AUTHOR=Wang Ziyao , Li Huaqiang , Liu Yamei , Wu Shuning 

TITLE=An improved deep learning algorithm in enabling load data classification for power system

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2022.988183

DOI=10.3389/fenrg.2022.988183

ISSN=2296-598X

ABSTRACT=Load behaviours significantly impact the planning, dispatching, and operation of the modern power systems. Load classification has been proved as one of the most effective ways of analyzing the load behaviours. However, due to the issues of data collection, transmission, and storage in current power systems, data missing problems frequently occur, which prevents the load classification tasks from precisely identifying the load classes. Simultaneously, because of the diversities of the load categories, different loads contribute various amounts of data, which causes the class imbalance issue. The traditional load data classification algorithms are lack of the ability to solve the above issues, which may deteriorate the load classification accuracy. Therefore, this paper proposed an improved deep learning algorithm based on load classification approach in terms of raising the classification performances with solving the data missing and class imbalance issues. Firstly, LATC (Low-rank Autoregressive Tensor Completion) algorithm is employed to solve the data missing issue to improve the quality of the training dataset. Borderline-SMOTE algorithm is further adopted to improve the class distribution in the training dataset to improve the training performances of biGRU (Bidirectional Gate Recurrent Unit). Afterwards, to improve the classification accuracy in the classification task, biGRU algorithm, combined with the attention mechanism, is employed as the underlying infrastructure. The experimental results show the effectiveness of the proposed approach.