Two-Tier Multi-Access Partial Computation Offloading via NOMA: A Hybrid Deep Learning Approach for Energy Minimization

Yang Li, Yuan Wu, Suzhi Bi, Liping Qian, Tony Q.S. Quek, Chengzhong Xu, Zhiguo Shi

研究成果: Conference contribution

摘要

Multi-access edge computing has been considered as a promising solution for enabling computation-intensive yet latency-sensitive applications at resource-constrained wireless devices (WDs). To improve the spectrum efficiency for multi-WD computation offloading, this paper considers non-orthogonal multiple access (NOMA) assisted two-tier multi-access edge computing scenario, which exploits the computation resources of both the edge servers (ESs) and the cloudlet server (CS) deployed at different tiers. In particular, the WDs can offload partial workloads to different ESs simultaneously via NOMA, and the ESs can form a NOMA-group to further offload partially received workloads to the CS for processing. We investigate the total energy consumption minimization problem by jointly optimizing the two-tier offloading decisions, the NOMA transmission duration, and the computation resource allocation. Due to the successive interference cancellation in the NOMA and the coupling effect in two-tier offloading, the formulated optimization problem is strictly non-convex. To address this difficulty, we exploit the hierarchical relationship among the joint optimization variables, and then propose a hybrid deep reinforcement learning (HDRL) algorithm to learn two policies that determine the coupled variables, i.e., the ESs' offloading decisions and the NOMA transmission duration, respectively. Then, the remaining decision variables can be jointly optimized by using the convex optimization methods directly based on the results provided by the HDRL algorithm. Specifically, the HDRL algorithm that uses different policies to determine the coupled variables can converge faster than the existing solutions that learn a single policy to determine all variables. Experimental results are provided to validate the performance of our proposed HDRL algorithm in comparison with two other learning-based algorithms.

原文English
主出版物標題2022 31st Wireless and Optical Communications Conference, WOCC 2022
發行者Institute of Electrical and Electronics Engineers Inc.
頁面138-143
頁數6
ISBN(電子)9781665469500
DOIs
出版狀態Published - 2022
事件31st Wireless and Optical Communications Conference, WOCC 2022 - Shenzhen, China
持續時間: 2022 8月 112022 8月 12

出版系列

名字2022 31st Wireless and Optical Communications Conference, WOCC 2022

Conference

Conference31st Wireless and Optical Communications Conference, WOCC 2022
國家/地區China
城市Shenzhen
期間22-08-1122-08-12

All Science Journal Classification (ASJC) codes

  • 安全、風險、可靠性和品質
  • 原子與分子物理與光學
  • 人工智慧
  • 電腦網路與通信
  • 訊號處理

指紋

深入研究「Two-Tier Multi-Access Partial Computation Offloading via NOMA: A Hybrid Deep Learning Approach for Energy Minimization」主題。共同形成了獨特的指紋。

引用此