A Hybrid Intelligent Algorithm for Real Time Metro Traffic Regulation in Cases of Disturbance

During the daily operation of the metro system, unexpected events such as obstruction of doors or medical emergencies will make trains dwell at the platform for a longer time than original timetable, resulting in passengers accumulating, platform crowding and subsequent trains operation being affected. To reduce the impact of interference and to make affected trains resume normal operation as soon as possible, this paper outlines a metro traffic regulation model which reduces the total delay of affected trains and the number of passengers stranded on platforms. Based on Particle Swarm Optimization (PSO) algorithm, a particle Speed-Up and Speed-Down (SUSD) strategy, the crossover and mutation operation of a Genetic Algorithm (GA) are introduced to develop a novel Hybrid Intelligent Algorithm (HIA). In a case study conducted based on real operational data, we have succeed in reducing the stranded passengers by 30% and the total delay by 23% compared with a commonly used fixed regulation method.

[1]  B Vitoriano,et al.  Predictive Traffic Regulation for Metro Loop Lines Based on Quadratic Programming , 2006 .

[2]  Lei Liu,et al.  Particle swarm optimization algorithm: an overview , 2017, Soft Computing.

[3]  Hairong Dong,et al.  Approximation-Based Robust Adaptive Automatic Train Control: An Approach for Actuator Saturation , 2013, IEEE Transactions on Intelligent Transportation Systems.

[4]  Russell C. Eberhart,et al.  Parameter Selection in Particle Swarm Optimization , 1998, Evolutionary Programming.

[5]  Haopeng Zhang,et al.  A speed-up and speed-down strategy for swarm optimization , 2014, GECCO.

[6]  Ziyou Gao,et al.  Energy-efficient metro train rescheduling with uncertain time-variant passenger demands: An approximate dynamic programming approach , 2016 .

[7]  Hairong Dong,et al.  Cooperative Control Synthesis and Stability Analysis of Multiple Trains Under Moving Signaling Systems , 2016, IEEE Transactions on Intelligent Transportation Systems.

[8]  Hairong Dong,et al.  Train operation adjustment of the urban rail transit based on dwell time model , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[9]  Ton J.J. van den Boom,et al.  Passenger-demands-oriented train scheduling for an urban rail transit network , 2015 .

[10]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[11]  Ziyou Gao,et al.  Joint optimal train regulation and passenger flow control strategy for high-frequency metro lines , 2017 .

[12]  Chi K. Tse,et al.  Analysis of metro network performance from a complex network perspective , 2018 .

[13]  Ziyou Gao,et al.  Real-time automatic rescheduling strategy for an urban rail line by integrating the information of fault handling , 2017 .

[14]  Kay W. Axhausen,et al.  Demand-driven timetable design for metro services , 2014 .

[15]  H Sasama,et al.  FLOATING TRAFFIC CONTROL FOR TRANSPORTATION SYSTEM , 1979 .

[16]  Thomas Kiel Rasmussen,et al.  Hybrid Particle Swarm Optimiser with breeding and subpopulations , 2001 .