Solar cell designs by maximizing energy production based on machine learning clustering of spectral variations
Though multijunction solar cells can exceed silicon technology in terms of standard efficiency, the uncertainty in solar spectral changes impacts its energy production. Here, the authors use machine learning techniques to predict the optimal solar cell designs in terms of yearly averaged efficiency.
Main Authors: | J. M. Ripalda, J. Buencuerpo, I. García |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2018-12-01
|
Series: | Nature Communications |
Online Access: | https://doi.org/10.1038/s41467-018-07431-3 |
Similar Items
-
Maximizing Solar Energy Production for Västra Stenhagenskolan : Designing an Optimal PV System
by: Kristofersson, Filip, et al.
Published: (2019) -
Spectral threshold dominance, Brouwer's conjecture and maximality of Laplacian energy
by: Helmberg, Christoph, et al.
Published: (2015) -
A Spectral Clustering Approach based on Modularity Maximization for Community Detection Problem
by: Sheng-Kai Chou, et al.
Published: (2015) -
Maximizing network throughput by cooperative reinforcement learning in clustered solar-powered wireless sensor networks
by: Yujia Ge, et al.
Published: (2021-04-01) -
Solar spectral variations and their influence on concentrator solar cell performance
by: Broderick, Lirong Z., et al.
Published: (2014)