Smart Power Quality Optimization in Hybrid Renewable Energy Systems Integrated with the Grid

Abstract

Modern power systems prioritize power quality (PQ) to meet electricity demand and address environmental concerns. However, integrating hybrid renewable energy sources (HRES) into the grid can challenge PQ. To improve this, this manuscript proposes a hybrid framework, combining the Harbor Seal Whiskers Optimization Algorithm (HSWOA) and Efficient Predefined Time Adaptive Neural Network (EPTANN), termed the HSWOA-EPTANN approach, to enhance the grid-connected system's PQ. The Distributed Power Flow Controller (DPFC) with the Tilted Integral Fractional Derivative with Filter plus Fractional Derivative (TIFDNFD) controller reduces PQ issues like reactive power, swell, voltage dips, interruptions, and Total Harmonic Distortion (THD). The proposed HSWOA is employed to optimally tune the gain factor of the TIFDNFD controller for improved grid stability under dynamic conditions, while the EPTANN adaptively predicts the gain parameter using predefined time convergence learning to improve overall system robustness and mitigate power quality disturbances. The proposed HSWOA-EPTANN technique is excluded from the MATLAB platform, and its performance is contrasted with existing approaches. The proposed HSWOA-EPTANN is more effective in reducing harmonic distortion, lowering it to 0.20%.