.png){kind=icon}
返回
Collaborative Cloud-Edge-End Task Offloading in NOMA-Enabled Mobile Edge Computing Using Deep Learning
.png){kind=icon}
PRE
AI
DOI：10.1007/s10723-022-09605-2.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Aiming at the problem that it is quite hard to guarantee the real-time requirements of medical users with high efficiency and low latency in the current Internet of Medical Things (IoMT), we investigate the task offloading for collaborative cloud-edge-end computing in mobile networks. Non-orthogonal multiple access (NOMA) is suitable for wireless networks with higher spectral efficiency, faster speed, and larger capacity, while the existing cloud-edge-end cooperative computing ignores the advantages of NOMA. Therefore, by exploiting NOMA for improving the efficiency of radio transmission, we integrate collaborative cloud-edge-end computing and NOMA to propose a novel network communication model, which can provide medical users with energy-efficient and low latency services. Specifically, considering the energy consumption, transmission delay, and quality of service, we jointly optimize the offloading decision and its radio resource allocations for NOMA-transmission to reduce the system cost (the weighted sum of consumed energy and delay) in the IoMT of cloud-edge-end computing networks supported by NOMA. Although the joint optimization problem is non-convex, we use its hierarchical structure and propose a collaborative computing offloading algorithm based on deep learning to find the optimal offloading solution. Through extensive simulations, it is shown that the proposed algorithm stably converges to its optimal value, provides approximately 25.2% and 79.2% lower system cost than schemes such as only using edge computing and fully local processing, respectively. In addition, compared with the traditional orthogonal multiple access(OMA), our proposed NOMA-enabled multi-access computation offloading can reduce the system cost by approximately 93.4%.
Keyword:
Computing offloading
Non-orthogonal multiple access
Deep learning
Internet of medical things
Offloading decision
Mobile edge computing
期刊
IF:
2.9
论文数:
761
被引数:
1.2K
机构
引用论文
.png){kind=icon}
Deep Reinforcement Learning for Online Computation Offloading in Wireless Powered Mobile-Edge Computing Networks用于无线供电的移动边缘计算网络中在线计算卸载的深度强化学习
OAAI
OAAI分享收藏Energy-Optimized Partial Computation Offloading in Mobile-Edge Computing With Genetic Simulated-Annealing-Based Particle Swarm Optimization基于遗传模拟退火粒子群算法的移动边缘计算能量优化部分计算卸载
PREAI
分享收藏
查看更多内容