Abstract
The increase in mobile data traffic has imposed unprecedented pressure on wireless network management. KPI-based anomaly diagnosis can alleviate such pressure by automatically identifying the cause of abnormalities in the traffic and providing end-to-end monitoring and optimization. Previous approaches mainly focus on finding a subset of anomaly-inducing KPIs on the basis of supervised learning procedures. These studies have two possible limitations: (1) the inherent correlations between KPIs that are proven to be effective for the anomaly diagnosis, are still largely underexplored; (2) machine learning models heavily rely on human annotations, which are expensive and labor-intensive. Therefore, we propose random matrix theory-based KPI identification (RKI), a novel method that automatically mines rich interactions between KPIs for anomaly diagnosis without using any learnable parameters or human annotations. Specifically, RKI diagnoses the abnormal KPIs in two steps. First, we build a matrix for anomaly KPI detection to mine the spectrum of its covariances. Second, another new matrix is reconstructed to calculate the correlation difference. By doing so, the anomaly KPIs that have larger correlation difference scores can be efficiently identified in the wireless traffic without any trainable parameters. In extensive experiments on a public dataset, RKI yields a 6.5% higher true diagnostic rate and 11.36% lower false alarming rate than the statistical model, demonstrating its effectiveness. A 100 × larger scale synthetic dataset also demonstrates the capabilities of RKI to explore massive data traffic under real-word scenarios. Finally, we discuss RKI’s potential applications of our method in future 6G wireless networks.
References
Index C V N. Cisco Visual Networking Index: Global Mobile Data Traffic Forecast Update, 2017–2022 White Paper. Cisco: San Jose, 2019
Aliu O G, Imran A, Imran M A, et al. A survey of self organisation in future cellular networks. IEEE Commun Surv Tutorials, 2013, 15: 336–361
Strinati E C, Barbarossa S, Gonzalez-Jimenez J L, et al. 6G: the next frontier: from holographic messaging to artificial intelligence using subterahertz and visible light communication. IEEE Veh Technol Mag, 2019, 14: 42–50
You X H, Wang C-X, Huang J, et al. Towards 6G wireless communication networks: vision, enabling technologies, and new paradigm shifts. Sci China Inf Sci, 2021, 64: 110301
Fernandes J G, Rodrigues J J P C, Carvalho L F, et al. A comprehensive survey on network anomaly detection. Telecommun Syst, 2019, 70: 447–489
Callado A, Kamienski C, Szabo G, et al. A survey on Internet traffic identification. IEEE Commun Surv Tut, 2009, 11: 37–52
Sui T, Tao X, Xia S, et al. A real-time hidden anomaly detection of correlated data in wireless networks. IEEE Access, 2020, 8: 60990–60999
Munoz P, Barco R, Serrano I, et al. Correlation-based time-series analysis for cell degradation detection in SON. IEEE Commun Lett, 2016, 20: 396–399
Palacios D, de-la-Bandera I, Gomez-Andrades A, et al. Automatic feature selection technique for next generation self-organizing networks. IEEE Commun Lett, 2018, 22: 1272–1275
Marnerides A K, Schaeffer-Filho A, Mauthe A. Traffic anomaly diagnosis in Internet backbone networks: a survey. Comput Networks, 2014, 73: 224–243
Jiang D, Yuan Z, Zhang P, et al. A traffic anomaly detection approach in communication networks for applications of multimedia medical devices. Multimed Tools Appl, 2016, 75: 14281–14305
Ahmed M, Mahmood A N, Hu J. A survey of network anomaly detection techniques. J Network Comput Appl, 2016, 60: 19–31
Jurdak R, Wang X R, Obst O, et al. Wireless sensor network anomalies: diagnosis and detection strategies. In: Intelligence-Based Systems Engineering. Berlin: Springer, 2011. 309–325
He Z, Xu X, Deng S. Discovering cluster-based local outliers. Pattern Recogn Lett, 2003, 24: 1641–1650
Brint A, Genovese A, Piccolo C, et al. Reducing data requirements when selecting key performance indicators for supply chain management: the case of a multinational automotive component manufacturer. Int J Production Economics, 2021, 233: 107967
Münz G, Li S, Carle G. Traffic anomaly detection using k-means clustering. In: Proceedings of GI/ITG Workshop MMBnet, 2007. 13–14
Khreich W, Khosravifar B, Hamou-Lhadj A, et al. An anomaly detection system based on variable N-gram features and one-class SVM. Inf Software Tech, 2017, 91: 186–197
Zhang C, Song D, Chen Y, et al. A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2019. 33: 1409–1416
Kwon D, Natarajan K, Suh S C, et al. An empirical study on network anomaly detection using convolutional neural networks. In: Proceedings of IEEE 38th International Conference on Distributed Computing Systems (ICDCS), 2018. 1595–1598
Kibria M G, Nguyen K, Villardi G P, et al. Big data analytics, machine learning, and artificial intelligence in next-generation wireless networks. IEEE Access, 2018, 6: 32328–32338
He X, Ai Q, Qiu R C, et al. A big data architecture design for smart grids based on random matrix theory. IEEE Trans Smart Grid, 2015. doi: https://doi.org/10.1109/TSG.2015.2445828
Qiu R C, Antonik P. Smart Grid Using Big Data Analytics: A Random Matrix Theory Approach. Hoboken: John Wiley & Sons, 2017
Xu F, Li Y, Wang H, et al. Understanding mobile traffic patterns of large scale cellular towers in urban environment. IEEE ACM Trans Networking, 2016, 25: 1147–1161
Yang J, Ma Z, Dong C, et al. An empirical investigation into CDMA network traffic classification based on feature selection. In: Proceedings of the 15th International Symposium on Wireless Personal Multimedia Communications, 2012. 448–452
Chen Z, Chen D, Zhang X, et al. Learning graph structures with transformer for multivariate time-series anomaly detection in IoT. IEEE Internet Things J, 2022, 9: 9179–9189
Tao T. Topics in Random Matrix Theory. Providence: American Mathematical Society, 2012
Brody T A, Flores J, French J B, et al. Random-matrix physics: spectrum and strength fluctuations. Rev Mod Phys, 1981, 53: 385–479
Guhr T, Müller-Groeling A, Weidenmüller H A. Random-matrix theories in quantum physics: common concepts. Phys Rep, 1998, 299: 189–425
Laloux L, Cizeau P, Potters M, et al. Random matrix theory and financial correlations. Int J Theor Appl Finan, 2000, 03: 391–397
Yeo J, Papanicolaou G. Random matrix approach to estimation of high-dimensional factor models. 2016. ArXiv:1611.05571
Chen H, Tao X F, Li N, et al. A data analysis of political polarization using random matrix theory. Sci China Inf Sci, 2020, 63: 129303
Luo F, Zhong J, Yang Y, et al. Application of random matrix theory to biological networks. Phys Lett A, 2006, 357: 420–423
Chen H, Tao X, Li N, et al. Physical layer data analysis for abnormal user detecting: a random matrix theory perspective. IEEE Access, 2019, 7: 169508
Couillet R, Debbah M. Random Matrix Methods for Wireless Communications. Cambridge: Cambridge University Press, 2011
Qiu R C, Hu Z, Li H, et al. Cognitive Radio Communication and Networking: Principles and PRACTICE. Hoboken: John Wiley & Sons, 2012
He Y, Yu F R, Zhao N, et al. Big data analytics in mobile cellular networks. IEEE Access, 2016, 4: 1985–1996
Tulino A M, Verdú S. Random matrix theory and wireless communications. FNT Commun Inf Theor, 2004, 1: 1–182
Han B, Luo L, Sheng G, et al. Framework of random matrix theory for power system data mining in a non-Gaussian environment. IEEE Access, 2016, 4: 9969–9977
Shi X, Qiu R, He X, et al. Early anomaly detection and localisation in distribution network: a data-driven approach. IET Gener Transm Distrib, 2020, 14: 3814–3825
Shi X, Qiu R, Ling Z, et al. Spatio-temporal correlation analysis of online monitoring data for anomaly detection and location in distribution networks. IEEE Trans Smart Grid, 2019, 11: 995–1006
Bun J, Bouchaud J P, Potters M. Cleaning large correlation matrices: tools from random matrix theory. Phys Rep, 2017, 666: 1–109
Benesty J, Chen J, Huang Y. On the importance of the Pearson correlation coefficient in noise reduction. IEEE Trans Audio Speech Lang Process, 2008, 16: 757–765
Bai Z, Silverstein J W. Spectral Analysis of Large Dimensional Random Matrices. 2nd ed. New York: Springer, 2010
Edelman A, Rao N R. Random matrix theory. Acta Numerica, 2005, 14: 233–297
Parwez M S, Rawat D B, Garuba M. Big data analytics for user-activity analysis and user-anomaly detection in mobile wireless network. IEEE Trans Ind Inf, 2017, 13: 2058–2065
Alwis C D, Kalla A, Pham Q V, et al. Survey on 6G frontiers: trends, applications, requirements, technologies and future research. IEEE Open J Commun Soc, 2021, 2: 836–886
Letaief K B, Chen W, Shi Y, et al. The roadmap to 6G: AI empowered wireless networks. IEEE Commun Mag, 2019, 57: 84–90
Yang H, Alphones A, Xiong Z, et al. Artificial-intelligence-enabled intelligent 6G networks. IEEE Network, 2020, 34: 272–280
Xiao Y, Shi G, Li Y, et al. Toward self-learning edge intelligence in 6G. IEEE Commun Mag, 2020, 58: 34–40
Han G, Tu J, Liu L, et al. Anomaly detection based on multidimensional data processing for protecting vital devices in 6G-enabled massive IIoT. IEEE Internet Things J, 2021, 8: 5219–5229
Acknowledgements
This work was supported by National Natural Science Foundation of China (Grant Nos. 61941105, U21A20449), Beijing Natural Science Foundation (Grant No. L212003), and the 111 Project of China (Grant No. B16006).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Sui, T., Tao, X., Wu, H. et al. Mining KPI correlations for non-parametric anomaly diagnosis in wireless networks. Sci. China Inf. Sci. 66, 162301 (2023). https://doi.org/10.1007/s11432-021-3522-0
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11432-021-3522-0