摘要详情

ID / 提交时间

265 / 2021-11-07 22:53:17

标题

Research on wind turbine power curve modeling method based on regression analysis and prediction model

关键字

wind power curve; Quartile method; Data cleaning; Regression analysis prediction model

主题及专题

Renewable energy system > Renewable energy system planning, design, and operation

状态

全文被拒

作者

Yanfeng Tian / Shenyang University of Technology School of Electrical Engineering

Shun Wang / Shenyang University of Technology School of Electrical Engineering

Zhe Wang / Shenyang University of Technology School of Electrical Engineering

Yang Liu / Shenyang University of Technology School of Electrical Engineering

Zuoxia Xing / Shenyang University of Technology School of Electrical Engineering

摘要

Wind power curve plays an important role in wind power prediction, wind turbine condition monitoring, wind energy potential prediction and wind turbine selection. In the actual operation of wind turbine, abnormal values will appear in the original data due to accidents such as wind abandonment, power limitation and blade damage. These abnormal values often affect the accuracy of wind power curve modeling. Based on the quartile method, this paper cleans the abnormal value data of wind power, effectively eliminates the data deviating from the main concentration trend, and reduces the impact of abnormal data on the rationality of mathematical modeling. The gradient lifting regression analysis prediction model, KNN regression analysis prediction model, decision tree regression analysis prediction model, random forest regression analysis prediction model and extreme random forest regression analysis model are studied. The average absolute error, root mean square error and determination coefficient are used as evaluation indexes. The experimental results show that, Compared with other methods, the gradient lifting regression analysis prediction model has higher prediction accuracy and can accurately reflect the characteristics of the real wind power curve.

重要日期

会议日期

07月11日

2023

至

08月18日

2023
11月10日 2021

初稿截稿日期
12月10日 2021

注册截止日期
12月11日 2021

报告提交截止日期

主办单位

IEEE IAS

承办单位

IEEE IAS Student Chapter of Southwest Jiaotong University (SWJTU)
IEEE IAS Student Chapter of Huazhong University of Science and Technology (HUST)
IEEE PELS (Power Electronics Society) Student Chapter of HUST