| Presentation | 2020-05-22 Learning and Analysis of Damping Factor in Massive MIMO Detection using BP Algorithm with Node Selection Junta Tachibana, Tomoaki Ohtsuki, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In a massive MIMO system, belief propagation (BP) detection is known as a method to separate and detect received signals.In BP detection, the transmitted symbols are estimated by message passing.However, the convergence property of BP deteriorates due to multiple loops included in the MIMO channel.As a method to improve the convergence property, the damped BP that averages two successive messages with a damping factor is known.To train the damping factors off-line for each antenna configuration, deep neural network-based damped BP (DNN-dBP) has been reported.The problem with DNN-dBP is that the detection performance deteriorates when there is a difference of the channel correlation between training and test, because the optimal damping factors vary with the channel correlation.As a method to mitigate the effects of the channel correlation, the node selection (NS) method has been reported.In our previous research, we derived the damping factors with the NS method using DNN-dBP.We showed that this method can improve the detection performance deterioration due to the mismatches of the channel correlations between training and test in DNN-dBP.In this report, we investigate the effect of reducing the computational complexity of the DNN-dBP with the NS method by improving the convergence property of BP, and the distribution of the trained damping factors.By computer simulation, it is shown that the DNN-dBP with the NS method can show the same BER performance with low computational complexity as the DNN-dBP without the NS method.We also investigate the distribution of the trained damping factors and evaluate the tendency of that. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Massive MIMO / BP detection / Neural network / 5G |
| Paper # | RCS2020-19 |
| Date of Issue | 2020-05-14 (RCS) |
| Conference Information | |
| Committee | IN / RCS |
|---|---|
| Conference Date | 2020/5/21(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Keio University |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Ad-Hoc/Sensor Networks/MANET, Mobile Networks, M2M/IoT Communications, Wi-Fi, IEEE802.15(ZigBee) and others |
| Chair | Takuji Kishida(NTT-AT) / Tomoaki Otsuki(Keio Univ.) |
| Vice Chair | Kenji Ishida(Hiroshima City Univ.) / Satoshi Suyama(NTT DoCoMo) / Fumiaki Maehara(Waseda Univ.) / Toshihiko Nishimura(Hokkaido Univ.) |
| Secretary | Kenji Ishida(NTT Communications) / Satoshi Suyama(NTT) / Fumiaki Maehara(Hiroshima City Univ.) / Toshihiko Nishimura(KDDI Research) |
| Assistant | / Kazushi Muraoka(NEC) / Shinsuke Ibi(Doshisha Univ.) / Koichi Adachi(Univ. of Electro-Comm.) / Osamu Nakamura(Sharp) / Manabu Sakai(Mitsubishi Electric) |
| Paper Information | |
| Registration To | Technical Committee on Information Networks / Technical Committee on Radio Communication Systems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Learning and Analysis of Damping Factor in Massive MIMO Detection using BP Algorithm with Node Selection |
| Sub Title (in English) | |
| Keyword(1) | Massive MIMO |
| Keyword(2) | BP detection |
| Keyword(3) | Neural network |
| Keyword(4) | 5G |
| 1st Author's Name | Junta Tachibana |
| 1st Author's Affiliation | Keio University(Keio Univ.) |
| 2nd Author's Name | Tomoaki Ohtsuki |
| 2nd Author's Affiliation | Keio University(Keio Univ.) |
| Date | 2020-05-22 |
| Paper # | RCS2020-19 |
| Volume (vol) | vol.120 |
| Number (no) | RCS-29 |
| Page | pp.pp.49-54(RCS), |
| #Pages | 6 |
| Date of Issue | 2020-05-14 (RCS) |