3.
4 Imact Factor WOS Q2
sensors
Article
A Dynamic Traffic Light Control Algorithm to Mitigate Traffic
Congestion in Metropolitan Areas
Bharathi Ramesh Kumar 1 , Narayanan Kumaran 1 , Jayavelu Udaya Prakash 2 , Sachin Salunkhe 3,4 ,
Raja Venkatesan 5, * , Ragavanantham Shanmugam 6 and Emad S. Abouel Nasr 7
1 Department of Mathematics, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology,
Chennai 600062, Tamil Nadu, India; [email protected] (B.R.K.); [email protected] (N.K.)
2 Department of Mechanical Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and
Technology, Chennai 600062, Tamil Nadu, India; [email protected]
3 Department of Biosciences, Saveetha School of Engineering, Saveetha Institute of Medical and Technical
Sciences, Chennai 602105, Tamil Nadu, India; [email protected]
4 Department of Mechanical Engineering, Faculty of Engineering, Gazi University, 06560 Ankara, Turkey
5 School of Chemical Engineering, Yeungnam University, 280 Daehak-Ro, Gyeongsan 38541, Republic of Korea
6 Department of Mechanical Engineering, Fairmont State University, Fairmont, WV 26554, USA;
[email protected]
7 Department of Industrial Engineering, College of Engineering, King Saud University, P.O. Box 800,
Riyadh 11421, Saudi Arabia; [email protected]
* Correspondence: [email protected]
Abstract: This paper proposes a convolutional neural network (CNN) model of the signal distribution
control algorithm (SDCA) to maximize the dynamic vehicular traffic signal flow for each junction
phase. The aim of the proposed algorithm is to determine the reward value and new state. It decon-
structs the routing components of the current multi-directional queuing system (MDQS) architecture
to identify optimal policies for every traffic scenario. Initially, the state value is divided into a function
value and a parameter value. Combining these two scenarios updates the resulting optimized state
value. Ultimately, an analogous criterion is developed for the current dataset. Next, the error or loss
value for the present scenario is computed. Furthermore, utilizing the Deep Q-learning methodology
with a quad agent enhances previous study discoveries. The recommended method outperforms all
other traditional approaches in effectively optimizing traffic signal timing.
Citation: Kumar, B.R.; Kumaran, N.;
Prakash, J.U.; Salunkhe, S.; Keywords: multi-queuing system; signal distribution; real-time traffic scenario; convolutional neural
Venkatesan, R.; Shanmugam, R.; network (CNN); traffic flow rate
Abouel Nasr, E.S. A Dynamic Traffic
Light Control Algorithm to Mitigate
Traffic Congestion in Metropolitan
Areas. Sensors 2024, 24, 3987.
1. Introduction
https://doi.org/10.3390/s24123987
In response to the demands of a challenging society, there is increasing pressure to
Received: 14 May 2024 expand urban transportation in modern cities. As travel demand rises, traffic bottlenecks
Revised: 14 June 2024 and vehicular accidents are becoming more serious. Due to unreasonable traffic signal
Accepted: 16 June 2024
settings, one of the most significant problems is traffic congestion. This issue lengthens
Published: 19 June 2024
passenger travel times and dramatically raises both local and global pollution levels. In
order to meet the demands of challenging societies, there is pressure on the expansion of
urban transportation in modern cities. As a result, one of the main problems in cities is
Copyright: © 2024 by the authors.
traffic congestion, especially around signalized junctions. The cyclic model of traffic signal
Licensee MDPI, Basel, Switzerland. lights at connection junction regions uses the current traffic signal flow system, which is one
This article is an open access article of the primary causes of the problems. Even density-based traffic signal timing has been
distributed under the terms and recently implemented in most modern cities. Particularly, in different parts of India, nearly
conditions of the Creative Commons 400 traffic signals have shifted to density-based traffic signal timing methods, such as:
Attribution (CC BY) license (https:// Delhi, Noida, Bhopal, Ghaziabad, Agra, Gwalior, Bulandshar, Murdabad, and Utta Pradesh
creativecommons.org/licenses/by/ (state) at Lucknow, using a hybrid method that uses an inventive algorithmic combination
4.0/). to determine the best times for traffic signals and can still improve obstacle avoidance.
Sensors 2024, 24, 3987. https://doi.org/10.3390/s24123987 https://www.mdpi.com/journal/sensors
