Presentation | 2022-08-25 [Encouragement Talk] One the use of machine learning for satellite communication systems Manabu Takagi, Yasunori Noda, Masatake Hangai, Masaki Noda, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Digitization of satellite payloads is a big trend. One example is a satellite with a fully digitized onboard processor called the Software Defined Satellite. Machine learning is compatible with these digitized on-board processing, and by constructing the digital signal processing of satellite systems based on machine learning, it is possible to further improve flexibility. As examples of machine learning for satellite systems, we proposed two methods. First, the blind center frequency estimation method that does not require a pilot signal. Second, the signal multiplexing for navigation signals. It was confirmed that the blind center frequency estimation of machine learning has a performance of 90% or more regardless of the modulation method. It was confirmed that the machine learning based signal multiplexing is superior in both performance and flexibility to the POCET method. When the number of signal multiplex increases due to a change in the operation scenario of the satellite system, the POCET method has been found to cause up to about 85% signal degradation, while the proposed method causes up to 16% signal degradation. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Satellite Communications / Frequency Estimation / Navigation Signal / Signal Multiplexing / Machine Learning |
Paper # | SAT2022-35 |
Date of Issue | 2022-08-18 (SAT) |
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 | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Encouragement Talk] One the use of machine learning for satellite communication systems |
Sub Title (in English) | |
Keyword(1) | Satellite Communications |
Keyword(2) | Frequency Estimation |
Keyword(3) | Navigation Signal |
Keyword(4) | Signal Multiplexing |
Keyword(5) | Machine Learning |
1st Author's Name | Manabu Takagi |
1st Author's Affiliation | Mitsubishi Electric Corporation(Mitsubishi Electric Corp.) |
2nd Author's Name | Yasunori Noda |
2nd Author's Affiliation | Mitsubishi Electric Corporation(Mitsubishi Electric Corp.) |
3rd Author's Name | Masatake Hangai |
3rd Author's Affiliation | Mitsubishi Electric Corporation(Mitsubishi Electric Corp.) |
4th Author's Name | Masaki Noda |
4th Author's Affiliation | Mitsubishi Electric Corporation(Mitsubishi Electric Corp.) |
Date | 2022-08-25 |
Paper # | SAT2022-35 |
Volume (vol) | vol.122 |
Number (no) | SAT-163 |
Page | pp.pp.36-41(SAT), |
#Pages | 6 |
Date of Issue | 2022-08-18 (SAT) |