Empirical Wavelet Transform-Based Intelligent Protection Scheme for Microgrids

Recently, the concept of microgrid (MG) has been developed to assist penetration large numbers distributed energy resources (DERs) into distribution networks. However, integration DERs in form MGs disturbs operating codes traditional Consequently, protection strategies cannot be applied MG against short-circuit faults. This paper presents a novel intelligent strategy (NIPS) for based on empirical wavelet transform (EWT) and long short-term memory (LSTM) In proposed NIPS, firstly, three-phase current signals measured by protective relays are decomposed modes (EMs). Then, various statistical features extracted from obtained EMs. Afterwards, along with measurement input three different LSTM network obtain exact fault type, phase, location information. Finally, trip signal information is generated disconnect faulty portion rest MG. The significant feature NIPS that it does not need adaptive relaying communication Moreover, independent scenario hence magnitude. To evaluate efficacy exhaustive simulations performed an international electro-technical commission (IEC) simulation results confirm efficiency NIPs terms accuracy, dependability, security. comparisons existing schemes validate highly accurate, secure, dependable.