CN104882006B - Message-based complex network traffic signal optimization control method - Google Patents
Message-based complex network traffic signal optimization control method Download PDFInfo
- Publication number
- CN104882006B CN104882006B CN201410318468.5A CN201410318468A CN104882006B CN 104882006 B CN104882006 B CN 104882006B CN 201410318468 A CN201410318468 A CN 201410318468A CN 104882006 B CN104882006 B CN 104882006B
- Authority
- CN
- China
- Prior art keywords
- node
- network
- traffic
- vehicle
- control method
- 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.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a message-based complex network traffic signal optimization control method, which comprises the steps of: establishing a traffic network model, and initializing parameters of the traffic network model; initializing signal lamp switching time of each network node and time for a vehicle to arrive at each node; establishing a traffic network system delay function, and establishing message passing functions among the network nodes; calculating time for the vehicle to arrive at the nodes; solving a minimal value of the traffic network system delay function, arriving at new values for establishing the message passing functions among the network nodes, and transmitting the values to upstream and downstream nodes; and returning to the step 3 to carry out loop iteration processing, and stopping the loop iteration when an optimal state is achieved. According to the message-based complex network traffic signal optimization control method provided by the invention, traffic signal control and vehicle driving path need to be optimized in a complex regional traffic system, so as to realize management and control on urban road traffic, and the message-based complex network traffic signal optimization control method has the advantages of being stable and reliable, high in environmental adaptability and high in real-time performance of algorithms, and having higher system optimization efficiency.
Description
Technical field
The present invention relates to intelligent transport system field, specifically a kind of message based complex network traffic signal are excellent
Change control method.
Background technology
In City road traffic system, transportation network is typically made up of road and the elementary cell of crossing two, road
It is the mid portion for connecting crossing, is the carrier that vehicle is spatially moved;Crossing is then the important component part of road,
Effect is relatively special, but realizes that vehicle is travelled to different directions;However, coordinating traffic circulation just because of crossing
During, bring numerous inconvenience, Traffic Capacity of Urban Road mainly to be coordinated by Intersections to the smooth operation of traffic
Control ability affects, therefore, crossing is also considered as being distributed most wide traffic bottlenecks node.
Traditional control method, such as can trace back to nineteen fifty for the analysis of single node traffic model, by based on Bai Song
The distributed model of arrival, has carried out the optimal control of signal to the queuing vehicle of single-point.Late 1970s, China start
City road network network coordinating control of traffic signals research.On the one hand, some scholars to external some typical area control systems (such as
SCATS, SCOOT etc.) secondary development is carried out, it is allowed to adapt to the situation of domestic mixed traffic flow;On the other hand, some scholars are to city
City's traffic coordinated control has carried out theoretical research, such as based on the Arterial Coordination Control model that system total delay is minimum, but it is hereditary
The operational efficiency of algorithm is not high, is not suitable for extension;One kind turns to object function, phase contrast as decision variable with green wave band width maximum
Variable speed rapid-curing cutback signal coordination control mathematical model, but it does not account for impact of the branch road left turn traffic to main line straight traffic;Adopt
The certainty factor in traffic system is modeled with linear programming, obtain the preliminary timing scheme of signal lighties, then using fuzzy
Control mode is compensated, but the amount of calculation of algorithm is too big, is not suitable for real-time traffic calculating.
Human lives in the middle of the world comprising various numerous and complicated network, from the Internet, power network, logistics
Net, the network of communication lines, telecommunications network, including the nerve net etc. of human body, although they adhere to different fields, all day to us separately
Often life produces irreplaceable effect.Therefore, how optimized to play respective network advantage, research worker is to each
Kind of network has all carried out careful research, it is found that these networks abstract for elementary cell and its can interact what is constituted
Net, for example:Urban road network can with it is abstract as crossing as node and with section connect network, wherein section for make vehicle from
One intersection node drives to the carrier of next node, and the distribution and circulation of the different directions of vehicle is then realized in crossing;
The Internet can with it is abstract as base station and signal channel composition network, wherein base station realize to user send resource, channel
It is then signal transmission passage and carrier etc..However, with the expansion of network size, causing the complexity of network constantly to increase
Plus, the operating mechanism of complex network is analysed in depth, is further to optimize and controlling network, and maximization network traffic efficiency is intelligence
The important topic of energy traffic system, urban traffic network congestion problems are exactly a typical complex network optimization and control problem.
