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 proceedingConference Paper published in ProceedingsResearchpeer-review

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 languageEnglish
Title of host publicationProceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages96-101
Number of pages6
ISBN (Electronic)9781728126005
DOIs
Publication statusPublished - 1 May 2019
Event2019 Cybersecurity and Cyberforensics Conference, CCC 2019 - Melbourne, Australia
Duration: 7 May 20198 May 2019

Publication series

NameProceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019

Conference

Conference2019 Cybersecurity and Cyberforensics Conference, CCC 2019
CountryAustralia
CityMelbourne
Period7/05/198/05/19

Fingerprint

Reinforcement learning
reinforcement
Base stations
Energy efficiency
energy
efficiency
learning
sleep
Switches
Communication systems
Electric power utilization
communication system
Decision making
traffic
decision making
Sleep

Cite this

Islam, N., Alazab, A., & Alazab, M. (2019). A reinforcement learning based algorithm towards energy efficient 5G multi-tier network. In Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019 (pp. 96-101). [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. 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 = "5",
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",
booktitle = "Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019",
address = "United States",

}

Islam, N, Alazab, A & Alazab, M 2019, A reinforcement learning based algorithm towards energy efficient 5G multi-tier network. in Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019., 8854559, Proceedings - 2019 Cybersecurity and Cyberforensics Conference, CCC 2019, IEEE, Institute of Electrical and Electronics Engineers, 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. 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 proceedingConference Paper published in ProceedingsResearchpeer-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

PB - IEEE, Institute of Electrical and Electronics Engineers

ER -

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