Method and system for adjusting power flow of power system based on deep reinforcement learning

The invention discloses a method and a system for adjusting power flow of a power system based on deep reinforcement learning, and relates to the field of automatic adjustment of large power grid power flow. The method comprises the following steps: taking a to-be-adjusted active power range of each target section as input information of a training target; carrying out preliminary screening on anadjustable generator in the power system; randomly obtaining the number of the target section m and the transmission power of the target section m; further determining a fine screening strategy of theadjustable generator based on the training target of each round, and compensating the change of the active power in real time; generating an adjustment strategy by using a deep reinforcement learningalgorithm; and executing an adjustment strategy to adjust the power flow state of the power system until the transmission power is adjusted to a target value. According to the method, automatic calculation of the operation mod