Machine learning reduces soft costs for residential solar photovoltaics

Dong, Changgui; Nemet, Gregory; Gao, Xue; Barbose, Galen; Sigrin, Benjamin; O’Shaughnessy, Eric

doi:10.1038/s41598-023-33014-4

Title: Machine learning reduces soft costs for residential solar photovoltaics

Journal Article · 03 May 2023 · Scientific Reports

DOI: https://doi.org/10.1038/s41598-023-33014-4 · OSTI ID:1974997

Dong, Changgui ^[1]; Nemet, Gregory ^[2]; Gao, Xue ^[3]; Barbose, Galen ^[4]; Sigrin, Benjamin ^[5]; O’Shaughnessy, Eric ^[6]

Renmin Univ. of China, Beijing (China)
Univ. of Wisconsin, Madison, WI (United States)
Florida State Univ., Tallahassee, FL (United States); Univ. of Miami, Coral Gables, FL (United States)
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
National Renewable Energy Laboratory (NREL), Golden, CO (United States)
Clean Kilowatts, LLC, Boulder, CO (United States)

Further deployment of rooftop solar photovoltaics (PV) hinges on the reduction of soft (non-hardware) costs—now larger and more resistant to reductions than hardware costs. The largest portion of these soft costs is the expenses solar companies incur to acquire new customers. In this study, we demonstrate the value of a shift from significance-based methodologies to prediction-oriented models to better identify PV adopters and reduce soft costs. We employ machine learning to predict PV adopters and non-adopters, and compare its prediction performance with logistic regression, the dominant significance-based method in technology adoption studies. Our results show that machine learning substantially enhances adoption prediction performance: The true positive rate of predicting adopters increased from 66 to 87%, and the true negative rate of predicting non-adopters increased from 75 to 88%. We attribute the enhanced performance to complex variable interactions and nonlinear effects incorporated by machine learning. With more accurate predictions, machine learning is able to reduce customer acquisition costs by 15% ($0.07/Watt) and identify new market opportunities for solar companies to expand and diversify their customer bases. Our research methods and findings provide broader implications for the adoption of similar clean energy technologies and related policy challenges such as market growth and energy inequality.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: National Renewable Energy Laboratory (NREL), Golden, CO (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)

Sponsoring Organization:: USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Solar Energy Technologies Office

Grant/Contract Number:: AC36-08GO28308; FOA-0000740; AC02-05CH11231

OSTI ID:: 1974997

Alternate ID(s):: OSTI ID: 1983933

Report Number(s):: NREL/JA-7A40-86336; MainId:87109; UUID:3da27812-c14f-4c8d-a1a5-d24a48a5b2fd; MainAdminID:69568

Journal Information:: Scientific Reports, Vol. 13, Issue 1; ISSN 2045-2322

Publisher:: Nature Publishing GroupCopyright Statement

Country of Publication:: United States

Language:: English

References (58)

