Adam B. Shinn
Research Subjects
Adam B. Shinn has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Ambarish Nag
Computational Science Center, National Renewable Energy Laboratory, 15013 Denver West Pkwy, Golden, CO 80401, USA
2 shared publications - Dirk Jordan
National Laboratory of the Rockies, Golden, CO (United States)
2 shared publications - Michael G. Deceglie
National Renewable Energy Laboratory
2 shared publications - Aaesha Alnuaimi
Dubai Electricity And Water Authority, P.O. Box 564, Dubai, United Arab Emirates, Dubai, UNITED ARAB EMIRATES
1 shared publication - Ammar B. A. Elnosh
Dubai Electricity & Water Authority, Dubai, UAE
1 shared publication - Anubhav Jain
Energy Technologies Area, Lawrence Berkeley National Laboratory, Berkeley, USA
1 shared publication
Latest Publications
- Open Access
- 20 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1606-1609
Assessing Machine Learning as a Tool to Explain Variance in Deployed Photovoltaic (PV) System Degradation
Degradation remains a large uncertainty in forecasting production for PV plants, creating significant risk for developers and financiers. This study aims to quantify the distribution and drivers of degradation across 10,000 PV systems deployed for distributed or utility generation by training a machine learning model to predict year-over-year degradation rates from metadata characteristics. A combination of K-Means clustering and random forest regressor were found to associate multiple metadata features as potential drivers of degradation, including module characteristics, system design, and climate features. From this, it is inferred that if machine learning is able to find complex patterns between metadata features and system performance loss, such methods can be employed to help developers and financiers make data-informed decisions when estimating long-term energy production forecasts in financial models.
- 20 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1606-1609
Open AccessAssessing Machine Learning as a Tool to Explain Variance in Deployed Photovoltaic (PV) System Degradation
Degradation remains a large uncertainty in forecasting production for PV plants, creating significant risk for developers and financiers. This study aims to quantify the distribution and drivers of degradation across 10,000 PV systems deployed for distributed or utility generation by training a machine learning model to predict year-over-year degradation rates from metadata characteristics. A combination of K-Means clustering and random forest regressor were found to associate multiple metadata features as potential drivers of degradation, including module characteristics, system design, and climate features. From this, it is inferred that if machine learning is able to find complex patterns between metadata features and system performance loss, such methods can be employed to help developers and financiers make data-informed decisions when estimating long-term energy production forecasts in financial models.
- 18 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Photovoltaics
- Vol. 10 (1) , 206-212
Reducing Interanalyst Variability in Photovoltaic Degradation Rate Assessments
The economic return on investment of a commercial photovoltaic system depends greatly on its performance over the long term and, hence, its degradation rate. Many methods have been proposed for assessing system degradation rates from outdoor performance data. However, comparing reported values from one analyst and research group to another requires a common baseline of performance; consistency between methods and analysts can be a challenge. An interlaboratory study was conducted involving different volunteer analysts reporting on the same photovoltaic performance data using different methodologies. Initial variability of the reported degradation rates was so high that analysts could not come to a consensus whether a system degraded or not. More consistent values are received when written guidance is provided to each analyst. Further improvements in analyst variance was accomplished by using the free open-source software RdTools, allowing a reduction in variance between analysts by more than two orders of magnitude over the first round, where multiple analysis methods are allowed. This article highlights many pitfalls in conducting “routine” degradation analysis, and it addresses some of the factors that must be considered when comparing degradation results reported by different analysts or methods.
- 18 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Photovoltaics
- Vol. 10 (1) , 206-212
Reducing Interanalyst Variability in Photovoltaic Degradation Rate Assessments
The economic return on investment of a commercial photovoltaic system depends greatly on its performance over the long term and, hence, its degradation rate. Many methods have been proposed for assessing system degradation rates from outdoor performance data. However, comparing reported values from one analyst and research group to another requires a common baseline of performance; consistency between methods and analysts can be a challenge. An interlaboratory study was conducted involving different volunteer analysts reporting on the same photovoltaic performance data using different methodologies. Initial variability of the reported degradation rates was so high that analysts could not come to a consensus whether a system degraded or not. More consistent values are received when written guidance is provided to each analyst. Further improvements in analyst variance was accomplished by using the free open-source software RdTools, allowing a reduction in variance between analysts by more than two orders of magnitude over the first round, where multiple analysis methods are allowed. This article highlights many pitfalls in conducting “routine” degradation analysis, and it addresses some of the factors that must be considered when comparing degradation results reported by different analysts or methods.
- 1 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Photovoltaics
- Vol. 9 (2) , 476-482
Fleet-Scale Energy-Yield Degradation Analysis Applied to Hundreds of Residential and Nonresidential Photovoltaic Systems
- 1 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Photovoltaics
- Vol. 9 (2) , 476-482
Fleet-Scale Energy-Yield Degradation Analysis Applied to Hundreds of Residential and Nonresidential Photovoltaic Systems