Smart Substation Network Fault Classification Based on a Hybrid Optimization Algorithm

• Autorzy: Xia Xin , Liu Xiaofeng , Lou Jichao

Identyfikatory

DOI

10.24425/ijet.2019.129825

• Języki publikacji: EN

Abstrakty

EN

Accurate network fault diagnosis in smart substations is key to strengthening grid security. To solve fault classification problems and enhance classification accuracy, we propose a hybrid optimization algorithm consisting of three parts: anti-noise processing (ANP), an improved separation interval method (ISIM), and a genetic algorithm-particle swarm optimization (GA-PSO) method. ANP cleans out the outliers and noise in the dataset. ISIM uses a support vector machine (SVM) architecture to optimize SVM kernel parameters. Finally, we propose the GA-PSO algorithm, which combines the advantages of both genetic and particle swarm optimization algorithms to optimize the penalty parameter. The experimental results show that our proposed hybrid optimization algorithm enhances the classification accuracy of smart substation network faults and shows stronger performance compared with existing methods.

Słowa kluczowe

EN

smart substation; network fault classification; improved separation interval method; ISIM; support vector; machine; SVM; anti-noise processing; ANP

• Wydawca: Polish Academy of Sciences, Committee of Electronics and Telecommunication
• Czasopismo: International Journal of Electronics and Telecommunications
• Rocznik: 2019
• Tom: Vol. 65, No. 4
• Strony: 657--663
• Opis fizyczny: Bibliogr. 40 poz., wykr., tab.

Twórcy

autor

Xia Xin

• Department of Information Technology, Wenzhou Vocational & Technical College, also with College of Computer Information Technology, Wuhan Institute of Shipbuilding Technology

