TY - JOUR
T1 - Learning-Based Model Predictive Control of DC-DC Buck Converters in DC Microgrids
T2 - A Multi-Agent Deep Reinforcement Learning Approach
AU - Sorouri, Hoda
AU - Oshnoei, Arman
AU - Novak, Mateja
AU - Blaabjerg, Frede
AU - Anvari-Moghaddam, Amjad
PY - 2022/7
Y1 - 2022/7
N2 - This paper proposes a learning-based finite control set model predictive control (FCS-MPC) to improve the performance of DC-DC buck converters interfaced with constant power loads in a DC microgrid (DC-MG). An approach based on deep reinforcement learning (DRL) is presented to address one of the ongoing challenges in FCS-MPC of the converters, i.e., optimal design of the weighting coefficients appearing in the FCS-MPC objective function for each converter. A deep deterministic policy gradient method is employed to learn the optimal weighting coefficient design policy. A Markov decision method formulates the DRL problem. The DRL agent is trained for each converter in the MG, and the weighting coefficients are obtained based on reward computation with the interactions between the MG and agent. The proposed strategy is wholly distributed, wherein agents exchange data with other agents, implying a multi-agent DRL problem. The proposed control scheme offers several advantages, including preventing the dependency of the converter control system on the operating point conditions, plug-and-play capability, and robustness against the MG uncertainties and unknown load dynamics.
AB - This paper proposes a learning-based finite control set model predictive control (FCS-MPC) to improve the performance of DC-DC buck converters interfaced with constant power loads in a DC microgrid (DC-MG). An approach based on deep reinforcement learning (DRL) is presented to address one of the ongoing challenges in FCS-MPC of the converters, i.e., optimal design of the weighting coefficients appearing in the FCS-MPC objective function for each converter. A deep deterministic policy gradient method is employed to learn the optimal weighting coefficient design policy. A Markov decision method formulates the DRL problem. The DRL agent is trained for each converter in the MG, and the weighting coefficients are obtained based on reward computation with the interactions between the MG and agent. The proposed strategy is wholly distributed, wherein agents exchange data with other agents, implying a multi-agent DRL problem. The proposed control scheme offers several advantages, including preventing the dependency of the converter control system on the operating point conditions, plug-and-play capability, and robustness against the MG uncertainties and unknown load dynamics.
KW - DC microgrids
KW - Finite set model predictive control (FS-MPC)
KW - dc-dc buck converter
KW - deep reinforcement learning
KW - Constant power load
UR - http://www.scopus.com/inward/record.url?scp=85136513335&partnerID=8YFLogxK
U2 - 10.3390/en15155399
DO - 10.3390/en15155399
M3 - Journal article
SN - 1996-1073
VL - 15
SP - 1
EP - 21
JO - Energies
JF - Energies
IS - 15
M1 - 5399
ER -