On Cost-Aware Heterogeneous Cloudlet Deployment for Mobile Edge Computing

On Cost-Aware Heterogeneous Cloudlet Deployment for Mobile Edge Computing

Hengzhou Ye, Fengyi Huang, Wei Hao
DOI: 10.4018/IJITWE.297968
Article PDF Download
Open access articles are freely available for download

Abstract

Edge computing undertakes downlink cloud services and uplink terminal computing tasks, data interaction latency and network transmission cost are thus significantly reduced. Although a lot of research has been conducted in mobile edge computing (MEC), which assumed that all homogeneous cloudlets are placed in WMAN and user mobility is also ignored, little attention is paid to how to place heterogeneous cloudlets in wireless metropolitan area network (WMAN) to minimize the deployment cost of cloudlets. Meanwhile, the method of selecting an optimal access point (AP) for deployment, modeling and heuristic algorithm (HA) needs to be improved. Therefore, this paper design a new heterogeneous cloudlet deployment model considering the quality of service (QoS) and mobility of users, and the Improved Heuristic Algorithm (IHA) is proposed to minimize cloudlet deployment cost. The extensive simulations demonstrate that IHA is more efficient than HA and the designed model is superior to the existing work.
Article Preview
Top

Introduction

Benefited from the rapid development of wireless network technology, smart mobile devices, mobile device software and hardware technologies, the growing number of users are peculiarly prone to run related services on mobile devices than on traditional computers. However, portable smart mobile devices are limited by enhanced computing resources, including computing ability, communication resources, storage and usability functions, including power, size, and weight. Meanwhile, it is difficult to provide computing resource demands for intensive and complex user tasks. Therefore, there is an increasing need for mobile users offloading tasks to the cloud, which has given birth to the new paradigm of Mobile Cloud Computing (MCC) (Gai et al., 2016; Pang et al., 2017; Shaukat et al., 2016). Although MCC can enable mobile devices to overcome resource shortages such as computing power, storage capacity, and energy, which remains some problems such as bandwidth constraints, unreliable links and latency when mobile devices access remote cloud services by using wireless signals or wireless networks. Therefore, MCC is not effective enough for delay-intensive applications such as high-quality video streaming, augmented reality (AR) and virtual reality (VR) (Tyng-Yeu & You-Jie, 2017).

In order to solve this problem, precursory researchers proposed the concept of mobile edge computing (MEC), which a key technology in the emerging fifth-generation network, which can host computing-intensive applications, and the network MEC is close to mobile users and provides context-aware services with the help of network information. MEC can support various applications that strictly require real-time response such as driverless vehicles, AR, VR, robotics, and immersive media by bringing cloudlets closer to mobile users.(Rahimi et al., 2020; Luo et al; 2019). Satyanarayanan et al., (2009) are the first to state that cloudlet is a new element to extend the cloud architecture of mobile devices and can access networks through high-speed wireless links such as Wi-Fi, and cloudlet is also called “data center in a box” and cloudlet technology is a supplement and extension to MCC. Ahuja & Rolli (2012) proposed that cloudlet, which is typically deployed at wireless access points (APs), has computing resources, reliable transmission and data processing ability, can process user task requests and reduce latency of user access to services. Therefore, compared with MCC, MEC is closer to mobile users than MCC, mobile devices can offload their computing tasks to the cloudlet or edge cloud by accessing the wireless network, which greatly reduces the access delay for mobile devices to access the cloud service and improve the task processing capability of the mobile device.

Complete Article List

Search this Journal:
Reset
Volume 19: 1 Issue (2024)
Volume 18: 1 Issue (2023)
Volume 17: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 16: 4 Issues (2021)
Volume 15: 4 Issues (2020)
Volume 14: 4 Issues (2019)
Volume 13: 4 Issues (2018)
Volume 12: 4 Issues (2017)
Volume 11: 4 Issues (2016)
Volume 10: 4 Issues (2015)
Volume 9: 4 Issues (2014)
Volume 8: 4 Issues (2013)
Volume 7: 4 Issues (2012)
Volume 6: 4 Issues (2011)
Volume 5: 4 Issues (2010)
Volume 4: 4 Issues (2009)
Volume 3: 4 Issues (2008)
Volume 2: 4 Issues (2007)
Volume 1: 4 Issues (2006)
View Complete Journal Contents Listing