王子乐, 王子谋, 蔡莹, 谭晶, 黄弦超. 基于长短期记忆神经网络组合算法的短期电力负荷预测[J]. 现代电力, 2023, 40(2): 201-209. DOI: 10.19725/j.cnki.1007-2322.2021.0293
引用本文: 王子乐, 王子谋, 蔡莹, 谭晶, 黄弦超. 基于长短期记忆神经网络组合算法的短期电力负荷预测[J]. 现代电力, 2023, 40(2): 201-209. DOI: 10.19725/j.cnki.1007-2322.2021.0293
WANG Ziyue, WANG Zimou, CAI Ying, TAN Jing, HUANG Xianchao. Short-term Load Forecasting Based on Long Short-term Memory Network Combination Algorithm[J]. Modern Electric Power, 2023, 40(2): 201-209. DOI: 10.19725/j.cnki.1007-2322.2021.0293
Citation: WANG Ziyue, WANG Zimou, CAI Ying, TAN Jing, HUANG Xianchao. Short-term Load Forecasting Based on Long Short-term Memory Network Combination Algorithm[J]. Modern Electric Power, 2023, 40(2): 201-209. DOI: 10.19725/j.cnki.1007-2322.2021.0293

基于长短期记忆神经网络组合算法的短期电力负荷预测

Short-term Load Forecasting Based on Long Short-term Memory Network Combination Algorithm

  • 摘要: 短期电力负荷具有不平稳、随机性强等特点,传统的负荷预测方法在建模中常表现出一定的局限性。为提高预测精度,提出了一种基于互补集合经验模态分解(complement-ary ensemble empirical mode decomposition, CEEMD)、长短期记忆 (long short-term memory, LSTM) 神经网络和多元线性回归 (multiple linear regression, MLR) 方法组合而成的CEEMD-LSTM-MLR短期电力负荷预测方法。首先将电力负荷数据通过CEEMD分解为高频分量和低频分量;将复杂的高频分量通过经贝叶斯优化的LSTM神经网络进行预测,周期性的低频分量通过MLR方法进行预测,最后将各分量叠加重构得到最终预测结果。通过算例分析,一方面将不同分解方法进行对比,一方面将不同模型进行对比并探究贝叶斯调参对结果的影响,验证了所提模型更具可靠性与准确性。

     

    Abstract: Short-term power load possesses such features as instability and randomness, so traditional load forecasting methods of present a certain limitation during the modeling. To improve forecasting accuracy, a short-term load forecasting method based on the combination of complementary ensemble empirical mode decomposition (abbr. CEEMD), long short-term memory (abbr. LSTM) and multiple linear regression (abbr. MLR) was proposed. Firstly, by means of CEEMD the power load data was composed into high-frequency component and low-frequency component, then the complex high-frequency component was predicted by Bayesian optimized LSTM neural network, and the periodical low-frequency component was predicted by MLR. Finally, each component was superposed and reconstructed to obtain the final prediction result. In the computing example, in one hand different decomposition methods were compared, and in the other hand different models and the influence of Bayesian parameter adjustment on prediction results were compared. Thus, both reliability and accuracy of the proposed method are verified.

     

/

返回文章
返回