An Intelligent Algorithm For Traffic Signal Scheduling

2y ago
29 Views
2 Downloads
775.14 KB
5 Pages
Last View : 1d ago
Last Download : 2m ago
Upload by : Samir Mcswain
Transcription

International Journal of Chemical, Environmental & Biological Sciences (IJCEBS) Volume 1, Issue 1 (2013) ISSN 2320–4087 (Online)An Intelligent Algorithm for Traffic SignalSchedulingAiswaria. Mohan, Janet Lourds. RaniAbstract— Traffic congestion is an increasingly importantproblem that has drawn attention of the public and hence propercounter measures need to be devised to facilitate better and efficienttransportation. Several conventional approaches to managing trafficflow at crossed junctions are practiced at present but exhibit poorefficiency owing to certain disadvantages. An Intelligent TrafficSignal Controller (ITSC) algorithm is being proposed in this paperfor a Two-lane crossed junction with dividers (road system inMalaysia) where each intersection serves two lanes. The design ofthe ITSC comprises of sensors placed at all four phases of a crossedjunction and an intelligent fuzzy controller. The working of the ITSCis based on two modes of timings: Non-Peak and Peak hours.Simulation showed positive results for improved phase schedulingand green signal allocation. Analysis also showed that for most cases,the ITSC performed better than the conventional controllers inminimizing the delay incurred at signalized intersections.intersection depending on its traffic characteristics and at thesame time take into account the starvation of vehicles on theother phases. Fuzzy Logic is one successful technique that hasproven its remarkable ability to map human mind intointelligent logic for appropriate decision making. An in-depthunderstanding of the technique facilitated the design of theIntelligent Traffic Signal Controller (ITSC).II. RELATED WORKSeveral conventional approaches to controlling trafficsignals include TRANSYT (Traffic Network Study Tool),SCOOT (Split, Cycle and Offset Optimization Technique) andSCATS (Sydney Co-ordinate adaptive traffic system) formsome of the best pre-determined off-line timing methods toaccount for traffic congestion.The Adaptive Signal-Vehicle Co-operative control system[3] provides an optimal traffic signal schedule as well as anoptimal vehicle speed advice. The traffic signal scheduling isachieved using Adaptive Dynamic Programming which hasthe advantage of reducing the computational requirement so asto bring about a feasible implementation. The IntelligentTransport System (ITS) technique to detect congestioncomprises of a wireless sender-receiver pair installed betweentwo points of the road [4]. The sender sends packets while thereceiver measured some metrics like signal strength, packetreception and link strength indicating the traffic congestionconditions.The Autonomous Agent Oriented Traffic control system[5] uses a hybrid approach wherein the internal working suchas the traffic data collection and processing is performed byagents while the traffic from each side is controlled by a singlecontroller.The fuzzy traffic-signal controller introduced in [6] for aroundabout consists of two fuzzy layers: Green extension timeand urgency degree. The input to the controller being thequeue length and the waiting period, the output decides thesignalling of the appropriate phase subset (from the predefinedset) of a chosen phase based on its urgency degree and latercomputes its extension factor at the second layer.An interactive fuzzy signal controller proposed in [7] makesuse of neighbouring traffic information to tackle congestionespecially during cases of over-saturation. The output of thecontroller decides whether to extend, early cut or terminatethe current signal phase depending on the observed trafficconditions.Keywords—: Crossed Junction, ITSC, Non-Peak Hour, PeakHour.I. INTRODUCTIONTRAFFIC density is an important factor that growsexponentially with more vehicles joining the roads day byday. Hence devising a solution should take into accountall possible dimensions of the problem to ensure a smoothtraffic flow.Roundabouts are one of the initial steps adopted to reducevehicle speed and thereby prevent accidents at intersections.This approach works well until the increased traffic demandresults in bottlenecks caused due to frequent deadlocks [1].The two other approaches to control traffic signals include thefixed time controllers and the vehicle actuated method. Thefixed time controllers to be the most commonly used approachworks quite well during off peak periods but fail to cope withthe sudden traffic changes that lead to increased delays. Onthe other hand a vehicle actuated method that uses sensors todetect vehicle presence appears to be more dynamic inscheduling extensions for green signals according to arrivalrates but fails to consider the queuing length at all the redsignal phases thus making it less efficient [2].From a human’s perspective, a traffic signal controllerneeds to allocate sufficient amount of green signal time to anAiswaria. Mohan is a student of MSc Technology Management atStamford College, Petaling Jaya, Malaysia. ( phone: 0107948846 ; e-mail:aishwariamh@gmail.com).Dr. Janet.Lourds Rani, is a Lecturer from the School of Computing, IT andEngineering, Stamford College, Petaling Jaya, Malaysia.(e-mail:jlr.1990@gmail.com).119

