CN106251649A - Based on alleviating the control strategy of intersection congestion under hypersaturated state - Google Patents
Based on alleviating the control strategy of intersection congestion under hypersaturated state Download PDFInfo
- Publication number
- CN106251649A CN106251649A CN201610648649.3A CN201610648649A CN106251649A CN 106251649 A CN106251649 A CN 106251649A CN 201610648649 A CN201610648649 A CN 201610648649A CN 106251649 A CN106251649 A CN 106251649A
- Authority
- CN
- China
- Prior art keywords
- phase place
- represent
- crossing
- alleviating
- max
- 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
Classifications
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of based on alleviating the control strategy of intersection congestion under hypersaturated state, belong to the technical field of intelligent transportation.First described control method considers by setting up a kind of multi objective control model, thus is effectively improved traffic circulation efficiency.The relation connected each other for multiple optimization aim and mutually restrict, the combining adaptive method of weighting is the Comprehensive Control model that three optimization aim right of distribution recuperations are arrived, optimum timing is solved according to improved adaptive GA-IAGA, improve search capability and also ensure the accuracy of timing, it is achieved alleviate the traffic jam of destination object.For fixing the scheme of timing scheme and former genetic algorithm in prior art, this method optimizes control effect, improves traffic circulation efficiency.
Description
Technical field
The present invention relates to a kind of based on alleviating the control strategy of urban road intersection congestion under hypersaturated state, belong to
Technical field in intelligent transportation.
Background technology
Along with the development of urban economy, vehicle guaranteeding organic quantity presents the state of quickly increase, and urban road increases limited
And slowly, causing the normal traffic trip in city to be seriously obstructed, traffic congestion takes place frequently, and vehicle transport efficiency is remarkably decreased, impact
The normal trip of urbanite, govern expanding economy.Meanwhile, incident vehicle accident, environmental pollution and the energy
Shortage further governs the development in city.The essence of traffic congestion be the demand run of supply and the vehicle of urban road not
Balance, is the demand contradiction that is more than supply, and the method solving this contradiction can be examined in terms of improving supply and demand for control two
Consider.But, improving the supply of road infeasible, main cause has: (1) road infrastructure construction needs to take basis, city
Space, and the basic space in city is rare limited resources, it is impossible to infinitely take;(2) the road infrastructure construction period is relatively
Long, existing traffic jam issue can not be fast and effeciently alleviated in the construction relying on road;(3) construction of road infrastructure
Relatively costly, due to economic restriction, it is impossible to the newly-built road of long-term investment.Based on above-mentioned analysis, by newly-built road with
Improve supply and solve imbalance between supply and demand infeasible, therefore, be only capable of alleviating traffic congestion by demand for control, and control traffic
The effective method of demand is traffic administration and control.Take effective signal control measure, can be from most starting to produce traffic congestion
Crossing start with, identify its traffic congestion state, and take effective measures in time, alleviate the shape that blocks up of local crossing
State, it is to avoid it has influence on upstream and downstream crossing.
In urban transport problems, 50%~80% results from crossing and surrounding place thereof, and motor vehicles is when urban district has 1/3
Between consume on signalized intersections, the delay time at stop of 80%~90% is caused by signalized crossing.By to signal lights
Optimal control can improve operational efficiency, reduce the delay time at stop, avoids traffic to gather around, reduces air pollution and environmental disruption.Signal
From the point of view of the purpose that crossing controls is exactly on the one hand to crossing user, delay to be made, stop, queue up the fewest;Another
From the point of view of aspect is to the crossing efficiency of management, the traffic capacity of crossing to be made is the biggest.The most conventional signal timing dial is most
Research is all under non-saturation conditions, to be delayed minimum to determine cycle duration or by traffic delay and stop frequency comprehensively for one
Individual performance indications.Consider the real time status of crossing user and crossing herein, choose mean delay, queue length and
The traffic capacity, as optimization aim, establishes the signalized intersections multi objective control model under supersaturated condition.
