arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.12401cs.LG
收藏

基于长短期记忆网络(LSTM)的风速预测与可视化

Wind Speed Prediction and Visualization Using Long Short-Term Memory Networks (LSTM)

Univ. of the District of Columbia(哥伦比亚特区大学)

Md Amimul Ehsan, Amir Shahirinia, Nian Zhang, Timothy Oladunni

摘要:

气候变化是本世纪最令人关注的问题之一。发电产生的排放是将关注提升到下一个水平的关键因素。可再生能源在全球范围内广泛分布,但主要挑战之一是以更翔实的方式了解其特征。本文提出了风速预测,简化风电场规划和可行性研究。12种人工智能算法被用于从收集的气象参数进行风速预测。比较了模型的性能,以确定风速预测精度。结果显示,深度学习方法,长短期记忆(LSTM)优于其他模型,最高准确率为97.8%。

英文摘要:

Climate change is one of the most concerning issues of this century. Emission from electric power generation is a crucial factor that drives the concern to the next level. Renewable energy sources are widespread and available globally, however, one of the major challenges is to understand their characteristics in a more informative way. This paper proposes the prediction of wind speed that simplifies wind farm planning and feasibility study. Twelve artificial intelligence algorithms were used for wind speed prediction from collected meteorological parameters. The model performances were compared to determine the wind speed prediction accuracy. The results show a deep learning approach, long short-term memory (LSTM) outperforms other models with the highest accuracy of 97.8%.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