CN108538065A - A kind of major urban arterial highway control method for coordinating based on adaptive iterative learning control - Google Patents
A kind of major urban arterial highway control method for coordinating based on adaptive iterative learning control Download PDFInfo
- Publication number
- CN108538065A CN108538065A CN201810374660.4A CN201810374660A CN108538065A CN 108538065 A CN108538065 A CN 108538065A CN 201810374660 A CN201810374660 A CN 201810374660A CN 108538065 A CN108538065 A CN 108538065A
- Authority
- CN
- China
- Prior art keywords
- intersection
- control
- iterative learning
- split
- controller
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/081—Plural intersections under common control
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
A kind of major urban arterial highway control method for coordinating based on adaptive iterative learning control includes:A. crucial intersection is determined:For being controlled major trunk roads, the wherein maximum intersection of transport need is determined as crucial intersection;B. common signal period, split, phase difference are initialized;C. optimize crucial intersection split;D. optimize non-key intersection split;E. it recycles, every 3~5 signal periods, repeats step c and d.The present invention is with intersection object in order to control, intersection is coordinated two-by-two using the flow correlations of upstream and downstream intersection, according to real-time vehicle flow situation, the green time that each phase of signal lamp is calculated by iterative learning control method (ILC) adjusts closed loop controller parameter in real time finally by pseudo- strategy is removed.Present invention reduces the real-time calculation amounts of major trunk roads control, improve the traffic efficiency of major trunk roads, and effect is better than traditional timing control scheme, and coordinating control for major urban arterial highway provides a kind of effective ways.
Description
Technical field
The present invention relates to technical field of traffic signal control, and adaptive iterative learning control is based on more particularly, to one kind
Major urban arterial highway control method for coordinating.
Background technology
With the raising of Chinese society expanding economy and living standards of the people, more and more automobiles enter commonly
The problems such as family, traffic accident, traffic congestion, environmental pollution and energy consumption, is on the rise, hourage, touring safety, ring
Border quality and quality of life all receive the restriction of traffic.
Controlling Traffic Signals in Urban Roads be Modern City Traffic management in extremely important one side, management with
The good and bad effect that will directly affect urban highway traffic operation of controlled level.In city road network, major trunk roads subject huge
Traffic loading therefore realize that good major urban arterial highway traffic signalization is the emphasis of urban transportation unimpededization measure.
Modern City Traffic signal control theory studies have shown that realize major urban arterial highway traffic signals Dynamic coordinated control,
Especially by signal timing optimization condition is realized, regulate and control traffic flow, and it is made to be evenly distributed in major trunk roads, it will greatly
The traffic capacity of road network is improved, improves the traffic overflow phenomenon of traffic major trunk roads itself and peripheral path, is urban transportation peak
The optimal selection of phase traffic signalization.
As a kind of efficient Coordinated Urban Traffic control mode, the city trunk based on adaptive iterative learning control
Road control method for coordinating has the characteristics that:1. ensureing that the wagon flow of major trunk roads entirety is balanced, overflow to reduce major trunk roads intersection
The case where stream;2. intersection green light service efficiency higher, to improve the traffic capacity of major trunk roads;3. according to real time data
Timing scheme is adjusted, the variation of transport need can be coped with rapidly, improve the stability of road network;4. major trunk roads can be made to bear more
Big transport need improves the traffic of entire road network to reduce the pressure of road network rest part.
External major trunk roads coordinating control of traffic signals method has achievement in research, such as:J.D.C.Little first proposed
MAXBAND algorithms provide the Signal phase of one group of optimization for the major urban arterial highway for including n crossing S1 ..., Sn
Difference makes motor vehicle as much as possible once can ceaselessly pass through major trunk roads in the velocity interval of setting.N.H.Gartner
MULTIBAND is proposed on the basis of MAXBAND methods, many key properties are all improved, such as clean up time
Setting, the control of left turning vehicle realize different bandwidth etc. to different sections of highway in main line.But these achievements in research and profit not yet in effect
The day repeat property changed with transport need, and with the expansion of road network scale, calculation amount rises rapidly.
Invention content
The present invention will overcome the above-mentioned deficiency of the prior art, provide a kind of city master based on adaptive iterative learning control
The method of arterial road coordinate control improves Urban Traffic efficiency to reduce the probability that major trunk roads get congestion.
The present invention is a kind of method of the major urban arterial highway coordination control based on adaptive iterative learning control, is used for one
A urban highway traffic region for including several continuous adjacent intersections, includes the following steps:
A. crucial intersection is determined:For being controlled major trunk roads, the wherein maximum intersection of transport need is determined as key
Intersection.
B. common signal period, split, phase difference are initialized:For crucial intersection, obtained according to Webster methods
The intersection signal period is obtained, and as the intersection common signal period;Each intersection is all made of four multiphase traffic time allocation schemes,
Its phase flow-rate ratio is pressed respectively calculates initial split;Simultaneously major trunk roads are calculated using road section length divided by road average-speed
Phase difference between Adjacent Intersections.
C. optimize crucial intersection split:According to real time traffic data, iterative learning is determined using pseudo- control method is gone
Then the closed-loop control rate of control utilizes the error of previous iteration and the error of current iteration, uses Open-closed-loop iterative learning
Control method optimizes split.
D. optimize non-key intersection split:Since the Adjacent Intersections of crucial intersection, coordinate two-by-two, it will be upper
Intersection is swum as master, downstream intersection is used as from crossing, is carried out principal and subordinate and is coordinated control design case, is sequentially completed non-key
The Split Optimization of intersection.
E. it recycles, every 3~5 signal periods, repeats step c and d.
The present invention is in limited control as a kind of major urban arterial highway control method for coordinating, step c, the optimization aim of d
In time [0, K], make the roadway occupancy of each phase key flow in crucial intersectionIt is intended to ideal occupation rate od, and make
The roadway occupancy of wagon flow is intended to the roadway occupancy that master corresponds to flow direction on non-key intersection major trunk roads direction, i.e.,
It is as follows to the algorithm steps of Split Optimization in step c:
1) closed loop controller for going pseudo- strategy to determine iterative learning control is utilized
A candidate controller parameter set is determined firstSo that wherein each parameter is corresponding
Controller ensures corresponding iterative learning control convergence.Then it determines and goes in pseudo- strategy to correspond to each candidate parameter
The computational methods of the virtual reference of controller:
Finally determine the performance indicator of each candidate controller:
Wherein α and β is setting vector.It is chosen from candidate controller parameter set maximumIt calculates it and corresponds to control
The virtual reference of deviceAnd performance indicatorIf candidate's controller meets performance indicator, which is non-puppet
Control system is added in controller, if not satisfied, then selecting maximum one to be counted in remaining candidate controller parameter
It calculates, until there is the corresponding controller of candidate parameter to meet performance indicator.
2) according to the calculating for going the controller that pseudo- strategy obtains to carry out crucial intersection green time, wherein iterative learning
The law of learning of control is set as:
Wherein un(k) it is the green time in k-th of sampling period of nth iteration, en(k) it is k-th of nth iteration process
The error of sampling instant,For Open-loop iterative learning control part,Learn control section for iterative,
For closed-loop learning control rate, koLearn control rate for open loop.
It is more prominent for urban transport problems, and aorta of the major urban arterial highway as urban transportation, traffic loading is not
Increased present situation of breaking rationally utilizes existing road infrastructure, reduction to gather around by coordinating the signal timing dial of major urban arterial highway
Stifled odds.The present invention with intersection object in order to control, using upstream and downstream intersection flow correlations to intersection into
Row is coordinated two-by-two, and according to real-time vehicle flow situation, each phase of signal lamp is calculated by iterative learning control method (ILC)
Green time, adjust closed loop controller parameter in real time finally by pseudo- strategy is removed.
It is an advantage of the invention that:The real-time calculation amount for reducing major trunk roads control, improves the traffic efficiency of major trunk roads,
Effect is better than traditional timing control scheme, and coordinating control for major urban arterial highway provides a kind of effective ways.
Description of the drawings
Fig. 1 is the city major trunk roads part way schematic diagram using the method for the present invention;
Specific implementation mode
Below by way of drawings and examples, the present invention is further illustrated.
