Chapter 7 CONCLUDING REMARKS
7.1 Conclusions
This study develops a self-learning traffic signal control model for both isolated and sequential intersections based on the MCTM traffic simulator. The contributions and findings related to this research are summarized in the following points:
1. Following most of the previous literatures, for the case of an isolated intersection, we choose traffic flow in green phase (TF) and queue length in red phase (QL) as two state variables and extension of green time (EGT) as the control variable and total vehicle delays (TVD) as performance measurement. For the case of sequential intersections of competing approaches, TF is the summation of traffic flows at all approaches in green phase; while QL is the summation of queen length at all approaches in red phase.
2. This study establishes an arterial coordinated signal control with a self-training capacity.
To reflect the various traffic conditions of different coordinated intersections, the green times along the arterial are independently determined by following the same control mechanism of an isolated intersection. However, to synchronize the signal timing plans of all coordinated intersections, an integrated signal control mechanism by considering the summation of traffic flows at all approaches in green phase and summation of queen length at all approaches in red phase. Therefore, the cycle length of all coordinated intersections is kept the same.
3. Based on the iterative GFLC model proposed by Chiou and Lan (2005), this research further develops stepwise GFLC signal control model. For the case of isolated intersection, the experimental example had shown that the control performance of SGFLC is almost the same as the optimal multiple timing plan and superior to the optimal single, IGFLC model, vanishing queue and maximum queue. Moreover, the SGFLC model can do much better than any other models as the traffic flows vary more conspicuously, indicating the robustness of the SGFLC model. The field case study also shows that SGFLC consistently outperforms over other single models and current timing plain. In the case of sequential intersections, both experimental example and field study have also shown that SGFLC performs better than other adaptive signal control models, no matter which coordinated signal system is operated. Those results present evidence
that GFLC is effective, robust and applicable to signal control for the intersections.
4. The validation results of the MCTM demonstrate its capability in replicating the mixed traffic behaviors at the signalized intersection. It is interesting to note that although both average delays of cars and motorcycles would be deteriorated as traffic demand grows, the average delay of cars grow much more rapidly than that of motorcycles, suggesting that the MCTM model can simulate the behaviors of motorcycles which do not follow the lane disciplines and may make lateral drifts breaking into two moving cars in order to keep moving forward.
5. According to the learning results of two similar GFLC models (IGFLC and SGFLC), although both GFLC models exhibit high control performance, the proposed SGFLC model selects much fewer rules (only five rules) with a relatively fewer generations than the IGFLC model does (374 rules). Additionally, by examining the rules selected by the IGFLC model, many of them are redundant or mutually conflicting. The merit of selecting few rules provides a chance for post-optimization adjustment and rule interpretation. Thus, the comparison shows that the proposed SGFLC is more effective, efficient and comprehensible than the IGFLC model.
6. The proposed SGFLC model mainly relies on the traffic information including traffic flow and queue length of cars and motorcycles to adaptively control the signal. Through a proper installation of two sets of sensors near the intersections, both traffic flow and queue length can be obtained (e.g. Sun et al., 2011). However, for the intersections with only one set of sensors, queue length can still be estimated based on traffic flow theories, e.g. shockwave method proposed by Liu et al. (2009).
7. In order to avoid the control performance of signal coordination degraded as the number of coordinated intersections increases. This study combines SGFLC traffic signal control rules with GAs for optimally determining which intersections have to be coordinated along a corridor. To validate the proposed hybrid models, the coordinated guidance suggested by MUTD and independent operation are compared. The experimental example has also shown that proposed model can increase 27% and 50% total vehicle throughput for off-peak traffic and 21% and 30% for peak traffic in medium- and large-sized corridors, respectively under type I traffic pattern. In the case of type II traffic pattern, the experimental example has also shown that hybrid model performs best, no
indices such as stopping probability, minimum fuel consuming and maximum throughput…etc. haven’t been examined.
2. This near-optimal signal control performance and validation results are mainly based on the MCTM simulation. The set of selected rules may not work well under other simulators. Additionally, the geometric design, such as parking space, bus stop and pedestrian facility… etc, has not been considered in this study.
3. The offset of progressive strategy was setting according to free flow speed and distance between intersections for simplification. The average vehicle speed under various traffic conditions should be further considered instead.
4. For sequential coordinated intersections, the mixed-traffic behaviors are assumed the same along the corridor and validated by the real traffic data near intersections.
However, the relationship between cars and motorcycles traveling at the mid-block of sections may not be the same as those behaviors near intersections.
7.3 Suggestions
Although this study has developed an effective, robust and applicable signal control models for the isolated and sequential intersections, some limitations should be mentioned and some findings are worth further studies.
1. The proposed stepwise algorithm is to select rules sequentially. However, an early selected rule may not be necessary to be the one of rules in the optimal rule combination.
A post-optimization adjustment mechanism can be developed to further fine tuned the selected rules and membership functions.
2. More effective and efficient encoding methods in selecting the logic rules or tuning the membership functions or both deserve to be explored.
3. For sequential coordinated intersections, the control performance is measured by TVD in this paper. Other performance indices, such as maximum green band, minimum stopping rate, and maximum throughput, deserve to be adopted and examined.
4. In this study, only simple two phase signal control plan is considered. Multi-phase signal control plans with consideration of turning flows at intersections deserves to be developed.
5. The control performances of the trained SGFLC model can be further examined by commonly-adopted traffic simulation software packages, such as AIMSUN, VISSIM,
PARAMICS, and CORSIM through build-in API interfaces, prior to field installation to judge effectiveness of the proposed model.
6. The mixed-traffic condition including lumps cars and heavy vehicles all together and scaled up to the network level should be considered in the traffic simulation model so as to further enhance the applicability and comprehensiveness of the proposed model.
7. The inaccuracy of traffic information detected on urban streets is pretty common. How to conduct an optimal control based on such inaccurate and unreliable vehicle detectors is also an interesting topic deserves a further attempt.
References
1. Autey, J., Sayed, T., Esawey, M.E., 2012. Operational performance comparison of four unconventional intersection designs using micro simulation. Journal of Advanced Transportation, DOI: 10.1002/atr.181.
2. Ben-Akiva, M., Cuneo, D., Hasan, M., Jha, M., Yang, Q., 2003. Evaluation of freeway control using a microscopic simulation laboratory. Transportation Research Part C 11, 29-50.
3. Chiou, Y.C., Lan, L.W., 2005. Genetic fuzzy logic controller: an iterative evolution algorithm with new encoding method. Fuzzy Sets and Systems 152, 617-635.
4. Chiou, Y.C., Lan, L.W., 2004. Adaptive traffic signal control with iterative genetic fuzzy logic controller (GFLC). presented at the 2004 IEEE International Conference on Networking, Sensing and Control, 287-292, Taipei, Taiwan, March 21-23.
5. Chiou, Y.C., Hsieh, C.W., 2012. Mixed traffic cell transmission models: development and validation. Journal of the Chinese Institute of Transportation 24, 245-276.
6. Chiou, Y.C., Huang, Y.F., 2011. Stepwise genetic fuzzy logic signal control under mixed traffic conditions. Proceedings of the International Conference on Advances in Highway Engineering & Transportation, Colombo, Sri Lanka.
7. Chiou, Y.C., Wang, Y.C., 2005. Development of genetic fuzzy logic controller-based ramp metering strategies. The 10th International Conference for Hong Kong Society of Transportation Studies, Hong Kong, Dec.10~12, 200-209.
8. Chiou, Y.C., Wang, M.T., Lan, L.W., 2003. Adaptive bus-preemption signals with genetic fuzzy logic controller (GFLC). Journal of the Eastern Asia Society for Transportation Studies 5, 1745-1758.
9. Chiou, Y.C., Wang, M.T., Lan, L.W., 2005. Coordinated transit-preemption signal along an arterial: iterative genetic fuzzy logic controller (GFLC) method. Journal of the Eastern Asia Society for Transportation Studies 6, 2321-2336.
10. Chiou, Y.C., Wang, M.T., Lan, L.W., 2007. A novel fuzzy logic controller for Transit Signal Preemption. The 17th International Symposium on Transportation and Traffic Theory (ISTTT), London, July 23-25.
11. Daganzo, C., 1994. The cell transmission model: A dynamic representation of highway traffic consistent with the hydrodynamic theory. Transportation Research Part B 28, 269-287.
12. Daganzo, C., 1995. The cell transmission model, part II: network traffic. Transportation Research Part B 29, 79-93.
13. Dion, F., Rakha, H., Zhang, Y., 2004. Evaluation of potential transit signal priority benefits along a fixed-time signalized arterial. Journal of Transportation Engineering 130, 294-303.
14. Esawey, M.E., Sayed, T., 2011. Unconventional USC intersection corridors: Evaluation of potential implementation in Doha, Qatar. Journal of Advanced Transportation 45,
38-53.