Traditional signal timing dial method is, by optimizing algorithm, specific crossing Controlling model is carried out optimizing, obtains
The signal allocative decision of excellent timing.Conventional method has climbing method, particle cluster algorithm, genetic algorithm etc..Researcher is typically chosen
Simplest timing method carries out signal timing dial, because road traffic condition is complex under supersaturation situation, utilizes timing method
The timing result obtained can cause mean delay and queue length bigger than normal, and the traffic capacity the most significantly strengthens, it is impossible to have
Effect alleviates blocking up of crossing;For overcoming the problems referred to above, choose genetic algorithm and Controlling model is carried out optimizing timing, genetic algorithm
Complicated traffic flow data can be carried out overall situation repeated searching thus obtain the most accurate timing result.
Summary of the invention
The technical problem to be solved is to provide a kind of based on alleviating urban road intersection under hypersaturated state
The control strategy of congestion.
The present invention solves above-mentioned technical problem by the following technical solutions:
The present invention provides a kind of based on alleviating the control method of intersection congestion under hypersaturated state, specifically walks
Rapid as follows:
Step 1, according to intersection vehicles running orbit model, chooses mean delay, queue length and traffic capacity conduct
Optimization aim, sets up crossing Comprehensive Control model, particularly as follows:
s.t.tmin< ti< tmax
λmin< λi< λmax
Tmin< T < Tmax
In formula, f (λi, T) and represent control function, n represents number of phases;λiRepresent the split of i-th phase place, λminAnd λmaxRespectively
Represent λiMinimum and maximum split in restriction range;T represents the signal period duration of crossing,tssRepresent
The lost time of phase place, TminAnd TmaxRepresent the minimum and maximum duration in T restriction range respectively;diRepresent the average of i-th phase place
It is delayed,DiFor the total delay of i-th phase place,
liRepresent the queuing vehicle number of i-th phase place initial time, qiRepresent the vehicle arriving rate of i-th phase place, siRepresent i-th phase
The saturation volume rate of position;NiRepresent the queue length of i-th phase place,qi(τ) when representing τ
Carve the vehicle arriving rate of i-th phase place, si(τ) saturation volume rate of τ moment i-th phase place is represented;QiRepresent the logical of i-th phase place
Row ability, Qi=siλi;It is respectively i-th phase place correspondence mean delay, queue length and the power of the traffic capacity
Weight;tiRepresent the Effective Green Time duration of i-th phase place, tminAnd tmaxRepresent t respectivelyiMinimum and maximum in restriction range is effective
Long green light time;XiRepresent the saturation of i-th phase place, XminAnd XmaxRepresent X respectivelyiMinimum and maximum in restriction range is saturated
Degree;
Step 2, the crossing Comprehensive Control model using genetic algorithm to obtain step 1 solves, and enters crossing
Row signal timing dial.
As the further prioritization scheme of the present invention, described crossing is the crossing of cross four phase place.
As the further prioritization scheme of the present invention, according to the change of crossing each phase place flow-rate ratio, use self adaptation power
Weight method is that mean delay, queue length and the traffic capacity carry out weight distribution.
As the further prioritization scheme of the present invention, i-th phase place correspondence mean delay, queue length and the traffic capacity
WeightWherein,siRepresent i-th phase
The saturation volume rate of position, yiRepresenting the flow-rate ratio of i-th phase place, Y represents the flow-rate ratio sum of four phase places, and α represents the dimension factor.
As the further prioritization scheme of the present invention, use genetic algorithm that crossing Comprehensive Control model is solved
Time, in a replication process, by comparing fitness size, select fitness high as requiredIndividual inheritance to of future generation.
