长短时记忆网络在风电短期功率预测中的应用与效果评估  

Application and Effect Evaluation of Short Term Memory Network in Short Term Power Forecast of Wind Power

作　　者：党琳 张宇轩 张悦欣 刘书生 李金林 孙华高 卞晓雪 王宝刚 DANG Lin;ZHANG Yuxuan;ZHANG Yuexin;LIU Shusheng;LI Jinlin;SUN Huagao;BIAN Xiaoxue;WANG Baogang(Nantional Energy(Shandong)New Energy Co.,Ltd.,Ji'nan 250000,China;Longyuan(Beijing)New Energy Engingeering Technology Co.,Ltd.,Beijing 100034,China)

机构地区：[1]国家能源(山东)新能源有限公司,济南250000 [2]龙源(北京)新能源工程技术有限公司,北京100034

出　　处：《风力发电》2023年第6期30-34,共5页Wind Power

摘　　要：本研究致力于研究风电场短期功率预测,这是应对可再生能源变化性的关键问题之一。短期功率预测在电力系统调度和可再生能源管理中将起到重要作用。为了提高预测准确性,我们采用了深度学习模型中的长短时记忆网络(LSTM)以及其改进方法。本研究将详细分析LSTM的原理和结构,并利用山东某风电场半年的历史数据作为实际案例,评估了模型在实际风电场预测中的性能。实验结果显示,改进的LSTM模型在风电场短期功率预测中表现出更高的准确性,尤其在夏季高温季节的准确率提升明显。这些结果强调了深度学习技术在解决风电功率预测问题中的巨大潜力,有望提高电力系统的可靠性和可再生能源资源的利用率。This study focuses on short-term power prediction for wind farms,which is one of the key issues in dealing with the variability of renewable energy sources.Short-term power forecasting plays an important role in power system scheduling and renewable energy management.In order to improve the prediction accuracy,we use the short term memory network(LSTM)in the deep learning model and its improvement method.This study will analyze the principle and structure of LSTM in detail,and use the historical data of a Shandong wind farm for half a year as a practical case to evaluate the performance of the model in the actual wind farm prediction.The experimental results show that the improved LSTM model has higher accuracy in the short-term power prediction of wind farms,especially in the summer high temperature season.These results highlight the great potential of deep learning techniques to solve wind power forecasting problems,which are expected to improve the reliability of power systems and the utilization of renewable energy resources.

关 键 词：风电功率预测 深度学习 长短时记忆网络(LSTM) 模型评估 

分 类 号：TM6[电气工程—电力系统及自动化]