Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (1): 237-242.DOI: 10.11772/j.issn.1001-9081.2020060930

Special Issue: 第八届中国数据挖掘会议(CCDM 2020)

• China Conference on Data Mining 2020 (CCDM 2020) • Previous Articles     Next Articles

Ultra-short-term wind power prediction based on empirical mode decomposition and multi-branch neural network

MENG Xinyu1, WANG Ruihan1, ZHANG Xiping2, WANG Mingjie3, QIU Gang4, WANG Zhengxia5   

  1. 1. School of Information Science and Engineering, Chongqing Jiaotong University, Chongqing 400074, China;
    2. China Datang Corporation Renewable Energy Science and Technology Research Institute Company Limited, Beijing 100043, China;
    3. Integrated Electronic Systems Laboratory Company Limited, Jinan Shandong 250104, China;
    4. State Grid Xinjiang Electric Power Company, Urumqi Xinjiang 830002, China;
    5. School of Computer Science and Cyberspace Security, Hainan University, Haikou Hainan 570228, China
  • Received:2020-05-31 Revised:2020-09-03 Online:2021-01-10 Published:2020-09-15
  • Supported by:
    This work is partially supported by the Natural Science Foundation of Chongqing (cstc2018jcyjAX0398), the Research Starting Foundation of Hainan University (KYQD(ZR)20022).

基于经验模态分解与多分支神经网络的超短期风功率预测

孟鑫禹1, 王睿涵1, 张喜平2, 王明杰3, 丘刚4, 王政霞5   

  1. 1. 重庆交通大学 信息科学与工程学院, 重庆 400074;
    2. 中国大唐集团新能源科学技术研究院有限公司, 北京 100043;
    3. 积成电子股份有限公司, 济南 250104;
    4. 国网新疆电力公司, 乌鲁木齐 830002;
    5. 海南大学 计算机与网络空间安全学院, 海口 570228
  • 通讯作者: 王政霞
  • 作者简介:孟鑫禹(1992-),男,河北沧州人,硕士研究生,主要研究方向:机器学习、风功率预测;王睿涵(1994-),男,重庆人,硕士研究生,主要研究方向:机器学习、风机故障诊断;张喜平(1977-),女,重庆人,副教授,博士,主要研究方向:工业物联网平台、工业物联网安全;王明杰(1988-),男,山东临沂人,工程师,硕士,主要研究方向:新能源发电;丘刚(1977-),男,新疆乌鲁木齐人,高级工程师,硕士,主要研究方向:自动化、新能源预测;王政霞(1977-),女,山东日照人,教授,博士,CCF会员,主要研究方向:机器学习、数据挖掘、图像处理。
  • 基金资助:
    重庆市自然科学基金资助项目(cstc2018jcyjAX0398);海南大学科研启动基金资助项目(KYQD(ZR)20022)。

Abstract: Wind power prediction is an important basis for the monitoring and information management of wind farms. Ultra-short-term wind power prediction is often used to balance load and optimize scheduling and requires high prediction accuracy. Due to the complex environment of wind farm and many uncertainties of wind speed, the wind power time series signals are often non-stationary and random. Recurrent Neural Network (RNN) is suitable for time series tasks, but the non-periodic and non-stationary time series signals will increase the difficulty of network learning. To overcome the interference of non-stationary signal in the prediction task and improve the prediction accuracy of wind power, an ultra-short-term wind power prediction method combining empirical model decomposition and multi-branch neural network was proposed. Firstly, the original wind power time series signal was decomposed by Empirical Mode Decomposition (EMD) to reconstruct the data tensor. Then, the convolution layer and Gated Recurrent Unit (GRU) layer were used to extract the local features and trend features respectively. Finally, the prediction results were obtained through feature fusion and full connection layer. Experimental results on the dataset of a wind farm in Inner Mongolia show that compared with AutoRegressive Integrated Moving Average (ARIMA) model, the proposed method improves the prediction accuracy by nearly 30%, which verifies the effectiveness of the proposed method.

Key words: ultra-short-term prediction of wind power, Empirical Mode Decomposition (EMD), neural network, convolution, Gated Recurrent Unit (GRU), feature fusion

摘要: 风功率预测是实现风电场监控及信息化管理的重要基础,风功率超短期预测常用于平衡负荷、优化调度,对预测精度有较高的要求。由于风电场环境复杂、风速不确定性因素较多,风功率时序信号往往具有非平稳性和随机性。循环神经网络(RNN)适用于时间序列任务,但无周期、非平稳的时序信号会增加网络学习的难度。为了克服非平稳信号在预测任务中的干扰,提高风功率预测精度,提出了一种结合经验模态分解与多分支神经网络的超短期风功率预测方法。首先将原始风功率时序信号通过经验模态分解(EMD)以重构数据张量,然后用卷积层和门控循环单元(GRU)层分别提取局部特征和趋势特征,最后通过特征融合与全连接层得到预测结果。在内蒙古某风场实测数据集上的实验结果表明,与差分整合移动平均自回归(ARIMA)模型相比,所提方法在预测精度方面有将近30%的提升,验证了所提方法的有效性。

关键词: 风功率超短期预测, 经验模态分解, 神经网络, 卷积, 门控循环单元, 特征融合

CLC Number: