Prediction method for adjustable load based on EEMD-BiLSTM

doi:10.3969/j.issn.2097-0706.2022.09.005

Abstract

Abstract:

To achieve the goals of carbon peaking and carbon neutrality,adjustable load has become emerging regulation resources of the power grid. In order to solve the mode aliasing phenomenon in EMD and obtain good time perception of load series,an adjustable load prediction method that combines EEMD with BiLSTM is proposed. The working principles of EEMD and BiLSTM were expounded. The preprocessed adjustable load series was decomposed by EEMD algorithm, and then the decomposed component data and original data were used for load prediction modeling and reconstruction, respectively. Experimental results show that EEMD-BiLSTM can effectively express the relation between time sequence and adjustable load with a high accuracy.

Key words: dual carbon target, ensemble empirical mode decomposition（EEMD）, bidirectional long short term memory（BiLSTM）, adjustable load, load forecasting, demand response

CLC Number:

TK01

LI Bin, HU Chunjin, WANG Jing. Prediction method for adjustable load based on EEMD-BiLSTM[J]. Integrated Intelligent Energy, 2022, 44(9): 33-39.

Figures/Tables 9

Fig.1

Fig.2

Table 1

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Table 2

References 17

[1]	国家发展改革委,国家能源局. 关于完善能源绿色低碳转型体制机制和政策措施的意见[R]. 2022.
[2]	国家电网有限公司. 能源互联网情境下负荷调控能力提升工作三年行动计划[R]. 2022.
[3]	张建寰, 吉莹, 陈立东. 深度学习在电力负荷预测中的应用[J]. 自动化仪表, 2019, 40(8):8-12.
	ZHANG Jianhuan, JI Ying, CHEN Lidong. Application of deep learning in power load forecasting[J]. Automation Instrumentation, 2019, 40(8):8-12.
[4]	陆继翔, 张琪培, 杨志宏, 等. 基于CNN-LSTM混合神经网络模型的短期负荷预测方法[J]. 电力系统自动化, 2019, 43(8):131-137.
	LU Jixiang, ZHANG Qipei, YANG Zhihong, et al. Short-term load forecasting method based on CNN-LSTM hybrid neural network model[J]. Automation of Electric Power Systems, 2019, 43(8):131-137.
[5]	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):1745-1751.
	PENG Wen, WANG Jinrui, YIN Shanqing. Short-term load forecasting model based on Attention-LSTM in power market[J]. Power Grid Technology, 2019, 43(5):1745-1751.
[6]	吕海灿, 王伟峰, 赵兵, 等. 基于Wide & Deep LSTM模型的短期台区负荷预测[J]. 电网技术, 2020, 44(2):428-436.
	LV Haican, WANG Weifeng, ZHAO Bing, et al. Short-term station load forecasting based on Wide & Deep LSTM model[J]. Power Grid Technology, 2020, 44(2):428-436.
[7]	刘建华, 李锦程, 杨龙月, 等. 基于EMD-SLSTM的家庭短期负荷预测[J]. 电力系统保护与控制, 2019, 47(6):40-47.
	LIU Jianhua, LI Jincheng, YANG Longyue, et al. Household short-term load forecasting based on EMD-SLSTM[J]. Electric Power System Protection and Control, 2019, 47(6):40-47.
[8]	邓带雨, 李坚, 张真源, 等. 基于EEMD-GRU-MLR的短期电力负荷预测[J]. 电网技术, 2020, 44(2):593-602.
	DENG Daiyu, LI Jian, ZHANG Zhenyuan, et al. Short-term power load forecasting based on EEMD-GRU-MLR[J]. Power Grid Technology, 2020, 44(2):593-602.
[9]	HUANG E, STEVER R L. A new view of nonstationary time series analysis:Empirical mode deconmposition and Hilbert spectral analysis[J]. Proceedings of SPIE—The International Society for Optical Engineering, 2000, 4056:197-209.
[10]	WU Z, HUANG N E. Ensemble empirical mode decomposition:A noised-assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1(1):1-41. doi: 10.1142/S1793536909000047
[11]	HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735. doi: 10.1162/neco.1997.9.8.1735
[12]	JIA Y C, LI G L, et al. A novel denoising method for vibration signal of hob spindle based on EEMD and grey theory[J]. Measurement, 2021, 169:108490. doi: 10.1016/j.measurement.2020.108490
[13]	YANG M, WANG J. Adaptability of financial time series prediction based on BiLSTM[J]. Procedia Computer Science, 2022, 199:18-25. doi: 10.1016/j.procs.2022.01.003
[14]	侯回位, 郑东健, 刘永涛, 等. 基于EEMD-SE-LSTM的混凝土坝变形监测模型[J]. 水利水电科技进展, 2022, 42(1):61-66.
	HOU Huiwei, ZHENG Dongjian, LIU Yongtao, et al. Deformation monitoring model of concrete dams based on EEMD-SE-LSTM[J]. Advances in Science and Technology of Water Resources, 2022, 42(1):61-66.
[15]	董军, 陈正鹏, 窦熙皓, 等. 基于EEMD-FCM的需求响应用户负荷曲线分类研究[J]. 电力科学与工程, 2021, 37(10):45-54.
	DONG Jun, CHEN Zhengpeng, DOU Xihao, et al. Research on demand response of user load curve classification based on EEMD-FCM method[J]. Electric Power Science and Engineering, 2021, 37(10):45-54.
[16]	张栋栋, 陈洁, 李洋. 基于VMD-SE和BiLSTM在短期负荷预测应用[J]. 现代电子技术, 2021, 44(23):155-159.
	ZHANG Dongdong, CHEN Jie, LI Yang. In short-term load forecasting based on VMD-SE and BiLSTM application[J]. Journal of Modern Electronic Technology, 2021, 44(23):155-159.
[17]	赵征, 周孜钰, 南宏钢. 基于VMD的CNN-BiLSTM超短期风电功率多步区间预测[J/OL]. 华北电力大学学报(自然科学版):1-7.(2021-09-07)[2022-02-23]. http://kns.cnki.net/kcms/detail/13.1212.TM.20210907.1610.004.html.
	ZHAO Zheng, ZHOU Ziyu, NAN Honggang. Multi-step interval prediction of ultra-short-term wind power based on CNN-BiLSTM based on VMD[J/OL]. Journal of North China Electric Power University(Natural Science Edition):1-7.(2021-09-07)[2022-02-23]. http://kns.cnki.net/kcms/detail/13.1212.TM.20210907.1610.004.html.

输入门	遗忘门	LSTM
0	1	只使用记忆
1	1	综合输入和记忆
0	0	清零记忆
1	0	输入覆盖记忆

模型	MAE/MW	MAPE
LSTM	19.560 0	0.010 6
EEMD-LSTM	13.740 2	0.007 8
BiLSTM	7.160 8	0.004 4
EEMD-BiLSTM	4.132 6	0.004 7