Energy saving through a learning framework in greener cellular radio access networks

R. Li; Z. Zhao; Xianfu Chen; H. Zhang

doi:10.1109/GLOCOM.2012.6503335

Energy saving through a learning framework in greener cellular radio access networks

R. Li, Z. Zhao, Xianfu Chen, H. Zhang

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

9 Citations (Scopus)

Abstract

Recent works have validated the possibility of energy efﬁciency improvement in radio access networks (RAN), depending on dynamically turn on/off some base stations (BSs). In this paper, we extend the research over BS switching operation, matching up with trafﬁc load variations. However, instead of depending on the predicted trafﬁc loads, which is still quite challenging to precisely forecast, we formulate the trafﬁc variation as a Markov decision process (MDP). Afterwards, in order to foresightedly minimize the energy consumption of RAN, we adopt the actor-critic method and design a reinforcement learning framework based BS switching operation scheme. In the end, we evaluate our proposed scheme by extensive simulations under various practical conﬁgurations and prove the feasibility of signiﬁcant energy efﬁciency improvement.

Original language	English
Title of host publication	Proceedings of Globecom 2012
Publisher	IEEE Institute of Electrical and Electronic Engineers
Pages	1556-1561
ISBN (Electronic)	978-1-4673-0921-9
ISBN (Print)	978-1-4673-0920-2
DOIs	https://doi.org/10.1109/GLOCOM.2012.6503335
Publication status	Published - 2012
MoE publication type	A4 Article in a conference publication
Event	IEEE Global Communications Conference, GLOBECOM 2012 - Anaheim, CA, United States Duration: 3 Dec 2012 → 7 Dec 2012

Conference

Conference	IEEE Global Communications Conference, GLOBECOM 2012
Abbreviated title	GLOBECOM 2012
Country	United States
City	Anaheim, CA
Period	3/12/12 → 7/12/12

Access to Document

10.1109/GLOCOM.2012.6503335

Fingerprint Dive into the research topics of 'Energy saving through a learning framework in greener cellular radio access networks'. Together they form a unique fingerprint.

Cite this

@inproceedings{02e98b948b2a44d985add6c8adbfb89d,

title = "Energy saving through a learning framework in greener cellular radio access networks",

abstract = "Recent works have validated the possibility of energy efﬁciency improvement in radio access networks (RAN), depending on dynamically turn on/off some base stations (BSs). In this paper, we extend the research over BS switching operation, matching up with trafﬁc load variations. However, instead of depending on the predicted trafﬁc loads, which is still quite challenging to precisely forecast, we formulate the trafﬁc variation as a Markov decision process (MDP). Afterwards, in order to foresightedly minimize the energy consumption of RAN, we adopt the actor-critic method and design a reinforcement learning framework based BS switching operation scheme. In the end, we evaluate our proposed scheme by extensive simulations under various practical conﬁgurations and prove the feasibility of signiﬁcant energy efﬁciency improvement.",

author = "R. Li and Z. Zhao and Xianfu Chen and H. Zhang",

note = "Project code: 43135; IEEE Global Communications Conference, GLOBECOM 2012, GLOBECOM 2012 ; Conference date: 03-12-2012 Through 07-12-2012",

year = "2012",

doi = "10.1109/GLOCOM.2012.6503335",

language = "English",

isbn = "978-1-4673-0920-2",

pages = "1556--1561",

booktitle = "Proceedings of Globecom 2012",

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

address = "United States",

}

TY - GEN

T1 - Energy saving through a learning framework in greener cellular radio access networks

AU - Li, R.

AU - Zhao, Z.

AU - Chen, Xianfu

AU - Zhang, H.

N1 - Project code: 43135

PY - 2012

Y1 - 2012

N2 - Recent works have validated the possibility of energy efﬁciency improvement in radio access networks (RAN), depending on dynamically turn on/off some base stations (BSs). In this paper, we extend the research over BS switching operation, matching up with trafﬁc load variations. However, instead of depending on the predicted trafﬁc loads, which is still quite challenging to precisely forecast, we formulate the trafﬁc variation as a Markov decision process (MDP). Afterwards, in order to foresightedly minimize the energy consumption of RAN, we adopt the actor-critic method and design a reinforcement learning framework based BS switching operation scheme. In the end, we evaluate our proposed scheme by extensive simulations under various practical conﬁgurations and prove the feasibility of signiﬁcant energy efﬁciency improvement.

AB - Recent works have validated the possibility of energy efﬁciency improvement in radio access networks (RAN), depending on dynamically turn on/off some base stations (BSs). In this paper, we extend the research over BS switching operation, matching up with trafﬁc load variations. However, instead of depending on the predicted trafﬁc loads, which is still quite challenging to precisely forecast, we formulate the trafﬁc variation as a Markov decision process (MDP). Afterwards, in order to foresightedly minimize the energy consumption of RAN, we adopt the actor-critic method and design a reinforcement learning framework based BS switching operation scheme. In the end, we evaluate our proposed scheme by extensive simulations under various practical conﬁgurations and prove the feasibility of signiﬁcant energy efﬁciency improvement.

U2 - 10.1109/GLOCOM.2012.6503335

DO - 10.1109/GLOCOM.2012.6503335

M3 - Conference article in proceedings

SN - 978-1-4673-0920-2

SP - 1556

EP - 1561

BT - Proceedings of Globecom 2012

PB - IEEE Institute of Electrical and Electronic Engineers

T2 - IEEE Global Communications Conference, GLOBECOM 2012

Y2 - 3 December 2012 through 7 December 2012

ER -