The present invention uses above technical scheme compared with prior art, has following technical effect that
(1) Model for Multi-Objective Optimization complicated state in view of reality road traffic is set up, by Signal phase
Scheme and the adjustment of timing, it is achieved the Comprehensive Control to urban traffic flow, using adaptive weighting method is that three optimization aim are divided
Join weight, can automatically distribute weight according to the change of actual traffic stream, carry out between the optimal value of each sub-goal subsequently point
Join, effectively overcome the coordination problem between multiple target;
(2), for compared to fixing the scheme of timing scheme and former genetic algorithm in prior art, this method optimizes
Control effect, improve traffic circulation efficiency.
Accompanying drawing explanation
Fig. 1 is crossing physical model and crossing phase place phase sequence figure, and wherein, (a) is crossing physical model, (b)
It it is crossing phase place phase sequence figure.
Fig. 2 is the intersection vehicles running orbit illustraton of model of multi-goal optimizing function in the derivation present invention.
Fig. 3 is the test function figure verifying improved adaptive GA-IAGA of the present invention.
Fig. 4 is to utilize test function checking difference in the present inventionThe simulated effect comparison diagram of improved adaptive GA-IAGA.
Fig. 5 is the control effectiveness comparison figure that in the application present invention, improved adaptive GA-IAGA and former genetic algorithm obtain.
Detailed description of the invention
Below in conjunction with the accompanying drawings and technical scheme is described in further detail by specific embodiment:
The crossing that crossing is typical cross four phase place of research in the present invention, four phase places are respectively A, B, C, D,
The most corresponding i=1 ..., j ..., n, n=4.Each access mouth direction all have left-hand rotation, keep straight on, wagon flow of turning right, due to right-hand rotation wagon flow
Typically no single signal controls phase place, does not the most consider right-hand rotation wagon flow.Crossing physical model and crossing phase place phase
Sequence is as shown in Figure 1.
Because reality traffic conditions is complex, need to consider to choose suitably control target and more accurately reflect crossing situation.
First considering the supersaturation situation of crossing, needing to increase the whole signal period expands the traffic capacity;Consider crossing simultaneously
The interests of user, delay time at stop and queue length all should be less.Therefore, mean delay, queue length and the traffic capacity are chosen
As optimization aim.Wherein, optimization object function is derived according to Fig. 2.
The analysis of oversaturated intersection is proceeded by, it is assumed that when initiateing with the green light of crossing phase place A from first cycle
Carve as initial time, i.e. t=0.If the traffic data of the two of a phase place imports is identical, so the present invention only analyzes one
The single direction traffic flow of phase place.Perform an analysis the period with phase place A Effective Green Time duration first below, with post analysis whole signal week
Phase, derive optimization object function.
1) using phase place A Effective Green Time duration as analyzing the period:
It is analyzed as a example by the access mouth Through Lane of phase place A east, crossing.In the time period of [0, t], arrive vehicle
Number isLeaving vehicle number is
At moment t (0 < t < t1) time queuing vehicle number be:
In formula, l1Queuing vehicle number for phase place A initial time.
Delay time at stop during green light is:
Being detained delay time at stop of producing under its excess-three phase place of vehicle number is:
Therefore, can be at the total delay of phase place A after the whole signal period terminates:
The crossing phase place A traffic capacity during the whole signal period:
Q1=s1λ1;
Signal period terminates rear queue length:
2) (four corresponding four kinds of scopes of phase place, corresponding moment t has four scopes (0, t to whole phase cycling1)、(t1,
t1+t2)、(t1+t2,t1+t2+t3)、(t1+t2+t3,t1+t2+t3+t4), so moment t scope is)
In the momentTime queuing vehicle number be:
Delay time at stop during green light is:
Being detained delay time at stop of producing under its excess-three phase place of vehicle number is:
Therefore, can be at the total delay after the whole signal period terminates:
Mean delay:
The crossing phase place i traffic capacity during the whole signal period:
Qi=siλi
Signal period terminates rear queue length:
Subsequently, design adaptive weighting method according to the change of crossing each phase place flow-rate ratio and be controlled the weight of target
Distribution.
