Expected output calculation based on inverse distance weighting and its application in anomaly detection of distributed photovoltaic power stations

Abstract With the increasing installed capacity of distributed photovoltaic generation, the anomaly detection is of great significance for the safe operation of distributed photovoltaic stations. Due to the lack of weather station, meteorological data based assessment and fault diagnosis methods are not applicable. To solve the problem, this paper proposes an expected output calculation and anomaly detection method based on inverse distance weighting. Output characteristics of different distributed stations in certain area are first analyzed, which show correlation with each other, the expected output calculation method of distributed stations is then proposed based on the inverse distance weighting algorithm. Robustness analysis is conducted to study the performance of inverse distance weighting method under different conditions. The parameters optimization of inverse distance weighting method is analyzed for its utilization in distributed photovoltaic generation. Three time series indexes: spatial performance ratio, similarity coefficient, and feature distance are selected as the anomaly detection indicators. Finally, an experimental study on the anomaly detection approach is conducted to prove its feasibility.

[1]  Cyril Voyant,et al.  Predictability of PV power grid performance on insular sites without weather stations: use of artificial neural networks , 2009, ArXiv.

[2]  Xurong Mei,et al.  A sustainable agricultural development assessment method and a case study in China based on euclidean distance theory , 2017 .

[3]  M. Diagne,et al.  Review of solar irradiance forecasting methods and a proposition for small-scale insular grids , 2013 .

[4]  Ying-Ming Wang,et al.  A new environmental governance cost prediction method based on indicator synthesis and different risk coefficients , 2019, Journal of Cleaner Production.

[5]  M. Braun,et al.  Analysis of the uncertainty in the estimates of regional PV power generation evaluated with the upscaling method , 2016 .

[6]  D. Shepard.  A two-dimensional interpolation function for irregularly-spaced data , 1968, ACM National Conference.

[7]  Ravindra Boojhawon,et al.  High resolution spatio-temporal modelling of solar photovoltaic potential for tropical islands: Case of Mauritius , 2019, Energy.

[8]  Aissa Chouder,et al.  Automatic fault detection in grid connected PV systems , 2013 .

[9]  Fatih Evrendilek,et al.  Assessing solar radiation models using multiple variables over Turkey , 2008 .

[10]  David W. S. Wong,et al.  An adaptive inverse-distance weighting spatial interpolation technique , 2008, Comput. Geosci..

[11]  Nicholas A. Engerer,et al.  Improved satellite-derived PV power nowcasting using real-time power data from reference PV systems , 2017, Solar Energy.

[12]  Gordon Reikard.  Predicting solar radiation at high resolutions: A comparison of time series forecasts , 2009 .

[13]  J. A. Ruiz-Arias,et al.  Benchmarking of different approaches to forecast solar irradiance , 2009 .

[14]  Chunhua Wu,et al.  An Intelligent Method for Fault Diagnosis in Photovoltaic Array , 2012 .

[15]  Masashi Baba,et al.  Examination of fault detection technique in PV systems , 2013 .

[16]  Siva Ramakrishna Madeti,et al.  Online modular level fault detection algorithm for grid-tied and off-grid PV systems , 2017 .

[17]  Amany El-Zonkoly,et al.  Fault diagnosis in distribution networks with distributed generation , 2011 .

[18]  Indradip Mitra,et al.  Performance ratio – Crucial parameter for grid connected PV plants , 2016 .

[19]  Stan Szpakowicz,et al.  Beyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation , 2006, Australian Conference on Artificial Intelligence.

[20]  E. E. van Dyk,et al.  Analysis of measured and simulated performance data of a 3.2 kWp grid-connected PV system in Port Elizabeth, South Africa , 2015 .

[21]  Yang Hu,et al.  Fault diagnosis approach for photovoltaic arrays based on unsupervised sample clustering and probabilistic neural network model , 2018, Solar Energy.

[22]  Aissa Chouder,et al.  Automatic supervision and fault detection of PV systems based on power losses analysis , 2010 .

[23]  Mamdouh El Haj Assad,et al.  Comparison of artificial intelligence methods in estimation of daily global solar radiation , 2018, Journal of Cleaner Production.

[24]  Hamidreza Zareipour,et al.  Performance assessment of photovoltaic modules based on daily energy generation estimation , 2018, Energy.

[25]  K. Otani,et al.  Experimental Studies of Failure Detection Methods in PV Module Strings , 2006, 2006 IEEE 4th World Conference on Photovoltaic Energy Conference.

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

[27]  Yang Hu,et al.  Study of joint temporal-spatial distribution of array output for large-scale photovoltaic plant and its fault diagnosis application , 2019 .

[28]  Nils Jakob Johannesen,et al.  Relative evaluation of regression tools for urban area electrical energy demand forecasting , 2019, Journal of Cleaner Production.

[29]  Farid Melgani,et al.  Multi-step ahead forecasting of daily global and direct solar radiation: A review and case study of Ghardaia region , 2018, Journal of Cleaner Production.

[30]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.

[31]  I. Loghmari,et al.  Performance comparison of two global solar radiation models for spatial interpolation purposes , 2018 .

[32]  Giuseppe Marco Tina,et al.  PV array fault DiagnosticTechnique for BIPV systems , 2016 .

[33]  Abdelhamid Rabhi,et al.  Neuro-Fuzzy fault detection method for photovoltaic systems , 2014 .

[34]  Khalid Zenkouar,et al.  New daily global solar irradiation estimation model based on automatic selection of input parameters using evolutionary artificial neural networks , 2019, Journal of Cleaner Production.