Comprehensive Energy Online Service Recommendation Algorithm based on Random Forest
Peng Wu, Fubao Li, Jing Cai, Yongze Zhang, Zhangjian Kang, Zhao Tang Luo, Zeyong Gao, Zhendong Zhu · 2021 6th Asia Conference on Power and Electrical Engineering (ACPEE) · 2021
Under the environment of fierce market competition and the upgrading of the power market, the integrated energy service industry will gradually become a new trend in future power development. Integrated energy online e-commerce service is a key component of future grid smart energy, and it is also an important way for the transition of energy sources from grid energy integration services to multi-energy service providers' competitive supply strategy transformation. An effective integrated energy service recommendation method plays an important role for integrated energy companies to occupy an advantageous position in the energy competition. According to the user's interest characteristics and the user's behavior data in the system, this paper analyzes the user's interest preferences. Part of the data is taken to establish a user interest map and perform spectral clustering, and the clustered data is imported into the random forest model for scoring prediction training. Part of the data is taken to establish a user interest map and perform spectral clustering, and the clustered data is imported into the random forest model for scoring prediction training.