The urban highway traffic area for including several continuous adjacent intersections of the method for the present invention is used as shown in Figure 1
Domain shares 3 intersections, is expressed as { 1,2,3 } with sequence of natural numbers, and wherein East and West direction road is major trunk roads, north-south road
For subsidiary road or branch, East and West direction flow is generally significantly greater than north-south.Definition is major trunk roads up direction from west toward east, by
East is westerly down direction.Each access connection traffic flow phase divides as follows:Phase 1 is that East and West direction keeps straight on and turns right;Phase 2 is east
It turns left and turns right in west;Phase 3 is that north-south keeps straight on and turns right;Phase 4 is that north and south turns left and turns right.
A kind of major urban arterial highway based on adaptive iterative learning control of the present invention coordinates the method for control, including such as
Lower step:
A. crucial intersection is determined:For being controlled major trunk roads, the wherein maximum intersection of transport need is determined as key
Intersection.
B. common signal period, split, phase difference are initialized:For crucial intersection, obtained according to Webster methods
To the intersection signal period, and as the intersection common signal period;Each intersection is all made of four multiphase traffic time allocation schemes,
Its phase flow-rate ratio is pressed respectively calculates initial split;Simultaneously major trunk roads are calculated using road section length divided by road average-speed
Phase difference between Adjacent Intersections.
C. optimize crucial intersection split:According to real time traffic data, iterative learning is determined using pseudo- control method is gone
Then the closed-loop control rate of control utilizes the error of previous iteration and the error of current iteration, uses Open-closed-loop iterative learning
Control method optimizes split.
D. optimize non-key intersection split:Since the Adjacent Intersections of crucial intersection, coordinate two-by-two, it will be upper
Intersection is swum as master, downstream intersection is used as from crossing, is carried out principal and subordinate and is coordinated control design case, is sequentially completed non-key
The Split Optimization of intersection.
E. it recycles, every 3~5 signal periods, repeats step c and d.
In step a crucial intersection select step for:
The traffic demand data { Q1, Q2, Q3 } of each intersection on controlled section is obtained, maximum one is selected
As crucial intersection, the crucial intersection of the control area as shown in Figure 1 is intersection 1.
In step c and d, the target optimized to split is to make key in limited control time [0, K]
The roadway occupancy of each phase key flow in intersectionIt is intended to ideal occupation rate od, and make non-key intersection major trunk roads
The roadway occupancy of wagon flow is intended to the roadway occupancy that master corresponds to flow direction on direction, i.e.,
The process for optimizing calculating to crucial intersection split in step c is:
1) closed loop controller for going pseudo- strategy to determine iterative learning control is utilized
A candidate controller parameter set is determined firstSo that wherein each parameter is corresponding
Controller ensures corresponding iterative learning control convergence.Then it determines and goes in pseudo- strategy to correspond to each candidate parameter
The computational methods of the virtual reference of controller:
Finally determine the performance indicator of each candidate controller:
Wherein α and β is setting vector.It is chosen from candidate controller parameter set maximumIt calculates it and corresponds to control
The virtual reference of deviceAnd performance indicatorIf candidate's controller meets performance indicator, which is non-puppet
Control system is added in controller, if not satisfied, then selecting maximum one to be counted in remaining candidate controller parameter
It calculates, until there is the corresponding controller of candidate parameter to meet performance indicator.
2) according to the calculating for going the controller that pseudo- strategy obtains to carry out crucial intersection green time, wherein iterative learning
The law of learning of control is set as:
The process optimized to the split of non-key intersection in step d is the adjacent intersection from crucial intersection
Mouthful start to coordinate the intersection on major trunk roads two-by-two, using upstream intersection as the ideal model of downstream intersection, into
Row master & slave control is sequentially completed the optimization of split, as shown in Figure 1, the Optimization Steps of the controlled area should be { 2,3 }.
Specific embodiment described herein is only an example for the spirit of the invention.It can not limited with this
The interest field of the fixed present invention.In fact, for more complicated field condition, such as there is T-shape intersection, part track
For actual conditions such as one-way roads, method of the present invention can equally be applied, as long as considering simple change flow rate calculation
Method.
