CN106600990B - Dynamic signal lamp evaluation method and system based on genetic algorithm - Google Patents
Dynamic signal lamp evaluation method and system based on genetic algorithm Download PDFInfo
- Publication number
- CN106600990B CN106600990B CN201611035666.6A CN201611035666A CN106600990B CN 106600990 B CN106600990 B CN 106600990B CN 201611035666 A CN201611035666 A CN 201611035666A CN 106600990 B CN106600990 B CN 106600990B
- Authority
- CN
- China
- Prior art keywords
- lane
- phase
- group
- key
- period
- 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.)
- Active
Links
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Genetics & Genomics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Physiology (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a dynamic signal lamp evaluation method based on a genetic algorithm, which comprises the following steps: initializing, and acquiring related information through crossing numbers; defining a lane group, wherein under a certain phase, all lanes with right of way on the same road section are defined as a lane group; finding a core passing lane group of the current phase, wherein if: under the condition that the lane has the right of way in all phases, removing the lane from the lane group; finding out a key lane of the phase; judging a theoretical minimum period and a theoretical maximum period; determining the saturation of each phase-critical lane; determining a penalty function for the cycle; and determining a planning function in a non-oversaturated phase, and calling a genetic function to solve the optimal solution of the planning function. The invention further provides a dynamic signal lamp evaluation system based on the genetic algorithm.
Description
Technical Field
The invention relates to the technical field of public transportation, in particular to a dynamic signal lamp evaluation method and system based on a genetic algorithm.
Background
In the Intelligent Transportation System (ITS), the control of urban traffic lights is an extremely important part. The rapid increase of urban vehicles and the limited road resources make the traditional traffic light control difficult to obtain satisfactory effect. The traditional traffic light control mainly has fixed-time control and induction control. The fixed-time control mode cannot make corresponding reaction to the traffic flow changing in real time.
Aiming at urban intersection signal lamps, the aim of reducing the average waiting time of vehicles is fulfilled, and on the premise of considering pedestrian traffic safety, a traffic light real-time timing algorithm is also provided in the prior art, and the timing of the traffic lights is regulated and controlled in real time according to the number of vehicles detected by a video in real time. The algorithm comprises two-stage control, wherein the first-stage control is based on a fuzzy control theory, and initial timing of a corresponding level is selected according to the traffic rate and the waiting time of the vehicle; and the secondary real-time control calculates the number of the simulated traffic, regulates and controls the initial timing in real time and controls the phase conversion. Under the same traffic condition, compared with fixed time control and fuzzy control, the traffic light real-time timing algorithm reduces the average waiting time of vehicles. Meanwhile, when the density difference of vehicles in each phase is large, waiting time dual polarization is avoided. However, the algorithm is complex in calculation and has high requirements on data processing.
Disclosure of Invention
The invention aims to provide a dynamic signal lamp evaluation method and system based on a genetic algorithm, which overcome the problems in the prior art.
In order to achieve the above object, the present invention provides a dynamic signal lamp evaluation method based on genetic algorithm, comprising:
step 1, initialization, wherein the following information is obtained through intersection numbers: phase configuration of the intersection, lanes corresponding to each phase, lane markings, saturation flow rate of each lane, traffic capacity of each lane, 15 minute traffic of each lane, critical lane grouping of each phase, rush hour coefficient, delay and park weight, incremental delay correction coefficient, upstream and downstream linkage correction coefficient, maximum minimum green time of each phase, maximum minimum cycle time of each phase, and loss time of each phase;
step 2, defining lane groups, wherein all lanes with right of way on the same road section are defined as one lane group in a certain phase;
and 3, finding out the core passing lane group of the current phase, wherein if: under the condition that the lane has the right of way in all phases, removing the lane from the lane group;
step 4, finding out a key lane of the phase;
step 5, judging a theoretical minimum period and a theoretical maximum period;
step 6, judging the saturation of each phase key lane;
step 7, determining a penalty function for the period;
and 8, determining a planning function in a non-oversaturated phase, and calling a genetic function to solve the optimal solution of the planning function.
In a further embodiment, in the step 2, the lane group determination condition is:
1. acquiring all lanes with right of way under the phase A;
2. the lanes are grouped by link, and those with the same link ID are grouped into one group.
