With the rapid development of microgrid (MG) technology, the microgrids in a certain area interconnect and constitute a microgrid group, which can mutually supply each other to meet regional power supply requirements. Uncertain factors such as wind speed, light intensity and load affect the operation of the microgrid group. This paper proposes a microgrid group energy management method that considers uncertainty. According to the probability density function of the wind speed, light intensity and the load, the uncertainty model of wind turbine (WT) output, photovoltaic (PV) output and load is derived, and the more realistic prediction value is obtained by the uncertainty model. First, the energy trade between the microgrids. Then, by using multi-time scale technique, the day-ahead scheduling plan is determined based on the predicted data, and on top of that, the plan is optimized based on the latest data. The particle swarm optimization (PSO) is used to minimize the operating costs of the microgrid group. The effectiveness of the proposed energy management method is verified by case simulation.