• CSCD核心库收录期刊
  • 中文核心期刊
  • 中国科技核心期刊

电力建设 ›› 2022, Vol. 43 ›› Issue (2): 98-108.doi: 10.12204/j.issn.1000-7229.2022.02.012

• 智能电网 • 上一篇    下一篇

基于完整自适应噪声集成经验模态分解的LSTM-Attention网络短期电力负荷预测方法

刘文杰(), 刘禾(), 王英男(), 杨国田(), 李新利()   

  1. 华北电力大学控制与计算机工程学院,北京市 102206
  • 收稿日期:2021-04-29 出版日期:2022-02-01 发布日期:2022-03-24
  • 作者简介:刘文杰(1997),男,硕士研究生,主要研究方向为深度学习和综合能源等,E-mail: wenjie@ncepu.edu.cn;
    刘禾(1961),男,教授,硕士生导师,主要研究方向为模式识别、锅炉燃烧优化及人工智能的应用等,E-mail: liuhe99@sina.com;
    王英男(1992),女,博士研究生,主要研究方向为模式识别与智能系统、火电厂大气污染物控制技术,E-mail: yingnan@ncepu.edu.cn;
    杨国田(1962),男,教授,博士生导师,主要研究方向为模式识别与智能系统、火电厂燃烧优化等,E-mail: ygt@ncepu.edu.cn;
    李新利(1973),女,副教授,硕士生导师,主要研究方向为模式识别与智能系统、图像处理等,E-mail: lixinli@ncepu.edu.cn
  • 基金资助:
    中央高校基本科研业务费专项资金资助项目(2018QN052)

Short-Term Power Load Forecasting Method Based on CEEMDAN and LSTM-Attention Network

LIU Wenjie(), LIU He(), WANG Yingnan(), YANG Guotian(), LI Xinli()   

  1. School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
  • Received:2021-04-29 Online:2022-02-01 Published:2022-03-24
  • Supported by:
    Fundamental Research Funds for the Central Universities(2018QN052)

摘要:

短期电力负荷预测在电网安全运行和制定合理调度计划方面发挥着重要作用。为了提高电力负荷时间序列预测的准确度,提出了一种由完整自适应噪声集成经验模态分解(complete ensemble empirical mode decomposition with adaptive noise, CEEMDAN)和基于注意力机制的长短期记忆神经网络(long short-term memory network based on attention mechanism, LSTM-Attention)相结合的短期电力负荷预测模型。完整自适应噪声集成经验模态分解有效地将负荷时间序列分解成多个层次规律平稳的本征模态分量,并通过神经网络模型预测极大值,结合镜像延拓方法抑制边界效应,提高分解精度,同时基于注意力机制的长短期记忆神经网络自适应地提取电力负荷数据输入特征并分配权重进行预测,最后各预测模态分量叠加重构后获得最终预测结果。通过不同实际电力负荷季节数据分别进行实验,并与其他电力负荷预测模型结果分析进行比较,验证了该预测方法在电力负荷预测精度方面具有更好的性能。

关键词: 负荷预测, 长短期记忆神经(LSTM)网络, 注意力机制, 经验模态分解(EMD), 边界效应

Abstract:

Short-term power load forecasting plays an important role in the safe operation of power grid and the formulation of reasonable dispatching plan. In order to improve the accuracy of power load time-series forecasting, a short-term power load forecasting model based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and short-term memory neural network based on attention mechanism (LSTM-Attention) is proposed in this paper. The complete ensemble empirical mode decomposition with adaptive noise effectively decomposes the load time series into multiple levels of regular and stable eigenmode components, and suppresses the boundary effect through the neural network model prediction maximum combined with the image continuation method to improve the decomposition accuracy. At the same time, the long short-term memory neural network based on attention mechanism adaptively extracts the input characteristics of power load data and assigns weights for prediction. Finally, the final prediction results are obtained after superposition and reconstruction of each prediction modal component. Experiments are carried out on different seasonal data of actual power load, and the results of other power load forecasting models are analyzed and compared to verify that the forecasting method has better performance in power load forecasting accuracy.

Key words: load forecasting, long-short term memory (LSTM), attention mechanism, empirical mode decomposition (EMD), boundary effect

中图分类号: