CN102708679A - Method for forecasting short-time traffic flows at urban signalized intersections - Google Patents
Method for forecasting short-time traffic flows at urban signalized intersections Download PDFInfo
- Publication number
- CN102708679A CN102708679A CN201210183958XA CN201210183958A CN102708679A CN 102708679 A CN102708679 A CN 102708679A CN 201210183958X A CN201210183958X A CN 201210183958XA CN 201210183958 A CN201210183958 A CN 201210183958A CN 102708679 A CN102708679 A CN 102708679A
- Authority
- CN
- China
- Prior art keywords
- crossing
- time
- short
- traffic flow
- time traffic
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000011144 upstream manufacturing Methods 0.000 claims abstract description 4
- CYTYCFOTNPOANT-UHFFFAOYSA-N Perchloroethylene Chemical compound ClC(Cl)=C(Cl)Cl CYTYCFOTNPOANT-UHFFFAOYSA-N 0.000 claims description 5
- 230000007246 mechanism Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- WPPDXAHGCGPUPK-UHFFFAOYSA-N red 2 Chemical compound C1=CC=CC=C1C(C1=CC=CC=C11)=C(C=2C=3C4=CC=C5C6=CC=C7C8=C(C=9C=CC=CC=9)C9=CC=CC=C9C(C=9C=CC=CC=9)=C8C8=CC=C(C6=C87)C(C=35)=CC=2)C4=C1C1=CC=CC=C1 WPPDXAHGCGPUPK-UHFFFAOYSA-N 0.000 claims description 3
- 230000007306 turnover Effects 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 description 11
- 230000006399 behavior Effects 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 9
- 238000005457 optimization Methods 0.000 description 8
- 238000011160 research Methods 0.000 description 8
- 241001417517 Scatophagidae Species 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000008901 benefit Effects 0.000 description 6
- 230000003044 adaptive effect Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000013178 mathematical model Methods 0.000 description 4
- 238000013456 study Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 2
- 238000000819 phase cycle Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 238000004804 winding Methods 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000009933 burial Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Abstract
The invention discloses a method for forecasting short-time traffic flows at urban signalized intersections. The method comprises the following steps: forecasting the waiting pass-through time of an upstream single intersection; estimating the spatial steering rate of the upstream single intersection; and creating a short-time traffic flow forecasting double-layered model of the urban signalized intersection. Short-time traffic flow forecasting is a main component for realizing traffic real-time self-adaptive control to urban main roads. The method provided by the invention achieves the self-adaptive capability of signalized intersections and improves the service level and efficiency of the intersections.
Description
Technical field
The present invention relates to the intelligent transport technology field, relate in particular to a kind of city signalized intersections short-time traffic flow forecast method.
Background technology
Intersection signal control originates from Britain in 1868 the earliest as the important step of modern urban road traffic control system, and in 1912 first in the Cleveland, Ohio, Usa; Attempt adopting red green two kinds of color signals to control traffic (referring to Van Katwijk; R.T., 2008.Multi-Agent Look-Ahead Traffic-Adaptive Control [D] .Ph.D dissertation, Delft University of Technology; Delft, Netherland; Pline, J.L., 2001.Traffic Control Devices Handbook 2001:An ITE Informational Report [R] .Institute of Transportation Engineers; U.S.Department of Transportation; Federal Highway Administration; 2009.Manual on Uniform Traffic Control Devices (MUTCD) [EB]; Http:// mutcd.fhwa.dot.gov/pdfs/2009/pdf_index.htm, access on Jan 12,2012; Yang Xiaoguang, 2004. traffic control and management systematic studyes [J], traffic and transportation system engineering and information, 4 (2): 79-83 towards the advanced person of Chinese city; ).With SCOOT is the adaptive control system of representative, calculates the volume of traffic, holding time, occupation rate and the degree of crowding according to the real time data that detecting device obtains.Simultaneously, the traffic parameter in conjunction with storage in advance carries out wagon flow prediction in short-term to each crossing.In order to follow the tracks of the transient change of traffic flow, the optimizer of SCOOT adopts little increment optimization method, and promptly the signal timing dial parameter can be made corresponding subtle change with the variation that traffic flow distributes; Accomplish the continuous motion of traffic is hindered minimum as far as possible, do not discover (fourth flower bud, 2009. short-time traffic flow forecast method researchs [D] again towards urban traffic control for traffic participant; Dalian University of Technology; Dalian, Liaoning), system obtains relevant control strategy model through the emulation of mathematical model; Thereby require abstract mathematical model in the short period, reflect the running status of system exactly, otherwise can influence the control effect.On the other hand, the degree of accuracy of mathematical model is high more, and structure is more complicated, and simulation time is also long more, will between real-time and reliability, produce contradiction; Particularly under some accident traffic behaviors, for example account for road construction, adverse weather, large-scale activity etc., when requiring further to improve traffic efficiency, this contradiction can be more outstanding.A method that improves precision of prediction is in implementation process, the toroid winding of wagon detector in the SCOOT system is embedded in the outlet of intersection, the upper reaches.Yet except that the California, USA few cities, coil is only laid at Parking Entrance in the letter control crossing in most cities in the world; Work to trigger traffic signals (Nobe; S., 1997.On-line estimation of traffic split parameters based on lane counts [D] .Ph.D.Dissertation, The University of Arizona; Tucson, Arizona).The crossing of China's existing trigger-type signal controlling in most of city, coil also only is embedded in Parking Entrance.If increase coil at exit ramp, with unavoidably bringing bigger additional purchasing and executive cost.Reflect this, problem the most basic is exactly how under facilities Allocation such as existing controller for urban single intersection device, signal lamp and coil, through improving, improving the forecasting traffic flow mathematical model, reaches the purpose that improves the adaptive control system performance.
Existing short-time traffic flow forecast model investigation common method has Kalman filtering (Xie, Y.-C., Zhang both at home and abroad; Y.-L., Ye, Z.-R.; 2007.Short-term traffic volume forecasting using Kalman flter with discrete wavelet decomposition [J], Computer-Aided Civil and Infrastructure Engineering, 22 (3): 326-334); Neuroid (Guo, J.-H., Williams; B.M., 2010.Real-time short-term traffic speed level forecasting and uncertainty quantification using layered Kalman filters [J] .Transportation Research Record, 2175:28-37.); (woods is grant cloud to ARIMA for Yu Dexin, Yang Zhaosheng; 2004. adaptive traffic signal control system volume forecasting model investigation [J]. the system engineering theory and practice; 12:132-136.), multiple agent (Roozemond, D.A.; 2001.Using intelligent agents for proactive real-time urban intersection control [J] .European Journal of Operation Research, 131:293-301.) etc.Most algorithms are based on history or space-time sequence data, and are emulation or training time that complex structure and needs are long, not high to the accuracy of big city accident status predication.
Specific to the forecasting traffic flow model; Existing research mainly comprise the statistical parameter method that is the basis with mathematical methods such as traditional mathematical statistics, infinitesimal analysis and with the modern technologies method (like analogue technique; Neural network, fuzzy control etc.) be the non-parametric estmation method of main means.Early stage statistical parameter method comes from predictive control theory and various prediction algorithm in the industrial control field; Be master (Smith mainly with the historical method of average and smoothing technique; B.L., Demetsky, M.J.; 1997.Traffic flow forecasting:Comparison of modeling approaches [J] .Journal ofTransportation Engineering-ASCE, 123 (4): 261-266.).Yet the method for average and smoothing method tend to outstanding average, ignore extreme case; The comparatively extreme behavior of need paying attention in the actual traffic of opposition just: the peak state and when fluctuating fast from crowded (Stop-And-Go) especially to transition process of free flow (Free Flow).
With the modern technologies method is that the non-ginseng of core is estimated rule mainly based on the principle of artificial intelligence, pattern-recognition and chaos system, and core is artificial identification and current traffic behavior in the close data of given predicting interval behavior, the method for employing non parametric regression (perhaps neuroid); The traffic behavior of target of prediction time (flow, speed and density) (Smith, B.L.; Williams; B.M., Oswald, R.K.; 2002.Comparison of parametric and nonparametric models for traffic flow forecasting [J] .Transportation Research Part C, 10 (4): 303-321; Jiang, X., Adeli, H., 2005.Dynamic wavelet neural network model for traffic flow forecasting [J] .Journal of Transportation Engineering-ASCE, 131 (10): 771-779.).With respect to statistical parameter method (like the historical method of average or ARIMA etc.), it is simple that non-ginseng method has model parameter, need not suppose that traffic behavior is advantage such as to seamlessly transit from a period to another period; To different data, possess portable preferably (adaptability) and robustness.Yet similar with artificial intelligence approach, the non-parametric estmation method is that the typical case is based upon the intensive process on the mass data basis, and in practical application, traffic forecast is difficult to obtain magnanimity and imports data accurately.In addition, the learning method of neural network adopts the empiric risk minimization principle, and expected risk is minimized, and has defective in theory, and needs to confirm network structure, crosses study and owe problems such as study and local optimum point.
(1) SCOOT system short-time traffic flow forecast model
As previously mentioned; The forecasting traffic flow model of SCOOT system is through the intersection exit place buries underground and detects toroid winding (burial place apart from intersection entrance 50-300 rice) at the upper reaches; Prediction crossing, downstream vehicle arrives and fluctuations in discharge; Thereby in follow-up signal optimizing timing, take little increment optimizing, optimize the signal parameter timing with the variation that traffic flow distributes.Upper reaches intersection exit detecting device obtains after the telecommunication flow information; Through handling; (Cyclic Flow Profiles CFP), combines static parameter (fleet's running time of storage in advance to formation cycle profile of flowrate again; Signal phase order and time etc.) be optimized, generate the best of breed of signal timing dial.The time reference line of an expression " current time " is arranged in the SCOOT model, move right in time; A signal period finishes, and this datum line returns the leftmost side again, sets up the traffic flow distribution plan of following one-period.So move in circles; Dynamic traffic flow point Butut on can this cross section; Predict vehicle queue situation (suppose that this highway section Vehicle Speed and road section length are known, can infer when the vehicle in the traffic flow distribution plan can arrive downstream intersection parking line) (Robertson, the D.I. of crossing, downstream more thus; Bretherton; R.D., 1991.Optimizingnetworks oftraffic signals in real time-the SCOOT method [J] .IEEE Transaction on Vehicular Technology, 40 (1): 11-15.).Thereby whether the signal condition and the queuing situation of acquisition respective downstream target crossing need queuing when arriving with decision prediction vehicle.In view of above principle and advantage, the SCOOT system is widely used in China Beijing, cities such as Chengdu at present.But the inherent characteristics of this system has determined to exist in its implementation process following problem: it is inconsistent that 1.SCOOT system and existing trigger-type intersection signal control detection device are laid rule, can't make full use of existing resource.Detecting device installation position (intersection exit road) has determined that its predicted time is shorter, can't satisfy the needs (being not enough to form the magnitude of traffic flow distribution plan of one-period) of longer predicted time window, influences the optimization of control decision.2.SCOOT system can't solve through the vehicle stop off of crossing, the upper reaches or drive towards other branch road etc., does not drive towards the situation of downstream intersection parking line.3. the estimation accuracy of the variation of highway section saturation volume in addition,, fleet's dissipation coefficient and travel speed etc. also directly influences the prediction of crossing queue length.Therefore, SCOOT system accuracy requirement to static parameter when modelling is higher.
(2) SCATS system short-time traffic flow forecast model
The SCATS system is researched and developed by New South Wales,Australia road traffic office; Its principal feature adopts three grades to coordinate distributed control structure (central controlled stage; Regional coordination controlled stage and crossing controlled stage) (Lowrie; P.R., 1992.SCATS:A traffic responsive method of controlling urban traffic control [R] .Roads and Traffic Authority.).The wagon detector of SCATS is installed on the intersection parking line, through real-time collection and the analysis to transport information, according to the traffic of continuous variation, proposes optimum control scheme in real time, guarantees unimpeded, the quick and safety of traffic.The optimal combination of the cycle of SCATS system, split and phase differential is stored in predetermined a plurality of scheme, can select according to the traffic intensity value of actual measurement.For example, four split schemes are prepared for each crossing in advance by system, are directed against the crossing respectively under four kinds of load conditions that possibly occur, and each phase place green time accounts for the ratio value of signal period length; System can change phase sequence or skip next phase place according to transport need, in time responds the transport need in each cycle.
The advantage of SCATS system is: select the intersection signal scheme through information acquisition, come standard to coordinate the vehicle drive behavior of control section through this scheme, reach the optimization that road vehicle goes.Its great advantage is to make full use of the existing resource (wagon detector etc.) of trigger-type signalized intersections, with low input, at utmost brings into play the economic benefit and the social benefit of traffic.Therefore, this system is widely used in the crossing of sections, city such as Shanghai, Hangzhou, Shenyang, Guangzhou at present.But owing to do not use traffic model in the system, belong in essence possess certain inducibility, based on the Scheme Choice system of actual wagon flow, thereby limited timing scheme optimization process, dirigibility is not enough.In addition,, be difficult to monitor advancing of fleet, cause the preferred reliability of the actual green time difference relatively poor because the wagon detector in the SCATS system is installed near the stop line.
(3) RHODES system short-time traffic flow forecast model
RHODES be by the exploitations such as professor Mirchandani of Arizona, USA university a kind of in real time, pass rank, optimized distributed system; Its core wagon flow prediction algorithm is the Predict model, and the phase optimization algorithm is COP (Controlled, Optimization ofPhases; The phase place optimized controllable) algorithm (Mirchandani; P.M., Wang, F.Y.; 2005.RHODES to intelligent transportation systems [J] .IEEE Intelligent Systems, 20 (1): 10-15; Sen, S., Head, L., 1997.Controlled, optimization of Phases at an intersection [J], Transportation Science, 31 (1): 5-17.).The RHODES system can be divided into three layers and pass rank on control structure, be respectively from bottom to top: crossing key-course, network flow key-course and offered load Distribution Layer.Also correspondingly on Forecasting Methodology equally be divided into three levels: key-course in the crossing; Main traffic flow and various constraint condition according to measurement is in real time carried out the crossing volume forecasting, uses the COP algorithm that phase sequence is controlled (to be unit second) with phase lengths (bit duration mutually); At the network flow key-course, mainly network flow (being the travel conditions of fleet) is predicted, for setting up coordination constraint (every 200-300 second once) in each crossing in the network; At the offered load Distribution Layer, total transport need is predicted (to be generally 1 hour) mainly to over a long time, confirms the running load of whole transportation network in the future in advance.The wagon detector of RHODES system is laid in the porch, track (about 50 meters apart from the crossing) of crossing.The Predict algorithm uses the detecting device image data that is installed in intersection entrance place, the upper reaches; Signal time distributing conception in conjunction with concrete traffic conditions and crossing, the upper reaches; Come the vehicle of following period of target of prediction crossing to arrive situation; And predicted value is tested and proofread and correct through target crossing detecting device, improve the accuracy that predicts the outcome.Because the running time from crossing, the upper reaches to current crossing is longer, and possibly meet with the delay of red light phase place in crossing, the upper reaches, so model allows long predicted time window.The Predict algorithm is also considered influence and the optimization problem of upper reaches intersection signal to current intersection signal control, the coordination between the adjacent crossing of the system of accomplishing.The installation position of RHODES system detecting device had both guaranteed the accuracy of prediction, had guaranteed longer predicted time window again; Its weak point is that system is fit to half congested traffic conditions, if take place highly congested in trafficly in the highway section, precision of prediction can obviously descend.In addition, the Predict algorithm among the RHODES only provides crossing, the upper reaches and is regularly situation, and considers other letter control pattern, like trigger-type etc.; When prediction crossing, downstream arrived wagon flow, the turning rate of Predict algorithm supposition crossing, the upper reaches was known, and these further in the popularization and the application of actual road network, can produce certain problem to it.
