Optimizing Smart Grid System through Renewable Energy Sources and PID Controller Using Artificial Rabbits Optimized Neural Network

The sporadic nature of today’s stochastic grid system and the influx of hybrid renewable resources make it susceptible to significant voltage changes. In smart microgrid networks, these variances are the main source of power quality problems. To address these issues, this manuscript proposes an effective approach that enhances the performance of the smart grid by utilizing Renewable Energy Sources (RES) in conjunction with a PID controller. The RES are Wind Turbine (WT), Photovoltaic (PV) and Battery. The primary objective of this work is to minimize the Integral Squared Error (ISE) and improve system performance. The Proposed approach uses an Artificial Rabbits Optimized Neural Network (ARONN) to predict the gain parameters of the PID controller and minimize error. The proposed ARONN method is implemented and validated using the MATLAB Simulink environment. The simulation outcomes show better performance and robustness of the proposed ARONN approach against existing approaches such as the Seagull Optimization Algorithm (SOA), Flying Foxes Optimization (FFO) and Radial Basis Functional Neural Network (RBFNN). The simulation results indicate that the proposed ARONN-based strategy achieves a settling time of 0.02[Formula: see text]s with minimal overshoot of 3% and undershoot of 2.7%, demonstrating superior system stability and responsiveness compared to existing approaches. In terms of efficiency, the proposed method reaches 95%, highlighting its enhanced performance over FFO, SOA and RBFNN.