Delay-Sensitive Energy-Efficient UAV Crowdsensing by Deep Reinforcement Learning

Zipeng Dai, Chi Harold Liu, Rui Han, Guoren Wang, Kin Leung, Jian Tang

Research output: Contribution to journalArticlepeer-review

Abstract

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.

Original languageEnglish (US)
JournalIEEE Transactions on Mobile Computing
DOIs
StateAccepted/In press - 2021
Externally publishedYes

Keywords

  • Computational modeling
  • Crowdsensing
  • Data collection
  • Deep reinforcement learning
  • Delay-sensitive applications
  • Delays
  • Energy-efficiency
  • Navigation
  • Sensors
  • Task analysis
  • UAV crowdsensing

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Delay-Sensitive Energy-Efficient UAV Crowdsensing by Deep Reinforcement Learning'. Together they form a unique fingerprint.

Cite this