FEMOS

Fog-Enabled Multi-tier Operations Scheduling in Dynamic Wireless Networks

Shuang Zhao, Yang Yang, Ziyu Shao, Xiumei Yang, Hua Qian, Cheng-Xiang Wang

Research output: Contribution to journalArticle

Abstract

Fog computing has recently emerged as a promising technique in content delivery wireless networks to alleviate the heavy bursty traffic burdens on backhaul connections. In order to improve the overall system performance, in terms of network throughput, service delay and fairness, it is very crucial and challenging to jointly optimize node assignments at control tier and resource allocation at access tier under dynamic user requirements and wireless network conditions. To solve this problem, in this paper, a fog-enabled multi-tier network architecture is proposed to model a typical content delivery wireless network with heterogeneous node capabilities in computing, communication and storage. Further, based on Lyapunov optimization techniques, a new online low-complexity algorithm, namely “Fog-Enabled Multi-tier Operations Scheduling" (FEMOS), is developed to decompose the original complicated problem into two operations across different tiers. Rigorous performance analysis derives the tradeoff relationship between average network throughput and service delay, i.e., [O(1/V), O(V)] with a control parameter V, under FEMOS algorithm in dynamic wireless networks. For different network sizes and traffic loads, extensive simulation results show that FEMOS is a fair and efficient algorithm for all user terminals (UTs) and, more importantly, it can offer much better performance, in terms of network throughput, service delay, and queue backlog, than traditional node assignment and resource allocation algorithms.

Original languageEnglish
Pages (from-to)1169-1183
Number of pages15
JournalIEEE Internet of Things Journal
Volume5
Issue number2
Early online date21 Feb 2018
DOIs
Publication statusPublished - Apr 2018

Fingerprint

Fog
Wireless networks
Scheduling
Throughput
Resource allocation
Scheduling algorithms
Network architecture
Communication

Keywords

  • 5G
  • Delay.
  • Delays
  • Dynamic scheduling
  • Fans
  • Fog Computing
  • Internet of Things (IoT)
  • Network architecture
  • Quality of Experience (QoE)
  • Resource management
  • Throughput
  • Wireless networks

ASJC Scopus subject areas

  • Signal Processing
  • Information Systems
  • Hardware and Architecture
  • Computer Science Applications
  • Computer Networks and Communications

Cite this

Zhao, Shuang ; Yang, Yang ; Shao, Ziyu ; Yang, Xiumei ; Qian, Hua ; Wang, Cheng-Xiang. / FEMOS : Fog-Enabled Multi-tier Operations Scheduling in Dynamic Wireless Networks. In: IEEE Internet of Things Journal. 2018 ; Vol. 5, No. 2. pp. 1169-1183.
@article{171439ae0c334ecb957db1e0b812baad,
title = "FEMOS: Fog-Enabled Multi-tier Operations Scheduling in Dynamic Wireless Networks",
abstract = "Fog computing has recently emerged as a promising technique in content delivery wireless networks to alleviate the heavy bursty traffic burdens on backhaul connections. In order to improve the overall system performance, in terms of network throughput, service delay and fairness, it is very crucial and challenging to jointly optimize node assignments at control tier and resource allocation at access tier under dynamic user requirements and wireless network conditions. To solve this problem, in this paper, a fog-enabled multi-tier network architecture is proposed to model a typical content delivery wireless network with heterogeneous node capabilities in computing, communication and storage. Further, based on Lyapunov optimization techniques, a new online low-complexity algorithm, namely “Fog-Enabled Multi-tier Operations Scheduling{"} (FEMOS), is developed to decompose the original complicated problem into two operations across different tiers. Rigorous performance analysis derives the tradeoff relationship between average network throughput and service delay, i.e., [O(1/V), O(V)] with a control parameter V, under FEMOS algorithm in dynamic wireless networks. For different network sizes and traffic loads, extensive simulation results show that FEMOS is a fair and efficient algorithm for all user terminals (UTs) and, more importantly, it can offer much better performance, in terms of network throughput, service delay, and queue backlog, than traditional node assignment and resource allocation algorithms.",
keywords = "5G, Delay., Delays, Dynamic scheduling, Fans, Fog Computing, Internet of Things (IoT), Network architecture, Quality of Experience (QoE), Resource management, Throughput, Wireless networks",
author = "Shuang Zhao and Yang Yang and Ziyu Shao and Xiumei Yang and Hua Qian and Cheng-Xiang Wang",
year = "2018",
month = "4",
doi = "10.1109/JIOT.2018.2808280",
language = "English",
volume = "5",
pages = "1169--1183",
journal = "IEEE Internet of Things Journal",
issn = "2327-4662",
publisher = "IEEE",
number = "2",