Claims (3)
1. a kind of major urban arterial highway control method for coordinating based on adaptive iterative learning control, if including involvement suitable for one
The urban highway traffic region of continuous Adjacent Intersections, includes the following steps:
A. crucial intersection is determined:For being controlled major trunk roads, the wherein maximum intersection of transport need is determined as crucial intersection
Mouthful;
B. common signal period, split, phase difference are initialized:For crucial intersection, intersected according to Webster methods
The mouth signal period, and as the intersection common signal period;Each intersection is all made of four multiphase traffic time allocation schemes, presses it respectively
Phase flow-rate ratio calculates initial split;Simultaneously major trunk roads Adjacent Intersections are calculated using road section length divided by road average-speed
Between phase difference;
C. optimize crucial intersection split:According to real time traffic data, iterative learning control is determined using pseudo- control method is gone
Closed-loop control rate, then utilize previous iteration error and current iteration error, use open-closed-loop iterative learning control
Method optimizes split;
D. optimize non-key intersection split:Since the Adjacent Intersections of crucial intersection, coordinate two-by-two, upstream is intersected
Mouth is used as master, downstream intersection to be used as from crossing, carries out principal and subordinate and coordinates control design case, is sequentially completed non-key intersection
Split Optimization;
E. it recycles, every 3~5 signal periods, repeats step c and d.
2. a kind of major urban arterial highway control method for coordinating based on adaptive iterative learning control according to claim 1,
It is characterized in that:The target of optimization described in step c and step d is to make crucial intersection in limited control time [0, K]
Each phase key flow roadway occupancyIt is intended to ideal occupation rate od, and make on non-key intersection major trunk roads direction
The roadway occupancy of wagon flow is intended to the roadway occupancy that master corresponds to flow direction, i.e.,
3. a kind of major urban arterial highway control method for coordinating based on adaptive iterative learning control according to claim 1,
It is characterized in that:Described in step c is the step of optimizing calculating to split:
1) closed loop controller for going pseudo- strategy to determine iterative learning control is utilized;
A candidate controller parameter set is determined firstMake the corresponding controller of wherein each parameter
Ensure corresponding iterative learning control convergence, then determines and go in pseudo- strategy to correspond to controller for each candidate parameter
The computational methods of virtual reference:
Finally determine the performance indicator of each candidate controller:
Wherein α and β is setting vector;It is chosen from candidate controller parameter set maximumCalculate the void that it corresponds to controller
Quasi- referenceAnd performance indicatorIf candidate's controller meets performance indicator, which is unfalsified control device,
Control system is added, if not satisfied, then selecting maximum one to be calculated in remaining candidate controller parameter, until having
The corresponding controller of candidate parameter meets performance indicator;
2) according to the calculating for going the controller that pseudo- strategy obtains to carry out crucial intersection green time, wherein iterative learning controls
Law of learning is set as:
Wherein un(k) it is the green time in k-th of sampling period of nth iteration, en(k) it is k-th of the sampling of nth iteration process
The error at moment,For Open-loop iterative learning control part,Learn control section for iterative,For closed loop
Learn control rate, koLearn control rate for open loop.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810374660.4A CN108538065B (en) | 2018-04-24 | 2018-04-24 | Urban main road coordination control method based on adaptive iterative learning control |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810374660.4A CN108538065B (en) | 2018-04-24 | 2018-04-24 | Urban main road coordination control method based on adaptive iterative learning control |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108538065A true CN108538065A (en) | 2018-09-14 |
CN108538065B CN108538065B (en) | 2020-10-02 |
