基于CEEMDAN与改进LSTM的短期光伏出力预测  

Short-Term Photovoltaic Output Prediction Based onCEEMDAN and Improved LSTM

作　　者：黄浚哲 印宇涵 汤明轩 梅飞[1] HUANG Junzhe;YIN Yuhan;TANG Mingxuan;MEI Fei(College of Energy and Electrical Engineering,Hohai University,Nanjing 211100,China)

机构地区：[1]河海大学能源与电气学院,江苏南京211100

出　　处：《电器与能效管理技术》2023年第10期36-43,共8页Electrical & Energy Management Technology

基　　金：国家重点研发计划项目(2022YFE01406)。

摘　　要：为了提高光伏出力的预测精度,提出了一种将自适应噪声完备集成经验模态分解(CEEMDAN)算法与改进的长短时记忆(LSTM)神经网络相结合的短期光伏功率预测模型。首先,利用CEEMDAN算法对光伏功率序列进行分解,得到子序列分量。然后,使用改进的LSTM神经网络对各个子序列分量分别进行预测,用粒子群(PSO)算法优化LSTM神经网络隐藏层神经元个数、学习率与训练次数,同时使用注意力机制优化训练过程中的概率分配。最后,叠加各分量预测结果,得到最终的预测值。算例分析表明,所提模型的3个预测评估指标MAE、RMSE、R2均为最佳,验证了所提模型的优越性。In order to improve the accuracy of photovoltaic output power prediction,a model that combines complete ensemble empirical mode decomposition with adaptive noise(CEEMDAN)algorithm with improved long short-term memory(LSTM)neural network is proposed to predict short-term photovoltaic power.Firstly,the photovoltaic power sequence is decomposed by CEEMDAN algorithm and the subsequence components are obtained.Then,improved LSTM neural network is used to predict each subsequence component.Particle swarm optimization(PSO)algorithm is used to optimize the number of hidden layer neurons,learning rate and training times of LSTM neural network.The attention mechanism is used to optimize the probability distribution in the process of training LSTM neural network.Finally,the final predicted value is obtained by adding the predicted results of each subsequence component.Example analysis shows that prediction evaluation indexes of the proposed model MAE,RMSE and R 2 are all the best by comparison with other algorithms,which can verify the superiority of the proposed model.

关 键 词：光伏出力预测 自适应噪声完备集成经验模态分解 长短时记忆神经网络 粒子群优化 注意力机制 

分 类 号：TM615[电气工程—电力系统及自动化]