Digital-Twin-Based Deep Reinforcement Learning Approach for Adaptive Traffic Signal Control

Kamal, Hani and Yánez, Wendy and Hassan, Sara and Sobhy, Dalia (2024) Digital-Twin-Based Deep Reinforcement Learning Approach for Adaptive Traffic Signal Control. IEEE Internet of Things Journal, 11 (12). pp. 21946-21953. ISSN 2372-2541

Preview

Text Accepted_version_-_Traffic_Optimization_IoT.pdf - Accepted Version Download (928kB)

Abstract

Urban vehicle emissions are one of the main contributors to air pollution since most vehicles still rely on fossil fuels, despite the growing popularity of alternative options, such as hybrids and electric cars. Recently, artificial intelligence (AI) and automation-based controllers have gained attention for their potential use in adaptive traffic signal control. Many studies have been conducted on the application of deep reinforcement learning (DRL) models to reduce travel time in adaptive traffic signal control. However, limited research has been done on adapting traffic signal control to reduce CO2 emissions and fuel consumption in urban vehicles. As such, this work proposes a digital-twin-based adaptive traffic signal control approach that relies on a digital twin (DT) of urban traffic network and uses the DRL multiagent deep deterministic policy gradient (MADDPG) to optimize for reduced fuel consumption and CO2 emission. The system is designed to simulate different traffic scenarios and control strategies, enabling for adaptation in traffic signal adjustments. To assess the effectiveness and applicability of the proposed approach, a quantitative simulation is performed using synthetic and real-world traffic data sets from a multi-intersection network in a neighborhood in Amman, Jordan, during peak hours. The findings suggest that the DRL approach based on DTs on synthetic networks can reduce CO2 emissions and fuel consumption even when using a basic reward function based on stopped vehicles.

Item Type:	Article
Identification Number:	10.1109/JIOT.2024.3377600
Dates:	Date Event 1 March 2024 Accepted 15 March 2024 Published Online
Uncontrolled Keywords:	Fuels, carbon emissions, junctions, traffic control, digitial twins, data collection, internet of things
Subjects:	CAH11 - computing > CAH11-01 - computing > CAH11-01-03 - information systems
Divisions:	Faculty of Computing, Engineering and the Built Environment > College of Computing
Depositing User:	Gemma Tonks
Date Deposited:	23 Oct 2024 12:28
Last Modified:	23 Oct 2024 12:28
URI:	https://www.open-access.bcu.ac.uk/id/eprint/15925

Actions (login required)

View Item