Please wait a minute...
浙江大学学报(工学版)
Journal of ZheJiang University (Engineering Science)  2021, Vol. 55 Issue (9): 1625-1633    DOI: 10.3785/j.issn.1008-973X.2021.09.003
    
Short term load forecasting based on gated recurrent unit and error correction
Wei HUANG(),Tian CHEN*(),Ru-jun WU
School of Mechanical Engineering, Shanghai Dianji University, Shanghai 201306, China
Download: HTML     PDF(1641KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

A combined prediction model combining stacked bidirectional gated recurrent unit (SBiGRU), complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and error correction was proposed, aiming at the problem of error accumulation in iterative training process of load forecasting model. The SBiGRU model was established to learn the time series characteristics of load series under the influence of temperature and date type, and the error characteristics were reflected in the error series generated in the prediction process of SBiGRU model. Then CEEMDAN algorithm was used to decompose the error series into several intrinsic mode function (IMF) components and trend components. For each component, SBiGRU model was established again for learning and forecasting, and the predicted values of all components were reconstructed to obtain the error prediction results. Finally, the prediction results were summed to correct the error. Model evaluation results show that the prediction accuracy of the combined model is 98.86%. Compared with SBiGRU, BiRNN, support vector regression, ect., the combined model has better accuracy.

Key words： load forecasting      gated recurrent unit      error correction      ensemble empirical mode decomposition     
Received: 28 August 2020      Published: 20 October 2021
CLC:  TP 183  
Fund:  上海市高峰高原学科资助项目（A1-5701-18-007-03）；上海多向模锻工程技术研究中心资助项目（20DZ2253200）
Corresponding Authors: Tian CHEN     E-mail: 1453256773@qq.com;chent@sdju.edu.cn
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Wei HUANG
Tian CHEN
Ru-jun WU
Cite this article:

Wei HUANG,Tian CHEN,Ru-jun WU. Short term load forecasting based on gated recurrent unit and error correction. Journal of ZheJiang University (Engineering Science), 2021, 55(9): 1625-1633.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2021.09.003     OR     https://www.zjujournals.com/eng/Y2021/V55/I9/1625


基于门控循环单元与误差修正的短期负荷预测

针对负荷预测模型迭代训练过程中存在误差积累的问题，提出结合叠式双向门控循环单元（SBiGRU）、完整自适应噪声集成经验模态分解（CEEMDAN）和误差修正的组合预测模型. 建立SBiGRU模型学习在气温、日期类型影响下负荷序列的时序特征，误差特征体现在SBiGRU模型预测产生的误差序列中；使用CEEMDAN算法将误差序列分解为数个本征模态函数（IMF）分量与趋势分量，对每项分量再次建立SBiGRU模型进行学习与预测，并对各分量的预测值进行序列重构，得到误差的预测结果；对预测结果进行求和以修正误差. 模型评估结果表明，组合模型的预测准确精度为98.86%，与SBiGRU、BiRNN、支持向量回归等方法相比，该模型具有更好的精度.


