An Optimized Machine Learning-Based Time-Frequency Transform for Protection of Distribution Generation Integrated Microg

This work focuses on the protection of distributed generation (DG) integrated microgrid system by using Kernel Extreme Learning Machine (KELM) based Hilbert–Huang Transform (HHT). Firstly, the current signals collected from buses are processed through Emp

  • PDF / 438,931 Bytes
  • 15 Pages / 439.37 x 666.142 pts Page_size
  • 72 Downloads / 222 Views

DOWNLOAD

REPORT


Abstract This work focuses on the protection of distributed generation (DG) integrated microgrid system by using Kernel Extreme Learning Machine (KELM) based Hilbert–Huang Transform (HHT). Firstly, the current signals collected from buses are processed through Empirical Mode Decomposition (EMD) to obtain the Intrinsic Mode Functions (IMFs). Subsequently, the most significant IMF is used for the calculation of spectral energy and differential energy of both the buses. Subsequently, the most relevant features for protection aspects like differential energy levels, mean, median, entropy, and standard deviation are recorded for all fault types in a gridconnected environment with both radial and looped structures on IEC microgrid model test system. Further, the Gaussian kernel is used with 70% data points for the training of the neural network and optimization of the random matrix. The optimized values are then analyzed for validation and the efficiency quotient. The accuracy, security, and dependability values clearly illustrate the superiority of this optimized KELM architecture for the detection of a fault in a grid-connected microgrid system. Keywords Signal processing technique · Machine learning technique · Kernel extreme learning machine (KELM) · Hilbert-Huang transform (HHT) · Microgrid protection · Feature extraction

1 Introduction The evolution throughout the ages increases the human dependability on electricity with uninterrupted supply. The microgrid plays an important role in a robust and S. Sarangi · B. K. Sahu Department of Electrical Engineering, ITER, Siksha O Anusandhan (Deemed to be University), Bhubaneswar 751030, Odisha, India e-mail: [email protected] B. K. Sahu e-mail: [email protected] P. K. Rout (B) Department of Electrical and Electronics Engineering, ITER, Siksha O Anusandhan (Deemed to be University), Bhubaneswar 751030, Odisha, India e-mail: [email protected] © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021 R. Sharma et al. (eds.), Green Technology for Smart City and Society, Lecture Notes in Networks and Systems 151, https://doi.org/10.1007/978-981-15-8218-9_33

385

386

S. Sarangi et al.

secure power system architecture. However, the conventional sources are limited in nature and pollution friendly whereas the renewable sources, i.e. solar, wind, biomass, and hydro, etc. are major emerging sources that lessen the burden to some extent. Microgrid works as a valuable solution for environmental as well as commercial issues associate with the traditional grid. It can be operated in two modes of operation, i.e. integrated mode and isolated mode and can also be operated independently. For reliability and flexibility purposes, the protection of microgrid is a prime factor [1]. To successfully address the protection issues many kinds of researches are carried out. In [2], the author has proposed an overcurrent technique based on impedance. However, this technique is not proficient for high impedance fault. Nikkhaj