International Journal of Chemical, Environmental & Biological Sciences (IJCEBS) Volume 1, Issue 1 (2013) ISSN 2320–4087 (Online)III. PROPOSED ITSC ALGORITHM Standard length of a car recorded is 5.25 m.A. Terminologies and DefinitionsThe following are the terminologies used for the ITSCalgorithm: Based on the observations performed on three strategiclocations in Malaysia, the mean number of waitingcars at each intersection during Peak and Non-Peakhours was recorded, generalized and the followingnumerical results were derived (See Table I, Table IIand Table III). Peak Hour – Time of a day the traffic congestion onthe road is at its highest and is normally found twicea day [8].TABLE I Non-Peak Hour – The day apart from the Peak hoursand the weekends where the traffic congestion is notvery high [8].FUZZY PARAMETERS FOR TRAFFIC RANGETraffic RangeTrafficRangeFuzzyMembershipValue Arrival Rate – It can be defined as the averagenumber of customers arriving to a particular system.(Non-Peak Hour) Service Time – The average time taken by a server toservice the customers waiting at a system [9].0 to 15.75 m0 to 25 mLESS15.76 to 36.75 m26 to 50 mMODERATE36.76 to 52.5 m51 to 75 mHIGH52.6 to 100 m76 to 100 mVERY HIGH(Peak Hour) Poisson Process – A stochastic process that deals withthe count of events and the time of occurrence ofeach such event. This time of occurrence for eachpair of consecutive events is assumed to beindependent for each event and follows anexponential distribution [9].TABLE II M/M/1 Queuing model – A discipline within theFUZZY PARAMETERS FOR INTER-ARRIVAL TIMEclassic Queuing theory representing a length ofqueue served by a single server. The arrival processby the customers to the systems assumes a Poissonprocess and its corresponding job service timeassumes an exponential distribution [9].Inter-Arrival Time0 to 0.703 secSHORT0.704 to 7 secLONGB. Basic AssumptionsThe following are the basic assumptions made for thedevelopment of the ITSC algorithm:TABLE IIIFUZZY PARAMETERS FOR SERVICE TIME The research is done for the road system in Malaysia(See Fig 1).Service Time Each intersection of the crossed junction has one lanefor upstream vehicles and the other lane fordownstream vehicles. Fuzzy Membership Value0 to 0.332 sec0.333 to 0.5 secFuzzy Membership ValueSHORTMODERATETraficam video detector over-roadway sensors placedat all the four intersections of a crossed junction candetect the presence of vehicles up to 100 m startingfrom the stopping line of the intersection. Only Red and Green signals are taken into account.The Amber signal (yellow signal) is not consideredfor the study. Pedestrian Crossing is not considered.Sensor Vehicles such as cars and small vans form theparticipants of the system.Fig. 1 Model of Two-Lane Crossed Junction with Dividers120