In a further embodiment, in the step 4, the specific implementation of finding out the key lane of the phase includes:
1. after the core lane group finishes screening lanes, two conditions exist in each road section
Case 1: if the lane group exists in the phase, executing the following steps:
1) finding out the lane with the maximum v/s ratio in the lane group, and defining the lane as a key lane of the road section;
2) finding out the lane with the maximum v/s ratio in all lane groups of the phase, and defining the lane as a key lane of the phase;
case 2: if no lane group exists in the phase, executing the following steps:
1) setting v/s of the key lane group of the phase to be 0.1;
2. the condition that at least one lane group exists in the road section corresponding to the phase; directly selecting a lane with the maximum flow from the lane group, and defining the lane as a key lane;
3. a phase does not have critical lanes because there is only one lane, then the phase runs the minimum green light directly.
In a further embodiment, in the step 5, the specific implementation of the determination of the theoretical minimum period and the theoretical maximum period is as follows:
according to the Webster delay theory, the theoretical minimum period is as follows:
if: if y is more than or equal to 1, the period is equal to Cmin in the data;
the theoretical maximum period is:
if: y is greater than or equal to 1, the period is equal to Cmax in the data;
where Y is the sum of the V/S ratios of all phases and L is the number of phases multiplied by 9.
In a further embodiment, the calculation formula for determining the saturation of each phase-critical lane in step 6 is as follows:
it should be understood that all combinations of the foregoing concepts and additional concepts described in greater detail below can be considered as part of the inventive subject matter of this disclosure unless such concepts are mutually inconsistent. In addition, all combinations of claimed subject matter are considered a part of the presently disclosed subject matter.
The foregoing and other aspects, embodiments and features of the present teachings can be more fully understood from the following description taken in conjunction with the accompanying drawings. Additional aspects of the present invention, such as features and/or advantages of exemplary embodiments, will be apparent from the description which follows, or may be learned by practice of specific embodiments in accordance with the teachings of the present invention.
Drawings
The drawings are not intended to be drawn to scale. In the drawings, each identical or nearly identical component that is illustrated in various figures may be represented by a like numeral. For purposes of clarity, not every component may be labeled in every drawing. Embodiments of various aspects of the present invention will now be described, by way of example, with reference to the accompanying drawings, in which:
FIG. 1 is a schematic flow diagram of a method for dynamic signal light assessment based on genetic algorithms according to some embodiments of the present invention.
FIG. 2 is a flow diagram of a general model of a real genetic algorithm.
Detailed Description
In order to better understand the technical content of the present invention, specific embodiments are described below with reference to the accompanying drawings.
In this disclosure, aspects of the present invention are described with reference to the accompanying drawings, in which a number of illustrative embodiments are shown. Embodiments of the present disclosure are not necessarily intended to include all aspects of the invention. It should be appreciated that the various concepts and embodiments described above, as well as those described in greater detail below, may be implemented in any of numerous ways, as the disclosed concepts and embodiments are not limited to any one implementation. In addition, some aspects of the present disclosure may be used alone, or in any suitable combination with other aspects of the present disclosure.
With reference to fig. 1 and fig. 2, according to an embodiment of the present invention, a dynamic signal lamp evaluation method based on a genetic algorithm includes the following specific implementation steps:
the first step is as follows: initializing data
Respectively acquiring the following information through crossing numbers
| Phase allocation at intersections | MD_PHASE_GROUP | Database auto-acquisition |
| Each phase corresponds to a lane | Database auto-acquisition | |
| Marking line of lane | Database auto-acquisition | |
| Saturation flow rate per lane | Database automatic acquisition, page revisable | |
| Traffic capacity per lane | Database automatic acquisition, page revisable | |
| 15 minute flow per lane | Obtaining in a database | |
| Each phase critical lane group | System computation, page modification | |
| High peak hour coefficient | Database reading, page modification | |
| Delay and parking weight | Database reading, page modification | |
| Incremental delay correction factor | Database reading, page modification | |
| Upstream and downstream linkage correction coefficient | Database is read by default, and page can be modified | |
| Maximum minimum green time per phase | Database is read by default, and page can be modified | |
| Maximum minimum cycle time per phase | Maximum minimum green time per phase | |
| Loss time per phase | 3 | Database is read by default, and page can be modified |
The second step is that: defining lane groups
And in a certain phase, all lanes with the right of way on the same road section are defined as a lane group. The judgment condition is that,
1. and acquiring all the lanes with the right of way in the phase A.
2. The lanes are grouped by link, and those with the same link ID are grouped into one group.
The third step: core passing lane group for finding current phase
If: in the case where the lane has right of way in all phases, the lane group excludes the lane.
