基于CEEMDAN和频谱时间图卷积网络的电力负荷预测方法

doi:10.19678/j.issn.1000-3428.0068925

摘要/Abstract

摘要：

针对电力负荷数据存在非平稳性且传统预测模型不能精确获取时序负荷数据的空间相关性和时间依赖性, 导致预测精度低的问题, 设计并实现一种基于完全集成经验模式分解的自适应噪声完备性(CEEMDAN)和频谱图卷积网络的电力负荷预测方法。首先使用CEEMDAN将目标负荷序列分解为多个本征模态分量(IMF), 通过计算模糊熵对IMF进行重构; 然后使用频谱时间图卷积网络对重构后分量的空间相关性和时间依赖性进行挖掘, 得到各分量的预测结果; 最后将各分量的预测结果线性相加得到最终预测结果。实验结果表明, 所提方法的平均绝对误差、均方根误差、平均绝对百分比误差3个评价指标分别达到了0.72 KW、0.89 KW、0.92%, 相较于对比模型StemGnn、TCN、LSTM、Informer、FEDformer, 预测精度分别提高了37.9%、17.2%、20.8%、22.5%、12.1%。证明本文所提出的预测方法可以有效降低非平稳性对预测结果的影响, 精确获取时序负荷数据的空间相关性和时间依赖性, 提高预测精度。

关键词: 电力负荷预测, 经验模态分解, 本征模态分量, 图卷积网络, 模糊熵

Abstract:

The traditional forecasting model cannot accurately determine the spatial correlation and temporal dependence of time-series load data, resulting in low forecasting accuracy. To address this issue and the non-stationarity of power load data, a time-series power load forecasting method based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and a spectrogram convolutional network is designed and implemented in this study. First, the target load sequence is decomposed into multiple Intrinsic Mode Function (IMF) components using CEEMDAN, and the IMF is reconstructed by calculating the fuzzy entropy. Subsequently, the temporal correlation and spatial dependence of the reconstructed components are mined using the spectral time graph convolutional network, and the prediction results for each component are obtained. Finally, these prediction results are summed linearly to obtain the final prediction results. The experimental results show that the proposed method achieves a Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) of 0.72 KW, 0.89 KW, and 0.92%, respectively. The prediction accuracy of the proposed method is 37.9%, 17.2%, 20.8%, 22.5%, and 12.1% greater than that of StemGnn, TCN, LSTM, Informer, and FEDformer, respectively. The results demonstrate that the proposed prediction method can effectively reduce the influence of non-stationarity on the prediction results and accurately obtain the spatial correlation and temporal dependence of the time-ordered load data, leading to improved prediction accuracy.

Key words: power load prediction, Empirical Mode Decomposition(EMD), Intrinsic Mode Function(IMF), Graph Convolutional Network(GCN), fuzzy entropy

朱莉, 夏禹, 朱春强, 邓凡. 基于CEEMDAN和频谱时间图卷积网络的电力负荷预测方法[J]. 计算机工程, 2025, 51(4): 339-349.

ZHU Li, XIA Yu, ZHU Chunqiang, DENG Fan. Power Load Prediction Method Based on CEEMDAN and Spectral Time Graph Convolutional Networks[J]. Computer Engineering, 2025, 51(4): 339-349.

https://www.ecice06.com/CN/Y2025/V51/I4/339

图/表 15

图1 STGCN模型结构

Fig.1 STGCN model structure

图2 Timesblock结构

Fig.2 Timesblock structure

图3 一维时间序列转换至二维

Fig.3 One-dimensional time series converted to two-dimensional

图4 Inception block整体结构

Fig.4 Overall structure of Inception block

图5 预测流程

Fig.5 Forecasting procedure

图6 序列分解结果

Fig.6 Sequence decomposition results

图7 预测时间对比

Fig.7 Forecast time comparison

图8 各分量预测结果

Fig.8 Predicted results of each component

图9 不同模型的预测结果对比

Fig.9 Comparison of prediction results of different models

图10 各模型的预测效果

Fig.10 The prediction effects of each models

参考文献 30

1	林麒麟. 基于神经网络智能算法的电力系统短期负荷预测研究[D]. 兰州: 兰州理工大学, 2017.
	LIN Q L. Research on short-term load forecasting of power system based on neural network intelligent algorithm[D]. Lanzhou: Lanzhou University of Technology, 2017. (in Chinese)
2	张振中, 郭傅傲, 刘大明, 等. 基于最大互信息系数和小波分解的多模型集成短期负荷预测. 计算机应用与软件, 2021, 38 (5): 82- 87.
	ZHANG Z Z , GUO F A , LIU D M , et al. Multi-model integrated short-term load prediction based on maximum mutual information coefficient and wavelet decomposition. Computer Applications and Software, 2021, 38 (5): 82- 87.
3	赵一鸣, 吉月辉, 刘俊杰, 等. 基于EMD-IPSO-LSTM模型的短期电力负荷预测. 国外电子测量技术, 2023, 42 (1): 132- 137.
	ZHAO Y M , JI Y H , LIU J J , et al. Short term power load forecasting based on EMD-IPSO-LSTM model. Foreign Electronic Measurement Technology, 2023, 42 (1): 132- 137.
4	吴铁洲, 邹智, 姜奔, 等. 基于TLBGA-GRU神经网络的短期负荷预测. 计算机工程, 2022, 48 (11): 69- 76. doi: 10.19678/j.issn.1000-3428.0063153
	WU T Z , ZOU Z , JIANG B , et al. Short-term load forecasting based on TLBGA-GRU neural network. Computer Engineering, 2022, 48 (11): 69- 76. doi: 10.19678/j.issn.1000-3428.0063153
5	朱子意, 孙晓燕, 柳先彪, 等. 基于相似用电单元及图卷积神经网络的电力负荷预测. 电力科学与工程, 2023, 39 (7): 9- 23.
	ZHU Z Y , SUN X Y , LIU X B , et al. Power load forecasting based on similar power units and graph convolution neural network. Electric Power Science and Engineering, 2023, 39 (7): 9- 23.
6	SHARMA S , MAJUMDAR A , ELVIRA V , et al. Blind Kalman filtering for short-term load forecasting. IEEE Transactions on Power Systems, 2020, 35 (6): 4916- 4919. doi: 10.1109/TPWRS.2020.3018623
7	CASTÁN-LASCORZ M A , JIMÉNEZ-HERRERA P , TRONCOSO A , et al. A new hybrid method for predicting univariate and multivariate time series based on pattern forecasting. Information Sciences, 2022, 586, 611- 627. doi: 10.1016/j.ins.2021.12.001
8	DUDEK G , PELKA P , SMYL S . A hybrid residual dilated LSTM and exponential smoothing model for midterm electric load forecasting. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33 (7): 2879- 2891. doi: 10.1109/TNNLS.2020.3046629
9	NTI I K , TEIMEH M , NYARKO-BOATENG O , et al. Electricity load forecasting: a systematic review. Journal of Electrical Systems and Information Technology, 2020, 7 (1): 13. doi: 10.1186/s43067-020-00021-8
10	李国栋, 周扬, 李凯. 基于SARIMAX-XGBoost模型的区域能耗预测. 电力信息与通信技术, 2022, 20 (3): 26- 33.
	LI G D , ZHOU Y , LI K . Regional energy consumption prediction based on SARIMAX-XGBoost model. Electric Power Information and Communication Technology, 2022, 20 (3): 26- 33.
11	KE G L. Lightgbm: a highly efficient gradient boosting decision tree[C]//Proceedings of Advances in Neural Information Processing Systems. Cambridge, USA: MIT Press, 2017: 317-326.
12	KWON B S , PARK R J , SONG K B . Short-term load forecasting based on deep neural networks using LSTM layer. Journal of Electrical Engineering & Technology, 2020, 15 (4): 1501- 1509.
13	IJAZ K , HUSSAIN Z , AHMAD J , et al. A novel temporal feature selection based LSTM model for electrical short-term load forecasting. IEEE Access, 2022, 10, 82596- 82613.
14	WU L Z , KONG C , HAO X H , et al. A short-term load forecasting method based on GRU-CNN hybrid neural network model. Mathematical Problems in Engineering, 2020, 2020, 1428104.
15	CHEPLYGINA V , DE BRUIJNE M , PLUIM J P W . Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis. Medical Image Analysis, 2019, 54, 280- 296.
16	WU F , JING X Y , WEI P F , et al. Semi-supervised multi-view graph convolutional networks with application to webpage classification. Information Sciences, 2022, 591, 142- 154.
17	KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[EB/OL]. [2023-10-20]. https://arxiv.org/abs/1609.02907v4.
18	DEFFERRARD M, BRESSON X, VANDERGHEYNST P, et al. Convolutional neural networks on graphs with fast localized spectral filtering[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems. New York, USA: ACM Press, 2016: 3844-3852.
19	LIU X Y , TANG T , DING N . Social network sentiment classification method combined Chinese text syntax with graph convolutional neural network. Egyptian Informatics Journal, 2022, 23 (1): 1- 12.
20	YAO L, MAO C S, LUO Y, et al. Graph convolutional networks for text classification[C]//Proceedings of the 31rd AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence. New York, USA: ACM Press, 2019: 7370-7377.
21	CAO D F, WANG Y J, DUAN J Y, et al. Spectral temporal graph neural network for multivariate time-series forecasting[C]//Proceedings of the 34th International Conference on Neural Information Processing Systems. New York, USA: ACM Press, 2020: 17766-17778.
22	卢武, 郑人杰, 赵文彬, 等. 基于EMD-GRU的短期电力负荷预测方法. 电气传动, 2022, 52 (21): 74- 80.
	LU W , ZHENG R J , ZHAO W B , et al. Short-term power load forecasting method based on EMD-GRU. Electric Drive, 2022, 52 (21): 74- 80.
23	张月宇, 李德成, 方大俊, 等. 基于EEMD-LSTM模型的集中供热系统热负荷预测方法研究. 能源工程, 2022, 42 (1): 1- 6.
	ZHANG Y Y , LI D C , FANG D J , et al. Study on heat load forecasting method of central heating system based on EEMD-LSTM model. Energy Engineering, 2022, 42 (1): 1- 6.
24	TORRES M E, COLOMINAS M A, SCHLOTTHAUER G, et al. A complete ensemble empirical mode decomposition with adaptive noise[C]//Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing. Washington D. C., USA: IEEE Press, 2011: 4144-4147.
25	CHENG Y , WANG Z W , CHEN B Y , et al. An improved complementary ensemble empirical mode decomposition with adaptive noise and its application to rolling element bearing fault diagnosis. ISA Transactions, 2019, 91, 218- 234.
26	WU H X, HU T G, LIU Y, et al. TimesNet: temporal 2D-variation modeling for general time series analysis[EB/OL]. [2023-10-20]. https://arxiv.org/abs/2210.02186v3.
27	WANG Q L, WU B G, ZHU P F, et al. ECA-net: efficient channel attention for deep convolutional neural networks[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2020: 11534-11542.
28	ZHANG R J , SUN F , SONG Z W , et al. Short-term traffic flow forecasting model based on GA-TCN. Journal of Advanced Transportation, 2021, 2021, 1338607.
29	ZHOU H Y , ZHANG S H , PENG J Q , et al. Informer: beyond efficient transformer for long sequence time-series forecasting. Artificial Intelligence, 2021, 35 (12): 11106- 11115.
30	ZHOU T, MA Z Q, WEN Q S, et al. FEDformer: frequency enhanced decomposed transformer for long-term series forecasting[EB/OL]. [2023-10-20]. https://arxiv.org/abs/2201.12740v3.

[1]	徐永刚, 孙琦烜, 李凡甲, 程健维, 戴佳俊. 基于扩展时间和时空特征融合图卷积网络的骨架行为识别[J]. 计算机工程, 2025, 51(4): 281-292.
[2]	汤志康, 武毓琦, 李春英, 汤庸. 基于知识图谱卷积网络的学习资源推荐[J]. 计算机工程, 2024, 50(9): 153-160.
[3]	刘锁兰, 王炎, 王洪元, 朱生升. 基于多流语义图卷积网络的人体行为识别[J]. 计算机工程, 2024, 50(8): 64-74.
[4]	代巍, 王丰羽, 冀常鹏. 基于情感增强与双图卷积网络的方面级情感分析[J]. 计算机工程, 2024, 50(5): 120-127.
[5]	莫少聪, 陈庆锋, 谢泽, 刘春雨, 邱俊铼. 基于动态图注意力与标签传播的实体对齐[J]. 计算机工程, 2024, 50(4): 150-159.
[6]	夏卫欢, 廖列法, 张守信, 张燕琴. 基于方面-词性感知的方面级情感分析[J]. 计算机工程, 2024, 50(3): 68-77.
[7]	杨兴耀, 马帅, 张祖莲, 于炯, 陈嘉颖, 王东晓. 基于偏好感知的去噪图卷积网络社交推荐[J]. 计算机工程, 2024, 50(10): 154-163.
[8]	马建红, 龚天, 姚爽. 基于证据句与图卷积网络的文档级关系抽取[J]. 计算机工程, 2023, 49(8): 104-110.
[9]	陈昱瑾, 王晶, 武志昊, 赵耀帅, 林友芳. 基于图卷积网络融合群组关系的社会化推荐方法[J]. 计算机工程, 2023, 49(5): 112-121.
[10]	陈文轩, 曾碧, 郭植星. 融合多特征与语义图卷积网络的摔倒检测方法[J]. 计算机工程, 2023, 49(5): 277-285,294.
[11]	袁立宁, 胡皓, 刘钊. 基于多通道图卷积自编码器的图表示学习[J]. 计算机工程, 2023, 49(2): 150-160,174.
[12]	杨海洋, 张兴鹏. 融合多通道图卷积网络的方面级情感分析模型[J]. 计算机工程, 2023, 49(11): 61-69.
[13]	刘宽, 奚小冰, 周明东. 基于自适应多尺度图卷积网络的骨架动作识别[J]. 计算机工程, 2023, 49(10): 264-271.
[14]	张文豪, 廖列法, 王茹霞. 融合句法树多信息学习方面级情感分析[J]. 计算机工程, 2023, 49(10): 72-79.
[15]	孔博, 韩虎, 陈景景, 白雪, 邓飞. 基于虚拟依存关系与知识增强的方面级情感分析[J]. 计算机工程, 2023, 49(10): 53-63.

选择文件类型/文献管理软件名称

选择包含的内容