Abstract:At present, there are many kinds and complex forms of retail electricity price packages in power transaction, and it is difficult for users to find the most suitable electricity price package for their own electricity demand. Based on the study of the similarity analysis of power user characteristic matrix and power user characteristic, a hybrid electricity package recommendation model is proposed. The model constructs the comprehensive utility function of electricity price package to users based on multi-attribute utility theory. Finally, the optimal price package is recommended based on the hybrid recommendation algorithm, so as to improve the overall operation efficiency of the power system and optimize the allocation of power resources. In the simulation stage, the power data of 50 typical users provided by a power company are analyzed as a case. The results show that the power cost is reduced by 1.47% through the hybrid recommended scheme. The proposed model provides a reference for smart grid power trading.