Power grid accidental fault safety regulation and control strategy generation method based on reinforcement learning

The invention discloses a power grid accidental fault safety regulation and control strategy generation method based on reinforcement learning. The method comprises the steps that a semi-physical simulation model of an actual power grid is built; a power grid regulation and control strategy represented by a neural network is generated by utilizing a large amount of historical operation data of an actual power grid, historical data is supplemented by artificially generating a security threat, and the power grid regulation and control strategy is optimized by utilizing reinforcement learning; and aiming at accidental faults of an actual power grid, the digital simulation platform senses the faults in time, and then generates regulation and control behaviors are generated by using a trained power grid regulation and control strategy. A complex power grid safety regulation and control problem is converted into a power grid regulation and control strategy expressed by a neural network, when a new safety threat occ