计算机科学
计算机网络
计算卸载
移动边缘计算
边缘计算
移动计算
计算
GSM演进的增强数据速率
分布式计算
服务器
电信
算法
作者
Jian Zhou,Qifan Yang,Lu Zhao,Haipeng Dai,Fu Xiao
标识
DOI:10.1109/tmc.2024.3359759
摘要
Satellite edge computing, as an extension of ground edge computing, is a key technology for achieving seamless global computing coverage. However, the low earth orbit (LEO) satellites have limited computing resources and are moving at a high speed. This naturally poses a challenge to find more suitable computation offloading strategies with minimum network latency and energy consumption, especially when a large number of co-existing users are to offload their tasks. In this paper, therefore, we mainly focus on computation offloading in the satellite edge computing network (SECN) by jointly considering LEO satellites' mobility and SECN's heterogeneous resource constraints to explore more practical computation offloading strategies. We first formulate the problem of M obility-aware C omputation O ffloading (MCO) in the SECN via specifying the effect of LEO satellites' high-speed movement on the computation offloading, aiming to minimize the network latency and energy consumption. Considering the MCO problem is discrete and non-convex as the objective function and constraints are associated with the binary decision variables. We then convert the original non-convex problem into a continuous convex problem which is proved to be feasible. To avoid a high computational complexity incurred by the extensive co-existing user offloading, we design MCO-A , a distributed algorithm based on ADMM (alternating direction method of multipliers) to solve the MCO problem efficiently. Finally, the performance of MCO-A is evaluated via extensive experiments including small-scale and large-scale scenarios. The experimental results show that MCO-A can achieve a lower network latency and energy consumption in an efficient way compared with the baseline and state-of-the-art approaches.
科研通智能强力驱动
Strongly Powered by AbleSci AI