关键词： 负荷预测,  门控循环单元,  误差修正,  集成经验模态分解 
Fig.1 Network structure of gated recurrent unit
Fig.2 Network structure of bidirectional gated recurrent unit
Fig.3 Forecasting process of combination model
Fig.4 Variation curve of partial load
模型结构 $ {{E}}_{\text{MAP}{E}} $ T/s
单层 0.020 4 13
2+1层 0.017 4 21
3+1层 0.018 6 29
4+1层 0.019 3 38
Tab.1 Performance comparison of different SBiGRU model structures
Fig.5 Network parameters of first stage stacked bidirectional gated recurrent unit
Fig.6 Prediction results of first stage stacked bidirectional gated recurrent unit
Fig.7 Error sequence of first stage stacked bidirectional gated recurrent unit
Fig.8 Load variation curve of each IMF component
Fig.9 Comparison of predictive results for five prediction models
Fig.10 Correlation of actual values and predicted values for five models
模型 ${ {E} }_{ {{\rm{MAPE}}} }$ ${ {E} }_{ {{\rm{Max}}} }$ ${ {E} }_{ {{\rm{RMSE}}} }$/MW
本文 0.011 4 0.014 9 137.69
SBiGRU- SBiGRU 0.015 5 0.026 2 178.79
SBiGRU 0.017 9 0.030 2 201.55
BiRNN 0.021 0 0.032 1 262.69
SVR 0.031 0 0.051 1 358.83
Tab.2 Error comparison of prediction results for five models
Fig.11 Error histograms of five models
Fig.12 Error Box-plot of five models
[1]   陈剑强, 杨俊杰, 楼志斌 基于XGBoost算法的新型短期负荷预测模型研究[J]. 电测与仪表, 2019, 56 (21): 23- 29
CHEN Jian-qiang, YANG Jun-jie, LOU Zhi-bin A new short-term load forecasting model based on XGBoost algorithm[J]. Electrical Measurement and Instrumentation, 2019, 56 (21): 23- 29
[2]   龚钢军, 安晓楠, 陈志敏, 等 基于SAE-ELM的电动汽车充电站负荷预测模型[J]. 现代电力, 2019, 36 (6): 9- 15
GONG Gang-jun, AN Xiao-nan, CHEN Zhi-min, et al Model of load forecasting of electric vehicle charging station based on SAE-ELM[J]. Modern Electric Power, 2019, 36 (6): 9- 15
doi: 10.3969/j.issn.1007-2322.2019.06.002
[3]   谢敏, 邓佳梁, 吉祥, 等 基于信息熵和变精度粗糙集优化的支持向量机降温负荷预测方法[J]. 电网技术, 2017, 41 (1): 217- 221
XIE Min, DENG Jia-liang, JI Xiang, et al Cooling load forecasting method of based on support vector machine optimized with entropy and variable accuracy roughness set[J]. Power System Technology, 2017, 41 (1): 217- 221
[4]   赵洪山, 田甜 基于自适应无迹卡尔曼滤波的电力系统动态状态估计[J]. 电网技术, 2014, 38 (1): 188- 192
ZHAO Hong-shan, TIAN Tian Dynamic state estimation for power system based on an adaptive unscented Kalman filter[J]. Power System Technology, 2014, 38 (1): 188- 192
[5]   LV P, LIU S, YU W, et al EGA-STLF: a hybrid short-term load forecasting model[J]. IEEE Access, 2020, 8: 31742- 31752
doi: 10.1109/ACCESS.2020.2973350
[6]   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 Ji-xiang, ZHANG Qi-pei, YANG Zhi-hong, 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
doi: 10.7500/AEPS20181012004
[7]   CHEN K, WANG Q, HE Z, HU J, et al Short-term load forecasting with deep residual networks[J]. IEEE Transactions on Smart Grid, 2019, 10 (4): 3943- 3952
doi: 10.1109/TSG.2018.2844307
[8]   HAQ M R, NI Z A new hybrid model for short-term electricity load forecasting[J]. IEEE Access, 2019, 7: 125413- 125423
doi: 10.1109/ACCESS.2019.2937222
[9]   SHI H, XU M, LI R Deep learning for household load forecasting: a novel pooling deep RNN[J]. IEEE Transactions on Smart Grid, 2018, 9 (5): 5271- 5280
doi: 10.1109/TSG.2017.2686012
[10]   SEHOVAC L, GROLINGER K Deep Learning for load forecasting: sequence to sequence recurrent neural networks with attention[J]. IEEE Access, 2020, 8: 36411- 36426
doi: 10.1109/ACCESS.2020.2975738
[11]   TANG X, DAI Y, LIU Q, et al Application of bidirectional recurrent neural network combined with deep belief network in short-term load forecasting[J]. IEEE Access, 2019, 7: 160660- 160670
doi: 10.1109/ACCESS.2019.2950957
[12]   JIAO R, ZHANG T, JIANG Y, et al Short-term non-residential load forecasting based on multiple sequences LSTM recurrent neural network[J]. IEEE Access, 2018, 6: 59438- 59448
doi: 10.1109/ACCESS.2018.2873712
[13]   KONG W, DONG Z Y, JIA Y, et al Short-term residential load forecasting based on LSTM recurrent neural network[J]. IEEE Transactions on Smart Grid, 2019, 10 (1): 841- 851
doi: 10.1109/TSG.2017.2753802
[14]   ZHENG C, WANG S, LIU Y, et al A novel equivalent model of active distribution networks based on LSTM[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 30 (9): 2611- 2624
doi: 10.1109/TNNLS.2018.2885219
