基于EMD-GM-Elman神经网络组合模型的新型电力系统新能源发电量及负荷需求量预测
Forecasting of the New Energy Generation and Load Demand in the Novel Power System Based on EMD-GM-Elman Neural Network Combined Model
赵汉超 1从兰美 1刘杰 1韩子月 1胡宁宁 1潘广源 1夏远洋2
作者信息
- 1. 临沂大学自动化与电气工程学院,山东临沂 276000
- 2. 雅砻江流域水电开发有限公司,四川成都 610000
- 折叠
摘要
针对新能源发电量预测中单一模型精度不足的问题,提出了一种EMD-GM-Elman(empirical mode decomposition-grey model-elman)神经网络组合模型.该模型通过经验模态分解(empirical mode decomposition,EMD)预处理数据,提取局部特征;利用灰色预测模型预测各本征模态函数(intrinsic mode functions,IMF),结果输入Elman神经网络捕捉动态特征;最终通过数据重构得出预测结果.仿真结果显示,该模型预测精度从传统模型的 58.1%提高到 65.14%.
Abstract
Aiming to address insufficient accuracy of the single model in the prediction of new energy power generation,a combined EMD-GM-Elman(Empirical Mode Decomposition-Grey Model-Elman)neural network model is proposed in this paper.The model pre-processes the data through Empirical Mode Decomposition(EMD)to extract local features,and predicts the Intrinsic Mode Functions(IMFs)using the gray prediction model,and inputs the results into the Elman neural network to capture the dynamic features,and then reconstructs the results through data reconstruction to obtain the prediction results.Finally,the prediction results are obtained through data reconstruction.The simulation results show that the prediction accuracy of the model is improved from 58.1%to 65.14%of the traditional model.
关键词
新型电力系统/新能源发电量预测/负荷需求预测/灰色理论/Elman神经网络/经验模态分解Key words
new power systems/new energy generation forecasting/load demand forecasting/Grey theory/Elman neural network/empirical modal decomposition引用本文复制引用
出版年
2024
NETL
NSTL
万方数据