에너지 특성 기반 통신 네트워크 신호 데이터의 이상진단Energy Feature-based Anomaly Detection for Network Traffic Signal Data
- Other Titles
- Energy Feature-based Anomaly Detection for Network Traffic Signal Data
- Authors
- 이재승; 임문원; 배석주
- Issue Date
- Dec-2023
- Publisher
- 한국신뢰성학회
- Keywords
- Change-point; Condition Monitoring; Fractional Brownian Motion; Hurst Exponent; Two-Sample t-Test
- Citation
- 신뢰성 응용연구, v.23, no.4, pp 325 - 334
- Pages
- 10
- Indexed
- KCI
- Journal Title
- 신뢰성 응용연구
- Volume
- 23
- Number
- 4
- Start Page
- 325
- End Page
- 334
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/194362
- DOI
- 10.33162/JAR.2023.12.23.4.325
- ISSN
- 1738-9895
2733-8320
- Abstract
- Purpose: With the rapid development of wireless communication, the occurrence of anomalies resulting from malicious network attacks and system overload is also increasing rapidly.
Consequently, detecting network traffic anomalies in a network system has become crucial for preventing server downtime. In this study, we proposed a method for detecting anomalies in network traffic data through signal processing and statistical tests.
Methods: Based on self-similar characteristics of network traffic data, we employed fractional Brownian motion to extract the Hurst exponent as the health index of network traffic data.
Additionally, we proposed the index-based change-point monitoring scheme to assess the network’s current status.
Results: Analysis of actual network traffic data shows that the method based on the Hurst exponent and change-point estimation can effectively detect anomalies early, prior to real traffic outbreak, preventing network traffic failures.
Conclusion: This research introduced a method for assessing abnormalities and detecting change-point in network overload based on the statistical property of long-range dependency, facilitating early detection of network issues.
- Files in This Item
-
- Appears in
Collections - 서울 공과대학 > 서울 산업공학과 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.