Presentation 2018-05-25
A Study on Resource Allocation Utilizing Q-Learning for Video Transmission in Multiple UAS Networks
Saki Tashiro, Yuichi Kawamoto, Hiroki Nishiyama, Nei Kato,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In recent years, the number of the use of unmanned aircrafts(UAs) has increased remarkably, and the world market size of UAs in 2020 is predicted to exceed 2 trillion yen. There are various services, for example, facility inspection, land surveillance, and package delivery, because of high mobility of UAs. Ensuring safety, improving work efficiency, reducing labor costs are realized by UAs. In some services, it is necessary to be able to watch a video taken by a UA in real-time. On the other hand, we can use the limited frequency bands. So, in this research, we consider a communication system that realizes high efficiency real-time video transmission in Multiple UAS Networks. We use LTE Direct, which is a technology of device-to-device communication for in this communication system. We propose an algorithm to realize efficient resource allocation. we consider time-slot allocation method using Q-learning as a proposed algorithm. By using Q-learning, it is possible to learn more efficient time-slot allocation method by repeating trial and error. In this reserch, we deal with video data. Even if such data size changes constantly, it is possible to utilize resouces effectively by learning appropriate communication resource allocation. Furthermore, we compare this proposed algorithm with other methods and evaluate its effectiveness.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) UAS / D2D / LTE Direct / Q-learning / Video Transmission
Paper # SAT2018-7
Date of Issue 2018-05-17 (SAT)

Conference Information
Committee SAT / WBS
Conference Date 2018/5/24(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Kagoshima University
Topics (in Japanese) (See Japanese page)
Topics (in English) Coding, Modulation, Signal processing and General
Chair Toshinori Susuki(Tohoku Gakuin Univ.) / Fumiaki Maehara(Waseda Univ.)
Vice Chair Hiroyuki Tsuji(NICT) / Fumihiro Yamashita(NTT) / Masanori Hamamura(Kochi Univ. of Tech.) / Fumie Ono(NICT)
Secretary Hiroyuki Tsuji(KDDI R&D Labs.) / Fumihiro Yamashita(NICT) / Masanori Hamamura(Mitsubishi Electric) / Fumie Ono(Ibaraki Univ.)
Assistant / Akira Nakamura(Tokyo Univ. of Science) / Ryohei Nakamura(National Defense Academy)

Paper Information
Registration To Technical Committee on Satellite Telecommunications / Technical Committee on Wideband System
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study on Resource Allocation Utilizing Q-Learning for Video Transmission in Multiple UAS Networks
Sub Title (in English)
Keyword(1) UAS
Keyword(2) D2D
Keyword(3) LTE Direct
Keyword(4) Q-learning
Keyword(5) Video Transmission
1st Author's Name Saki Tashiro
1st Author's Affiliation Tohoku University(Tohoku Univ.)
2nd Author's Name Yuichi Kawamoto
2nd Author's Affiliation Tohoku University(Tohoku Univ.)
3rd Author's Name Hiroki Nishiyama
3rd Author's Affiliation Tohoku University(Tohoku Univ.)
4th Author's Name Nei Kato
4th Author's Affiliation Tohoku University(Tohoku Univ.)
Date 2018-05-25
Paper # SAT2018-7
Volume (vol) vol.118
Number (no) SAT-52
Page pp.pp.31-36(SAT),
#Pages 6
Date of Issue 2018-05-17 (SAT)