Big data cleaning model of smart grid based on Tensor Tucker decomposition

Big data cleaning model of smart grid based on Tensor Tucker decomposition

연구 분야: Databases

학회: 2020 International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE)

The traditional big data cleaning model processes data in the form of template matching, which is limited by the data dimension. It not only needs a large calculation space, but also has poor data cleaning effect. To solve the above problems, a smart grid big data cleaning model based on tensor Tucker decomposition is proposed. KNN algorithm is used to detect abnormal data in power grid big data, and the missing data is filled and removed. The tensor Tucker decomposition is used to compress the data and reduce the data dimension. Based on the neural network structure, the data cleaning model is constructed. Compared with the traditional model, the average effective cleaning rate of the cleaning model after tensor Tucker decomposition is 94.16%, which has good data cleaning effect.