Scholarlink

<p>The soaring global demand for ubiquitous wireless connectivity, which epitomizes the digital era, can only be fulfilled with heterogenous networks that, increasingly, need to include aerial platform fleets for a more holistic approach. However, deploying aerial platforms to serve as a fleet would inevitably result in interference, especially for high frequency bands and increased power consumption. This work presents a framework that integrates Machine Learning with a fleet positioning mechanism to mitigate interference and reduce power consumption in a multilayer fleet of aerial platforms. In turn, this optimizes flight time in the short run and the sustainability of the holistic connectivity approach in the long run. Assessment of the post-optimisation Received Signal Strength Index reveals a 16% improvement to pre-optimisation. The work is validated with a proof-of-concept for smart agriculture.</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

Integrating machine learning with a positioning mechanism for managing interference and power consumption in a multilayer fleet of unmanned aerial platforms

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年6月16日

查看全文
  • Faris A. Almalki,
  • Marios C. Angelides

摘要

The soaring global demand for ubiquitous wireless connectivity, which epitomizes the digital era, can only be fulfilled with heterogenous networks that, increasingly, need to include aerial platform fleets for a more holistic approach. However, deploying aerial platforms to serve as a fleet would inevitably result in interference, especially for high frequency bands and increased power consumption. This work presents a framework that integrates Machine Learning with a fleet positioning mechanism to mitigate interference and reduce power consumption in a multilayer fleet of aerial platforms. In turn, this optimizes flight time in the short run and the sustainability of the holistic connectivity approach in the long run. Assessment of the post-optimisation Received Signal Strength Index reveals a 16% improvement to pre-optimisation. The work is validated with a proof-of-concept for smart agriculture.