Open AccessAn Improved Neural Network Based on Parasitism – Predation Algorithm for an Automatic Voltage Regulator
Author(s) -
Widi Aribowo,
Bambang Suprianto,
I Gusti Putu Asto Buditjahjanto,
Mahendra Widyartono,
Miftahur Rohman
Publication year - 2021
Publication title -
ecti transactions on electrical eng. / electronics and communications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.148
H-Index - 7
ISSN - 1685-9545
DOI - 10.37936/ecti-eec.2021192.241628
Subject(s) - backpropagation , artificial neural network , overshoot (microwave communication) , computer science , control theory (sociology) , regulator , recurrent neural network , artificial intelligence , algorithm , biology , telecommunications , control (management) , biochemistry , gene
The parasitism – predation algorithm (PPA) is an optimization method that duplicates the interaction of mutualism between predators (cats), parasites (cuckoos), and hosts (crows). The study employs a combination of the PPA methods using the cascade-forward backpropagation neural network. This hybrid method employs an automatic voltage regulator (AVR) on a single machine system, with the performance measurement focusing on speed and the rotor angle. The performance of the proposed method is compared with the feed-forward backpropagation neural network (FFBNN), cascade-forward backpropagation neural network (CFBNN), Elman recurrent neural network (E-RNN), focused time-delay neural network (FTDNN), and distributed time-delay neural network (DTDNN). The results show that the proposed method exhibits the best speed and rotor angle performance. The PPA-CFBNN method has the ability to reduce the overshoot of the speed by 1.569% and the rotor angle by 0.724%.