Summary of the invention
The present invention is the weak point that exists in the above-mentioned prior art for avoiding, and the arrival vehicle flowrate of a kind of target of prediction crossing in given interval is provided.
The present invention adopts following technical scheme for the technical solution problem.
A kind of signalized intersections short-time traffic flow forecast method may further comprise the steps:
Single cross prong in the upper reaches is waited for through the time prediction step;
Single cross prong space, upper reaches turning rate estimation steps;
Set up letter control crossing, city short-time traffic flow forecast bilayer model step.
Further; As a kind of preferred; Said upper reaches single cross prong is waited for through the time prediction step and being specially according to the mode of operation of crossing, upper reaches controller and traffic lights phase place for the vehicle that arrives the adjacent upstream crossing; After Parking Entrance detection trigger device, how long prediction can arrive the target downstream crossing.
Further, as a kind of preferred, the mode of operation of crossing, said upper reaches controller is a timing mode.
Further, as a kind of preferred, the mode of operation of crossing, said upper reaches controller is a trigger mode.
Further, as a kind of preferred, said traffic lights phase place is: green 1: be green light time of arrival, and this direction of crossing does not have queuing; Green 2: be green light time of arrival, but this direction has queuing; Red 1: be red light time of arrival, and this direction of crossing does not have queuing; Red 2: be red light time of arrival, but this direction has queuing.
Further; As a kind of preferred; Said upper reaches single cross prong space turning rate estimation steps is specially: suppose that given intersection signal adopts NEMA-8 phase place mechanism, and the distribution of the right-hand rotation vehicle flowrate of all directions Parking Entrance is known, according to the vehicle number conservation of out of phase turnover crossing in the cycle; The wagon flow of 8 phase places of NEMA controller being analyzed one by one all directions concerns, dynamically extrapolates the ratio of turning of these crossing all directions of next cycle.
Further, as a kind of preferred, said letter control crossing, the city short-time traffic flow forecast bilayer model step of setting up is specially: the upper strata arrives, waits for through the time estimation model for letter control crossing vehicle; Lower floor is the ratio of turning appraising model of letter control crossing.
Compared with present technology, beneficial effect of the present invention is embodied in:
The present invention starts with from resolving based on the road traffic state evolution mechanism of crossing driving behavior and signal controlling influence; Explore the urban transportation short-term prediction of confirming under the space resources restriction, thereby reach the purpose of research urban intersection state analysis and adaptive control technology.City area-traffic coordination linkage control theory and control strategy towards implementation process have been proposed.To urban intersection itself; From vehicle arrival wait with through time prediction, the estimation of intersection turning ratio; And city area-traffic is collaborative with a plurality of aspects such as letter control crossing interlock control the regional traffic system is carried out management and control and rationally induce, to reach the operation optimum of traffic network.
Description of drawings
Fig. 1 is a Forecasting Methodology process flow diagram of the present invention;
Fig. 2 is a trigger-type signal controller green time composition diagram;
Fig. 3 is NEMA eight-phase signal controller phase place 1 pairing direction of traffic figure;
Fig. 4 gets into and rolls away from crossing vehicle flow figure in 8 times of NEMA controller phase place.
Below pass through embodiment, and combine accompanying drawing that the present invention is described further.
Embodiment
Referring to Fig. 1, a kind of signalized intersections short-time traffic flow forecast method may further comprise the steps:
S1, upper reaches single cross prong are waited for through the time prediction step;
S2, single cross prong space, upper reaches turning rate estimation steps;
S3, set up letter control crossing, city short-time traffic flow forecast bilayer model step.
This method is from current demand; Start with from adjacent crossing; Through crossing vehicle microscopic behavior is carried out modeling; Adopt the whistle control system and the facility of crossing, the upper reaches, from probability and the corresponding time that each vehicle of microcosmic angle estimation is about to come the target crossing, thereby the target of prediction crossing is in the arrival wagon flow of given interval.
What suppose the employing of crossing, the upper reaches is the whistle control system of classical NEMA-8 phase place; Respectively upper reaches intersection signal is worked under the different situations of timing signal control (fixed time) and trigger-type signal controlling (actuated), arrive the time that vehicle need be waited for respectively.Under every kind of letter control pattern,, carry out modeling to the difference of vehicle arriving signal phase place; In conjunction with the existing queuing situation in crossing, estimate that the arrival vehicle needs the time of waiting for, passing through.
