沈建良,来骏,张翼,王建锋,仲赞,杨平
SHEN Jianliang,LAI Jun,ZHANG Yi,WANG Jianfeng,ZHONG Zan,YANG Ping

• 1:国网浙江省电力有限公司湖州供电公司
• 2:四川大学电气工程学院

摘要(Abstract)：

为降低用户侧负荷的波动性和随机性对负荷预测精度的影响，提出一种基于ACMD（自适应啁啾模态分解）和含Attention机制的BiGRU-Attention（双向门控循环单元）短期负荷预测模型。首先采用ACMD将负荷时间序列分解为多个相对规律的子分量；然后使用BiGRU模型分别对各子分量进行预测并相加得到最终预测结果，为突出重要信息的影响，在BiGRU模型中引入Attention机制赋予BiGRU网络隐含状态相应的权重；使用麻雀搜索算法对模型超参数进行优化选择，以减小模型超参数选择不当的影响。采用公开数据集进行算例分析，并分别与单一模型和组合模型进行比较，结果表明该方法具有更好的预测效果。
To lessen the impact of fluctuation and randomness of the user-side load on the load forecasting accuracy, a BiGRU-Attention(bidirectional gated recurrent unit with attention) short-term load forecasting model based on ACMD(adaptive chirp mode decomposition) and the Attention mechanism is proposed. Firstly, ACMD is used to decompose the load time series into several relatively regular subcomponents; then, the BiGRU model is used to predict the subcomponents and sum them up to obtain the final prediction results. To highlight the influence of important information, the Attention mechanism is introduced into the BiGRU model to give corresponding weights to the implied states of the BiGRU network. The sparrow search algorithm is used for the optimal selection of model hyperparameters to reduce the impact of misselection of model hyperparameters. An open data set is used for example analysis that is compared with a single model and combined model respectively. The results show that the method is superior in prediction.

关键词(KeyWords)： 负荷预测;双向门控循环单元;自适应啁啾模态分解;麻雀搜索算法;注意力机制
load forecasting;BiGRU;ACMD;sparrow search algorithm;Attention mechanism

Abstract:

Keywords:

基金项目(Foundation): 国网浙江省电力有限公司科技项目（5211UZ2000K2）

作者(Author): 沈建良,来骏,张翼,王建锋,仲赞,杨平
SHEN Jianliang,LAI Jun,ZHANG Yi,WANG Jianfeng,ZHONG Zan,YANG Ping

