CN101789182A - Traffic signal control system and method based on parallel simulation technique - Google Patents
Traffic signal control system and method based on parallel simulation technique Download PDFInfo
- Publication number
- CN101789182A CN101789182A CN201010108763A CN201010108763A CN101789182A CN 101789182 A CN101789182 A CN 101789182A CN 201010108763 A CN201010108763 A CN 201010108763A CN 201010108763 A CN201010108763 A CN 201010108763A CN 101789182 A CN101789182 A CN 101789182A
- Authority
- CN
- China
- Prior art keywords
- data
- algorithm
- intersection
- traffic flow
- module
- 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
- 238000004088 simulation Methods 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 110
- 238000012545 processing Methods 0.000 claims abstract description 34
- 238000004458 analytical method Methods 0.000 claims abstract description 32
- 238000011156 evaluation Methods 0.000 claims description 26
- 238000005516 engineering process Methods 0.000 claims description 23
- 230000003044 adaptive effect Effects 0.000 claims description 11
- 230000005540 biological transmission Effects 0.000 claims description 11
- 238000007619 statistical method Methods 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 6
- 238000007621 cluster analysis Methods 0.000 abstract 1
- 238000005457 optimization Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 9
- 238000011217 control strategy Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 206010021033 Hypomenorrhoea Diseases 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention relates to a traffic signal control system and a method based on a parallel simulation technique, belonging to the field of urban traffic signal control systems. The system comprises the following five modules: a data acquisition module, a data processing module, an algorithm adaptability off-line analysis module, an algorithm on-line selection module and a teleseme execution module, wherein the data acquisition module is responsible for acquiring traffic flow information of intersections in real time and transferring the information to the data processing module; the data processing module computes traffic flow data according to the information, establishes a signalized intersection data dictionary, and simultaneously determines flow sections to divide threshold values by using a cluster analysis method; the algorithm adaptability off-line analysis module analyzes adaptability aiming at various control algorithms and establishes a control algorithm matching rule base; the algorithm on-line selection module selects a proper signal control algorithm according to the real-time traffic flow information and the matching rule base; and the teleseme execution module finishes the implementation of a signal control scheme according to the selected control algorithm. The signal control system provided by the invention realizes the on-line selection of the control algorithm, solves the problem of simulation and control deviation, and has the characteristic of strong expandability.
Description
Technical Field
The invention belongs to the field of urban traffic signal control systems, and particularly relates to a traffic signal control system and a traffic signal control method based on a parallel simulation technology.
Background
With the rapid development of national economy, the living standard of people is continuously improved, various demands for transportation are obviously increased, so that the contradiction among people, vehicles, roads, traffic and the environment is increasingly excited, and the problem of traffic jam becomes one of the main urban diseases commonly faced by cities of various countries in the world at present. Under the double constraints of economy and environmental resources, the traditional traffic strategy of only repairing roads and bridges in an extending way is unrealistic, and at present, the traditional traffic strategy is mainly solved by adopting an inner strategic policy, namely, on the basis of properly expanding road hardware conditions, an Intelligent Transportation System (ITS) based on a 3C technology (a control technology, a communication technology and a computer technology) is adopted to integrate road resources, so that the resource sharing and the optimized scheduling of the road conditions are realized to the maximum extent, and the road application efficiency is improved in an all-round way. The urban traffic signal control system is an important component module of ITS, and is always a research hotspot and focus, wherein the representative systems include a transport system, a SCOOT system, a SCATS system and the like.
The traffic Network Study (TRRL) system is a signal control system based on an off-line optimization traffic Network signal timing algorithm. The system mainly comprises two parts of simulation and optimization, and the weighted value of the total delay time and the total parking times is used as an objective function. During optimization, information of the geometric size, flow, initial timing and the like of the network is sent into a simulation model, the value of the objective function is obtained through simulation and sent into an optimization part for optimization, then the optimization part is returned to the simulation part, and the optimal signal timing is obtained through repeated iteration and optimization.
The SCOOT (Split Cycle and Offset Optimization technique) system is also an adaptive control system for real-time coordination control of a traffic network, which is proposed by TRRL, and is developed on the basis of TRANSYT system, the models and Optimization principles of the two systems are similar, and the difference is that SCOOT is a scheme forming type control system. The arrival information of the vehicles collected by the vehicle detectors arranged at the upstream of each entrance lane at each intersection is processed online to form a control scheme, and three control parameters, namely the split ratio, the period and the phase difference, are continuously adjusted in real time to adapt to the changing traffic state.
The SCATS (systematic coded Adaptive Traffic method) system is a real-time timing scheme selection system developed in the late Australia 70 s, and needs to optimize and draw up a set of control strategies adapted to different Traffic flow change grades of a controlled intersection and a road network in an off-line manner. And selecting a signal control scheme from the set schemes to execute according to the actual traffic flow.
The above systems have achieved certain desired effects in traffic practice, but these systems still have some problems: (1) the offline optimization mode (TRANSYT system) has large calculation amount and cannot adapt to the dynamic change of real-time traffic flow; (2) an online scheme forming formula (SCOOT system), wherein control strategies of the system are obtained through accurate data model simulation, the higher the model accuracy is, the more complex the structure is, the longer the simulation time is, and therefore the problem of disjointed simulation and control exists; (3) in addition, in recent years, many domestic and foreign scholars introduce advanced intelligent algorithms such as reinforcement learning, fuzzy systems, genetic algorithms and the like into the field of traffic engineering aiming at the defects and limitations of the traditional control system, so that a good simulation effect is obtained, but the application of the advanced control algorithms which are suitable for traffic state change in an actual system is difficult to realize. The above problems need to be solved.