}

FEMOS : Fog-Enabled Multi-tier Operations Scheduling in Dynamic Wireless Networks. / Zhao, Shuang; Yang, Yang; Shao, Ziyu; Yang, Xiumei; Qian, Hua; Wang, Cheng-Xiang.

In: IEEE Internet of Things Journal, Vol. 5, No. 2, 04.2018, p. 1169-1183.

Research output: Contribution to journalArticle

TY - JOUR

T1 - FEMOS

T2 - Fog-Enabled Multi-tier Operations Scheduling in Dynamic Wireless Networks

AU - Zhao, Shuang

AU - Yang, Yang

AU - Shao, Ziyu

AU - Yang, Xiumei

AU - Qian, Hua

AU - Wang, Cheng-Xiang

PY - 2018/4

Y1 - 2018/4

N2 - Fog computing has recently emerged as a promising technique in content delivery wireless networks to alleviate the heavy bursty traffic burdens on backhaul connections. In order to improve the overall system performance, in terms of network throughput, service delay and fairness, it is very crucial and challenging to jointly optimize node assignments at control tier and resource allocation at access tier under dynamic user requirements and wireless network conditions. To solve this problem, in this paper, a fog-enabled multi-tier network architecture is proposed to model a typical content delivery wireless network with heterogeneous node capabilities in computing, communication and storage. Further, based on Lyapunov optimization techniques, a new online low-complexity algorithm, namely “Fog-Enabled Multi-tier Operations Scheduling" (FEMOS), is developed to decompose the original complicated problem into two operations across different tiers. Rigorous performance analysis derives the tradeoff relationship between average network throughput and service delay, i.e., [O(1/V), O(V)] with a control parameter V, under FEMOS algorithm in dynamic wireless networks. For different network sizes and traffic loads, extensive simulation results show that FEMOS is a fair and efficient algorithm for all user terminals (UTs) and, more importantly, it can offer much better performance, in terms of network throughput, service delay, and queue backlog, than traditional node assignment and resource allocation algorithms.

AB - Fog computing has recently emerged as a promising technique in content delivery wireless networks to alleviate the heavy bursty traffic burdens on backhaul connections. In order to improve the overall system performance, in terms of network throughput, service delay and fairness, it is very crucial and challenging to jointly optimize node assignments at control tier and resource allocation at access tier under dynamic user requirements and wireless network conditions. To solve this problem, in this paper, a fog-enabled multi-tier network architecture is proposed to model a typical content delivery wireless network with heterogeneous node capabilities in computing, communication and storage. Further, based on Lyapunov optimization techniques, a new online low-complexity algorithm, namely “Fog-Enabled Multi-tier Operations Scheduling" (FEMOS), is developed to decompose the original complicated problem into two operations across different tiers. Rigorous performance analysis derives the tradeoff relationship between average network throughput and service delay, i.e., [O(1/V), O(V)] with a control parameter V, under FEMOS algorithm in dynamic wireless networks. For different network sizes and traffic loads, extensive simulation results show that FEMOS is a fair and efficient algorithm for all user terminals (UTs) and, more importantly, it can offer much better performance, in terms of network throughput, service delay, and queue backlog, than traditional node assignment and resource allocation algorithms.

KW - 5G

KW - Delay.

KW - Delays

KW - Dynamic scheduling

KW - Fans

KW - Fog Computing

KW - Internet of Things (IoT)

KW - Network architecture

KW - Quality of Experience (QoE)

KW - Resource management

KW - Throughput

KW - Wireless networks

UR - http://www.scopus.com/inward/record.url?scp=85042387843&partnerID=8YFLogxK

U2 - 10.1109/JIOT.2018.2808280

DO - 10.1109/JIOT.2018.2808280

M3 - Article

VL - 5

SP - 1169

EP - 1183

JO - IEEE Internet of Things Journal

JF - IEEE Internet of Things Journal

SN - 2327-4662

IS - 2

ER -