南方电网技术2026，Vol.20Issue(5)：71-80,102,11.DOI:10.13648/j.cnki.issn1674-0629.2026.05.008
基于多头自注意力特征变换和CNN-LSTM的超短期风电功率预测
Ultra-Short-Term Wind Power Forecasting Based on Multi-Head Self-Attention Feature Transformation and CNN-LSTM
摘要
Abstract
Wind power generation is significantly influenced by environmental factors,exhibiting high randomness and volatility,making it difficult to accurately predict the amount of electricity generated.To address this,an ultra-short-term wind power forecast-ing model combining multi-head self-attention,convolutional neural network,and long short-term memory(AM-CNN-LSTM)is proposed.The multi-head self-attention mechanism assigns weights based on the varying importance of historical wind power and meteorological data,generating key feature representations and mitigating interference.The convolutional neural network extracts complex spatial patterns and local dependencies between wind power and meteorological factors.The long short-term memory network captures long-term dependencies and dynamic changes in time series,enhancing forecasting accuracy.The results demonstrate that under the optimal time window of T=4 h,the model achieves mean absolute error,root mean square error,and mean absolute percentage error of 13.45%,19.48%and 3.78%,respectively,It outperforms comparative methods such as LSTM,CNN and CNN-LSTM.A comparison of forecasting errors for the optimal time window of different models over the next eight sample points reveals that the proposed model offers significant advantages in ultra-short-term forecasting accuracy and stability.Variable analysis indicates that the combined use of multiple meteorological variables significantly outperforms single-variable,uncovering the complex interactions and nonlinear relationships among meteorological factors.关键词
风电功率预测/多头自注意力机制/卷积神经网络/长短时记忆网络/参数优化器/时间窗口Key words
wind power forecasting/multi-head self-attention mechanism/convolutional neural network/long short-term memory network/parameter optimizer/time window分类
信息技术与安全科学引用本文复制引用
虞伟,黄浩,金晨星,陈菁伟,周玲,王逢浩,何强..基于多头自注意力特征变换和CNN-LSTM的超短期风电功率预测[J].南方电网技术,2026,20(5):71-80,102,11.基金项目
国家自然科学基金资助项目(52007174) （52007174）
国网浙江省电力有限公司科技项目(5211ZS220001). Supported by the National Natural Science Foundation of China(52007174) （5211ZS220001）
the Science and Technology Project of State Grid Zhejiang Electric Power Co.,Ltd.(5211ZS220001). （5211ZS220001）
