在這個能源需求不斷上升化石能源不斷稀缺的時代，再生能源已
然成為能源發展的重點，其中再生能源的裝機容量中以水力、風力及
太陽能最大，太陽能也為近期發展最為重視的發展目標，除了不斷擴
大建設太陽能的建置外，由於太陽能的建設通常為大範圍定期的巡檢
費時費力又不一定找得出故障，必須思考設計出管理太陽能發電系統
的故障狀態檢測機制以提高管理案場的可靠性，透過於案場設備讀取
所得到的設備數據進行數據分析，以快速找出太陽能故障的位置並加
以排除，以維持太陽能電廠的最佳發電性能與太陽能系統的效益。
有鑑於此，本研究旨在研究如何檢測太陽能系統故障，其中包含:
(1) 研究太陽能監控架構及故障狀態檢測方法，(2) 監控系統的相關
設置，(3) 故障狀態檢測的機制建立，(4) 撰寫故障狀態檢測相關程
式語言相關功能，(5) 實際運行並找出故障位置，(6)實際案場驗證故
障並分析原因，經測試得以證明藉由有效的故障狀態檢測方式可以在
短時間內發現故障並修繕減少發電損失，該方法可對於大型太陽能電
廠在故障狀態檢測與電廠效能評估上，提供一個具有價值的參考依
據。

In this era of rising energy demand, petrochemical energy is
constantly scarce, renewable energy has become the focus of energy
development, among them, the installed capacity of renewable energy is
hydropower, wind power and solar energy. Solar energy is also the most
important development goal for recent development. In addition to
continuously expanding the building of solar energy, since the
construction of solar energy is usually a large-scale regular inspection, it
is time-consuming and laborious and may not necessarily find faults. We
must think about designing a fault diagnosis mechanism for managing
solar power generation systems to improve the reliability of the
management case. Data analysis is carried out through the equipment data
obtained by reading the equipment in the field. In order to quickly find
the location of the solar failure and eliminate it, to maintain the best
power generation performance of solar power plants and the benefits of
solar systems.
In view of this, this research aims to study how to detect solar system
failures, including: (1) Research on solar monitoring architecture and
fault diagnosis methods, (2) Related settings of the monitoring system, (3)
Establishment of fault diagnosis mechanism, (4) Compose programming
language related functions related to fault diagnosis, (5) Actual operation
and find out the fault location, (6) The actual case verifies the failure and
analyzes the cause, tests have proved that through effective fault
diagnosis methods, faults can be found and repaired in a short time to
reduce power loss. This method can be used for fault diagnosis and power
plant efficiency evaluation of large-scale solar power plants. Provide a
valuable reference basis.

[1] REN21, RENEWABLES 2019 GLOBAL STATUS REPORT. Retrieved April 15, 2020, from https://www.ren21.net/wp-content/uploads/2019/05/gsr_2019_full_report_en.pdf
[2] Semantic scholar, Maintenance Optimization of Offshore Wind Power - Concept Development for Future Cost Reduction Master of Science Thesis in Management and Economics of Innovation
https://www.semanticscholar.org/paper/Maintenance-Optimization-of-Offshore-Wind-Power-for-Gustavsson-Nyberg/b83afdc824a33d9083c1c3095e44dc0ac7663daa
[3] National Renewable Energy Laboratory, Sandia National Laboratory, SunSpec Alliance, and the SunShot National Laboratory Multiyear Partnership (SuNLaMP) PV O&M Best Practices Working Group. 2018. Best Practices for Operation and Maintenance of Photovoltaic and Energy Storage Systems; 3rd Edition. Golden, CO: National Renewable Energy Laboratory. NREL/TP-7A40-73822. https://www.nrel.gov/docs/fy19osti/73822.pdf.
[4] Solar Power Europe, Inc. Operation & Maintenance Best Practice Guidelines / Version 4.0. Retrieved March 8, 2020, from https://www.solarpowereurope.org/om-best-practice-guidelines-version-4-0/.
[5] IEC61724-1ed1.0, Photovoltaic System Performance - Part 1: Monitoring, March 2017.
[6] IEC61724:1998, Photovoltaic System Performance Monitoring – Guidelines for Measurement, Data Exchange and Analysis, first ed., Switz. IEC, Geneva,1998.

[7] Ding, Hanxiang, et al. "Local outlier factor-based fault detection and evaluation of photovoltaic system." Solar Energy 164 (2018): 139-148.
[8] Ammiche, Mustapha, et al. "Fault detection in a grid-connected photovoltaic system using adaptive thresholding method." Solar Energy 174 (2018): 762-769.
[9] Kopp, Emily S., et al. "I–V curves and visual inspection of 250 PV modules deployed over 2 years in Tucson." 2012 38th IEEE Photovoltaic Specialists Conference. IEEE, 2012.
[10] Stegner, C., et al. "Monitoring and assessment of PV generation based on a combination of smart metering and thermographic measurement." Solar Energy 163 (2018): 16-24.
[11] Karimi, A. M., Fada, J. S., Liu, J., Braid, J. L., Koyutürk, M., & French, R. H. (2018, June). Feature extraction, supervised and unsupervised machine learning classification of PV cell electroluminescence images. In 2018 IEEE 7th World Conference on Photovoltaic Energy Conversion (WCPEC)(A Joint Conference of 45th IEEE PVSC, 28th PVSEC & 34th EU PVSEC) (pp. 0418-0424). IEEE.
[12] Dhoke, Amit, Rahul Sharma, and Tapan Kumar Saha. "An approach for fault detection and location in solar PV systems." Solar Energy 194 (2019): 197-208.
[13] Madeti, Siva Ramakrishna, and S. N. Singh. "Modeling of PV system based on experimental data for fault detection using kNN method." Solar Energy 173 (2018): 139-151.
[14] Ding, Hanxiang, et al. "Local outlier factor-based fault detection and evaluation of photovoltaic system." Solar Energy 164 (2018): 139-148.
[15] Ammiche, Mustapha, et al. "Fault detection in a grid-connected photovoltaic system using adaptive thresholding method." Solar Energy 174 (2018): 762-769.
[16] Livera, Andreas, et al. "Recent advances in failure diagnosis techniques based on performance data analysis for grid-connected photovoltaic systems." Renewable energy 133 (2019): 126-143.
[17] Bressan, M., El Basri, Y., Galeano, A. G., & Alonso, C. (2016). A shadow fault detection method based on the standard error analysis of IV curves. Renewable Energy, 99, 1181-1190.
[18] Sibai, Fadi N. "Power, Voltage, and Current Characteristics of Photovoltaic Modules in Saudi Arabian Cities." 2020 7th International Conference on Electrical and Electronics Engineering (ICEEE). IEEE, 2020.
[19] Ma, Jieming, et al. "Automatic shading detection system for photovoltaic strings." 2018 International SoC Design Conference (ISOCC). IEEE, 2018.
[20] Ventura, C., & Tina, G. M. (2015). Development of models for on-line diagnostic and energy assessment analysis of PV power plants: The study case of 1 MW Sicilian PV plant. Energy Procedia, 83, 248-257.
[21] Chine, W., and A. Mellit. "ANN-based fault diagnosis technique for photovoltaic stings." 2017 5th International Conference on Electrical Engineering-Boumerdes (ICEE-B). IEEE, 2017.