In order to reduce the impact of wind power, photovoltaic and other renewable energy output prediction uncertainty on the economics of day-ahead optimized dispatching operations, a wind-solar-storage joint optimized dispatching method that takes into account the uncertainty of wind and solar energy is proposed. Firstly, based on the generative adversarial networks (GAN) and affinity propagation (AP), the uncertainty characteristics of wind and solar output are converted into a typical set of deterministic scenarios, and based on the wind and solar prediction curves generate wind and solar output typical scenarios. Secondly, with the goal of optimizing the improvement of the net load fluctuation and minimizing the cost of the system operation, a wind-solar-storage joint optimized dispatching model is constructed. Finally, the proposed scheme is simulated and analyzed. The results show that the proposed method can effectively reduce net load fluctuations, improve wind and solar consumption rates, and reduce system operating costs.