Disclosure of Invention
The invention aims to overcome the defects of the prior system by adopting a method of combining off-line algorithm adaptability analysis and on-line algorithm selection on the basis of realizing intersection data second-level acquisition, and provides a signal control system and a signal control method based on a parallel simulation technology. The system not only meets the problems of matching of real-time flow and a control algorithm, and synchronization of algorithm simulation and system control, but also provides decision support for application of a complex control algorithm. The system adjusts the signal control mode in real time according to the actual condition of the signalized intersection, and improves the traffic capacity of the intersection and the traffic efficiency of the whole road network.
The invention is realized by adopting the following technical scheme.
A traffic signal control system and method based on parallel simulation technology comprises a data acquisition module, a data processing module, an algorithm adaptability off-line analysis module, an algorithm on-line selection module and a signal machine execution module, and is characterized in that: the data acquisition module comprises a detector and a data transmission unit, wherein the detector is buried at the signal intersection and is used for acquiring the traffic flow information of the intersection in real time, and the data transmission unit is responsible for transmitting the acquired information to the data processing module; the data processing module comprises a real-time data processing unit, a data statistical analysis unit and a data dictionary, wherein the input end of the real-time data processing unit is connected with the output end of the data transmission unit in the data acquisition module, and calculates traffic flow data according to the data acquired by the detector, and then stores the traffic flow data in the database to establish a signalized intersection data dictionary; a data statistical analysis unit in the data processing module applies a fuzzy C-means clustering analysis method to intersection traffic flow information in a data dictionary, wherein the algorithm is a fuzzy C-means clustering algorithm combining subtractive clustering and clustering effectiveness judgment, and determines a reasonable flow segment division threshold value reflecting the internal structure of intersection data; the algorithm adaptability offline analysis module adopts simulation software, performs adaptability condition analysis on various control algorithms according to flow segment thresholds divided by the data statistical analysis unit and based on the evaluation index with the minimum intersection average delay, and establishes a matching rule base between the various control algorithms and a traffic flow segment; the algorithm on-line selection module is used for applying simulation software, adopting a parallel simulation technology, selecting a signal control algorithm matched with the real-time traffic flow on line according to the real-time traffic flow information and the control algorithm adaptive conditions in the matching rule base, carrying out on-line simulation on the selected control algorithm, and giving out an evaluation index of signal control in real time to serve as a decision support for further implementing the algorithm; and the signal machine execution module specifically selects and executes an optimal control algorithm according to the evaluation result of the parallel online simulation, and completes the implementation of the optimal control scheme of the signalized intersection through a communication interface provided by the signal machine.
The detector in the data acquisition module can adopt a coil vehicle detector with level output and also can adopt a video detector, and the frequency of traffic flow data acquisition and transmission is in the order of seconds.
A traffic signal control method based on a parallel simulation technology is carried out by the traffic signal control system according to the following steps:
step 1: data acquisition
The detector buried at the signal intersection is used for acquiring the traffic flow information of the intersection in real time;
step 2: data processing
Step 2.1: the real-time data processing unit in the data processing module calculates traffic flow data according to the data collected by the detector;
step 2.2: storing traffic flow data in a database, and establishing a signalized intersection data dictionary;
step 2.3: a data statistical analysis unit in the data processing module applies a fuzzy c-means clustering Sub _ FCM method to the intersection traffic flow data for traffic clustering analysis, and determines a reasonable flow segment division threshold value reflecting the internal structure of intersection data;
and step 3: algorithm adaptive offline analysis
Simulation software in the algorithm adaptability offline analysis module performs adaptability condition analysis on various control algorithms according to flow segment thresholds divided by clustering analysis of the data statistical analysis unit and based on the evaluation index with the minimum intersection average delay, namely, the various control algorithms can obtain the optimal control effect when used in which traffic flow segment, thereby establishing a matching rule base between the various control algorithms and the traffic flow segment.
And 4, step 4: algorithm online selection
Applying simulation software, adopting a parallel simulation technology, selecting a signal control algorithm matched with the real-time traffic flow on line according to the real-time traffic flow information and the adaptive conditions of the control algorithm in the matching rule base, carrying out on-line simulation on the selected control algorithm, and giving an evaluation index of signal control in real time to serve as a decision support for further implementing the algorithm;
and 5: semaphore execution
And according to the evaluation result of the parallel online simulation, specifically selecting and executing an optimal control algorithm, and completing the implementation of the optimal control scheme of the signalized intersection through a communication interface provided by the signaler.
The signalized intersection data dictionary comprises intersection real-time traffic flow, time occupancy, average headway and average vehicle speed.
Compared with the existing signal control system, the invention has the following beneficial effects: the signal control system designed and developed by the invention can realize second-level acquisition of data, thereby comprehensively and carefully mastering intersection information and solving the bottleneck problem of a parallel simulation technology; the method combining off-line algorithm adaptability analysis and on-line algorithm selection is adopted, so that the on-line selection of the control algorithm is realized, and the problem of control strategy aging existing in the conventional system is avoided; the parallel simulation technology is applied to realize the online parallel simulation and online evaluation functions of the control algorithm, and the problem of simulation and control derailment is solved; meanwhile, based on the idea of establishing an algorithm matching rule base in an off-line manner, the system also provides decision support for the application of a complex control algorithm. In addition, the system has strong expandability, and once a new algorithm is generated, offline analysis can be performed and embedded into an algorithm matching rule base, so that a foundation is laid for further realizing a control strategy.
