TY - JOUR
T1 - Machine Learning for Solar Array Monitoring, Optimization, and Control
AU - Rao, Sunil
AU - Katoch, Sameeksha
AU - Narayanaswamy, Vivek
AU - Muniraju, Gowtham
AU - Tepedelenlioglu, Cihan
AU - Spanias, Andreas
AU - Turaga, Pavan
AU - Ayyanar, Raja
AU - Srinivasan, Devarajan
N1 - Funding Information:
The study was supported in part by the NSF CPS award 1659871. Portions were also supported by the NSF IRES program award 1854273. Logistical support was provided by the ASU SenSIP center and NCSS I/UCRC site. We also thank Ph.D. student Jie Fan for his contribution on graph signal processing for fault detection.
Publisher Copyright:
Copyright © 2020 by Morgan & Claypool.
PY - 2020
Y1 - 2020
N2 - The efficiency of solar energy farms requires detailed analytics and information on each panel regarding voltage, current, temperature, and irradiance. Monitoring utility-scale solar arrays was shown to minimize the cost of maintenance and help optimize the performance of the photo-voltaic arrays under various conditions. We describe a project that includes development of machine learning and signal processing algorithms along with a solar array testbed for the purpose of PV monitoring and control. The 18kW PV array testbed consists of 104 panels fitted with smart monitoring devices. Each of these devices embeds sensors, wireless transceivers, and relays that enable continuous monitoring, fault detection, and real-time connection topology changes. The facility enables networked data exchanges via the use of wireless data sharing with servers, fusion and control centers, and mobile devices. We develop machine learning and neural network algorithms for fault classification. In addition, we use weather camera data for cloud movement prediction using kernel regression techniques which serves as the input that guides topology reconfiguration. Camera and satellite sensing of skyline features as well as parameter sensing at each panel provides information for fault detection and power output optimization using topology reconfiguration achieved using programmable actuators (relays) in the SMDs. More specifically, a custom neural network algorithm guides the selection among four standardized topologies. Accuracy in fault detection is demonstrate at the level of 90+% and topology optimization provides increase in power by as much as 16% under shading.
AB - The efficiency of solar energy farms requires detailed analytics and information on each panel regarding voltage, current, temperature, and irradiance. Monitoring utility-scale solar arrays was shown to minimize the cost of maintenance and help optimize the performance of the photo-voltaic arrays under various conditions. We describe a project that includes development of machine learning and signal processing algorithms along with a solar array testbed for the purpose of PV monitoring and control. The 18kW PV array testbed consists of 104 panels fitted with smart monitoring devices. Each of these devices embeds sensors, wireless transceivers, and relays that enable continuous monitoring, fault detection, and real-time connection topology changes. The facility enables networked data exchanges via the use of wireless data sharing with servers, fusion and control centers, and mobile devices. We develop machine learning and neural network algorithms for fault classification. In addition, we use weather camera data for cloud movement prediction using kernel regression techniques which serves as the input that guides topology reconfiguration. Camera and satellite sensing of skyline features as well as parameter sensing at each panel provides information for fault detection and power output optimization using topology reconfiguration achieved using programmable actuators (relays) in the SMDs. More specifically, a custom neural network algorithm guides the selection among four standardized topologies. Accuracy in fault detection is demonstrate at the level of 90+% and topology optimization provides increase in power by as much as 16% under shading.
KW - PV inverters
KW - PV topology optimization
KW - computer vision in PV
KW - deep learning
KW - graph signal processing
KW - machine learning
KW - neural networks
KW - photovoltaic systems
KW - smart grid
KW - solar array fault detection
KW - solar panel shading
UR - http://www.scopus.com/inward/record.url?scp=85096183706&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85096183706&partnerID=8YFLogxK
U2 - 10.2200/S01027ED1V01Y202006PEL013
DO - 10.2200/S01027ED1V01Y202006PEL013
M3 - Article
AN - SCOPUS:85096183706
SN - 1931-9525
VL - 7
SP - 1
EP - 91
JO - Synthesis Lectures on Power Electronics
JF - Synthesis Lectures on Power Electronics
IS - 1
ER -