基于数据预处理的ARIMA模型超短期风电功率预测
Ultra-short Term Wind Power Prediction Based on ARIMA Model Based on Data Preprocessing
魏晓钢 1张建瑞 1杨燕平 1马栓平 1李洪林1
作者信息
- 1. 中核汇能(内蒙古)能源有限公司,内蒙古呼和浩特 010011
- 折叠
摘要
为了提高超短期风电功率预测的精确度和稳定性,文章提出了基于预处理数据的ARIMA时间序列自回归差分移动平均模型风电超短期预测算法.以黑龙江省某风电场的实测数据为例,对测风塔数据进行预处理,对风电场数据异常值进行处理,并对风电功率影响因素相关性进行分析,对所得到的数据进行差分处理,从而适应ARIMA模型的预测.结果表明,此方法可以有效提高预测精度和覆盖率.
Abstract
In order to improve the accuracy and stability of short-term wind power forecasting,a wind power ultra-short-term forecasting algorithm based on preprocessed data and ARIMA time series autoregressive integrated moving average model is proposed in this paper.Taking the actual measurement data from a wind farm in Heilongjiang Province as an example,the wind tower data is initially preprocessed,addressing anomalies in the wind farm data and analyzing the correlation of factors influencing wind power output.The obtained data is differentially processed to suit the requirements of the ARIMA model for prediction.Results indicate that this method effectively enhances prediction accuracy and coverage.
关键词
风电功率预测/ARIMA模型/时间序列预测Key words
wind power forecasting/ARIMA model/time series forecasting引用本文复制引用
出版年
2024
NETL
NSTL
万方数据