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