For the crossing that is operated in timing signal control, its stand-by period model comprises following sight:
● green 1: be green light time of arrival, and this direction of crossing does not have queuing;
● green 2: be green light time of arrival, but this direction has queuing;
● red 1: be red light time of arrival, and this direction of crossing does not have queuing;
● red 2: be red light time of arrival, but this direction has queuing.
For the crossing that works in the trigger-type signal controlling, its stand-by period model still can similarly be divided into the traffic lights situation analysis; But because trigger-type control green light and red time are uncertain, so need in green light or red time, further estimate.Concrete research step is following:
1, letter control crossing vehicle arrives and waits for and through time study: to being operated in the crossing of timing signal control, its stand-by period model is divided into four kinds of sights: green 1-time of arrival is a green light, and this direction of crossing does not have queuing; Green 2-time of arrival is a green light, but this direction has queuing; Red 1-time of arrival is a red light, and this direction of crossing does not have queuing; Red 2-time of arrival is a red light, but this direction has queuing.For the crossing that works in the trigger-type signal controlling, arrive the phase place difference according to it, current red time or green time are estimated (because red time and green time are not determined values).The estimation of green time here can be according to the definition (see figure 2) of trigger-type signal controlling; Estimate that according to different triggered time points the triggered time zone can further be subdivided into
and
red time then can be calculated according to the green time of other phase place.
G
Min: minimum green time,
G
Max: maximum green time,
U: unit green extension,
2, letter control crossing Vehicular turn ratio research: suppose that given intersection signal adopts NEMA-8 phase place mechanism; And the right-hand rotation vehicle flowrate of all directions Parking Entrance distributes known; Vehicle number conservation according to out of phase turnover crossing in the cycle; The wagon flow of 8 phase places of NEMA controller being analyzed one by one all directions concerns, dynamically extrapolates the ratio of turning of these crossing all directions of next cycle.
Fig. 3 provides in the NEMA-8 phase control, and phase place 1 is the sight that east-west direction turns left, and supposes:
D
i(l) be illustrated in 1 phase place, leave the crossing toward i (i=E, W, N, S) the actual measurement vehicle number of direction;
Be illustrated in 1 phase place, and the i from the crossing (i=E, W, N, S) direction gets into, and drives towards j (j=E, W, N, the estimated value of vehicle number S);
Thereby, to the north of direction (N) highway section be example, the vehicle number that gets into the crossing has following relation:
In view of common intersection exit road mounting vehicle detecting device not,, come the approximate estimation (see figure 4) at the measured wagon flow number of Δ t after the moment so need utilize the detecting device 1 in intersection entrance road, all directions downstream respectively.For example: the running time of supposition adjacent crossing detecting device from the target crossing to respective downstream is: Δ t
W, Δ t
sWith Δ t
E, the situation of correspond respectively to right-hand rotation, keeping straight on and turning left.The K-1 cycle starts from t
iIn the i phase time constantly, the vehicle number of through the crossing, turning right, keep straight on and turning left can be expressed as respectively:
O here
U(t
i, t
j) (U=W EorS) is illustrated in the respective downstream crossing detecting device time interval [t
i, t
j] in the vehicle number that passes through.
3, on the basis of above analysis, set up letter control crossing, city short-time traffic flow forecast bilayer model: this method upper strata arrives, waits for through the time estimation model for letter control crossing vehicle; Lower floor is the ratio of turning appraising model of letter control crossing.Can select suitable platform to programming realizes to this crossing, urban area short-time traffic flow forecast algorithm, so integrated, develop urban area crossing self-adapting control emulation plug-in unit.
Through above-mentioned description, the related personnel can change and revise under the condition of mentality of designing of the present invention and technical indicator appointment.Technical scope of the present invention is not limited to the content on the instructions, must confirm technical scope according to the claim scope.
Claims (7)
1. signalized intersections short-time traffic flow forecast method is characterized in that: may further comprise the steps:
Single cross prong in the upper reaches is waited for through the time prediction step;
Single cross prong space, upper reaches turning rate estimation steps;
Set up letter control crossing, city short-time traffic flow forecast bilayer model step.
2. a kind of according to claim 1 signalized intersections short-time traffic flow forecast method; It is characterized in that: said upper reaches single cross prong is waited for and being specially through the time prediction step: according to the mode of operation of crossing, upper reaches controller and traffic lights phase place for the vehicle that arrives the adjacent upstream crossing; After Parking Entrance detection trigger device, how long prediction can arrive the target downstream crossing.
3. like the said a kind of signalized intersections short-time traffic flow forecast method of claim 2, it is characterized in that: the mode of operation of crossing, said upper reaches controller is a timing mode.
4. like the said a kind of signalized intersections short-time traffic flow forecast method of claim 2, it is characterized in that: the mode of operation of crossing, said upper reaches controller is a trigger mode.
5. like the said a kind of signalized intersections short-time traffic flow forecast method of claim 2, it is characterized in that: said traffic lights phase place is: green 1: be green light time of arrival, and this direction of crossing does not have queuing; Green 2: be green light time of arrival, but this direction has queuing; Red 1: be red light time of arrival, and this direction of crossing does not have queuing; Red 2: be red light time of arrival, but this direction has queuing.
