| Paper Abstract and Keywords |
| Presentation |
2019-11-26 14:10
[Poster Presentation]
A Recognition Method of Symptoms of Anomalies by Forecasting Time Series Data in Network Management
Kenta Masaki, Shingo Ata (Osaka City Univ.) |
| Abstract |
(in Japanese) |
(See Japanese page) |
| (in English) |
In recent years, there has been a lot of research on systems that detect anomalies in order to quicklyrecover from faults when some kind of anomalies occur in the network management operation. Most of these areable to detect anomalies only after a failure occurs and are unable to recover network services quickly because theyare bothered by dealing with the failure. There is a need for a system that can detect that a failure is likely tooccur in advance, rather than after a failure. If symptoms of a failure can be detected, the failure can be preventedand the failure can be dealt with quickly. In this paper, the time series data of the number of users in the networkis predicted by a recurrent neural network (RNN), and we detect the state just before the failure occurs, in otherwords the abnormal symptoms. RNN is a model that enables neural networks to learn even time-dependent data,and RNN learns and predicts network user transitions from past time-series data. By assuming this forecastingnumber as the transition of the number of normal users, we catch an unnatural transitions in the number of usersand judge the symptoms of abnormalities. |
| Keyword |
(in Japanese) |
(See Japanese page) |
| (in English) |
Network Management / Time Series Data / A Recognition Method of Symptoms of Anomalies / Recurrent Neural Network / Attention Model / / / |
| Reference Info. |
IEICE Tech. Rep. |
| Paper # |
|
| Date of Issue |
|
| ISSN |
|
| Download PDF |
|
| Conference Information |
| Committee |
RISING |
| Conference Date |
2019-11-26 - 2019-11-27 |
| Place (in Japanese) |
(See Japanese page) |
| Place (in English) |
Fukutake Learning Theater, Hongo Campus, Univ. Tokyo |
| Topics (in Japanese) |
(See Japanese page) |
| Topics (in English) |
Researches on Super-Intelligent Networking, etc. |
| Paper Information |
| Registration To |
RISING |
| Conference Code |
2019-11-RISING |
| Language |
Japanese |
| Title (in Japanese) |
(See Japanese page) |
| Sub Title (in Japanese) |
(See Japanese page) |
| Title (in English) |
A Recognition Method of Symptoms of Anomalies by Forecasting Time Series Data in Network Management |
| Sub Title (in English) |
|
| Keyword(1) |
Network Management |
| Keyword(2) |
Time Series Data |
| Keyword(3) |
A Recognition Method of Symptoms of Anomalies |
| Keyword(4) |
Recurrent Neural Network |
| Keyword(5) |
Attention Model |
| Keyword(6) |
|
| Keyword(7) |
|
| Keyword(8) |
|
| 1st Author's Name |
Kenta Masaki |
| 1st Author's Affiliation |
Osaka City University (Osaka City Univ.) |
| 2nd Author's Name |
Shingo Ata |
| 2nd Author's Affiliation |
Osaka City University (Osaka City Univ.) |
| 3rd Author's Name |
|
| 3rd Author's Affiliation |
() |
| 4th Author's Name |
|
| 4th Author's Affiliation |
() |
| 5th Author's Name |
|
| 5th Author's Affiliation |
() |
| 6th Author's Name |
|
| 6th Author's Affiliation |
() |
| 7th Author's Name |
|
| 7th Author's Affiliation |
() |
| 8th Author's Name |
|
| 8th Author's Affiliation |
() |
| 9th Author's Name |
|
| 9th Author's Affiliation |
() |
| 10th Author's Name |
|
| 10th Author's Affiliation |
() |
| 11th Author's Name |
|
| 11th Author's Affiliation |
() |
| 12th Author's Name |
|
| 12th Author's Affiliation |
() |
| 13th Author's Name |
|
| 13th Author's Affiliation |
() |
| 14th Author's Name |
|
| 14th Author's Affiliation |
() |
| 15th Author's Name |
|
| 15th Author's Affiliation |
() |
| 16th Author's Name |
|
| 16th Author's Affiliation |
() |
| 17th Author's Name |
|
| 17th Author's Affiliation |
() |
| 18th Author's Name |
|
| 18th Author's Affiliation |
() |
| 19th Author's Name |
|
| 19th Author's Affiliation |
() |
| 20th Author's Name |
|
| 20th Author's Affiliation |
() |
| Speaker |
Author-1 |
| Date Time |
2019-11-26 14:10:00 |
| Presentation Time |
50 minutes |
| Registration for |
RISING |
| Paper # |
|
| Volume (vol) |
vol. |
| Number (no) |
|
| Page |
|
| #Pages |
|
| Date of Issue |
|