Power Quality

Power quality research focuses on reliably detecting and classifying disturbances in electrical grids, aiming to improve grid stability, security, and efficiency. Current research heavily utilizes machine learning, particularly deep learning models like transformers and diffusion models, along with wavelet transforms and other signal processing techniques, to achieve high-accuracy classification even in noisy or adversarial conditions. These advancements are crucial for enhancing grid operations, enabling proactive maintenance, and mitigating the risks associated with increasingly complex and distributed energy systems. The development of robust and explainable AI methods for anomaly detection and event forecasting is a key focus, addressing concerns about reliability and accountability in critical infrastructure applications.