Swarm learning anomaly detection framework for cloud data center using multi-channel BiWGAN-GTN and CEEMDAN^☆

Abstract

Anomaly detection is an important task for maintaining the performance of cloud data center. Traditional anomaly detection primarily examines individual Virtual Machine (VM) behavior, neglecting the impact of interactions among multiple VMs on Key Performance Indicator (KPI) data, e.g., memory utilization. Furthermore, the non-stationarity, high complexity, and uncertain periodicity of KPI data in VM also bring difficulties to deep learning-based anomaly detection tasks. To settle these challenges, this paper proposes MCBiWGAN-GTN, a multi-channel semi-supervised time series anomaly detection algorithm based on the Bidirectional Wasserstein Generative Adversarial Network with Graph-Time Network (BiWGAN-GTN) and the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN). (a) The BiWGAN-GTN algorithm is proposed to extract spatiotemporal information from data. (b) The loss function of BiWGAN-GTN is redesigned to solve the abnormal data intrusion problem during the training process. (c) MCBiWGAN-GTN is designed to reduce data complexity through CEEMDAN for time series decomposition and utilizes BiWGAN-GTN to train different components. (d) To adapt the proposed algorithm for the entire cloud data center, a cloud data center anomaly detection framework based on Swarm Learning (SL) is designed. The evaluation results on a real-world cloud data center dataset show that MCBiWGAN-GTN outperforms the baseline, with an F1-score of 0.96, an accuracy of 0.935, a precision of 0.954, a recall of 0.967, and an FPR of 0.203. The experiments also verify the stability of MCBiWGAN-GTN, the impact of parameter configurations, and the effectiveness of the proposed SL framework.

Keywords

Cloud data center / Anomaly detection / BiWGAN-GTN / Time series decomposition / Swarm learning

References

[1] Z. Zhu, R. Gu, C. Pan, Y. Li, B. Zhu, J. Li,Cpu and network traffic anomaly detection method for cloud data center, in:Proceedings of the 1st International Conference on Advanced Information Science and System, 2019, pp. 1-7.

[2] X. Zhou, X. Peng, T. Xie, J. Sun, C. Ji, W. Li, D. Ding, Fault analysis and debugging of microservice systems: industrial survey, benchmark system, and empirical study, IEEE Trans. Softw. Eng. 47 (2) (2018) 243-260.

[3] K.V. Vishwanath, N. Nagappan,Characterizing cloud computing hardware relia-bility, in:Proceedings of the 1st ACM Symposium on Cloud Computing, 2010, pp. 193-204.

[4] H. Liu, S. Lu, M. Musuvathi, S. Nath,What bugs cause production cloud inci-dents?, in:Proceedings of the Workshop on Hot Topics in Operating Systems, 2019, pp. 155-162.

[5] H. Zhang, J. Liu, T. Wu, Adaptive and incremental-clustering anomaly detection algorithm for vms under cloud platform runtime environment, IEEE Access 6 (2018) 76984-76992.

[6] H. Xu, W. Chen, N. Zhao, Z. Li, J. Bu, Z. Li, Y. Liu, Y. Zhao, D. Pei, Y. Feng, et al., Unsupervised anomaly detection via variational auto-encoder for seasonal kpis in web applications,in: Proceedings of the 2018 World Wide Web Conference, 2018, pp. 187-196.

[7] W. Chen, H. Xu, Z. Li, D. Pei, J. Chen, H. Qiao, Y. Feng, Z. Wang, Unsuper-vised anomaly detection for intricate kpis via adversarial training of vae, in: IEEE INFOCOM 2019-IEEE Conference on Computer Communications, IEEE, 2019, pp. 1891-1899.

[8] O. Vallis, J. Hochenbaum, A. Kejariwal, A novel technique for Long-Term anomaly detection in the cloud, in: 6th USENIX Workshop on Hot Topics in Cloud Computing, Philadelphia, PA, 2014, pp. 1-15.

[9] S. Meng, L. Liu, T. Wang, State monitoring in cloud datacenters, IEEE Trans. Knowl. Data Eng. 23 (9) (2011) 1328-1344.

[10] D. Smith, Q. Guan, S. Fu, An anomaly detection framework for autonomic manage-ment of compute cloud systems, in: 2010 IEEE 34th Annual Computer Software and Applications Conference Workshops, IEEE, 2010, pp. 376-381.

[11] D. Li, D. Chen, B. Jin, L. Shi, J. Goh, S.-K. Ng Mad-gan, Multivariate anomaly de-tection for time series data with generative adversarial networks, in: International Conference on Artificial Neural Networks, Springer, 2019, pp. 703-716.

[12] A. Deng, B. Hooi,Graph neural network-based anomaly detection in multivariate time series, in:Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, 2021, pp. 4027-4035.

[13] A. Chaudhary, H. Mittal, A. Arora, Anomaly detection using graph neural networks, in: 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon), IEEE, 2019, pp. 346-350.

