Innovative approach for improving power quality in solar energy systems with DSTATCOM for stabilising the grid and effectively mitigating harmonics

Solar-powered systems suffer from power quality issues which can degrade system performance and affect grid stability. Traditional control strategies struggle to effectively mitigate harmonics and optimize controller parameters , which leads to inefficiencies in power compensation. The study proposes an intelligent and optimized method to enhance the effectiveness of Distributed Static Synchronous Compensators (D-STATCOM) in stabilizing the grid and improving power quality. The proposed approach utilizes Beluga Whale Optimization (BWO) in synergy with Cascade Correlation Growing Deep Learning Neural Network (CCG-DLNN) to fine-tune the PI controller parameters and accurately predict optimal control settings. The proposed strategy is simulated utilizing MATLAB and compared to optimization techniques like Wild Horse Optimizer (WHO), Grasshopper Optimization Algorithm (GOA) and Seagull Optimization Algorithm (SOA). From the findings, the proposed technique achieves a low THD of 2 % for voltage and 2.3 % for current, ensuring improved power quality and enhanced grid stability. In terms of efficiency, the proposed method has a higher value of 98.13 % compared to 86.2 % for GOA, 84.09 % for SOA, and 78 % for WHO. The enhanced power quality and reduced harmonic distortion achieved by the proposed BWO-CCG-DLNN lead to a more reliable and efficient solar energy system , minimizing losses and ensuring compliance with grid standards.