CL-ADMM: A Cooperative-Learning-Based Optimization Framework for Resource Management in MEC
CL-ADMM: A Cooperative-Learning-Based Optimization Framework for Resource Management in MEC
复制标题
CL-ADMM：MEC 中基于合作学习的资源管理优化框架
DOI：
10.1109/jiot.2020.3043749
复制
发表时间：
2020-03
影响因子：
10.6
通讯作者：
Zhang Weizhe
中科院分区：
文献类型：
--
作者：
Zhong Xiaoxiong;Wang Xinghan;Li Li;Yang Yuanyuan;Qin Yang;Yang Tingting;Zhang Bin;Zhang Weizhe
研究了移动边缘计算（MEC）中智能高效的资源管理框架问题，该框架能够降低延迟和能耗，具有分布式优化和有效的拥塞避免功能。在这篇文章中，我们提出了一个合作学习的框架，在MEC资源管理的交替方向乘数法（ADMMs）的角度来看，命名为CL-ADMM框架。首先，计算一个任务需要用户的个人数据和相应的程序处理它，有效地缓存程序在一个组中，提出了一种新的程序流行度估计方案，这是基于半马尔可夫过程模型。在此基础上，提出了一种贪婪程序协同缓存机制，有效地降低了延迟和能耗。其次，针对群组拥塞问题，提出了一种基于改进的协作Q学习的动态任务迁移方案，该方案能有效地减少延迟，缓解拥塞。第三，为了最小化组内资源分配的延迟和能量消耗，我们将其表示为具有大量变量的优化问题，然后利用一种新的基于ADMM的方案来解决该问题，该方案可以通过一组新的辅助变量来降低问题的复杂性，这些子问题都是凸问题，可以使用原始-对偶方法来解决，这保证了它的收敛性。最后，利用李雅普诺夫理论证明了其收敛性.数值结果表明，CL-ADMM框架在减少MEC的延迟和能量消耗的有效性。
We consider the problem of the intelligent and efficient resource management framework in mobile-edge computing (MEC), which can reduce delay and energy consumption, and features distributed optimization and efficient congestion avoidance. In this article, we present a cooperative learning framework for resource management in MEC from an alternating direction method of multipliers (ADMMs) perspective, named the CL-ADMM framework. First, computing a task requires both the user personal data and corresponding program that processes it, to efficiently cache program in a group, a novel program popularity estimation scheme is proposed, which is based on a semi-Markov process model. Then, a greedy program cooperative caching mechanism is established, which can effectively reduce delay and energy consumption. Second, to address group congestion, a dynamic task migration scheme based on improved cooperative $Q$ -learning is proposed, which can effectively reduce delay and alleviate congestion. Third, to minimize delay and energy consumption for resource allocation in a group, we formulate it as an optimization problem with a large number of variables, and then exploit a novel ADMM-based scheme to solve this problem, which can reduce the complexity of the problem with a new set of auxiliary variables, these subproblems are all convex problems that can be solved by using a primal-dual approach, which guarantees its convergence. Finally, we prove its convergence by using the Lyapunov theory. The numerical results demonstrate the effectiveness of the CL-ADMM framework in reducing delay and energy consumption in MEC.
登录
查看更多内容
影响因子：
10.4
作者：
Zijie Zheng;Lingyang Song;Zhu Han;Geoffrey Ye Li;H. V. Poor
通讯作者：
Zijie Zheng;Lingyang Song;Zhu Han;Geoffrey Ye Li;H. V. Poor
影响因子：
7.9
作者：
Lin Wang;Lei Jiao;Jun Li;Julien Gedeon;M. Mühlhäuser
通讯作者：
Lin Wang;Lei Jiao;Jun Li;Julien Gedeon;M. Mühlhäuser
DOI：
10.1109/itc30.2018.00017
发表时间：
2018-09
期刊：
2018 30th International Teletraffic Congress (ITC 30)
影响因子：
--
作者：
Peiyue Zhao;G. Dán
通讯作者：
Peiyue Zhao;G. Dán
DOI：
10.1109/jsac.2019.2894306
发表时间：
2019-03-01
影响因子：
16.4
作者：
Alameddine, Hyame Assem;Sharafeddine, Sanaa;Assi, Chadi
通讯作者：
Assi, Chadi
影响因子：
8.3
作者：
Andrews, Jeffrey G.;Baccelli, Francois;Ganti, Radha Krishna
通讯作者：
Ganti, Radha Krishna