Therefore, the present invention easily receives the shadows such as non-linear traffic behavior, discrete time variation, randomness for conventional traffic model
Ring, cause the problems such as traffic prediction model is unstable, system operations amount is big, stability is poor.With complex network informationization model it is
Basis, by the transportation network abstract network for intersection node and road, by the vehicle abstract packet for network communication, intersects
The switching control time of the sequential of the control of message signal lamp, as network node, propose that a kind of distributed transportation network is adaptive
Optimization method is answered, complicated transportation network vehicle pass-through efficiency is improved, is reduced system delay, with great theory significance and engineering
Using value.
The content of the invention
For the deficiencies in the prior art, the present invention provides one kind in complex region traffic system, needs to traffic signal
Control and vehicle running path are optimized, and so as to realize during the management and control to urban highway traffic, propose stable, reliability, environment
Strong adaptability, algorithm real-time are high, system optimization complicated transportation network signal control optimization method in hgher efficiency.
The technical scheme that adopted for achieving the above object of the present invention is:A kind of message based complex network traffic signal
Optimal control method, comprises the following steps:
Step 1:Traffic network design is set up, transportation network parameter is initialized;
Step 2:Based on transportation network parameter, the signal lighties switching time and vehicle for initializing each network node reaches node
Time;
Step 3:Traffic network system delay function is set up, the vehicle time of advent, signal according to initialization network node
Between lamp switching time and network node, link length distribution, sets up message sending function between each network node;
Step 4:Vehicle queue length, road traffic, average speed and occupation rate information are obtained using wagon detector,
Calculate vehicle and reach node time;
Step 5:The information obtained using wagon detector, seeks the minima of traffic network system delay function, obtains new
The value for setting up message sending function between each network node, be transferred to upstream and downstream node;
Step 6:Return to step 3 is circulated iterative processing, when state is optimal, stops loop iteration.
The transportation network parameter include between transportation network junction node matrix, network node link length distribution matrix with
And different road wagon flows and occupation rate observing matrix between network node.
The transportation network parameter includes that transportation network junction node matrix is:
Wherein, N is M × N-dimensional matrix, wherein, i ∈ [0, N-1], j ∈ [0, M-1], x (i, j) are traffic in transportation network
Crossing position coordinateses.
Between the network node, link length distribution matrix is the spatial distribution of two groups of roads:
Wherein:Dx(i,j)Matrix is tieed up for N × M-1, horizontal road distribution is represented;Dy(i,j)Matrix is tieed up for N-1 × M, is represented and is hung down
Straight way road is distributed.
Between the network node, different road wagon flows and occupation rate observing matrix are:
Wherein:Lx(i,j)Matrix is tieed up for N × M-1, horizontal road wagon flow and occupation rate observing matrix is represented;Ly(i,j)For N-1
× M ties up matrix, represents vertical road wagon flow and occupation rate observing matrix.
The vehicle reaches node time:
In formula, x(x,j)T () represents junction node x (i, j) place signal lighties switching time, Dx(i,j)Represent junction node adjacent
Direction reaches junction node link length.
The traffic network system delay function is:
Wherein, ad(i, j) represents that vehicle reaches the time of node, L from a directionxd(i, j), Lyd(i, j) is represented respectively
The vehicle queue length of node, D are above reached both horizontally and verticallyxd(i,j),Dyd(i, j) is represented both horizontally and vertically respectively
The link length of upper node all directions, δ (i, j) represent the delay value of node.
