基于改进残差网络的光伏逆变器数据异常检测方法

姚森山; 庞成鑫

doi:10.19912/j.0254-0096.tynxb.2024-0006

PDF(2497 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (4) : 322-330. DOI: 10.19912/j.0254-0096.tynxb.2024-0006

基于改进残差网络的光伏逆变器数据异常检测方法

姚森山, 庞成鑫

作者信息 +

DATA ANOMALY DETECTION METHOD FOR PHOTOVOLTAIC INVERTER DATA BASED ON IMPROVED RESIDUAL NETWORK

Yao Senshan, Pang Chengxin

Author information +

文章历史 +

摘要

为解决光伏组件异常导致光伏逆变器数据异常的问题,提出一种基于改进残差网络（SCCB-ResNet50）的光伏逆变器数据异常检测方法。该方法引入马尔可夫转移场将光伏功率时序数据化转为二维图像,以增加数据特征点从而提高检测精度,同时使用改进残差网络提取数据异常特征,进行数据异常检测。改进残差网络在残差网络中引入通道注意力和空间注意力融合机制（CBAM）,并使用改进的随机梯度下降（SGD）优化器和余弦退火学习率下降策略,以提高数据异常检测精度。结果表明：该方法在AUC、召回率和准确率上分别达到95.8%、81.5%、96.0%,与LSTM等其他数据异常检测方法相比,3个评价指标均得到有效提高,具有优异的数据异常检测能力。

Abstract

In order to solve the problem of PV module anomalies leading to PV inverter data anomalies, a PV inverter data anomaly detection method based on improved residual network （SCCB-ResNet50） is proposed. The method introduces a Markov transfer field to convert the PV power time series data into a two-dimensional image in order to increase the data feature points and thus improve the detection accuracy, and also extracts the data anomaly features using the improved residual network for data anomaly detection. The improved residual network introduces channel attention and spatial attention fusion mechanism in the residual network and uses improved SGD optimizer and cosine annealing learning rate reduction strategy to improve the data anomaly detection accuracy. The experimental results show that; the method achieves 95.8%, 81.5% and 96.0% in AUC, recall rdtio, and accuracy, respectively. Compared with other data anomaly detection methods such as LSTM, all the three evaluation indexes are effectively improved and have excellent data anomaly detection capability.

导出引用

姚森山, 庞成鑫. 基于改进残差网络的光伏逆变器数据异常检测方法[J]. 太阳能学报. 2025, 46(4): 322-330 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0006

Yao Senshan, Pang Chengxin. DATA ANOMALY DETECTION METHOD FOR PHOTOVOLTAIC INVERTER DATA BASED ON IMPROVED RESIDUAL NETWORK[J]. Acta Energiae Solaris Sinica. 2025, 46(4): 322-330 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0006

中图分类号： TM615

参考文献

[1] WU K T, PENG X G, LI Z L, et al.A short-term photovoltaic power forecasting method combining a deep learning model with trend feature extraction and feature selection[J]. Energies, 2022, 15(15): 5410.
[2] BETTI A, TUCCI M, CRISOSTOMI E, et al.Fault prediction and early-detection in large PV power plants based on self-organizing maps[J]. Sensors, 2021, 21(5): 1687.
[3] 顾晓东, 唐丹宏, 黄晓华. 基于深度学习的电网巡检图像缺陷检测与识别[J]. 电力系统保护与控制, 2021, 49(5): 91-97.
GU X D, TANG D H, HUANG X H.Deep learning-based defect detection and recognition of a power grid inspection image[J]. Power system protection and control, 2021, 49(5): 91-97.
[4] 任惠, 夏静, 卢锦玲, 等. 基于红外图像和改进MobileNet-V3的光伏组件故障诊断方法[J]. 太阳能学报, 2023, 44(8): 238-245.
REN H, XIA J, LU J L, et al.Research on fault diagnosis of photovoltaic modules based on infrared images and improved MobileNet-V3[J]. Acta energiae solaris sinica, 2023, 44(8): 238-245.
[5] 王银, 高瑞泽, 李茂环, 等. 基于YOLOv5 LiteX算法的光伏组件缺陷检测[J]. 太阳能学报, 2023, 44(9): 101-108.
WANG Y, GAO R Z, LI M H, et al.Photovoltaic modules defect detection based on YOLOv5 LiteX algorithm[J]. Acta energiae solaris sinica, 2023, 44(9): 101-108.
[6] 杨剑锋, 秦钟, 庞小龙, 等. 基于深度学习网络的输电线路异物入侵监测和识别方法[J]. 电力系统保护与控制, 2021, 49(4): 37-44.
YANG J F, QIN Z, PANG X L, et al.Foreign body intrusion monitoring and recognition method based on Dense-YOLOv3 deep learning network[J]. Power system protection and control, 2021, 49(4): 37-44.
[7] 齐风杨. 基于无人机巡检的光伏区域视觉识别与定位方法研究[D]. 杭州: 浙江大学, 2021.
QI F Y.Research on visual recognition and positioning method of photovoltaic area based on UAV inspectionon[D]. Hangzhou: Zhejiang University, 2021.
[8] JIANG Y, ZHAO C H.Attention classification-and-segmentation network for micro-crack anomaly detection of photovoltaic module cells[J]. Solar energy, 2022, 238: 291-304.
[9] PRIMANA A P, HARDIANTO T.Fault prediction in photovoltaic systems with extreme learning machine modeling[C]//2022 International Conference on Electrical Engineering, Computer and Information Technology (ICEECIT), Jember, Indonesia, 2022: 268-273.
[10] LIVERA A, THERISTIS M, MICHELI L, et al.Failure diagnosis and trend-based performance losses routines for the detection and classification of incidents in large-scale photovoltaic systems[J]. Progress in photovoltaics: research and applications, 2022, 30(8): 921-937.
[11] 马乐, 毕利. 基于多维时间序列的光伏逆变器异常检测方法[J]. 电力电子技术, 2022, 56(7): 78-82.
MA L, BI L.An anomaly detection method of photovoltaic inverter based on multidimensional time series[J]. Power electronics, 2022, 56(7): 78-82.
[12] TAGHEZOUIT B, HARROU F, SUN Y, et al.A simple and effective detection strategy using double exponential scheme for photovoltaic systems monitoring[J]. Solar energy, 2021, 214: 337-354.
[13] MA W T, MA M Y, ZHANG Z X, et al.Anomaly detection of mountain photovoltaic power plant based on spectral clustering[J]. IEEE journal of photovoltaics, 2023, 13(4): 621-631.
[14] ZULFAUZI I A, DAHLAN N Y, SINTUYA H, et al.Anomaly detection using K-means and long-short term memory for predictive maintenance of large-scale solar (LSS) photovoltaic plant[J]. Energy reports, 2023, 9: 154-158.
[15] 叶进, 卢泉, 王钰淞, 等. 基于级联随机森林的光伏故障诊断模型研究[J]. 太阳能学报, 2021, 42(3): 358-362.
YE J, LU Q, WANG Y S, et al.Research on PV fault diagnosis model based on cascaded random forest[J]. Acta energiae solaris sinica, 2021, 42(3): 358-362.
[16] LIN M Q, WU J, ZOU J Q, et al.Retired battery screening based on Markov transition field and swin transformer[J]. IEEE transactions on transportation electrification, 2024, 10(2): 4217-4227.
[17] 周嘉琪, 毕利. 基于GAN的光伏逆变器数据异常检测技术[J]. 电力系统保护与控制, 2022, 50(1): 133-140.
ZHOU J Q, BI L.Abnormal detection technology of photovoltaic inverter data based on GAN[J]. Power system protection and control, 2022, 50(1): 133-140.
[18] HE K M, ZHANG X Y, REN S Q, et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016: 770-778.
[19] HE K M, ZHANG X Y, REN S Q, et al.Identity mappings in deep residual networks[M]. Lecture Notes in Computer Science Cham: Springer International Publishing, 2016: 630-645.
[20] HU J, SHEN L, SUN G.Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018: 7132-7141.
[21] BOTTOU L.Large-scale machine learning with stochastic gradient descent[M]. Proceedings of COMPSTAT'2010. Heidelberg: Physica-Verlag HD, 2010: 177-186.
[22] SMITH L N.A disciplined approach to neural network hyper-parameters: part 1: learning rate, batch size, momentum, and weight decay[EB/OL]. https://arxiv.org/abs/1803.09820v2.
[23] DKA Solar Centre.DKASC, Alice springs[EB/OL]. https://dkasolarcentre.com.au/download.
[24] WANG L, BAI Z C, ZHANG Y H, et al.Show, recall, and tell: image captioning with recall mechanism[J]. Proceedings of the AAAI conference on artificial intelligence, 2020, 34(7): 12176-12183.
[25] AKCAY S, ATAPOUR-ABARGHOUEI A, BRECKON T P. GANomaly: semi-supervised anomaly detection via adversarial training[J]. arXiv e-prints, 2018: arXiv: 1805.06725.
[26] 吴刚. 基于数据内在特性和LSTM的用电数据异常检测算法研究[J]. 无线互联科技, 2019, 16(10): 96-99, 112.
WU G.Study on power data anomaly detection algorithm based on data intrinsic property and LSTM[J]. Wireless Internet technology, 2019, 16(10): 96-99, 112.
[27] GAO H X, KUENZEL S, ZHANG X Y.A hybrid ConvLSTM-based anomaly detection approach for combating energy theft[J]. IEEE transactions on instrumentation and measurement, 2022, 71: 2517110.