Ramp Metering Control Based on the Q-Learning Algorithm

Cybernetics and Information Technologies

卷:15

Koltovska Nečoska Daniela¹  Gregurić Martin²  Jurković Goran²  Ivanjko Edouard²  Mandžuka Sadko²  Vujić Miroslav² 

[1] Faculty of Technical Sciences, Bitola, St. Kliment Ohridski University, Makedonska falanga 33, 7000 Bitola, Republic of Macedonia;

[2] Faculty of Transport and Traffic Sciences, University of Zagreb, Vukelićeva 4, HR-10000 Zagreb, Republic of Croatia;

关键词: ramp metering;    q-learning;    autonomic systems;    artificial intelligence;    microscopic simulation;   

DOI  :  10.1515/cait-2015-0019

来源: DOAJ

【 摘 要 】

Modern urban highways are under the influence of increased traffic demand and cannot fulfill the desired level of service anymore. In most of the cases there is no space available for any infrastructure building. Solutions from the domain of intelligent transport systems are used, such as ramp metering. To cope with the significant daily changes of the traffic demand, various approaches with autonomic properties like self-learning are applied for ramp metering. One of these approaches is reinforced learning. In this paper the Q-Learning algorithm is applied to learn the local ramp metering control law in a simulation environment, implemented in a VISSIM microscopic simulator. The approach proposed is tested in simulations with emphasis on the mainstream speed and travel time, using a typical on-ramp configuration.

【 授权许可】

Unknown