计算机与现代化

• 人工智能 • 上一篇    下一篇

基于局部高斯过程的短期风速预测

  

  1. (1.苏州大学艺术学院,江苏 苏州 215123; 2.安徽科技学院信息与网络工程学院,安徽 滁州 233100)
  • 收稿日期:2016-06-21 出版日期:2017-01-12 发布日期:2017-01-11
  • 作者简介:常纯(1989-),女,安徽望江人,苏州大学艺术学院助教,硕士,研究方向:人工智能与模式识别,风速及风功率预测; 李德胜(1979-),男,安徽科技学院信息与网络工程学院副教授,博士,研究方向:人工智能与模式识别。
  • 基金资助:
    安徽省自然科学基金资助项目(1308085QF103); 安徽省教育厅自然科学基金资助项目(KJ2013B073)

Short-term Wind Speed Forecasting Based on Local Gaussian Process

  1. (1. School of Arts, Soochow University, Suzhou 215123, China; 
    2. College of Information and Network Engineering, University of Science and Technology of Anhui, Chuzhou 233100, China)
  • Received:2016-06-21 Online:2017-01-12 Published:2017-01-11

摘要: 准确的风速预测对于风电场和电力系统的稳定运行具有重要意义。本文提出一种基于局部高斯过程的短期风速预测方法。首先,把总的训练样本集按固定长度的时间窗划分成许多个子训练集。然后,运用局部高斯过程模型对各个子训练集进行建模,通过最小化训练集的预测误差为优化目标,用改进粒子群算法求取模型的最优超参数。最后,对某实测风速数据进行风速预测分析,结果表明基于局部高斯过程的短期风速预测能有效提高风速预测精度。

关键词: 风速预测, 短期, 局部高斯过程, 改进粒子群算法

Abstract: Wind speed forecasting is very important to the operation of wind power plants and power system. A short-term wind speed forecasting method based on local Gaussian process model is proposed. Firstly, the training sample set is divided into many sub training set according to the fixed length of time window. Secondly, the local Gaussian process model is used to forecast the wind speed of each sub training set. By minimizing prediction error of the training set as the optimization goal, the improved PSO algorithm is used to optimize the hyper parameters. The prediction results show that the proposed method can improve the prediction accuracy.

Key words: wind speed forecasting, short-term, local Gaussian process, improved PSO algorithm

中图分类号: