Exploring regression models to enable monitoring capability of local energy communities for self‐management in low‐voltage distribution networks

This study proposes a data-driven approach to enable the self-management capability of local energy communities (LECs) via transformer congestion monitoring in low-voltage distribution networks. A set regression models is adopted this approach, while data from residential smart meters (SMs) leveraged. Four machine learning algorithms, namely ridge regression, support vector random forest (RFR) and eXtreme gradient boosting (XGBR), are compared select best-performing model using cross-validation method. comprehensive framework provided facilitate comparison algorithm, consisting pre-processing, fitting validation, deployment. thorough analysis also SMs' measurements. The obtained results highlight that regression-based method can effectively estimate loading, with Pearson correlation coefficient R root mean square error calculated for real values estimated around 0.98 0.87, respectively, by only limited SM measurements (5 out 21 SMs used) LECs preserving customers' privacy rights. Among examined XGBR algorithm appears best as it achieves adequate accuracy at significantly less simulation time (i.e. one-third RFR). By applying proposed be realised.