期刊
SUSTAINABILITY
卷 13, 期 20, 页码 -出版社
MDPI
DOI: 10.3390/su132011254
关键词
deep reinforcement learning; emission-reduction; sustainability; traffic signal control
资金
- Ministry of Innovation and Technology NRDI Office
- Hungarian Government
- European Social Fund through the project Talent management in autonomous vehicle control technologies [EFOP-3.6.3-VEKOP-16-2017-00001]
This paper researches the traffic signal control problem, emphasizing emission reduction, and proposes a novel rewarding concept for solving this problem. Experimental results show that the proposed approach outperforms modern actuated control methods in performance and also excels in reducing emissions.
The traffic signal control problem is an extensively researched area providing different approaches, from classic methods to machine learning based ones. Different aspects can be considered to find an optima, from which this paper emphasises emission reduction. The core of our solution is a novel rewarding concept for deep reinforcement learning (DRL) which does not utilize any reward shaping, hence exposes new insights into the traffic signal control (TSC) problem. Despite the omission of the standard measures in the rewarding scheme, the proposed approach can outperform a modern actuated control method in classic performance measures such as waiting time and queue length. Moreover, the sustainability of the realized controls is also placed under investigation to evaluate their environmental impacts. Our results show that the proposed solution goes beyond the actuated control not just in the classic measures but in emission-related measures too.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据