Power data quality improvement through PMU bad data detection based on deep complex

被引:0
作者
Kabra P. [1 ,2 ]
Rani D.S. [3 ]
机构
[1] Koneru Lakshmaiah Education Foundation, Mangalagiri, Andhra Pradesh, Vaddeswaram
[2] Deccan College of Engineering and Technology, Telangana, Hyderabad
[3] Sri Vasavi College of Engineering, Andhra Pradesh, Tadepalligudem
关键词
bad data; batch normalisation; DCNN; deep complex neural network; phasor measurement units; PMUs; SE; state estimator; weight normalisation;
D O I
10.1504/IJPELEC.2023.134437
中图分类号
学科分类号
摘要
Phasor measurement units (PMUs) allow devices to be switched in a variety of power signal modes. PMU data from spike produces jitter or signal glitches and disturbance in transmission creates bad data. Due to these challenges, PMU data experience varying degrees of data quality issues. Several methods have been already used to detect fake data, but they come with drawbacks like complexity. Similarly, it has not been possible to identify faulty data caused by topology fluctuations optimally. To resolve these problems a deep complex neural network (DCNN) has been proposed in which robust bad data detection technique analyses complex numbers with both voltage magnitude and phase angles. Comparisons are made between the proposed methods and existing methods in terms of accuracy, bad data detection capabilities, bad data detection range, running time, F1-score, and computational cost. The proposed technique provides an accuracy of 99.5% which is higher than the existing techniques. © 2023 Inderscience Publishers. All rights reserved.
引用
收藏
页码:394 / 414
页数:20
相关论文
共 33 条
  • [1] Kabra P., Rani D.S., Power data quality improvement through PMU bad data detection based on deep complex, Int. J. Power Electronics, 18, 4, pp. 394-414, (2023)
  • [2] Abiodun O.I., Abiodun E.O., Alawida M., Alkhawaldeh R.S., Arshad H., A review on the security of the internet of things: challenges and solutions, Wireless Personal Communications, 6, 3, pp. 1-35, (2021)
  • [3] Affonso C., Et al., Deep learning for biological image classification, Expert Systems with Applications, 85, 9, pp. 114-122, (2017)
  • [4] Ahmed A., Sajan K.S., Srivastava A., Wu Y., Anomaly detection, localization and classification using drifting synchrophasor data streams, IEEE Transactions on Smart Grid, 12, 4, pp. 3570-3580, (2021)
  • [5] Alalousi A., Et al., A preliminary performance evaluation of K-means, KNN, and EM unsupervised machine learning methods for network flow classification, International Journal of Electrical and Computer Engineering, 6, 2, (2016)
  • [6] Aljohani N., Bretas A., A Bi-level model for detecting and correcting parameter cyber-attacks in power system state estimation, Applied Sciences, 11, 14, (2021)
  • [7] Amutha A.L., Uthra A.R., Preetha R.J., Brunet G.R., Anomaly detection in multivariate streaming PMU data using density estimation technique in wide area monitoring system, Expert Systems with Applications, 175, 15, (2021)
  • [8] Chauhan S.V.S., Gao G.X., Synchrophasor data under GPS spoofing: attack detection and mitigation using residuals, IEEE Transactions on Smart Grid, 12, 4, pp. 3415-3424, (2021)
  • [9] Dorier M., Frigo G., Abur A., Paolone M., Leverage point identification method for LAV-based state estimation, IEEE Transactions on Instrumentation and Measurement, 70, 7, (2021)
  • [10] Ghosh D., Novel trends in resilience assessment of a distribution system using synchrophasor application: a literature review, International Transactions on Electrical Energy Systems, 31, 8, (2021)