Between each network node, message sending function is:
h(i,j)(aN)=min f (x;aW,L,D)+g(i,j+1)(x(i,j)+DE(i,j+1))+h(i+1,j)(x(i,j)+DS(i+
1,j))
g(i,j)(aW)=min f (x;aN,L,D)+g(i,j+1)(x(i,j)+DE(i,j+1))+h(i+1,j)(x(i,j)+DS(i+
1,j))
Wherein, aWRepresent vehicle from west node time of advent, aNRepresent vehicle from north node time of advent, g(i,j+1)
Expression is transferred to the message value of x (i, j+1), h from node x (i, j)(i,j+1)Represent from node x (i, j) be transferred to x (i+1, j)
Message value, x are the current crossing green light time started, and D is link length of node x (i, j) to node x (i, j+1), and L is to reach
The Vehicle length of node x (i, j), DEFor the link length between present node and east adjacent node, DSFor present node and south
Link length between the adjacent node of face.
The wagon detector is microwave vehicle detector or ground induction coil.
The optimum state for previous cycle minimum network delay with upper one circulation minimum network delay difference not
More than defined threshold.
The invention has the advantages that and advantage:
1. the present invention is based on complex network informationization model, by transportation network abstract for intersection node and road
Network, by the vehicle abstract packet for network communication, the switching of the sequential of the control of Intersections, as network node
Control time, a kind of message based distributed traffic network signal control iterative optimization method;
2. the present invention adopts microwave vehicle detector or ground induction coil, the road traffic that obtained using sensor in real time,
The information such as lane occupancy ratio, average speed, carry out real-time renewal process to node transmission message, it is to avoid in conventional traffic model
Need big data to carry out learning the problem of optimization, improve system real time and stability;
3. the present invention is simplified the complexity of conventional traffic model, is carried by Message function transmission function between structure node
High systematic learning efficiency and quick convergence;
4. the present invention has quick convergence and system stability.
Description of the drawings
Fig. 1 is method of the present invention flow chart;
Fig. 2 is the two-dimentional traffic networking model schematic of present invention emulation;
Under the conditions of Fig. 3 is for present invention emulation parallel equidistant, traffic time delay stability and convergence curve chart;
Fig. 4 be between simulated point of the present invention road be uniformly distributed with the conditions of normal distribution, traffic time delay stability and receipts
Hold back linearity curve figure.
Specific embodiment
Below in conjunction with the accompanying drawings and embodiment the present invention is described in further detail.
As shown in figure 1, being present system schematic flow sheet.
The step 1, complicated transportation network junction node matrix are expressed as:
In formula, N is M × N-dimensional matrix, wherein, i ∈ [0, N-1], j ∈ [0, M-1], x (i, j) are traffic in transportation network
Crossing position coordinateses.
Between transport node, link length distribution matrix is the spatial distribution of two groups of roads, as follows
In formula:Dx(i,j)Matrix is tieed up for N × M-1, horizontal road distribution is represented;Dy(i,j)Matrix is tieed up for N-1 × M, is represented and is hung down
Straight way road is distributed;
Between node, different terrain vehicle stream mode observing matrixes, use Lx(i,j)、Ly(i,j)Represent.
Wherein:Lx(i,j)Matrix is tieed up for N × M-1, horizontal road wagon flow and occupation rate observing matrix is represented;Ly(i,j)For N-1
× M ties up matrix, represents vertical road wagon flow and occupation rate observing matrix.
In the step 2, transportation network reaches the time, and crossing west as follows was expressed as to the time of advent:
In formula, x(x,j)T () represents junction node x (i, j) place signal lighties switching time, Dx(i,j)Represent junction node west to
Link length.
The step 3:Traffic system network delay function, is expressed as:
In formula, ad(i, j) represents that vehicle reaches the time of node, L from a directionxd(i, j), Lyd(i, j) is represented respectively
The Vehicle length of node, D are above reached both horizontally and verticallyxd(i,j),Dyd(i, j) represents both horizontally and vertically upper respectively and saves
The link length of point all directions, δ (i, j) represent the delay value of node.
Message sending function between each network node, is expressed as:
h(i,j)(aN)=min f (x;aW,L,D)+g(i,j+1)(x(i,j)+DE(i,j+1))+h(i+1,j)(x(i,j)+DS(i+
1,j))
g(i,j)(aW)=min f (x;aN,L,D)+g(i,j+1)(x(i,j)+DE(i,j+1))+h(i+1,j)(x(i,j)+DS(i+
1,j))
In formula, aWRepresent vehicle from west node time of advent, aNRepresent vehicle from north node time of advent, g(i,j+1)
Expression is transferred to the little message value of x (i, j+1), h from node x (i, j)(i,j+1)Represent from node x (i, j) be transferred to x (i+1, j)
Message value.
The step 4, obtains road traffic, average speed, occupation rate using microwave vehicle detector or ground induction coil
Etc. information, set up vehicle and reach crossing average time, vehicle queue length information determines a in message sending functionW, L, D, and
By a for obtainingW, L, D bring into, sets up the initial value of message sending function.
The step 5, the vehicle obtained using sensors such as microwave vehicle detectors and road real time information, meter solve net
The minima of network delay function δ (i, j), obtains the value of message sending function between each network node, is transferred to upstream and downstream section
Point.With regard to upstream node, by travel direction by west to east, then west is upstream, and east is downstream, then west node is upstream node,
East node is downstream node.Wherein, network delay function δ (i, j) for minima when, x*(i, j) is network node
In signal lighties switching time x(x,j)T the local optimum of (), is expressed as follows shown:
In formula, x*(i, j) for network delay δ (i, j) for minima when signal lighties switching time local optimum, ad(i,j)
Represent that vehicle reaches the time of node, L from a directionxd(i, j), Lyd(i, j) represents both horizontally and vertically upper respectively and reaches
The vehicle queue length of node, Dxd(i,j),Dyd(i, j) represents that the road for both horizontally and vertically going up node all directions is long respectively
Degree, δ (i, j) represent the delay value of node.
The step 6, using step 5 result of calculation, is iterated circular treatment, until system is optimal value.It is optimum
State is not more than defined threshold Th with the difference of the minimum network delay of upper one circulation for the minimum network delay of previous cycle, wherein
Threshold value be twice iterative network totality delay inequality fiducial value, formula δ (t1)-δ(t2) < Th, threshold value can affect network convergence
Time.After finally determining that network delay δ (i, j) meets conditions above, each signal lighties switching time x in network node(x,j)(t)
As global optimum.
The effect of the present invention can be further illustrated by following emulation
Emulation content:
By traffic intersection abstract for network node, studied for face control traffic model, in order to simplify research, such as Fig. 2
Shown, the two-dimensional network model for setting up a 10x10 carries out simulating, verifying, carries out following vacation to above-mentioned two-dimentional traffic network design
If, 1) signal lamp cycle is normalized to (0,1] in the range of, phase cycling 0.5;2) the amber light cycle is not considered;3) new round week
Phase node exterior traffic stream is accumulated.
Simulating, verifying is carried out to algorithm, each junction node vehicle time of advent and signal lighties switching time is initialized, each
The average delay of node is T/2, it is considered to 10x10 junction node situation, and system population mean delay time is 50, wherein T=
1s.First for path for checking under parallel equidistant distribution situation, is analyzed to algorithm in emulation, parallel equidistant emulation is tied
Really, as shown in Figure 2.The initialization time delay of 10x10 meshed networks is 50s or so, and, after 10 iteration, total delay time is fast for system
Speed converges to 10s, after iteration 50 times, within overall time delay maintains 10s.By emulation, algorithm is demonstrated in parallel network
Under the conditions of, with strong convergence and higher optimization efficiency.
