Forecasting Renewable Energy Generation Using Random Forest Analysis
學年 113
學期 2
發表日期 2025-06-16
作品名稱 Forecasting Renewable Energy Generation Using Random Forest Analysis
作品名稱（其他語言）
著者 Chien Hsin Wu; Yao Ting Tseng; Wen Fang Lo; Yu Hsiang Haung
作品所屬單位
出版者
會議名稱 International Association for Management of Technology: 34th IAMOT
會議地點 Montréal, Canada
摘要 Renewable energy forecasting is critical for sustainable energy development and grid stability. This study applies a Random Forest model to analyze the contribution of different renewable energy sources to total energy generation in Taiwan. The results indicate that geothermal and solar energy have the highest impact, while offshore wind, onshore wind, and conventional hydropower contribute less significantly. This analysis aligns with previous research and highlights the necessity of optimizing renewable energy strategies. By leveraging machine learning techniques, policymakers can gain deeper insights into renewable energy trends and make data-driven decisions to enhance energy security and efficiency. The study also suggests that further improvements in wind energy forecasting could contribute to better grid stability. Future research could explore hybrid machine learning approaches to refine predictive accuracy and model robustness.
關鍵字 Renewable Energy; Forecasting; Random Forest; Energy Policy; Machine Learning
語言 en
收錄於
會議性質 國際
校內研討會地點 無
研討會時間 20250616~20250619
通訊作者 Chien-Hsin Wu
國別 CAN
公開徵稿
出版型式
出處 IAMOT 2025 conference proceedings
SDGS 永續城市與社區,可負擔的潔淨能源