The fourth step: key lane for finding phase
After the core lane group finishes screening lanes, two conditions exist in each road section
Case 1: in-phase lane group
The execution steps are as follows:
1. and finding out the lane with the maximum v/s ratio in the lane group, and defining the lane as a key lane of the road section.
2. And finding out the lane with the maximum v/s ratio in all lane groups of the phase, and defining the lane as a key lane of the phase.
Case 2: non-existent lane group in phase
The execution steps are as follows:
● sets v/s of the key lane group for that phase to 0.1.
● when at least one lane group exists on the road section corresponding to the phase
This is a common situation, and the lane with the largest flow is directly selected from the lane group. The lane is defined as a critical lane.
● No critical lane at a certain phase because there is only one lane
This is the less frequent case that occurs when the phase is running the minimum green light directly.
The fifth step: determining theoretical minimum and maximum periods
According to the Webster delay theory, the theoretical minimum period is
If: y is greater than or equal to 1, the period is equal to Cmin in the data.
Theoretical maximum period of
If: y ≧ 1, the period equals Cmax in the data.
Where Y is the sum of the V/S ratios of all phases and L is the number of phases multiplied by 9.
And a sixth step: determining saturation of each phase critical lane
The calculation formula of the saturation is
The seventh step: determining penalty functions for cycles
The penalty function logic as shown above is as follows:
if the saturation is >1
The average delay is equal to 2500 squared of the original average delay + | saturation-1 |;
if the saturation is <0.8
The average delay is equal to the original average delay plus | saturation-1 | squared 5000;
eighth step: determining a planning function in a non-oversaturated phase
Wherein
n is the number of phases
c，gkAs an unknown number, if the target phase is locked, it corresponds to gkIs a known number.
k represents a lane group of a certain phase, and A, B, and C are phase numbers.
T: the value analysis period is taken, and the recommended value is 0.25.
k: the incremental delay correction, suggested value 0.5.
I: and performing upstream and downstream linkage control correction, wherein the recommended value is 1.
λk: stored in the table MD _ UTC _ priority, it can be obtained from the link number + phase group number. The default value is 1.
Calling a genetic algorithm (shown in figure 2) to call for help from the planning function and outputting an optimal solution.
The parameters and interface relationships in the foregoing method are defined as follows:
in the implementation process of the invention, the basic idea of timing theory is as follows:
there are three situations in traffic signal timing practical application based on flow, respectively
1. When the saturation is between 0 and 0.3
The timing of the signal is limited by the minimum green light. This is because the green time of the traffic light is wasted, but the green time cannot be shortened because of safety and pedestrian crossing.
2. When the saturation is between 0.6 and 0.9
At the moment, the timing of the signal lamp can be optimized to improve the efficiency, and the optimization method adopts a classical Webster method combined with a weighting method to carry out optimization solution.
3. When the saturation is greater than 0.9
The timing of the signal is limited by the maximum green light. The reason for this is that the green time of the signal cannot be increased further, since an excessive period can lead to a traffic bottleneck downstream.
| Automatic calculation |
The module is operated once every 1 minute, only the flow is obtained, and other numerical values are the buffer obtained for the first time. The RESULT of the calculation is stored in the AY _ RESULT _ UTC _ BESTREGARDS table.
| Request computation |
The module accepts the data of the underlying table that the page has passed in, and if several entries are not passed, the data in the database is used by default. And generating a calculation result according to the user request. And stored in AY _ RESULT _ UTC _ BESTREGARDS.
Description of terms:
| term(s) for | Introduction to |
| Control delay d | Due to the control of the signal lights, the road generates time when the vehicle stops or cannot normally pass. |
| Uniform delay d1 | Suppose a delay occurs when the vehicle arrives on average, but fails to pass through the intersection at an average speed. |
| Incremental delay d2 | As the saturation and density increase, the vehicle presents non-uniformity and delays. |
| Saturation flow rate sa | The intersection has no signal lamp, and the vehicles are densely queued at the designed speed to pass through the number of the intersections. |
Fig. 2 shows an exemplary genetic algorithm, which is a general model of a real genetic algorithm.
Some steps and processes of the algorithm are described below in conjunction with the description of fig. 2.
The third step: determining termination condition
The termination condition is a set of termination conditions that are combined together to stop the iterative operation as long as any one of the conditions is satisfied.
The termination condition one: genetic algebra
And setting the genetic algebra as 1000, increasing the algebra by 1 every time a termination condition is judged, and returning to true when the algebra exceeds 1000.
