An unsupervised monitoring procedure for detecting anomalies in photovoltaic systems using a one-class Support Vector Machine

Abstract One of the greatest challenges in a photovoltaic solar power generation is to keep the designed photovoltaic systems working with the desired operating efficiency. Towards this goal, fault detection in photovoltaic plants is essential to guarantee their reliability, safety, and to maximize operating profitability and avoid expensive maintenance. In this context, a model-based anomaly detection approach is proposed for monitoring the DC side of photovoltaic systems and temporary shading. First, a model based on the one-diode model is constructed to mimic the characteristics of the monitored photovoltaic array. Then, a one-class Support Vector Machine (1SVM) procedure is applied to residuals from the simulation model for fault detection. The choice of 1SVM approach to quantify the dissimilarity between normal and abnormal features is motivated by its good capability to handle nonlinear features and do not make assumptions on the underlying data distribution. Experimental results over real data from a 9.54 kWp grid-connected plant in Algiers, show the superior detection efficiency of the proposed approach compared with other binary clustering schemes (i.e., K-means, Birch, mean-shift, expectation–maximization, and agglomerative clustering).

[1]  N. Panwar,et al.  Role of renewable energy sources in environmental protection: A review , 2011 .

[2]  Josep M. Guerrero,et al.  Transient Monitoring Function–Based Fault Detection for Inverter-Interfaced Microgrids , 2018, IEEE Transactions on Smart Grid.

[3]  Wei Zhou,et al.  A novel model for photovoltaic array performance prediction , 2007 .

[4]  C. Nagamani,et al.  A Method to Detect Photovoltaic Array Faults and Partial Shading in PV Systems , 2016, IEEE Journal of Photovoltaics.

[5]  Mikhail Sorin,et al.  Explicit model of photovoltaic panels to determine voltages and currents at the maximum power point , 2011 .

[6]  Greg Ball,et al.  Comparative Evaluation of DC Fault-Mitigation Techniques in Large PV Systems , 2015, IEEE Journal of Photovoltaics.

[7]  Nabil Zerrouki,et al.  Statistical Monitoring of Changes to Land Cover , 2018, IEEE Geoscience and Remote Sensing Letters.

[8]  Sergei Vassilvitskii,et al.  k-means++: the advantages of careful seeding , 2007, SODA '07.

[9]  Ying Sun,et al.  Statistical fault detection in photovoltaic systems , 2017 .

[10]  Xiaodong Wang,et al.  Quickest Fault Detection in Photovoltaic Systems , 2018, IEEE Transactions on Smart Grid.

[11]  Giuseppe Acciani,et al.  Descriptive and Inferential Statistics for Supervising and Monitoring the Operation of PV Plants , 2009, IEEE Transactions on Industrial Electronics.

[12]  Fouzi Harrou,et al.  Unsupervised obstacle detection in driving environments using deep-learning-based stereovision , 2018, Robotics Auton. Syst..

[13]  Aissa Chouder,et al.  Monitoring, modelling and simulation of PV systems using LabVIEW , 2013 .

[14]  N. Rajasekar,et al.  A comprehensive review on protection challenges and fault diagnosis in PV systems , 2018, Renewable and Sustainable Energy Reviews.

[15]  Santiago Silvestre.  Strategies for Fault Detection and Diagnosis of PV Systems , 2018 .

[16]  Zhehan Yi,et al.  Line-to-Line Fault Detection for Photovoltaic Arrays Based on Multiresolution Signal Decomposition and Two-Stage Support Vector Machine , 2017, IEEE Transactions on Industrial Electronics.

[17]  David L. Olson,et al.  Advanced Data Mining Techniques , 2008 .

[18]  Aboelsood Zidan,et al.  Fault Detection, Isolation, and Service Restoration in Distribution Systems: State-of-the-Art and Future Trends , 2017, IEEE Transactions on Smart Grid.

[19]  Aissa Chouder,et al.  Modeling and simulation of a grid connected PV system based on the evaluation of main PV module parameters , 2012, Simul. Model. Pract. Theory.

[20]  Zhehan Yi,et al.  Fault Detection for Photovoltaic Systems Based on Multi-Resolution Signal Decomposition and Fuzzy Inference Systems , 2017, IEEE Transactions on Smart Grid.

[21]  Goran Knežević,et al.  The mathematical model for finding an optimal PV system configuration for the given installation area providing a maximal lifetime profit , 2017 .

[22]  Soteris A. Kalogirou,et al.  Fault detection and diagnosis methods for photovoltaic systems: A review , 2018, Renewable and Sustainable Energy Reviews.

[23]  T. Hiyama,et al.  Controlling of artificial neural network for fault diagnosis of photovoltaic array , 2011, 2011 16th International Conference on Intelligent System Applications to Power Systems.

[24]  Jay Johnson,et al.  A Comprehensive Review of Catastrophic Faults in PV Arrays: Types, Detection, and Mitigation Techniques , 2015, IEEE Journal of Photovoltaics.

[25]  Bernhard Schölkopf,et al.  Estimating the Support of a High-Dimensional Distribution , 2001, Neural Computation.

[26]  William A. Beckman,et al.  Improvement and validation of a model for photovoltaic array performance , 2006 .

[27]  A. Hadj Arab,et al.  Improvement and validation of PV motor-pump model for PV pumping system performance analysis , 2017 .

[28]  D. Karaboga,et al.  On the performance of artificial bee colony (ABC) algorithm , 2008, Appl. Soft Comput..

[29]  Saeed Lotfifard,et al.  Modeling and Health Monitoring of DC Side of Photovoltaic Array , 2015, IEEE Transactions on Sustainable Energy.

[30]  Rabah Benkercha,et al.  Fault detection and diagnosis based on C4.5 decision tree algorithm for grid connected PV system , 2018, Solar Energy.

[31]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[32]  H. Mekki,et al.  Artificial neural network-based modelling and fault detection of partial shaded photovoltaic modules , 2016, Simul. Model. Pract. Theory.

[33]  Wei Wang,et al.  Incident detection algorithm based on partial least squares regression , 2008 .

[34]  J. Ma,et al.  Time-series novelty detection using one-class support vector machines , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[35]  Derrick Holliday,et al.  Thermography-Based Virtual MPPT Scheme for Improving PV Energy Efficiency Under Partial Shading Conditions , 2014, IEEE Transactions on Power Electronics.

[36]  Siva Ramakrishna Madeti,et al.  Modeling of PV system based on experimental data for fault detection using kNN method , 2018, Solar Energy.

[37]  Ye Zhao,et al.  Line–Line Fault Analysis and Protection Challenges in Solar Photovoltaic Arrays , 2013, IEEE Transactions on Industrial Electronics.

[38]  Imane Drouiche,et al.  A new approach for modelling the aging PV module upon experimental I–V curves by combining translation method and five-parameters model , 2018, Electric Power Systems Research.

[39]  Tian Zhang,et al.  BIRCH: an efficient data clustering method for very large databases , 1996, SIGMOD '96.

[40]  Ying Sun,et al.  Reliable fault detection and diagnosis of photovoltaic systems based on statistical monitoring approaches , 2018 .

[41]  Ying Sun,et al.  Robust and flexible strategy for fault detection in grid-connected photovoltaic systems , 2019, Energy Conversion and Management.