The invention relates to a regional integrated energy system equipment capacity optimization method based on improved NSGA-III. The method comprises the following steps: establishing a regional integrated energy system model composed of photovoltaic, wind power, CCHP and electric energy storage equipment; from the perspective of a carbon target, determining a target function and constraint conditions of the regional integrated energy system model; the method comprises the following steps: constructing an improved NSGA-III algorithm based on a self-adaptive SBX-NBX hybrid crossover operator; the method comprises the following steps: simulating cooling, heating and power loads of a research area, collecting annual temperature, solar radiation intensity and wind speed data, and dividing the whole year into three typical days of summer, winter and transition season by adopting a K-means clustering method; and by utilizing an improved NSGA-III algorithm, according to a target function and constraint conditions of the model, in combination with typical daily data of a research region, solving capacity configuration of the regional integrated energy system equipment, and obtaining an optimal capacity configuration scheme. Compared with the prior art, the method provided by the invention can accurately and stably solve the optimal scheme for the equipment capacity configuration of the low-carbon regional integrated energy system.