DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Park, Hyuncheol | - |
dc.contributor.advisor | 박현철 | - |
dc.contributor.author | Yang, Hyewon | - |
dc.date.accessioned | 2022-04-27T19:31:17Z | - |
dc.date.available | 2022-04-27T19:31:17Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=948720&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/295994 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2021.2,[iv, 40 p. :] | - |
dc.description.abstract | To support high data rate/large capacity in next-generation communication, beamforming techniques on a massive multiple-input multiple-output (MIMO) system are actively proposed. For designing beamformer, however, a downlink channel state information (CSI) is required. Estimation of the downlink CSI in the massive MIMO system is a challenging task due to an increase in overhead according to the channel size. Therefore, most studies assume a time division duplexing (TDD) system in which the uplink and downlink channels are the same. However, in realistic communication system, non-reciprocity of uplink and downlink channels occurs even in the TDD system due to the influence of hardware such as an radio frequency (RF) chain. Recently, deep learning (DL)-based channel estimation and beamforming techniques have been proposed, thanks to the advantage of being applicable regardless of the type of system and channel. However, the DL-based approach requires the large number of training data for performance above a certain level. In this paper, we aim to train the deep neural network (DNN) for designing the beamformer, and introduce deep transfer learning (DTL) using information from pre-trained DNN to reduce the number of required training data. When DTL-based training method is applied, it is possible to train the DNN to properly adapt to the surrounding channel environment with a small number of channel data. Also, through the simulation, the performance of the DTL-based beamforming in various conditions and systems is confirmed. And the factors affecting the performance of the DTL-based beamforming are analyzed. Furthermore, we propose `step-by-step' DTL as the extended DTL-based method that can flexibly respond to the uncertainties of realistic communication environment. The simulation results show that DTL-based DNN training method not only improves the performance by considering the non-reciprocity between uplink and downlink channels regardless of the system and channel type, but also significantly reduces the number of training data for adapting to realistic hardware influence of a specific base station (BS). | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Massive MIMO▼aBeamforming▼aDeep Learning▼aDeep Transfer Learning▼aPrecoder | - |
dc.subject | 다중 입출력 시스템▼a빔포밍▼a심층학습▼a심층 전이학습▼a프리코더 | - |
dc.title | Deep transfer learning-based adaptive beamforming for realistic communication systems | - |
dc.title.alternative | 실제 통신 시스템의 특성을 고려한 심층 전이학습 기반 적응형 빔포밍에 대한 연구 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 양혜원 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.