6. a kind of according to claim 1 signalized intersections short-time traffic flow forecast method; It is characterized in that: said upper reaches single cross prong space turning rate estimation steps is specially: suppose that given intersection signal adopts NEMA-8 phase place mechanism; And the right-hand rotation vehicle flowrate of all directions Parking Entrance distributes known; Vehicle number conservation according to out of phase turnover crossing in the cycle; The wagon flow of 8 phase places of NEMA controller being analyzed one by one all directions concerns, dynamically extrapolates the ratio of turning of these crossing all directions of next cycle.
7. a kind of according to claim 1 signalized intersections short-time traffic flow forecast method is characterized in that: said letter control crossing, the city short-time traffic flow forecast bilayer model step of setting up is specially: the upper strata arrives, waits for through the time estimation model for letter control crossing vehicle; Lower floor is the ratio of turning appraising model of letter control crossing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210183958.XA CN102708679B (en) | 2012-05-29 | 2012-05-29 | A kind of city signal crossing Short-time Traffic Flow Forecasting Methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210183958.XA CN102708679B (en) | 2012-05-29 | 2012-05-29 | A kind of city signal crossing Short-time Traffic Flow Forecasting Methods |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102708679A true CN102708679A (en) | 2012-10-03 |
| CN102708679B CN102708679B (en) | 2016-12-14 |
Family
ID=46901391
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210183958.XA Expired - Fee Related CN102708679B (en) | 2012-05-29 | 2012-05-29 | A kind of city signal crossing Short-time Traffic Flow Forecasting Methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102708679B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103927866A (en) * | 2013-12-31 | 2014-07-16 | 北京航空航天大学 | Method for forecasting traffic light waiting time of vehicle based on GPS |
| CN104282162A (en) * | 2014-09-29 | 2015-01-14 | 同济大学 | Adaptive intersection signal control method based on real-time vehicle track |
| CN104851285A (en) * | 2015-06-08 | 2015-08-19 | 成都维普特科技有限公司 | Road network load indication method for steering-based load statistics |
| CN104978857A (en) * | 2015-05-26 | 2015-10-14 | 重庆邮电大学 | Traffic state prediction method based on chaos theory and device thereof |
| CN106295849A (en) * | 2015-06-23 | 2017-01-04 | 福特全球技术公司 | Rapid transit parameter estimation |
| CN106447119A (en) * | 2016-10-11 | 2017-02-22 | 济南观澜数据技术有限公司 | Short-term traffic flow prediction method and system based on convolutional neural network |
| CN106652480A (en) * | 2016-12-28 | 2017-05-10 | 山东理工大学 | Intersection maximum queuing length calculation method based on microwave and terrestrial magnetism data |
| CN106710255A (en) * | 2017-02-16 | 2017-05-24 | 清华大学 | Control method and device for traffic signal and traffic signal system |
| CN107784835A (en) * | 2016-08-30 | 2018-03-09 | 蓝色信号株式会社 | Traffic behavior model prediction system and its Forecasting Methodology based on traffic data analyzing |
| CN109544922A (en) * | 2018-11-27 | 2019-03-29 | 华南理工大学 | A kind of traffic network Distributed Predictive Control method based on region division |
| CN109635495A (en) * | 2018-12-29 | 2019-04-16 | 西南交通大学 | Arterial highway phase difference simulation optimization method based on artificial neural network and genetic algorithms |
| CN109791731A (en) * | 2017-06-22 | 2019-05-21 | 北京嘀嘀无限科技发展有限公司 | A kind of method and system for estimating arrival time |
| CN109993349A (en) * | 2019-03-11 | 2019-07-09 | 同济大学 | A kind of optimization method and device of city refuge addressing |
| WO2020098079A1 (en) * | 2018-11-16 | 2020-05-22 | 北京嘀嘀无限科技发展有限公司 | Method and system for predicting transit duration |
| CN111582030A (en) * | 2020-04-02 | 2020-08-25 | 北京百度网讯科技有限公司 | Traffic light identification method and device, electronic equipment and computer storage medium |
| CN113112823A (en) * | 2021-04-14 | 2021-07-13 | 吉林大学 | Urban road network traffic signal control method based on MPC |
| CN114730522A (en) * | 2019-10-14 | 2022-07-08 | 华为云计算技术有限公司 | Traffic reasoning machine |
| CN117593043A (en) * | 2024-01-16 | 2024-02-23 | 华侨大学 | Method, device and equipment for estimating future short-term moment distribution of inter-city network vehicle |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000149186A (en) * | 1998-11-17 | 2000-05-30 | Mitsubishi Electric Corp | Method for controlling traffic signal |
| CN1372230A (en) * | 2001-02-23 | 2002-10-02 | 株式会社日立制作所 | Method for speculating traffic state by flowing car data and systme for speculating and providing traffic state |
| JP2003085687A (en) * | 2001-09-10 | 2003-03-20 | Sumitomo Electric Ind Ltd | Device for estimating time required for traveling between intersections |
| CN101089913A (en) * | 2007-07-12 | 2007-12-19 | 中国科学院地理科学与资源研究所 | Method for computing cross turning ratio based on genetic calculating method and large entropy mould |
