Adaptive power quality control with forecast-driven parameter optimization for reduced harmonic distortion in grid systems

The increasing integration of distributed renewable energy sources (RES) into modern utility grids has intensified power quality (PQ) challenges, particularly under nonlinear and dynamically varying operating conditions. To overcome these challenges, this paper presents an intelligent method for developing PQ in grid-connected systems with a Tilted Integral Fractional Derivative with Filter plus Fractional Derivative (TIFDNFD) controller. The proposed method combines the Humboldt Squid Optimization Algorithm (HSOA) and Temporal Inductive Path Neural Network (TIPNN), which is termed the HSOA-TIPNN technique. The main objective of the proposed method is to minimize Total Harmonic Distortion (THD), thereby enhancing PQ. The HSOA is utilized to optimize the gain parameters of the TIFDNFD controller, while TIPNN is used to predict the performance of the controller. The proposed technique is tested in MATLAB and compared with Artificial Neural Network (ANN), Convolutional Neural Network (CNN) and Deep Recurrent Neural Network (DRNN). The proposed HSOA-TIPNN is able to get the THD of 0.8% while ANN, CNN, and DRNN are 0.9%, 1.0%, and 1.1%, respectively. It also achieves a prediction accuracy of 99.90%, an MSE of 0.0032, and a settling time of 0.15 s, demonstrating improved harmonic suppression, faster dynamic response, and enhanced PQ under nonlinear and disturbed grid conditions.