Presentation | 2022-08-26 Multi-Agent Deep Q-Learning based Inter-Cell Interference Coordination for Cellular Systems Liu Yuchen, Chang Yuyuan, Fukawa Kazuhiko, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In small cell systems, inter-cell interference (ICI) can severely degrade the overall system capacity. To alleviate ICI, this report applies multi-agent reinforcement learning (MARL) to three-sector small cell systems, which aims to jointly optimize transmit power levels and beamforming vectors of base stations (BSs). Each BS, which plays a role of the agent in the reinforcement learning, exchanges its partial channel information and control results with neighboring BSs as the local information for the training and control. Then, the agent is expected to exploit the local information on the same environment for estimating control parameters, which can be extended and applied to large scale systems including more BSs. Computer simulations are conducted in order to verify the effectiveness of the proposed scheme. It is shown that the proposed scheme can improve average system capacity of 3-link and 21-link MIMO communications more drastically than the random control, while requiring much less computational complexity than that of the local exhaust search (ES). |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | MIMO / inter-cell interference coordination / multi-agent reinforcement learning / transmit beamforming / transmit power control |
Paper # | RCS2022-119 |
Date of Issue | 2022-08-18 (RCS) |
Conference Information | |
Committee | SAT / RCS |
---|---|
Conference Date | 2022/8/25(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Tetsushi Ikegami(Meiji Univ.) / Kenichi Higuchi(Tokyo Univ. of Science) |
Vice Chair | Masashi Kamei(NHK) / Takana Kaho(Shonan Inst. of Tech.) / Tomoya Tandai(Toshiba) / Fumihide Kojima(NICT) / Osamu Muta(Kyushu Univ.) |
Secretary | Masashi Kamei(NTT) / Takana Kaho(NICT) / Tomoya Tandai(Panasonic) / Fumihide Kojima(Univ. of Electro-Comm) / Osamu Muta(Sharp) |
Assistant | Riichiro Nagareda(KDDI Research) / Yuuki Koizumi(NHK) / Manabu Sakai(Mitsubishi Electric) / Masashi Iwabuchi(NTT) / Issei Kanno(KDDI Research) / Yuyuan Chang(Tokyo Inst. of Tech) |
Paper Information | |
Registration To | Technical Committee on Satellite Telecommunications / Technical Committee on Radio Communication Systems |
---|---|
Language | ENG-JTITLE |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Multi-Agent Deep Q-Learning based Inter-Cell Interference Coordination for Cellular Systems |
Sub Title (in English) | |
Keyword(1) | MIMO |
Keyword(2) | inter-cell interference coordination |
Keyword(3) | multi-agent reinforcement learning |
Keyword(4) | transmit beamforming |
Keyword(5) | transmit power control |
1st Author's Name | Liu Yuchen |
1st Author's Affiliation | Tokyo Institute of Technology(Tokyo Tech) |
2nd Author's Name | Chang Yuyuan |
2nd Author's Affiliation | Tokyo Institute of Technology(Tokyo Tech) |
3rd Author's Name | Fukawa Kazuhiko |
3rd Author's Affiliation | Tokyo Institute of Technology(Tokyo Tech) |
Date | 2022-08-26 |
Paper # | RCS2022-119 |
Volume (vol) | vol.122 |
Number (no) | RCS-164 |
Page | pp.pp.126-131(RCS), |
#Pages | 6 |
Date of Issue | 2022-08-18 (RCS) |