Consider the supersaturation situation of crossing, i.e. when the vehicle flowrate of crossing is bigger, need to increase the whole signal period
Expand the traffic capacity;Consider the interests of crossing user simultaneously, i.e. when the vehicle flowrate of crossing is less, the delay time at stop and
Queue length all should reduce.Therefore for the flow-rate ratio situation of phase place each in crossing, when the flow-rate ratio of certain phase place is relatively big, then table
Bright phase place vehicle flowrate is relatively big, passes through efficiency for being effectively improved wagon flow, need to increase the phase place traffic capacity, distributes to current energy accordingly
The weight of the control target of power is bigger, and the weight that mean delay, queue length are assigned to is less;Flow-rate ratio when certain phase place
Less, on the contrary then consider.
The most corresponding mean delay, queue length and the weight of the traffic capacity, wherein, α represents the dimension factor, is constant.
The Comprehensive Control model simultaneously obtained under the object of four phase place Single Intersections need to meet following constraints, with
Ensure the stability of whole system.The Effective Green Time duration summation of the most each phase place need to be equal to cycle duration, if each phase place is effective
Long green light time summation is more than cycle duration, does not meets reality, and the most whole crossing system plays pendulum;As each in obtain
The Effective Green Time duration summation of phase place is less than cycle duration, then it represents that four actual phase place crossings are long for lost time, vehicle
Traffic efficiency is relatively low, causes whole crossing system to play pendulum.
Constraints formula is as follows:
Wherein, tssRepresent the lost time of phase place.
Setting the error that e represents that the Effective Green Time duration of phase place and total cycle duration are compared, expression formula is as follows:
Choosing performance indications after analysis is:
When e more levels off to 0, and whole system tends towards stability.
After being three optimization aim distribution weights, the Comprehensive Control model obtained (includes control function and constraint as follows
Condition):
s.t.tmin< ti< tmax
λmin< λi< λmax
Tmin< T < Tmax
After obtaining Comprehensive Control model, with optimized algorithm it need to be solved and carry out signal timing dial.
Choose simple timing method and carry out signal timing dial, because actual traffic stream situation is complex, utilize timing method
The timing result obtained can cause mean delay and queue length bigger than normal, and the traffic capacity the most significantly strengthens, it is impossible to have
Effect alleviates blocking up of crossing;Choose genetic algorithm for described problem and Controlling model is solved timing, it is possible to complexity
Traffic flow data carry out the overall situation repeated searching thus obtain the most accurate timing result.
Genetic algorithm mainly includes parameter coding, solves fitness, replicates, intersects, makes a variation and the operation such as termination.The most first
Using non-Revised genetic algorithum (representing with GA below) to carry out optimum signal timing, in GA, proportion of utilization selection method, two point are handed over
Fork and uniform variation carry out replicating, intersecting and mutation operation respectively.Find that the ratio selection method in GA has certain defect herein,
Make improvements the genetic algorithm after being improved (representing with MGA below) subsequently.
The basic thought of the ratio selection method in GA is based on individual selected probability and is directly proportional to its fitness size
Relation.If setting in GA group size as M, the fitness of individual Ι is fΙ, then individual probability selected for Ι is as follows:
The probability understanding the highest individuality of fitness selected is the biggest.Where there is selection defect, because method being random
Choose, the individuality that fitness is high may be omitted in a replication process, cause the Select Error in reproduction process bigger.
Therefore, the present invention is that the problem overcoming the Select Error of ratio selection method bigger has made improvement, obtains elite choosing
Selecting method, the elitist selection method after improvement is compared to former method can improve its accuracy selected, and reduces its Select Error, simultaneously
Improve the MGA ability of searching optimum at signal timing dial.
This patent carries out method improvement on the basis of ratio selection method, in reproduction process, by comparing fitness size,
Filter the individuality that in whole colony, part fitness is less, select the elite individual inheritance that residue fitness is high to of future generation.If
In reproduction process, heredity to follow-on individuality isBelow with test function TF (Test Function), the property to MGA
Can test.
