To solve the problem of manpower and time consumption caused by power flow state adjustment in a large-scale power grid, a power system operation state adjustment method considering the static stability constraint based on parallel deep reinforcement learning is proposed. By introducing the process of adjusting the power flow state that satisfies static stability, the Markov decision-making process of adjusting power flow is constructed. Then, based on the positioning of the adjustment target, the selection of actionable devices and the calculation of the amount of action, a power flow state adjustment strategy is developed. The adjustment process is accelerated through sensitivity, transfer ratio and load margin. Then, a parallel deep reinforcement learning model is established, and it maps actions to power flow adjustment to form a pair of generator actions and realises parallel adjustment of multi-sectional objectives. In addition, the reinforcement learning strategy and the deep learning network are improved to promote learning efficiency. Finally, the New England 39-bus standard system and actual power grid are used to verify the effectiveness of the method.