A Distributed Intelligent Hungarian Algorithm for Workload Balance in Sensor-Cloud Systems Based on Urban Fog Computing

Junbin Liang, Yuxuan Long, Yaxin Mei, Tian Wang, Qun Jin

Research output: Contribution to journalArticle

Abstract

With the help of fog computing, urban computing and intelligence novel systems can be created to improve the urban environment and the quality of human life. Sensor-cloud systems based on urban fog computing (SCS-UFC) are new intelligent network systems, which combine a cloud platform with wireless sensor networks (WSNs) as well as fog nodes to provide functions such as sensing, computation, and storage of large-scale data. Since the sensor nodes in WSNs only have limited transmission capacity, they cannot transmit their data to the cloud platform directly. Therefore, fog nodes with stronger transmission capacity are deployed to relay the data from WSNs to the cloud platform. However, different fog nodes may be burdened with different workloads (i.e., amounts of data): usually, the fog nodes with heavier workloads mean longer transmission delay and more energy consumption. If a fog node exhausts its energy, it will die and then make the network cease to work. Therefore, it is necessary to balance the workload of all fog nodes so as to reduce transmission delay and energy consumption of the sensors. However, addressing the problem is challenging because each fog node only knows local information of its neighbors, and thus it is difficult to get a global optimization result by itself. In this paper, a distributed intelligent algorithm based on the Hungarian method is proposed. First, each fog node collects the information connected with its neighboring fog nodes that are located within its transmission range. Then, a new genetic algorithm is designed to find an approximate optimization solution. Finally, each fog node decides if it should forward parts of its workload to other fog nodes so that the workloads of all fog nodes are balanced. Simulation results show that our algorithm can achieve shorter delay and less energy consumption than existing works.

Original languageEnglish
Article number8735711
Pages (from-to)77649-77658
Number of pages10
JournalIEEE Access
Volume7
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Fog
Sensors
Wireless sensor networks
Energy utilization
Intelligent networks
Global optimization
Sensor nodes
Genetic algorithms

Keywords

  • Fog computing
  • sensor-cloud system
  • wireless sensor networks
  • workload balance

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

A Distributed Intelligent Hungarian Algorithm for Workload Balance in Sensor-Cloud Systems Based on Urban Fog Computing. / Liang, Junbin; Long, Yuxuan; Mei, Yaxin; Wang, Tian; Jin, Qun.

In: IEEE Access, Vol. 7, 8735711, 01.01.2019, p. 77649-77658.

Research output: Contribution to journalArticle

Liang, Junbin ; Long, Yuxuan ; Mei, Yaxin ; Wang, Tian ; Jin, Qun. / A Distributed Intelligent Hungarian Algorithm for Workload Balance in Sensor-Cloud Systems Based on Urban Fog Computing. In: IEEE Access. 2019 ; Vol. 7. pp. 77649-77658.
@article{71668e0c787b49f28923b9293af0d9c3,
title = "A Distributed Intelligent Hungarian Algorithm for Workload Balance in Sensor-Cloud Systems Based on Urban Fog Computing",
abstract = "With the help of fog computing, urban computing and intelligence novel systems can be created to improve the urban environment and the quality of human life. Sensor-cloud systems based on urban fog computing (SCS-UFC) are new intelligent network systems, which combine a cloud platform with wireless sensor networks (WSNs) as well as fog nodes to provide functions such as sensing, computation, and storage of large-scale data. Since the sensor nodes in WSNs only have limited transmission capacity, they cannot transmit their data to the cloud platform directly. Therefore, fog nodes with stronger transmission capacity are deployed to relay the data from WSNs to the cloud platform. However, different fog nodes may be burdened with different workloads (i.e., amounts of data): usually, the fog nodes with heavier workloads mean longer transmission delay and more energy consumption. If a fog node exhausts its energy, it will die and then make the network cease to work. Therefore, it is necessary to balance the workload of all fog nodes so as to reduce transmission delay and energy consumption of the sensors. However, addressing the problem is challenging because each fog node only knows local information of its neighbors, and thus it is difficult to get a global optimization result by itself. In this paper, a distributed intelligent algorithm based on the Hungarian method is proposed. First, each fog node collects the information connected with its neighboring fog nodes that are located within its transmission range. Then, a new genetic algorithm is designed to find an approximate optimization solution. Finally, each fog node decides if it should forward parts of its workload to other fog nodes so that the workloads of all fog nodes are balanced. Simulation results show that our algorithm can achieve shorter delay and less energy consumption than existing works.",
keywords = "Fog computing, sensor-cloud system, wireless sensor networks, workload balance",
author = "Junbin Liang and Yuxuan Long and Yaxin Mei and Tian Wang and Qun Jin",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/ACCESS.2019.2922322",
language = "English",
volume = "7",
pages = "77649--77658",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - A Distributed Intelligent Hungarian Algorithm for Workload Balance in Sensor-Cloud Systems Based on Urban Fog Computing