The expression formula of test function is as follows:
f(x1,x2)=21.5+x1sin(4πx1)+x2sin(20πx2)
-3.0≤x1≤12.1
-4.1≤x2≤5.8
Wherein, f (x1,x2) represent test function, x1And x2Represent the variable in test function.
The fitness function of test function is as follows:
F(x1,x2)=cmax1-f(x1,x2)
Wherein, F (x1,x2) represent test function fitness function;cmax1Represent a sufficiently large constant, the present invention
Middle selection cmax1=40.
As it is shown on figure 3, wherein, X-axis represents variable x to test function1, Y-axis represents variable x2, Z axis represents test function value.
By the genetic algorithm (MGA) after improving, test function is carried out optimizing, choose four hereinValue emulates
Relatively,Being respectively 80%, 60%, 40% and 20%, simulated effect comparative result is as shown in Figure 4.
By the simulation result of Fig. 4, can be proper60% compared to working asWhen 80%, it emulates effect
Really curve shows and can more quickly obtain optimal value.Again because the optimization problem of genetic algorithm is that object function maximum is asked
Topic, fitness function value is the biggest i.e. the least when test function value, shows that the optimizing ability of algorithm is the strongest.In comparison diagram 2 four
Simulation curve, when60%, the optimizing ability of the algorithm (MGA) after improvement compared to MGA (80%)
Strengthen.To sum up analyze, whenTime, algorithm has stronger optimizing ability and more preferable rapidity, because of
This chooses hereinIndividuality as retain elite individuality replicate.
Comprehensive Control model because obtaining above includes control function and constraints, adapts at genetic algorithm for solving
Need to consider constraints when spending, using Means of Penalty Function Methods to convert Comprehensive Control function herein is unconstrained problem function, obtains
Fitness function is as follows:
Wherein, cmax2Being a sufficiently large constant, η represents penalty factor.
Fig. 5 is to utilize MATLAB software, the control obtained in conjunction with improved adaptive GA-IAGA as herein described and former genetic algorithm
Effectiveness comparison figure processed.
As shown in table 1 is to utilize the genetic algorithm after improving in timing method, genetic algorithm and the present invention to carry out most preferably
The comparison of timing result.
Genetic algorithm after table 1: timing method, genetic algorithm and improvement carries out the comparison of optimal timing result
According to simulation result, by three kinds of algorithm gained optimal timing results of contrast, the timing of improved adaptive GA-IAGA than
Other two method more preferably, demonstrates the practicality of innovatory algorithm.
The technological merit of the present invention is as follows:
(1) Model for Multi-Objective Optimization complicated state in view of reality road traffic is set up, by Signal phase
Scheme and the adjustment of timing, it is achieved the Comprehensive Control to urban traffic flow, using adaptive weighting method is that three optimization aim are divided
Join weight, can automatically distribute weight according to the change of actual traffic stream, carry out between the optimal value of each sub-goal subsequently point
Join, effectively overcome the coordination problem between multiple target;
(2), for compared to fixing the scheme of timing scheme and former genetic algorithm in prior art, this method optimizes
Control effect, improve traffic circulation efficiency.
The above, the only detailed description of the invention in the present invention, but protection scope of the present invention is not limited thereto, and appoints
What is familiar with the people of this technology in the technical scope that disclosed herein, it will be appreciated that the conversion expected or replacement, all should contain
Within the scope of the comprising of the present invention, therefore, protection scope of the present invention should be as the criterion with the protection domain of claims.