International Journal of Chemical, Environmental & Biological Sciences (IJCEBS) Volume 1, Issue 1 (2013) ISSN 2320–4087 (Online)IV. WORKING PRINCIPLE OF THE ITSC ALGORITHM10. Call Fuzzy Controller ()The ITSC works under two different phases: Non-Peak Hourand Peak Hour. The main module, ITSC Main () firstinitializes the sensors at each intersection and determines theday and time of recording event. A call to the Non-Peak Hour() subroutine is made during the Non-Peak hour timings andduring weekends by default. If the time of recording is that forPeak hours, a call to the Peak Hour () subroutine is made.11. EndAlgorithm 2: Non-Peak Hour ()Input: Phase ID, Area CoveredOutput: Sequence of scheduled Phases1. Initialize the Phase ID for each sensorA. Pseudo code For ITSC AlgorithmAlgorithm 1:ITSC Main ()Phase[1]: NorthPhase[2] : EastInput: RecordingTime, RecordingDay,InterarrivaltimePhase[3] : WestPhase[4] : SouthOutput: Intelligent Traffic Signal Schedule2. Read Sensor Inputs for each phase and initialize astructure //Structures stores details about trafficconditions for each phase.1. Start2. Initialize variables: RecordingTime ,RecordingDay and Interarrivaltime3. Read Time[i]3. for i 1 to 4 // variable: i refers to the phasedirection. [The inter-arrival time of vehiclesarriving at an intersection is categorized asSHORT and LONG].4. Initialize Var State: n // the variable: state is toidentify the congestion condition for a particularphase.5. For i 1 to 4 // variable: i refers to the phasedirection. [The area covered by vehicles at anintersection is categorized as follows: LESS,MODERATE, HIGH and VERY HIGH].If (interarrivaltime SHORT)Phase[i].time 0;Elseif (interarrivaltime SHORT &&interarrivaltime LONG)If (areacovered LESS)Phase[i].state 0;Elseif (areacovered LESS && areacovered MODERATE)Phase[i].state 1;Elseif (areacovered MODERATE &&areacovered HIGH)Phase[i].state 2;Elseif (areacovered HIGH &&areacovered VERYHIGH)Phase[i].state 3;Phase[i].time 1;End (if)Time[i] -Phase[i].time // Time[i] is anarray containing information on the interarrival time for each phase.4. End of for loop5. Return (Time[i])End (If)6. If RecordingDay ! weekends // trafficcontrol for weekdays7.Phase[i] - Phase[i].state6. End of for loopIf (RecordingTime Non-Peak hour)Call Non-Peak Hour () subroutine7. Return (Phase[i])ElseAlgorithm 3:Peak Hour ()Call Peak Hour () subroutineInput: Phase ID, Area Covered,ServiceTimeOutput: Sequence of scheduled Phases, ExtensionIntervalEnd (if)8. Call Non-Peak Hour () routine9.Steps 1 through 7 remain the same as in NonPeak Hour ().End(if)121

