In viewing the power grid for large-scale new energy integration and power electrification of power grid equipment

the impact of power system faults is increased

and the ability of anti-disturbance is decreased

which makes the power system fault clearance more difficult. In this paper

a load shedding control strategy based on artificial intelligence is proposed

this action strategy of load shedding

which is selected by deep reinforcement learning

can support autonomous voltage control. First

the power system operation data is used as the basic data to construct the network training dataset

and then a novel reward function for voltage is established. This value function

which conforms to the power grid operation characteristics

will act as the reward value for deep reinforcement learning

and the Deep Deterministic Policy Gradient algorithm (DDPG) algorithm

with the continuous action strategy

will be adopted. Finally

the deep reinforcement learning network is continuously trained

and the load shedding strategy concerning the grid voltage control problem will be obtained in the power system emergency control situation

and this strategy action is input into the Pypower module for simulation verification

thereby realizing the joint drive of data and model. According to the numerical simulation analysis

it shows that this method can effectively determine the accurate action selection of load shedding

and improve the stable operational ability of the power system.