The invention is described in further detail below with reference to the following description of the drawings and the detailed description.
Drawings
FIG. 1: the invention provides a traffic signal control system structure schematic diagram based on a parallel simulation technology;
FIG. 2: the data acquisition flow chart is the data acquisition flow chart in the invention;
FIG. 3: establishing an algorithm matching rule base schematic diagram for off-line algorithm adaptability analysis;
FIG. 4: selecting a schematic diagram for the online algorithm in the invention;
FIG. 5: an online algorithm simulation and evaluation flow chart is obtained;
FIG. 6: laying a schematic diagram of the Huairou external field coil;
FIG. 7: a clustering result graph of the traffic flow data at the intersection of the highway bureau;
FIG. 8: a coordinated game cooperation solution algorithm control effect diagram is adopted in the road junction signal control of the highway bureau.
Detailed Description
The road network of the Huairou city road in Beijing city is mainly composed of 3 longitudinal roads and 10 transverse roads, wherein the south road and the north road are 'youth road, welcome road and east road', and in the east-west cross streets, the south China street, the Fule north street and the prefecture street are taken as main driving lines. The road network has 4 roundabouts and 18 signal control intersections, and the system disclosed by the invention is adopted to implement a Huairou signal control system.
At present, the Huairou signal control system is characterized in that: (1) embedding induction coils at each signalized intersection according to the form shown in the figure 6, and acquiring intersection traffic volume through a coil detector; (2) a single-point signal lamp control method is adopted. Although the control mode can collect the traffic of the wye road network, the second-level transmission of the traffic cannot be realized due to the limitation of the parameters and the performance of the detector. Meanwhile, although some optimization designs are made on the control algorithm, the control algorithm does not have good adaptability to the traffic state with complex Huai flexibility.
The novel signal control system designed by the invention is applied to the signal control of the intersections of the highway bureau in the urban area, and is implemented as follows:
1. data acquisition module
A coil detector MUD3002 is adopted to collect coil data of the intersection, and an intersection singlechip data collection system is designed by applying the characteristics of the detector and the openness of the design. The single chip microcomputer directly processes the high-low level output of the detector MUD3002 (the device gives low level when a vehicle enters the coil and gives high level when the vehicle exits the coil), and a data transmission unit is designed to realize the return of external field data, and the data is returned to a remote server through the optical transceiver (refer to fig. 2).
Coil detector MUD3002 is a single, dual channel vehicle detector designed specifically for vehicle access control, with two output configurations (opto-electrically isolated output and relay output) for each channel. For data acquisition, there are two modes of operation: one is to detect the output level of the MUD 3002; the other is that the upper computer obtains the current coil state through serial port communication. 24 coils at the intersection of the highway bureau correspond to 12 MUD3002 devices, the state of a coil needs about 3s when being inquired, the authenticity of data is seriously damaged, and in order to improve the data acquisition speed, the module adopts the level inquiry function of the MUD3002 and carries out data acquisition and transmission through a single chip microcomputer. The time for setting up a test platform to detect the acquisition of a single chip microcomputer for one period is about 500ms, so that the real-time reliability of data is ensured, and the problem of the bottleneck of a parallel simulation technology, namely the data acquisition hysteresis is solved.
The data transmitted from the data acquisition module to the data processing module has a total of four bytes, the first three bytes store the level state values of 24 coils, and the last byte is a check byte.
2. Data processing module
(1) And (3) building a data detection platform, verifying and confirming 4 bytes transmitted back by the singlechip, extracting each bit of information, storing the information in a database, and providing basic data for extracting subsequent traffic volume.
(2) Extracting real-time high and low level data from a database to complete the following data statistical analysis processing:
one is real-time data processing, which is to discriminate traffic parameters capable of reflecting real-time traffic states of intersections by using extracted real-time high and low level data, such as real-time traffic flow, time occupancy, headway, speed and other intersection traffic volume information, and store the traffic parameters in a database, so as to provide basis for algorithm on-line selection and simulation, wherein the processing process of the traffic parameters is as follows:
1) traffic flow Q: traffic flow is the number of vehicles passing a location per unit time in units of vehicles per hour. Q is N/T. Counting the traffic flow 5min before every 1s by adopting a recursion method, recording the passing time of a vehicle in a detector as '1', and recording the passing time from t in a database0Counting the number of '1' in 5 minutes from the moment:
the flow Q is N/5 (veh/min).
2) Vehicle occupancy: occupancy is the ratio of the sum of the road lengths occupied by vehicles within a road segment to the road segment length. Due to the difficulty of measurement, the time occupancy is usually represented by the letter o, i.e., the ratio of the sum of the pulse signal widths obtained by the vehicle passing the vehicle detector during one cycle time to the cycle time. And (5) counting the vehicle occupancy rate of the first 5min every 1s by adopting a recursion method.
In the database, all falling edge time t within 5 minutes are countedFalling edgeAnd rising edge time tRising edgeThe difference is the sum of the pulse signal widths obtained by the vehicle passing the detector during one cycle. Since the statistical occupancy is recursive in seconds, the following four situations occur in the acquired time interval.
First, data of 5 minutes are taken from the database, and the first data is "0", and the last data is "1", and the data is recorded as (0, 1).
And secondly, taking data of 5 minutes from the database, wherein the first data is '0', and the last data is '0', and recording the data as (0, 0).
And taking data of 5 minutes from the database, wherein the first data is '1', and the last data is '0' and is recorded as (1, 0).
And fourthly, taking data of 5 minutes from the database, wherein the first data is 1, and the last data is 1 and is marked as (1, 1).
In the case of (0, 1):
in the case of (0, 0):
in the case of (1, 1):
in the case of (1, 0):
wherein "t" represents the time when the 5 minutes taken starts, "t + 5" represents the time when the 5 minutes taken ends, and "0first"time at which" represents the first "0", "1last"indicates the last" 1 "time.
3) Vehicle speed vi: the observed value of the vehicle speed when the vehicle passes through a certain section of a road is calculated in a database from the first 1 of a statistical time period to the absolute value of the time difference between the 1 and the adjacent 0, and the vehicle speed of the ith vehicle is:
the arithmetic mean of the point vehicle speeds over the observation time is:
wherein,is the time average vehicle speed (km/h), n1The number of vehicles observed within the observation time is shown. And counting the time average vehicle speed of 5min before every 1s by adopting a recursion method.
When (0, 0), (0, 1) is the case: n is1＝N-1；
When (1, 1), (1, 0) is the case: n is1＝N。
Thus:
4) the headway is as follows: the difference in time between two adjacent vehicles arriving at the same location. According to the data recording mode of the database, the time headway is the time difference of two adjacent rising edges, namely the difference of two adjacent '1's. Since no vehicle passes through the coil in the red light period, only the headway of the vehicle in the green light period is considered. And counting the headway time of 5min before every 1s by adopting a recursion method.
Taking data of 5-minute time period from the database for processing, and calculating the time difference between the last "1" and the first "1", namely:
t0＝|′1first′-′1last′|，
judging whether a red light exists within 5 minutes, if no red light exists, t is t ═ t0. N is N when (1, 1), N is N-2 when (0, 0), and N is N-1 when (1, 0) or (0, 1); if there is red light, counting the number k of red light, and calculating the difference between the red light time and the green light starting time <math><mrow><msub><mi>t</mi><mn>1</mn></msub><mo>=</mo><munderover><mi>Σ</mi><mrow><mi>j</mi><mo>=</mo><mn>1</mn></mrow><mi>k</mi></munderover><mo>|</mo><msub><mi>t</mi><mi>red</mi></msub><mo>-</mo><msub><mi>t</mi><mi>green</mi></msub><mo>|</mo><mo>,</mo></mrow></math> And t is t0-t1. When (1, 1), N is N-k, when (0, 0), N is N-k-2, and when (1, 0) or (0, 1), N is N-k-1.
Therefore, the headway is as follows:
and secondly, statistical data analysis, wherein the main function of the statistical data analysis is to adopt a fuzzy c-means clustering analysis means combining subtractive clustering and clustering effectiveness judgment aiming at a data dictionary of each intersection to obtain traffic data characteristics of the intersection, establish a reasonable flow segment division threshold capable of reflecting the internal structure of intersection data, and lay a foundation for algorithm adaptability analysis. Taking the intersection of the Huairou road bureau as an example, taking 24h as statistical time, analyzing traffic flow data from 4-20 days in 2009 to 4-24 days in 2009, taking vehicle flow of every 15min as a data point, and performing data analysis by using a fuzzy c-means clustering method to obtain a reasonable flow segment division threshold (shown in fig. 7) reflecting the internal structure of the intersection traffic flow data, establishing a statistical database reflecting the statistical characteristics of the intersection traffic flow, and laying a foundation for algorithm adaptability analysis.
(3) The real-time data and the statistical data of the signalized intersection extracted by the data processing module are used for a method simulation, selection and evaluation decision platform. The real-time data is used for controlling algorithm selection and online simulation; statistical data for algorithm adaptability analysis.
3. Control algorithm adaptive offline analysis module
In order to meet the requirement of huge state space description of intersection signal lamp control modes and realize the parallel simulation technology and the algorithm on-line evaluation function, Paramics is selected as simulation software.
Paramics (PARAllel Microscopic simulator) is a product of Quadstone Limited, UK, and it employs parallel processing technology to simulate various road networks from single node to national scale. The road/network scale can reach 100 ten thousand nodes, 400 ten thousand road sections and 32000 areas at most, 25 ten thousand vehicles are calculated simultaneously, and the speed is faster than real time. In addition, Paramics provides an API function for secondary development, can realize the linkage with other simulation programs, geographic information software, databases and the like, and realizes man-machine interaction.
The Paramics has a road network evaluation function, the generated simulation evaluation report is divided into a simulation operation report, a statistical report, an analyzer report and GEH calibration evaluation, an evaluation data report is synchronously generated according to data simulated by the Paramics, the report can be read by EXCEL and the like at the same time, the simulation evaluation report is conveniently linked with a simulation evaluation platform built by MATLAB, the on-line evaluation function of a signal control algorithm is realized, and the whole algorithm selection module comprises two parts of contents.
