The invention discloses a photovoltaic power generation user group division method based on multi-factor mapping, and relates to the field of electric power. For a photovoltaic group comprising a plurality of photovoltaic power stations, a simple accumulation method has obvious limitation due to factors such as difficult collection of historical output data of a single power station and incapability of obtaining local meteorological factors. According to the technical scheme, a clustering analysis method is used for partitioning the photovoltaic power of the user under each weather type according to regions, the output consistency of different areas is analyzed, the grouping positions of user photovoltaics are optimized, and the power of each user photovoltaic in the group is predicted byusing the least meteorological data, so that not only is the position selection of the meteorological station optimized to ensure the photovoltaic prediction precision, but also the cost of introducing the meteorological data is reduced, and the economy is improved. Besides, even if a meteorological station is not added, meteorological consistency of the large-scale distributed power stations is grouped, and grouped time-space photovoltaic prediction can be established through the meteorological consistency distributed power stations. Accuracy of prediction is effectively improved.