Cluster Feature based Multivariate Data Analysis and Recovery Method for Renewable Energy Operation and Control

Renewable energy sources is becoming the main form of energy supply side in the energy internet. To improve the absorption capacity and operation analysis level of large-scale distributed renewable energy, it is important to guarantee the accuracy of renewable energy operation data. Based on multi-scenario application analysis, this paper proposed a data quality analysis, abnormal data detection and repair method for renewable energy operation data. Firstly, the renewable energy data types are analyzed, the K-means clustering analysis method is used step by step to form data characteristic curve for data evaluation, and a diagnosis method for abnormal data. Then rough set theory is used to reduce the associated attributes of the operation data value, and establish the importance between data attribute types and data values. Finally, a predictive decision-making attributes forecasting tree is constructed to repair the abnormal data. A numerical load case verifies the effectiveness of the method.