A microgrid (MG) is part of a distribution system that comprises loads and distributed energy resources, capable of operating either connected to or islanded from the primary grid. Having an appropriate design, MG controllers improve energy efficiency, playing a vital role in the modern distribution system. Thus, MG management and control has become a broad area of research due to its complex operation. Reinforcement learning (RL) offers adaptive solutions for handlingMGcomplex dynamics and nonlinearity. It is an alternative to traditional algorithms and control methods in tasks such as load frequency control, resource allocation, and energy management. Due to the relevance of the topic, this survey examined the role of RL in MG control and management, offering a comprehensive update on previous reviews, categorising articles by RL type, control objectives, and MG operational modes. Additionally, hardware implementations and performance assessments across RL-based solutions were evaluated. The present survey identified key research trends and gaps, contributing to understanding the role of RL in MG management and control and guiding future solutions in the field.

This paper proposes an adaptive hybrid-tripping-based protection strategy for microgrids (MGs) that enables a fast and reliable response to faults by leveraging phase voltage and current measurements from relay locations. The protection coordination problem was addressed by optimizing the relay settings for different MG operating scenarios, ensuring proper coordination between the primary and backup relays. Comprehensive performance evaluation using PSCAD simulations demonstrated that the proposed protection scheme operates with 50% of faults cleared within 41.5 ms, while 90% of cases are cleared within 530.8 ms across various fault conditions in both grid-connected and islanded operating conditions. The backup relays exhibited a minimum trip time of 230 ms and a median trip time of 299.6 ms, while the coordination time intervals remained within safe margins (50% of cases maintaining a margin of 246.7 ms), ensuring selectivity. Moreover, real-time hardware-in-the-loop (HIL) tests using TMSF28335 microcontrollers validated the scheme’s practical applicability, showing a strong correlation between simulated and experimental results. The mean difference between the simulated and experimental trip times was 29 ms, with maximum deviations below 7.2% (64 ms) and a minimum deviation of 5 ms. The results confirm the effectiveness of the proposed strategy in reducing tripping times while maintaining coordination, making it a promising solution for both islanded and grid-connected MG operating modes.

The fault location is an important issue to be studied in the context of smart grids and microgrids. Thus, this article presents a methodology based on Artificial Neural Networks (ANNs) to locate areas under fault. To train and validate the ANNs, the superimposed components of the voltage and current measurements, acquired by a single meter at the substation, were used. The proposed strategy was tested utilizing the medium voltage distribution system benchmark from CIGRE, including the analysis of different ANN topologies. After several simulations via the PSCAD™/EMTDC™ software, the analysis demonstrated that the proposed methodology is promising and leads to a high level of accuracy in locating areas under fault.