Below for being uniformly distributed (Uniform Distribution), Gauss distribution (Gaussian
Distribution the comparison of Algorithm Convergence and effectiveness) is carried out, road distance distribution is different between analysis different junction nodes
In the case of, the optimization of algorithm and convergence situation.Under the conditions of hypothesis is uniformly distributed, path meets U [d- δ, d+ δ] distributions, wherein d=
(0,0.5), under the conditions of Gauss distribution, path meets U (u, δ to 0.5, δ ∈2) distribution, wherein d=0.5, δ ∈ (0,0.5).Fig. 3 tables
Show and total time postpone to reduce with the increase of iterationses.In Fig. 4, circular dot represents road under the conditions of being uniformly distributed, algorithm
Optimization time delay distribution;Triangle point represents road for, under the conditions of Gauss distribution, algorithm optimization time delay is distributed.Demonstrate transportation network
Internal node carries out curve minimum variance quadratic fit after for different δ time delays point marks when being uniformly distributed with Gauss distribution,
It can be seen that under two kinds of road distribution situations of algorithm, convergence is provided with, and before the delay Optimization rate convergence of totality is not optimised
25%.
Claims (10)
1. a kind of message based complex network traffic signal optimization control method, it is characterised in that:Comprise the following steps:
Step 1:Traffic network design is set up, transportation network parameter is initialized;
Step 2:Based on transportation network parameter, when the signal lighties switching time and vehicle for initializing each network node reaches node
Between;
Step 3:Traffic network system delay function is set up, the vehicle time of advent, signal lighties according to initialization network node cuts
Link length distribution between time and network node is changed, message sending function between each network node is set up;
Step 4:Vehicle queue length, road traffic, average speed and occupation rate information are obtained using wagon detector, is calculated
Vehicle reaches node time;
Step 5:The information obtained using wagon detector, is sought the minima of traffic network system delay function, obtains new building
The value of message sending function between each network node is found, upstream and downstream node is transferred to;
Step 6:Return to step 3 is circulated iterative processing, when state is optimal, stops loop iteration.
2. message based complex network traffic signal optimization control method according to claim 1, it is characterised in that:Institute
Stating transportation network parameter includes link length distribution matrix and network node between transportation network junction node matrix, network node
Between different road wagon flows and occupation rate observing matrix.
3. message based complex network traffic signal optimization control method according to claim 2, it is characterised in that:Institute
Stating transportation network parameter includes that transportation network junction node matrix is:
Wherein, N is M × N-dimensional matrix, wherein, i ∈ [0, N-1], j ∈ [0, M-1], x (i, j) are traffic intersection in transportation network
Position coordinateses.
4. message based complex network traffic signal optimization control method according to claim 2, it is characterised in that:Institute
State the spatial distribution that link length distribution matrix between network node is two groups of roads:
Wherein:Dx(i,j)Matrix is tieed up for N × M-1, horizontal road distribution is represented;Dy(i,j)Matrix is tieed up for N-1 × M, vertical road is represented
Road is distributed.
5. message based complex network traffic signal optimization control method according to claim 2, it is characterised in that:Institute
Stating different road wagon flows and occupation rate observing matrix between network node is:
Wherein:Lx(i,j)Matrix is tieed up for N × M-1, horizontal road wagon flow and occupation rate observing matrix is represented;Ly(i,j)Tie up for N-1 × M
Matrix, represents vertical road wagon flow and occupation rate observing matrix.
6. message based complex network traffic signal optimization control method according to claim 1, it is characterised in that:Institute
Stating vehicle arrival node time is:
In formula, x(x,j)T () represents junction node x (i, j) place signal lighties switching time, Dx(i,j)Represent the adjacent direction of junction node
Reach junction node link length.
