The high initial investment cost of energy storage equipment in the household energy system limits its practical application. Therefore, the capacity configuration of hybrid energy storage is studied to solve this problem. Firstly, the rigid load, flexible load and energy storage equipment load models are constructed respectively; on this basis, the household energy management system model aimed at the lowest daily electricity cost of users is built; finally, an improved artificial bee colony algorithm is proposed to solve the model. Compared with the single energy storage system, the experimental results show that the home energy system equipped with hybrid energy storage can effectively reduce the daily electricity cost of users while meeting the electricity demand of users. By comparing the optimization results of the proposed algorithm with the artificial bee colony algorithm and particle swarm algorithm it is proved that the proposed algorithm has short optimization time, fast convergence speed and is not easy to fall into local optimum.