The module mainly completes the off-line analysis of the control algorithm. Based on the reasonable flow segment division of each intersection obtained by processing statistical data in the data processing module, Paramics simulation software is applied, the evaluation index of the minimum delay of the intersection is used, and the adaptability of different control algorithms relative to the traffic state characteristics of the intersection is researched by off-line simulation, so that the optimal traffic flow matching relation aiming at the different control algorithms is established, and a matching rule base of the intersection flow segment and the signal control algorithm is established (refer to fig. 3). The research and implementation of any control algorithm need to perform adaptive analysis of the control algorithm based on paramics simulation software, store the analysis result in a database, and establish the matching relationship between various control algorithms and traffic states in an off-line manner. For example, at the intersection of the wye road bureau, attempts were made to use "game theory-based traffic signal control" -a new signal control algorithm. Establishing a Huairou simulation road network based on Paramics, and setting the phase number of an intersection according to the actual situation, wherein the intersection has two phases: straight, left and straight, right. Through simulation research, the control algorithm is suitable for the situation that the traffic flow is asymmetric, and is suitable when the east-west vehicle flow is 800veh/h and the north-south vehicle flow is 200veh/h (as shown in FIG. 8). Therefore, aiming at different control algorithms, through a large amount of simulation researches, a traffic flow matching relation adaptive to the control algorithms can be established, and a basis is provided for the use and implementation of control strategies.
4. Control algorithm on-line selection module
And on the basis of the real-time data obtained from the data processing module, selecting a signal control algorithm matched with the real-time traffic data on line according to a control algorithm adaptability matching rule base established by a simulation research institute of the control algorithm (refer to fig. 4). In order to ensure the effectiveness of the control algorithm, a parallel decision support evaluation system (refer to fig. 5) based on Paramics is applied to evaluate the effectiveness of the control algorithm on line in the current real-time traffic state, so as to provide a decision support basis for a user whether to apply the algorithm.
5. Signal module
And downloading a control algorithm for finishing the effect evaluation by the decision support system to the annunciator through an external interface of the annunciator to execute the algorithm.
Finally, it should be noted that: the above embodiments are only used for illustrating the present invention and do not limit the technical solutions described in the present invention; therefore, although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art that the present invention may be modified and equivalents may be substituted; all such modifications and variations are intended to be included herein within the scope of this disclosure and the present invention and protected by the following claims.
Claims (4)
1. A traffic signal control system and method based on parallel simulation technology comprises a data acquisition module, a data processing module, an algorithm adaptability off-line analysis module, an algorithm on-line selection module and a signal machine execution module, and is characterized in that: the data acquisition module comprises a detector and a data transmission unit, wherein the detector is buried at the signal intersection and is used for acquiring the traffic flow information of the intersection in real time, and the data transmission unit is responsible for transmitting the acquired information to the data processing module; the data processing module comprises a real-time data processing unit, a data statistical analysis unit and a data dictionary, wherein the input end of the real-time data processing unit is connected with the output end of the data transmission unit in the data acquisition module, and calculates traffic flow data according to the data acquired by the detector, and then stores the traffic flow data in the database to establish a signalized intersection data dictionary; a data statistical analysis unit in the data processing module applies a fuzzy C-means clustering analysis method to intersection traffic flow information in a data dictionary, wherein the algorithm is a fuzzy C-means clustering algorithm combining subtractive clustering and clustering effectiveness judgment, and determines a reasonable flow segment division threshold value reflecting the internal structure of intersection data; the algorithm adaptability offline analysis module adopts simulation software, performs adaptability condition analysis on various control algorithms according to flow segment thresholds divided by the data statistical analysis unit and based on the evaluation index with the minimum intersection average delay, and establishes a matching rule base between the various control algorithms and a traffic flow segment; the algorithm on-line selection module is used for applying simulation software, adopting a parallel simulation technology, selecting a signal control algorithm matched with the real-time traffic flow on line according to the real-time traffic flow information and the control algorithm adaptive conditions in the matching rule base, carrying out on-line simulation on the selected control algorithm, and giving out an evaluation index of signal control in real time to serve as a decision support for further implementing the algorithm; and the signal machine execution module specifically selects and executes an optimal control algorithm according to the evaluation result of the parallel online simulation, and completes the implementation of the optimal control scheme of the signalized intersection through a communication interface provided by the signal machine.
2. The traffic signal control system based on the parallel simulation technology as claimed in claim 1, wherein: the detector in the data acquisition module can adopt a coil vehicle detector with level output and also can adopt a video detector, and the frequency of traffic flow data acquisition and transmission is in the order of seconds.
3. A traffic signal control method based on a parallel simulation technology is characterized in that: the traffic signal control system of claim 1 or 2, performed by the steps of:
step 1: data acquisition
The detector buried at the signal intersection is used for acquiring the traffic flow information of the intersection in real time;
step 2: data processing
Step 2.1: the real-time data processing unit in the data processing module calculates traffic flow data according to the data collected by the detector;
step 2.2: storing traffic flow data in a database, and establishing a signalized intersection data dictionary;
step 2.3: a data statistical analysis unit in the data processing module applies a fuzzy c-means clustering Sub _ FCM method to the intersection traffic flow data for traffic clustering analysis, and determines a reasonable flow segment division threshold value reflecting the internal structure of intersection data;
and step 3: algorithm adaptive offline analysis
Simulation software in the algorithm adaptability offline analysis module performs adaptability condition analysis on various control algorithms according to flow segment thresholds divided by clustering analysis of the data statistical analysis unit and based on the evaluation index with the minimum intersection average delay, namely, the various control algorithms can obtain the optimal control effect when used in which traffic flow segment, thereby establishing a matching rule base between the various control algorithms and the traffic flow segment.
