Smart Processing of Exceptional Values in Electrical Networks Using Neuro-Fuzzy Algorithms

This research introduces a novel smart meter topology within the context of an integrated PV-Wind hybrid system for DC electric micro-networks. The proposed topology incorporates advanced techniques such as Linear Interpolation, Artificial Neural Network (ANN), and Adaptive Neuro-Fuzzy Inference System (ANFIS) for identifying and correcting outliers in the collected data. The integration of the smart meter with outlier detection and correction modules enhances the accuracy and reliability of the measurements, contributing to the overall efficiency of the micro-network. Linear Interpolation is employed to estimate and fill in missing data points, ensuring a continuous and consistent dataset. The ANN module is designed to identify outliers by learning patterns from historical data, allowing for real-time anomaly detection. Furthermore, the ANFIS module enhances the system's adaptability by providing a fuzzy logicbased approach to correct outliers, taking into account the dynamic nature of renewable energy sources in the hybrid system. The proposed smart meter topology offers a comprehensive solution for ensuring the integrity of data collected in DC electric micronetworks. By leveraging the synergies of Linear Interpolation, ANN, and ANFIS, the system demonstrates improved robustness against data anomalies, thereby enabling more accurate monitoring, control, and optimization of the PV-Wind hybrid system. This research contributes to the advancement of smart grid technologies, particularly in the realm of renewable energy micro-networks, by addressing the challenges associated with data quality and reliability.