Guest Editorial: Special Issue on Machine Learning Techniques in Power Electronics

Power conditioning systems are performing a key role in smart grid operation. The increase in renewable energy installation leads to an increase in the power electronic converters installation for distributed generation, rural electrification, and grid integration. As the numbers are increasing, the reliability of the grid is impacted mainly due to the power conditioning weak link. Thus, there is a need to improve the reliability and efficiency of overall power processing. One way to achieve this is to improve health by smart monitoring and make the controller fault-tolerant. For example, approaches that monitor the health of the devices along with fault-tolerant control architecture can be implemented in the controller to detect failures and to get timely alarm signals. For this, relevant data gathering and analysis are extremely critical. Machine learning (ML) and deep learning (DL) are approaches that analyze the data, learn from the data, and then apply it during the decision-making process. The Special Issue on Machine Learning Techniques in Power Electronics invites the articles related to data gathering/analysis and improvements of reliable operation of power conditioning and renewable energy resources with applications to the smart grid.