Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (1): 311-317.DOI: 10.11772/j.issn.1001-9081.2023010078
Special Issue: 前沿与综合应用
• Frontier and comprehensive applications • Previous Articles Next Articles
Received:
2023-01-31
Revised:
2023-03-31
Accepted:
2023-04-03
Online:
2023-06-06
Published:
2024-01-10
Contact:
Leichun WANG
About author:
SHI Hanxiao, born in 1998, M. S. candidate. His research interests include power load forecasting, deep learning.
Supported by:
通讯作者:
王雷春
作者简介:
史含笑(1998—),男,河南商丘人,硕士研究生,主要研究方向:电力负荷预测、深度学习;基金资助:
CLC Number:
Hanxiao SHI, Leichun WANG. Short-term power load forecasting by graph convolutional network combining LSTM and self-attention mechanism[J]. Journal of Computer Applications, 2024, 44(1): 311-317.
史含笑, 王雷春. 结合LSTM和自注意力机制的图卷积网络短期电力负荷预测[J]. 《计算机应用》唯一官方网站, 2024, 44(1): 311-317.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2023010078
分类 | 范围 |
---|---|
训练集 | 2017年1月1日—2017年9月30日 |
验证集 | 2017年10月1日—2017年11月30日 |
测试集 | 2017年12月1日—2017年12月31日 |
Tab. 1 Division of Morocco dataset
分类 | 范围 |
---|---|
训练集 | 2017年1月1日—2017年9月30日 |
验证集 | 2017年10月1日—2017年11月30日 |
测试集 | 2017年12月1日—2017年12月31日 |
分类 | 范围 |
---|---|
训练集 | 2016年1月1日—2019年12月31日 |
验证集 | 2020年1月1日—2020年2月29日 |
测试集 | 2020年3月1日—2020年6月26日 |
Tab. 2 Division of Panama dataset
分类 | 范围 |
---|---|
训练集 | 2016年1月1日—2019年12月31日 |
验证集 | 2020年1月1日—2020年2月29日 |
测试集 | 2020年3月1日—2020年6月26日 |
LSTM层数 | GCN层数 | 训练轮数 | MAPE/% |
---|---|---|---|
1 | 1 | 100 | 1.86 |
2 | 1 | 100 | 1.67 |
3 | 1 | 100 | 1.79 |
4 | 1 | 100 | 1.90 |
Tab. 3 Forecasting results with different LSTM layers on Morocco dataset
LSTM层数 | GCN层数 | 训练轮数 | MAPE/% |
---|---|---|---|
1 | 1 | 100 | 1.86 |
2 | 1 | 100 | 1.67 |
3 | 1 | 100 | 1.79 |
4 | 1 | 100 | 1.90 |
LSTM层数 | GCN层数 | 训练轮数 | MAPE/% |
---|---|---|---|
2 | 1 | 100 | 1.67 |
2 | 2 | 100 | 1.60 |
2 | 3 | 100 | 1.54 |
2 | 4 | 100 | 1.62 |
Tab. 4 Forecasting results with different GCN layers on Morocco dataset
LSTM层数 | GCN层数 | 训练轮数 | MAPE/% |
---|---|---|---|
2 | 1 | 100 | 1.67 |
2 | 2 | 100 | 1.60 |
2 | 3 | 100 | 1.54 |
2 | 4 | 100 | 1.62 |
残差次数 | 训练轮数 | MAPE/% |
---|---|---|
0 | 100 | 1.54 |
1 | 100 | 1.40 |
2 | 100 | 1.67 |
3 | 100 | 1.79 |
Tab. 5 Forecasting results with different residual times on Morocco dataset
残差次数 | 训练轮数 | MAPE/% |
---|---|---|
0 | 100 | 1.54 |
1 | 100 | 1.40 |
2 | 100 | 1.67 |
3 | 100 | 1.79 |
模型 | 工作日 | 休息日 | 全部测试集 | ||||||
---|---|---|---|---|---|---|---|---|---|
MAPE/% | MAE/kW | RMSE/kW | MAPE/% | MAE/kW | RMSE/kW | MAPE/% | MAE/kW | RMSE/kW | |
SVM | 3.36 | 961.10 | 1 074.51 | 3.24 | 870.83 | 1 038.03 | 3.34 | 948.20 | 1 069.30 |
LSTM | 2.34 | 678.47 | 790.26 | 2.03 | 563.89 | 656.80 | 2.30 | 662.10 | 771.19 |
CNN-LSTM | 1.88 | 561.80 | 687.33 | 1.94 | 523.61 | 650.85 | 1.89 | 556.34 | 682.11 |
CNN-LSTM-attention | 1.76 | 524.31 | 658.97 | 1.81 | 500.69 | 604.09 | 1.77 | 520.94 | 651.13 |
GCNLS-STLF | 1.36 | 402.08 | 510.79 | 1.62 | 412.50 | 530.20 | 1.40 | 403.57 | 513.56 |
Tab. 6 Forecasting results of different models on Morocco dataset
模型 | 工作日 | 休息日 | 全部测试集 | ||||||
---|---|---|---|---|---|---|---|---|---|
MAPE/% | MAE/kW | RMSE/kW | MAPE/% | MAE/kW | RMSE/kW | MAPE/% | MAE/kW | RMSE/kW | |
SVM | 3.36 | 961.10 | 1 074.51 | 3.24 | 870.83 | 1 038.03 | 3.34 | 948.20 | 1 069.30 |
LSTM | 2.34 | 678.47 | 790.26 | 2.03 | 563.89 | 656.80 | 2.30 | 662.10 | 771.19 |
CNN-LSTM | 1.88 | 561.80 | 687.33 | 1.94 | 523.61 | 650.85 | 1.89 | 556.34 | 682.11 |
CNN-LSTM-attention | 1.76 | 524.31 | 658.97 | 1.81 | 500.69 | 604.09 | 1.77 | 520.94 | 651.13 |
GCNLS-STLF | 1.36 | 402.08 | 510.79 | 1.62 | 412.50 | 530.20 | 1.40 | 403.57 | 513.56 |
模型 | MAPE/% | MAE/MW | RMSE/MW |
---|---|---|---|
SVM | 2.74 | 34.21 | 42.76 |
LSTM | 2.29 | 29.17 | 34.19 |
CNN-LSTM | 1.73 | 22.17 | 29.22 |
CNN-LSTM-attention | 1.64 | 20.79 | 26.98 |
GCNLS-STLF | 1.35 | 17.14 | 22.71 |
Tab. 7 Forecasting results of different models in March on Panama dataset
模型 | MAPE/% | MAE/MW | RMSE/MW |
---|---|---|---|
SVM | 2.74 | 34.21 | 42.76 |
LSTM | 2.29 | 29.17 | 34.19 |
CNN-LSTM | 1.73 | 22.17 | 29.22 |
CNN-LSTM-attention | 1.64 | 20.79 | 26.98 |
GCNLS-STLF | 1.35 | 17.14 | 22.71 |
模型 | MAPE/% | MAE/MW | RMSE/MW |
---|---|---|---|
SVM | 2.81 | 31.04 | 42.11 |
LSTM | 2.40 | 26.23 | 35.04 |
CNN-LSTM | 1.76 | 19.08 | 24.97 |
CNN-LSTM-attention | 1.69 | 18.45 | 24.84 |
GCNLS-STLF | 1.41 | 16.37 | 22.22 |
Tab. 8 Forecasting results of different models in June on Panama dataset
模型 | MAPE/% | MAE/MW | RMSE/MW |
---|---|---|---|
SVM | 2.81 | 31.04 | 42.11 |
LSTM | 2.40 | 26.23 | 35.04 |
CNN-LSTM | 1.76 | 19.08 | 24.97 |
CNN-LSTM-attention | 1.69 | 18.45 | 24.84 |
GCNLS-STLF | 1.41 | 16.37 | 22.22 |
1 | AHMAD N, GHADI Y, ADNAN M, et al. Load forecasting techniques for power system: Research challenges and survey [J]. IEEE Access, 2022, 10: 71054-71090. 10.1109/access.2022.3187839 |
2 | SABER A Y, ALAM A K M R. Short term load forecasting using multiple linear regression for big data [C]// Proceedings of the 2017 IEEE Symposium Series on Computational Intelligence. Piscataway: IEEE, 2017: 1-6. 10.1109/ssci.2017.8285261 |
3 | SHARMA S, MAJUMDAR A, ELVIRA V, et al. Blind Kalman filtering for short-term load forecasting [J]. IEEE Transactions on Power Systems, 2020, 35(6): 4916-4919. 10.1109/tpwrs.2020.3018623 |
4 | 安颖坤,朱永丹.基于线性回归法和指数平滑法对电力负荷的预测[J].电力设备管理, 2021(5): 177-179. |
AN Y K, ZHU Y D. Power load prediction based on linear regression method and exponential smoothing method [J]. Electric Power Equipment Management, 2021(5): 177-179. | |
5 | SINGH U, VADHERA S. Random forest and Xgboost technique for short-term load forecasting [C]// Proceedings of the 2022 1st International Conference on Sustainable Technology for Power and Energy Systems. Piscataway: IEEE, 2022: 1-6. 10.1109/stpes54845.2022.10006635 |
6 | ZHANG J, ZHANG Q, LI G, et al. Application of HIMVO-SVM in short-term load forecasting [C]// Proceedings of the 2020 Chinese Control and Decision Conference. Piscataway: IEEE, 2020: 768-772. 10.1109/ccdc49329.2020.9164644 |
7 | EMHAMED A A, SHRIVASTAVA J. Electrical load distribution forecasting utilizing Support Vector Model (SVM) [J]. Materials Today: Proceedings, 2021, 47: 41-46. 10.1016/j.matpr.2021.03.516 |
8 | NASSIF A B, SOUDAN B, AZZEH M, et al. Artificial intelligence and statistical techniques in short-term load forecasting: A review [EB/OL]. (2021-12-29) [2023-03-10]. . 10.15866/iremos.v14i6.21328 |
9 | JANKOVIĆ Z, SELAKOV A, BEKUT D, et al. Day similarity metric model for short-term load forecasting supported by PSO and artificial neural network [J]. Electrical Engineering, 2021, 103: 2973-2988. 10.1007/s00202-021-01286-6 |
10 | CHI D W. Research on electricity consumption forecasting model based on wavelet transform and multi-layer LSTM model [J]. Energy Reports, 2022, 8: 220-228. 10.1016/j.egyr.2022.01.169 |
11 | BIANCHI F M, MAIORINO E, KAMPFFMEYER M C, et al. An overview and comparative analysis of recurrent neural networks for short term load forecasting [EB/OL]. (2018-07-20) [2023-03-09]. . 10.1007/978-3-319-70338-1_4 |
12 | 肖勇,郑楷洪,郑镇境,等.基于多尺度跳跃深度长短期记忆网络的短期多变量负荷预测[J].计算机应用, 2021, 41(1): 231-236. |
XIAO Y, ZHENG K H, ZHENG Z J, et al. Multi-scale skip deep long short-term memory network for short-term multivariate load forecasting [J]. Journal of Computer Applications, 2021, 41(1): 231-236. | |
13 | RAFI S H, NAHID-AL-MASOOD, DEEBA S R, et al. A short-term load forecasting method using integrated CNN and LSTM network [J]. IEEE Access, 2021, 9: 32436-32448. 10.1109/access.2021.3060654 |
14 | XU F, WENG G, YE Q, et al. Research on load forecasting based on CNN-LSTM hybrid deep learning model [C]// Proceedings of the 2022 IEEE 5th International Conference on Electronics Technology. Piscataway: IEEE, 2022: 1332-1336. 10.1109/icet55676.2022.9824615 |
15 | AGGA A, ABBOU A, LABBADI M, et al. Short-term self consumption PV plant power production forecasts based on hybrid CNN-LSTM, ConvLSTM models [J]. Renewable Energy, 2021, 177: 101-112. 10.1016/j.renene.2021.05.095 |
16 | 魏健,赵红涛,刘敦楠,等.基于注意力机制的CNN-LSTM短期电力负荷预测方法[J].华北电力大学学报(自然科学版), 2021, 48(1): 42-47. 10.3969/j.ISSN.1007-2691.2021.01.05 |
WEI J, ZHAO H T, LIU D N, et al. Short-term power load forecasting method by attention-based CNN-LSTM [J]. Journal of North China Electric Power University (Natural Science Edition), 2021, 48(1): 42-47. 10.3969/j.ISSN.1007-2691.2021.01.05 | |
17 | LIU J, GAO H, YAN Q, et al. Short-term load forecasting method based on LSTM-attention mechanism [C]// Proceedings of the 2021 IEEE Sustainable Power and Energy Conference. Piscataway: IEEE, 2021: 3837-3842. 10.1109/ispec53008.2021.9735593 |
18 | WU Z, PAN S, CHEN F, et al. A comprehensive survey on graph neural networks [J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(1): 4-24. 10.1109/tnnls.2020.2978386 |
19 | XIONG J, HONG H, XU C, et al. Graph convolutional network based electricity demand forecasting in power distribution networks [C]// Proceedings of the 2022 International Conference on Artificial Intelligence and Autonomous Robot Systems. Piscataway: IEEE, 2022: 104-109. 10.1109/aiars57204.2022.00031 |
20 | JIANG R, WANG S, ZHANG Y. A dynamic temporal self-attention graph convolutional network for traffic prediction [EB/OL]. (2023-02-21) [2023-03-08]. . |
21 | CAO D, WANG Y, DUAN J, et al. Spectral temporal graph neural network for multivariate time-series forecasting [EB/OL]. (2021-03-13) [2023-03-13]. . 10.48550/arXiv.2103.07719 |
22 | YIN X, YAN D, ALMUDAIFER A, et al. Forecasting stock prices using stock correlation graph: A graph convolutional network approach [C]// Proceedings of the 2021 International Joint Conference on Neural Networks. Piscataway: IEEE, 2021: 1-8. 10.1109/ijcnn52387.2021.9533510 |
23 | AZAM M F, YOUNIS M S. Multi-horizon electricity load and price forecasting using an interpretable multi-head self-attention and EEMD-based framework [J]. IEEE Access, 2021, 9: 85918-85932. 10.1109/access.2021.3086039 |
[1] | Chuanlin PANG, Rui TANG, Ruizhi ZHANG, Chuan LIU, Jia LIU, Shibo YUE. Distributed power allocation algorithm based on graph convolutional network for D2D communication systems [J]. Journal of Computer Applications, 2024, 44(9): 2855-2862. |
[2] | Guixiang XUE, Hui WANG, Weifeng ZHOU, Yu LIU, Yan LI. Port traffic flow prediction based on knowledge graph and spatio-temporal diffusion graph convolutional network [J]. Journal of Computer Applications, 2024, 44(9): 2952-2957. |
[3] | Jing QIN, Zhiguang QIN, Fali LI, Yueheng PENG. Diagnosis of major depressive disorder based on probabilistic sparse self-attention neural network [J]. Journal of Computer Applications, 2024, 44(9): 2970-2974. |
[4] | Liting LI, Bei HUA, Ruozhou HE, Kuang XU. Multivariate time series prediction model based on decoupled attention mechanism [J]. Journal of Computer Applications, 2024, 44(9): 2732-2738. |
[5] | Huanhuan LI, Tianqiang HUANG, Xuemei DING, Haifeng LUO, Liqing HUANG. Public traffic demand prediction based on multi-scale spatial-temporal graph convolutional network [J]. Journal of Computer Applications, 2024, 44(7): 2065-2072. |
[6] | Zexin XU, Lei YANG, Kangshun LI. Shorter long-sequence time series forecasting model [J]. Journal of Computer Applications, 2024, 44(6): 1824-1831. |
[7] | Yue LIU, Fang LIU, Aoyun WU, Qiuyue CHAI, Tianxiao WANG. 3D object detection network based on self-attention mechanism and graph convolution [J]. Journal of Computer Applications, 2024, 44(6): 1972-1977. |
[8] | Shibin LI, Jun GONG, Shengjun TANG. Semi-supervised heterophilic graph representation learning model based on Graph Transformer [J]. Journal of Computer Applications, 2024, 44(6): 1816-1823. |
[9] | Rong HUANG, Junjie SONG, Shubo ZHOU, Hao LIU. Image aesthetic quality evaluation method based on self-supervised vision Transformer [J]. Journal of Computer Applications, 2024, 44(4): 1269-1276. |
[10] | Longtao GAO, Nana LI. Aspect sentiment triplet extraction based on aspect-aware attention enhancement [J]. Journal of Computer Applications, 2024, 44(4): 1049-1057. |
[11] | Xianfeng YANG, Yilei TANG, Ziqiang LI. Aspect-level sentiment analysis model based on alternating‑attention mechanism and graph convolutional network [J]. Journal of Computer Applications, 2024, 44(4): 1058-1064. |
[12] | Xinran LUO, Tianrui LI, Zhen JIA. Chinese medical named entity recognition based on self-attention mechanism and lexicon enhancement [J]. Journal of Computer Applications, 2024, 44(2): 385-392. |
[13] | Ziqi HUANG, Jianpeng HU. Entity category enhanced nested named entity recognition in automotive domain [J]. Journal of Computer Applications, 2024, 44(2): 377-384. |
[14] | Kaitian WANG, Qing YE, Chunlei CHENG. Classification method for traditional Chinese medicine electronic medical records based on heterogeneous graph representation [J]. Journal of Computer Applications, 2024, 44(2): 411-417. |
[15] | Zucheng WU, Xiaojun WU, Tianyang XU. Image-text retrieval model based on intra-modal fine-grained feature relationship extraction [J]. Journal of Computer Applications, 2024, 44(12): 3776-3783. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||