About this document
Li 2022 J. Phys. Conf. Ser. 2195 012028 by meklitsol1 is a document available to read on EtoBox.
This paper presents an improved power load forecasting model called GS-XGBoost, which enhances prediction accuracy and interpretability using SHAP for model analysis. The model was tested on an enterprise electricity consumption dataset in Jiangsu, demonstrating superior performance compared to other machine learning models. Key factors influencing electricity load were identified, providing valuable insights for power system management and decision-making.
- Author
- meklitsol1
- Language
- EN