International Journal of Chemical, Environmental & Biological Sciences (IJCEBS) Volume 1, Issue 1 (2013) ISSN 2320–4087 (Online)Algorithm 4: Fuzzy Controller ()signal duration with four membership functions. Theextension of green signal duration to the currently servicingphase is also determined similarly with two inputs to the FLC:Inter arrival time and Service time with two membershipfunctions each.Inputs: Phase[i], Time[i]Output: Green Signal Interval assignment1. for i 1 to 4 // var i refers to direction.VI. RESULTSRead Phase[i] and Time[i].The results obtained after the simulation of the ITSCalgorithm are shown below. Fig.2 shows the rule viewerwindow of the Fuzzy Logic Controller (FLC) for Non-Peakhour. It indicates the choice of selection of the appropriategreen signal duration for a particular phase for varying inputvalues.Evaluate inputs against fuzzy rule set.2. End of for loop.3. Schedule output to external traffic signal controller.4. If (RecordingTime Peak-Hour)Call Fuzzy Extension ()End (if)5. EndAlgorithm 4.1: Fuzzy Extension ()Input: ServiceTime, Phase[i], Time[i]Output: Green Extension Interval1. for i 1 to 4 //// var i refers to direction.If (ServiceTime SHORT)Phase[i].servicetime 0;Elseif(ServiceTime SHORT&&ServiceTime MODERATE)Phase[i].servicetime 1;End (if)Stime[i] -Phase[i].servicetime2. End of for loop3. for i 1 to 4Fig.2 Fuzzy Rule Viewer for Non-Peak HourThe Fuzzy Rule Viewer window of the FLC for peak hour isillustrated in Fig. 3. The fuzzy rule viewer for peak houroperations indicate the decision for selection of phase greensignal duration for the varying input values. The extensionrequirements for the currently servicing phase are alsomodelled similarly in Fig. 4.Read Phase[i] and Time[i].Evaluate inputs against fuzzy rule set.4. End of for loop.5. Schedule outputcontroller.toexternaltrafficsignal6. EndV. SIMULATION OF TRAFFIC AT A CROSSEDJUNCTIONFig. 3 Fuzzy Rule Viewer for Peak HourThe process of traffic signal scheduling is achieved byprogramming in C language. The appropriate green signalduration for the scheduled phases is determined using theFuzzy Logic toolbox of Matlab. The process of phasescheduling is facilitated using two inputs to the Fuzzy LogicController (FLC): Area covered and Inter arrival time withfour and two membership functions and a single output: Green122

International Journal of Chemical, Environmental & Biological Sciences (IJCEBS) Volume 1, Issue 1 (2013) ISSN 2320–4087 (Online)algorithm proposed in this research is an attempt to bringabout such a kind of a solution. The design of the ITSCcomprises of sensors placed at all four phases of a crossedjunction and an intelligent fuzzy controller. The data providedby sensors determine congestion characteristics in terms ofarea covered by vehicles at an intersection. Simulation of theITSC showed positive results for improved phase schedulingand green signal allocation. Future work could be theimprovement of the capacity of the sensors to facilitatedetection range up to 200 m and above. Traffic caused byPedestrian crossing can also be considered.REFERENCES[1] Nair , B.M., Cai, J., 2007. A Fuzzy logic controller for Isolated SignalizedIntersection with Traffic Abnormality Considered, Proceedings of the2007 IEEE Intelligent Vehicles Symposium, Istanbul, June 13-15 2007,Turkey.[2] Kaczmarek, M.K., 1990. Group Control Of Traffic At Roundabouts, TheThird International Conference on Road Traffic Control, 1-3 May 1990.[3] Le, T., Cai, C., Walsh, T., 2011. Adaptive Signal-Vehicle CooperativeControlling System. 2011 14th International IEEE Conference onIntelligent Transportation Systems, Washington, DC, October 5-7 2011.[4] Roy, S., Sen, R., Kulkarni, S., Kulkarni, P., Raman, B., Singh, L.K., 2011.Wireless Across Road: RF Based Road Traffic Congestion Detection,2011 Third International Conference on Communication Systems andNetworks, 4-8 January, 2011.[5] Afsar, S., Maliq, Z. I., Elnaffar, S., 2010. Autonomous Agent-OrientedTraffic Control System, The 2nd International Conference on Computerand Automation Engineering, 2010, 26-28 February, 2010.[6] Gong, Y., Zhang, J., Liu, O., Liu, Y., 2011. A Novel Fuzzy Model for theTraffic Signal Control of Modern Roundabouts, 2011 IEEE InternationalConference on Systems, Man and Cybernetics, 9-12 October 2011.[7] Tian, Y., Li, Z., Zhou, D., Song, J., Xiao, D., 2008. Interactive SignalControl for Over-saturated Arterial Intersections Using Fuzzy Logic. In:ITS (Intelligent Transportation Systems),Proceedings of the 11thInternational IEEE Conference on Intelligent Transportation System,Beijing, October 12-15 2008.[8] Electronics for You, 2002. Automated Traffic Signal Controller ylinux/circuit/nov2002/traffic.pdf.[9] Taha, H.A., 2008. Operation Research: An Introduction. 8th ed. Pearson.Fig.4 Fuzzy Rule Viewer for ExtensionIt is also found that the ITSC compared to the conventionaltraffic signal controller in most cases exhibited betterperformance in minimizing the delay at signalizedintersections. The comparisons are shown for both Non-peakand Peak hours from the observed results (See Fig.5 and Fig.6).Fig. 5 Delay incurred during Non-Peak HourFig. 6 Delay incurred during Peak hourVII. CONCLUSIONThe characteristics of road traffic have seen to evolveenormously. It would be a hard procedure to enforce a controlon the entry of new cars on the road. Hence one possiblesolution available would be to devise methods to effectivelycontrol the congestion by facilitating an uninterrupted trafficflow. The Intelligent Traffic Signal Controller (ITSC)123

