Presentation 2021-12-17
[Invited Lecture] Energy-Efficient DQN-based User Association for Sub6GHz/mmWave Networks
Megumi Kaneko, Thi Ha Ly Dinh, Keisuke Wakao, Kenichi Kawamura, Takatsune Moriyama, Yasushi Takatori,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This work investigates the design of an energy-efficient Deep Q-Network (DQN) implemented at the user device, whose purpose is to optimize its association to multiple access points (AP) in a Beyond 5G (B5G) Sub-6GHz and mmWave integratednetwork. To better cope with dynamic mobile environments, we first propose an adaptive epsilon-greedy policy at each user DQN in order to maximize the long-term sum-rate while simultaneously satisfying the Quality of Service (QoS) constraints of different applications. We then provide the detailed analysis of the energy consumed by each user device, in particular the power for DQN processing and for data movement. The trade-off between network performance in terms of sum-rate and QoS outage probability, and energy consumption at the user side is evaluated. Numerical results not only show the effectiveness of the proposed method compared to baseline, but also reveal the tremendous energy costs required by the default user DQN, underlining the importance of such energy-efficiency aware protocol design.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Deep Reinforcement Learning / energy efficiency / User-to-multiple access points association / Deep Q-Network
Paper # NS2021-109,RCS2021-192
Date of Issue 2021-12-09 (NS, RCS)

Conference Information
Committee RCS / NS
Conference Date 2021/12/16(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Nara-ken Bunka Kaikan and Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Multi-hop/Relay/Cooperation, Disaster-resistant wireless network, Sensor/Mesh network, Ad-hoc network, D2D/M2M, Wireless network coding, Handover/AP switching/Connected cell control/Load balancing among base stations/Mobile network dynamic reconfiguration, QoS/QoE assurance, Wireless VoIP, IoT, Edge computing, etc.
Chair Eiji Okamoto(Nagoya Inst. of Tech.) / Akihiro Nakao(Univ. of Tokyo)
Vice Chair Toshihiko Nishimura(Hokkaido Univ.) / Tomoya Tandai(Toshiba) / Fumihide Kojima(NICT) / Tetsuya Oishi(NTT)
Secretary Toshihiko Nishimura(NEC) / Tomoya Tandai(Panasonic) / Fumihide Kojima(NTT) / Tetsuya Oishi(Chuo Univ.)
Assistant Koichi Adachi(Univ. of Electro-Comm.) / Osamu Nakamura(Sharp) / Manabu Sakai(Mitsubishi Electric) / Masashi Iwabuchi(NTT) / Tatsuki Okuyama(NTT DOCOMO) / Kotaro Mihara(NTT)

Paper Information
Registration To Technical Committee on Radio Communication Systems / Technical Committee on Network Systems
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Invited Lecture] Energy-Efficient DQN-based User Association for Sub6GHz/mmWave Networks
Sub Title (in English)
Keyword(1) Deep Reinforcement Learning
Keyword(2) energy efficiency
Keyword(3) User-to-multiple access points association
Keyword(4) Deep Q-Network
1st Author's Name Megumi Kaneko
1st Author's Affiliation National Institute of Informatics(NII)
2nd Author's Name Thi Ha Ly Dinh
2nd Author's Affiliation National Institute of Informatics(NII)
3rd Author's Name Keisuke Wakao
3rd Author's Affiliation NTT Corporation(NTT)
4th Author's Name Kenichi Kawamura
4th Author's Affiliation NTT Corporation(NTT)
5th Author's Name Takatsune Moriyama
5th Author's Affiliation NTT Corporation(NTT)
6th Author's Name Yasushi Takatori
6th Author's Affiliation NTT Corporation(NTT)
Date 2021-12-17
Paper # NS2021-109,RCS2021-192
Volume (vol) vol.121
Number (no) NS-301,RCS-302
Page pp.pp.65-65(NS), pp.88-88(RCS),
#Pages 1
Date of Issue 2021-12-09 (NS, RCS)