[15]   XIUYUN G, YING W, YANG G, et al. Short-term load forecasting model of GRU network based on deep learning framework [C]// 2018 2nd IEEE Conference on Energy Internet and Energy System Integration (EI2). Beijing: IEEE, 2018: 1-4.
[16]   DONG M, GRUMBACH L A hybrid distribution feeder long-term load forecasting method based on sequence prediction[J]. IEEE Transactions on Smart Grid, 2020, 11 (1): 470- 482
doi: 10.1109/TSG.2019.2924183
[17]   SEHOVAC L, NESEN C, GROLINGER K. Forecasting building energy consumption with deep learning: a sequence to sequence approach [C]// 2019 IEEE International Congress on Internet of Things (ICIOT). Milan: IEEE, 2019: 108-116.
[18]   AFRASIABI M, MOHAMMADI M, RASTEGAR M, et al Probabilistic deep neural network price forecasting based on residential load and wind speed predictions[J]. IET Renewable Power Generation, 2019, 13 (11): 1840- 1848
doi: 10.1049/iet-rpg.2018.6257
[19]   TANG X, DAI Y, WANG T, et al Short-term power load forecasting based on multi-layer bidirectional recurrent neural network[J]. IET Generation, Transmission and Distribution, 2019, 13 (17): 3847- 3854
doi: 10.1049/iet-gtd.2018.6687
[20]   PAN D, XU B, MA J, et al. Short-term load forecasting based on EEMD-approximate entropy and ELM [C]// 2019 IEEE Sustainable Power and Energy Conference. Beijing: IEEE, 2019: 1772-1775.
[21]   YE J, YANG L. Short-term load forecasting using ensemble empirical mode decomposition and harmony search optimized support vector regression [C]// 2019 14th IEEE Conference on Industrial Electronics and Applications. Xi'an: IEEE, 2019: 851-855.
[22]   ZHU X, QI H, HUANG X, et al. A hybrid method for short-term load forecasting in power system [C]// Proceedings of the 10th World Congress on Intelligent Control and Automation. Beijing: [s.n], 2012: 696-699.
[23]   LI P, LIU H, LI M, et al. Power load forecasting based on VMD multifrequency combinations [C]// 2019 IEEE 3rd Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC). Chongqing: [s.n], 2019: 1214-1218.
[1] Lin TONG,Zheng GUAN,Li-wei WANG,Wen-tao YANG,Yang YAO. New energy ramp event prediction based on time series decomposition and error correction[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(2): 338-346.
[2] Xing LIU,Jian-bo YU. Attention convolutional GRU-based autoencoder and its application in industrial process monitoring[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(9): 1643-1651.
[3] Yan-nan ZHANG,Xiao-hong HUANG,Yan MA,Qun CONG. Method with recording text classification based on deep learning[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(7): 1264-1271.
[4] Chen-lin WANG,Jie YANG,Wen-jun JU,Fu GU,Ji-xi CHEN,Yang-jian JI. Short term load forecasting and peak shaving optimization based on intelligent home appliance[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(7): 1418-1424.
[5] Wen-hao WANG,Xiao ZHANG,Yong-jing WAN. Improved deep belief network and its application in voice conversion[J]. Journal of ZheJiang University (Engineering Science), 2019, 53(12): 2372-2380.
[6] Jing-chang WANG,Ling CHEN,Shan-shan YU,Chen-shu JIANG,Yong WU. Multi-factor perceived short-term tourist number prediction model based on gated recurrent unit[J]. Journal of ZheJiang University (Engineering Science), 2019, 53(12): 2357-2364.
[7] ZHU Tao-tao, XIANG Xiao-yan, CHEN Chen, MENG Jian-yi, YAN Xiao-lang. Timing error resilient clock gate design for wide-voltage application[J]. Journal of ZheJiang University (Engineering Science), 2018, 52(9): 1796-1803.
[8] WU Xin-zhong, XING Qiang, CHEN Ming, CHENG Jiang-yang, YANG Chun-yu. Power quality disturbance detection method using improved complementary ensemble empirical mode decomposition[J]. Journal of ZheJiang University (Engineering Science), 2017, 51(9): 1834-1843.
[9] HAO Zi-yi, XIANG Xiao-yan, CHEN Chen, MENG Jian-yi. Error cancellation flip-flop design with lightweight in-situ error correction[J]. Journal of ZheJiang University (Engineering Science), 2017, 51(3): 605-611.
[10] ZHENG Xu, HAO Zhi-yong, JIN Yang, LU Zhao-gang. Studying noise contributions of IC engine via MEEMD method[J]. Journal of ZheJiang University (Engineering Science), 2012, 46(5): 954-960.
[11] ZHANG Ling, TIAN Chuan-Gao. Difference among housing markets and ripple effect of house price: empirical study of 35 metropolitans[J]. Journal of ZheJiang University (Engineering Science), 2010, 44(1): 197-202.