A Machine Learning-Based Communication-Free PV Controller for Voltage Regulation

Due to the recent advancements in manufacturing process of solar photovoltaics (PVs) and electronic converters, PVs has emerged as a viable investment option for energy trading. However, distribution system with large-scale integration rooftop PVs, would be subjected voltage upper limit violations, unless properly controlled. Most traditional solutions introduced address this problem do not ensure fairness amongst on-line sources. In addition, other schemes assume presence communication linkages between these This paper proposes control scheme mitigate over-voltages without any distributed The proposed approach is based on artificial neural networks that can utilize two locally obtainable inputs, namely, nodal node sensitivity PV power. controller trained using extensive data generated various loading conditions include daily load variations. was implemented tested 12.47 kV feeder 85 households connected 220 V system. results demonstrate fair all mounted houses are maintained within allowed limits defined by ANSI C84.1-2016 standard. Furthermore, verify robustness controller, it during cloudy weather condition impact electric vehicles also analyzed. prove efficacy controller.