AUTHOR=Li Zhihao , Chen Zhongli 

TITLE=Short-term load forecasting based on CEEMDAN-FE-ISSA-LightGBM model

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2023.1111786

DOI=10.3389/fenrg.2023.1111786

ISSN=2296-598X

ABSTRACT=To address the problems of low load forecasting accuracy due to the strong non-stationarity of electric loads, this paper proposes a short-term load forecasting method based on a combination of the complete ensemble empirical modal decomposition adaptive noise method-fuzzy entropy (CEEMDAN-FE) and the Light Gradient Boosting Machine (LightGBM) optimized by the improved sparrow search algorithm (ISSA). First, the original data are decomposed by the CEEMDAN algorithm to obtain the eigenmodal components (IMFs) and residual values. Second, the obtained sequences are entropy reorganized by fuzzy entropy, and thus new sequences are obtained. Third, the new sequences are input into the ISSA-LightGBM model for training and prediction. The ISSA algorithm can realize parameter optimization of the LightGBM model to make the data match the model better, and the predicted values of each grouping of the model output are superimposed to obtain the final predicted values. Finally, the effect is compared by the error function, and the comparison results are used to test the performance of the algorithm. The experiments show that the MAPE of the proposed algorithm is 0.64%, which is much lower than that of other models, and the training time is reduced by 38.42%, which improves the prediction efficiency, and the com-parison results prove the feasibility of the proposed algorithm.