Optimization research on UAV semantic communication system based on SVD-MADRL

The study optimizes the flight trajectory and power of multiple unmanned aerial vehicles with the deep deterministic policy gradient algorithm and constructs a multi-unmanned aerial vehicle semantic communication optimization model based on singular value decomposition and multi-agent deep reinforce...

Full description

Saved in:
Bibliographic Details
Main Authors: Yibo Yang, Yahe Tan, Liu Liu
Format: Article
Language:English
Published: Canadian Science Publishing 2025-01-01
Series:Drone Systems and Applications
Subjects:
Online Access:https://cdnsciencepub.com/doi/10.1139/dsa-2024-0049
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849414694433980416
author Yibo Yang
Yahe Tan
Liu Liu
author_facet Yibo Yang
Yahe Tan
Liu Liu
author_sort Yibo Yang
collection DOAJ
description The study optimizes the flight trajectory and power of multiple unmanned aerial vehicles with the deep deterministic policy gradient algorithm and constructs a multi-unmanned aerial vehicle semantic communication optimization model based on singular value decomposition and multi-agent deep reinforcement learning. The results show that the relay system developed in this study is better than traditional algorithms in terms of coverage and flight path, with a coverage rate of up to 90%. Moreover, the energy consumption of the model to complete task transmission is only 2835 joules, and the delay time is only 15 s. In addition, compared with traditional algorithms, the semantic communication optimization model constructed in this study performs the best in terms of total reward, data collection efficiency, and accuracy. It has strong stability and convergence ability, with an accuracy close to 1, significantly improving the accuracy and efficiency of unmanned aerial vehicle communication transmission. The effectiveness of the two models designed for research is relatively high, both superior to traditional methods, providing a theoretical basis for optimizing the overall performance of unmanned aerial vehicle communication. It is of great significance in promoting the widespread application of unmanned aerial vehicle technology.
format Article
id doaj-art-83a7660c66a74efe95e5c0a008b65539
institution Kabale University
issn 2564-4939
language English
publishDate 2025-01-01
publisher Canadian Science Publishing
record_format Article
series Drone Systems and Applications
spelling doaj-art-83a7660c66a74efe95e5c0a008b655392025-08-20T03:33:45ZengCanadian Science PublishingDrone Systems and Applications2564-49392025-01-011311310.1139/dsa-2024-0049Optimization research on UAV semantic communication system based on SVD-MADRLYibo Yang0Yahe Tan1Liu Liu2School of Electrical and Electronic Engineering, Shijiazhuang TieDao University, Shijiazhuang 050043, ChinaSchool of Resources and Civil Engineering, Northeastern University, Shenyang 110819, ChinaSchool of Electrical and Electronic Engineering, Shijiazhuang TieDao University, Shijiazhuang 050043, ChinaThe study optimizes the flight trajectory and power of multiple unmanned aerial vehicles with the deep deterministic policy gradient algorithm and constructs a multi-unmanned aerial vehicle semantic communication optimization model based on singular value decomposition and multi-agent deep reinforcement learning. The results show that the relay system developed in this study is better than traditional algorithms in terms of coverage and flight path, with a coverage rate of up to 90%. Moreover, the energy consumption of the model to complete task transmission is only 2835 joules, and the delay time is only 15 s. In addition, compared with traditional algorithms, the semantic communication optimization model constructed in this study performs the best in terms of total reward, data collection efficiency, and accuracy. It has strong stability and convergence ability, with an accuracy close to 1, significantly improving the accuracy and efficiency of unmanned aerial vehicle communication transmission. The effectiveness of the two models designed for research is relatively high, both superior to traditional methods, providing a theoretical basis for optimizing the overall performance of unmanned aerial vehicle communication. It is of great significance in promoting the widespread application of unmanned aerial vehicle technology.https://cdnsciencepub.com/doi/10.1139/dsa-2024-0049unmanned aerial vehicleposition deploymentdeep deterministic policy gradient algorithmpower optimizationsingular value decomposition
spellingShingle Yibo Yang
Yahe Tan
Liu Liu
Optimization research on UAV semantic communication system based on SVD-MADRL
Drone Systems and Applications
unmanned aerial vehicle
position deployment
deep deterministic policy gradient algorithm
power optimization
singular value decomposition
title Optimization research on UAV semantic communication system based on SVD-MADRL
title_full Optimization research on UAV semantic communication system based on SVD-MADRL
title_fullStr Optimization research on UAV semantic communication system based on SVD-MADRL
title_full_unstemmed Optimization research on UAV semantic communication system based on SVD-MADRL
title_short Optimization research on UAV semantic communication system based on SVD-MADRL
title_sort optimization research on uav semantic communication system based on svd madrl
topic unmanned aerial vehicle
position deployment
deep deterministic policy gradient algorithm
power optimization
singular value decomposition
url https://cdnsciencepub.com/doi/10.1139/dsa-2024-0049
work_keys_str_mv AT yiboyang optimizationresearchonuavsemanticcommunicationsystembasedonsvdmadrl
AT yahetan optimizationresearchonuavsemanticcommunicationsystembasedonsvdmadrl
AT liuliu optimizationresearchonuavsemanticcommunicationsystembasedonsvdmadrl