Line loss is an important indicator for evaluating the economic operation of the power system. With the development of smart grid, it has accumulated a large amount of line loss data, which allows us to use a data-driven approach for line loss estimation. In this paper, an algorithm based on K-Medoids clustering and ensemble learning (KMC-EL) is proposed for feeder loss estimation. Firstly, considering the difference between feeders, an unsupervised learning algorithm, which is called the K-Medoids clustering, is used for feeders clustering. And then, for each type of feeder, an ensemble learning algorithm based on Bagging, Boosting and weighted integrated algorithm are proposed to estimate line loss. Compared with the traditional algorithms, the KMC-EL model has a lower MSE value, which means it has a better generalization ability and can be applied in different feeder loss estimation scenarios.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.