Augmenting microgrid control with GHNO for efficient BLDC motor integration and renewable energy utilization

With an emphasis on optimizing the use of renewable energy sources, this work introduces a novel optimization technique called genetic HopNet optimization (GHNO) for improving bidirectional power converter management in microgrid systems. In contrast with traditional converters, this state-of-the-art bidirectional converter allows for the smooth integration of various energy sources, including wind turbines and solar panels, into the microgrid, and GHNO dynamically optimizes its functioning. GHNO iteratively refines control parameters to provide optimal performance under varied situations by combining genetic algorithms and HopNet optimization. Genetic algorithm-based GHNO enhances system efficiency and reduces energy loss, while HopNet optimization allows quick adaptability to load and source condition changes. The converter’s adaptability allows it to buck–boost, ensuring constant power delivery to the microgrid’s critical loads. The control technique uses an adaptive neuro-fuzzy inference system (ANFIS) with neural network learning. The converter system can maintain optimal performance even in the face of fluctuations in load demands and environmental circumstances thanks to the adaptive control parameter adjustments made possible by ANFIS. Through the strategic integration of batteries, MATLAB/Simulink is used to implement and validate the proposed GHNO approach. The key outcomes are 92.145% efficiency in burst-mode operation of the dual-input LLC converter at 200 W, the total harmonic distortion of 20.28% of the PMBLDC motor, and the optimal burst-mode efficiency improvement for light loads compared to standard operation.