Family
ID=63478738
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810374660.4A Active CN108538065B (en) | 2018-04-24 | 2018-04-24 | Urban main road coordination control method based on adaptive iterative learning control |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108538065B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111047883A (en) * | 2019-12-23 | 2020-04-21 | 西南科技大学 | Traffic signal control method for key intersection and adjacent intersection |
CN111429733A (en) * | 2020-03-24 | 2020-07-17 | 浙江工业大学 | Road network traffic signal control method based on macroscopic basic graph |
CN111445694A (en) * | 2020-03-04 | 2020-07-24 | 青岛海信网络科技股份有限公司 | Festival and holiday traffic scheduling method and device based on traffic flow prediction |
CN111951574A (en) * | 2020-07-29 | 2020-11-17 | 太原理工大学 | Traffic signal self-adaptive iterative learning control method based on attenuation memory false-removing control |
CN113053120A (en) * | 2021-03-19 | 2021-06-29 | 宁波亮控信息科技有限公司 | Traffic signal lamp scheduling method and system based on iterative learning model predictive control |
CN113066295A (en) * | 2021-03-23 | 2021-07-02 | 绵阳职业技术学院 | Traffic signal lamp control method and device |
CN113362603A (en) * | 2021-07-15 | 2021-09-07 | 山东交通学院 | Regional intersection traffic control method and system based on edge calculation |
CN113936482A (en) * | 2020-06-29 | 2022-01-14 | 阿里巴巴集团控股有限公司 | Timing control method and device, electronic equipment and computer readable storage medium |
CN114333363A (en) * | 2021-12-15 | 2022-04-12 | 上海电科智能***股份有限公司 | Bottleneck intersection signal optimization method considering upstream and downstream cooperation |
CN117912272A (en) * | 2024-03-19 | 2024-04-19 | 深圳市新创中天信息科技发展有限公司 | Urban traffic signal optimization method based on AI large model |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2005048018A3 (en) * | 2003-10-23 | 2005-11-03 | Clearsight Systems Inc | Method for optimization using state functions |
JP2012078906A (en) * | 2010-09-30 | 2012-04-19 | Internatl Business Mach Corp <Ibm> | Configuration method, program and system of pid controller |
CN102842238A (en) * | 2012-08-30 | 2012-12-26 | 浙江大学 | Dynamic coordination and control method of traffic signals of urban main road |
CN103632555A (en) * | 2013-11-28 | 2014-03-12 | 东南大学 | Green wave bandwidth maximization-based artery green wave coordination control timing method |
CN106228819A (en) * | 2016-08-18 | 2016-12-14 | 广东工业大学 | The traffic signal optimization control method of a kind of multi-intersection and device |
CN106707745A (en) * | 2016-11-22 | 2017-05-24 | 东华大学 | Unfalsified control method used for tensioning link during short polyester fiber production process |
CN106971565A (en) * | 2017-04-22 | 2017-07-21 | 高新兴科技集团股份有限公司 | A kind of regional traffic boundary Control based on Internet of Things and induction Synergistic method and system |
-
2018
- 2018-04-24 CN CN201810374660.4A patent/CN108538065B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2005048018A3 (en) * | 2003-10-23 | 2005-11-03 | Clearsight Systems Inc | Method for optimization using state functions |
JP2012078906A (en) * | 2010-09-30 | 2012-04-19 | Internatl Business Mach Corp <Ibm> | Configuration method, program and system of pid controller |
CN102842238A (en) * | 2012-08-30 | 2012-12-26 | 浙江大学 | Dynamic coordination and control method of traffic signals of urban main road |
CN103632555A (en) * | 2013-11-28 | 2014-03-12 | 东南大学 | Green wave bandwidth maximization-based artery green wave coordination control timing method |
CN106228819A (en) * | 2016-08-18 | 2016-12-14 | 广东工业大学 | The traffic signal optimization control method of a kind of multi-intersection and device |
CN106707745A (en) * | 2016-11-22 | 2017-05-24 | 东华大学 | Unfalsified control method used for tensioning link during short polyester fiber production process |
CN106971565A (en) * | 2017-04-22 | 2017-07-21 | 高新兴科技集团股份有限公司 | A kind of regional traffic boundary Control based on Internet of Things and induction Synergistic method and system |
Non-Patent Citations (3)
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》 * |
王晶 等: "基于去伪策略的间歇过程自适应迭代学习", 《中南大学学报(自然科学版)》 * |
闫飞 等: "城市交通信号的迭代学习控制及其对路网宏观基本图的影响", 《控制理论与应用》 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111047883A (en) * | 2019-12-23 | 2020-04-21 | 西南科技大学 | Traffic signal control method for key intersection and adjacent intersection |
CN111445694A (en) * | 2020-03-04 | 2020-07-24 | 青岛海信网络科技股份有限公司 | Festival and holiday traffic scheduling method and device based on traffic flow prediction |
