Efficient Computation Resource Management in Mobile Edge-Cloud Computing

作     者：Zhang, Yongmin Lan, Xiaolong Li, Yue Cai, Lin Pan, Jianping 

作者机构：Univ Victoria Dept Elect & Comp Engn Victoria BC V8W 3P6 Canada Southwest Jiaotong Univ Sch Informat Sci & Technol Chengdu 611756 Sichuan Peoples R China Univ Victoria Dept Comp Sci Victoria BC V8W 3P6 Canada 

出 版 物：《IEEE INTERNET OF THINGS JOURNAL》 (IEEE Internet Things J.)

年 卷 期：2019年第6卷第2期

页      面：3455-3466页

核心收录：

学科分类：0810[工学-信息与通信工程] 0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Natural Sciences and Engineering Research Council of Canada National Natural Science Foundation of China [61702450, 61629302] CSC (China Scholarship Council) Compute Canada 

主　　题：Cloud networks computation resources Internet of Things (IoT) mobile edge server profit maximization 

摘      要：We study the computation resource management problem in mobile edge-cloud computing networks. Mobile edge servers shall first satisfy the computation requirements of mobile users and Internet of Things (IoT) devices, and then wholesale redundant computation resources to the cloud networks to maximize their profit. Due to the coarse time granularity of wholesales, computation resource buyback may happen occasionally to deal with traffic bursts. Thus, the mobile edge servers need to make a tradeoff between the wholesale profit and the buyback cost. In this paper, the computation resource management problem is modeled as profit maximization. To solve this problem, we first analyze the relationship among the reserved computation resources, the computation tasks of mobile users and IoT devices, and the buyback cost. Then, we design an efficient wholesale scheme to determine the amount of the wholesaled computation resources, by which the total expected profit of the mobile edge server can be maximized. Given the reserved computation resources, we also propose a fast-convergent realtime buyback scheme for mobile edge servers to minimize the buyback cost. Finally, the simulation results show that our proposed efficient wholesale and buyback scheme can increase the total profit while guaranteeing the computation delay of all the computation tasks, especially when the computation workloads are time-varying.