| CN101281685A (en) * | 2008-01-30 | 2008-10-08 | 吉林大学 | Coordination control method for area mixed traffic self-adaption signal |
| CN101364344A (en) * | 2008-06-27 | 2009-02-11 | 北京工业大学 | Road network limitation capacity determining method based on pressure test |
| CN101593424A (en) * | 2009-07-10 | 2009-12-02 | 浙江大学 | A kind of intelligent combination forecasting method for short-term traffic flow |
| CN102436751A (en) * | 2011-09-30 | 2012-05-02 | 上海交通大学 | Short-time forecasting method for traffic flow based on urban macroscopic road network model |
-
2012
- 2012-05-29 CN CN201210183958.XA patent/CN102708679B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000149186A (en) * | 1998-11-17 | 2000-05-30 | Mitsubishi Electric Corp | Method for controlling traffic signal |
| CN1372230A (en) * | 2001-02-23 | 2002-10-02 | 株式会社日立制作所 | Method for speculating traffic state by flowing car data and systme for speculating and providing traffic state |
| JP2003085687A (en) * | 2001-09-10 | 2003-03-20 | Sumitomo Electric Ind Ltd | Device for estimating time required for traveling between intersections |
| CN101089913A (en) * | 2007-07-12 | 2007-12-19 | 中国科学院地理科学与资源研究所 | Method for computing cross turning ratio based on genetic calculating method and large entropy mould |
| CN101281685A (en) * | 2008-01-30 | 2008-10-08 | 吉林大学 | Coordination control method for area mixed traffic self-adaption signal |
| CN101364344A (en) * | 2008-06-27 | 2009-02-11 | 北京工业大学 | Road network limitation capacity determining method based on pressure test |
| CN101593424A (en) * | 2009-07-10 | 2009-12-02 | 浙江大学 | A kind of intelligent combination forecasting method for short-term traffic flow |
| CN102436751A (en) * | 2011-09-30 | 2012-05-02 | 上海交通大学 | Short-time forecasting method for traffic flow based on urban macroscopic road network model |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103927866A (en) * | 2013-12-31 | 2014-07-16 | 北京航空航天大学 | Method for forecasting traffic light waiting time of vehicle based on GPS |
| CN103927866B (en) * | 2013-12-31 | 2016-02-10 | 北京航空航天大学 | Traffic light time Forecasting Methodology waited for by vehicle based on GPS |
| CN104282162A (en) * | 2014-09-29 | 2015-01-14 | 同济大学 | Adaptive intersection signal control method based on real-time vehicle track |
| CN104978857A (en) * | 2015-05-26 | 2015-10-14 | 重庆邮电大学 | Traffic state prediction method based on chaos theory and device thereof |
| CN104851285A (en) * | 2015-06-08 | 2015-08-19 | 成都维普特科技有限公司 | Road network load indication method for steering-based load statistics |
| CN106295849B (en) * | 2015-06-23 | 2022-12-02 | 福特全球技术公司 | Fast traffic parameter estimation |
| CN106295849A (en) * | 2015-06-23 | 2017-01-04 | 福特全球技术公司 | Rapid transit parameter estimation |
| CN107784835A (en) * | 2016-08-30 | 2018-03-09 | 蓝色信号株式会社 | Traffic behavior model prediction system and its Forecasting Methodology based on traffic data analyzing |
| CN107784835B (en) * | 2016-08-30 | 2021-06-25 | 蓝色信号株式会社 | Traffic state mode prediction system based on traffic data analysis and prediction method thereof |
| CN106447119A (en) * | 2016-10-11 | 2017-02-22 | 济南观澜数据技术有限公司 | Short-term traffic flow prediction method and system based on convolutional neural network |
| CN106652480B (en) * | 2016-12-28 | 2018-01-19 | 山东理工大学 | A kind of intersection maximum queue length computational methods based on microwave geomagnetic data |
| CN106652480A (en) * | 2016-12-28 | 2017-05-10 | 山东理工大学 | Intersection maximum queuing length calculation method based on microwave and terrestrial magnetism data |
| CN106710255A (en) * | 2017-02-16 | 2017-05-24 | 清华大学 | Control method and device for traffic signal and traffic signal system |
| CN109791731A (en) * | 2017-06-22 | 2019-05-21 | 北京嘀嘀无限科技发展有限公司 | A kind of method and system for estimating arrival time |
| WO2020098079A1 (en) * | 2018-11-16 | 2020-05-22 | 北京嘀嘀无限科技发展有限公司 | Method and system for predicting transit duration |
| CN109544922A (en) * | 2018-11-27 | 2019-03-29 | 华南理工大学 | A kind of traffic network Distributed Predictive Control method based on region division |
| CN109635495A (en) * | 2018-12-29 | 2019-04-16 | 西南交通大学 | Arterial highway phase difference simulation optimization method based on artificial neural network and genetic algorithms |
| CN109635495B (en) * | 2018-12-29 | 2023-08-22 | 西南交通大学 | Arterial road phase difference simulation optimization method based on neural network and genetic algorithm |
| CN109993349A (en) * | 2019-03-11 | 2019-07-09 | 同济大学 | A kind of optimization method and device of city refuge addressing |
| CN114730522A (en) * | 2019-10-14 | 2022-07-08 | 华为云计算技术有限公司 | Traffic reasoning machine |
| CN111582030A (en) * | 2020-04-02 | 2020-08-25 | 北京百度网讯科技有限公司 | Traffic light identification method and device, electronic equipment and computer storage medium |
| CN111582030B (en) * | 2020-04-02 | 2023-08-29 | 北京百度网讯科技有限公司 | Traffic light identification method and device, electronic equipment and computer storage medium |
