-22 | 华南理工大学 | Smart city signal lamp timing optimization method based on multi-sample learning particle swarm |
| WO2022188387A1 (en) * | 2021-03-11 | 2022-09-15 | 华南理工大学 | Multi-model learning particle swarm-based intelligent city signal light timing optimization method |
Non-Patent Citations (8)
| Title |
|---|
| ZEYU ZHANG 等: "Multi-Objective Optimization of Traffic Signal Timing at Typical Junctions Based on Genetic Algorithms", COMPUTER SYSTEMS SCIENCE AND ENGINEERING, 28 July 2023 (2023-07-28) * |
| 刘脐锺 等: "基于遗传算法的智能交通信号区域协调控制研究", 西华大学学报（自然科学版）, vol. 33, no. 6, 30 November 2014 (2014-11-30) * |
| 孙昊琛: "城市干线道路交通系统信号优化策略研究", 中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑, no. 05, 15 May 2020 (2020-05-15), pages 034 - 230 * |
| 庄宏斌;周亚平;曹宪生;: "基于改进遗传算法的区域交通信号配时优化", 交通运输系统工程与信息, no. 04, 15 August 2012 (2012-08-15) * |
| 彭飞: "城市道路平面交叉口信号配时优化与仿真研究", 中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑, no. 10, 15 October 2012 (2012-10-15), pages 034 - 677 * |
| 徐山峰: "区域交通协同控制的混沌量子进化算法研究", 中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑, no. 09, 15 September 2012 (2012-09-15), pages 034 - 186 * |
| 沙尧尧: "城市干道动态交通控制系统研究", 中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑, no. 03, 15 March 2014 (2014-03-15), pages 034 - 735 * |
| 赵宇航: "基于遗传算法的城市区域交通信号优化控制", 中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑, no. 01, 15 January 2019 (2019-01-15), pages 034 - 2428 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | A review of the self-adaptive traffic signal control system based on future traffic environment | |
| CN109785619B (en) | Regional traffic signal coordination optimization control system and control method thereof | |
| CN114038212B (en) | Signal lamp control method based on two-stage attention mechanism and deep reinforcement learning | |
| CN114495527A (en) | Method and system for collaborative optimization of vehicle paths at internet intersection in mixed traffic environment | |
| CN113963555B (en) | Depth combined with state prediction control method for reinforcement learning traffic signal | |
| CN114495499B (en) | Multi-target intelligent internet vehicle cooperative optimization control method | |
| US20230351890A1 (en) | Traffic light control method for urban road network based on expected return estimation | |
| Tamimi et al. | Intelligent traffic light based on genetic algorithm | |
| Wang et al. | Traffic signal priority control based on shared experience multi‐agent deep reinforcement learning | |
| CN112562363B (en) | Intersection traffic signal optimization method based on V2I | |
| Chen et al. | Cooperative control of connected hybrid electric vehicles and traffic signals at isolated intersections | |
| CN116758767B (en) | Traffic signal lamp control method based on multi-strategy reinforcement learning | |
| CN114120670A (en) | Method and system for traffic signal control | |
| CN117523823A (en) | Regional traffic signal control optimization method based on quantum genetic algorithm | |
| Wu et al. | Deep Reinforcement Learning Based Traffic Signal Control: A Comparative Analysis | |
| CN115331460B (en) | Large-scale traffic signal control method and device based on deep reinforcement learning | |
| CN115547050A (en) | Intelligent traffic signal control optimization method and software based on Markov decision process | |
| CN115472023A (en) | Intelligent traffic light control method and device based on deep reinforcement learning | |
| Dong et al. | Battery-aware cooperative merging strategy of connected electric vehicles based on reinforcement learning with hindsight experience replay | |
| Jiang et al. | Evolution towards optimal driving strategies for large‐scale autonomous vehicles | |
| Zhong et al. | Deep Q‐Learning Network Model for Optimizing Transit Bus Priority at Multiphase Traffic Signal Controlled Intersection | |
| Kwasnicka et al. | Genetic approach to optimize traffic flow by timing plan manipulation | |
| Zhang et al. | Region-based evaluation particle swarm optimization with dual solution libraries for real-time traffic signal timing optimization | |
| Zhai et al. | Model for the cooperative obstacle‐avoidance of the automated vehicle swarm in a connected vehicles environment | |
| Zou et al. | Vehicle Trajectory Control and Signal Timing Optimization of Isolated Intersection under V2X Environment |
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 |