Claims (5)
1. based on alleviating the control method of intersection congestion under hypersaturated state, it is characterised in that concrete steps are such as
Under:
Step 1, according to intersection vehicles running orbit model, chooses mean delay, queue length and the traffic capacity as optimization
Target, sets up crossing Comprehensive Control model, particularly as follows:
s.t.tmin< ti< tmax
λmin< λi< λmax
Tmin< T < Tmax
In formula, f (λi, T) and represent control function, n represents number of phases;λiRepresent the split of i-th phase place, λminAnd λmaxRepresent λ respectivelyi
Minimum and maximum split in restriction range;T represents the signal period duration of crossing,tssRepresent phase place
Lost time, TminAnd TmaxRepresent the minimum and maximum duration in T restriction range respectively;diRepresent the mean delay of i-th phase place,DiFor the total delay of i-th phase place,
liRepresent the queuing vehicle number of i-th phase place initial time, qiRepresent the vehicle arriving rate of i-th phase place, siRepresent i-th phase
The saturation volume rate of position;NiRepresent the queue length of i-th phase place,qi(τ) when representing τ
Carve the vehicle arriving rate of i-th phase place, si(τ) saturation volume rate of τ moment i-th phase place is represented;QiRepresent the logical of i-th phase place
Row ability, Qi=siλi;It is respectively i-th phase place correspondence mean delay, queue length and the power of the traffic capacity
Weight;tiRepresent the Effective Green Time duration of i-th phase place, tminAnd tmaxRepresent t respectivelyiMinimum and maximum in restriction range is effective
Long green light time;XiRepresent the saturation of i-th phase place, XminAnd XmaxRepresent X respectivelyiMinimum and maximum in restriction range is saturated
Degree;
Step 2, the crossing Comprehensive Control model using genetic algorithm to obtain step 1 solves, and crossing is carried out letter
Number timing.
The most according to claim 1 based on alleviating the control method of intersection congestion under hypersaturated state, its
Being characterised by, described crossing is the crossing of cross four phase place.
The most according to claim 1 based on alleviating the control method of intersection congestion under hypersaturated state, its
It is characterised by, according to the change of crossing each phase place flow-rate ratio, uses adaptive weighting method to be mean delay, queue length and lead to
Row ability carries out weight distribution.
The most according to claim 3 based on alleviating the control method of intersection congestion under hypersaturated state, its
It is characterised by, i-th phase place correspondence mean delay, queue length and the weight of the traffic capacityWherein,siRepresent the saturation volume rate of i-th phase place, yiRepresent i-th
The flow-rate ratio of individual phase place, Y represents the flow-rate ratio sum of four phase places, and α represents the dimension factor.
The most according to claim 1 based on alleviating the control method of intersection congestion under hypersaturated state, its
It is characterised by, when using genetic algorithm that crossing Comprehensive Control model is solved, in a replication process, by comparing adaptation
Degree size, selects fitness high as requiredIndividual inheritance to of future generation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610648649.3A CN106251649A (en) | 2016-08-09 | 2016-08-09 | Based on alleviating the control strategy of intersection congestion under hypersaturated state |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610648649.3A CN106251649A (en) | 2016-08-09 | 2016-08-09 | Based on alleviating the control strategy of intersection congestion under hypersaturated state |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106251649A true CN106251649A (en) | 2016-12-21 |
Family
ID=58079122