7. message based complex network traffic signal optimization control method according to claim 1, it is characterised in that:Institute
Stating traffic network system delay function is:
Wherein, ad(i, j) represents that vehicle reaches the time of node, L from a directionxd(i, j), Lyd(i, j) represents level respectively
With Vertical Square up to node vehicle queue length, Dxd(i,j),Dyd(i, j) represents both horizontally and vertically upper respectively and saves
The link length of point all directions, δ (i, j) represent the delay value of node, xi,jRepresent the road of the i-th row jth row in two-dimentional transportation network
Mouth node.
8. message based complex network traffic signal optimization control method according to claim 1, it is characterised in that:Institute
Stating message sending function between each network node is:
h(i,j)(aN)=minf (x;aW,L,D)+g(i,j+1)(x(i,j)+DE(i,j+1))
+h(i+1,j)(x(i,j)+DS(i+1,j))
g(i,j)(aW)=minf (x;aN,L,D)+g(i,j+1)(x(i,j)+DE(i,j+1))
+h(i+1,j)(x(i,j)+DS(i+1,j))
Wherein, aWRepresent vehicle from west node time of advent, aNRepresent vehicle from north node time of advent, g(i,j+1)Represent
The message value of x (i, j+1), h are transferred to from node x (i, j)(i,j+1)Represent from node x (i, j) and be transferred to x (i+1, message j)
Value, x are the current crossing green light time started, and D is link length of node x (i, j) to node x (i, j+1), and L is to reach node x
The Vehicle length of (i, j), DEFor the link length between present node and east adjacent node, DSFor present node and phase in the south
Link length between neighbors.
9. message based complex network traffic signal optimization control method according to claim 1, it is characterised in that:Institute
Wagon detector is stated for microwave vehicle detector or ground induction coil.
10. message based complex network traffic signal optimization control method according to claim 1, it is characterised in that:
The optimum state is no more than specified with the difference of the minimum network delay of upper one circulation for the minimum network delay of previous cycle
Threshold value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410318468.5A CN104882006B (en) | 2014-07-03 | 2014-07-03 | Message-based complex network traffic signal optimization control method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410318468.5A CN104882006B (en) | 2014-07-03 | 2014-07-03 | Message-based complex network traffic signal optimization control method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104882006A CN104882006A (en) | 2015-09-02 |
CN104882006B true CN104882006B (en) | 2017-05-03 |
Family
ID=53949483
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410318468.5A Expired - Fee Related CN104882006B (en) | 2014-07-03 | 2014-07-03 | Message-based complex network traffic signal optimization control method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104882006B (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105279978B (en) * | 2015-10-15 | 2018-05-25 | 青岛智能产业技术研究院 | Intersection traffic signal control method and equipment |
CN105279982B (en) * | 2015-11-13 | 2017-11-21 | 北京航空航天大学 | A kind of Single Intersection dynamic traffic signal control method based on data-driven |
CN107170235B (en) * | 2017-06-13 | 2020-03-03 | 广东石油化工学院 | Traffic flow prediction time sequence method based on depth feature extraction network |
CN109544922B (en) * | 2018-11-27 | 2020-11-24 | 华南理工大学 | Traffic network distributed predictive control method based on region division |
CN110189529B (en) * | 2019-03-21 | 2021-06-15 | 江苏智通交通科技有限公司 | Traffic signal control scheme switching adjustment management system and method |
CN112767717B (en) * | 2021-01-25 | 2022-08-02 | 泉州装备制造研究所 | Regional traffic signal coordination control method and system oriented to complex traffic control environment |
CN113192318B (en) * | 2021-01-29 | 2022-09-02 | 安徽科力信息产业有限责任公司 | Data drive control regional traffic signal dynamic optimization method and system |
CN117275239A (en) * | 2023-11-21 | 2023-12-22 | 天津轻工职业技术学院 | Traffic big data information processing method, device and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1472710A (en) * | 2003-05-16 | 2004-02-04 | 上海交通大学 | Automatic unit based self organizing and controlling method for urban traffic signals |
