Design of high transmission color filters for solar cells directed by deep Q-learning

Iman Sajedian; Heon Lee; Junsuk Rho

doi:10.1016/j.solener.2019.12.013

Design of high transmission color filters for solar cells directed by deep Q-learning

Iman Sajedian, Heon Lee, Junsuk Rho

Department of Materials Science and Engineering

Research output: Contribution to journal › Article › peer-review

23 Citations (Scopus)

Abstract

In this paper, we have used deep Q-learning networks (DQN) to find a colored coating for solar cells with high transmission. A basic structure with a huge range of possibilities was given to DQN, and it was designed to find the best structures fitting our purpose. The number of possibilities given to the model was more than 12 billion. Our model could find the structures with higher transmission and deeper colors compared to other human researchers in around 32,000 steps. Our numerical results cover a large area of color gamut which can be used for aesthetic purposes.

Original language	English
Pages (from-to)	670-676
Number of pages	7
Journal	Solar Energy
Volume	195
DOIs	https://doi.org/10.1016/j.solener.2019.12.013
Publication status	Published - 2020 Jan 1

Keywords

Building integrated photovoltaics
Colored solar cells
Deep Q-learning
Neural networks

ASJC Scopus subject areas

Renewable Energy, Sustainability and the Environment
Materials Science(all)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.solener.2019.12.013

Cite this

@article{ffcbb2b5001841408a6868f8dfe59a12,

title = "Design of high transmission color filters for solar cells directed by deep Q-learning",

abstract = "In this paper, we have used deep Q-learning networks (DQN) to find a colored coating for solar cells with high transmission. A basic structure with a huge range of possibilities was given to DQN, and it was designed to find the best structures fitting our purpose. The number of possibilities given to the model was more than 12 billion. Our model could find the structures with higher transmission and deeper colors compared to other human researchers in around 32,000 steps. Our numerical results cover a large area of color gamut which can be used for aesthetic purposes.",

keywords = "Building integrated photovoltaics, Colored solar cells, Deep Q-learning, Neural networks",

author = "Iman Sajedian and Heon Lee and Junsuk Rho",

note = "Funding Information: National Research Foundation grants (NRF-2018M3D1A1058998, NRF-2019R1A2C3003129, CAMM-2019M3A6B3030637, NRF-2019R1A5A8080290, NRF-2015R1A5A1037668) funded by the Ministry of Science and ICT, Republic of Korea. Funding Information: National Research Foundation grants (NRF- 2018M3D1A1058998 , NRF-2019R1A2C3003129 , CAMM-2019M3A6B3030637 , NRF- 2019R1A5A8080290 , NRF- 2015R1A5A1037668 ) funded by the Ministry of Science and ICT, Republic of Korea . Publisher Copyright: {\textcopyright} 2019 International Solar Energy Society",

year = "2020",

month = jan,

day = "1",

doi = "10.1016/j.solener.2019.12.013",

language = "English",

volume = "195",

pages = "670--676",

journal = "Solar Energy",

issn = "0038-092X",

publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Design of high transmission color filters for solar cells directed by deep Q-learning

AU - Sajedian, Iman

AU - Lee, Heon

AU - Rho, Junsuk

N1 - Funding Information: National Research Foundation grants (NRF-2018M3D1A1058998, NRF-2019R1A2C3003129, CAMM-2019M3A6B3030637, NRF-2019R1A5A8080290, NRF-2015R1A5A1037668) funded by the Ministry of Science and ICT, Republic of Korea. Funding Information: National Research Foundation grants (NRF- 2018M3D1A1058998 , NRF-2019R1A2C3003129 , CAMM-2019M3A6B3030637 , NRF- 2019R1A5A8080290 , NRF- 2015R1A5A1037668 ) funded by the Ministry of Science and ICT, Republic of Korea . Publisher Copyright: © 2019 International Solar Energy Society

PY - 2020/1/1

Y1 - 2020/1/1

N2 - In this paper, we have used deep Q-learning networks (DQN) to find a colored coating for solar cells with high transmission. A basic structure with a huge range of possibilities was given to DQN, and it was designed to find the best structures fitting our purpose. The number of possibilities given to the model was more than 12 billion. Our model could find the structures with higher transmission and deeper colors compared to other human researchers in around 32,000 steps. Our numerical results cover a large area of color gamut which can be used for aesthetic purposes.

AB - In this paper, we have used deep Q-learning networks (DQN) to find a colored coating for solar cells with high transmission. A basic structure with a huge range of possibilities was given to DQN, and it was designed to find the best structures fitting our purpose. The number of possibilities given to the model was more than 12 billion. Our model could find the structures with higher transmission and deeper colors compared to other human researchers in around 32,000 steps. Our numerical results cover a large area of color gamut which can be used for aesthetic purposes.

KW - Building integrated photovoltaics

KW - Colored solar cells

KW - Deep Q-learning

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=85076187639&partnerID=8YFLogxK

U2 - 10.1016/j.solener.2019.12.013

DO - 10.1016/j.solener.2019.12.013

M3 - Article

AN - SCOPUS:85076187639

SN - 0038-092X

VL - 195

SP - 670

EP - 676

JO - Solar Energy

JF - Solar Energy

ER -

Design of high transmission color filters for solar cells directed by deep Q-learning

Abstract

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this