Skip to main navigation Skip to search Skip to main content

Lightweight Joint Optimization of Clustering and Trajectory for UAV-Assisted WSNs

  • Chenhui Chu
  • , Bo Xiao*
  • *Corresponding author for this work
  • East China Normal University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

UAV-assisted data collection in wireless sensor networks offers flexibility and cost-efficiency, yet faces challenges from complex air-ground coupling and joint trajectory-resource optimization. Traditional deep reinforcement learning (DRL) methods still struggle with limited deployment capability on embedded platforms. This paper proposes a lightweight DQN framework with structured pruning to jointly optimize UAV path planning and cluster head selection. The approach employs forward-activation-based pruning for model compression. Simulations show that the proposed method outperforms ACO, with model size reduced by up to 90% while maintaining real-time performance suitable for UAV deployment.

Original languageEnglish
Title of host publication2026 IEEE 8th International Conference on Communications, Information System and Computer Engineering, CISCE 2026
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages238-241
Number of pages4
ISBN (Electronic)9798331560423
DOIs
StatePublished - 2026
Event8th IEEE International Conference on Communications, Information System and Computer Engineering, CISCE 2026 - Guangzhou, China
Duration: 27 Mar 202629 Mar 2026

Publication series

Name2026 IEEE 8th International Conference on Communications, Information System and Computer Engineering, CISCE 2026

Conference

Conference8th IEEE International Conference on Communications, Information System and Computer Engineering, CISCE 2026
Country/TerritoryChina
CityGuangzhou
Period27/03/2629/03/26

Keywords

  • deep Q network (DQN)
  • pruning
  • unmanned aerial vehicle (UAV)
  • wireless sensor network (WSN)

Fingerprint

Dive into the research topics of 'Lightweight Joint Optimization of Clustering and Trajectory for UAV-Assisted WSNs'. Together they form a unique fingerprint.

Cite this