Energy-Efficient Task Offloading and DNN Inference in Dynamic STAR-RIS Assisted MEC With Decomposition-Based DRL
IEEE Transactions on Wireless Communications · 2026 · 25 · 1640-1655
DOI: 10.1109/twc.2025.3592255 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2026. Verfasst von Yiting Huang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: Guangxi Natural Science Foundation, Guangxi Science and Technology Projects, National Natural Science Foundation of China.
Abstract (Originalsprache)
Deploying Deep Neural Network (DNN) models of varying capabilities to support collaborative inference for User Equipment (UE) tasks is becoming increasingly common in Mobile Edge Computing (MEC) systems. In this paper, we aim to minimize energy consumption in a dynamic Non-Orthogonal Multiple Access (NOMA)-based MEC system assisted by a Simultaneously Transmitting and Reflecting Reconfigurable Intelligent Surface (STAR-RIS) under complex Non-Line-of-Sight (NLoS) conditions, while meeting latency requirements and preserving inference accuracy for UEs. We formulate the problem as a non-convex optimization and address it using a Decomposition-Based Twin Delayed Deep Deterministic Policy Gradient (DB-TD3) approach. The problem is decomposed into two subproblems: 1) computation resource allocation and power optimization, and 2) optimization of the offloading ratio, time fractions allocated for reflection and transmission, phase shift, and transmission time. For the first subproblem, we derive optimal CPU frequencies and transmit power allocation through theoretical analysis. For the second subproblem, the offloading ratio, time fractions allocated for reflection and transmission, phase shift, and transmission time are optimized using the TD3 algorithm. Experimental results demonstrate that the DB-TD3 method significantly improves system efficiency and reduces average energy consumption by 59.3% compared to baseline algorithms. Furthermore, the proposed NOMA with STAR-RIS scheme outperforms other offloading methods, achieving an average energy reduction of 41.3%.
Förderung
- Guangxi Natural Science Foundation
- Guangxi Science and Technology Projects
- National Natural Science Foundation of China
- Key Laboratory of Nonlinear Circuits and Optical Communications (Guangxi Normal University), Education Department of Guangxi Zhuang Autonomous Region
- Guangxi Key Laboratory of Brain-Inspired Computing and Intelligent Chips
- Innovation Project of Guangxi Graduate Education
Zitieren
APA
Huang, Y., Lu, B., Luo, Y., Fang, J., Fu, Q., Qin, S., & Liu, J. (2026). Energy-Efficient Task Offloading and DNN Inference in Dynamic STAR-RIS Assisted MEC With Decomposition-Based DRL. IEEE Transactions on Wireless Communications, 25, 1640-1655. https://doi.org/10.1109/twc.2025.3592255
Vancouver
Huang Y, Lu B, Luo Y, Fang J, Fu Q, Qin S, et al. Energy-Efficient Task Offloading and DNN Inference in Dynamic STAR-RIS Assisted MEC With Decomposition-Based DRL. IEEE Transactions on Wireless Communications. 2026;25:1640-1655. doi:10.1109/twc.2025.3592255
BibTeX
@article{Huang2026,
author = {Huang, Yiting and Lu, Baoshan and Luo, Yuling and Fang, Junli and Fu, Qiang and Qin, Sheng and Liu, Junxiu},
title = {Energy-Efficient Task Offloading and DNN Inference in Dynamic STAR-RIS Assisted MEC With Decomposition-Based DRL},
journal = {IEEE Transactions on Wireless Communications},
year = {2026},
volume = {25},
pages = {1640--1655},
doi = {10.1109/twc.2025.3592255}
}
EUVIMED