Aiming at the multi-microgrid system model considering the output of electric vehicles
photovoltaics and wind power
an economic optimization scheduling structure for multi microgrid systems based on deep reinforcement learning is established with the minimization of the total operating cost of the system as the objective function
and the state
action
reward function and neural network structure of the improved SAC algorithm are designed by using the framework of the improved SAC algorithm. After simulation and comparative analysis
the scheduling strategy obtained by the algorithm reduces the total operating cost.
KIUMARSI B, LEWIS F L.Actor-critic-based optimal tracking for partially unknown nonlinear discrete-time systems[J]. IEEE transactions on neural networks and learning systems, 2015, 26(1): 140-151.
MBUWIR B V, RUELENS F, SPIESSENS F, et al.Battery energy management in a microgrid using batch reinforcement learning[J]. Energies, 2017, 10(11): 1846.
PRIANTO E, KIM M, PARK J H, et al.Path planning for multi-arm manipulators using deep reinforcement learning: soft actor-critic with hindsight experience replay[J]. Sensors, 2020, 20(20): 5911.