QoS Aware Slice Resource Management Using Deep Reinforcement Learning in IoT Networks

Kamran Zia; Alessandro Chiumento; Paul J.M. Havinga; Roberto Riggio; Yanqiu Huang

doi:10.1109/DCOSS-IoT58021.2023.00035

QoS Aware Slice Resource Management Using Deep Reinforcement Learning in IoT Networks

Kamran Zia
, Alessandro Chiumento
, Paul J.M. Havinga
, Roberto Riggio
, Yanqiu Huang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

4 Citations (Scopus)

197 Downloads (Pure)

Abstract

WiFi, a widely used technology in IoT, provides QoS through IEEE 802.11e EDCA Access Categories (AC) which have fixed configuration with strict priorities. This makes WiFi QoS unsuitable to the rising QoS diversity, changing wireless conditions and network dynamics. QoS slicing, where network resources are divided into chinks for diverse QoS requirements, is a potent technology that can provide more flexible, adaptable and highly configurable QoS in WiFi based IoT networks. However, resource management of QoS slices with diverse IoT applications, limited network capacity and varying channel conditions is a complex and challenging task. Traditional queuing theoretic and optimization models become intractable to solve such complex and dynamic problem. Therefore, we have developed a Deep Reinforcement Learning (DRL) based slice resource management scheme to meet IoT QoS requirements in a real world 5GEmpower controlled SDN network. Our proposed scheme outperforms Airtime Excess Round Robin (ATERR) scheme and no slicing-based scheme in terms of slice throughput (QoS) satisfaction. Moreover, our proposed scheme is tested in real world environment and can adapt to the changing slice requirements in an IoT network.

Original language	English
Title of host publication	QoS Aware Slice Resource Management Using Deep Reinforcement Learning in IoT Networks
Pages	150-154
Number of pages	5
ISBN (Electronic)	979-8-3503-4649-7
DOIs	https://doi.org/10.1109/DCOSS-IoT58021.2023.00035
Publication status	Published - 27 Sept 2023
Event	19th International Conference on Distributed Computing in Smart Systems and the Internet of Things, DCOSS-IoT 2023 - Paphos, Cyprus Duration: 19 Jun 2023 → 21 Jun 2023 Conference number: 19 https://dcoss.org/dcoss23/

Publication series

Name	2023 19th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT)
Publisher	IEEE
ISSN (Print)	2325-2936
ISSN (Electronic)	2325-2944

Conference

Conference	19th International Conference on Distributed Computing in Smart Systems and the Internet of Things, DCOSS-IoT 2023
Abbreviated title	DCOSS-IoT 2023
Country/Territory	Cyprus
City	Paphos
Period	19/06/23 → 21/06/23
Internet address	https://dcoss.org/dcoss23/

Keywords

Deep Learning
Wireless communication
Quality of service
Reinforcement learning
IoT Networks
Resource Management
2023 OA procedure

Access to Document

10.1109/DCOSS-IoT58021.2023.00035

QoS_Aware_Slice_Resource_Management_Using_Deep_Reinforcement_Learning_in_IoT_NetworksFinal published version, 1.03 MBLicence: Taverne

WIFI empowerment: Towards Flexible, Adaptable and Reliable QoS in IoT Networks
Zia, K., 6 May 2025, Enschede, The Netherlands: University of Twente. 168 p.
Research output: Thesis › PhD Thesis - Research UT, graduation UT

Open Access
File
112 Downloads (Pure)

Cite this

Zia, K., Chiumento, A., Havinga, P. J. M., Riggio, R., & Huang, Y. (2023). QoS Aware Slice Resource Management Using Deep Reinforcement Learning in IoT Networks. In QoS Aware Slice Resource Management Using Deep Reinforcement Learning in IoT Networks (pp. 150-154). ( 2023 19th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT)). https://doi.org/10.1109/DCOSS-IoT58021.2023.00035

Zia, Kamran ; Chiumento, Alessandro ; Havinga, Paul J.M. et al. / QoS Aware Slice Resource Management Using Deep Reinforcement Learning in IoT Networks. QoS Aware Slice Resource Management Using Deep Reinforcement Learning in IoT Networks. 2023. pp. 150-154 ( 2023 19th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT)).

@inproceedings{d5003507f15d4da39ccfd8962732681b,

title = "QoS Aware Slice Resource Management Using Deep Reinforcement Learning in IoT Networks",

abstract = "WiFi, a widely used technology in IoT, provides QoS through IEEE 802.11e EDCA Access Categories (AC) which have fixed configuration with strict priorities. This makes WiFi QoS unsuitable to the rising QoS diversity, changing wireless conditions and network dynamics. QoS slicing, where network resources are divided into chinks for diverse QoS requirements, is a potent technology that can provide more flexible, adaptable and highly configurable QoS in WiFi based IoT networks. However, resource management of QoS slices with diverse IoT applications, limited network capacity and varying channel conditions is a complex and challenging task. Traditional queuing theoretic and optimization models become intractable to solve such complex and dynamic problem. Therefore, we have developed a Deep Reinforcement Learning (DRL) based slice resource management scheme to meet IoT QoS requirements in a real world 5GEmpower controlled SDN network. Our proposed scheme outperforms Airtime Excess Round Robin (ATERR) scheme and no slicing-based scheme in terms of slice throughput (QoS) satisfaction. Moreover, our proposed scheme is tested in real world environment and can adapt to the changing slice requirements in an IoT network.",

keywords = "Deep Learning, Wireless communication, Quality of service, Reinforcement learning, IoT Networks, Resource Management, 2023 OA procedure",

