A Pricing Based Cost-Aware Dynamic Resource Management for Cooperative Cloudlets in Edge Computing

Mobile edge computing (MEC) attracts a growing interests as its benefits for computation intensive and delay sensitive tasks. As an essential component in MEC architecture, cloudlet handles the computing tasks of applications offloaded from mobile devices, and pushes contents close to the mobile users, in order to improve the quality of experience, as well as application deployment and delivery efficiency. Existing work mostly focuses on cloudlet placement and assumes that the capacities of cloudlets are given and fixed, while little work has been done on resource allocation and scheduling among the cloudlets. Aiming to minimize the operator''s cost while preserving user experience, we proposes a pricing based cost-aware dynamic resource management framework (DRMF) for cooperative cloudlets with a centralized controller. Specifically, to stimulate the cooperation between cloudlets and the controller, we formulate the interactions as a Stackelberg game to minimize the cloudlets cost and increase the utility of the cloudlet-based edge computing system by eventually determining the amount of physical resources assigned to each cloudlet during deployment phase and the amount of resources shared among cooperated cloudlets during operation phase. Additionally, two algorithms have been proposed targeting latency-sensitive scenario and computation-intensive scenario, respectively. Evaluations validate the existence of Subgame Perfect Equilibrium (SPE), and show that the dynamic resource management framework could save the cost compared to static allocation.

I. Introduction

With the rapid development of Internet of Things (IoT) and 5G technologies, emerging mobile applications, e.g., augmented reality, online games and live video, are experiencing an exploded increasing during recent years. However, due to the limitations of battery, storage capacity and computing power, mobile devices can hardly meet the requirement of mobile applications on latency, computation and reliability. To tackle with this issue, mobile cloud computing (MCC) are proposed that allows mobile devices to migrate local computing tasks partially or fully to clouds with rich resources [1], [2]. However, offloading tasks to clouds located in core networks brings additional network delay and consumes bandwidth resources, resulting in failing to meet the requirements of delay-sensitive and computation-intensive applications.