A microgrid is an aggregation of multiple distributed generators (DGs), such as renewable energy sources, conventional generators, and energy storage systems that provide both electric power and thermal energy. Typically, a microgrid operates in parallel with the main grid. However, there are cases in which a microgrid operates in an islanded mode, or in a disconnected state. Islanded microgrid can change its operational mode to gridconnected operation by reconnection to the grid, which is referred to as synchronization. Generally, a single machine simply synchronizes with the grid using a synchronizer. However, the synchronization of microgrids that operate with multiple DGs and loads cannot be controlled by a traditional synchronizer. It is needed to control multiple generators and energy storage systems in a coordinated way for the microgrid synchronization. This is not a simple problem, considering that a microgrid consists of various power electronics-based DGs as well as alternator-based generators that produce power together. This paper proposes an active synchronizing control scheme that adopts the network-based coordinated control of multiple DGs. From the simulation results using Simulink dynamic models, it is shown that the scheme provides the microgrid with a deterministic and reliable reconnection to the grid. The proposed method is verified by using the test cases with the experimental setup of a practical microgrid pilot plant.Index Terms-Energy storage system, microgrid, microgrid central controller (MCC), network-based control, static transfer switch (STS), synchronization.
Sufficient amount of learning data is an essential condition to implement a classifier with excellent performance. However, the obtained data usually follow a significantly biased distribution of classes. It is called a class imbalance problem, which is one of the frequently occurred issues in the real world applications. This problem causes a considerable performance drop because most of the machine learning methods assume given data follow a balanced distribution of classes. The implemented classifier will derive false classification results if the problem is not solved. Therefore, this paper proposes a novel method, named as Gaussianbased SMOTE, to solve the problem by combining Gaussian distribution in a synthetic data generation process. It is confirmed that the proposed method could solve the class imbalance problem by conducting experiments with actual cases.
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.