Scholarlink

<p>One of the main causes of wasted time and energy in society is traffic congestion. Vehicle flows in metropolitan cities are disrupted by various traffic infrastructures, in contrast to the generally smooth vehicle flows on rural roads and highways. Urban areas have become more congested as a result of the significant increase in population density and the rapid migration of individuals from rural areas. Monitoring traffic in these areas is a major concern because of the high volume of vehicles on the roads. In today’s smart transportation systems; it is essential to guarantee effective and safe vehicle-to-infrastructure (V2I) communication for improving traffic control, safety, and overall transportation efficiency. Initially, a Lightweight message verification scheme is proposed to authenticate messages between vehicles and infrastructure. To enhance the communication and resource allocation efficiency we suggest a Double Deep Q-Learning (DDQL) method for adaptive V2I scheduling. Next is the RF-DT-TCONT, which combines Decision Tree and Random Forest algorithms with T-CONTs, is used for predicting traffic. The research also presents HyRSIC, a “Hybrid Routing for Safety data with Intermittent V2I Connectivity” algorithm to guarantee dependable data transmission. This technique improves the resilience and adaptability of traffic control systems. The performance of the proposed method is measured using key metrics of throughput, packet delivery ratio, latency, computational cost, and routing overhead.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Smart traffic management for VANET and IoT environment using lightweight message verification and DD-Q learning techniques

  • 期刊论文

  • 发表日期：

    2025年11月24日

查看全文
  • Moses Odiagbe,
  • Opeyemi Osanaiye,
  • Omotayo Oshiga

摘要

One of the main causes of wasted time and energy in society is traffic congestion. Vehicle flows in metropolitan cities are disrupted by various traffic infrastructures, in contrast to the generally smooth vehicle flows on rural roads and highways. Urban areas have become more congested as a result of the significant increase in population density and the rapid migration of individuals from rural areas. Monitoring traffic in these areas is a major concern because of the high volume of vehicles on the roads. In today’s smart transportation systems; it is essential to guarantee effective and safe vehicle-to-infrastructure (V2I) communication for improving traffic control, safety, and overall transportation efficiency. Initially, a Lightweight message verification scheme is proposed to authenticate messages between vehicles and infrastructure. To enhance the communication and resource allocation efficiency we suggest a Double Deep Q-Learning (DDQL) method for adaptive V2I scheduling. Next is the RF-DT-TCONT, which combines Decision Tree and Random Forest algorithms with T-CONTs, is used for predicting traffic. The research also presents HyRSIC, a “Hybrid Routing for Safety data with Intermittent V2I Connectivity” algorithm to guarantee dependable data transmission. This technique improves the resilience and adaptability of traffic control systems. The performance of the proposed method is measured using key metrics of throughput, packet delivery ratio, latency, computational cost, and routing overhead.