Performance Anomaly Detection Models of Virtual Machines for Network Function Virtualization Infrastructure with Machine Learning.
作者： Juan Qiu , Qingfeng Du , Yu He , YiQun Lin , Jiaye Zhu
DOI: 10.1007/978-3-030-01421-6_46
关键词:
摘要: Networking Function Virtualization (NFV) technology has become a new solution for running network applications. It proposes paradigm function management and brought much innovation space the technology. However, complexity of NFV Infrastructure (NFVI) impose hard-to-predict relationship between Virtualized Network (VNF) performance metrics (e.g., latency, throughput), underlying allocated resources load vCPU), overall system workload, thus evolving scenario calls adequate analysis methodologies, early detection anomalies plays significant role in providing high-quality services. In this paper, we have proposed novel method detecting infrastructure with machine learning methods. We present case study on open source NFV-oriented project, namely Clearwater, which is an IP Multimedia Subsystem (IMS) application. Several classical classifiers are applied compared empirically anomaly dataset built by ourselves. Considering risk over-fitting issue, experimental results show that neutral networks best model accuracy over 94%.
springer.com
sci-hub.se 参考文章(13)
R. Bonafiglia, I. Cerrato, F. Ciaccia, M. Nemirovsky, F. Risso, Assessing the Performance of Virtualization Technologies for NFV: A Preliminary Benchmarking 2015 Fourth European Workshop on Software Defined Networks. pp. 67- 72 ,(2015) , 10.1109/EWSDN.2015.63
Song Fu, Performance Metric Selection for Autonomic Anomaly Detection on Cloud Computing Systems global communications conference. pp. 1- 5 ,(2011) , 10.1109/GLOCOM.2011.6134532
Dapeng Liu, Youjian Zhao, Haowen Xu, Yongqian Sun, Dan Pei, Jiao Luo, Xiaowei Jing, Mei Feng, Opprentice: Towards Practical and Automatic Anomaly Detection Through Machine Learning internet measurement conference. pp. 211- 224 ,(2015) , 10.1145/2815675.2815679
Chengwei Wang, Vanish Talwar, Karsten Schwan, Parthasarathy Ranganathan, Online detection of utility cloud anomalies using metric distributions network operations and management symposium. pp. 96- 103 ,(2010) , 10.1109/NOMS.2010.5488443
Shashank Shanbhag, Yu Gu, Tilman Wolf, A Taxonomy and Comparative Evaluation of Algorithms for Parallel Anomaly Detection international conference on computer communications and networks. pp. 1- 8 ,(2010) , 10.1109/ICCCN.2010.5560167
Takehisa Yairi, Yoshinobu Kawahara, Ryohei Fujimaki, Yuichi Sato, Kazuo Machida, Telemetry-mining: a machine learning approach to anomaly detection and fault diagnosis for space systems ieee international conference on space mission challenges for information technology. pp. 466- 476 ,(2006) , 10.1109/SMC-IT.2006.79
Kun-Lun Li, Hou-Kuan Huang, Sheng-Feng Tian, Wei Xu, Improving one-class SVM for anomaly detection international conference on machine learning and cybernetics. ,vol. 5, pp. 3077- 3081 ,(2003) , 10.1109/ICMLC.2003.1260106
Michail-Alexandros Kourtis, George Xilouris, Georgios Gardikis, Ioannis Koutras, Statistical-based anomaly detection for NFV services 2016 IEEE Conference on Network Function Virtualization and Software Defined Networks (NFV-SDN). pp. 161- 166 ,(2016) , 10.1109/NFV-SDN.2016.7919492
Priyanka Naik, Dilip Kumar Shaw, Mythili Vutukuru, NFVPerf: Online performance monitoring and bottleneck detection for NFV 2016 IEEE Conference on Network Function Virtualization and Software Defined Networks (NFV-SDN). pp. 154- 160 ,(2016) , 10.1109/NFV-SDN.2016.7919491
Domenico Cotroneo, Luigi De Simone, Roberto Natella, NFV-Bench: A Dependability Benchmark for Network Function Virtualization Systems IEEE Transactions on Network and Service Management. ,vol. 14, pp. 934- 948 ,(2017) , 10.1109/TNSM.2017.2733042