Machine learning assessment of IoT managed microgrid protection in existence of SVC using wavelet methodology

Abstract

In the last decade, research has been started due to accelerated growth in power demand has mainly concentrated on the large power production and quality of power. After the digital revolution, non-conventional energy sources, many state-of-art equipment, power electronics loads, reactive power compensating devices, sophisticated measuring devices, etc., entered the power industry. The reactive power compensating devices, connected electrical equipment, renewable energy sources can be anticipated/unanticipated action can cause considerable reactions may be failure issues to power grids. To deal with these challenges, the power sector crucially needs to design and implement new security systems to protect its systems. The Internet-of-Things (IoT) is treated as revolution technology after the invention of the digital machine and the internet. New developments in sensor devices with wireless technologies through embedded processors provide effective monitoring and different types of faults can be detected during electric power transmission. The wavelet (WT) is one of the mathematical tools to asses transient signals of different frequencies and provides crucial information in the form of detailed coefficients. Machine learning (ML) methods are recommended in the power systems community to simplify digital reform. ML and AI techniques can make effective and rapid decisions to improve the stability and safety of the power grid. This recommended approach can contribute critical information about symmetrical or asymmetrical faults through machine learning assessment of IoT supervised microgrid protection in the presence of SVC using the wavelet approach covers diversified types of faults combined with fault-inception-angles (FIA).