Aiming at the influence of generation-load uncertainties on the capacity configuration of the photovoltaic storage system, a multi-objective optimization method considering uncertainties in meteorological parameters, building disturbance factors, personnel density, and air-conditioning system was proposed, constructing a multi-objective optimization model of the rural residential photovoltaic storage system with the objectives of minimizing the annual operating cost of the system and maximizing the self-consumption rate (SCR) and the self-supply rate (SSR), and the modified adaptive weighted particle swarm optimization algorithm was used to solve the problem. The results show that the relative deviations of the maximum and minimum values of the average and peak loads of the building are 41.08% and 71.65%, respectively, and the relative deviations of the maximum and minimum values of the peak power, average power, and annual power generation of PV are 3.55%, 23.65%, and 23.91%, respectively. The optimal combination of photovoltaic and battery capacity can be found using multi-objective optimization methods. By adopting the SCR and SSR with the highest frequency of occurrence within a relative deviation of 7% as representative values for the technical performance indicators of the PV-storage system, the capacity allocation indicators for photovoltaic and battery storage in rural residential buildings in the Changsha area are derived.