System Response Topology for the Anomalies (SysRTA) using Ideology Based-Deep Reinforcement Learning (IB-DRL) in Intelligent Transport System

Abstract

An Intelligent Transport System (ITS) is a comprehensive technological solution designed to enhance the efficiency, safety, and sustainability of transportation networks. Leveraging a range of information and communication technologies, ITS aims to manage and optimize traffic flow, enhance transportation safety, reduce congestion, and enhance overall mobility. This paper proposed System Response Topology for the Anomalies (SysRTA) using Ideology Based-Deep Reinforcement Learning (IB-DRL). SysRTA-ID-DRL algorithm proposes. Dynamic Speed Harmonisation (DSH) is a component of the proposed algorithm. It has potential for reducing traffic fluctuations during periods of congestion. However, because of drivers' low adherence rates and long access times to information, its effectiveness frequently encounters limitations. Intelligent transport systems attempt to improve in a number of ways by integrating connected and automated vehicles (CAVs).This approach involves calibrating the Multiple Vehicle Intelligent Driver Model (IDM) and subsequently employing the actual dataset HISTORIC for training the trajectory prediction model. IB-DRL is under development to explore the ways in which Connected and Automated Vehicles (CAVs) can improve operational performance. A thorough analysis is conducted to measure the impacts of multiple simulated scenarios, each featuring different levels of CAV adoption.