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610648649.3A Pending CN106251649A (en) | 2016-08-09 | 2016-08-09 | Based on alleviating the control strategy of intersection congestion under hypersaturated state |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106251649A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107067768A (en) * | 2017-04-24 | 2017-08-18 | 河南省城乡规划设计研究总院有限公司 | A kind of supersaturated traffic flow self-organizing signal control method in city |
CN109446630A (en) * | 2018-10-23 | 2019-03-08 | 宁夏大学 | Multiple target water resource optimal allocation method based on Hybrid Particle Swarm |
CN109935079A (en) * | 2019-03-19 | 2019-06-25 | 吉林大学 | Intersection supply and demand cooperates with optimal control method |
CN110415519A (en) * | 2019-07-30 | 2019-11-05 | 黄卫 | A kind of regional traffic signal method for real-time optimization control based on track of vehicle data |
CN110491143A (en) * | 2019-08-25 | 2019-11-22 | 苏州布德泽信息科技有限公司 | A kind of current multi-target optimal design method of traffic |
CN110956826A (en) * | 2019-11-21 | 2020-04-03 | 浙江大华技术股份有限公司 | Method and device for generating traffic signal timing scheme and storage medium |
CN113204734A (en) * | 2021-03-31 | 2021-08-03 | 东南大学 | Queuing theory-based system modeling method for multi-scale supply and demand relationship of traffic system in oversaturated state |
CN113362618A (en) * | 2021-06-03 | 2021-09-07 | 东南大学 | Multi-mode traffic adaptive signal control method and device based on strategy gradient |
CN114255590A (en) * | 2021-12-17 | 2022-03-29 | 重庆市城投金卡信息产业(集团)股份有限公司 | Traffic operation analysis method based on RFID data |
CN114973695A (en) * | 2021-02-26 | 2022-08-30 | 长沙智能驾驶研究院有限公司 | Vehicle priority passing control method and related equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009193475A (en) * | 2008-02-16 | 2009-08-27 | Masahiro Watanabe | Traffic control method |
CN101707000A (en) * | 2009-10-26 | 2010-05-12 | 北京交通大学 | Urban road traffic multiobjective optimization control method |
CN103927890A (en) * | 2014-04-29 | 2014-07-16 | 北京建筑大学 | Artery coordination signal control method based on dynamic O-D matrix estimation |
CN104021686A (en) * | 2014-06-26 | 2014-09-03 | 广东工业大学 | Traffic coordination control method of multiple intersections |
-
2016
- 2016-08-09 CN CN201610648649.3A patent/CN106251649A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009193475A (en) * | 2008-02-16 | 2009-08-27 | Masahiro Watanabe | Traffic control method |
CN101707000A (en) * | 2009-10-26 | 2010-05-12 | 北京交通大学 | Urban road traffic multiobjective optimization control method |
CN103927890A (en) * | 2014-04-29 | 2014-07-16 | 北京建筑大学 | Artery coordination signal control method based on dynamic O-D matrix estimation |
CN104021686A (en) * | 2014-06-26 | 2014-09-03 | 广东工业大学 | Traffic coordination control method of multiple intersections |
Non-Patent Citations (2)
Title |
---|
唐瑾: "过饱和路***通信号控制动态规划优化模型", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
李瑞敏: "《城市交通信号控制》", 30 November 2015, 清华大学出版社 * |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107067768B (en) * | 2017-04-24 | 2019-08-16 | 河南省城乡规划设计研究总院有限公司 | A kind of city supersaturation traffic flow self-organizing signal control method |
CN107067768A (en) * | 2017-04-24 | 2017-08-18 | 河南省城乡规划设计研究总院有限公司 | A kind of supersaturated traffic flow self-organizing signal control method in city |
CN109446630A (en) * | 2018-10-23 | 2019-03-08 | 宁夏大学 | Multiple target water resource optimal allocation method based on Hybrid Particle Swarm |
CN109935079A (en) * | 2019-03-19 | 2019-06-25 | 吉林大学 | Intersection supply and demand cooperates with optimal control method |
CN110415519B (en) * | 2019-07-30 | 2020-07-07 | 黄卫 | Regional traffic signal real-time optimization control method based on vehicle track data |
CN110415519A (en) * | 2019-07-30 | 2019-11-05 | 黄卫 | A kind of regional traffic signal method for real-time optimization control based on track of vehicle data |
CN110491143A (en) * | 2019-08-25 | 2019-11-22 | 苏州布德泽信息科技有限公司 | A kind of current multi-target optimal design method of traffic |
CN110956826B (en) * | 2019-11-21 | 2021-07-13 | 浙江大华技术股份有限公司 | Method and device for generating traffic signal timing scheme and storage medium |
