A Time Series Clustering Method for Network Big Data

• Published in: Proceedings - International Conference on Parallel and Distributed Systems pp. 1516 - 1521
• Main Authors: Zhu, Yujia, Min, Geyong, Wu, Yulei, Wang, Haozhe
• Format: Conference Proceeding
• Language: English
• Published: IEEE 17.12.2023
• Subjects: Clustering algorithms; Clustering methods; deep clustering; Distributed databases; Fault diagnosis; hidden representations; Machine learning; Machine learning algorithms; network big data; Time series analysis; Time series clustering
• ISSN: 2690-5965
• DOI: 10.1109/ICPADS60453.2023.00214

In the era of big data, network data increase rapidly in a distributed manner, giving birth to the network big data. Network big data with the extra features such as distributed and decentralized data collection and storage, distributed and parallel data processing, more complex and evolving relationships among data, and heterogeneous data representation, pose opportunities together with challenges to the traditional network analysis algorithms. A hopeful solution is combining machine learning techniques with network big data analysis. In this paper, we proposed a novel time series clustering method which effectively combines machine learning techniques with network big data analysis for fault diagnosis task based on network logs. Verification experimental results on classic HDFS dataset demonstrate the outstanding performance of the proposed method.