Traffic control optimization is a challenging task for various traffic centers around the world and the majority of existing approaches focus only on developing adaptive methods for normal (recurrent) traffic conditions. Optimizing the control plans when severe incidents occur still remains an open problem, especially when a high number of lanes or entire intersections are affected. This paper presents a novel methodology for optimizing the traffic signal timings in signalized urban intersections, under non-recurrent traffic incidents. With the purpose of producing fast and reliable decisions, we combine the fast running Machine Learning (ML) algorithms and the reliable Genetic Algorithms (GA) into a single optimization framework. Firstly, we deploy a typical GA algorithm by considering the phase duration as the decision variable and the objective function as the total travel time in the network. We fine tune the GA for crossover, mutation, fitness calculation and obtain the optimal parameters. Secondly, we train several regression models to predict the total travel time in the studied traffic network, and select the best performing model which we further hyper-tune. Lastly, we propose a new algorithm BGA-ML combining the GA algorithm and the extreme-gradient decision-tree (XGBT), which is the best performing regression model, together in a single optimization framework. Comparison and results are generated by two experiments (one synthetic and one from real urban traffic network) and show that the new BGA-ML is much faster than the original GA algorithm and can reduce the total travel time by almost half when used under incident conditions.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Boosted Genetic Algorithm Using Machine Learning for Traffic Control Optimization


    Beteiligte:
    Mao, Tuo (Autor:in) / Mihaita, Adriana-Simona (Autor:in) / Chen, Fang (Autor:in) / Vu, Hai L. (Autor:in)


    Erscheinungsdatum :

    01.07.2022


    Format / Umfang :

    9450861 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    CJAMmer - traffic JAM Cause Prediction using Boosted Trees

    Moreira-Matias, Luis / Cerqueira, Vitor | IEEE | 2016


    Marine Traffic Optimization Using Petri Net and Genetic Algorithm

    Anita Gudelj / Danko Kezić / Stjepan Vidačić | DOAJ | 2012

    Freier Zugriff

    Optimizing a Solid Rocket Motor Boosted Ramjet Powered Missile Using a Genetic Algorithm

    Hartfield, Roy / Jenkins, Rhonald / Burkhalter, John | AIAA | 2005


    Optimizing a Solid Rocket Motor Boosted Ramjet Powered Missile Using a Genetic Algorithm

    Hartfield, R. J. / Jenkins, R. M. / Burkhalter, J. E. et al. | British Library Conference Proceedings | 2005


    Decentralized Traffic Signal Control for Grid Traffic Network using Genetic Algorithm

    Tan, Min Keng / Ee Chuo, Helen Sin / Yeo, Kiam Beng et al. | IEEE | 2019