Development of TSCLab: A Tool for Evaluation of the Effectiveness of Adaptive Traffic Control Systems
Adaptive Traffic Control Systems (ATCS) have been widely implemented for urban traffic control due to their capability to alleviate congestion. ATCS adjust the signal programs of signalized intersections in real time according to the measured fluctuations of traffic flow. This results in an improvement of the efficiency of traffic operations of urban networks. The process of evaluating the effectiveness of complex ATCS is challenging and presents an open problem. The most important issue is to identify whether the ATCS fulfills the goals and needs it was envisioned to achieve. For this, different measures of effectiveness with in-depth insights into the traffic situations of the controlled signalized intersection are required. In this paper, development of TSCLab (Traffic Signal Control Laboratory), a MATLAB based tool for evaluation of ATCS is presented. TSCLab can gather and visualize relevant data, which describe the performance of ATCS (green time duration, maximum green time utilization ratio, percent of arrived vehicles on green, etc.) in real time, in a VISSIM based microscopic simulation environment using different traffic scenarios. It can also process the gathered data to evaluate the effectiveness of the analyzed ATCS after simulation. To proof the capabilities of TSCLab, the effectiveness of the UTOPIA/SPOT ATCS using an isolated signalized urban intersection as the use case has been evaluated.
KeywordsIntelligent Transport Systems Adaptive Traffic Control System Isolated signalized urban intersection Evaluation of effectiveness
The authors would like to thank the companies PTV Group and SWARCO MIZAR S.r.l., the Traffic management and control center of the City of Skopje, and the Faculty of Transport and Traffic Sciences, University of Zagreb for supporting the work published in this paper.
- 1.Wahlstedt, J.: Evaluation of the two self-optimising traffic signal systems Utopia/Spot and ImFlow, and comparison with existing signal control in Stockholm, Sweden. In: Proceedings of the 16th International IEEE Annual Conference on Intelligent Transportation Systems (ITSC 2013), pp. 1541–1546 (2013)Google Scholar
- 2.El-Tantawy, S., Abdulhai, B., Abdelgawad, H.: Multiagent reinforcement learning for integrated network of adaptive traffic signal controllers (MARLIN-ATSC): methodology and large-scale application on Downtown Toronto. IEEE Trans. ITS 14(3), 1140–1150 (2013)Google Scholar
- 3.Michailidis, I.T., Manolis, D., Michailidis, P., Diakaki, C., Kosmatopoulos, E.B.: Autonomous self-regulating intersections in large-scale urban traffic networks: a Chania City case study. In: 2018 5th International Conference on Control, Decision and Information Technologies (CoDIT), pp. 853–858 (2018)Google Scholar
- 4.SWARCO MIZAR S.p.A.: ATM Skopje Preliminary Before/After Study, Turin, Italy (2014)Google Scholar
- 5.Dakic, I., Mladenović, M., Stevanović, A., Zlatkovic, M.: Upgrade evaluation of traffic signal assets: high-resolution performance measurement framework. Promet Traffic Transp. 30(3), 323–332 (2018)Google Scholar
- 6.Pavleski, D., Nechoska Koltovska, D., Ivanjko, E.: Evaluation of adaptive traffic control system UTOPIA using microscopic simulation. In: Proceedings of 59th International Symposium ELMAR-2017, pp. 17–20 (2017)Google Scholar
- 7.Pavleski, D., Nechoska Koltovska, D., Ivanjko, E.: Evaluation of adaptive and fixed time traffic signal strategies: case study of Skopje. In: Book of abstracts of Second International Conference Transport for Today’s Society (2018)Google Scholar
- 8.Pavleski, D.: Adaptive traffic signal control performances evaluation in micro-simulation environment. Master thesis, Faculty of Technical Sciences, Bitola, Macedonia (2018). (in Macedonian)Google Scholar
- 10.Gettman, D., et al.: Measures of effectiveness and validation guidance for adaptive signal control technologies, US Department of Transportation, Federal Highway Administration (2013)Google Scholar
- 13.Smith, J., Blewitt, R. (eds.): Mayor of London: Traffic modelling guidelines, TfL Traffic manager and network performance best practices, Transport for London (2010)Google Scholar