A Physics-Informed Machine Learning Framework for Adaptive Harmonic Mitigation in Residential Power Systems

This study focuses on reducing harmonic distortion in residential electrical systems caused by the use of nonlinear household appliances. A combined prediction and control framework is proposed to estimate and reduce total harmonic distortion (THD) under different operating conditions. Measurements were collected from common domestic appliances, along with environmental factors such as temperature and humidity. An auto-optimized neighborhood fuzzy rough set (AO-NFRS) method is used to identify important input features. These features are then used in a physics-informed machine learning model to predict THD. Based on the predicted values, a Bayesian-optimized ANFIS controller is applied to decide the suitable filtering mode in real time. The results show that the proposed method improves prediction accuracy and reduces harmonic distortion compared to existing methods. It also provides stable filter switching under changing load conditions. The study demonstrates that combining measurement data, physical relationships, and adaptive control can improve power quality in residential systems.