Scholarlink

<p>Recently, Flying Ad-hoc Networks (FANETs) has become a growing subfield of wireless ad-hoc networks that allow multiple Unmanned Aerial Vehicles (UAVs) to directly connect to each other for accomplishing various military and civilian purposes. The flexible nature of this network, including the rapid movement of UAVs, low density, unpredictable topology changes, and limited energy, makes developing a trustworthy and effective routing strategy a very challenging task. Currently, most research has employed the advanced Machine Learning (ML) approach to enhance routing techniques for information dissemination, as ML ensures an effective routing solution with high message delivery, energy efficiency, and low delay. This systematic review outlines the key advantages and applications of ML technology, providing a methodical examination of various ML-based routing approaches specifically designed to enhance the performance of FANETs. This paper offers a comprehensive evaluation of diverse ML-based routing methods, examining their performance metrics, contributions, and identified areas for improvement. Finally, this paper explores the key challenges and future research directions in FANETs that motivate the researcher to apply ML techniques to overcome various challenges in highly dynamic Networks.</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

Machine Learning Based Routing Approaches for Flying Ad-hoc Networks (FANETs): A Systematic Review

  • 期刊论文

  • 发表日期：

    2026年5月7日

查看全文
  • Khushbu Jaiswal,
  • Sudesh Kumar,
  • Neeraj Kumar Rathore

摘要

Recently, Flying Ad-hoc Networks (FANETs) has become a growing subfield of wireless ad-hoc networks that allow multiple Unmanned Aerial Vehicles (UAVs) to directly connect to each other for accomplishing various military and civilian purposes. The flexible nature of this network, including the rapid movement of UAVs, low density, unpredictable topology changes, and limited energy, makes developing a trustworthy and effective routing strategy a very challenging task. Currently, most research has employed the advanced Machine Learning (ML) approach to enhance routing techniques for information dissemination, as ML ensures an effective routing solution with high message delivery, energy efficiency, and low delay. This systematic review outlines the key advantages and applications of ML technology, providing a methodical examination of various ML-based routing approaches specifically designed to enhance the performance of FANETs. This paper offers a comprehensive evaluation of diverse ML-based routing methods, examining their performance metrics, contributions, and identified areas for improvement. Finally, this paper explores the key challenges and future research directions in FANETs that motivate the researcher to apply ML techniques to overcome various challenges in highly dynamic Networks.