上海交通大学学报 ›› 2021, Vol. 55 ›› Issue (9): 1080-1086.doi: 10.16183/j.cnki.jsjtu.2020.433

所属专题: 《上海交通大学学报》2021年12期专题汇总专辑 《上海交通大学学报》2021年“能源与动力工程”专题

• • 上一篇    下一篇

基于互信息理论与递归神经网络的短期风速预测模型

王岩a, 陈耀然a, 韩兆龙a,b,c, 周岱a,b,c(), 包艳a,b,c   

  1. a. 上海交通大学 船舶海洋与建筑工程学院, 上海 200240
    b.上海交通大学 海洋工程国家重点实验室, 上海 200240
    c.上海交通大学 水动力学教育部重点实验室,上海 200240
  • 收稿日期:2020-12-25 出版日期:2021-09-28 发布日期:2021-10-08
  • 通讯作者: 周岱 E-mail:zhoudai@sjtu.edu.cn
  • 作者简介:王 岩(1994-),男,河北省保定市人,硕士生,研究方向为机器学习在风电中的应用
  • 基金资助:
    上海市教育委员会科研创新计划自然科学重大项目(2019-01-07-00-02-E00066);国家自然科学基金(51879160);国家自然科学基金(42076210);国家自然科学基金(11772193);上海市“东方学者”计划(TP2017013);上海市曙光学者计划(19SG10)

Short-Term Wind Speed Forecasting Model Based on Mutual Information and Recursive Neural Network

WANG Yana, CHEN Yaorana, HAN Zhaolonga,b,c, ZHOU Daia,b,c(), BAO Yana,b,c   

  1. a. School of Naval Architecture, Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
    b. State Key Laboratory of Ocean Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
    c. Key Laboratory of Hydrodynamics of the Ministry of Education, Shanghai Jiao Tong University, Shanghai 200240, China
  • Received:2020-12-25 Online:2021-09-28 Published:2021-10-08
  • Contact: ZHOU Dai E-mail:zhoudai@sjtu.edu.cn

摘要:

风速的波动性和随机性为风电并网造成安全隐患,提高风速预测精度对于风电系统的稳定和风能发展十分重要.提出一种基于互信息(MI)理论和递归神经网络(RNN)的短期风速预测组合新模型(MI-RNN).该模型利用MI理论选择最优的历史风速序列长度(τ),通过每τ步预测下一时间点风速的方式,将历史风速数据输入RNN中进行模型训练,并由训练后的RNN模型输出最终的风速预测结果.将MI-RNN模型应用于风电场的风速数据集中,与传统机器学习风速预测模型进行比较,以验证模型的预测精度.结果显示,MI-RNN模型的预测精度更高,预测稳定性更强,并且能够准确预测未来风向,有望应用于含空间维度的风电场的风速预测.

关键词: 风速预测, 风能, 互信息理论, 深度学习, 递归神经网络, 风电场

Abstract:

The volatility and randomness of wind speed have caused potential safety hazards to wind power grid integration. Improving wind speed forecasting is crucial to the stability of wind power systems and the development of wind energy. A novel short-term wind speed forecasting model (MI-RNN) was proposed based on mutual information (MI) and recursive neural network (RNN). In this model, the MI theory was introduced to select the optimal length of historical wind speed sequence (τ), and the method of using each τ step to forecast wind speed at the next time point was adopted to input the historical wind speed data into RNN for model training. The final wind speed forecasting result was output by the trained RNN model. Besides, the MI-RNN model was applied to the wind speed dataset collected from a wind farm and the forecasting accuracy was compared with that of the traditional wind forecasting methods. The results show that the MI-RNN model has achieved a higher forecasting accuracy compared with the commonly used wind farm wind speed forecasting methods, and can accurately forecast the future wind direction, which is expected to be applied to wind speed forecasting of wind farms with spatial dimensions.

Key words: wind speed forecasting, wind energy, mutual information (MI), deep learning, recurrent neural network (RNN), wind farm

中图分类号: