| Presentation | 2023-03-01 A Novel DNN-based CSI Feedback with Quantization for FDD Massive MIMO Systems Junjie Gao, Mondher Bouazizi, Tomoaki Ohtsuki, Gui Guan, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Accessing the accurate downlink channel state information(CSI) is essential to take full advantage of frequencydivision duplex (FDD) massive multiple-input multiple-output(MIMO) systems due to its weak channel reciprocity. Meanwhile, great computational burdens will happen, which is accompaniedby continuous CSI feedback. The existing compressive sensing(CS)-based and deep learning (DL)-based methods try to solvesuch problems, but do not achieve desired effect to get ideal CSIfeedback or decrease the overhead. An adaptive deep neuralnetwork (DNN)-based CSI feedback method is proposed in thispaper to address this. A classification block of the compressionratio is adopted and modified to apply to a more complexchannel model named Clustered-Delay-Line (CDL), which helpsdecrease the computational overhead of the network. Besides, thereconstruction accuracy of the CSI feedback is further improvedby proposing a new structure of the encoder. Quantization anddequantization modules are also applied to make the wholenetwork more robust and effectively minimize the quantizationdistortion in the real communication scenario, respectively. Thesimulation results show that the proposed method performs betterthan the conventional ones on the CSI reconstruction accuracyin terms of normalized mean square error (NMSE), even thoughthe quantization module is added. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | CSI feedbackdeep neural networkclassificationquantizationmassive MIMO |
| Paper # | RCS2022-252 |
| Date of Issue | 2023-02-22 (RCS) |
| Conference Information | |
| Committee | RCS / SR / SRW |
|---|---|
| Conference Date | 2023/3/1(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Tokyo Institute of Technology, and Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Mobile Communication Workshop |
| Chair | Kenichi Higuchi(Tokyo Univ. of Science) / Suguru Kameda(Hiroshima Univ.) / Hanako Noda(Anritsu) |
| Vice Chair | Tomoya Tandai(Toshiba) / Fumihide Kojima(NICT) / Osamu Muta(Kyushu Univ.) / Osamu Takyu(Shinshu Univ.) / Kentaro Ishidu(NICT) / Kazuto Yano(ATR) / Keiichi Mizutani(Kyoto Univ.) / Kentaro Saito(Tokyo Denki Univ.) / Hirokazu Sawada(NICT) |
| Secretary | Tomoya Tandai(Panasonic) / Fumihide Kojima(Univ. of Electro-Comm) / Osamu Muta(Sharp) / Osamu Takyu(Mie Univ.) / Kentaro Ishidu(Tokai Univ.) / Kazuto Yano(NTT) / Keiichi Mizutani(KUT) / Kentaro Saito(NIigata Univ.) / Hirokazu Sawada |
| Assistant | Manabu Sakai(Mitsubishi Electric) / Masashi Iwabuchi(NTT) / Issei Kanno(KDDI Research) / Yuyuan Chang(Tokyo Inst. of Tech) / Kazuki Maruta(Tokyo Univ. of Science) / Mai Ohta(NEC) / WANG Xiaoyan(Ibaraki Univ.) / Akemi Tanaka(MathWorks) / Katsuya Suto(Univ. of Electro-Comm) / Maki Arai(Nihon Univ.) / Yuichi Masuda(Univ. of Tokyo) |
| Paper Information | |
| Registration To | Technical Committee on Radio Communication Systems / Technical Committee on Smart Radio / Technical Committee on Short Range Wireless Communications |
|---|---|
| Language | ENG |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Novel DNN-based CSI Feedback with Quantization for FDD Massive MIMO Systems |
| Sub Title (in English) | |
| Keyword(1) | CSI feedbackdeep neural networkclassificationquantizationmassive MIMO |
| 1st Author's Name | Junjie Gao |
| 1st Author's Affiliation | Keio University(Keio Univ.) |
| 2nd Author's Name | Mondher Bouazizi |
| 2nd Author's Affiliation | Keio University(Keio Univ.) |
| 3rd Author's Name | Tomoaki Ohtsuki |
| 3rd Author's Affiliation | Keio University(Keio Univ.) |
| 4th Author's Name | Gui Guan |
| 4th Author's Affiliation | Nanjing University of Posts and Telecommunications(NJUPT) |
| Date | 2023-03-01 |
| Paper # | RCS2022-252 |
| Volume (vol) | vol.122 |
| Number (no) | RCS-399 |
| Page | pp.pp.31-35(RCS), |
| #Pages | 5 |
| Date of Issue | 2023-02-22 (RCS) |