AU - Liang, Junbin

AU - Long, Yuxuan

AU - Mei, Yaxin

AU - Wang, Tian

AU - Jin, Qun

PY - 2019/1/1

Y1 - 2019/1/1

N2 - With the help of fog computing, urban computing and intelligence novel systems can be created to improve the urban environment and the quality of human life. Sensor-cloud systems based on urban fog computing (SCS-UFC) are new intelligent network systems, which combine a cloud platform with wireless sensor networks (WSNs) as well as fog nodes to provide functions such as sensing, computation, and storage of large-scale data. Since the sensor nodes in WSNs only have limited transmission capacity, they cannot transmit their data to the cloud platform directly. Therefore, fog nodes with stronger transmission capacity are deployed to relay the data from WSNs to the cloud platform. However, different fog nodes may be burdened with different workloads (i.e., amounts of data): usually, the fog nodes with heavier workloads mean longer transmission delay and more energy consumption. If a fog node exhausts its energy, it will die and then make the network cease to work. Therefore, it is necessary to balance the workload of all fog nodes so as to reduce transmission delay and energy consumption of the sensors. However, addressing the problem is challenging because each fog node only knows local information of its neighbors, and thus it is difficult to get a global optimization result by itself. In this paper, a distributed intelligent algorithm based on the Hungarian method is proposed. First, each fog node collects the information connected with its neighboring fog nodes that are located within its transmission range. Then, a new genetic algorithm is designed to find an approximate optimization solution. Finally, each fog node decides if it should forward parts of its workload to other fog nodes so that the workloads of all fog nodes are balanced. Simulation results show that our algorithm can achieve shorter delay and less energy consumption than existing works.

AB - With the help of fog computing, urban computing and intelligence novel systems can be created to improve the urban environment and the quality of human life. Sensor-cloud systems based on urban fog computing (SCS-UFC) are new intelligent network systems, which combine a cloud platform with wireless sensor networks (WSNs) as well as fog nodes to provide functions such as sensing, computation, and storage of large-scale data. Since the sensor nodes in WSNs only have limited transmission capacity, they cannot transmit their data to the cloud platform directly. Therefore, fog nodes with stronger transmission capacity are deployed to relay the data from WSNs to the cloud platform. However, different fog nodes may be burdened with different workloads (i.e., amounts of data): usually, the fog nodes with heavier workloads mean longer transmission delay and more energy consumption. If a fog node exhausts its energy, it will die and then make the network cease to work. Therefore, it is necessary to balance the workload of all fog nodes so as to reduce transmission delay and energy consumption of the sensors. However, addressing the problem is challenging because each fog node only knows local information of its neighbors, and thus it is difficult to get a global optimization result by itself. In this paper, a distributed intelligent algorithm based on the Hungarian method is proposed. First, each fog node collects the information connected with its neighboring fog nodes that are located within its transmission range. Then, a new genetic algorithm is designed to find an approximate optimization solution. Finally, each fog node decides if it should forward parts of its workload to other fog nodes so that the workloads of all fog nodes are balanced. Simulation results show that our algorithm can achieve shorter delay and less energy consumption than existing works.

KW - Fog computing

KW - sensor-cloud system

KW - wireless sensor networks

KW - workload balance

UR - http://www.scopus.com/inward/record.url?scp=85068205769&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068205769&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2019.2922322

DO - 10.1109/ACCESS.2019.2922322

M3 - Article

AN - SCOPUS:85068205769

VL - 7

SP - 77649

EP - 77658

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8735711

ER -