TY - GEN
T1 - Real-time Solar Array Data Acquisition and Fault Detection using Neural Networks
AU - Rao, Sunil
AU - Pujara, Deep
AU - Spanias, Andreas
AU - Tepedelenlioglu, Cihan
AU - Srinivasan, Devarajan
N1 - Funding Information:
This research is supported in part by the NSF CPS Award number 1646542 and MRI award 2019068. Infrastructure for our experiments is provided by the ASU SenSIP Center.
Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Continuous real-time solar system monitoring for fault detection and classification can improve solar panel efficiency and overall output. In this study, we developed and implemented a real-time PV fault detection system based on machine learning. The system was implemented on an 18kW testbed facility which consists of 104 solar panels located at the ASU Research Park. Each solar panel is connected to a smart monitoring device (SMD) which obtains real-time voltage and current measurements. SMDs are attached to each panel and transmit all the acquired data to a server that is connected to the internet. We implement fault detection using real-time measurements and various neural network architectures. We train and test both fully connected and dropout neural networks with different dropout regularization. We use both a real-time dataset and a synthetic dataset and present comparative results. We train and classify for the following conditions: soiled panels, shaded and degraded panels, and standard test conditions.
AB - Continuous real-time solar system monitoring for fault detection and classification can improve solar panel efficiency and overall output. In this study, we developed and implemented a real-time PV fault detection system based on machine learning. The system was implemented on an 18kW testbed facility which consists of 104 solar panels located at the ASU Research Park. Each solar panel is connected to a smart monitoring device (SMD) which obtains real-time voltage and current measurements. SMDs are attached to each panel and transmit all the acquired data to a server that is connected to the internet. We implement fault detection using real-time measurements and various neural network architectures. We train and test both fully connected and dropout neural networks with different dropout regularization. We use both a real-time dataset and a synthetic dataset and present comparative results. We train and classify for the following conditions: soiled panels, shaded and degraded panels, and standard test conditions.
KW - Deep Learning
KW - Fault Detection
KW - Photovoltaic Cyber-Physical Systems
UR - http://www.scopus.com/inward/record.url?scp=85163085673&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85163085673&partnerID=8YFLogxK
U2 - 10.1109/ICPS58381.2023.10128030
DO - 10.1109/ICPS58381.2023.10128030
M3 - Conference contribution
AN - SCOPUS:85163085673
T3 - Proceedings - 2023 IEEE 6th International Conference on Industrial Cyber-Physical Systems, ICPS 2023
BT - Proceedings - 2023 IEEE 6th International Conference on Industrial Cyber-Physical Systems, ICPS 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 6th IEEE International Conference on Industrial Cyber-Physical Systems, ICPS 2023
Y2 - 8 May 2023 through 11 May 2023
ER -