基于CNN-LSTM混合网络的新型配电网异常数据检测模型

王冰梅; 张冶; 李书斌; 回茜; 张雯舒

doi:10.19912/j.0254-0096.tynxb.2024-0897

PDF(1527 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (5) : 243-250. DOI: 10.19912/j.0254-0096.tynxb.2024-0897

基于CNN-LSTM混合网络的新型配电网异常数据检测模型

王冰梅, 张冶, 李书斌, 回茜, 张雯舒

作者信息 +

ABNORMAL DATA DETECTION OF NEW DISTRIBUTION NETWORK BASED ON CNN-LSTM HYBRID NETWORK

Wang Bingmei, Zhang Ye, Li Shubin, Hui Qian, Zhang Wenshu

Author information +

文章历史 +

摘要

为提升包含分布式光伏的新型配电网异常数据检测精确率,降低异常数据检测虚警率,提出一种基于卷积神经网络-长短期记忆网络（CNN-LSTM）混合网络的新型配电网异常数据检测方法。首先,针对新型配电网采集的异构数据,通过新型配电网数据组成的信息传感网络,建立新型配电网多能源数据同构模型;然后,将卷积神经网络和长短期记忆网络结合,提出基于CNN-LSTM混合网络的异常数据检测方法,确定能够对新型配电网异常数据检测结果评价的相关指标。最后,参考新型配电网历史数据,对比分析CNN-LSTM混合网络与其他算法下的新型配电网异常数据检测性能。仿真结果表明,基于CNN-LSTM混合网络的新型配电网异常数据检测性能,在不同划分的数据集上表现更稳定,对异常数据的检测结果更准确。

Abstract

In order to improve the accuracy of abnormal data detection of new distribution network with distributed photovoltaic and reduce the false alarm rate of abnormal data detection, this article proposes a new method of abnormal data detection of distribution network based on CNN-LSTM hybrid network. Firstly, aiming at the heterogeneous data collected by the new distribution network, the multi-energy data isomorphism model of the new distribution network is established using the information sensor network of the new distribution network. Then, combining the convolutional neural network with the long-term and short-term memory network, an abnormal data detection method based on CNN-LSTM hybrid network is proposed to determine the relevant indicators that can evaluate the abnormal data detection results of the new distribution network. Finally, referring to the historical data of the new distribution network, the performance of abnormal data detection in the new distribution network using the CNN-LSTM hybrid network and other algorithms is compared and analyzed. The simulation results show that the detection performance of the new distribution network anomaly data based on CNN-LSTM hybrid network is more stable on different data sets and the detection results of abnormal data are more accurate.

导出引用

王冰梅, 张冶, 李书斌, 回茜, 张雯舒. 基于CNN-LSTM混合网络的新型配电网异常数据检测模型[J]. 太阳能学报. 2025, 46(5): 243-250 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0897

Wang Bingmei, Zhang Ye, Li Shubin, Hui Qian, Zhang Wenshu. ABNORMAL DATA DETECTION OF NEW DISTRIBUTION NETWORK BASED ON CNN-LSTM HYBRID NETWORK[J]. Acta Energiae Solaris Sinica. 2025, 46(5): 243-250 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0897

中图分类号： TK73

参考文献

[1] 杨经纬, 张宁, 王毅, 等. 面向可再生能源消纳的多能源系统: 述评与展望[J]. 电力系统自动化, 2018, 42(4): 11-24.
YANG J W, ZHANG N, WANG Y, et al.Multi-energy system towards renewable energy accommodation: review and prospect[J]. Automation of electric power systems, 2018, 42(4): 11-24.
[2] 潘华, 梁作放, 薛强中, 等. 基于分时电价的含风-光-气-储虚拟电厂经济调度[J]. 太阳能学报, 2020, 41(8): 115-122.
PAN H, LIANG Z F, XUE Q Z, et al.Economic dispatch of wind/PV/gas/storage virtual power plant based on time-of-use power price[J]. Acta energiae solaris sinica, 2020, 41(8): 115-122.
[3] 牟哲岳, 孙勇, 王瑞良, 等. 基于实测数据和机器学习的风电机组载荷预测模型[J]. 太阳能学报, 2023, 44(10): 414-419.
MOU Z Y, SUN Y, WANG R L, et al.Prediction model for wind turbine loads based on experimental data and machine learning[J]. Acta energiae solaris sinica, 2023, 44(10): 414-419.
[4] 夏海南, 王项南, 李强, 等. 潮流能发电装置输出功率异常数据识别方法研究及应用[J]. 太阳能学报, 2022, 43(8): 472-476.
XIA H N, WANG X N, LI Q, et al.Research and application of abnormal data identification method of output power for tidal energy converters[J]. Acta energiae solaris sinica, 2022, 43(8): 472-476.
[5] AMBACH D, SCHMID W.A new high-dimensional time series approach for wind speed, wind direction and air pressure forecasting[J]. Energy, 2017, 135: 833-850.
[6] 杨茂, 杨春霖, 杨琼琼, 等. 计及风向信息的风电功率异常数据识别研究[J]. 太阳能学报, 2019, 40(11): 3265-3272.
YANG M, YANG C L, YANG Q Q, et al.Study on data recognition of wind power abnormality considering wind direction information[J]. Acta energiae solaris sinica, 2019, 40(11): 3265-3272.
[7] 汪亚洲, 蔡新, 林世发, 等. 基于监测数据的风电机组湍流识别及降载研究[J]. 太阳能学报, 2023, 44(6): 360-366.
WANG Y Z, CAI X, LIN S F, et al.Study on turbulence identification and load reduction of wind turbines based on monitoring data[J]. Acta energiae solaris sinica, 2023, 44(6): 360-366.
[8] 刘科研, 盛万兴, 马晓晨, 等. 基于多种群遗传算法的分布式光伏接入配电网规划研究[J]. 太阳能学报, 2021, 42(6): 146-155.
LIU K Y, SHENG W X, MA X C, et al.Planning research of distributed photovoltaic source access distribution network based on multi-population genetic algorithm[J]. Acta energiae solaris sinica, 2021, 42(6): 146-155.
[9] 李红霞. 数据感应与图像识别技术在风电监控中的应用[J]. 太阳能学报, 2023, 44(5): 488-489.
LI H X.Application of data induction and image recognition technology in wind power monitoring[J]. Acta energiae solaris sinica, 2023, 44(5): 488-489.
[10] KOO J, HAN G D, CHOI H J, et al.Wind-speed prediction and analysis based on geological and distance variables using an artificial neural network: a case study in South Korea[J]. Energy, 2015, 93: 1296-1302.
[11] 王丽朝, 孟子尧, 陈诗明, 等. 基于GRU神经网络的光伏电站数据预处理方法[J]. 太阳能学报, 2022, 43(11): 78-84.
WANG L C, MENG Z Y, CHEN S M, et al.Preprocessing method for photovoltaic power plant data based on GRU neural network[J]. Acta energiae solaris sinica, 2022, 43(11): 78-84.
[12] 汪海宁, 陈昱明, 樊涛, 等. 光伏系统采集数据在线清洗与修复方法研究[J]. 太阳能学报, 2022, 43(6): 57-65.
WANG H N, CHEN Y M, FAN T, et al.On line cleaning and repairing method of photovoltaic system data acquisition[J]. Acta energiae solaris sinica, 2022, 43(6): 57-65.
[13] TAKIDDIN A, ISMAIL M, ZAFAR U, et al.Robust electricity theft detection against data poisoning attacks in smart grids[J]. IEEE transactions on smart grid, 2021, 12(3): 2675-2684.
[14] 徐昊, 王永生, 许志伟, 等. 基于生成对抗网络多变量风电时间序列异常值处理[J]. 太阳能学报, 2022, 43(12): 300-311.
XU H, WANG Y S, XU Z W, et al.Outlier processing of multivariable wind power time series based on generative adversarial network[J]. Acta energiae solaris sinica, 2022, 43(12): 300-311.
[15] 向玲, 邓泽奇, 赵玥. 基于SCADA数据的风电机组异常识别方法[J]. 太阳能学报, 2020, 41(11): 278-284.
XIANG L, DENG Z Q, ZHAO Y.Anomaly recognition method for wind turbines based on SCADA data[J]. Acta energiae solaris sinica, 2020, 41(11): 278-284.
[16] 梁涛, 陈春宇, 谭建鑫, 等. 基于多方面特征提取和迁移学习的风速预测[J]. 太阳能学报, 2023, 44(4): 132-139.
LIANG T, CHEN C Y, TAN J X, et al.Wind speed prediction based on multiple feature extraction and transfer learning[J]. Acta energiae solaris sinica, 2023, 44(4): 132-139.
[17] 贺飞, 张雪霞, 陈维荣. 基于P-L双重特征提取的PEMFC系统故障诊断方法[J]. 太阳能学报, 2024, 45(1): 492-499.
HE F, ZHANG X X, CHEN W R.Fault diagnosis method of PEMFC system based on P-L dual feature extraction[J]. Acta energiae solaris sinica, 2024, 45(1): 492-499.
[18] 王斌, 房向阳, 毛华, 等. 基于深度学习的电力工程数据异常检测模型设计[J]. 电子设计工程, 2024, 32(2): 111-115.
WANG B, FANG X Y, MAO H, et al.Design of power engineering data anomaly detection model based on deep learning[J]. Electronic design engineering, 2024, 32(2): 111-115.
[19] 郑瑶, 张颉, 姚文轩, 等. 基于空间特征的电网同步量测虚假数据注入攻击检测[J]. 电力系统自动化, 2023, 47(10): 128-134.
ZHENG Y, ZHANG J, YAO W X, et al.Spatial feature based detection of false data injection attack on synchronous grid measurements[J]. Automation of electric power systems, 2023, 47(10): 128-134.
[20] FANG F, LIU S, BASAK A, et al.Introduction to game theory[J]. Game theory and machine learning for cyber security, 2021,21(5): 21-46.