AUTHOR=Wang Shiqian , Han Ding , Hua Yuanpeng , Wang Yuanyuan , Wang Lei , Liu Yang TITLE=An improved selective ensemble learning approach in enabling load classification considering base classifier redundancy and class imbalance JOURNAL=Frontiers in Energy Research VOLUME=Volume 10 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2022.987982 DOI=10.3389/fenrg.2022.987982 ISSN=2296-598X ABSTRACT=In current modern power systems, to analyze the behaviors of the end users is of great significance to improve the system security, stability, and economy. The load classification provides an efficient way to implement the awareness of the user behaviors. However, due to the developments of the data collection, transmission, and storage technologies, the volumes of the load data keep increasing whilst the structure and knowledge hidden in the data become complicated. Therefore, the parallelized ensemble learning has been widely employed in the recent load classification researches. Although the positive performances of ensemble learning have been proved, two critical issues including class imbalance and base classifier redundancy still raise challenges of improving the classification accuracy and saving the computational resource. Therefore, to solve the issues this paper presents an improved selective ensemble learning approach in enabling load classification considering base classifier redundancy and class imbalance. Firstly, a Gaussian SMOTE based on density clustering (GSDC) is introduced to handle the class imbalance, which aims at achieving higher classification accuracy. Secondly, the classifier pruning strategy and the optimization strategy of the ensemble learning are further introduced to handle the base classifier redundancy. The experimental results indicate that combining with the popular classifiers, the presented approach shows effectiveness for serving the load classification tasks.