Energy consumption demand side energy consumption prediction method based on DBN deep belief network

The invention relates to an energy consumption demand side energy consumption prediction method based on a DBN deep belief network. The method comprises the following steps: collecting historical energy consumption data of different energy consumption categories of an energy consumption demand side as an original data set; on the basis of a BIRTH clustering algorithm, generalization processing is carried out, a plurality of clustering results of the original data of different energy consumption categories are obtained, and energy consumption labels are added to all the clustering results; constructing a DBN deep belief network, dividing original data into a plurality of groups of training sample sets according to energy consumption type labels of a clustering result, taking each group of training sample sets as input of the network, setting a plurality of corresponding working groups, and training each working group through each group of training sample sets to obtain a plurality of working groups; obtaining