Scholarlink

<p>Congestion control is a demanding functionality for intelligent transportation systems. It involves various functionalities and tasks, namely, traffic estimation and forecasting, sensing and communication, and traffic signal control. The literature on traffic congestion estimation and control has emerged significantly, and different methodologies and approaches have evolved. In this survey, an exploration of the existing systems in traffic congestion estimation and control was conducted. Furthermore, this review provides the primary taxonomy of the current methodologies and approaches; namely, for congestion estimation: machine learning, fusion methods, and for congestion control: machine learning and data-driven models, optimization techniques, technology-driven approaches, fuzzy logic and systems, game theory and decision making, and hybrid traffic management. In addition, this survey is considered the first to address traffic congestion handling in intelligent transportation systems from sensing, estimation, detection, recognition, and control perspectives. Finally, the survey provides an overview of the existing issues and challenges for traffic congestion in intelligent transportation systems, as well as future research directions.</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

Traffic Congestion Estimation and Control: A Comprehensive Review of the Applied Computational Intelligence Models

  • 期刊论文

  • 发表日期：

    2025年7月5日

查看全文
  • Younus Hasan Taher,
  • Jit Singh Mandeep,
  • Haydar Abdulameer Marhoon,
  • Hamdi A. Al-Jamimi,
  • Hamzah Luqman,
  • Farag Azzedin,
  • Muhammad Abdullah,
  • Hassan M. Al-Ahmadi,
  • Zaher Mundher Yaseen

摘要

Congestion control is a demanding functionality for intelligent transportation systems. It involves various functionalities and tasks, namely, traffic estimation and forecasting, sensing and communication, and traffic signal control. The literature on traffic congestion estimation and control has emerged significantly, and different methodologies and approaches have evolved. In this survey, an exploration of the existing systems in traffic congestion estimation and control was conducted. Furthermore, this review provides the primary taxonomy of the current methodologies and approaches; namely, for congestion estimation: machine learning, fusion methods, and for congestion control: machine learning and data-driven models, optimization techniques, technology-driven approaches, fuzzy logic and systems, game theory and decision making, and hybrid traffic management. In addition, this survey is considered the first to address traffic congestion handling in intelligent transportation systems from sensing, estimation, detection, recognition, and control perspectives. Finally, the survey provides an overview of the existing issues and challenges for traffic congestion in intelligent transportation systems, as well as future research directions.