Adaptive signal Control. Tom Mathew

Transcription

1 Adaptive signal Control Tom Mathew

2 Adaptive Control: Outline 1. Signal Control Taxonomy 2. Coordinated Signal System 3. Vehicle Actuated System 4. Area Traffic Control (Responsive) 5. Adaptive Traffic Control Systems (1, II, III) 2

3 I. Signal Control Taxonomy

4 Traffic Signal Control Fixed Time Signal Vehicle Actuated Coordinated Signal Area Traffic Control Responsive Adaptive 4

5 Traffic Signal Control Coordinated control Offset downstream green start Assumes constant link travel time Implies smooth progression 5

6 Traffic Signal Control Fixed time control 6

7 Vehicle Actuated Control

8 Vehicle Actuated Control Concept 8

9 Vehicle Actuated Control Working principle 9

10 Vehicle Actuated Control Parameters Minimum Green time Maximum Green time Threshold gap Unit extension 10

11 Vehicle Actuated Control Basic Algorithm for every phase set green equals queue service time for every scan time get detector state for each lane-group compute gap if gap greater than threshold terminate green else increment green time limit green to max green time if green greater than max green terminate green 11

12 Traffic Signal Control Area traffic control Traffic responsive 13

13 Traffic Signal Control Area traffic control Adaptive to Traffic 14

14 Area (Adaptive) Traffic Control

15 Traffic Signal Control Two Popular Network Systems Centralized system SCOOT Split, Cycle, Offset, Optimization Distributed system SCAT Sydney Coordinated Adaptive Traffic System 16

16 Working philosophy Upstream detection Data communicated to central controller SCOOT system It computes the timing and send to intersections Limitations Communication overheads Poor progression prediction Calibration issues 17

17 Working philosophy SCATS system Downstream detection Local controller acts akin to a VA controller Communicate periodically to the central controller Limitations Not an optimal system 18

18 SCOOT vs. SCAT SCOOT Centralized System Upstream detection Fixed traffic regions Fallback - fixed Modal based SCAT Distributed system Stop line detection Adjustable region Fallback - VA Heuristic 19

19 Adaptive Control I CoSiCoSt

20 CoSiCoSt Composite Signal Control Strategy Developed by: CDAC(T) Features Use the philosophy of Split, Cycle and Offset approximation for optimum throughput Every controlled lane require detection Use stop-line and exit detectors Built-in filters to segregate turning traffic 21

21 Detector placement CoSiCoSt Stop line - No demand prediction Input Demand from every loop from every cycle Output Green time for each phase, Cycle length and delay 22

22 Heuristic algorithm CoSiCoSt Based on actual & utilized green time 23

23 Basic Algorithm of VA CoSiCoSt for every phase set green equals queue service time for every scan time get detector state for each lane-group compute gap if gap greater than threshold terminate green else increment green time limit green to max green time if green greater than max green terminate green 24

24 CoSiCoSt Working principle of VA 25

25 CoSiCoSt Indian Adaptive Traffic Control System Reactive Rule based adjustments Distributed network architecture Real-time Signal Coordination of dynamically selected corridors Self-calibrating Cycle lengths and Phase lengths Fall-back operation in VA

26 CoSiCoSt Light weight Operates on standard desktop Windows / Linux Platform PostgreSQL database TCP/IP Protocol Optimized data transfer Networking possible even on Broadband VPN Scalable from two junctions to 6000 junctions 200 corridors x 30 junctions on a 32-bit machine

27 CoSiCoSt Central Server Web Enabled Data Logger Configurator User friendly GUI Remote Monitoring Reports, Views and Graphs ATCS Application Software Real-time animation of Signal Operation Real-time animation of Time-Space Diagram

28 CoSiCoSt Implementation Jaipur, Rajasthan Pune, Maharashtra Kolkata, West Bengal Ahmedabad, Gujarat Patna, Bihar (in progress) Surat, Gujarat (in progress)

29 CoSiCoSt Dynamic Offset Progression modeling Improve offset calculation Establish relation between link travel time, loop occupancy and link length 19 April

30 Adaptive Control II Machine Learning

31 Current Green Times Adaptive control Adaptive learning Estimate of Gmax Agent State s t Reward r t Actual discharges Action a t Max Green r t+1 Environment S t+1 32

32 Adaptive control Evaluation using traffic simulator 33

33 Adaptive control Results Volume Control Delay Queue Low (V/C ) Medium (V/C ) High (V/C ) Adaptive 15 6 VA 17 6 Fixed 20 8 Adaptive VA Fixed Adaptive VA Fixed

34 Green (s) Green (s) Volume (veh) Adaptive control Volume Green Time by VA control Time (s) Green Time by Adaptive control Time (s) Green -1 Vol- 1 Green -1

35 Adaptive Control III Optimization of Modified HCM

36 Objective Adaptive control Minimize average delay per vehicle Decision variable Green time for each phase Constraints Upper and lower limits for green times Maximum cycle length Input Not upstream volume, but stop line discharge 37

37 Adaptive control Mathematical formulation 38

38 Adaptive control Delay function (HCM 2000) 39

39 Adaptive control Delay function (HCM 2000) q p 40

40 Numerical example Evaluation 41

41 Evaluation 42

42 Evaluation 43

43 Input demand Evaluation 44

44 Output - Cycle Evaluation 45

45 Output Green times Evaluation 46

46 47

47 Output Delays Evaluation 48

48 Evaluation (Smoothening) 49

49 Adaptive Control Summary Sensitive to fluctuating traffic demand Evaluation by traffic simulators Optimal use of infrastructure Enhances service quality 50

50 Adaptive Control Advanced topics Developing for large systems Better traffic model Heuristics Machine Learning Delay Models Traffic management capabilities 51

51 ATMS Detection system Vehicle Decision Optimal Control system Intersection control System optimal 52

52 53

53 Thank You, Questions?

54 Adaptive Control Summary Sensitive to fluctuating traffic demand Evaluation by traffic simulators Optimal use of infrastructure Enhances service quality 57

55 Adaptive Control Research directions Developing for large systems Optimal control Traffic management capabilities 58