基于CEEMDAN-QPSO-LSTM的短期电力负荷预测  

CEEMDAN-QPSO-LSTM-based Short-term Electric Load Forecasting

作　　者：王献鑫 WANG Xianxin(Anhui University of Science and Technology,Huainan 232000,China)

机构地区：[1]安徽理工大学,安徽淮南232000

出　　处：《电工技术》2024年第20期54-58,共5页Electric Engineering

摘　　要：为了实现高精度的短期电力负荷预测,设计了一种短期电力负荷预测算法,该算法由完全自适应噪声集合经验模态分解(CEEMDAN)、量子粒子群算法(QPSO)和长短期记忆网络(LSTM)构成。该算法首先通过CEEMDAN将数据处理成数个模态分量,然后应用基于QPSO改进的LSTM进行预测,最后叠加重构输出结果。经过实验论证,所提出的预测方法相比其他算法可以取得更高的预测精度和更好的拟合效果。In order to achieve high-precision short-term electric load forecasting,a new method combining complete ensemble empirical mode decomposition with adaptive noise(CEEMDAN),quantum particle swarm optimization(QPSO)and long short-term memory(LSTM)was proposed by this work.The algorithm was designed to first processed the data into several modal components through CEEMDAN,and then used the QPS-based modified LSTM for prediction to superimpose reconstructed output results.The proposed method was domenstrated by experimen to achieve higher prediction accuracy and better fitting effect than other algorithms.

关 键 词：短期电力负荷预测 CEEMDAN QPSO LSTM 

分 类 号：TM714[电气工程—电力系统及自动化]