基于GCN-LSTM的云计算服务异常检测算法
Cloud Computing Service Anomaly Detection Algorithm Based on GCN-LSTM
DOI: 10.12677/CSA.2022.123077, PDF,   
作者: 石 林, 郭炜彬：广东工业大学计算机学院，广东 广州；吴卓儒：广东工业大学自动化学院，广东 广州
关键词: 云计算服务；异常检测；GCN；LSTM；时间序列；Copula；Cloud Computing Service； Anomaly Detection； GCN； LSTM； Copula
摘要: 随着云计算服务架构日渐庞大，运维人员需要对大量性能指标数据进行检测以确保云计算各系统和业务的可靠和稳定。为提高服务器异常检测准确率，本文提出了一种基于GCN和LSTM的云计算服务异常检测算法。首先，通过建立图模型描述云计算服务器的空间特征和属性，并通过GCN模型提取其空间信息；然后将不同时刻的空间信息构成时间序列输入到LSTM模型从中提取时间信息，使用训练好的GCN-LSTM模型对时间序列进行重建；最后使用基于Copula函数的方法对重构误差进行异常检测。本文使用了来自大数据批处理系统的MBD数据进行实验，实验结果表明我们提出的模型具有有效性。
Abstract: With the increasing scale of cloud computing service architecture, the operating personnel need to detect a large amount of performance data to ensure the reliability and stability of cloud computing systems and businesses. In order to improve the detection accuracy of the servers, this paper proposes a cloud computing service anomaly detection algorithm based on GCN-LSTM. This algorithm first describes the spatial features and attribute of cloud computing server by constructing a graph model, extracts its spatial information by GCN; then inputs the spatial information at different times into LSTM to extract time information, and uses the trained GCN-LSTM model to reconstruct the time series; the method based on Copula function is used to detect the anomaly of reconstruction error finally. In this paper, MBD data from big data batch processing system is used for experiments. The experimental results show that the model we proposed is effective.
文章引用：石林, 郭炜彬, 吴卓儒. 基于GCN-LSTM的云计算服务异常检测算法[J]. 计算机科学与应用, 2022, 12(3): 755-767. https://doi.org/10.12677/CSA.2022.123077

参考文献

[1] González, S., Sedano J., Herrero, Á., Baruque, B. and Corchado, E. (2011) Testing Ensembles for Intrusion Detection: On the Identification of Mutated Network Scans. In: Herrero, Á. and Corchado, E., Eds., Computational Intelligence in Security for Information System, Springer, Berlin, Heidelberg, 109-117. [Google Scholar] [CrossRef] 
[2] Atkinson, A.C. (2018) Review: Identification of Outliers. by D. M. Hawkins. Biometrics, 37, 860-861. [Google Scholar] [CrossRef] 
[3] Cohen, W.W. (1995) Fast Effective Rule Induction. Proceedings of the 12th International Conference on Machine Learning, Tahoe City, 9-12 July 1995, 115-123. [Google Scholar] [CrossRef] 
[4] Quinlan, J. (2014) RC4.5: Programs for Machine Learning. Morgan Kaufmann, Cambridge.
[5] Barnett, V., Lewis, T. and Abeles, F. (1994) Outliers in Statistical Data. 3rd Edition, Wiley, Chichester.
[6] Ramaswamy, S., Rastogi, R. and Shim, K. (2000) Efficient Algorithms for Mining Outliers from Large Data Sets. ACM SIGMOD Record, 29, 427-438. [Google Scholar] [CrossRef] 
[7] Breunig, M.M., Kriegel, H.P., Ng, R.T. and Sander, J. (1999) Op-tics-of: Identifying Local Outliers. Proceedings of European Conference on Principles of Data Mining and Knowledge Discovery, Prague, 15-18 September 1999, 262-270. [Google Scholar] [CrossRef] 
[8] Li, Z., Zhao, Y., Botta, N., Ionescu, C. and Hu, X. (2020) COPOD: Copula-Based Outlier Detection. 2020 IEEE International Conference on Data Mining, Sorrento, 17-20 November 2020, 1118-1123. [Google Scholar] [CrossRef] 
[9] Li, Z., Zhao, Y., Hu, X., Botta, N., Ionescu, C. and Chen, G.H. (2022) ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functions. IEEE Trans-actions on Knowledge and Data Engineering. arXiv preprint arXiv:2201.00382. [Google Scholar] [CrossRef] 
[10] Fei, T.L., Kai, M.T. and Zhou, Z.H. (2008) Isolation Forest. 2008 IEEE International Conference on Data Mining, Pisa, 19 January 2009, 413-422.
[11] Pascal, V., Larochelle, H., Bengio, Y. and Manzagol, P.-A. (2008) Extracting and Composing Robust Features with Denoising Autoencoders. Pro-ceedings of the 25th International Conference on Machine Learning, Helsinki, 5-9 July 2008, 1096-1103. [Google Scholar] [CrossRef] 
[12] Wang, H., Zhou, C., Jia, W., Dang, W., Zhu, X. and Wang, J. (2018) Deep Structure Learning for Fraud Detection. 2018 IEEE International Conference on Data Mining (ICDM), Singapore, 17-20 November 2018, 567-576. [Google Scholar] [CrossRef] 
[13] Zhang, M., Li, T., Shi, H., Li, Y. and Hui, P. (2019) A Decompo-sition Approach for Urban Anomaly Detection across Spatiotemporal Data. 28th International Joint Conference on Arti-ficial Intelligence (IJCAI-19), Macao (China), 10-19 August 2019, 6043-6049. [Google Scholar] [CrossRef] 
[14] Zheng, P., Yuan, S., Wu, X., Li, J. and Lu, A. (2018) One-Class Ad-versarial Nets for Fraud Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 33, 1286-1293. [Google Scholar] [CrossRef] 
[15] Du, M., Li, F., Zheng, G. and Srikumar, V. (2017) DeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning. Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, Dallas, 30 October-3 November 2017, 1285-1298. [Google Scholar] [CrossRef] 
[16] Meng, W., Liu, Y., Zhu, Y., Zhang, S., Pei, D., Liu, Y., et al. (2020) LogAnomaly: Unsupervised Detection of Sequential and Quantitative Anomalies in Unstructured Logs. Proceed-ings of the 28th International Joint Conference on Artificial Intelligence, Macao (China), 10-16 August 2019, 4739-4745. [Google Scholar] [CrossRef] 
[17] Defferrard, M., Bresson, X. and Vandergheynst, P. (2016) Convolu-tional Neural Networks on Graphs with Fast Localized Spectral Filtering. arXiv:1606.09375.
[18] Henaff, M., Bruna, J. and Lecun, Y. (2015) Deep Convolutional Networks on Graph-Structured Data. arXiv:1506.05163.
[19] Kip, F.T.N. and Welling, M. (2016) Semi-Supervised Classification with Graph Convolutional Networks. arXiv:1609.02907.
[20] Sklar, A. (1996) Random Variables, Distribution Functions, and Copulas—A Personal Look Backward and Forward. Institute of Mathematical Statistics, Beachwood. [Google Scholar] [CrossRef] 
[21] Breunig, M.M., Kriegel, H.P., Ng, R.T. and Sander, J. (2000) LOF: Identifying Density-Based Local Outliers. Proceedings of the 2000 ACM SIGMOD international conference on Man-agement of Data, Dallas, 15-18 May 2000, 93-104. [Google Scholar] [CrossRef] 
[22] Tang, J., Chen, Z., Fu, A. and Cheung, D.W.-L. (2002) Enhancing Effectiveness of Outlier Detections for Low Density Patterns. Advances in Knowledge Discovery and Data Mining. Proceedings of the 6th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, Taipei, 6-8 May 2002, 535-548.