计算机科学
计算卸载
分布式计算
能源消耗
Lyapunov优化
计算
边缘计算
服务质量
点对点
移动边缘计算
计算机网络
高效能源利用
GSM演进的增强数据速率
服务器
算法
电信
Lyapunov重新设计
生态学
李雅普诺夫指数
人工智能
混乱的
电气工程
生物
工程类
作者
Xinyuan Zhang,Jiang Liu,Ran Zhang,Yudong Huang,Jincheng Tong,Ning Xin,Liang Liu,Zehui Xiong
标识
DOI:10.1109/tmc.2023.3269801
摘要
Recently, MEC has been integrated with satellite networks to process remote terrestrial computation tasks with superior coverage and delay. Since single satellite computation is hard to tackle spatially uneven computation workloads, computation peer offloading among multiple satellites is urgently needed to further improve service quality and resource utilization. However, considering limited resources, deficient energy, and costly overheads of communication and computation, how to enable efficient offloading cooperation in the time-varying satellite networks is a significant challenge. In this paper, we first design a satellite peer offloading scheme, where offloading is performed along multi-hop paths to explore collaborative computing capabilities. Second, we formulate the Multi-Hop Satellite Peer offloading (MHSPO) problem, aiming to jointly minimize the delay and energy consumption under system resources and backlog constraints. Then, to adapt to the network dynamics, the decision-making process with uncertain future workloads is optimized by leveraging the delayed online learning method under the Lyapunov framework. Finally, we develop a practical online distributed algorithm to solve the MHSPO problem, which is proven to achieve close-to-optimal performance. Extensive simulations show that multi-hop peer offloading among satellites improves edge computing performance efficiently.
科研通智能强力驱动
Strongly Powered by AbleSci AI