Power system load flow calculation method considering data privacy security

The invention provides a power system load flow calculation method considering data privacy security. The power system load flow calculation method comprises the following steps that S1, a center coordinator server constructs a load flow calculation model based on ResNet; s2, the model is distributed to each client client, the client client comprises a local model and a local data set, and the client client uses the local data set to train the model; s3, integrating data set training model parameters of various regions, updating global model parameters, and returning to the step S2; s4, judging whether specified training times are reached or not, if so, stopping iteration to obtain a load flow calculation global model, and otherwise, returning to the step S2; and S5, inputting the power flow data into the model to obtain the voltage amplitude and the phase angle of each node. According to the invention, through distributed training of federal learning, communication cost and local storage and calculation cost