Abstarct: The rapid growth of urban populations and the development of large residential mega-complexes have highlighted the urgent need for a sustainable, economical, and reliable energy supply. On the other hand, the inherent intermittency of renewable resources such as wind and solar energy poses a major challenge to their utilization as primary energy sources. In this regard, the integration of energy storage systems (ESS) is essential to balance power supply and demand, enhance network reliability, and reduce dependency on fossil fuels. The main objective of this study is to determine the optimal capacities of battery and hydrogen-baxsed energy storage systems within the frxamework of an autonomous hybrid microgrid for large residential complexes. To achieve this goal, mathematical models are developed for the major system components, including photovoltaic (PV) panels, wind turbines, diesel generators, batteries, and hydrogen subsystems. The PV model is formulated baxsed on solar irradiance and ambient temperature data; the wind turbine output is calculated using the turbine’s power curve and local wind speed; and the diesel generator model is defined according to the relationship between electrical load and fuel consumption. In the storage subsystem, the charging and discharging dynamics of the battery, along with efficiency and operational constraints, are considered. The hydrogen system model includes electrolyzer operation, hydrogen storage, and electricity generation by a fuel cell. The power balance equation of the microgrid is formulated such that, at each time step, the total power from renewable sources, the diesel generator, the battery, and the fuel cell equals the load demand and storage consumption. The problem is then formulated as a multi-objective optimization task aiming to minimize both the Loss of Load Probability (LOLP) and the Cost of Energy (COE). A Multi-Objective Self-Adaptive Differential Evolution (MOSaDE) algorithm is employed to solve this complex, nonlinear problem due to its high search efficiency in multidimensional spaces. Simulation results indicate that the combined utilization of battery and hydrogen storage systems significantly improves system reliability and reduces total energy cost compared to single-storage configurations. Furthermore, the renewable energy contribution to load supply increases, leading to a noticeable reduction in diesel generator usage and associated emissions. Sensitivity analysis reveals that diesel fuel price and the capital cost of storage systems have the greatest impact on optimal sizing results. Overall, the findings confirm that optimal design and sizing of hybrid energy storage systems provide an effective and practical solution for achieving sustainable and economical energy supply in large residential mega-complexes.