A reinforcement learning based algorithm towards energy efficient 5G multi-tier network

Nahina Islam; Ammar Alazab; Mamoun Alazab

doi:10.1109/CCC.2019.000-2

A reinforcement learning based algorithm towards energy efficient 5G multi-tier network

Nahina Islam, Ammar Alazab, Mamoun Alazab

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper published in Proceedings › peer-review

8 Citations (Scopus)

Abstract

Energy efficiency is a key factor in the next generation wireless communication systems. Sleep mode implementation in multi-tier 5G networks has proven to be a very good approach for improving the energy efficiency. In this paper, we propose a novel reinforcement learning based decision making algorithm to implement sleep mode in the base stations (BSs) used in multi-tier 5G networks. We propose a Markovian Decision process (MDP) based algorithm to switch between three different power consumption modes of a BS for improving the energy efficiency of the 5G network. The MDP based approach intelligently switches between the states of the BS based on the offered traffic whilst maintaining a prescribed minimum channel rate per user. Our results show that there is a significant gain in the energy efficiency when using our proposed MDP algorithm together with the three-state BSs. We have also shown the energy-delay tradeoff in order to design a delay aware network.

Original language	English
Title of host publication	Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019
Editors	Cristina Ceballos
Place of Publication	Piscataway, NJ
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	96-101
Number of pages	6
ISBN (Electronic)	9781728126005
DOIs	https://doi.org/10.1109/CCC.2019.000-2
Publication status	Published - 1 May 2019
Event	2019 Cybersecurity and Cyberforensics Conference, CCC 2019 - Melbourne, Australia Duration: 7 May 2019 → 8 May 2019

Publication series

Name	Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019

Conference

Conference	2019 Cybersecurity and Cyberforensics Conference, CCC 2019
Country/Territory	Australia
City	Melbourne
Period	7/05/19 → 8/05/19

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/CCC.2019.000-2

Cite this

Islam, N., Alazab, A., & Alazab, M. (2019). A reinforcement learning based algorithm towards energy efficient 5G multi-tier network. In C. Ceballos (Ed.), Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019 (pp. 96-101). Article 8854559 (Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CCC.2019.000-2

Islam, Nahina ; Alazab, Ammar ; Alazab, Mamoun. / A reinforcement learning based algorithm towards energy efficient 5G multi-tier network. Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019. editor / Cristina Ceballos. Piscataway, NJ : IEEE, Institute of Electrical and Electronics Engineers, 2019. pp. 96-101 (Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019).

@inproceedings{8c969ea1c9364f93abfcabed733f52e0,

title = "A reinforcement learning based algorithm towards energy efficient 5G multi-tier network",

abstract = "Energy efficiency is a key factor in the next generation wireless communication systems. Sleep mode implementation in multi-tier 5G networks has proven to be a very good approach for improving the energy efficiency. In this paper, we propose a novel reinforcement learning based decision making algorithm to implement sleep mode in the base stations (BSs) used in multi-tier 5G networks. We propose a Markovian Decision process (MDP) based algorithm to switch between three different power consumption modes of a BS for improving the energy efficiency of the 5G network. The MDP based approach intelligently switches between the states of the BS based on the offered traffic whilst maintaining a prescribed minimum channel rate per user. Our results show that there is a significant gain in the energy efficiency when using our proposed MDP algorithm together with the three-state BSs. We have also shown the energy-delay tradeoff in order to design a delay aware network.",

keywords = "Energy Efficient 5G networks, Green communication, Markov decision process, Reinforcement based learning, Sleep mode",

author = "Nahina Islam and Ammar Alazab and Mamoun Alazab",

year = "2019",

month = may,

day = "1",

doi = "10.1109/CCC.2019.000-2",

language = "English",

series = "Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

pages = "96--101",

editor = "Cristina Ceballos",

booktitle = "Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019",

address = "United States",

note = "2019 Cybersecurity and Cyberforensics Conference, CCC 2019 ; Conference date: 07-05-2019 Through 08-05-2019",

}

Islam, N, Alazab, A & Alazab, M 2019, A reinforcement learning based algorithm towards energy efficient 5G multi-tier network. in C Ceballos (ed.), Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019., 8854559, Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019, IEEE, Institute of Electrical and Electronics Engineers, Piscataway, NJ, pp. 96-101, 2019 Cybersecurity and Cyberforensics Conference, CCC 2019, Melbourne, Australia, 7/05/19. https://doi.org/10.1109/CCC.2019.000-2

A reinforcement learning based algorithm towards energy efficient 5G multi-tier network. / Islam, Nahina; Alazab, Ammar; Alazab, Mamoun.
Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019. ed. / Cristina Ceballos. Piscataway, NJ: IEEE, Institute of Electrical and Electronics Engineers, 2019. p. 96-101 8854559 (Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper published in Proceedings › peer-review

TY - GEN

T1 - A reinforcement learning based algorithm towards energy efficient 5G multi-tier network

AU - Islam, Nahina

AU - Alazab, Ammar

AU - Alazab, Mamoun

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Energy efficiency is a key factor in the next generation wireless communication systems. Sleep mode implementation in multi-tier 5G networks has proven to be a very good approach for improving the energy efficiency. In this paper, we propose a novel reinforcement learning based decision making algorithm to implement sleep mode in the base stations (BSs) used in multi-tier 5G networks. We propose a Markovian Decision process (MDP) based algorithm to switch between three different power consumption modes of a BS for improving the energy efficiency of the 5G network. The MDP based approach intelligently switches between the states of the BS based on the offered traffic whilst maintaining a prescribed minimum channel rate per user. Our results show that there is a significant gain in the energy efficiency when using our proposed MDP algorithm together with the three-state BSs. We have also shown the energy-delay tradeoff in order to design a delay aware network.

AB - Energy efficiency is a key factor in the next generation wireless communication systems. Sleep mode implementation in multi-tier 5G networks has proven to be a very good approach for improving the energy efficiency. In this paper, we propose a novel reinforcement learning based decision making algorithm to implement sleep mode in the base stations (BSs) used in multi-tier 5G networks. We propose a Markovian Decision process (MDP) based algorithm to switch between three different power consumption modes of a BS for improving the energy efficiency of the 5G network. The MDP based approach intelligently switches between the states of the BS based on the offered traffic whilst maintaining a prescribed minimum channel rate per user. Our results show that there is a significant gain in the energy efficiency when using our proposed MDP algorithm together with the three-state BSs. We have also shown the energy-delay tradeoff in order to design a delay aware network.

KW - Energy Efficient 5G networks

KW - Green communication

KW - Markov decision process

KW - Reinforcement based learning

KW - Sleep mode

UR - http://www.scopus.com/inward/record.url?scp=85073873969&partnerID=8YFLogxK

U2 - 10.1109/CCC.2019.000-2

DO - 10.1109/CCC.2019.000-2

M3 - Conference Paper published in Proceedings

T3 - Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019

SP - 96

EP - 101

BT - Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019

A2 - Ceballos, Cristina

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway, NJ

T2 - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019

Y2 - 7 May 2019 through 8 May 2019

ER -

Islam N, Alazab A, Alazab M. A reinforcement learning based algorithm towards energy efficient 5G multi-tier network. In Ceballos C, editor, Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019. Piscataway, NJ: IEEE, Institute of Electrical and Electronics Engineers. 2019. p. 96-101. 8854559. (Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019). doi: 10.1109/CCC.2019.000-2

A reinforcement learning based algorithm towards energy efficient 5G multi-tier network

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this