Agent-Based Traffic Flow Optimization at Multiple Signalized Intersections

被引：11

作者：

Teo, Kenneth Tze Kin ^{[1
]}

Yeo, Kiam Beng ^{[1
]}

Chin, Yit Kwong ^{[1
]}

Chuo, Helen Sin Ee ^{[1
]}

Tan, Min Keng ^{[1
]}

机构：

[1] Univ Malaysia Sabah, Fac Engn, Modelling Simulat & Comp Lab, Mat & Min Res Unit, Kota Kinabalu, Malaysia

来源：

ASIA MODELLING SYMPOSIUM 2014 (AMS 2014) | 2014年

关键词：

Disturbance; Multi-Agent; Q-Learning; Traffic Signalizatio; Traffic Flow Optimization;

D O I：

10.1109/AMS.2014.16

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Relieving urban traffic congestion has always been an urgent call in a dynamic traffic network. The objective of this research is to control the traffic flow within a traffic network consists of multiple signalized intersections with traffic ramp. The massive traffic network problem is dealt through Q-learning actuated traffic signalization (QLTS), where the traffic phases will be monitored so that immediate actions can be taken when congestion is happening to minimize the number of vehicles in queue. QLTS has better performance than the existing common fixed-time traffic signalization (FTS) in dealing with the ramp flow due to its flexibility in changing the traffic signal with accordance to the traffic conditions and necessity

引用

页码：21 / 26

页数：6

共 13 条

[11] Applying a traffic lights evolutionary optimization technique to a real case: "Las Ramblas" area in Santa Cruz de Tenerife [J].

Sanchez, Javier ;

Galan, Manuel ;

Rubio, Enrique .

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2008, 12 (01) :25-40

[12]

Teo K. T. K., 2010, Proceedings 2010 Second International Conference on Computational Intelligence, Modelling and Simulation (CIMSiM 2010), P172, DOI 10.1109/CIMSiM.2010.95

[13]

Webster F.V, 1958, Road Research Paper No. 39

← 1 2 →