And (2) termination condition II: the individual fitness tends to be stable.
The fourth step: invoking a Contention operator
The competition algorithm is divided into two parts, wherein the first part is to call a competition operator to obtain a solution of the fitness.
Whether the competition algorithm has a penalty item or not is judged,
and if the penalty item exists, calling a penalty function to solve the value of the competition operator again.
And if no penalty item exists, directly outputting the value of the competition operator.
The fifth step: calling penalty function
The system provides an interface to the penalty function, the input of which is one individual of the population. The output is the modified individual.
And a sixth step: writing selection algorithm
The selection algorithm is divided into 2 parts, and the fitness of the individual is obtained by calling a selection operator. The fitness function should evolve in a direction that is favorable for the objective function. I.e. the greater the fitness, the closer the objective function is to the target.
Let the fitness of each individual be fiAnd there are n individuals in total, the fitness wheel may be represented by the following numerical sequence.
And transmitting the probability sequence into a probability wheel algorithm to obtain subscripts of n individuals. The n individuals are selected to generate a new population.
The seventh step: invoking crossover operators
And (4) setting the hybridization probability as [ rho, 1-rho ], calling a probability wheel disc, calling a hybridization operator if the probability wheel disc is hit, and not calling the hybridization operator if the probability wheel disc is not hit.
The input of the hybridization operator is an individual, and the output is a new individual after hybridization. For the real number genetic algorithm, the arithmetic hybridization mode is uniformly adopted by the hybridization operator.
Eighth step: calling mutation operator
And (4) setting the mutation probability as [ sigma, 1-sigma ], calling a probability wheel disc, calling a mutation operator if the probability wheel disc is hit, and not calling the mutation operator if the probability wheel disc is not hit.
The input of the hybridization operator is an individual, and the output is a new individual after hybridization. The hybridization operator needs to be specifically defined according to a specific problem.
The ninth step: selecting an optimal solution
And sequencing the individuals according to the fitness of the individuals, selecting a solution with the highest fitness, and outputting a result.
Real number chromosome coding
The system provides a coding method and a decoding algorithm of the gene locus based on the code table. The encoding algorithm converts objective knowledge into mathematical knowledge, and the decoding algorithm is used for reducing mathematics into objective knowledge only. The gene coding is a coding interface, namely different coding methods can be called according to different service requirements.
Real number coded cipher table
Real number encoded gene loci
A chromosome is used for representing objective knowledge, the chromosome is composed of a plurality of genes which are arranged according to a certain sequence, different genes have different data types, but are uniformly coded according to real numbers, and the genes are ordered.
xn＝{z，bool，......enum}
Wherein xnIs a chromosome, that is, an objective fact. z, borol.. enum are genes arranged in a certain order.
The generation of the gene locus is very simple, and if the problem to be solved has n unknown variables, only n variables are required to be organized into a gene vector according to the sequence.
xn＝{x1，x2，......xn}
Encoding adapter and decoding adapter
Under the condition of gene locus, the coding module is called to perform real number coding according to the code table. The inverse transformation of the encoding module is called as the decoding module. The coding and decoding adapter is matched and is realized in an interface definition mode.
Generating real initial population
The initial population is a combination of feasible solutions and infeasible solutions, and only the number of the solutions is studied, but the accuracy is not studied. But better initial population has better universality and can avoid local convergence of genetic algorithm. Therefore, the system adopts a uniformly distributed random algorithm to generate the initial population.
Randomly invoking a coding algorithm generates a number of chromosomes,
1. each gene on the chromosome, within the value range, uses the random variable of uniform analysis to obtain the corresponding real value.
2. The calculated gene values are combined into chromosomes according to the gene loci.
3. Several such chromosomes are generated in succession to form a population. The number of chromosomes is 80 by default.
Selection operator and penalty function
The selection operator comprises a selection planning function and a penalty function,
1, the planning function is a planning function section in the text.
And 2, carrying out a penalty function, and carrying out strong penalty by adopting an R functional mode.
Removing one of the equality constraints from the constraint conditions, obtaining the following constraint:
1.vscwhen the ratio is less than or equal to 0.6, the restriction is as follows
gi-gmax≤0
gmin-gi≤0
The penalty function for the constraint is:
for each giI ═ 1,2,3 …, n, the following penalty function is defined:
the overall penalty function:
2.vscat > 0.6, the constraint is as follows
gi-gmax≤0
gmin-gi≤0
For each giI ═ 1,2,3 …, n, the following penalty function is defined:
the overall penalty function:
although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the invention. Therefore, the protection scope of the present invention should be determined by the appended claims.
