Bacterial Foraging Algorithm for a Neural Network Learning Improvement in an Automatic Generation Controller

The frequency diversion in hybrid power systems is a major challenge due to the unpredictable generation of renewable energies. An automatic controller (AGC) system utilised correct when energies and consumers’ load demand are changing rapidly. While neural network (NN) model based on back-propagation (BP) training algorithm commonly used design AGCs, it requires complicated methodology longer processing time. In this paper, bacterial foraging (BF) was employed enhance learning NN for AGCs adequately identifying initial weights model. Hence, error addressed quickly compared with traditional model, resulting an accurate signal prediction. To assess proposed AGC, photovoltaic (PV) test designed using MATLAB/Simulink. outcomes research demonstrate that AGC BF-NN-based effective correcting minimising its overshoot under various conditions. BP-NN PID, showing former achieved lowest standard transit time 5.20 s mismatching conditions disturbance PV fluctuation.