Scholarlink

<p>Rapid urbanization and the exponential growth of vehicular traffic have intensified congestion, travel delays, and emissions, posing serious challenges for sustainable urban mobility. To address these issues, numerous studies have explored both algorithmic and communication-based traffic management approaches. However, existing reviews often treat these domains separately, lacking a unified perspective. This paper presents a comprehensive review that bridges algorithmic optimization and communication-enabled cooperative control. The study systematically categorizes traffic signal optimization algorithms including fixed time, actuated, adaptive, fuzzy logic, genetic, reinforcement learning and game theory based methods and communication-driven strategies such as Vehicle-to-Vehicle (V2V) &amp; Vehicle-to-Infrastructure (V2I), IoV / RSU / Edge / Fog / SDN, CAV Coordination &amp; Reservation Systems, AI/ML + Communication Fusion and Safety &amp; Perception Enhancement. A PRISMA process has been followed for the selection of the papers and selected papers were analyzed to evaluate performance metrics, limitations, and research trends. The findings reveal that adaptive control and reinforcement learning, particularly deep and multi-agent RL models, dominate algorithmic research, while CAV coordination and IoV frameworks are emerging as key communication paradigms. Persistent challenges include scalability, penetration rate, real-time responsiveness, and limited real-world validation. The paper’s unique contribution lies in synthesizing these two research streams to propose a hybrid, future ready architecture that integrates local adaptive intelligence with global, communication-based coordination providing a strategic roadmap toward sustainable, intelligent traffic systems.</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

From Algorithms to Connectivity: A Comprehensive Review of Traffic Signal Optimization and Communication Based Cooperative Control

  • 期刊论文

  • 发表日期：

    2025年11月5日

查看全文
  • Viral Patel,
  • Nilesh Maltare

摘要

Rapid urbanization and the exponential growth of vehicular traffic have intensified congestion, travel delays, and emissions, posing serious challenges for sustainable urban mobility. To address these issues, numerous studies have explored both algorithmic and communication-based traffic management approaches. However, existing reviews often treat these domains separately, lacking a unified perspective. This paper presents a comprehensive review that bridges algorithmic optimization and communication-enabled cooperative control. The study systematically categorizes traffic signal optimization algorithms including fixed time, actuated, adaptive, fuzzy logic, genetic, reinforcement learning and game theory based methods and communication-driven strategies such as Vehicle-to-Vehicle (V2V) & Vehicle-to-Infrastructure (V2I), IoV / RSU / Edge / Fog / SDN, CAV Coordination & Reservation Systems, AI/ML + Communication Fusion and Safety & Perception Enhancement. A PRISMA process has been followed for the selection of the papers and selected papers were analyzed to evaluate performance metrics, limitations, and research trends. The findings reveal that adaptive control and reinforcement learning, particularly deep and multi-agent RL models, dominate algorithmic research, while CAV coordination and IoV frameworks are emerging as key communication paradigms. Persistent challenges include scalability, penetration rate, real-time responsiveness, and limited real-world validation. The paper’s unique contribution lies in synthesizing these two research streams to propose a hybrid, future ready architecture that integrates local adaptive intelligence with global, communication-based coordination providing a strategic roadmap toward sustainable, intelligent traffic systems.