Review Study on Recent Advancements in Islanding Detection and Diagnosis in Microgrids Using Signal Processing and Machine Learning Techniques

Abstract

The integration of renewable energy sources and microgrids has become a key focus in the pursuit of sustainable and resilient power systems. Microgrids, being decentralized and often operating in isolation from the main grid, face unique challenges, including the need for accurate islanding detection and diagnosis to ensure safe and efficient operations. This review article comprehensively investigates and evaluates the application of signal processing and machine learning techniques in the context of islanding detection and diagnosis within microgrids. The significance of islanding detection and diagnosis is highlighted in this review study which emphasizes grid stability, safety risk mitigation, and energy efficiency enhancement during islanding. Further, the study explores the technical aspects, covering signal processing techniques and machine learning approaches used for islanding detection, including harmonic analysis, wavelet transforms, and neural networks. This research explores the most recent developments in the domain, encompassing a variety of strategies that harness sophisticated algorithms and data analysis to improve the dependability and effectiveness of microgrid operations. Subsequently, this review sheds light on the state-of-the-art methodologies, challenges, and promising avenues in islanding detection and diagnosis, ultimately contributing to the advancement of microgrid technology and the broader vision of sustainable and resilient energy systems. As the transition toward renewable energy sources accelerates, microgrids represent a promising solution for enhancing grid resilience and integrating distributed generation. However, ensuring the safety and efficiency of microgrid operations during islanding events is a critical concern. This study explores the intersection of signal processing and machine learning, offering a comprehensive examination of islanding detection and diagnosis techniques in microgrids.