15. Fang, F.C., Elefteriadou, L., 2010. Modeling and simulation of vehicle projection arrival–discharge process in adaptive traffic signal controls. Journal of Advanced Transportation 44, 176-192.
16. Herrera, F., Lozano, M., Verdegay, J.L., 1995. Tuning fuzzy logic controllers by genetic algorithms. International Journal of Approximate Reasoning 12, 299-315.
17. Herrera, F., Lozano, M., Verdegay, J.L., 1998. A learning process for fuzzy control rules using genetic algorithms. Fuzzy Sets and Systems 100, 143-158.
18. Hoyer, R. and Jumar, U., 1994. An advanced fuzzy controller for traffic lights. Annual Review in Automatic Programming 19, 67-72.
19. Jacob, C., Abdulhai, B., 2006. Automated Adaptive Traffic Corridor Control Using Reinforcement Learning: Approach and Case Studies. Transportation Research Record 1959, 67-73.
20. Kosonen, I., 2003. Multi-agent fuzzy signal control based on real-time simulation.
Transportation Research Part C 11, 389-403.
21. Lan, L.W., Chiou, Y.C., Lin, Z.H., Hsu, C.C., 2010. Cellular automaton simulations for mixed traffic with erratic motorcycles’ behaviours. Physica A 389, 2077-2089.
22. Lekova, A., Mikhailov, L., Boyadjiev, D., Nabout, A., 1998. Redundant fuzzy rules exclusion by genetic algorithms. Fuzzy Sets and Systems 100, 235-243.
23. Lighthill, M.J., Whitham, J.B., 1955. On kinematic waves. I. folw movement in long rivers. II. A theory of traffic flow on long crowded reads. Proceedings of Royal Society, London, 281-345.
24. Lin, L.T., Tung, L.W., Ku, H.C., 2010. A synchronized signal control model for maximizing progression along an arterial. Journal of Transportation Engineering 136, 727-735.
25. Lin, W.H., Ahanotu, D., 1995. Validating the basic cell transmission model on a single freeway link. Technical note, UCB-ITS-PATH-TN-95-3, University of California, Berkeley , CA, USA.
26. Lin, W.H., Lo, H.K., 2008. A robust quasi-dynamic traffic signal control scheme for queue management. Proceedings of the Thirteenth International Conference of Hong Kong Society for Transportation Studies, Hong Kong: 563-572.
27. Liu, H.X., Oh, J.S., Recker, W., 2002. Adaptive signal control system with online performance measure for a single intersection. Transportation Research Record 1811, 131-138.
dynamic timing plans. Transportation Science 35, 148-164.
31. Lo, H.K., Szeto, W.Y., 2002. A cell-based dynamic traffic assignment model:
Formulation and properties. Mathematical and Computer modeling 35, 849-865.
32. Logghe, S., Immers, L.H., 2008. Multi-class kinematic wave theory of traffic flow.
Transportation Research Part B 42, 523-541.
33. May, A.D., 1990. Traffic Flow Fundamentals. Prentice Hall, Englewood Cliffs.
34. McShane, W.R., Roess, R.P., 1990. Traffic Engineering. Prentice Hall, Englewood Cliffs.
35. Michalewicz, Z., 1992. Genetic Algorithms + Data Structures = Evolution Programs.
Springer, Berlin.
36. Mirchandani, P., Head, L., 2001. real-time traffic signal control system: architecture, algorithms, and analysis. Transportation Research Part C 9, 415-432.
37. Mohamed, B.T., Mohamed, S.K., Murali, A., 1999. A two-stage fuzzy logic controller for traffic signals. Transportation Research Part C 7, 353-367.
38. Munoz, L., Sun, X., Sun, D., Gomes, G., Horowitz, R., Alvarez, L., 2004.
Methodological calibration of the cell transmission model. Proceedings of the 2004 American Control Conference, Boston, 798-803.
39. Murat, Y.S., Gedizlioglu, E., 2005. A fuzzy logic multi-phased signal control model for isolated junctions. Transportation Research Part C 13, 19-36.
40. Niittymäki, J., 2001. Installation and experiences of field testing a fuzzy logic controller.
European Journal of Operational Research 131, 273-281.
41. Papageorgiou, M., Papamichail, I., Spiliopoulou, A.D., Lentzakis, A.F., 2008. Real-time merging traffic control with applications to toll plaza and work zone management.
Transportation Research Part C 16, 535-55.
