Geodesic
Methods and software for anomalies searching in the telemetry data of a solar power plant based on the artificial neuron network – autoencoder
Problemy fiziki, matematiki i tehniki, no. 3 (2024), pp. 92-100.

Voir la notice de l'article provenant de la source Math-Net.Ru

A new method and software tool for identifying anomalies in the operation of solar panels have been developed based on an artificial neural network of the autoencoder type, trained using solar power plant telemetry data. The method is based on statistical studies of deviations measured from the values of current and voltage of all solar panels of the power plant restored by the neural network. A criterion for assessing the presence of a malfunction in the operation of a solar panel based on statistical studies is introduced. Using the developed methodology and software for searching for anomalies in telemetry data over six months of observations, 14 to 45 anomalies were detected in 33 solar panels under different evaluation criteria. All the cases were analyzed for the causes of anomalies in the operation of solar panels. It has been established that the use of four standard deviations for average daily measured values of current $\Delta I$ and voltage $\Delta U$ as anomaly detection criterion in the analysis of the results of the artificial neural network operation makes it possible to detect faulty solar panels. And the use of three and two standard deviations as anomaly detection criterion can help to detect a decrease in the efficiency of solar panels associated with degradation, excessive shading and other factors.
Keywords: solar panel, normalized power value, anomaly detection, maximum power point, solar power plant, telemetry. 
@article{PFMT_2024_3_a15,
     author = {K. S. Dzick and N. I. Mukhurov and I. Kruse and R. M. Asimov and V. S. Asipovich},
     title = {Methods and software for anomalies searching in the telemetry data of a solar power plant based on the artificial neuron network {\textendash} autoencoder},
     journal = {Problemy fiziki, matematiki i tehniki},
     pages = {92--100},
     publisher = {mathdoc},
     number = {3},
     year = {2024},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/PFMT_2024_3_a15/}
}
TY  - JOUR
AU  - K. S. Dzick
AU  - N. I. Mukhurov
AU  - I. Kruse
AU  - R. M. Asimov
AU  - V. S. Asipovich
TI  - Methods and software for anomalies searching in the telemetry data of a solar power plant based on the artificial neuron network – autoencoder
JO  - Problemy fiziki, matematiki i tehniki
PY  - 2024
SP  - 92
EP  - 100
IS  - 3
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/PFMT_2024_3_a15/
LA  - ru
ID  - PFMT_2024_3_a15
ER  - 
%0 Journal Article
%A K. S. Dzick
%A N. I. Mukhurov
%A I. Kruse
%A R. M. Asimov
%A V. S. Asipovich
%T Methods and software for anomalies searching in the telemetry data of a solar power plant based on the artificial neuron network – autoencoder
%J Problemy fiziki, matematiki i tehniki
%D 2024
%P 92-100
%N 3
%I mathdoc
%U http://geodesic.mathdoc.fr/item/PFMT_2024_3_a15/
%G ru
%F PFMT_2024_3_a15
K. S. Dzick; N. I. Mukhurov; I. Kruse; R. M. Asimov; V. S. Asipovich. Methods and software for anomalies searching in the telemetry data of a solar power plant based on the artificial neuron network – autoencoder. Problemy fiziki, matematiki i tehniki, no. 3 (2024), pp. 92-100. http://geodesic.mathdoc.fr/item/PFMT_2024_3_a15/

[1] P. Dorin, C. Farcas, I. Ciocan, “Modelling and simulation of photovoltaic cells”, ACTA Technica Napocensis, 49:1 (2008), 42-47

[2] O.D. Adeniyi et al., “Modeling and simulation of energy recovery from a photovoltaic solar cell”, Nigerian J. of Technological Research, 11 (2016), 26-31 | DOI

[3] T. Salmi et al., “MATLAB/Simulink based modelling of solar photovoltaic cell”, Intern. J. of Renewable Energy Research, 2:2 (2012), 213-218

[4] G. Tina, F. Cosentino, C. Ventura, “Monitoring and diagnostics of photovoltaic power plants”, Renewable Energy in the Service of Mankind, v. 2, ed. A. Sayigh, Springer, Cham, 2016, 505-516 | DOI

