Presentation | 2021-11-26 A Vectorization Method for Device Alarms with High Generalization Performance for AI Application to NW Operations Ryosuke Sato, Mizuto Nakamura, Seiji Sakuma, Atsushi Takada, Kyoko Yamagoe, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The automation of network operation(NWOP) has been progressing, Recently, AI using machine learning models such as neural networks has been developed to automate more advanced decisions in NWOPs. However, when we use the one-hot encoding for vectorization of the device alarm (ALM), which is commonly used data in many NWOP decisions for the input to the AI, the generalization performance tends to be low despite the huge amount of computation. In this paper, we propose a vectorization method that can reduce the computational complexity and improve the generalization performance byreflecting the relationship information on the NW topology between ALM data. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | network automation / machine learning |
Paper # | ICM2021-32 |
Date of Issue | 2021-11-18 (ICM) |
Conference Information | |
Committee | CQ / ICM / NS |
---|---|
Conference Date | 2021/11/25(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | JR Hakata Stn. Hakata EkiHigashi Rental Room |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Network quality, Network measurement/management, Network virtualization, Network service, Blockchain, Security, Network intelligence/AI, etc. |
Chair | Jun Okamoto(NTT) / Kazuhiko Kinoshita(Tokushima Univ.) / Akihiro Nakao(Univ. of Tokyo) |
Vice Chair | Takefumi Hiraguri(Nippon Inst. of Tech.) / Gou Hasegawa(Tohoku Univ.) / Haruo Ooishi(NTT) / Eiji Takahashi(NEC) / Tetsuya Oishi(NTT) |
Secretary | Takefumi Hiraguri(NTT) / Gou Hasegawa(Ritsumeikan Univ.) / Haruo Ooishi(Bosco) / Eiji Takahashi(Fujitsu) / Tetsuya Oishi(NTT) |
Assistant | Yoshiaki Nishikawa(NEC) / Ryoichi Kataoka(KDDI Research) / Kimiko Kawashima(NTT) / Yoshifumi Kato(NTT) / Kotaro Mihara(NTT) |
Paper Information | |
Registration To | Technical Committee on Communication Quality / Technical Committee on Information and Communication Management / Technical Committee on Network Systems |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A Vectorization Method for Device Alarms with High Generalization Performance for AI Application to NW Operations |
Sub Title (in English) | |
Keyword(1) | network automation |
Keyword(2) | machine learning |
1st Author's Name | Ryosuke Sato |
1st Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION(NTT) |
2nd Author's Name | Mizuto Nakamura |
2nd Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION(NTT) |
3rd Author's Name | Seiji Sakuma |
3rd Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION(NTT) |
4th Author's Name | Atsushi Takada |
4th Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION(NTT) |
5th Author's Name | Kyoko Yamagoe |
5th Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION(NTT) |
Date | 2021-11-26 |
Paper # | ICM2021-32 |
Volume (vol) | vol.121 |
Number (no) | ICM-264 |
Page | pp.pp.49-54(ICM), |
#Pages | 6 |
Date of Issue | 2021-11-18 (ICM) |