首页|基于二次模态分解的LSTM短期电力负荷预测

基于二次模态分解的LSTM短期电力负荷预测

扫码查看
原文链接
  • 万方数据
  • 维普
为进一步提高短期电力负荷的预测精度,需要更深层次发掘负荷数据中隐藏的非线性关系.提出一种基于信号分解技术的二次模态分解的长短期记忆神经网络(long short-term memory network,LSTM)用于电力负荷的短期预测.所提算法先对原始负荷序列进行自适应噪声的完全集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN),再将CEEMDAN分解后分量中的强非平稳分量进行变分模态分解(variational mode decomposition,VMD),同时用中心频率法对VMD分解个数进行优化,然后将两次分解后得到的负荷子序列送入LSTM中进行预测,并将所得分量预测结果进行叠加.结果表明,本文所提方法对短期电力负荷预测结果精度和模型性能都有较大提升.
Short-term Power Load Forecasting Based on Quadratic Mode Decomposition through LSTM
To further improve the accuracy of short-term power load prediction,it is necessary to explore the hidden nonlinear rela-tionships in load data at a deeper level.A short-term memory neural network based on quadratic modal decomposition of signal decom-position technology was proposed for short-term power load forecasting.Firstly,the proposed algorithm decomposed the original load da-ta using the complete ensemble empirical mode decomposition with adaptive noise(CEEMDAN)algorithm.Secondly,the strong non-stationary components in the CEEMDAN decomposed components were decomposed by the variational mode decomposition(VMD)algo-rithm.at the same time,the number of VMD decomposition was optimized by using the central frequency method,and then the load subsequences obtained after two decompositions were fed into long short-term memory network(LSTM)for prediction,and the predicted results of the obtained components were overlaid.The results indicate that the method proposed in this article has significantly improved the accuracy of short-term power load forecasting results and model performance.

short-term power load predictionquadratic mode decompositioncomplete ensemble empirical mode decomposition with adaptive noise(CEEMDAN)variational mode decomposition(VMD)long short-term memory network(LSTM)

张淑娴、江文韬、陈玉花、杨晓东、金丰、白莉

展开 >

国家电网有限公司大数据中心,北京 100052

合肥工业大学电气与自动化工程学院,合肥 230009

短期负荷预测 二次模态分解 自适应噪声的完全集合经验模态分解(CEEMDAN) 变分模态分解(VMD) 长短期记忆网络(LSTM)

国家电网大数据中心项目

SGSJ0000YYJS2200101

2024

10.12404/j.issn.1671-1815.2302728

科学技术与工程
中国技术经济学会

科学技术与工程

CSTPCD北大核心
影响因子：0.338
ISSN：1671-1815
年,卷(期)：2024.24(7)
  • 24