42. Pappis, C.P., Mamdani, E.H., 1977. A fuzzy logic controller for a traffic junction. IEEE Transactions on Systems, Man and Cybernetics 7, 707-717.
43. Pham, V.C., Alam, F., Potgieter, J., Fang, F.C., Xu, W.L., 2011. Integrated fuzzy signal and ramp-metering at a diamond interchange. Journal of Advanced Transportation, DIO:
10.1002/atr.167.
44. Richard, P.I., 1956. Shockwaves on the highway. Operations Research 4, 42-51.
45. Schmocker, J., Ahuja, S., Bell, M., 2008. Multi-objective signal control of urban junctions-Framework and a London case study. Transportation Research Part C 16, 454-470.
46. Smilowitz, K., Daganzo, C., 1999. Predictability of time-dependent traffic backups and other reproducible traits in experimental highway data. Working paper UCB-ITS-PWP-99-5, California PATH Program, Institute of Transportation Studies, University of California, Berkeley, CA, USA.
47. Sun, X., Han, L.D., Urbanik, T., 2011. Secondary coordination at closely spaced actuated traffic signals. Journal of Transportation Engineering 137, 751-759.
48. Teodorovic, D., 1999. Fuzzy logic systems for transportation engineering: the state of the art. Transportation Research Part A 33, 337-364.
49. Waller, S. and Ziliaskopoulos, A., 2001. Stochastic dynamic network design problem.
Transportation Research Record 1771, 106-113.
50. Wang, L., Yen, J., 1999. Extracting fuzzy rules for system modeling using a hybrid of genetic algorithms and Kalman filter. Fuzzy Sets and Systems 101, 353-362.
51. Wong, C.K., Wong, S.C., Lo, H.K., 2010. A spatial queuing approach to optimize coordinated signal settings to obviate gridlock in adjacent work zones. Journal of Advanced Transportation 44, 231-244.
52. Wong, S.C., 1997. Group-based optimisation of signal timing using parallel computing.
Transportation Research Part C 5, 123-139.
53. Wu, Y.Z., Ho, C.H., 2009. The development of Taiwan arterial traffic-adaptive signal control system and its field test: A Taiwan experience. Journal of Advanced Transportation 43, 455-480.
54. Xu, H., Zheng, M., 2009. Impact of Phase Scheme on Development and Performance of a Logic Rule-Based Bus Rapid Transit Signal Priority. Journal of Transportation Engineering 135, 953-965.
55. Yao, R., 2012. Sensitivity analysis of optimization models for isolated intersections with short left-turn lanes on approaches. Journal of Advanced Transportation, DOI:
10.1002/atr.1185.
56. Zadeh, L., 1973. utline of a new approach to the analysis of complex systems and decision processes. IEEE Transactions on Systems, Man and Cybernetic 3, 28-44.
57. Zhang, M., Ritchie, S., Recker, W, 1996. Some general results on the optimal ramp control problem. Transportation Research Part C 4, 51-69.
VITA
YEN-FEI HUANG EDUCATION
Ph.D Institute of Traffic and Transportation
National Chiao Tung University, Taipei, Taiwan (2007/09-2012/09) Advisor: Prof. Yu-Chiun Chiou
Dissertation: Genetic Fuzzy Logic Signal Control with Mixed-Traffic Cell Transmission Modeling
M.S. Graduate Institute of Traffic and Transportation Engineering and Management Feng Chia University, Taichung, Taiwan (2003/09-2005/06)
Advisor: Prof. Yu-Chiun Chiou
Thesis: A Multi-Attribute Evaluation Model of Rescue and Evacuation Routes for the Accident in Highway Long Tunnel
B.S. Department of Traffic and Transportation Engineering and Management Feng Chia University, Taichung, Taiwan (1999/09-2003/06)
RESEARCH EXPERIENCE
Research Assistant National Tung University, Taiwan (2007/09-2012/09) Research Assistant Feng Chia University, Taiwan (2003/09-2007/06)
AWARDS
Best Student Paper Award: Conference on Traffic Engineering and Intelligent Transportation Systems, 2009.
Best Student Paper Award: Cross-strait Conference on Intelligent Transportation Systems, 2009.
