Presentation 2018-05-24
A Study of Proactive Beam Forming Control using Machine Learning for 5G Mobile Communication System
Takashi Seyama, Teppei Oyama, Takashi Dateki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In fifth generation mobile communication systems, beam forming have been studied in order to compensate increase of pathloss at higher frequency than 4G. In beam forming at high frequency, the received power will degrade when UE moves behind buildings or traffic signs or a human bodies. In this paper, we proposed a proactive beam forming control on the basis of prediction of received power change using machine learning techniques to mitigate blockage effect by static objects when UE moves. As a preliminary study, we study prediction of the received power degradation event by means of neural network whose inputs are time series data of beam index and received power fed back by UE. We train the prediction model using training data generated by computer simulations and evaluate the success rate, the miss detection rate and the false alarm rate.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) 5G / Beam forming / Proactive beam forming control / Machine Learning / Neural Network
Paper # SR2018-7
Date of Issue 2018-05-17 (SR)

Conference Information
Committee SR
Conference Date 2018/5/24(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Tokyo big sight
Topics (in Japanese) (See Japanese page)
Topics (in English) Technical Exhibition, Machine Learning, AI
Chair Kenta Umebayashi(Tokyo Univ. of Agric. and Tech.)
Vice Chair Masayuki Ariyoshi(NEC) / Suguru Kameda(Tohoku Univ.)
Secretary Masayuki Ariyoshi(NICT) / Suguru Kameda(ATR)
Assistant Mamiko Inamori(Tokai Univ.) / Hiroyuki Shiba(NTT) / Gia Khanh Tran(Tokyo Inst. of Tech.) / Syusuke Narieda(NIT, Akashi College)

Paper Information
Registration To Technical Committee on Smart Radio
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study of Proactive Beam Forming Control using Machine Learning for 5G Mobile Communication System
Sub Title (in English)
Keyword(1) 5G
Keyword(2) Beam forming
Keyword(3) Proactive beam forming control
Keyword(4) Machine Learning
Keyword(5) Neural Network
1st Author's Name Takashi Seyama
1st Author's Affiliation FUJITSU LABORATORIES LTD.(Fujitsu Lab.)
2nd Author's Name Teppei Oyama
2nd Author's Affiliation FUJITSU LABORATORIES LTD.(Fujitsu Lab.)
3rd Author's Name Takashi Dateki
3rd Author's Affiliation FUJITSU LABORATORIES LTD.(Fujitsu Lab.)
Date 2018-05-24
Paper # SR2018-7
Volume (vol) vol.118
Number (no) SR-57
Page pp.pp.43-48(SR),
#Pages 6
Date of Issue 2018-05-17 (SR)