Secrecy energy efficiency maximization in D2D-enabled MEC networks: a GNN-based approach

Jingying Hu; Zhifei Zhang; Yiyang Ge; Jin Mao; Zhipeng Chu; Ke Xiong; Pingyi Fan

doi:10.1117/12.3031371

19 July 2024 Secrecy energy efficiency maximization in D2D-enabled MEC networks: a GNN-based approach

Jingying Hu, Zhifei Zhang, Yiyang Ge, Jin Mao, Zhipeng Chu, Ke Xiong, Pingyi Fan

Proceedings Volume 13181, Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024); 131817R (2024) https://doi.org/10.1117/12.3031371
Event: Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024), 2024, Beijing, China

Abstract

This paper investigates the device-to-device (D2D)-enabled mobile edge computing (MEC) network, where multiple users offload their tasks to an MEC server or their paired devices for computing. In such a network, secrecy and green communication requirements are crucial due to the presence of potential eavesdroppers and the energy demands of global carbon emissions. To this end, a secrecy energy efficiency (SEE) maximization problem is formulated by jointly optimizing the computation frequency at users, the transmit power at users and the subchannel assignments, subject to the quality of service (QoS) and the available energy constraints. To solve the formulated non-convex mixed-integer nonlinear programming problem, a graph neural networks (GNNs) and genetics based resource allocation (GGRA) method is presented, where the communication system is modelled as a directed graph with relationships among users as edges. In order to enhance the ability to process users' own features and handle deep data patterns, self-loops and the ResNet blocks in convolutions and the genetics based optimization are employed. Simulations show that the proposed GGRA improves SEE performance by about 40% compared with the traditional GNN-based method with the same energy budget.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Jingying Hu, Zhifei Zhang, Yiyang Ge, Jin Mao, Zhipeng Chu, Ke Xiong, and Pingyi Fan "Secrecy energy efficiency maximization in D2D-enabled MEC networks: a GNN-based approach", Proc. SPIE 13181, Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024), 131817R (19 July 2024); https://doi.org/10.1117/12.3031371

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available