Key points are not available for this paper at this time.
This paper presents an application of reinforcement learning for control of large-scale power systems. The temporal difference reinforcement learning is investigated as an online learning strategy for optimising fuzzy logic controllers of synchronous generators interconnected in the power system. The simulation study is undertaken, based on a three-machine power system which has multimode oscillations, to evaluate the proposed learning control strategy.
K.H. Chan (2000) studied this question.