Green transmit power assignment for cognitive radio networks by applying multi-agent Q-learning approach

Xianfu Chen; Zhifeng Zhao; Honggang Zhang

Green transmit power assignment for cognitive radio networks by applying multi-agent Q-learning approach

Xianfu Chen^*, Zhifeng Zhao, Honggang Zhang

^*Corresponding author for this work

Not published at VTT

Zhejiang University

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

11 Citations (Scopus)

Abstract

As the scarce spectrum resource is becoming overcrowded, cognitive wireless mesh networks (CogMesh) indicate great flexibility to improve the spectrum utilization by opportunistically accessing the authorized frequency bands. In this paper, we consider non-cooperative green power assignment in CogMesh with the consideration of energy efficiency. The problem is modeled as a stochastic learning process. We extend the single-agent Q-learning to a multi-user context, and propose a conjecture based multi-agent Q-learning scheme to obtain the optimal strategies with private and incomplete information. A learning secondary user performs Q-function updates based on the conjecture about other secondary users' behaviors. Simulations are used to verify the performance of our algorithm and demonstrate its effectiveness of improving the energy efficiency.

Original language	English
Title of host publication	European Microwave Week 2010, EuMW2010
Subtitle of host publication	Connecting the World, Conference Proceedings - European Wireless Technology Conference, EuWiT 2010
Publisher	IEEE Institute of Electrical and Electronic Engineers
Pages	113-116
ISBN (Electronic)	978-2-87487-018-7
ISBN (Print)	978-1-4244-7233-8
Publication status	Published - 15 Dec 2010
MoE publication type	A4 Article in a conference publication
Event	13th European Microwave Week 2010, EuMW2010: Connecting the World - 3rd European Wireless Technology Conference - Paris, France Duration: 27 Sept 2010 → 28 Sept 2010

Conference

Conference	13th European Microwave Week 2010, EuMW2010
Country/Territory	France
City	Paris
Period	27/09/10 → 28/09/10

UN SDGs

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

Access to Document

https://ieeexplore.ieee.org/document/5615246

Cite this

Chen, X., Zhao, Z., & Zhang, H. (2010). Green transmit power assignment for cognitive radio networks by applying multi-agent Q-learning approach. In European Microwave Week 2010, EuMW2010: Connecting the World, Conference Proceedings - European Wireless Technology Conference, EuWiT 2010 (pp. 113-116). Article 5615246 IEEE Institute of Electrical and Electronic Engineers. https://ieeexplore.ieee.org/document/5615246

@inproceedings{6c287eaf26e04a3f9e0a478bcf0c2666,

title = "Green transmit power assignment for cognitive radio networks by applying multi-agent Q-learning approach",

abstract = "As the scarce spectrum resource is becoming overcrowded, cognitive wireless mesh networks (CogMesh) indicate great flexibility to improve the spectrum utilization by opportunistically accessing the authorized frequency bands. In this paper, we consider non-cooperative green power assignment in CogMesh with the consideration of energy efficiency. The problem is modeled as a stochastic learning process. We extend the single-agent Q-learning to a multi-user context, and propose a conjecture based multi-agent Q-learning scheme to obtain the optimal strategies with private and incomplete information. A learning secondary user performs Q-function updates based on the conjecture about other secondary users' behaviors. Simulations are used to verify the performance of our algorithm and demonstrate its effectiveness of improving the energy efficiency.",

author = "Xianfu Chen and Zhifeng Zhao and Honggang Zhang",

year = "2010",

month = dec,

day = "15",

language = "English",

isbn = "978-1-4244-7233-8",

pages = "113--116",

booktitle = "European Microwave Week 2010, EuMW2010",

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

address = "United States",

note = "13th European Microwave Week 2010, EuMW2010 : Connecting the World - 3rd European Wireless Technology Conference ; Conference date: 27-09-2010 Through 28-09-2010",

}

Chen, X, Zhao, Z & Zhang, H 2010, Green transmit power assignment for cognitive radio networks by applying multi-agent Q-learning approach. in European Microwave Week 2010, EuMW2010: Connecting the World, Conference Proceedings - European Wireless Technology Conference, EuWiT 2010., 5615246, IEEE Institute of Electrical and Electronic Engineers, pp. 113-116, 13th European Microwave Week 2010, EuMW2010, Paris, France, 27/09/10. <https://ieeexplore.ieee.org/document/5615246>

Green transmit power assignment for cognitive radio networks by applying multi-agent Q-learning approach. / Chen, Xianfu; Zhao, Zhifeng; Zhang, Honggang.
European Microwave Week 2010, EuMW2010: Connecting the World, Conference Proceedings - European Wireless Technology Conference, EuWiT 2010. IEEE Institute of Electrical and Electronic Engineers, 2010. p. 113-116 5615246.

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

TY - GEN

T1 - Green transmit power assignment for cognitive radio networks by applying multi-agent Q-learning approach

AU - Chen, Xianfu

AU - Zhao, Zhifeng

AU - Zhang, Honggang

PY - 2010/12/15

Y1 - 2010/12/15

N2 - As the scarce spectrum resource is becoming overcrowded, cognitive wireless mesh networks (CogMesh) indicate great flexibility to improve the spectrum utilization by opportunistically accessing the authorized frequency bands. In this paper, we consider non-cooperative green power assignment in CogMesh with the consideration of energy efficiency. The problem is modeled as a stochastic learning process. We extend the single-agent Q-learning to a multi-user context, and propose a conjecture based multi-agent Q-learning scheme to obtain the optimal strategies with private and incomplete information. A learning secondary user performs Q-function updates based on the conjecture about other secondary users' behaviors. Simulations are used to verify the performance of our algorithm and demonstrate its effectiveness of improving the energy efficiency.

AB - As the scarce spectrum resource is becoming overcrowded, cognitive wireless mesh networks (CogMesh) indicate great flexibility to improve the spectrum utilization by opportunistically accessing the authorized frequency bands. In this paper, we consider non-cooperative green power assignment in CogMesh with the consideration of energy efficiency. The problem is modeled as a stochastic learning process. We extend the single-agent Q-learning to a multi-user context, and propose a conjecture based multi-agent Q-learning scheme to obtain the optimal strategies with private and incomplete information. A learning secondary user performs Q-function updates based on the conjecture about other secondary users' behaviors. Simulations are used to verify the performance of our algorithm and demonstrate its effectiveness of improving the energy efficiency.

UR - http://www.scopus.com/inward/record.url?scp=78649950325&partnerID=8YFLogxK

M3 - Conference article in proceedings

AN - SCOPUS:78649950325

SN - 978-1-4244-7233-8

SP - 113

EP - 116

BT - European Microwave Week 2010, EuMW2010

PB - IEEE Institute of Electrical and Electronic Engineers

T2 - 13th European Microwave Week 2010, EuMW2010

Y2 - 27 September 2010 through 28 September 2010

ER -

Green transmit power assignment for cognitive radio networks by applying multi-agent Q-learning approach

Abstract

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this