PUBLICATION
Journal
1. Chiou, Y.C. and Huang, Y.F. (2012) “Stepwise genetic fuzzy logic signal control under mixed traffic conditions,＂ Journal of Advanced Transportation (SCI) (Accepted) 2. Chiou, Y.C. and Huang, Y.F. (2012) “Genetic fuzzy logic traffic signal control with
cell transmission modeling,＂ Journal of the Chinese Institute of Engineers (SCI) (Accepted)
3. Chiou, Y.C. Huang, Y.F. and Lin, P.C. (2012) “Optimal variable speed-limited control under abnormal traffic conditions,＂ Journal of the Chinese Institute of Engineers (SCI), Vol. 35 pp.299-308
4. 邱裕鈞、王銘德、黃彥斐 (民 100)，「臺灣地區公路客運供給與補貼之區域資源分
配差異分析」，運輸計劃季刊(TSSCI) 。（已接受）
5. 邱裕鈞、張凱羚、黃彥斐 (民 93)，「公路長隧道事故救援策略之多準則決策模型」，
交通學報，第四卷第二期，第93～112 頁。
Conference
1. Chiou, Y.C., Lan, L.W., Huang, Y.F. and Hsieh, C.W. (2011) “Traffic responsive signal control system under mixed traffic conditions,＂ presented at the 16th Conference of Hong Kong Society for Transportation Studies, Hong Kong, China, Dec. 17-20.
2. Chiou, Y.C. and Huang, Y.F. (2011) “Stepwise genetic fuzzy logic signal control under mixed traffic conditions,＂ presented at the International Conference on Advances in Highway Engineering & Transportation Systems & Transport Research Forum 2011, Colombo, Sri Lanka, July 25-27.
3. Chiou, Y.C. and Huang, Y.F. (2010) “Genetic fuzzy logic traffic signal control with a stepwise learning algorithm,＂ presented at the 15th Conference of Hong Kong Society for Transportation Studies, Hong Kong, China, Dec. 11-14.
4. Chiou, Y.C., Lan, L.W., Lin, P.C. and Huang, Y.F. (2009) “Development of optimal variable speed-limit control model,＂ presented at the 14th Conference of Hong Kong Society for Transportation Studies, Hong Kong, China, Dec. 10-12.
5. 邱裕鈞、林柏辰、黃彥斐 (民 98)，建立異常交通狀況下之可變速限控制模式，2009
大專院校交通工程與智慧型運輸系統專題論文/創作成果競賽暨研討會，臺灣，臺 北，12 月。
6. 邱裕鈞、黃彥斐 (民 98)「基因模糊邏輯號誌控制系統-格位轉換模式之模擬分析」，
2009 海峽兩岸智慧型運輸系統學術研討會，臺灣，臺中，5 月。
Research Report
1. 邱裕鈞（2011-2012），「混合車流下之綠色適應性交通號誌控制模式」,國科會專題
研究報告(編號：NSC 100-2221-E-009-121)
2. 邱裕鈞（2008-2011），「基因及螞蟻規則探勘模式－以事故分析及事故鑑定為例（I、
II&III）」，國科會專題研究報告（編號：NSC 97-2628-E-009-035-MY3）
3. 邱裕鈞（2007-2010），「應用車輛辨識系統提昇起迄旅次矩陣推估之研究（I、
II&III）」，國科會專題研究報告（編號：NSC96-2628-E-009-171-MY3）
4. 邱裕鈞（2007-2008），「預測型模糊邏輯匝道儀控系統之建構與驗證（I & II）」，國
科會專題研究報告（編號：NSC95-2221-E-009-368-MY2）
8. 邱裕鈞（2011），「100 年運輸研究統計資料蒐集及彙編」，交通部運輸研究所委託。
9. 馮正民、邱裕鈞等（2011），「因應公路客運業市場環境與結構改變政府之輔導轉型
策略與管理技術研究」，交通部運輸研究所委託。
10. 馮正民、邱裕鈞等（2010），「前瞻運輸物流管理系統整體發展架構與推動策略規
劃」，交通部運輸研究所委託。
11. 馮正民、邱裕鈞等（2009），「強化公路公共運輸政策研析」，交通部運輸研究所委 託。
12. 邱裕鈞、鍾政棋（2008~2010），「97-99 年運輸研究統計資料蒐集及彙編」，交通部 運輸研究所委託。
13. 邱裕鈞、陳穆臻、鍾政棋（2007），「96 年運輸研究統計資料蒐集及彙編」，交通部 運輸研究所委託。
14. 邱裕鈞、艾嘉銘、温傑華（2005~2007），「高速公路局中區工程處交控中心人力委
外工作」，國道高速公路局中區工程處委託。
外工作」，國道高速公路局中區工程處委託。