author = "Kamran Zia and Alessandro Chiumento and Havinga, \{Paul J.M.\} and Roberto Riggio and Yanqiu Huang",

year = "2023",

month = sep,

day = "27",

doi = "10.1109/DCOSS-IoT58021.2023.00035",

language = "English",

isbn = "979-8-3503-4650-3",

series = " 2023 19th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT)",

publisher = "IEEE",

pages = "150--154",

booktitle = "QoS Aware Slice Resource Management Using Deep Reinforcement Learning in IoT Networks",

note = "19th International Conference on Distributed Computing in Smart Systems and the Internet of Things, DCOSS-IoT 2023, DCOSS-IoT 2023 ; Conference date: 19-06-2023 Through 21-06-2023",

url = "https://dcoss.org/dcoss23/",

}

Zia, K, Chiumento, A, Havinga, PJM, Riggio, R & Huang, Y 2023, QoS Aware Slice Resource Management Using Deep Reinforcement Learning in IoT Networks. in QoS Aware Slice Resource Management Using Deep Reinforcement Learning in IoT Networks. 2023 19th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT), pp. 150-154, 19th International Conference on Distributed Computing in Smart Systems and the Internet of Things, DCOSS-IoT 2023, Paphos, Cyprus, 19/06/23. https://doi.org/10.1109/DCOSS-IoT58021.2023.00035

QoS Aware Slice Resource Management Using Deep Reinforcement Learning in IoT Networks. / Zia, Kamran; Chiumento, Alessandro; Havinga, Paul J.M. et al.
QoS Aware Slice Resource Management Using Deep Reinforcement Learning in IoT Networks. 2023. p. 150-154 ( 2023 19th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT)).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - QoS Aware Slice Resource Management Using Deep Reinforcement Learning in IoT Networks

AU - Zia, Kamran

AU - Chiumento, Alessandro

AU - Havinga, Paul J.M.

AU - Riggio, Roberto

AU - Huang, Yanqiu

N1 - Conference code: 19

PY - 2023/9/27

Y1 - 2023/9/27

N2 - WiFi, a widely used technology in IoT, provides QoS through IEEE 802.11e EDCA Access Categories (AC) which have fixed configuration with strict priorities. This makes WiFi QoS unsuitable to the rising QoS diversity, changing wireless conditions and network dynamics. QoS slicing, where network resources are divided into chinks for diverse QoS requirements, is a potent technology that can provide more flexible, adaptable and highly configurable QoS in WiFi based IoT networks. However, resource management of QoS slices with diverse IoT applications, limited network capacity and varying channel conditions is a complex and challenging task. Traditional queuing theoretic and optimization models become intractable to solve such complex and dynamic problem. Therefore, we have developed a Deep Reinforcement Learning (DRL) based slice resource management scheme to meet IoT QoS requirements in a real world 5GEmpower controlled SDN network. Our proposed scheme outperforms Airtime Excess Round Robin (ATERR) scheme and no slicing-based scheme in terms of slice throughput (QoS) satisfaction. Moreover, our proposed scheme is tested in real world environment and can adapt to the changing slice requirements in an IoT network.

AB - WiFi, a widely used technology in IoT, provides QoS through IEEE 802.11e EDCA Access Categories (AC) which have fixed configuration with strict priorities. This makes WiFi QoS unsuitable to the rising QoS diversity, changing wireless conditions and network dynamics. QoS slicing, where network resources are divided into chinks for diverse QoS requirements, is a potent technology that can provide more flexible, adaptable and highly configurable QoS in WiFi based IoT networks. However, resource management of QoS slices with diverse IoT applications, limited network capacity and varying channel conditions is a complex and challenging task. Traditional queuing theoretic and optimization models become intractable to solve such complex and dynamic problem. Therefore, we have developed a Deep Reinforcement Learning (DRL) based slice resource management scheme to meet IoT QoS requirements in a real world 5GEmpower controlled SDN network. Our proposed scheme outperforms Airtime Excess Round Robin (ATERR) scheme and no slicing-based scheme in terms of slice throughput (QoS) satisfaction. Moreover, our proposed scheme is tested in real world environment and can adapt to the changing slice requirements in an IoT network.

KW - Deep Learning

KW - Wireless communication

KW - Quality of service

KW - Reinforcement learning

KW - IoT Networks

KW - Resource Management

KW - 2023 OA procedure

U2 - 10.1109/DCOSS-IoT58021.2023.00035

DO - 10.1109/DCOSS-IoT58021.2023.00035

M3 - Conference contribution

SN - 979-8-3503-4650-3

T3 - 2023 19th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT)

SP - 150

EP - 154

BT - QoS Aware Slice Resource Management Using Deep Reinforcement Learning in IoT Networks

T2 - 19th International Conference on Distributed Computing in Smart Systems and the Internet of Things, DCOSS-IoT 2023

Y2 - 19 June 2023 through 21 June 2023

ER -

Zia K, Chiumento A, Havinga PJM, Riggio R, Huang Y. QoS Aware Slice Resource Management Using Deep Reinforcement Learning in IoT Networks. In QoS Aware Slice Resource Management Using Deep Reinforcement Learning in IoT Networks. 2023. p. 150-154. ( 2023 19th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT)). doi: 10.1109/DCOSS-IoT58021.2023.00035

QoS Aware Slice Resource Management Using Deep Reinforcement Learning in IoT Networks

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Research output

WIFI empowerment: Towards Flexible, Adaptable and Reliable QoS in IoT Networks

Cite this