CN101826261A (en) * | 2010-05-20 | 2010-09-08 | 西北工业大学 | Method for building signal control model for urban traffic network crossroad |
CN103778791A (en) * | 2012-10-26 | 2014-05-07 | 中兴通讯股份有限公司 | Traffic adaptive control method and traffic adaptive control device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9076332B2 (en) * | 2006-10-19 | 2015-07-07 | Makor Issues And Rights Ltd. | Multi-objective optimization for real time traffic light control and navigation systems for urban saturated networks |
-
2014
- 2014-07-03 CN CN201410318468.5A patent/CN104882006B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1472710A (en) * | 2003-05-16 | 2004-02-04 | 上海交通大学 | Automatic unit based self organizing and controlling method for urban traffic signals |
CN101826261A (en) * | 2010-05-20 | 2010-09-08 | 西北工业大学 | Method for building signal control model for urban traffic network crossroad |
CN103778791A (en) * | 2012-10-26 | 2014-05-07 | 中兴通讯股份有限公司 | Traffic adaptive control method and traffic adaptive control device |
Non-Patent Citations (1)
Title |
---|
基于复杂网络的区域交通信号控制系统优化研究;魏路;《中国优秀硕士学位论文全文数据库》;20121015;第34-63页 * |
Also Published As
Publication number | Publication date |
---|---|
CN104882006A (en) | 2015-09-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104882006B (en) | Message-based complex network traffic signal optimization control method | |
Balaji et al. | Type-2 fuzzy logic based urban traffic management | |
CN106875710B (en) | A kind of intersection self-organization control method towards net connection automatic driving vehicle | |
Maslekar et al. | CATS: An adaptive traffic signal system based on car-to-car communication | |
Singh et al. | Time optimization for traffic signal control using genetic algorithm | |
CN102833160B (en) | Contact predication based large-scale mobile delay tolerant network cluster-based routing method and system thereof | |
CN105208616A (en) | Road topology based adaptive multi-copy routing method in vehicular ad hoc network | |
Zhao et al. | A novel adaptive routing and switching scheme for software-defined vehicular networks | |
Li et al. | Improved AODV routing protocol for vehicular Ad hoc networks | |
CN104835026A (en) | Automatic stereoscopic warehouse selection operation scheduling modeling and optimizing method based on Petri network and improved genetic algorithm | |
CN104123849A (en) | Adjacent intersection bidirectional linkage control method in consideration of dynamic queuing length | |
Pham et al. | Learning coordinated traffic light control | |
CN104021685A (en) | Traffic control method of intersections containing mixed traffic flows | |
CN103794065A (en) | Active urban road area signal timing parameter collaborative optimization method | |
Huang et al. | ECDS: Efficient collaborative downloading scheme for popular content distribution in urban vehicular networks | |
CN105844370B (en) | Urban road vehicle degree of communication optimization method based on particle swarm algorithm | |
CN102932840A (en) | Wireless router active queue management method based on rates and queue length | |
CN105743783A (en) | Car-Networking Node Selecting Method based on BS-TS and Autoencoder Network, and Accessibility Routing Mechanism Thereof | |
AU2021103022A4 (en) | A Method of Controlling Traffic Light Based on Fog Computing and Reinforcement Learning | |
Hu et al. | Network-wide traffic signal optimization under connected vehicles environment | |
Huang et al. | Cooperative multi-intersection traffic signal control based on deep reinforcement learning | |
CN103096412B (en) | Data fusion method with time delay restriction in delay tolerant network | |
CN106157643B (en) | A kind of traffic signal optimization alternative manner based on message matrix gridding | |
CN115063988A (en) | Emergency vehicle priority cross-traffic sub-area signal cooperative control method | |
Wu et al. | A method for short-term traffic flow prediction and control on urban road |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
EXSB | Decision made by sipo to initiate substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170503 Termination date: 20180703 |