Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Automated tuning of ITS management and control systems: results from real-life experiments

Manolis Diamantis, Papamichail Ioannis, Kosmatopoulos Ilias, Papageorgiou Markos

Full record


URI: http://purl.tuc.gr/dl/dias/0EC95C71-461E-4C84-8B07-5490B814AA38
Year 2016
Type of Item Peer-Reviewed Journal Publication
License
Details
Bibliographic Citation D. Manolis, I. Papamichail, E. B. Kosmatopoulos and M. Papageorgiou, "Automated tuning of ITS management and control systems: results from real-life experiments," Transport Res C: Emer., vol. 66, pp. 119-135, May 2016. doi: 10.1016/j.trc.2015.08.020 https://doi.org/10.1016/j.trc.2015.08.020
Appears in Collections

Summary

The design and deployment of the majority of Management and Control Systems (MCS) for ITS involves a tedious, effort- and time-consuming manual tuning and calibration procedure not only during the initial design and deployment of the ITS but, in most cases, during its whole lifetime. Recently, we have developed and evaluated, both by means of theoretical analysis and extensive simulation experiments, a new methodology which fully automatically takes over the manual tuning and calibration procedure. Most importantly, this new methodology, called Adaptive Fine-Tuning (AFT), achieves to improve the performance of the system and compensate the effect of the continuous changes of its behavior that may be due to either internal or external factors. In this paper, we report results of implementing AFT to a real-life ITS MCS. More precisely, this paper reports and analyzes the results from implementing AFT to an urban traffic signal control application. The results from AFT real-life application demonstrate that it is capable of significantly improving the performance of the system in a safe and robust manner. Moreover, the real-life results exhibit the capability of AFT to efficiently adapt and compensate in cases of changes in the system behavior, even if these changes are significant.

Services

Statistics