| CN113112823A (en) * | 2021-04-14 | 2021-07-13 | 吉林大学 | Urban road network traffic signal control method based on MPC |
| CN117593043A (en) * | 2024-01-16 | 2024-02-23 | 华侨大学 | Method, device and equipment for estimating future short-term moment distribution of inter-city network vehicle |
| CN117593043B (en) * | 2024-01-16 | 2024-04-09 | 华侨大学 | Method, device and equipment for estimating future short-term moment distribution of inter-city network vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102708679B (en) | 2016-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102708679A (en) | Method for forecasting short-time traffic flows at urban signalized intersections | |
| Wang et al. | A review of the self-adaptive traffic signal control system based on future traffic environment | |
| Tajalli et al. | Distributed optimization and coordination algorithms for dynamic speed optimization of connected and autonomous vehicles in urban street networks | |
| Ahmed et al. | An integrated real-time traffic signal system for transit signal priority, incident detection and congestion management | |
| Ahmane et al. | Modeling and controlling an isolated urban intersection based on cooperative vehicles | |
| WO2019061933A1 (en) | Traffic signal chord panning control method and system | |
| Smith et al. | Smart urban signal networks: Initial application of the surtrac adaptive traffic signal control system | |
| CN106846835B (en) | Self-adaptive coordination control method for urban area traffic signals | |
| Yagar et al. | A procedure for real-time signal control that considers transit interference and priority | |
| Li et al. | Modeling and implementation of adaptive transit signal priority on actuated control systems | |
| Lin et al. | Transit priority strategies for multiple routes under headway-based operations | |
| Płaczek | A self-organizing system for urban traffic control based on predictive interval microscopic model | |
| Ma et al. | Integrated optimization of lane markings and timings for signalized roundabouts | |
| CN108133613A (en) | A kind of real-time release road-surface concrete Service Index method and system | |
| Zhang et al. | An optimization model and traffic light control scheme for heterogeneous traffic systems | |
| CN106355905A (en) | Control method for overhead signal based on checkpoint data | |
| Lee et al. | Group-based hierarchical adaptive traffic-signal control Part II: Implementation | |
| CN109255493A (en) | A kind of real-time predicting method of the subway train track based on Robust Strategies | |
| Chen et al. | Influence of pedestrian traffic on capacity of right-turning movements at signalized intersections | |
| Lin et al. | Service-oriented dynamic data driven application systems to traffic signal control | |
| CN105095983B (en) | The real-time predicting method of subway train track | |
| Makhloga | IMPROVING INDIA’S TRAFFIC MANAGEMENT USING INTELLIGENT TRANSPORTATION SYSTEMS | |
| Vasudevan | Robust optimization model for bus priority control under arterial progression | |
| Ha | Smart and adaptive traffic light system | |
| Gutesa | Development and evaluation of cooperative intersection management algorithm under connected vehicles environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C53 | Correction of patent of invention or patent application | ||
| CB02 | Change of applicant information |
Address after: 230088 innovation industry park, No. 800 Wangjiang West Road, hi tech Zone, Anhui, Hefei, B1, South 605 Applicant after: Sun Jian Address before: 320, room 1, No. 230088 Road Software Park, hi tech Zone, Anhui, Hefei Applicant before: Sun Jian |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20190710 Address after: 030006 Xiaodian District Comprehensive Reform Demonstration Zone, Taiyuan Xuefu Park, Shanxi Province Patentee after: Shanxi compass Technology Co., Ltd. Address before: 230088 South Block 605, Innovation Industrial Park B1, 800 Wangjiangxi Road Avenue, Hefei High-tech Zone, Anhui Province Patentee before: Sun Jian |
|
| TR01 | Transfer of patent right | ||
| DD01 | Delivery of document by public notice |
Addressee: Xu Liang Document name: Notification to Pay the Fees |
|
| DD01 | Delivery of document by public notice | ||
| DD01 | Delivery of document by public notice |
Addressee: Patent director of Shanxi Beidou Hansen Technology Co.,Ltd. Document name: Notice of termination of patent |
|
| DD01 | Delivery of document by public notice | ||
| DD01 | Delivery of document by public notice |
Addressee: Shanxi Beidou Hansen Technology Co.,Ltd. The person in charge Document name: Notice of correction for restoration of rights |
|
| DD01 | Delivery of document by public notice | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20161214 Termination date: 20200529 |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| DD01 | Delivery of document by public notice |
Addressee: Xu Liang Document name: Notice of resumption of claim approval |
|
| DD01 | Delivery of document by public notice |