[1]方娜,余俊杰,李俊晓,等.注意力机制下的EMD-GRU短期电力负荷预测[J].华侨大学学报(自然科学版),2021,42(6):817-824.[doi:10.11830/ISSN.1000-5013.202008003]
　FANG Na,YU Junjie,LI Junxiao,et al.Short-Term Power Load Forecasting Under EMD-GRU Attention Mechanism[J].Journal of Huaqiao University(Natural Science),2021,42(6):817-824.[doi:10.11830/ISSN.1000-5013.202008003]
点击复制

注意力机制下的EMD-GRU短期电力负荷预测()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第42卷
期数:
2021年第6期
页码:
817-824
栏目:
出版日期:
2021-11-12

文章信息/Info

Title:
Short-Term Power Load Forecasting Under EMD-GRU Attention Mechanism
文章编号:
1000-5013(2021)06-0817-08
作者:
方娜1; 2;  余俊杰1; 2;  李俊晓1; 2;  陈浩1; 2
1. 湖北工业大学 太阳能高效利用及储能运行控制湖北省重点实验室, 湖北 武汉 430068;2. 湖北工业大学 湖北省电网智能控制与装备工程技术研究中心, 湖北 武汉 430068
Author(s):
FANG Na1; 2;  YU Junjie1; 2;  LI Junxiao1; 2;  CHEN Hao1; 2
1. Hubei Key Laboratory for High-Efficiency Utilization and Storage Operation Control of Energy Storage System, Hubei University of Technology, Wuhan 430068, China; 2. Hubei Power Grid Intelligent Control and Equipment Engineering Technology Research Center, Hubei University of Technology, Wuhan 430068, China
关键词:
短期负荷预测;  经验模态分解;  门控循环单元;  注意力机制
Keywords:
short-term load forecasting;  empirical mode decomposition;  gated recurrent unit;  mechanism of attention
分类号:
TP183
DOI:
10.11830/ISSN.1000-5013.202008003
文献标志码:
A
摘要:
为进一步提高短期电力负荷预测精度,构建一种基于注意力机制的经验模态分解(EMD)和门控循环单元(GRU)混合模型,对时间序列的短期负荷进行预测.首先,对负荷序列进行EMD,将数据重构成多个分量;再通过GRU提取各分量中时序数据的潜藏特征;经注意力机制突出关键特征后,分别对各分量进行预测;最后,将各分量的预测结果叠加,得到最终预测值.仿真结果表明:相对于BP网络模型、支持向量机(SVR)模型、GRU网络模型和EMD-GRU模型,基于EMD-GRU-Attention的混合预测模型能取得更高的预测精度,有效地提高短期电力负荷预测精度.
Abstract:
In order to further improve the accuracy of short-term power load forecasting, a mixed model of empirical mode decomposition(EMD)and gated recurrent unit(GRU)based on attention mechanism is constructed to forecast short-term load of time series. Firstly, EMD is performed on the load sequence, reconstitute data into multiple components. Then, GRU is used to extract the underlying characteristics of time series data in each component. After the key features are highlighted by combining the attention mechanism, each component is predicted respectively. Finally, the forecast results of each component are superimposed to obtain the final predictive value. The simulation results show that the EMD-GRU-Attention mixed prediction model has higher forecast accuracy compared with BP network mode, support vector machine(SVR)mode, GRU network mode and EMD-GRU mode, and it can effectively improve the accuracy of short-term power load forecasting.

参考文献/References:

[1] KHWAJA A S,ZHANG Xiaoying,ANPALAGAN A,et al.Boosted neural networks for improved short-term electric load forecasting[J].Electric Power Systems Research,2017,143:431-437.DOI:10.1016/j.epsr.2016.10.067.
[2] 夏家盛,吉培荣.负荷预测指数平滑法“厚近薄远”规律研究[J].电力学报,2019,34(1):23-29.DOI:10.13357/j.cnki.jep.002770.
[3] 甘中学,喻想想,许裕栗,等.基于周期性ARMA-SVR模型的空调冷热负荷预测[J].控制工程,2020,27(2):380-385.DOI:10.14107/j.cnki.kzgc.170759.
[4] 俱鑫,刘尚科,苟瑞欣,等.基于ARMA和Kalman Filter的需求响应基线负荷预测[J].电子设计工程,2020,28(18):175-180.DOI:10.14022/j.issn1674-6236.2020.18.039.
[5] MOEENI H,BONAKDARI H.Impact of normalization and input on ARMAX-ANN model performance in suspended sediment load prediction[J].Water Resources Management,2018,32(3):1-19.DOI:10.1007/s11269-017-1842-z.
[6] 邢晓敏,何铁新,郑雪瑞,等.基于ANN-dropout的配电网可靠性预测方法[J].南方电网技术,2019,13(2):66-73.DOI:10.13648/j.cnki.issn1674-0629.2019.02.010.
[7] 陈亮,王震,王刚.深度学习框架下LSTM网络在短期电力负荷预测中的应用[J].电力信息与通信技术,2017,15(5):8-11.DOI:10.16543/j.2095-641x.electric.power.ict.2017.05.002.
[8] 张宇帆,艾芊,林琳,等.基于深度长短时记忆网络的区域级超短期负荷预测方法[J].电网技术,2019,43(6):1884-1892.DOI:10.13335/j.1000-3673.pst.2018.2101.
[9] RAHMAN A,SRIKUMAR V,SMITH A D.Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks[J].Applied Energy,2018,212:372-385.DOI:10.1016/j.apenergy.2017.12.051.
[10] 李鹏,何帅,韩鹏飞.基于长短期记忆的实时电价条件下智能电网短期负荷预测[J].电网技术,2018,42(12):4045-4052.DOI:10.13335/j.1000-3673.pst.2018.0433.
[11] 黄发良,连亚飞.Senti-LSTM: 一个基于递归神经网络的情感分析模型[J].福建师范大学学报(自然科学版),2020,36(1):12-18.DOI:10.12046/j.issn.1000-5277.2020.01.003.
[12] KANG Ke,SUN Hongbin,ZHANG Chengkang,et al.Short-term electrical load forecasting method based on stacked auto-encoding and GRU neural network[J].Evolutionary Intelligence,2019,12(3):385-394.DOI:10.1007/s12065-018-00196-0.
[13] 姚程文,杨苹,刘泽健.基于CNN-GRU混合神经网络的负荷预测方法[J].电网技术,2020,44(9):3416-3424.DOI:10.13335/j.1000-3673.pst.2019.2058.
[14] 魏骜,茅大钧,韩万里,等.基于EMD和长短期记忆网络的短期电力负荷预测研究[J].热能动力工程,2020,35(4):203-209.DOI:10.16146/j.cnki.rndlgc.2020.04.028.
[15] 汤庆峰,刘念,张建华,等.基于EMD-KELM-EKF与参数优选的用户侧微电网短期负荷预测方法[J].电网技术,2014,38(10):2691-2699.DOI:10.13335/j.1000-3673.pst.2014.10.012.
[16] BEDI J,TOSHNIWAL D.Empirical mode decomposition based deep learning for electricity demand forecasting[J].IEEE Access,2018,6:49144-49156.DOI:10.1109/ACCESS.2018.2867681.
[17] 彭文,王金睿,尹山青.电力市场中基于Attention-LSTM的短期负荷预测模型[J].电网技术,2019,43(5):745-751.DOI:10.13335/j.1000-3673.pst.2018.1554.
[18] 赵兵,王增平,纪维佳,等.基于注意力机制的CNN-GRU短期电力负荷预测方法[J].电网技术,2019,43(12):4370-4376.DOI:10.13335/j.1000-3673.pst.2019.1524.
[19] 李昭昱,艾芊,张宇帆,等.基于Attention机制的LSTM神经网络超短期负荷预测方法[J].供用电,2019,36(1):17-22.DOI:10.19421/j.cnki.1006-6357.2019.01.003.

相似文献/References:

[1]李志农,刘立州.分数阶经验模态分解方法在机械故障诊断中应用[J].华侨大学学报(自然科学版),2010,31(4):367.[doi:10.11830/ISSN.1000-5013.2010.04.0367]
　LI Zhi-nong,LIU Li-zhou.Application of the Method of Fractional Empirical Mode Decomposition to Machine Fault Diagnosis[J].Journal of Huaqiao University(Natural Science),2010,31(6):367.[doi:10.11830/ISSN.1000-5013.2010.04.0367]
[2]陈建灿,刘晓梅.运用EMD分形盒维数的电梯机械故障诊断[J].华侨大学学报(自然科学版),2013,34(5):494.[doi:10.11830/ISSN.1000-5013.2013.05.0494]
　CHEN Jian-can,LIU Xiao-mei.Application of EMD and Box Dimension in Fault Diagnosis of Elevator Machinery[J].Journal of Huaqiao University(Natural Science),2013,34(6):494.[doi:10.11830/ISSN.1000-5013.2013.05.0494]

备注/Memo

备注/Memo:
收稿日期: 2020-08-06
通信作者: 方娜(1979-),女,讲师,博士,主要从事电网运行监测、电力负荷的研究.E-mail:fangna@hbut.edu.cn.
基金项目: 国家自然科学基金青年科学基金资助项目(51809097); 湖北省教育厅科学技术研究计划指导性项目(B2018044); 太阳能高效利用湖北省协同创新中心开放基金资助项目(HBSKFQN2016007); 湖北工业大学博士科研启动基金项目(BSQD14029)http://www.hdxb.hqu.edu.cn
更新日期/Last Update: 2021-11-20