Distributed power distribution network electricity price adjusting method based on convolutional network and collaborative filtering

The invention provides a distributed power distribution network electricity price adjustment method based on a convolutional network and collaborative filtering. The method comprises the steps of 1, performing feature extraction according to power distribution network data; 2, constructing a scoring matrix; 3, singular value decomposition; 4, calculating the similarity degree; 5, confirming a to-be-recommended user; and 6, selecting recommended users according to the sequence. According to the method, output prediction of the power distribution network containing the distributed power supplies is realized by adopting a convolutional neural network method, data feature extraction is realized, output abundant time periods of the power distribution network containing the distributed power supplies are predicted, and electricity price adjustment is performed by utilizing a prediction result. The electricity price preferential information is pushed to the user by adopting a collaborative filtering method based on