参考文献(References)：

• [1]赵洋，王瀚墨，康丽，等.基于时间卷积网络的短期电力负荷预测[J].电工技术学报，2022,37(5):1242-1251.ZHAO Yang,WANG Hanmo,KANG Li,et al.Temporal convolution network-based short-term electrical load forecasting[J]. Transactions of China Electrotechnical Society,2022,37(5):1242-1251.
• [2]林珊，王红，齐林海，等.基于条件生成对抗网络的短期负荷预测[J].电力系统自动化，2021,45(11):52-60.LIN Shan,WANG Hong,QI Linhai,et al.Short-term load forecasting based on conditional generative adversarial network[J].Automation of Electric Power Systems,2021,45(11):52-60.
• [3]刘友波，吴浩，刘挺坚，等.集成经验模态分解与深度学习的用户侧净负荷预测算法[J].电力系统自动化，2021,45(24):57-64.LIU Youbo,WU Hao,LIU Tingjian,et al.User-side net load forecasting method integrating empirical mode decomposition and deep learning[J]. Automation of Electric Power Systems,2021,45(24):57-64.
• [4]赵军，苏鹏伟，安青松，等.面向分布式能源系统优化的负荷预测研究进展[J].电力系统及其自动化学报，2018,30(8):12-18.ZHAO Jun,SU Pengwei,AN Qingsong,et al.Progress in researches on load forecasting technology for optimization of distributed energy system[J].Proceedings of the CSUEPSA,2018,30(8):12-18.
• [5]李冬辉，尹海燕，郑博文.基于MFOA-GRNN模型的年电力负荷预测[J].电网技术，2018,42(2):585-590.LI Donghui,YIN Haiyan,ZHENG Bowen.Annual power load forecasting based on MFOA-GRNN model[J].Power System Technology,2018,42(2):585-590.
• [6]唐俊熙，曹华珍，高崇，等.一种基于时间序列数据挖掘的用户负荷曲线分析方法[J].电力系统保护与控制，2021,49(5):140-148.TANG Junxi,CAO Huazhen,GAO Chong,et al.A new user load curve analysis method based on time series data mining[J].Power System Protection and Control,2021,49(5):140-148.
• [7] YUAN S,CHEN L,SUN G,et al. Analysis of electric load data based on time series[J]. Advances in Applied Mathematics,2016,5(2):214-224.
• [8]张淑清，李君，姜安琦，等.基于FPA-VMD和BiLSTM神经网络的新型两阶段短期电力负荷预测[J].电网技术，2022,46(8):3269-3279.ZHANG Shuqing,LI Jun,JIANG Anqi,et al. A novel two-stage model based on FPA-VMD and BiLSTM neural network for short-term power load forecasting[J].Power System Technology,2022,46(8):3269-3279.
• [9] LI Z L,LI Y Z,LIU Y,et al.Deep learning based densely connected network for load forecasting[J].IEEE Transactions on Power Systems,2021,36(4):2829-2840.
• [10]蔡秋娜，潮铸，苏炳洪，等.基于一种新型鲁棒损失的神经网络短期负荷预测方法[J].电网技术，2020,44(11):4132-4139.CAI Qiuna,CHAO Zhu,SU Binghong,et al.Short-term load forecasting method based on A novel robust loss neural network algorithm[J]. Power System Technology,2020,44(11):4132-4139.
• [11] KONG X Y,LI C,ZHENG F,et al.Improved deep belief network for short-term load forecasting considering demand-side management[J]. IEEE Transactions on Power Systems,2020,35(2):1531-1538.
• [12] KONG W C,DONG Z Y,JIA Y W,et al.Short-term residential load forecasting based on LSTM recurrent neural network[J].IEEE Transactions on Smart Grid,2019,10(1):841-851.
• [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.YAO Chengwen,YANG Ping,LIU Zejian.Load forecasting method based on CNN-GRU hybrid neural network[J].Power System Technology,2020,44(9):3416-3424.
• [14]吴云，雷建文，鲍丽山，等.基于改进灰色关联分析与蝙蝠优化神经网络的短期负荷预测[J].电力系统自动化，2018,42(20):67-72.WU Yun,LEI Jianwen,BAO Lishan,et al. Short-term load forecasting based on improved grey relational analysis and neural network optimized by bat algorithm[J].Automation of Electric Power Systems,2018,42(20):67-72.
• [15] WANG Y Y,KONG Y,TANG X F,et al.Short-term industrial load forecasting based on ensemble hidden Markov model[J].IEEE Access,2020,8:160858-160870.
• [16]马得银，孙波，刘澈.基于天气信息的短期冷热电负荷联合预测方法[J].电网技术，2021,45(3):1015-1022.MA Deyin,SUN Bo,LIU Che. Short-term cooling and heating power load prediction method based on multiweather information[J].Power System Technology,2021,45(3):1015-1022.
• [17]张雲钦，程起泽，蒋文杰，等.基于EMD-PCA-LSTM的光伏功率预测模型[J].太阳能学报，2021,42(9):62-69.ZHANG Yunqin,CHENG Qize,JIANG Wenjie,et al.Photovoltaic power prediction model based on emd-pcalstm[J].Acta Energiae Solaris Sinica,2021,42(9):62-69.
• [18]孙辉，杨帆，高正男，等.考虑特征重要性值波动的MIBILSTM短期负荷预测[J].电力系统自动化，2022,46(8):95-103.SUN Hui,YANG Fan,GAO Zhengnan,et al.Short-term load forecasting based on mutual information and Bidirectional long short-term memory network considering fluctuation in importance values of features[J]. Automation of Electric Power Systems,2022,46(8):95-103.
• [19]刘俊，赵宏炎，刘嘉诚，等.基于协整-格兰杰因果检验和季节分解的中期负荷预测[J].电力系统自动化，2019,43(1):73-80.LIU Jun,ZHAO Hongyan,LIU Jiacheng,et al.Mediumterm load forecasting based on cointegration-granger causality test and seasonal decomposition[J]. Automation of Electric Power Systems,2019,43(1):73-80.
• [20]盛四清，金航，刘长荣.基于VMD-WSGRU的风电场发电功率中短期及短期预测[J].电网技术，2022,46(3):897-904.SHENG Siqing,JIN Hang,LIU Changrong. Short-term and mid-short-term wind power forecasting based on VMD-WSGRU[J].Power System Technology,2022,46(3):897-904.
• [21] CHEN Q M,CHEN J,LANG X,et al. Diagnosis of nonlinearity-induced oscillations in process control loops based on adaptive chirp mode decomposition[C]//2020American Control Conference(ACC). July 1-3,2020,Denver,CO,USA.IEEE,2020:2772-2777.
• [22]乔石，王磊，张鹏超，等.基于模态分解及注意力机制长短时间网络的短期负荷预测[J].电网技术，2022,46(10):3940-3951.QIAO Shi,WANG Lei,ZHANG Pengchao,et al.Shortterm load forecasting by long-and short-term temporal networks with attention based on modal decomposition[J].Power System Technology,2022,46(10):3940-3951.
• [23]曾囿钧，肖先勇，徐方维，等.基于CNN-BiGRU-NN模型的短期负荷预测方法[J].中国电力，2021,54(9):17-23.ZENG Youjun,XIAO Xianyong,XU Fangwei,et al. A short-term load forecasting method based on CNNBiGRU-NN model[J].Electric Power,2021,54(9):17-23.
• [24] XUE J K,SHEN B.A novel swarm intelligence optimization approach:sparrow search algorithm[J].Systems Science&Control Engineering,2020,8(1):22-34.