Claims (2)
1. A dynamic signal lamp evaluation method based on a genetic algorithm is characterized by comprising the following steps:
step 1, initialization, wherein the following information is obtained through intersection numbers: phase configuration of the intersection, lanes corresponding to each phase, lane markings, saturation flow rate of each lane, traffic capacity of each lane, 15 minute traffic of each lane, critical lane grouping of each phase, rush hour coefficient, delay and park weight, incremental delay correction coefficient, upstream and downstream linkage correction coefficient, maximum minimum green time of each phase, maximum minimum cycle time of each phase, and loss time of each phase;
step 2, defining lane groups, wherein all lanes with right of way on the same road section are defined as one lane group in a certain phase;
and 3, finding out the core passing lane group of the current phase, wherein if: under the condition that the lane has the right of way in all phases, removing the lane from the lane group;
step 4, finding out a key lane of the phase;
step 5, judging a theoretical minimum period and a theoretical maximum period;
step 6, judging the saturation of each phase key lane;
step 7, determining a penalty function for the period;
step 8, determining a planning function in a non-oversaturated phase, and calling a genetic function to solve the optimal solution of the planning function;
in step 2, the lane group determination conditions are:
1. acquiring all lanes with right of way under the phase A;
2. grouping the lanes according to road sections, wherein the lanes are a group with the same road section ID;
in step 4, the specific implementation of finding out the key lane of the phase includes:
1. after the core lane group finishes screening lanes, two conditions exist in each road section
Case 1: if the lane group exists in the phase, executing the following steps:
1) finding out the lane with the maximum v/s ratio in the lane group, and defining the lane as a key lane of the road section;
2) finding out the lane with the maximum v/s ratio in all lane groups of the phase, and defining the lane as a key lane of the phase;
case 2: if no lane group exists in the phase, executing the following steps:
1) setting v/s of the key lane group of the phase to be 0.1;
2. the condition that at least one lane group exists in the road section corresponding to the phase; directly selecting a lane with the maximum flow from the lane group, and defining the lane as a key lane;
3. a certain phase does not have a key lane, because only one lane exists, the phase directly runs the minimum green light;
in the step 5, the specific implementation of the theoretical minimum period and the theoretical maximum period is determined as follows:
according to the Webster delay theory, the theoretical minimum period is as follows:
if: if y is more than or equal to 1, the period is equal to Cmin in the data;
the theoretical maximum period is:
if: y is greater than or equal to 1, the period is equal to Cmax in the data;
wherein Y is the sum of the V/S ratios of all phases, and L is the number of phases multiplied by 9;
wherein, the calculation formula for determining the saturation of each phase key lane in the step 6 is as follows:
2. a dynamic signal lamp evaluation system based on genetic algorithm is characterized by comprising:
at least one processor;
a memory;
wherein the memory is arranged for storing data for use by the processor and program modules comprising program instructions for carrying out the method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611035666.6A CN106600990B (en) | 2016-11-23 | 2016-11-23 | Dynamic signal lamp evaluation method and system based on genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611035666.6A CN106600990B (en) | 2016-11-23 | 2016-11-23 | Dynamic signal lamp evaluation method and system based on genetic algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106600990A CN106600990A (en) | 2017-04-26 |
| CN106600990B true CN106600990B (en) | 2021-12-03 |
Family
ID=58591773
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611035666.6A Active CN106600990B (en) | 2016-11-23 | 2016-11-23 | Dynamic signal lamp evaluation method and system based on genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106600990B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106971566B (en) * | 2017-05-04 | 2020-03-24 | 无锡安邦电气股份有限公司 | Self-adaptive control method based on genetic algorithm |
| CN107393319B (en) * | 2017-08-31 | 2020-06-19 | 长安大学 | Signal optimization control method for preventing single cross port queuing overflow |
