Jointly improving energy efficiency and smoothing power oscillations of integrated offshore wind and photovoltaic power: a deep reinforcement learning approach

Abstract This paper proposes a novel deep reinforcement learning (DRL) control strategy for an integrated offshore wind and photovoltaic (PV) power system improving generation efficiency while simultaneously damping oscillations. A variable-speed turbine (OWT) with electrical torque is used in the whose dynamic models are detailed. By considering as partially-observable Markov decision process, actor-critic architecture model-free DRL algorithm, namely, deterministic policy gradient, adopted implemented to explore learn optimal multi-objective policy. The potential effectiveness of evaluated. results imply that OWT can respond quickly sudden changes inflow conditions maximize total generation. Significant oscillations overall output also be well suppressed by regulating generator torque, which further indicates complementary operation PV achieved.