Scholarlink

<p>The current study aims to investigate a mobile edge computing (MEC) system reinforced by several unmanned aerial vehicles (UAVs), which function as edge servers (ESs), catering to the computing requirements of Internet of Things (IoT) devices. The primary objective of this study is to maximize revenue by minimizing the energy consumption of the system. This will be achieved by utilizing the ideal time of UAVs for monitoring marine life, which can increase profit. However, achieving this objective poses a significant challenge since it entails considering the order of halting points (HPs), their deployment and the relationship between UAVs and HPs. This research proposes a solution to the multi-task UAVs and introduces an innovative Energy Harvesting Model (EHM) to minimize the energy consumption of the UAVs. Additionally, the results presented here demonstrate the effectiveness of the novel evolutionary strategies developed for minimizing energy consumption and increasing the system’s efficacy. Specifically, the MoOP algorithm offers a higher utilization rate of 28.68% compared to 21.34% for G.A. and 16.29% for Random algorithms. Furthermore, the MoOP algorithm also achieves a larger profit by 11.29% compared to G.A., 26.37% compared to the random technique, and 34.91% compared to the K-means algorithm.</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

Exploring Profitability Allocation and Halting Problems for Multitask AI Edge-Assisted IoT Device

  • 期刊论文

  • 发表日期：

    2025年8月1日

查看全文
  • Vaibhav Tiwari,
  • Chandrasen Pandey,
  • Diptendu Sinha Roy

摘要

The current study aims to investigate a mobile edge computing (MEC) system reinforced by several unmanned aerial vehicles (UAVs), which function as edge servers (ESs), catering to the computing requirements of Internet of Things (IoT) devices. The primary objective of this study is to maximize revenue by minimizing the energy consumption of the system. This will be achieved by utilizing the ideal time of UAVs for monitoring marine life, which can increase profit. However, achieving this objective poses a significant challenge since it entails considering the order of halting points (HPs), their deployment and the relationship between UAVs and HPs. This research proposes a solution to the multi-task UAVs and introduces an innovative Energy Harvesting Model (EHM) to minimize the energy consumption of the UAVs. Additionally, the results presented here demonstrate the effectiveness of the novel evolutionary strategies developed for minimizing energy consumption and increasing the system’s efficacy. Specifically, the MoOP algorithm offers a higher utilization rate of 28.68% compared to 21.34% for G.A. and 16.29% for Random algorithms. Furthermore, the MoOP algorithm also achieves a larger profit by 11.29% compared to G.A., 26.37% compared to the random technique, and 34.91% compared to the K-means algorithm.