Load frequency active disturbance rejection control for an interconnected power system via deep reinforcement learning

Load frequency control is an important issue in power systems, so focusing on the typical two-area interconnected power system with non-reheat turbines, this paper designed the learning active disturbance rejection controller to achieve intelligent and adaptive tuning of control parameters, in which the deep reinforcement learning is adopted to adapt to unexpected uncertainties and faults, even a new environment. Finally, numerical simulations show the better performance of the learning controller, and the strong capability to deal with uncertainties and disturbances comparing with the general LADRC controller.