[5] M. Ibbini, A. Adawi, “Analysis and design of a maximum power point tracker for a stand-alone photo voltaic system using simscape”, Intern. J. of Advanced Trends in Computer Science and Engineering, 8:1 (2019), 54-57 | DOI

[6] Md.M. Rashid, A. Habib, M. Mahdi Hasan, “Design and construction of the solar photovoltaic simulation system with the implementation of MPPT and boost converter using Matlab/Simulink”, Asian J. of Current Research, 3:1 (2018), 27-36

[7] G.-A. Leopoldo et al., “Flatness-based control for the maximum power point tracking in a photovoltaic system”, Energies, 12 (2019), 1843–1862 | DOI

[8] N. Kishor et al., “Modeling of PV module with consideration of environmental factors”, 2010 IEEE PES Innovative Smart Grid Technologies Conf. Europe (ISGT Europe) (Gothenburg, Sweden, 11-13 Oct. 2010), Gothenburg, 2010, 121-126

[9] N. Kishor et al., “Simulation of PV array output power for modified PV cell model”, 2010 IEEE Intern. Conf. on Power and Energy (Kuala Lumpur, Malaysia, 29 Nov. - 01 Dec. 2010), Kuala Lumpur, 2010, 533-538 | DOI

[10] Y. Wang et al., “Steady-state model and power flow analysis of grid-connected photovoltaic power system”, 2008 IEEE Intern. Conf. on Industrial Technology (Chengdu, China, 21-24 Apr. 2008), Chengdu, 2008, 1-6

[11] R.M. Asimov et al., “Virtual laboratory for testing of solar power plants in big data analysis”, Collection of Materials of the V Intern. Scientific and Practical Conf. “Big Data and Advanced Analytics” (Minsk, 13-14 Mar. 2019), Minsk, 2019, 61-65

[12] V.S. Asipovich, R.M. Asimov, S.V. Chernoshey, “Digital twin in the analysis of a big data”, Collection of Materials of the IV Intern. Scientific and Practical Conf. “Big Data and Advanced Analytics” (Minsk, 3-4 May 2018), Minsk, 2018, 69-78 | MR

[13] S. Valevich et al., “Digital twin for PV module fault detection”, J. of Engineering Science, XXVII:4 (2020), 80–87

[14] R. M. Asimov et al., “Digital twin for PV plant's power generation analysis”, Collection of Materials of the VI Intern. Scientific and Practical Conf. “Big Data and Advanced Analytics” (Minsk, 20-21 May 2020), Minsk, 2020, 78-88

[15] M. Mansouri, M. Trabelsi, H. Nounou, M. Nounou, “Deep Learning-Based Fault Diagnosis of Photovoltaic Systems: A Comprehensive Review and Enhancement Prospects”, IEEE Access, 9 (2021), 126286–126306 | DOI

[16] M. Jaber, A. Sufiyan, A. Hamid, K. Sopian, A. Fazlizan, A. Ibrahim, “Prediction Model for the Performance of Different PV Modules Using Artificial Neural Networks”, Appl. Sci., 12 (2022), 3349 | DOI

[17] Y. Zhang, C. Qin, A.K. Srivastava, C. Jin, R.K. Sharma, “Data-Driven Day-Ahead PV Estimation Using Autoencoder-LSTM and Persistence Model”, IEEE Transactions on Industry Applications, 56:6 (2020), 7185–7192 | DOI

[18] M. Ibrahim, A. Alsheikh, F.M. Awaysheh, M.D. Alshehri, “Machine Learning Schemes for Anomaly Detection in Solar Power Plants”, Energies, 15 (2022), 1082 | DOI

[19] S. V. Valevich i dr., “Informatsionnoe obespechenie monitoringa tekhnicheskogo sostoyaniya solnechnykh elektrostantsii”, Informatsionnye tekhnologii, 26:10 (2020), 594-601

[20] K.S. Dik, “Metodika poiska defektnykh solnechnykh panelei v dannykh telemetrii elektrostantsii na osnove rezultatov raboty tsifrovogo dvoinika”, Doklady BGUIR, 21:6 (2023), 113-120

[21] K.S. Dzik et al., “Methods and software tool for automating static and dynamic search for anomalies in telemetry data of a solar power plant”, International Journal of Advanced Research, 11:8 (2023), 143-155 | DOI