Abstract
Monitoring data or sensor data could reflect the working situation of power grid system at a fine-grained level. Specifically, when an anomaly event happened, some variations will appear and propagate between these interrelated sensor data. However, their latent relationship are complex and difficult to capture. To address this challenge, we propose a data-driven anomaly detection method, which performs real-time correlation analysis of sensor data and implements anomaly detection at runtime. Firstly, the method adopts the correlation coefficient calculation methods to obtain the time-varying correlation between sensed data. Additionally, graph is applied to represent the relationship between them. The edges of the graph are labeled with the degree of correlation and the nodes are marked with some statistical characteristics of the original sensor data. Moreover, an anomaly detection algorithm based on graph convolution network is implemented. The effectiveness of this approach is verified based on real power grid datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Han, Y.B., Liu, C., Su, S., et al.: A decentralized and service-based approach to proactively correlating stream data. In: International Conference on Internet of Things, pp. 93–100 (2016)
Chu, V.W., Wong, R.K., Liu, W., et al.: Traffic analysis as a service via a unified model. In: IEEE International Conference on Services Computing, pp. 195–202. IEEE (2014)
Zhang, J., Radia, N., Li, Z., et al.: An infrastructure supporting considerate sensor service provisioning. In: The 6th IEEE International Conference on Service Oriented Computing and Applications (SOCA), pp. 69–76. IEEE (2013)
Guilly, T.L., Olsen, P., Ravn, A.P., et al.: HomePort: middleware for heterogeneous home automation networks. In: IEEE International Conference on Pervasive Computing and Communications Workshops, pp. 627–633. IEEE (2013)
Atkinson, A.C., Hawkins, D.M., et al.: Identification of outliers. Biometrics 37(4), 860 (1981)
Budgaga, W., Malensek, M., Pallickara, S.L., et al.: A framework for scalable real-time anomaly detection over voluminous, geospatial data streams. In: Concurrency & Computation Practice & Experience, pp. 1–24 (2017)
Kieu, T., Yang, B., Jensen, C.S., et al.: Outlier detection for multidimensional time series using deep neural networks. In: 2018 19th IEEE International Conference on Mobile Data Management (MDM), pp. 125–134 (2018)
Subramaniam, S., Palpanas, T., Papadopoulos, D.: Online outlier detection in sensor data using non-parametric models. In: 32nd International Conference on Very Large Data Bases, pp. 187–198 (2006)
Nguyen, H.T., Thai, N.H.: Temporal and spatial outlier detection in wireless sensor networks. ETRI J. 41(8), 437–451 (2019)
Huang, H.: Data anomaly detection method of sensor nodes in Internet of Things. Computer Simul. 05, 167–170 (2012)
Qi, Z., Yupeng, H., Cun, J.: Edge computing application: real-time anomaly detection algorithm for sensing data. J. Comput. Res. Dev. 55(3), 524–536 (2018)
Xie, M., Hu, J., Guo, S.: Distributed segment-based anomaly detection with kullback–leibler divergence in wireless sensor networks. IEEE Trans. Inf. Forensics Secur. 12(1), 101–110 (2017)
Tian, L., Zhang, D.: An anomaly detection method of sensor data based on information entropy. Comput. Eng. Softw. 39(09), 77–81 (2018)
Grabaskas, N., Si, D.: Anomaly detection from kepler satellite time-series data. In: International Conference on Machine Learning & Data Mining in Pattern Recognition, pp. 220–232 (2017)
Khatkhate, A., Ray, A., Keller, E., et al.: Symbolic time-series analysis for anomaly detection in mechanical systems. IEEE/ASME Trans. Mechatron. 11(4), 439–447 (2006)
Laptev, N., Amizadeh, S., Flint, I., et al.: Generic and scalable framework for automated time-series anomaly detection. In: 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1939–1947 (2015)
Burgess, M.: Two dimensional time-series for anomaly detection and regulation in adaptive systems. In: 13th IFIP/IEEE International Workshop on Distributed Systems: Operations and Management, pp. 169–180 (2002)
Fei, H., Xiao, F., Li, G., et al.: An anomaly detection method of wireless sensor network based on multi-modals data stream. Chin. J. Comput. 40(8), 1829–1842 (2017)
Wang, L., Zhang, R., Sheng, W., et al.: Regression forecast and abnormal data detection based on support vector regression. Proc. CSEE 08, 94–98 (2009)
Chen, Y.: Density-based clustering for real-time stream data. In: ACM International Conference on Knowledge Discovery & Data Mining, pp. 133–142 (2007)
Zhang, J., Li, B., Liu, X., et al.: Abnormal time series detection in wireless sensor network based on hadoop. Chin. J. Sens. Actuators 12, 1659–1665 (2014)
Cai, L., Thornhill, N., Kuenzel, S., et al.: Real-time detection of power system disturbances based on k-nearest neighbor analysis. IEEE Access 5, 5631–5639 (2017)
Yan, Q.Y., Xia, S.X., Feng, K.W., et al.: Probabilistic distance based abnormal pattern detection in uncertain series data. Knowl.-Based Syst. 36, 182–190 (2012)
Xu, J.M.: Anomaly detection of mobile network interaction behavior based on Internet of Things. J. Eastern Liaoning Univ. (Nat. Sci. Ed.) 28(01), 34–38 (2021)
Qiu, Y., Chang, X., et al.: Stream data anomaly detection method based on long short-term memory network and sliding window. J. Comput. Appl. 40(05), 1335–1339 (2020)
Liu, F.: Research on threshold selection algorithm of time series data anomaly detection based on DBSCAN. Modern Comp. 04, 3–6 (2020)
Li, R., Jia, Y., Jiao, Z., et al.: Network behavior anomaly detection based on time series. Commun. Technol. 53(10), 2550–2554 (2020)
Acknowledgement
This work is supported by the science and technology project of State Grid Corporation of China: “Research on data governance and knowledge mining technology of power IOT based on Artificial Intelligence” (Grand No.5700-202058184A-0–0-00).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Weiwei, L. et al. (2021). An Anomaly Detection Method Based on GCN and Correlation of High Dimensional Sensor Data in Power Grid System. In: Wang, X., Wong, KK., Chen, S., Liu, M. (eds) Artificial Intelligence for Communications and Networks. AICON 2021. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 396. Springer, Cham. https://doi.org/10.1007/978-3-030-90196-7_38
Download citation
DOI: https://doi.org/10.1007/978-3-030-90196-7_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-90195-0
Online ISBN: 978-3-030-90196-7
eBook Packages: Computer ScienceComputer Science (R0)