Abstract: The programming and configuration of hydrogen production, seasonal hydrogen storage and mixed hydrogen-fueled gas turbine system can comprehensively solve the problems of energy storage in the abundant energy season and application in the missing energy season. It can guarantee the power supply reliability of new power system with new energy as the main body. Considering the uncertainty of multi-energy, load and the coupling characteristics of long time scale fluctuations, the minimum mean deviation-entropy weight method and seasonal decomposition method are proposed to establish scenarios of stochastic programming. The minimum mean deviation-entropy weight method is used to select a typical year for multi-energy load systems. The seasonal decomposition method is used to decompose multi-energy and load into long-term trend component, seasonal component and random component. Then, the random component is superimposed with the typical year determined scene to establish the typical scene set of stochastic programming. Aiming at the planning problem of complex coupled systems, a two-stage stochastic programming strategy is proposed. The optimal capacity configuration models of "hydrogen production–seasonal hydrogen storage" system in the abundant energy season and mixed hydrogen-fueled gas turbines in the missing energy season are established. Simulation results show that the proposed method is effective, and the configuration of this system has low carbon value and economic feasibility compared with added configuration of thermal power units.