And 4, step 4: algorithm online selection
Applying simulation software, adopting a parallel simulation technology, selecting a signal control algorithm matched with the real-time traffic flow on line according to the real-time traffic flow information and the adaptive conditions of the control algorithm in the matching rule base, carrying out on-line simulation on the selected control algorithm, and giving an evaluation index of signal control in real time to serve as a decision support for further implementing the algorithm;
and 5: semaphore execution
And according to the evaluation result of the parallel online simulation, specifically selecting and executing an optimal control algorithm, and completing the implementation of the optimal control scheme of the signalized intersection through a communication interface provided by the signaler.
4. The traffic signal control method based on the parallel simulation technology as claimed in claim 3, wherein: the signalized intersection data dictionary comprises intersection real-time traffic flow, time occupancy, average headway and average vehicle speed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010108763A CN101789182B (en) | 2010-02-05 | 2010-02-05 | Traffic signal control system and method based on parallel simulation technique |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010108763A CN101789182B (en) | 2010-02-05 | 2010-02-05 | Traffic signal control system and method based on parallel simulation technique |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101789182A true CN101789182A (en) | 2010-07-28 |
| CN101789182B CN101789182B (en) | 2012-10-10 |
Family
ID=42532383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201010108763A Expired - Fee Related CN101789182B (en) | 2010-02-05 | 2010-02-05 | Traffic signal control system and method based on parallel simulation technique |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101789182B (en) |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102645930A (en) * | 2012-05-07 | 2012-08-22 | 同济大学 | Hardware in-loop simulation test system for traffic signal control system |
| CN102945607A (en) * | 2012-11-19 | 2013-02-27 | 西安费斯达自动化工程有限公司 | On-line predictive control method of traffic bottlenecks based on field programmable gate array (FPGA) and improved Aw-Rascle model |
| WO2013097112A1 (en) * | 2011-12-28 | 2013-07-04 | 中国科学院自动化研究所 | Parallel transportation signal control system |
| CN103337161A (en) * | 2013-07-11 | 2013-10-02 | 上海济安交通工程咨询有限公司 | Optimization method of intersection dynamic comprehensive evaluation and signal control system based on real-time simulation model |
| CN103593535A (en) * | 2013-11-22 | 2014-02-19 | 南京洛普股份有限公司 | Urban traffic complex self-adaptive network parallel simulation system and method based on multi-scale integration |
| CN103971517A (en) * | 2014-05-19 | 2014-08-06 | 迈锐数据（北京）有限公司 | Real-time data traffic simulation method and system |
| CN105224384A (en) * | 2015-08-28 | 2016-01-06 | 杭州鼎鹏交通科技有限公司 | A kind of traffic control algorithm real-time simulation evaluation system |
| CN105761515A (en) * | 2016-01-29 | 2016-07-13 | 吴建平 | Road crossing signal dynamic regulation method, device and system |
| CN104157151B (en) * | 2014-06-13 | 2016-08-24 | 东南大学 | The Synergistic method that urban traffic guidance controls with signal |
| CN105913672A (en) * | 2016-06-28 | 2016-08-31 | 广东振业优控科技股份有限公司 | Intersection traffic signal control scheme recording and design method based on VISIO |
| CN107734482A (en) * | 2017-09-11 | 2018-02-23 | 西安电子科技大学 | The content distribution method unloaded based on D2D and business |
| CN108242977A (en) * | 2017-12-26 | 2018-07-03 | 深圳市超思维电子股份有限公司 | A kind of data processing method, data processing equipment and electronic equipment |
| CN108364483A (en) * | 2018-02-22 | 2018-08-03 | 清华大学 | Single Intersection signal timing dial method based on Cooperative Game Theory cost sharing method |
| CN108364484A (en) * | 2018-02-22 | 2018-08-03 | 清华大学 | A kind of Single Intersection signal timing dial method based on Sequential Game |
| CN108847037A (en) * | 2018-06-27 | 2018-11-20 | 华中师范大学 | A kind of city road network paths planning method towards non-global information |
| CN109003459A (en) * | 2018-07-17 | 2018-12-14 | 泉州装备制造研究所 | A kind of regional traffic signal control method and system based on layering stream calculation |
| CN109191875A (en) * | 2018-09-17 | 2019-01-11 | 杭州中奥科技有限公司 | Signal timing plan generation method and device |
| CN109887284A (en) * | 2019-03-13 | 2019-06-14 | 银江股份有限公司 | A kind of smart city traffic signalization recommended method, system and device |
| CN110942627A (en) * | 2019-11-27 | 2020-03-31 | 北京建筑大学 | Road network coordination signal control method and device for dynamic traffic |
| CN111183465A (en) * | 2018-10-16 | 2020-05-19 | 北京嘀嘀无限科技发展有限公司 | Adaptive traffic control using vehicle trajectory data |
| CN111383453A (en) * | 2020-02-18 | 2020-07-07 | 山东摩西网络科技有限公司 | Traffic signal control on-line simulation and real-time tracking feedback system and operation method |
| CN107817696B (en) * | 2017-10-13 | 2021-01-05 | 武汉科技大学 | Microcosmic traffic semi-physical simulation tool |
