Presentation 2022-03-04
A Study on Network Fault Recovery Framework with Reinforcement Learning
Tatsuji Miyamoto, Genichi Mori, Yusuke Suzuki, Tomohiro Otani, Junji Takemasa, Yuki Koizumi, Toru Hasegawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Network operator automates failure recovery operation with implementing programs for each service and failure case. However, 5G introduces additional complexity into network monitoring and management due to the network function being independent of the hardware. In fact, a vast amount of workflows for automated the failure recovery operation have to be created and maintained per type of service and failure case. To address the above problems, this paper proposes a reinforcement learning-based fault recovery framework by applying the reinforcement learning algorithm. We demonstrate the effectiveness of the proposed framework for network failure recovery operation with simulation results.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Network management / Failure recovery / Automation / Machine learning
Paper # ICM2021-54
Date of Issue 2022-02-24 (ICM)

Conference Information
Committee ICM
Conference Date 2022/3/3(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Kazuhiko Kinoshita(Tokushima Univ.)
Vice Chair Haruo Ooishi(NTT) / Eiji Takahashi(NEC)
Secretary Haruo Ooishi(Bosco) / Eiji Takahashi(Fujitsu)
Assistant Yoshifumi Kato(NTT)

Paper Information
Registration To Technical Committee on Information and Communication Management
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study on Network Fault Recovery Framework with Reinforcement Learning
Sub Title (in English)
Keyword(1) Network management
Keyword(2) Failure recovery
Keyword(3) Automation
Keyword(4) Machine learning
1st Author's Name Tatsuji Miyamoto
1st Author's Affiliation KDDI Research, Inc./Osaka University(KDDI Research, Inc./Osaka Univ.)
2nd Author's Name Genichi Mori
2nd Author's Affiliation KDDI Research, Inc.(KDDI Research, Inc.)
3rd Author's Name Yusuke Suzuki
3rd Author's Affiliation KDDI Corporation(KDDI)
4th Author's Name Tomohiro Otani
4th Author's Affiliation KDDI Research, Inc.(KDDI Research, Inc.)
5th Author's Name Junji Takemasa
5th Author's Affiliation Osaka University(Osaka Univ.)
6th Author's Name Yuki Koizumi
6th Author's Affiliation Osaka University(Osaka Univ.)
7th Author's Name Toru Hasegawa
7th Author's Affiliation Osaka University(Osaka Univ.)
Date 2022-03-04
Paper # ICM2021-54
Volume (vol) vol.121
Number (no) ICM-399
Page pp.pp.63-67(ICM),
#Pages 5
Date of Issue 2022-02-24 (ICM)