autor

Liu Xiaofeng

• Department of Information Technology, Wenzhou Vocational & Technical College

autor

Lou Jichao

• School of Computer Science, Wuhan University

Bibliografia

• [1] A. Belaout, F. Krim, and A. Mellit, “Multiclass adaptive neuro-fuzzy classifier and feature selection techniques for photovoltaic array fault detection and classification,” Renewable Energy, vol. 127, pp. 548-558, 2018.
• [2] A. Chattopadhyay, A. Ukil, and D. Jap, “Toward Threat of Implementation Attacks on Substation Security: Case Study on Fault Detection and Isolation,” IEEE Transactions on Industrial Informatics, vol. 14, no. 6, pp. 2442-2443, 2018.
• [3] W. Chen, M. Nguyen, and W. Chiu, “Optimization of the plastic injection molding process using the Taguchi method, RSM, and hybrid GA-PSO,” International Journal of Advanced Manufacturing Technology, vol. 83, no. 9, pp. 1873-1886, 2016.
• [4] L. Dalton, and E. Dougherty, “Optimal classifiers with minimum expected error within a Bayesian framework,” Pattern Recognition, vol. 46, no. 5, pp. 1288-1300, 2013.
• [5] U. Carmo, D. Sadok, and J. Kelner, “IEC 61850 traffic analysis in electrical automation networks,” IEEE International Conference on Smart Grid Communications, Miami, USA, pp. 466-471, 2015.
• [6] A. Elgargouri, R. Virrankoski, and Elmusrati M., “IEC 61850 Based Smart Grid Security,” IEEE International Conference on Industrial Technology, Seville, Spain, pp. 2461-2465, 2015.
• [7] H. Meizi et al., “Research on Intelligent Diagnosis Strategy of Secondary Device Abnormity in Smart Substation,” 2018 2nd International Conference on Power and Energy Engineering, Xiamen, China, 2018.
• [8] J. Hong, C. Liu, and M. Govindarasu, “Integrated Anomaly Detection for Cyber Security of the Substations,” IEEE Transactions on Smart Grid, vol. 5, no. 4, pp. 1643-1654, 2014.
• [9] C. Hou, F. Nie, and C. Zhang, “Multiple rank multi-linear SVM for matrix data classification,” Pattern Recognition, vol. 47, no. 1, pp. 454-469, 2014.
• [10] K. Qader and M. Adda, “Fault Classification System for Computer Networks Using Fuzzy Probabilistic Neural Network Classifier,” Communications in Computer and Information Science, vol. 459, , pp. 217-226, 2014.
• [11] O. Khaled, A. Marín, and F. Almenares, “Analysis of Secure TCP/IP Profile in 61850 Based Substation Automation System for Smart Grids,” International Journal of Distributed Sensor Network, vol. 2016, no. 2, pp. 1-11, 2016.
• [12] K. Knuth, M. Habeck, and N. Malakar, “Bayesian evidence and model selection,” Digital Signal Processing, vol. 47, pp. 50-67, 2015.
• [13] O. Kocadağlı, “A novel hybrid learning algorithm for full Bayesian approach of artificial neural networks,” Applied Soft Computing, vol. 35, pp. 52-65, 2015.
• [14] M. Kordestani, M. Samadi, and M. Saif, “A New Fault Diagnosis of Multifunctional Spoiler System Using Integrated Artificial Neural Network and Discrete Wavelet Transform Methods,” IEEE Sensors Journal, vol. 18, no. 12, pp. 4990-5001, 2018.
• [15] C. Lin, and S. Wang, “An intelligent lung cancer diagnosis system using cuckoo search optimization and support vector machine classifier,” Journal of Ambient Intelligence and Humanized Computing, vol. 10, no. 1, pp. 267-293, 2019.
• [16] Y. Lin, F. Lv, and S. Zhu, “Large-scale image classification: Fast feature extraction and SVM training,” IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, USA, pp. 1689-1696, 2011.
• [17] H. Livani, and C. Evrenosoğlu, “A fault classification method in power systems using DWT and SVM classifier,” IEEE/PES Transmission and Distribution Conference and Exposition, Orlando, FL, USA, pp. 1-5, 2012.
• [18] D. Lu, and W. Qiao, “A GA-SVM hybrid classifier for multiclass fault identification of drivetrain gearboxes,” IEEE Energy Conversion Congress and Exposition, Pittsburgh, PA, USA, pp. 3894-3900, 2014.
• [19] D. Mack, G. Biswas, and X. Koutsoukos, “Learning Bayesian Network Structures to Augment Aircraft Diagnostic Reference Models,” IEEE Transactions on Automation Science and Engineering, vol. 14, no. 1, pp. 358-369, 2017.
• [20] M. TanveerD., “Newton method for implicit Lagrangian twin support vector machines,” International Journal of Machine Learning and Cybernetics, vol. 6, no. 6, pp. 1029-1040, 2015.
• [21] H. Faris et al., “An intelligent system for spam detection and identification of the most relevant features based on evolutionary Random Weight Networks,” Information Fusion , vol. 48, pp. 67-83, 2019.
• [22] T. RenatoR et al, “NK Hybrid Genetic Algorithm for Clustering,” IEEE Transactions on Evolutionary Computation, vol. 22, no. 5, pp. 748-761, 2018.
• [23] H. Md Alamgir et al, “Modified PSO algorithm for real-time energy management in grid-connected microgrids”, vol. 136, pp. 746-757, 2019.
• [24] Y. Qian, H. Zhang, and D. Peng, “Fault diagnosis for generator unit based on RBF neural network optimized by GA-PSO,” International Conference on Natural Computation Natural Computation, Chongqing, China, pp. 233-236, 2012.
• [25] N. Raj, G. Jagadanand, and S. George, “Fault detection and diagnosis in asymmetric multilevel inverter using artificial neural network,” International Journal of Electronics, vol. 105, no. 4, pp. 559-571, 2018.
• [26] A. Hadbah, A. Kalam, and A. Zayegh, “Powerful IEDs, ethernet networks and their effects on IEC 61850-based electric power utilities security,” 2017 Australasian Universities Power Engineering Conference, Melbourne, Australia,, pp. 1-5, 2017.
• [27] F. Saraiva, W. Bernardes, and E. Asada, “A framework for classification of non-linear loads in smart grids using Artificial Neural Networks and Multi-Agent Systems,” Neurocomputing, vol. 170, pp. 328-338, 2015.
• [28] J. Steckenrider, and T. Furukawa, “Detection and classification of stochastic features using a multi-Bayesian approach,” IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, Daegu, South Korea, pp. 150-155, 2017.
• [29] F. Sun, N. Wang, and J. He, “Lamb Wave Damage Quantification Using GA-Based LS-SVM,” Materials, vol. 10, no. 6, pp. 1-21, 2017.
• [30] K. Topuz, F. Zengul, and A. Dag, “Predicting graft survival among kidney transplant recipients: A Bayesian decision support model,” Decision Support Systems, vol. 106, pp. 97-109, 2018.
• [31] A. Valdes, R. Macwan, and M. Backes, “Anomaly Detection in Electrical Substation Circuits via Unsupervised Machine Learning,” IEEE 17th International Conference on Information Reuse and Integration, Pittsburgh, PA, USA, pp. 500-505, 2016.
• [32] S. Valuvanathorn, S. Nitsuwat, and M. Huang, “Multi-feature face recognition based on PSO-SVM,” 10th International Conference on ICT and Knowledge Engineering, Bangkok, Thailand, pp. 140-145, 2012.
• [33] M. Wang, and X. Li, “Power Cable Fault Recognition Using the Improved PSO-SVM Algorithm,” Applied Mechanics and Materials, vol. 427, pp. 830-833, 2013.
• [34] W. Wang, Z. Xu, and W. Lu, “Determination of the spread parameter in the Gaussian kernel for classification and regression,” Neurocomputing, vol. 55, no. 3, pp. 643-663, 2003.
• [35] M. Panda, A. Abraham, and BK. Tripathy,” Soft granular computing based classification using hybrid fuzzy-KNN-SVM,” Intelligent Decision Technologies, vol. 10, no. 2, pp. 115-128, 2016.
• [36] Y. Wang, and M. Simaan, “A Suction Detection System for Rotary Blood Pumps Based on the Lagrangian Support Vector Machine Algorithm,” IEEE Journal of Biomedical & Health Informatics, vol. 17, no. 3, pp. 654-663, 2013.
• [37] Z. Xu, M. Dai, and D. Meng, “Fast and Efficient Strategies for Model Selection of Gaussian Support Vector Machine,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 39, no. 5, pp. 1292-1307, 2009.
• [38] H. Yoo, and T. Shon, “Novel Approach for Detecting Network Anomalies for Substation Automation based on IEC 61850,” Multimedia Tools & Applications, vol. 74, no. 1, pp. 303-318, 2015.
• [39] H. Zheng, Y. Zhang, and J. Liu, “A novel model based on wavelet LS-SVM integrated improved PSO algorithm for forecasting of dissolved gas contents in power transformers,” Electric Power Systems Research, vol. 155, pp. 196-205, 2018.
• [40] T. Zhou, S. Popescu, and A. Lawing, “Bayesian and Classical Machine Learning Methods: A Comparison for Tree Species Classification with LiDAR Waveform Signatures,” Remote Sensing, vol. 10, no. 1, pp. 1-27, 2018.

Uwagi

This work was supported by the scientific research project of Zhejiang Provincial Department of Education (project number: Y201738745), the National Natural Science Foundation of China (project number: 61772386).