The invention discloses a wind power plant aggregation characteristic modeling method, which comprises the following steps of: 1, acquiring actually measured operation data at the positions of a plurality of wind turbine generators of a wind power plant, and cleaning and normalizing the data; 2, establishing a wind power fluctuation measurement index; 3, establishing an aggregated output smooth effect measurement index of the wind power plant, and obtaining a relational expression among the smooth effect measurement index, the aggregated unit number N and the correlation coefficient of an inter-unit power sequence; 4, establishing a mapping model of multi-position-point wind condition information and inter-unit power sequence correlation based on a convolutional neural network; 5, forminga model training sample, training a neural network model by using a root-mean-square error function index, and outputting a unit output correlation mapping result; and 6, realizing wind power plant aggregation characteristic modeling based on the convolutional neural network.