CN111445694B (en) * | 2020-03-04 | 2022-02-01 | 青岛海信网络科技股份有限公司 | Festival and holiday traffic scheduling method and device based on traffic flow prediction |
CN111429733A (en) * | 2020-03-24 | 2020-07-17 | 浙江工业大学 | Road network traffic signal control method based on macroscopic basic graph |
CN113936482A (en) * | 2020-06-29 | 2022-01-14 | 阿里巴巴集团控股有限公司 | Timing control method and device, electronic equipment and computer readable storage medium |
CN111951574A (en) * | 2020-07-29 | 2020-11-17 | 太原理工大学 | Traffic signal self-adaptive iterative learning control method based on attenuation memory false-removing control |
CN113053120A (en) * | 2021-03-19 | 2021-06-29 | 宁波亮控信息科技有限公司 | Traffic signal lamp scheduling method and system based on iterative learning model predictive control |
CN113066295B (en) * | 2021-03-23 | 2022-05-31 | 绵阳职业技术学院 | Traffic signal lamp control method and device |
CN113066295A (en) * | 2021-03-23 | 2021-07-02 | 绵阳职业技术学院 | Traffic signal lamp control method and device |
CN113362603A (en) * | 2021-07-15 | 2021-09-07 | 山东交通学院 | Regional intersection traffic control method and system based on edge calculation |
CN114333363A (en) * | 2021-12-15 | 2022-04-12 | 上海电科智能***股份有限公司 | Bottleneck intersection signal optimization method considering upstream and downstream cooperation |
CN117912272A (en) * | 2024-03-19 | 2024-04-19 | 深圳市新创中天信息科技发展有限公司 | Urban traffic signal optimization method based on AI large model |
CN117912272B (en) * | 2024-03-19 | 2024-05-24 | 深圳市新创中天信息科技发展有限公司 | Urban traffic signal optimization method based on AI large model |
Also Published As
Publication number | Publication date |
---|---|
CN108538065B (en) | 2020-10-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108538065A (en) | A kind of major urban arterial highway control method for coordinating based on adaptive iterative learning control | |
CN109544945B (en) | Regional control phase timing optimization method based on lane saturation | |
CN108847037B (en) | Non-global information oriented urban road network path planning method | |
CN104134356B (en) | Control method of city intersection model reference self-adaptive signals | |
CN101707000B (en) | Urban road traffic multiobjective optimization control method | |
CN106297329A (en) | A kind of signal timing dial adaptive optimization method of networking signals machine | |
CN102982688B (en) | Regional traffic signal control method based on arterial road coordination priority | |
CN105185130B (en) | A kind of signal coordinating control method between intersection under variable period | |
CN104200680B (en) | The coordinating control of traffic signals method of arterial street under supersaturation traffic behavior | |
CN105046987A (en) | Road traffic signal lamp coordination control method based on reinforcement learning | |
CN105788298B (en) | A kind of method and device of two-way green wave control | |
CN109035767A (en) | A kind of tide lane optimization method considering Traffic Control and Guidance collaboration | |
CN110136455A (en) | A kind of traffic lights timing method | |
CN104123849A (en) | Adjacent intersection bidirectional linkage control method in consideration of dynamic queuing length | |
CN104485004A (en) | Signal control method combining main trunk road bidirectional dynamic green wave and secondary trunk road semi-induction | |
CN103794065B (en) | Active urban road area signal timing parameter collaborative optimization method | |
CN104916142A (en) | Adaptive intersection traffic signal control method of trunk road priority | |
CN108734973A (en) | A kind of phase of main line two-way green wave-signal synthesis optimization method | |
CN103996289A (en) | Flow-speed matching model and travel time forecasting method and system | |
CN111951549A (en) | Self-adaptive traffic signal lamp control method and system in networked vehicle environment | |
CN114038212A (en) | Signal lamp control method based on two-stage attention mechanism and deep reinforcement learning | |
CN109872531B (en) | Method for constructing optimal control objective function of road network controlled by road traffic signals | |
CN103942968A (en) | Intelligent traffic light dispatching system and method based on traffic flow sensing | |
CN111951574A (en) | Traffic signal self-adaptive iterative learning control method based on attenuation memory false-removing control | |
WO2023035666A1 (en) | Urban road network traffic light control method based on expected reward estimation |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |