Power system state estimation method based on width learning

The invention discloses an electric power system state estimation method based on width learning, and the method comprises the steps: screening known operation parameters which are strongly correlated with to-be-estimated operation parameters through combining a known operation parameter database of an electric power system and utilizing a Spearman correlation coefficient, and constructing a training set and a test set of a state estimation model; establishing a power system state estimation model with an input layer, a hidden layer and an output layer based on a width learning theory; iteratively training the state estimation model for multiple times on the training set, determining weight coefficients from an input layer to a hidden layer, from a feature node to an enhanced node and from the hidden layer to an output layer in the model, and performing precision test on the state estimation model on the test set to realize precise estimation of the to-be-estimated operating parameters of the power system. Co