Exception analysis and treatment of operation data in green building

Along with the continuous improvement of various properties of green building, the amount of data is more and more big. The operation and maintenance of the green buildings need to use these data to analyze and make decisions, and the premise of the data analysis is that the data collected by each system is accurate. In this paper, the data in the PV power generation system and the air conditioning system of the green building were analyzed and pre-treatment, using the Cook-distance algorithm based on the deletion model and improved LOF algorithm to analysis abnormal according to the characteristics of the data, and establishing a real-time detection model of abnormal data.