SCATS (Sydney Co-ordinate adaptive traffic system) form some of the best pre-determined off-line timing methods to account for traffic congestion. The Adaptive Signal-Vehicle Co-operative control system [3] provides an optimal traffic signal schedule as well as an optimal vehicle speed advice. The traffic signal scheduling is

Related Documents:

Bruksanvisning för bilstereo . Bruksanvisning for bilstereo . Instrukcja obsługi samochodowego odtwarzacza stereo . Operating Instructions for Car Stereo . 610-104 . SV . Bruksanvisning i original

10 tips och tricks för att lyckas med ert sap-projekt 20 SAPSANYTT 2/2015 De flesta projektledare känner säkert till Cobb’s paradox. Martin Cobb verkade som CIO för sekretariatet för Treasury Board of Canada 1995 då han ställde frågan

service i Norge och Finland drivs inom ramen för ett enskilt företag (NRK. 1 och Yleisradio), fin ns det i Sverige tre: Ett för tv (Sveriges Television , SVT ), ett för radio (Sveriges Radio , SR ) och ett för utbildnings program (Sveriges Utbildningsradio, UR, vilket till följd av sin begränsade storlek inte återfinns bland de 25 största

Hotell För hotell anges de tre klasserna A/B, C och D. Det betyder att den "normala" standarden C är acceptabel men att motiven för en högre standard är starka. Ljudklass C motsvarar de tidigare normkraven för hotell, ljudklass A/B motsvarar kraven för moderna hotell med hög standard och ljudklass D kan användas vid

LÄS NOGGRANT FÖLJANDE VILLKOR FÖR APPLE DEVELOPER PROGRAM LICENCE . Apple Developer Program License Agreement Syfte Du vill använda Apple-mjukvara (enligt definitionen nedan) för att utveckla en eller flera Applikationer (enligt definitionen nedan) för Apple-märkta produkter. . Applikationer som utvecklas för iOS-produkter, Apple .

the destination. The traffic light system designed by Salim Bin Islam provided a design and development of a microcontroller based intelligent traffic control system. He proposed a new intelligent traffic control system that is to control the traffic system through traffic signal on the basis of current traffic density.

SA Learner Driver Manual Road Traffic Signs Version: Draft Page 1 of 56 2. ROAD TRAFFIC SIGNS, SIGNALS AND MARKINGS The purpose of road traffic signs is to regulate traffic in such a way that traffic flow and road traffic safety are promoted. 1. SIGNS IN GENERAL Road traffic signs can be divided into the following six main groups:

och krav. Maskinerna skriver ut upp till fyra tum breda etiketter med direkt termoteknik och termotransferteknik och är lämpliga för en lång rad användningsområden på vertikala marknader. TD-seriens professionella etikettskrivare för . skrivbordet. Brothers nya avancerade 4-tums etikettskrivare för skrivbordet är effektiva och enkla att