| CN112905475A (en) * | 2021-03-11 | 2021-06-04 | 湖南化工职业技术学院（湖南工业高级技工学校） | Software testing platform based on computer |
| CN113077640A (en) * | 2021-04-13 | 2021-07-06 | 广东振业优控科技股份有限公司 | Ring intersection traffic organization method, system and medium based on upstream intersection coordination control of inlets |
| CN113077641A (en) * | 2021-03-24 | 2021-07-06 | 中南大学 | Decision mapping method and device for bus on-the-way control and storage medium |
| CN113223293A (en) * | 2021-05-06 | 2021-08-06 | 杭州海康威视数字技术股份有限公司 | Road network simulation model construction method and device and electronic equipment |
| CN113377092A (en) * | 2021-08-12 | 2021-09-10 | 深圳市城市交通规划设计研究中心股份有限公司 | Signal priority algorithm simulation test method and system, test equipment and storage medium |
| CN114333301A (en) * | 2021-12-06 | 2022-04-12 | 北京东土正创科技有限公司 | Traffic signal control optimization method and system and traffic signal optimization equipment |
| CN116758762A (en) * | 2023-05-05 | 2023-09-15 | 无锡多优多网络科技有限公司 | Control method based on big data |
-
2010
- 2010-02-05 CN CN201010108763A patent/CN101789182B/en not_active Expired - Fee Related
Cited By (43)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013097112A1 (en) * | 2011-12-28 | 2013-07-04 | 中国科学院自动化研究所 | Parallel transportation signal control system |
| CN102645930A (en) * | 2012-05-07 | 2012-08-22 | 同济大学 | Hardware in-loop simulation test system for traffic signal control system |
| CN102945607A (en) * | 2012-11-19 | 2013-02-27 | 西安费斯达自动化工程有限公司 | On-line predictive control method of traffic bottlenecks based on field programmable gate array (FPGA) and improved Aw-Rascle model |
| CN102945607B (en) * | 2012-11-19 | 2015-02-04 | 西安费斯达自动化工程有限公司 | On-line predictive control method of traffic bottlenecks based on field programmable gate array (FPGA) and improved Aw-Rascle model |
| CN103337161A (en) * | 2013-07-11 | 2013-10-02 | 上海济安交通工程咨询有限公司 | Optimization method of intersection dynamic comprehensive evaluation and signal control system based on real-time simulation model |
| CN103593535B (en) * | 2013-11-22 | 2017-02-22 | 南京洛普股份有限公司 | Urban traffic complex self-adaptive network parallel simulation system and method based on multi-scale integration |
| CN103593535A (en) * | 2013-11-22 | 2014-02-19 | 南京洛普股份有限公司 | Urban traffic complex self-adaptive network parallel simulation system and method based on multi-scale integration |
| CN103971517A (en) * | 2014-05-19 | 2014-08-06 | 迈锐数据（北京）有限公司 | Real-time data traffic simulation method and system |
| CN104157151B (en) * | 2014-06-13 | 2016-08-24 | 东南大学 | The Synergistic method that urban traffic guidance controls with signal |
| CN105224384A (en) * | 2015-08-28 | 2016-01-06 | 杭州鼎鹏交通科技有限公司 | A kind of traffic control algorithm real-time simulation evaluation system |
| CN105224384B (en) * | 2015-08-28 | 2018-07-27 | 杭州鼎鹏交通科技有限公司 | A kind of traffic control algorithm real-time simulation evaluation system |
| CN105761515A (en) * | 2016-01-29 | 2016-07-13 | 吴建平 | Road crossing signal dynamic regulation method, device and system |
| CN105761515B (en) * | 2016-01-29 | 2018-07-24 | 吴建平 | A kind of intersection signal dynamic adjusting method and device, system |
| CN105913672A (en) * | 2016-06-28 | 2016-08-31 | 广东振业优控科技股份有限公司 | Intersection traffic signal control scheme recording and design method based on VISIO |
| CN107734482A (en) * | 2017-09-11 | 2018-02-23 | 西安电子科技大学 | The content distribution method unloaded based on D2D and business |
| CN107734482B (en) * | 2017-09-11 | 2019-10-11 | 西安电子科技大学 | The content distribution method unloaded based on D2D and business |
| CN107817696B (en) * | 2017-10-13 | 2021-01-05 | 武汉科技大学 | Microcosmic traffic semi-physical simulation tool |
| CN108242977A (en) * | 2017-12-26 | 2018-07-03 | 深圳市超思维电子股份有限公司 | A kind of data processing method, data processing equipment and electronic equipment |
| CN108364483B (en) * | 2018-02-22 | 2020-07-14 | 清华大学 | Single-intersection signal timing method based on cooperative game theory cost allocation method |
| CN108364483A (en) * | 2018-02-22 | 2018-08-03 | 清华大学 | Single Intersection signal timing dial method based on Cooperative Game Theory cost sharing method |
| CN108364484A (en) * | 2018-02-22 | 2018-08-03 | 清华大学 | A kind of Single Intersection signal timing dial method based on Sequential Game |
| CN108364484B (en) * | 2018-02-22 | 2021-03-30 | 清华大学 | Single-intersection signal timing method based on sequential game |
| CN108847037A (en) * | 2018-06-27 | 2018-11-20 | 华中师范大学 | A kind of city road network paths planning method towards non-global information |
| CN109003459A (en) * | 2018-07-17 | 2018-12-14 | 泉州装备制造研究所 | A kind of regional traffic signal control method and system based on layering stream calculation |
| CN109191875A (en) * | 2018-09-17 | 2019-01-11 | 杭州中奥科技有限公司 | Signal timing plan generation method and device |
| CN109191875B (en) * | 2018-09-17 | 2020-12-29 | 杭州中奥科技有限公司 | Signal control scheme generation method and device |
| CN111183465A (en) * | 2018-10-16 | 2020-05-19 | 北京嘀嘀无限科技发展有限公司 | Adaptive traffic control using vehicle trajectory data |
| CN111183465B (en) * | 2018-10-16 | 2021-03-23 | 北京嘀嘀无限科技发展有限公司 | Adaptive traffic control using vehicle trajectory data |
