The increasing complexity and demand for reliability in modern power systems necessitate advanced techniques for fault detection, classification, and location. This work presents a comprehensive study on the application of Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) for fault management in power systems. ANFIS, combining the benefits of neural networks and fuzzy logic, offers a robust framework for handling the non-linearities and uncertainties inherent in power system faults. The proposed method leverages historical fault data to train the ANFIS model, enabling it to accurately detect, classify, and locate various types of faults, including line-to-ground, line-to-line, and three-phase faults. The model’s performance is evaluated using a simulated power system environment, and its effectiveness is validated through extensive testing under different fault scenarios. Results demonstrate that the ANFIS-based approach achieves high accuracy in fault detection and classification, significantly reducing the response time. Additionally, the system exhibits a strong capability in pinpointing fault locations with minimal error margins. This research underscores the potential of ANFIS as a powerful tool for improving the consistency and competence of fault management in power systems. The findings suggest that integrating ANFIS into existing protection schemes can lead to improved operational efficiency (97–99%), whereas in case of ANN, the efficiency is (92–95%) resilience and reduced downtime. Future work will focus on real-time implementation and the incorporation of ANFIS with other smart grid technologies to further augment fault management capabilities.
Microgrids are gaining prominence within modern power systems, fueled by advancements in renewable energy-based distributed generation. However, dynamic network architectures and high bidirectional power flows render traditional protection schemes designed for passive radial distribution networks inadequate. Conventional overcurrent protection faces challenges due to fluctuating fault currents in both grid-connected and islanded modes, further complicated by the unpredictable output impedance of inverter-interfaced distributed generation units during faults. This article aims to comprehensively review current microgrid protection methods, analyzing their benefits and drawbacks while highlighting critical challenges and identifying areas for future research. A hybrid AC-DC microgrid simulation is conducted to validate fault current variations under different operating conditions. The study focuses on intelligent methods and apparatuses that enhance existing protection systems. Ultimately, this thorough investigation seeks to demonstrate the critical role of efficient microgrid protection in ensuring a reliable and sustainable future electricity supply.
15 October 2024 in Journal of Electrical Engineering & Technology