A novel intelligent control using RBFNN-class topper optimization for stability enhancement in hybrid standalone microgrid

Abstract This paper presents an intelligent coordinated control framework for a hybrid standalone microgrid integrating solar photovoltaic, wind, and battery energy storage systems. The proposed Radial Basis Function Neural Network–Class Topper Optimization Algorithm (RBFNN–CTOA) controller combines the online adaptive learning capability of the RBFNN with the supervisory optimization strength of the CTOA to enhance voltage stability and dynamic performance under renewable intermittency and load disturbances. The effectiveness of the proposed control strategy is validated through MATLAB/Simulink simulations under varying operating conditions, including sudden load changes and nonlinear loads. The results demonstrate tight DC-link voltage regulation, fast transient recovery, and low current harmonic distortion in compliance with IEEE 519–2014 standards. Comparative analysis further confirms that the proposed controller outperforms conventional PI and ANN-based controllers in terms of voltage regulation accuracy, power quality, and robustness. In addition, the proposed framework exhibits low computational overhead and real-time feasibility, making it suitable for embedded implementation. Owing to its modular structure and supervised online adaptation, the control strategy supports scalable extension to larger or multi-area microgrids without requiring offline retraining for moderate changes in system capacity.