TY - JOUR
T1 - Brain Modeling for Microgrid Control and Protection
T2 - State of the Art, Challenges, and Future Trends
AU - De La Cruz, Jorge
AU - Tan, Sen
AU - Saha, Diptish
AU - Bazmohammadi, Najmeh
AU - Vasquez, Juan C.
AU - Guerrero, Josep M.
PY - 2024
Y1 - 2024
N2 - Microgrids (MGs) are building blocks of smart power systems formed by integrating local power generation resources, energy storage systems (ESSs), and power-consuming units. While MGs offer many benefits, including increased resilience and flexibility, there remains a need for improved control and protection techniques that can ensure their performance and automatic restoration in response to dynamic operating conditions and failure events. Recently, researchers have explored model-free emotional learning adaptive strategies based on the emotional response of human brains to control MGs. These model-free control strategies are well-suited for handling the complexity, nonlinearity, and uncertainty present in MGs and offer several advantages over traditional approaches. This article provides an overview of different emotional learning techniques applied to MG control and protection, their challenges, and future trends. In addition, we draw parallels between the hierarchical control architecture (HCA) of MGs and the emotional learning process in the human brain, discussing their operational strategies and key areas of research. Finally, the future implementations of brain emotional learning (BEL) in the control and protection of MGs are discussed, and concluding remarks on the potential of this approach are provided.
AB - Microgrids (MGs) are building blocks of smart power systems formed by integrating local power generation resources, energy storage systems (ESSs), and power-consuming units. While MGs offer many benefits, including increased resilience and flexibility, there remains a need for improved control and protection techniques that can ensure their performance and automatic restoration in response to dynamic operating conditions and failure events. Recently, researchers have explored model-free emotional learning adaptive strategies based on the emotional response of human brains to control MGs. These model-free control strategies are well-suited for handling the complexity, nonlinearity, and uncertainty present in MGs and offer several advantages over traditional approaches. This article provides an overview of different emotional learning techniques applied to MG control and protection, their challenges, and future trends. In addition, we draw parallels between the hierarchical control architecture (HCA) of MGs and the emotional learning process in the human brain, discussing their operational strategies and key areas of research. Finally, the future implementations of brain emotional learning (BEL) in the control and protection of MGs are discussed, and concluding remarks on the potential of this approach are provided.
KW - Artificial intelligence
KW - Brain modeling
KW - Computational modeling
KW - Control systems
KW - Emotional responses
KW - Frequency control
KW - Voltage control
UR - http://www.scopus.com/inward/record.url?scp=85188914061&partnerID=8YFLogxK
U2 - 10.1109/MIE.2024.3374234
DO - 10.1109/MIE.2024.3374234
M3 - Journal article
SN - 1932-4529
SP - 2
EP - 13
JO - I E E E Industrial Electronics Magazine
JF - I E E E Industrial Electronics Magazine
M1 - Early Access
ER -