In the research on the capacity ratio of wind-solar hybrid systems, the randomness of the actual output power of wind-solar power generation is not considered. Therefore, a capacity allocation method of a wind-solar hybrid system based on stochastic programming was proposed in this paper. Considering the randomness of the actual output power of wind-solar power generation, a capacity allocation model of the wind-solar hybrid system was established based on stochastic programming theory, aiming at stable power output. The model was solved by particle swarm optimization (PSO) algorithm based on stochastic simulation technology, and the optimal wind-solar capacity ratio of the wind-solar hybrid system was discussed. Taking the actual wind-solar resources of a certain place in Qionghai city as an example, Matlab was used for simulation verification. The results show that when 53% wind power is combined with 47% photoelectricity, the output power of the wind-solar complementary system is the most stable. Besides, the proposed method was applied to different regions, combining with the distribution of China's wind-solar resources, and finally, the optimal ratio of wind-solar capacity in different regions of China was obtained. This method provides a certain reference for the design and planning of the wind-solar complementary system and the comprehensive adjustment of energy resources among urban areas in the future, and also provides a new idea for the study of wind-solar capacity ratio.