•  
  •  
 

Abstract

The increasing complexity of networks comprising both Connected Autonomous Vehicles (CAVs) and Human-Driven Vehicles (HDVs) presents substantial challenges in achieving accurate positioning, efficient communication, and optimal route planning. Current methodologies fall short in enhancing vehicular network efficiency and reliability due to noise interference, inefficient data transmission, and unstable data transfer. This study aims to improve localization accuracy, reduce communication noise, and enhance path planning efficiency in mixed CAV and HDV environments through the Stable Heterogeneous Traffic Flow using Deep Reinforcement Learning and Effective Path Planning (SHTDR-EPP) approach. The primary goals are to ensure dependable localization, efficient communication, and reliable route planning, thereby maintaining stable and efficient vehicle operations. The SHTDR-EPP approach integrates advanced techniques to analyze heterogeneous traffic flow. Firstly, effective localization is achieved among CAVs. Secondly, a deep reinforcement learning model is developed using the Markov Decision Process to manage mixed traffic flow efficiently. Thirdly, effective path planning is conducted using Extended Direction Analysis. These methods collectively ensure efficient communication between CAVs and HDVs. Experiments were conducted using NS3 and SUMO, with key parameters evaluated including vehicle delay, energy consumption, and safety metrics. The proposed SHTDR-EPP approach significantly enhances vehicular network performance. Positional accuracy is improved through effective localization techniques. Communication efficiency is increased by employing DRL to manage noise and stability. Path planning is optimized through EDA, ensuring efficient and reliable data transmission routes. Comparative analysis with prior methods such as OPP-CAVs and ROC-CAVs demonstrates that SHTDR-EPP achieves superior energy efficiency and vehicle safety. The SHTDR-EPP model effectively addresses critical issues of localization, communication noise, and path planning in mixed vehicular networks. By leveraging modern techniques, the proposed approach significantly enhances the overall efficiency, stability, and reliability of CAV and HDV interactions.

Download

Share

COinS