MORE | Management of Real-time Energy Data - Upcoming webinar from MORE: Data-driven soiling detection in PV modules

We present a solution to the problem of estimating the soiling ratio in photo-voltaic (PV) modules, i.e., the ratio of the real power output to the power output that would be produced if solar panels were clean. A key advantage of our method is that it can estimate soiling, without needing to train on labelled data, i.e., periods of explicitly monitoring the soiling in each park, and without relying on generic analytical formulas which do not take into account the peculiarities of each installation. We consider as input a time series comprising a minimum set of measurements, that are available to most PV park operators. Our experimental evaluation shows that we significantly outperform current state-of-the-art methods for estimating soiling ratio.

Short Bio

Ioannis Psarros received his Bsc. degree in Informatics and Telecommunications from the National Kapodistrian University of Athens (NKUA), Greece, in 2013, his Msc. degree in Logic, Algorithms and Computation from NKUA, in 2015, and his PhD in Computer Science from NKUA, in 2019. He is currently a Scientific Associate at IMSI of Athena Research. Prior to that, he was a postdoctoral researcher at the University of Bonn and an affiliated member of the Hausdorff Center for Mathematics in Bonn, Germany. His research interests include time series analysis and proximity problems for high-dimensional data.

Date: Friday 31 March, 11.00 EET

20 Mar 2023