| CN109887284A (en) * | 2019-03-13 | 2019-06-14 | 银江股份有限公司 | A kind of smart city traffic signalization recommended method, system and device |
| CN109887284B (en) * | 2019-03-13 | 2020-08-21 | 银江股份有限公司 | Smart city traffic signal control recommendation method, system and device |
| CN110942627A (en) * | 2019-11-27 | 2020-03-31 | 北京建筑大学 | Road network coordination signal control method and device for dynamic traffic |
| CN110942627B (en) * | 2019-11-27 | 2020-11-03 | 北京建筑大学 | Road network coordination signal control method and device for dynamic traffic |
| CN111383453A (en) * | 2020-02-18 | 2020-07-07 | 山东摩西网络科技有限公司 | Traffic signal control on-line simulation and real-time tracking feedback system and operation method |
| CN112905475A (en) * | 2021-03-11 | 2021-06-04 | 湖南化工职业技术学院（湖南工业高级技工学校） | Software testing platform based on computer |
| CN112905475B (en) * | 2021-03-11 | 2022-09-06 | 湖南化工职业技术学院（湖南工业高级技工学校） | Software testing platform based on computer |
| CN113077641A (en) * | 2021-03-24 | 2021-07-06 | 中南大学 | Decision mapping method and device for bus on-the-way control and storage medium |
| CN113077640A (en) * | 2021-04-13 | 2021-07-06 | 广东振业优控科技股份有限公司 | Ring intersection traffic organization method, system and medium based on upstream intersection coordination control of inlets |
| CN113223293A (en) * | 2021-05-06 | 2021-08-06 | 杭州海康威视数字技术股份有限公司 | Road network simulation model construction method and device and electronic equipment |
| CN113223293B (en) * | 2021-05-06 | 2023-08-04 | 杭州海康威视数字技术股份有限公司 | Road network simulation model construction method and device and electronic equipment |
| CN113377092A (en) * | 2021-08-12 | 2021-09-10 | 深圳市城市交通规划设计研究中心股份有限公司 | Signal priority algorithm simulation test method and system, test equipment and storage medium |
| CN114333301A (en) * | 2021-12-06 | 2022-04-12 | 北京东土正创科技有限公司 | Traffic signal control optimization method and system and traffic signal optimization equipment |
| CN114333301B (en) * | 2021-12-06 | 2023-09-26 | 北京东土正创科技有限公司 | Traffic signal control optimization method, system and traffic signal optimization equipment |
| CN116758762A (en) * | 2023-05-05 | 2023-09-15 | 无锡多优多网络科技有限公司 | Control method based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101789182B (en) | 2012-10-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101789182B (en) | Traffic signal control system and method based on parallel simulation technique | |
| CN108428348B (en) | Road traffic optimization method and device and electronic equipment | |
| WO2019047905A1 (en) | Road traffic analysis system, method and apparatus | |
| CN108428338B (en) | Traffic road condition analysis method and device and electronic equipment | |
| CN104157139B (en) | A kind of traffic congestion Forecasting Methodology and method for visualizing | |
| CN101727746B (en) | Method for dynamically estimating travel time of motor vehicle on urban road under control of signal lamps | |
| CN102087788A (en) | Method for estimating traffic state parameter based on confidence of speed of float car | |
| CN104464310A (en) | Signal collaborative optimization control method and system of multiple intersections of urban region | |
| CN102708688A (en) | Secondary fuzzy comprehensive discrimination-based urban road condition recognition method | |
| Zhang et al. | Optimal signal timing method of intersections based on bus priority | |
| CN102610092A (en) | Urban road speed predication method based on RBF (radial basis function) neural network | |
| CN106971535B (en) | A kind of urban traffic blocking index computing platform based on Floating Car GPS real time data | |
| CN102708698A (en) | Vehicle optimal-path navigation method based on vehicle internet | |
| CN104112357B (en) | A kind of urgent emergency planning method of city area-traffic of severe haze weather | |
| CN109272746A (en) | A kind of MFD estimating and measuring method based on BP neural network data fusion | |
| CN112950940B (en) | Traffic diversion method in road construction period | |
| CN109272745A (en) | A kind of track of vehicle prediction technique based on deep neural network | |
| CN109308805A (en) | A kind of road network MFD estimating and measuring method based on self-adaptive weighted average data fusion | |
| CN104298540A (en) | Underlaying model parameter correction method of microscopic traffic simulation software | |
| CN107680391A (en) | Two pattern fuzzy control methods of crossroad access stream | |
| CN101877169A (en) | Data fusion system and method for controlling balance of multi-intersection traffic flow of trunk road | |
| CN107240264A (en) | A kind of non-effective driving trace recognition methods of vehicle and urban road facility planing method | |
| CN112967493A (en) | Neural network-based prediction method for vehicle passing intersection travel time | |
| CN106846808B (en) | A kind of vehicle parking based on license plate data time number calculating method | |
| CN112699535A (en) | Adaptive control method for overhead ground linkage traffic signal area |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20121010 Termination date: 20140205 |