基于ST-SSIM的电力系统缺失数据重建方法

doi:10.12204/j.issn.1000-7229.2022.07.012

摘要/Abstract

摘要：

电力系统数据采集、测量、传输和存储等过程均可能出现数据缺失问题,威胁电网安全。针对传统电力系统缺失数据重建方法仅考虑数据分布规律,忽略了数据时序与空间特性的问题,提出一种考虑时空特性的电力系统缺失数据重建模型(spatial-temporal seq2seq imputation model, ST-SSIM)。ST-SSIM具备编码-解码结构,编码器由基于图卷积层与长短时记忆单元构造的时空信息提取单元组成,用于提取数据高维时空特征,解码器由长短时记忆单元与全连接层组成,用于解码高维特征,生成电力系统数据。所提模型的输入包括电力系统数据时间序列与电网拓扑邻接矩阵,因此ST-SSIM可实现对电力系统数据复杂时空关系的自动学习。算例中,将所提方法与现有方法在不同规模电网下比较,ST-SSIM具有最高的重建精度,证明了ST-SSIM能有效地学习到电力系统数据的时空特性。通过讨论重建误差与数据缺失节点数以及缺失时间跨度的关系,验证了所提模型重建效果较稳定。

关键词: 电力系统, 缺失数据重建, 时空特性, 图卷积, 长短时记忆单元

Abstract:

Power system data may miss during acquisition, measurement, transmission and storage, which threatens the security of power grid. Since traditional missing data reconstruction methods only consider the data distribution and ignore the spatio-temporal characteristics, a power system missing data reconstruction model called ST-SSIM (spatio-temporal seq2seq imputation model) is proposed in this paper. ST-SSIM has an encoder-decoder structure. The encoder is composed of a spatio-temporal information extraction unit which is constructed by graph convolution layer and long short-term memory cell. The decoder is composed of long short-term memory cell and full connection layer. The input of the proposed model includes power system timeseries and adjacency matrix, so ST-SSIM can realize the automatic learning of complex time-space relationship of data. In experiment, compared the proposed method with the existing methods in power grids of different scales, ST-SSIM has the highest reconstruction accuracy, which proves that ST-SSIM can effectively learn the spatio-temporal characteristics of power system data. By discussing the relationship between reconstruction error and the number of missing nodes and time span, it is verified that the reconstruction effect of the proposed model is stable.

Key words: power system, missing data reconstruction, spatio-temporal characteristics, graph convolution network, long short-term memory cell

中图分类号:

TM715

宋铁维, 施伟锋, 毕宗. 基于ST-SSIM的电力系统缺失数据重建方法[J]. 电力建设, 2022, 43(7): 103-112.

SONG Tiewei, SHI Weifeng, BI Zong. Reconstruction Method Based on ST-SSIM for Missing Data in Power System[J]. ELECTRIC POWER CONSTRUCTION, 2022, 43(7): 103-112.

图/表 14

图1 电力系统数据张量图

Fig.1 Power system data tensor diagram

图2 图卷积结构

Fig.2 Structure of GCN

图3 长短时记忆网络单元结构

Fig.3 Structure of LSTM cell

图4 时空信息提取单元结构

Fig.4 Structure of ST unit

图5 ST-SSIM结构

Fig.5 Structure of ST-SSIM

图6 IEEE 39 节点标准算例拓扑结构

Fig.6 IEEE 39-node standard case

表1 ST-SSIM模型参数表

Table 1 Parameters of ST-SSIM

图7 缺失数据重建结果

Fig.7 Reconstruct results of missing data

表A1 SSIM模型参数表

Table A1 Parameters of ST-SSIM

表A2 LSTM模型参数表

Table A2 Parameters of LSTM

表A3 CNN-LSTM模型参数表

Table A3 Parameters of ST-SSIM

图8 不同模型重建误差对比

Fig.8 Reconstruction error comparison of different models

表2 各模型重建误差

Table 2 Reconstruction error of each model

图9 重建结果平均绝对误差

Fig.9 MAE of reconstruction results

参考文献 22

[1]	张素香, 赵丙镇, 王风雨, 等. 海量数据下的电力负荷短期预测[J]. 中国电机工程学报, 2015, 35(1): 37-42.
	ZHANG Suxiang, ZHAO Bingzhen, WANG Fengyu, et al. Short-term power load forecasting based on Big data[J]. Proceedings of the CSEE, 2015, 35(1): 37-42.
[2]	王德文, 孙志伟. 电力用户侧大数据分析与并行负荷预测[J]. 中国电机工程学报, 2015, 35(3):527-537.
	WANG Dewen, SUN Zhiwei. Big data analysis and parallel load forecasting of electric power user side[J]. Proceedings of the CSEE, 2015, 35(3): 527-537.
[3]	KIM D I, CHUN T Y, YOON S H, et al. Wavelet-based event detection method using PMU data[J]. IEEE Transactions on Smart Grid, 2017, 8(3): 1154-1162. doi: 10.1109/TSG.2015.2478421 URL
[4]	王守相, 陈海文, 潘志新, 等. 采用改进生成式对抗网络的电力系统量测缺失数据重建方法[J]. 中国电机工程学报, 2019, 39(1): 56-64, 320.
	WANG Shouxiang, CHEN Haiwen, PAN Zhixin, et al. A reconstruction method for missing data in power system measurement using an improved generative adversarial network[J]. Proceedings of the CSEE, 2019, 39(1): 56-64, 320.
[5]	韩升科, 胡飞虎, 陈之腾, 等. 基于GCN-LSTM的日前市场边际电价预测[J]. 中国电机工程学报, 2022, 42(9): 3276-3286.
	HAN Shengke, HU Feihu, CHEN Zhiteng, et al. Day ahead market marginal price forecasting based on GCN-LSTM[J]. Proceedings of the CSEE, 2022, 42(9): 3276-3286.
[6]	ZHU X H, SHEN M. Based on the ARIMA model with grey theory for short term load forecasting model[C]// 2012 International Conference on Systems and Informatics (ICSAI2012). Yantai, China: IEEE, 2012: 564-567.
[7]	郭蕴颖, 丁云峰. 基于CNN和LSTM联合预测并修正的电量缺失数据预测[J]. 计算机系统应用, 2020, 29(8): 192-198.
	GUO Yunying, DING Yunfeng. Prediction and correction of power loss data based on CNN and LSTM[J]. Computer Systems & Applications, 2020, 29(8): 192-198.
[8]	MIRANDA V, KRSTULOVIC J, KEKO H, et al. Reconstructing missing data in state estimation with autoencoders[J]. IEEE Transactions on Power Systems, 2012, 27(2): 604-611. doi: 10.1109/TPWRS.2011.2174810 URL
[9]	辜超, 白德盟, 王晶, 等. LSTM在输变电设备缺失值填补中的应用[J]. 电测与仪表, 2019, 56(5): 63-69, 142.
	GU Chao, BAI Demeng, WANG Jing, et al. Application of LSTM in filling missing value of power transmission and transformation equipment[J]. Electrical Measurement & Instrumentation, 2019, 56(5): 63-69, 142.
[10]	王子馨, 胡俊杰, 刘宝柱. 基于长短期记忆网络的电力系统量测缺失数据恢复方法[J]. 电力建设, 2021, 42(5): 1-8.
	WANG Zixin, HU Junjie, LIU Baozhu. Recovery method for missing measurement data of power systems based on long short-term memory networks[J]. Electric Power Construction, 2021, 42(5): 1-8.
[11]	WU Z Z, HUANG M X, ZHAO A P, et al. Traffic prediction based on GCN-LSTM model[J]. Journal of Physics: Conference Series, 2021, 1972(1): 012107. doi: 10.1088/1742-6596/1972/1/012107 URL
[12]	LI Z S, XIONG G, CHEN Y Y, et al. A hybrid deep learning approach with GCN and LSTM for traffic flow prediction[C]// 2019 IEEE Intelligent Transportation Systems Conference. Auckland, New Zealand: IEEE, 2019: 1929-1933.
[13]	王渝红, 沈靖, 曾琦, 等. 基于谱图论和图卷积神经网络的直流电网节点电压估计研究[J]. 电网技术, 2022, 46(2): 521-532.
	WANG Yuhong, SHEN Jing, ZENG Qi, et al. Voltage estimation for DC grid nodes based on spectral theory and graph convolutional neural network[J]. Power System Technology, 2022, 46(2): 521-532.
[14]	廖文龙, 于贇, 王煜森, 等. 基于图卷积网络的配电网无功优化[J]. 电网技术, 2021, 45(6): 2150-2160.
	LIAO Wenlong, YU Yun, WANG Yusen, et al. Reactive power optimization of distribution network based on graph convolutional network[J]. Power System Technology, 2021, 45(6): 2150-2160.
[15]	ZHOU J, CUI G Q, HU S D, et al. Graph neural networks: A review of methods and applications[J]. AI Open, 2020, 1: 57-81. doi: 10.1016/j.aiopen.2021.01.001 URL
[16]	XU D, RUAN C, KORPEOGLU E, et al. Inductive representation learning on temporal graphs[J]. 2020.
[17]	SCHLICHTKRULL M, KIPF T N, BLOEM P, et al. Modeling relational data with graph convolutional networks[C]// The Semantic Web, 2018.
[18]	武昭旭, 杨岸, 祝龙记. 基于循环神经网络的电能质量扰动识别[J]. 电力系统保护与控制, 2020, 48(18): 88-94.
	WU Zhaoxu, YANG An, ZHU Longji. Power quality disturbance recognition based on a recurrent neural network[J]. Power System Protection and Control, 2020, 48(18): 88-94.
[19]	曹梦舟, 张艳. 基于卷积-长短期记忆网络的电能质量扰动分类[J]. 电力系统保护与控制, 2020, 48(2): 86-92.
	CAO Mengzhou, ZHANG Yan. Classification for power quality disturbances based on CNN-LSTM network[J]. Power System Protection and Control, 2020, 48(2): 86-92.
[20]	王俊, 李霞, 周昔东, 等. 基于VMD和LSTM的超短期风速预测[J]. 电力系统保护与控制, 2020, 48(11): 45-52.
	WANG Jun, LI Xia, ZHOU Xidong, et al. Ultra-short-term wind speed prediction based on VMD-LSTM[J]. Power System Protection and Control, 2020, 48(11): 45-52.
[21]	TODERICI G, O'MALLEY S M, HWANG S J, et al. Variable rate image compression with recurrent neural networks[J]. Computer Science, 2015.
[22]	李应求, 安勃, 李恒通. 基于NARX及混沌支持向量机的短期风速预测[J]. 电力系统保护与控制, 2019, 47(23): 65-73.
	LI Yingqiu, AN Bo, LI Hengtong. Short-term wind speed prediction based on NARX and chaos-support vector machine[J]. Power System Protection and Control, 2019, 47(23): 65-73.