Joint Optimization of Security and Energy Efficiency in UAV-Assisted Mobile Edge Computing Systems Using Deep Reinforcement Learning

Wenxiang Shen; Yuanjian Li; Rui Zhao; Zhiping Lin; Zhenguo Gao

doi:10.1109/ICSE68658.2025.11407655

Joint Optimization of Security and Energy Efficiency in UAV-Assisted Mobile Edge Computing Systems Using Deep Reinforcement Learning

Wenxiang Shen
, Yuanjian Li^*
, Rui Zhao^*
, Zhiping Lin
, Zhenguo Gao

^*Corresponding author for this work

Huaqiao University

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

Abstract

This paper studies secure task offloading and energy efficiency in Unmanned Aerial Vehicle (UAV)-assisted systems. The UAV serves as both an edge server and a jammer to help ground User Equipment (UEs) with limited resources. We formulate an optimization problem to maximize security and energy efficiency. This problem jointly optimizes UAV trajectory, CPU frequency, and communication resources under physical constraints. To solve this problem, we model it as a Markov game and propose a Multi-agent Nash-Stackelberg Decision Process (MNDP) algorithm based on multi-agent deep reinforcement learning. Simulation results show that MNDP outperforms baseline algorithms including MADDPG and MATD3.

Original language	English
Title of host publication	2025 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	180-184
Number of pages	5
ISBN (Electronic)	9798331579364
DOIs	https://doi.org/10.1109/ICSE68658.2025.11407655
Publication status	Published - 2025
Event	2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025 - Shenzhen, China Duration: 12 Dec 2025 → 14 Dec 2025

Publication series

Name	2025 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025

Conference

Conference	2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025
Country/Territory	China
City	Shenzhen
Period	12/12/25 → 14/12/25

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

6G Networks
Deep Reinforcement Learning
Mobile Edge Computing
Physical Layer Security

Access to Document

10.1109/ICSE68658.2025.11407655

Cite this

Shen, W., Li, Y., Zhao, R., Lin, Z., & Gao, Z. (2025). Joint Optimization of Security and Energy Efficiency in UAV-Assisted Mobile Edge Computing Systems Using Deep Reinforcement Learning. In 2025 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025 (pp. 180-184). (2025 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSE68658.2025.11407655

Shen, Wenxiang ; Li, Yuanjian ; Zhao, Rui et al. / Joint Optimization of Security and Energy Efficiency in UAV-Assisted Mobile Edge Computing Systems Using Deep Reinforcement Learning. 2025 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025. Institute of Electrical and Electronics Engineers Inc., 2025. pp. 180-184 (2025 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025).

@inproceedings{4457281ad13a409e8ff9c828668e91d2,

title = "Joint Optimization of Security and Energy Efficiency in UAV-Assisted Mobile Edge Computing Systems Using Deep Reinforcement Learning",

abstract = "This paper studies secure task offloading and energy efficiency in Unmanned Aerial Vehicle (UAV)-assisted systems. The UAV serves as both an edge server and a jammer to help ground User Equipment (UEs) with limited resources. We formulate an optimization problem to maximize security and energy efficiency. This problem jointly optimizes UAV trajectory, CPU frequency, and communication resources under physical constraints. To solve this problem, we model it as a Markov game and propose a Multi-agent Nash-Stackelberg Decision Process (MNDP) algorithm based on multi-agent deep reinforcement learning. Simulation results show that MNDP outperforms baseline algorithms including MADDPG and MATD3.",

keywords = "6G Networks, Deep Reinforcement Learning, Mobile Edge Computing, Physical Layer Security",

author = "Wenxiang Shen and Yuanjian Li and Rui Zhao and Zhiping Lin and Zhenguo Gao",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025 ; Conference date: 12-12-2025 Through 14-12-2025",

year = "2025",

doi = "10.1109/ICSE68658.2025.11407655",

language = "English",

series = "2025 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "180--184",

booktitle = "2025 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025",

}

Shen, W, Li, Y, Zhao, R, Lin, Z & Gao, Z 2025, Joint Optimization of Security and Energy Efficiency in UAV-Assisted Mobile Edge Computing Systems Using Deep Reinforcement Learning. in 2025 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025. 2025 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025, Institute of Electrical and Electronics Engineers Inc., pp. 180-184, 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025, Shenzhen, China, 12/12/25. https://doi.org/10.1109/ICSE68658.2025.11407655

Joint Optimization of Security and Energy Efficiency in UAV-Assisted Mobile Edge Computing Systems Using Deep Reinforcement Learning. / Shen, Wenxiang; Li, Yuanjian; Zhao, Rui et al.
2025 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025. Institute of Electrical and Electronics Engineers Inc., 2025. p. 180-184 (2025 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025).

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - Joint Optimization of Security and Energy Efficiency in UAV-Assisted Mobile Edge Computing Systems Using Deep Reinforcement Learning

AU - Shen, Wenxiang

AU - Li, Yuanjian

AU - Zhao, Rui

AU - Lin, Zhiping

AU - Gao, Zhenguo

PY - 2025

Y1 - 2025

N2 - This paper studies secure task offloading and energy efficiency in Unmanned Aerial Vehicle (UAV)-assisted systems. The UAV serves as both an edge server and a jammer to help ground User Equipment (UEs) with limited resources. We formulate an optimization problem to maximize security and energy efficiency. This problem jointly optimizes UAV trajectory, CPU frequency, and communication resources under physical constraints. To solve this problem, we model it as a Markov game and propose a Multi-agent Nash-Stackelberg Decision Process (MNDP) algorithm based on multi-agent deep reinforcement learning. Simulation results show that MNDP outperforms baseline algorithms including MADDPG and MATD3.

AB - This paper studies secure task offloading and energy efficiency in Unmanned Aerial Vehicle (UAV)-assisted systems. The UAV serves as both an edge server and a jammer to help ground User Equipment (UEs) with limited resources. We formulate an optimization problem to maximize security and energy efficiency. This problem jointly optimizes UAV trajectory, CPU frequency, and communication resources under physical constraints. To solve this problem, we model it as a Markov game and propose a Multi-agent Nash-Stackelberg Decision Process (MNDP) algorithm based on multi-agent deep reinforcement learning. Simulation results show that MNDP outperforms baseline algorithms including MADDPG and MATD3.

KW - 6G Networks

KW - Deep Reinforcement Learning

KW - Mobile Edge Computing

KW - Physical Layer Security

UR - https://www.scopus.com/pages/publications/105036190626

U2 - 10.1109/ICSE68658.2025.11407655

DO - 10.1109/ICSE68658.2025.11407655

M3 - Conference Proceeding

AN - SCOPUS:105036190626

T3 - 2025 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025

SP - 180

EP - 184

BT - 2025 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025

Y2 - 12 December 2025 through 14 December 2025

ER -

Shen W, Li Y, Zhao R, Lin Z, Gao Z. Joint Optimization of Security and Energy Efficiency in UAV-Assisted Mobile Edge Computing Systems Using Deep Reinforcement Learning. In 2025 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025. Institute of Electrical and Electronics Engineers Inc. 2025. p. 180-184. (2025 2nd International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2025). doi: 10.1109/ICSE68658.2025.11407655

Joint Optimization of Security and Energy Efficiency in UAV-Assisted Mobile Edge Computing Systems Using Deep Reinforcement Learning

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Cite this