SVM based protection scheme for microgrid

This paper describes a support vector machine (SVM) based protection scheme for microgrid. The aim of this study is to propose an efficient and novel approach for fault detection/classification and faulty section identification of shunt faults in grid-connected and islanding modes of operation considering the intermittent behavior of PV source and non-linear loading conditions. The proposed scheme uses three phase voltage and current signals obtained by creating various fault situations with variation in fault parameters. Discrete wavelet transform (DWT) is used further to obtain approximate co-efficient of these signals as input to train the SVM based classifier for both modes of operation separately. Test results reveal that the proposed scheme has been proved to be effective and has significantly contributed in the protection of microgrid.

[1]  S. R. Samantaray,et al.  Data-Mining Model Based Intelligent Differential Microgrid Protection Scheme , 2017, IEEE Systems Journal.

[2]  Ehab F. El-Saadany,et al.  Fault Type Classification in Microgrids Including Photovoltaic DGs , 2016, IEEE Transactions on Smart Grid.

[3]  Geza Joos,et al.  A Combined Wavelet and Data-Mining Based Intelligent Protection Scheme for Microgrid , 2016, IEEE Transactions on Smart Grid.

[4]  S. R. Mohanty,et al.  Classification of Power Quality Disturbances Due to Environmental Characteristics in Distributed Generation System , 2013, IEEE Transactions on Sustainable Energy.

[5]  Niraj Kumar Choudhary,et al.  A review on Microgrid protection , 2014, 2014 International Electrical Engineering Congress (iEECON).

[6]  Susmita Kar,et al.  Time-frequency transform-based differential scheme for microgrid protection , 2014 .

[7]  Zahra Moravej,et al.  Power quality events classification and recognition using a novel support vector algorithm , 2009 .

[8]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

[9]  S. C. Srivastava,et al.  A Classification Approach Using Support Vector Machines to Prevent Distance Relay Maloperation Under Power Swing and Voltage Instability , 2012, IEEE Transactions on Power Delivery.

[10]  G. Panda,et al.  Fault Classification and Section Identification of an Advanced Series-Compensated Transmission Line Using Support Vector Machine , 2007, IEEE Transactions on Power Delivery.

[11]  Subhojit Ghosh,et al.  A modular neuro-wavelet based non-unit protection scheme for zone identification and fault location in six-phase transmission line , 2017, Neural Computing and Applications.

[12]  N. K. Verma,et al.  Wavelet transforms for fault detection using SVM in Power Systems , 2012, 2012 IEEE International Conference on Power Electronics, Drives and Energy Systems (PEDES).

[13]  Seyed Hossein Hesamedin Sadeghi,et al.  An overview of microgrid protection methods and the factors involved , 2016 .

[14]  Taha Selim Ustun,et al.  Recent developments in microgrids and example cases around the world—A review , 2011 .

[15]  Adam Dysko,et al.  Traveling Wave-Based Protection Scheme for Inverter-Dominated Microgrid Using Mathematical Morphology , 2014, IEEE Transactions on Smart Grid.