A Review of Machine Learning Approaches in Synchrophasor Technology

Abstract

As power systems (PS) move toward smart grids and microgrids in modern times, complexity eventually rises as a result of integration with various distributed energy resources, demand-side management, and cybersecurity issues. Additionally, frequent PS network blackouts will have an impact on a country’s social, economic, and financial position. To ensure the reliability as well as security of the network’s smart-driven power system, more advanced monitoring and measurement technology, which is dominated by SCADA systems, is required. This is where synchrophasor-based phasor measurement units (PMUs) come into play, which process and analyze massive amounts of data in real-time more precisely to identify systemic anomalies. Due to their quick response times, high computing speeds, accuracy, and scalability, machine learning (ML)-based techniques are becoming more popular for handling real-time big data. The many ML algorithms used recently in synchrophasor technology, which enhances cybersecurity, fault detection and classification, transient stability assessment, voltage stability assessment, and forced oscillation localization are thoroughly reviewed in this paper. With the help of more than 190 pertinent papers, this work effectively discusses the ML applications in the synchrophasor technology where PMUs and μPMUs are deployed. The article also shows that several concerns have not yet been resolved and are still up for consideration by researchers in the future. One of them is the detection and observation of oscillation and line-tripping occurrences in the distribution area where μPMUs are installed. To address these problems, sophisticated DL approaches are recommended. Future possibilities to decrease bandwidth usage and improve processing delay using edge computing technology are also mentioned in this paper. The research potential for ML and DL approaches also extends to power line communication, wide area monitoring systems, and 5G and 6G network communications.