计算机工程 ›› 2019, Vol. 45 ›› Issue (7): 315-320.doi: 10.19678/j.issn.1000-3428.0053148

• 开发研究与工程应用 • 上一篇    

考虑不确定区间的电力负荷GELM-WNN预测方法

李廷顺1, 王伟2, 刘泽三2   

  1. 1. 华北电力大学 控制与计算机工程学院, 北京 102206;
    2. 北京中电普华信息技术有限公司, 北京 100192
  • 收稿日期:2018-11-15 修回日期:2018-12-26 出版日期:2019-07-15 发布日期:2019-07-23
  • 作者简介:李廷顺(1977-),男,讲师、博士,主研方向为物联网技术、大数据分析;王伟、刘泽三,硕士。
  • 基金项目:
    北京市自然科学基金(2015BJ0206)。

GELM-WNN Forecasting Method of Power Load Considering Uncertain Interval

LI Tingshun1, WANG Wei2, LIU Zesan2   

  1. 1. School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China;
    2. Beijing China Power Information Technology Co. Ltd., Beijing 100192, China
  • Received:2018-11-15 Revised:2018-12-26 Online:2019-07-15 Published:2019-07-23

摘要: 为提高电力市场负荷预测的可靠性,结合广义极值学习机(GELM)、小波神经网络(WNN)和抽样模型构建技术,提出一种混合概率电力负荷预测方法。考虑预测模型和数据噪声的不确定性,利用小波函数将信息分成具有不同频率属性的子序列,并采用相似的分辨率尺度对其进行分析。使用GELM对WNN进行快速训练,通过迭代自适应抽样技术实现模型的不确定性评估,以概率区间形式输出电力负荷预测。提前24 h预测电力系统的最大负荷,结果表明,该方法的MAPE值低于1.1%,优于灰度值预测和比率估计方法。

关键词: 预测区间, 不确定性, 电力负荷, 小波神经网络, 广义极限学习机

Abstract: In order to improve the reliability of load forecasting in power market,combining Generalized Extreme Learning Machine(GELM),Wavelet Neural Network(WNN) and sampling model construction technology,this paper proposes a hybrid probability power load forecasting method.Considering the uncertainty of the prediction model and data noise,the wavelet function is used to divide the information into sub-sequences with different frequency attributes and to analyze them with similar resolution scales.GELM is used to perform fast training for WNN, and the iterative adaptive sampling technique is used to evaluate the uncertainty of the model.The power load prediction is output in the form of probability intervals.The largest load of the power system is predicted 24 h in advance.The results show that the mean absolute percent error(MAPE) of the proposed method is lower than 1.1%,which is better than those of the gray value prediction model and the ratio estimation method.

Key words: prediction interval, uncertainty, power load, Wavelet Neural Network(WNN), Generalized Extreme Learning Machine(GELM)

中图分类号: