摘要
【目的】海上风电对于实现碳达峰、碳中和目标具有重要意义,但其功率预测较为困难,为此提出了一种融合时序卷积网络(temporal convolutional network,TCN)与Transformer架构的海上风电功率预测新方法。【方法】首先,引入离散余弦变换(discrete cosine transform,DCT)技术,旨在有效提取时间序列数据的频域特征,充分挖掘频域特性来优化特征权重的分配。在此基础上,构建了TCN-Transformer复合模型,该模型能够充分整合时域与经过DCT处理的频域信息,实现对数据的深度学习与精准预测。【结果】选取某海上风电场的2组实际运行数据开展对比实验,结果表明,所提方法不仅在特征提取方面表现出色,还显著地提升了发电功率预测精度,充分验证了其有效性与应用价值。【结论】融合了DCT技术的TCN-Transformer模型在海上风电功率预测方面展现出了卓越的预测性能,相较于其他对比模型,其预测精度得到了显著提升,为海上风电场的高效运行与优化管理提供了有力支持。
[Objectives]Offshore wind power is of great significance for achieving carbon peaking and carbon neutrality goals,yet its power prediction remains challenging.To address this issue,this study proposes a novel offshore wind power prediction method integrating temporal convolutional network(TCN)with the Transformer framework.[Methods]Firstly,discrete cosine transform(DCT)technology is incorporated to effectively extract frequency-domain features from time-series data,optimizing feature weight allocation by fully exploiting frequencydomain characteristics.Based on this,a hybrid TCN-Transformer model is constructed,which is capable of comprehensively integrating both time-domain and DCT processed frequency-domain information,enabling the deep learning and accurate prediction of the data.[Results]Comparative experiments are conducted using two sets of actual operational data from an offshore wind farm.The results show that the proposed method not only performs well in feature extraction but also significantly improves the accuracy of power prediction,fully verifying its effectiveness and application value.[Conclusions]The TCN-Transformer model integrated with DCT technology demonstrates exceptional prediction performance in offshore wind power prediction.Compared to other benchmark models,it achieves a significant improvement in prediction accuracy.This approach provides robust support for the efficient operation and optimal management of offshore wind farms.
作者
王曦
陈心怡
WANG Xi;CHEN Xinyi(School of Computer Science and Technology,Harbin University of Science and Technology,Harbin 150080,Heilongjiang Province,China)
出处
《发电技术》
2025年第6期1123-1132,共10页
Power Generation Technology
基金
国家重点研发计划项目(2023YFB4403500)。
关键词
海上风电
功率预测
离散余弦变换
时序卷积网络
机器学习
深度学习
可再生能源
offshore wind power
power prediction
discrete cosine transform
temporal convolutional network
machine learning
deep learning
renewable energy
