Abstract :

The Integration Of Large-scale Solar Photovoltaic (PV) Systems Into Modern Distribution Networks Introduces Critical Operational Vulnerabilities During Asymmetrical Low-Voltage Ride-Through (LVRT) Disturbances. Under These Unbalanced Grid Faults, Conventional Control Architectures Primarily Reliant On Decoupled Double Synchronous Reference Frame (DDSRF) Configurations Paired With Linear Proportional-Integral (PI) Regulators Exhibit Severe Performance Degradation. These Conventional Systems Suffer From Prolonged Phase Delays Caused By Sequence Extraction Filters, Structural Vulnerability To Time-varying Grid Impedances (𝑟𝑔, 𝑥𝑔), And An Inability To Simultaneously Mitigate Coupled Double-frequency (2𝜔) Active Power Oscillations And DC-link Voltage Ripples Without Causing Inverter Current Saturation. To Resolve These Limitations, This Paper Proposes A Unified, Data-driven Control Paradigm Utilizing A Trained Multi-layer Artificial Neural Network (ANN) For Adaptive Current Reference Generation. The Proposed ANN Operates As A Multi-variable Non-linear Optimizer, Simultaneously Mapping Nine High-dimensional Real-time Grid And PV Parameters Directly To Optimal Decoupled Current Reference Commands (𝑖𝑑 ∗ , 𝑖𝑞 ∗ ). By Eliminating Delayed Analytical Filtering Blocks And Coordinate Transformations, The Intelligent Controller Inherently Reshapes The Distorted Elliptical Current Trajectory In The Stationary Frame Back Into An Optimized Profile. Crucially, The ANN Dynamically Incorporates Changing Grid Impedance Ratios While Balancing Conflicting Optimization Objectives To Enforce Strict Protection Boundaries, Keeping DC-link Voltage Ripples Within ±15% Of Nominal Values And Preventing Over-modulation Distortion. Validated Within The MATLAB/Simulink Environment Across Extensive Operational Profiles Including Diverse Irradiance Levels And Severe Asymmetrical Faults The Proposed Intelligent Control Paradigm Demonstrates Instantaneous Dynamic Response Times, Superior Harmonic Suppression, And Absolute Compliance With Stringent International Grid Codes. Consequently, This Research Provides A Highly Robust, Tuning-free Alternative That Significantly Enhances Hardware Asset Longevity And Grid Resilience In High-penetration Renewable Energy Infrastructures.

Published:

17-7-2026

Issue:

Vol. 26 No. 7 (2026)

Page Nos:

710-723

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite