期刊
IEEE TRANSACTIONS ON MOBILE COMPUTING
卷 22, 期 4, 页码 2038-2052出版社
IEEE COMPUTER SOC
DOI: 10.1109/TMC.2021.3113052
关键词
Sensors; Task analysis; Crowdsensing; Data collection; Navigation; Delays; Computational modeling; UAV crowdsensing; delay-sensitive applications; energy-efficiency; deep reinforcement learning
This paper proposes a centralized control, distributed execution framework called DRL-eFresh, which utilizes unmanned aerial vehicles (UAVs) for mobile crowdsensing (MCS) applications. The framework aims to maximize data collection, maintain geographical fairness, minimize energy consumption, and guarantee data freshness. The proposed framework utilizes decentralized deep reinforcement learning (DRL) and features a synchronous computational architecture with GRU sequential modeling. Simulation results show that DRL-eFresh improves energy efficiency compared to the best baseline by 14% and 22% on average.
Mobile crowdsensing (MCS) by unmanned aerial vehicles (UAVs) servicing delay-sensitive applications becomes popular by navigating a group of UAVs to take advantage of their equipped high-precision sensors and durability for data collection in harsh environments. In this paper, we aim to simultaneously maximize collected data amount, geographical fairness, and minimize the energy consumption of all UAVs, as well as to guarantee the data freshness by setting a deadline in each timeslot. Specifically, we propose a centralized control, distributed execution framework by decentralized deep reinforcement learning (DRL) for delay-sensitive and energy-efficient UAV crowdsensing, called DRL-eFresh. It includes a synchronous computational architecture with GRU sequential modeling to generate multi-UAV navigation decisions. Also, we derive an optimal time allocation solution for data collection while considering all UAV efforts and avoiding much data dropout due to limited data upload time and wireless data rate. Simulation results show that DRL-eFresh significantly improves the energy efficiency, as compared to the best baseline DPPO, by 14% and 22% on average when varying different sensing ranges and number of PoIs, respectively.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据