| CN111597700B (en) * | 2020-05-09 | 2023-08-15 | 北京百度网讯科技有限公司 | Signal control algorithm evaluation method and device, electronic equipment and readable storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101540109A (en) * | 2008-03-17 | 2009-09-23 | 上海宝康电子控制工程有限公司 | Control system for automatically accomplishing bus priority according to traffic stream change |
| CN106023608A (en) * | 2016-06-08 | 2016-10-12 | 吉林大学 | Crossroad traffic signal lamp real time dynamic timing method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102008050822A1 (en) * | 2008-10-08 | 2010-04-15 | Gevas Software Systementwicklung Und Verkehrsinformatik Gmbh | Traffic Adaptive Network Control and Method for Optimizing Control Parameters |
| CN103473935B (en) * | 2013-09-03 | 2015-07-29 | 青岛海信网络科技股份有限公司 | Crossing traffic based on sensor detector blocks up judgement and control method and system |
| CN104077919B (en) * | 2014-07-02 | 2016-05-04 | 杭州鼎鹏交通科技有限公司 | The optimization method of a kind of demand track combinatorial phase |
| CN105448093B (en) * | 2015-12-28 | 2018-04-20 | 中兴软创科技股份有限公司 | A kind of intersection V/C is than acquisition methods and system |
| CN105608913B (en) * | 2016-03-15 | 2017-11-28 | 北方工业大学 | Handheld device for urban road intersection signal control |
-
2016
- 2016-11-23 CN CN201611035666.6A patent/CN106600990B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101540109A (en) * | 2008-03-17 | 2009-09-23 | 上海宝康电子控制工程有限公司 | Control system for automatically accomplishing bus priority according to traffic stream change |
| CN106023608A (en) * | 2016-06-08 | 2016-10-12 | 吉林大学 | Crossroad traffic signal lamp real time dynamic timing method |
Non-Patent Citations (2)
| Title |
|---|
| 信号控制交叉口动态车道功能优化方法;赵靖等;《同济大学学报(自然科学版)》;20130627(第07期);全文 * |
| 基于关键交通流向的道路交叉口信号配时方法;张雷元等;《城市交通》;20121125(第06期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106600990A (en) | 2017-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106558226B (en) | Signal lamp timing evaluation and real-time adjustment method | |
| CN106971566B (en) | Self-adaptive control method based on genetic algorithm | |
| CN105513400B (en) | The method of Dynamic Programming trip route | |
| CN106600990B (en) | Dynamic signal lamp evaluation method and system based on genetic algorithm | |
| CN111739284B (en) | Traffic signal lamp intelligent timing method based on genetic algorithm optimization fuzzy control | |
| CN111814626B (en) | Dynamic gesture recognition method and system based on self-attention mechanism | |
| CN103839412B (en) | A kind of crossing dynamic steering ratio combination method of estimation based on Bayes's weighting | |
| CN101587647B (en) | Networked public transport priority signal coordinating control method | |
| CN107393319B (en) | Signal optimization control method for preventing single cross port queuing overflow | |
| CN111915894A (en) | Variable lane and traffic signal cooperative control method based on deep reinforcement learning | |
| CN114495499B (en) | Multi-target intelligent internet vehicle cooperative optimization control method | |
| CN109558969A (en) | A kind of VANETs car accident risk forecast model based on AdaBoost-SO | |
| CN108629970B (en) | Intersection signal parameter optimization method based on Monte Carlo tree search | |
| CN103198648A (en) | Self-adaption dispatching method used for public traffic system | |
| CN110766956A (en) | Fuzzy logic based traffic signal control method | |
| CN113537580B (en) | Public transportation passenger flow prediction method and system based on self-adaptive graph learning | |
| CN111768638A (en) | Lane distribution method for single-point signalized intersection | |
| CN110930696B (en) | AI navigation-based intelligent city traffic management operation method and system | |
| CN112950934A (en) | Road congestion reason identification method | |
| CN117275260B (en) | Emergency control method for urban road intersection entrance road traffic accident | |
| CN111524345A (en) | Induction control method for multi-objective optimization under constraint of real-time queuing length of vehicle | |
| CN110047284A (en) | A kind of Traffic Signal Timing Optimal Decision-making support method based on expert system | |
| CN109255948A (en) | A kind of divided lane wagon flow scale prediction method based on Kalman filtering | |
| CN109872532B (en) | Automatic selection method and system for intersection signal control scheme | |
| CN111091286A (en) | Public bicycle scheduling model and solving method |
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 | ||
| CB02 | Change of applicant information |
Address after: 210012 room 627, Ning Shuang Road, Yuhuatai District, Nanjing, Jiangsu, 627 Applicant after: Ho whale cloud computing Polytron Technologies Inc Address before: 210012 No. 68 Bauhinia Road, Yuhuatai District, Jiangsu, Nanjing Applicant before: ZTEsoft Technology Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |