Filters








2 Hits in 2.6 sec

DeepSolarEye: Power Loss Prediction and Weakly Supervised Soiling Localization via Fully Convolutional Networks for Solar Panels [article]

Sachin Mehta, Amar P. Azad, Saneem A. Chemmengath, Vikas Raykar, and Shivkumar Kalyanaraman
2018 arXiv   pre-print
Our approach takes an RGB image of solar panel and environmental factors as inputs to predict power loss, soiling localization, and soiling type.  ...  In this paper, we present the first convolutional neural network (CNN) based approach for solar panel soiling and defect analysis.  ...  Acknowledgments The authors thank Mohit Jain for helping in designing the subjective assessment study.  ... 
arXiv:1710.03811v2 fatcat:jwudomzuzjgwxe2eajxnrhfzeu

Decision Support System Design for Photovoltaic Systems Operation and Maintenance by using Big Data Technologies

Oprea Simona Vasilica, Bâra Adela, Elefterescu Luminița
2018 Ovidius University Annals: Economic Sciences Series  
Main goal of this paper is to present a decision support system (DSS) for operation andmaintenance (O&M) of photovoltaic power (PV) systems which are integrated with batterysystems.  ...  Such DSS essentially necessitates inclusion of Big Data analytics that will be utilized tomaximize profit from power generation and consumption in a PV-battery integrated system.  ...  DeepSolarEye: Power Loss Prediction and Weakly Supervised Localization via Fully Convolutional Networks for /arxiv.org/pdf/1710.03811.pdf. [Accessed 28 December 2017] • Mokri J., Cunningham J., 2014.  ... 
doaj:38365e52bf4e44a1ae6630aed46ea203 fatcat:oj6jxp222jfpfgtnaj6i5jol5a