[14] M. Hasan, J. Choi, J. Neumann, A.K. Roy-Chowdhury, L.S. Davis,Learning temporal regularity in video sequences, in:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 733-742.

[15] W. Luo, W. Liu, S. Gao, Remembering history with convolutional lstm for anomaly detection, in: 2017 IEEE International Conference on Multimedia and Expo (ICME), IEEE, 2017, pp. 439-444.

[16] J. Gao, X. Song, Q. Wen, P. Wang, L. Sun, H. Xu, Robusttad: robust time series anomaly detection via decomposition and convolutional neural networks, preprint, arXiv :2002.09545, 2020.

[17] T. Huang, P. Chen, R. Li,A semi-supervised vae based active anomaly detection framework in multivariate time series for online systems, in:Proceedings of the ACM Web Conference 2022, Virtual Event, Lyon, France, 2022, pp. 1797-1806.

[18] W. Wang, C. Liang, L. Tang, H. Yanikomeroglu, Q. Chen, Federated multi-discriminator biwgan-gp based collaborative anomaly detection for virtualized net-work slicing, IEEE Trans. Mob. Comput. 22 (11) (2023) 6445-6459.

[19] T.N. Kipf, M. Welling, Semi-supervised classification with graph convolutional net-works, preprint, arXiv :1609.02907, 2016.

[20] S. Bai, J.Z. Kolter, V. Koltun, An empirical evaluation of generic convolutional and recurrent networks for sequence modeling, preprint, arXiv :1803.01271, 2018.

[21] M.E. Torres, M.A. Colominas, G. Schlotthauer, P. Flandrin, A complete ensem-ble empirical mode decomposition with adaptive noise, in: 2011 IEEE Interna-tional Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2011, pp. 4144-4147.

[22] S. Warnat-Herresthal, H. Schultze, K.L. Shastry, S. Manamohan, S. Mukherjee, V. Garg, R. Sarveswara, K. Händler, P. Pickkers, N.A. Aziz, et al., Swarm learning for decentralized and confidential clinical machine learning, Nature 594 (7862) (2021) 265-270.

[23] R. Chalapathy, E.Z. Borzeshi, M. Piccardi, An investigation of recurrent neural ar-chitectures for drug name recognition, preprint, arXiv :1609.07585, 2016.

[24] H. Ren, B. Xu, Y. Wang, C. Yi, C. Huang, X. Kou, T. Xing, M. Yang, J. Tong, Q. Zhang,Time-series anomaly detection service at Microsoft, in:Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019, pp. 3009-3017.

[25] D. Liu, Y. Zhao, H. Xu, Y. Sun, D. Pei, J. Luo, X. Jing, M. Feng, Opprentice: towards practical and automatic anomaly detection through machine learning,in: Proceed-ings of the 2015 Internet Measurement Conference, 2015, pp. 211-224.

[26] V. Chandola, A. Banerjee, V. Kumar, Anomaly detection: a survey, ACM Comput. Surv. 41 (3) (2009) 1-58.

[27] B. Schölkopf, R.C. Williamson, A. Smola, J. Shawe-Taylor, J. Platt, Support vector method for novelty detection, in: Proceedings of the 13th International Conference on Neural Information Processing Systems, Denver, CO, 2018, pp. 582-588.

[28] M.M. Breunig, H.-P. Kriegel, R.T. Ng, J. Sander, Lof: identifying density-based lo-cal outliers,in: Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, 2000, pp. 93-104.

[29] N. Gugulothu, P. Malhotra, L. Vig, G. Shroff, Sparse neural networks for anomaly detection in high-dimensional time series, in: AI4IOT Workshop in Conjunction with ICML, IJCAI and ECAI, 2018, pp. 1551-3203.

[30] C. Zhang, T. Zhou, Q. Wen, L. Sun, Tfad: a decomposition time series anomaly detection architecture with time-frequency analysis,in:Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022, pp. 2497-2507.

[31] P. Malhotra, A. Ramakrishnan, G. Anand, L. Vig, P. Agarwal, G. Shroff, Lstm-based encoder-decoder for multi-sensor anomaly detection, preprint, arXiv :1607.00148, 2016.

[32] F. Scarselli, M. Gori, A.C. Tsoi, M. Hagenbuchner, G. Monfardini, The graph neural network model, IEEE Trans. Neural Netw. 20 (1) (2008) 61-80.

[33] H. Zhao, Y. Wang, J. Duan, C. Huang, D. Cao, Y. Tong, B. Xu, J. Bai, J. Tong, Q. Zhang, Multivariate time-series anomaly detection via graph attention network, in: 2020 IEEE International Conference on Data Mining (ICDM), IEEE, 2020, pp. 841-850.

[34] Z. Chen, D. Chen, X. Zhang, Z. Yuan, X. Cheng, Learning graph structures with trans-former for multivariate time-series anomaly detection in iot, IEEE Int. Things J. 9 (12) (2021) 9179-9189.

[35] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. Bengio, Generative adversarial nets, in: Proceedings of the 28th Interna-tional Conference on Neural Information Processing Systems -Volume 2, Montreal, Canada, 2014, pp. 2672-2680.

[36] T. Hu, Q. Guo, H. Sun, T.-E. Huang, J. Lan, Nontechnical losses detection through coordinated biwgan and svdd, IEEE Trans. Neural Netw. Learn. Syst. 32 (5) (2020) 1866-1880.

[37] Y. Lyu, Z. Han, J. Zhong, C. Li, Z. Liu, A generic anomaly detection of catenary support components based on generative adversarial networks, IEEE Trans. Instrum. Meas. 69 (5) (2019) 2439-2448.

[38] J. Donahue, P. Krähenbühl, T. Darrell, Adversarial feature learning, preprint, arXiv: 1605.09782, 2016.

[39] I. Haloui, J.S. Gupta, V. Feuillard, Anomaly detection with Wasserstein gan, preprint, arXiv :1812.02463, 2018.

[40] I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, A.C. Courville, Improved training of Wasserstein gans, in: Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, California, USA, 2017, pp. 5769-5779.

[41] T. Li, Z. Qian, T. He, Short-term load forecasting with improved ceemdan and gwo-based multiple kernel elm, Complexity 2020 (20) (2020) 1-20.

[42] S. Takianngam, W. Usaha, Discrete wavelet transform and one-class support vector machines for anomaly detection in wireless sensor networks, in: 2011 International Symposium on Intelligent Signal Processing and Communications Systems (ISPACS), IEEE, 2011, pp. 1-6.

[43] J. Han, J.Z. Zhang, Network traffic anomaly detection using weighted self-similarity based on emd, in: 2013 Proceedings of IEEE Southeastcon, IEEE, 2013, pp. 1-5.

[44] L. Wang, X. Li, Y. Bai, Short-term wind speed prediction using an extreme learning machine model with error correction, Energy Convers. Manag. 162 (2018) 239-250.

[45] Y. Rao, J. Zhao, Time Series Anomaly Detection Based on Ceemdan and Lstm, 2021 IEEE International Conference on Networking, Sensing and Control (ICNSC), vol. 1, IEEE, 2021, pp. 1-6.

[46] S. Sun, H. Huang, T. Peng, C. Shen, D. Wang, A data privacy protection diagno-sis framework for multiple machines vibration signals based on a swarm learning algorithm, IEEE Trans. Instrum. Meas. 72 (2) (2023) 1-9.

[47] Y. Peng, J. Cheng, Y. Yang, B. Li, Adaptive sparsest narrow-band decomposi-tion method and its applications to rotor fault diagnosis, Measurement 91 (2016) 451-459.

[48] D.S. Singh, Q. Zhao, Pseudo-fault signal assisted emd for fault detection and isolation in rotating machines, Mech. Syst. Signal Process. 81 (2016) 202-218.

[49] P. Lu, L. Ye, B. Sun, C. Zhang, Y. Zhao, J. Teng, A new hybrid prediction method of ultra-short-term wind power forecasting based on eemd-pe and lssvm optimized by the gsa, Energies 11 (4) (2018) 697.

[50] M. Santhosh, C. Venkaiah, D.V. Kumar, Ensemble empirical mode decomposition based adaptive wavelet neural network method for wind speed prediction, Energy Convers. Manag. 168 (2018) 482-493.

[51] Y. Huang, S. Liu, L. Yang, Wind speed forecasting method using eemd and the com-bination forecasting method based on gpr and lstm, Sustainability 10 (10) (2018) 3693.

[52] S. Wang, N. Zhang, L. Wu, Y. Wang, Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and ga-bp neural network method, Renew. Energy 94 (2016) 629-636.

[53] J. Hong, Q. Wang, X. Qiu, H.L. Chan, Remaining useful life prediction using time-frequency feature and multiple recurrent neural networks, in: 2019 24th IEEE In-ternational Conference on Emerging Technologies and Factory Automation (ETFA), IEEE, 2019, pp. 916-923.

[54] S. Cherrared, S. Imadali, E. Fabre, G. Gössler, Sfc self-modeling and active diagnosis, IEEE Trans. Netw. Serv. Manag. 18 (3) (2021) 2515-2530.

[55] L. Zhao, M. Zhang, G. Li, Z. Guan, S. Liu, Z. Xiao, Y. Cao, Z. Lv, Y. Liang, Design of jiutian intelligent network simulation platform, preprint, arXiv :2310.06858, 2023.

[56] Jiutian Open, Innovation platform for next generation artificial intelligence on in-telligen network, https://jiutian.10086.cn/open, 2023. (Accessed 24 March 2023).

[57] A.B. Nassif, M.A. Talib, Q. Nasir, F.M. Dakalbab, Machine learning for anomaly de-tection: a systematic review, IEEE Access 9 (2021) 78658-78700.