Traffic operators in traffic control centers have various measures at their disposition to control the traffic flows on motorways and on urban roads such as ramp metering, variable speed limits, dynamic route guidance, opening of shoulder lanes, etc. When having to determine which of these control measures have to be applied and where they have to be applied for a given traffic situation, the traffic operator should be able to predict the effect of a control scenario in order to be able to select the best scenario. As on-line, real-time simulation of a large number of possible scenarios is usually not tractable for even relatively small motorway networks, a fast method to predict the effects of control measures on-line is a key requirement for effectively applying traffic control. In this paper we develop a multi-agent case-based approach to assist traffic operators in evaluating or predicting the effects of control measures. The proposed approach is much faster than straightforward traffic simulation so that it can be used for on-line and real-time evaluation of a large number of different control scenarios. In addition, it is scalable so that it can also be used for large networks.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A multi-agent case-based traffic control scenario evaluation system


    Contributors:


    Publication date :

    2003-01-01


    Size :

    507207 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A Multi-Agent Case-Based Traffic Control Scenario Evaluation System

    De Schutter, B. / Hoogendoorn, S. P. / Schuurman, H. et al. | British Library Conference Proceedings | 2003


    A multi-agent case-based traffic control scenario evaluation system

    De Schutter, B. / Hoogendoorn, S.P. / Schuurman, H. et al. | Tema Archive | 2003



    Air Traffic Scenario Evaluation Based on Metric Learning

    Dong SUI / Qian LI / Tingting ZHOU et al. | DOAJ | 2024

    Free access