CN110956826A (en) * | 2019-11-21 | 2020-04-03 | 浙江大华技术股份有限公司 | Method and device for generating traffic signal timing scheme and storage medium |
CN114973695A (en) * | 2021-02-26 | 2022-08-30 | 长沙智能驾驶研究院有限公司 | Vehicle priority passing control method and related equipment |
CN114973695B (en) * | 2021-02-26 | 2023-09-26 | 长沙智能驾驶研究院有限公司 | Vehicle priority passing control method and related equipment |
CN113204734A (en) * | 2021-03-31 | 2021-08-03 | 东南大学 | Queuing theory-based system modeling method for multi-scale supply and demand relationship of traffic system in oversaturated state |
CN113204734B (en) * | 2021-03-31 | 2024-04-09 | 东南大学 | System modeling method for traffic system multi-scale supply-demand relation in supersaturated state based on queuing theory |
CN113362618A (en) * | 2021-06-03 | 2021-09-07 | 东南大学 | Multi-mode traffic adaptive signal control method and device based on strategy gradient |
CN113362618B (en) * | 2021-06-03 | 2022-08-09 | 东南大学 | Multi-mode traffic adaptive signal control method and device based on strategy gradient |
CN114255590A (en) * | 2021-12-17 | 2022-03-29 | 重庆市城投金卡信息产业(集团)股份有限公司 | Traffic operation analysis method based on RFID data |
CN114255590B (en) * | 2021-12-17 | 2023-04-25 | 重庆市城投金卡信息产业(集团)股份有限公司 | Traffic operation analysis method based on RFID data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106251649A (en) | Based on alleviating the control strategy of intersection congestion under hypersaturated state | |
CN108510764B (en) | Multi-intersection self-adaptive phase difference coordination control system and method based on Q learning | |
CN104282162B (en) | A kind of crossing self-adapting signal control method based on real-time vehicle track | |
CN103996289B (en) | A kind of flow-speeds match model and Travel Time Estimation Method and system | |
CN106846842A (en) | Urban arterial road coordinate control optimization method based on multi-period control program | |
CN111899534A (en) | Traffic light intelligent control method based on road real-time capacity | |
Liu et al. | Traffic signal timing optimization for isolated intersections based on differential evolution bacteria foraging algorithm | |
CN104021685A (en) | Traffic control method of intersections containing mixed traffic flows | |
CN113112823A (en) | Urban road network traffic signal control method based on MPC | |
CN104809890A (en) | Traffic signal timing optimization method based on principal component analysis and local search improvement orthogonality genetic algorithm | |
Boukerche et al. | Feco: An efficient deep reinforcement learning-based fuel-economic traffic signal control scheme | |
AU2021103022A4 (en) | A Method of Controlling Traffic Light Based on Fog Computing and Reinforcement Learning | |
Li et al. | Cellular automata model for unsignalized T-shaped intersection | |
Wu et al. | Traffic signal networks control optimize with PSO algorithm | |
CN113409576B (en) | Bayesian network-based traffic network dynamic prediction method and system | |
Li et al. | A perimeter control strategy for oversaturated network preventing queue spillback | |
Jiang et al. | Traffic signal light control model based on evolutionary programming algorithm optimization BP neural network | |
Dong et al. | Analysis and control of intelligent traffic signal system based on adaptive fuzzy neural network | |
Yang et al. | Acyclic real-time traffic signal control based on a genetic algorithm | |
CN115472023A (en) | Intelligent traffic light control method and device based on deep reinforcement learning | |
Ma et al. | Adaptive coordinated traffic control for arterial intersections based on reinforcement learning | |
Ma et al. | Optimization Method of Cycle Time in Signalized Intersection | |
Wei et al. | Intersection signal control approach based on pso and simulation | |
Zhonghe et al. | Consensus feedback control for urban road traffic networks | |
Qiao et al. | Optimization of bidirectional green wave of traffic systems on urban arterial road |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20161221 |