SELF-ADAPTING REWARD-BASED REINFORCEMENT LEARNING FOR OPTIMIZING TRAFFIC SIGNALS WITH AN SUMO-BASED DIGITAL TWIN IN SMART CITY TRAFFIC CONTROL

Read full text Summarise with VIRAT
Authors: NILANJAN DAS
Cited by: 0
References: 9

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

As the traffic complexities and issues increases in smart intelligent cities, intelligent smart adaptive management and controlling mechanism is in highly priority.A proposed framework of real-time traffic digital twin using Simulation of Urban Mobility (SUMO) with TraCI, and Python-based reinforcement learning to optimize traffic flow has been incorporated in this paper.In this paper, proposed framework of digital twin captured real-time traffic data including, waiting time, and queue length and CO2 emission using reinforcement learning with Genetic Algorithm dynamically control the traffic signal to reduce the congestion and traffic delay.This paper incorporate a Genetic algorithm based hybrid Reinforcement Learning framework to reduce the congestion and CO2 emission by optimizing traffic signal dynamically.

Fields of Study & Subjects

Traffic control and management Traffic Prediction and Management Techniques Road Transport and Highway Systems

Publication details

Journal / source
Science and Culture
Volume
92
Publication date
17 March 2026
Language
EN