An Artificial Rabbit Optimized Neural Network-Based Hybrid DC-AC Microgrid Energy Management System

This study provides a synthetic Rabbit optimization for artificial neural networks to accomplish power utilization in DC-AC hybrid supply systems. A load, distributed generation, and battery-based power supervision system is suggested. A neural network was trained to predict energy storage device charging and discharging in multiple distribution-network power circumstances using profile data. The 10% error rate was a plus. Rabbit-inspired artificial Rabbit optimizers educate a neural network to operate efficiently in the recommended power supervision system. The artificial Rabbit optimizer adjusts the neural network weights and bias based on grid power, distributed generator energy, and direct axis reference current to provide the best power supervision scheme. Limited power microgrids with hybrid DC/AC system were tried to replicate and assess the planned power supervision system. The artificial rabbit optimization optimizer improved power management with neural network system is the most efficient in the literature at 99.55%.