DeepSolar: A Machine Learning Framework to Efficiently Construct a Solar Deployment Database in the United States Yu, Jiafan; Wang, Zhecheng; Majumdar, Arun Joule, Vol. 2, Issue 12 https://doi.org/10.1016/j.joule.2018.11.021	journal	December 2018
What drives the solar energy transition? The effect of policies, incentives and behavior in a cross-country comparison Colasante, Annarita; D'Adamo, Idiano; Morone, Piergiuseppe Energy Research & Social Science, Vol. 85 https://doi.org/10.1016/j.erss.2021.102405	journal	March 2022
Modelling complex investment decisions in Germany for renewables with different machine learning algorithms Frey, Ulrich J.; Klein, Martin; Deissenroth, Marc Environmental Modelling & Software, Vol. 118 https://doi.org/10.1016/j.envsoft.2019.03.006	journal	August 2019
Public perceptions of and responses to new energy technologies Boudet, Hilary S. Nature Energy, Vol. 4, Issue 6 https://doi.org/10.1038/s41560-019-0399-x	journal	May 2019
Rapid cost decrease of renewables and storage accelerates the decarbonization of China’s power system He, Gang; Lin, Jiang; Sifuentes, Froylan Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-020-16184-x	journal	May 2020
The climate and air-quality benefits of wind and solar power in the United States Millstein, Dev; Wiser, Ryan; Bolinger, Mark Nature Energy, Vol. 2, Issue 9 https://doi.org/10.1038/nenergy.2017.134	journal	August 2017
DeepRoof Lee, Stephen; Iyengar, Srinivasan; Feng, Menghong Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining https://doi.org/10.1145/3292500.3330741	conference	July 2019
Households with solar installations are ideologically diverse and more politically active than their neighbours Mildenberger, Matto; Howe, Peter D.; Miljanich, Chris Nature Energy, Vol. 4, Issue 12 https://doi.org/10.1038/s41560-019-0498-8	journal	November 2019
Determinants of household adoption of solar energy technology in rural Ethiopia Guta, Dawit Diriba Journal of Cleaner Production, Vol. 204 https://doi.org/10.1016/j.jclepro.2018.09.016	journal	December 2018
Household installation of solar panels – Motives and barriers in a 10-year perspective Palm, Jenny Energy Policy, Vol. 113 https://doi.org/10.1016/j.enpol.2017.10.047	journal	February 2018
Forecasting Solar Energy Production Using Machine Learning Vennila, C.; Titus, Anita; Sudha, T. Sri International Journal of Photoenergy, Vol. 2022 https://doi.org/10.1155/2022/7797488	journal	April 2022
A novel machine learning based identification of potential adopter of rooftop solar photovoltaics Bhavsar, S.; Pitchumani, R. Applied Energy, Vol. 286 https://doi.org/10.1016/j.apenergy.2021.116503	journal	March 2021
A meta-analysis of residential PV adoption: the important role of perceived benefits, intentions and antecedents in solar energy acceptance Schulte, Emily; Scheller, Fabian; Sloot, Daniel Energy Research & Social Science, Vol. 84 https://doi.org/10.1016/j.erss.2021.102339	journal	February 2022
Distributed solar and environmental justice: Exploring the demographic and socio-economic trends of residential PV adoption in California Lukanov, Boris R.; Krieger, Elena M. Energy Policy, Vol. 134 https://doi.org/10.1016/j.enpol.2019.110935	journal	November 2019
Benefits and costs of a utility-ownership business model for residential rooftop solar photovoltaics Barbose, Galen; Satchwell, Andrew J. Nature Energy, Vol. 5, Issue 10 https://doi.org/10.1038/s41560-020-0673-y	journal	August 2020
Pleasure is the profit - The adoption of solar PV systems by households in Finland Karjalainen, Sami; Ahvenniemi, Hannele Renewable Energy, Vol. 133 https://doi.org/10.1016/j.renene.2018.10.011	journal	April 2019
Diffusion into new markets: evolving customer segments in the solar photovoltaics market Sigrin, Ben; Pless, Jacquelyn; Drury, Easan Environmental Research Letters, Vol. 10, Issue 8 https://doi.org/10.1088/1748-9326/10/8/084001	journal	August 2015
XGBoost: A Scalable Tree Boosting System Chen, Tianqi; Guestrin, Carlos Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16 https://doi.org/10.1145/2939672.2939785	conference	January 2016
Testing Diffusion of Innovations Theory with data: Financial incentives, early adopters, and distributed solar energy in Australia Simpson, Genevieve; Clifton, Julian Energy Research & Social Science, Vol. 29 https://doi.org/10.1016/j.erss.2017.04.005	journal	July 2017
Predictors, taxonomy of predictors, and correlations of predictors with the decision behaviour of residential solar photovoltaics adoption: A review Alipour, M.; Salim, H.; Stewart, Rodney A. Renewable and Sustainable Energy Reviews, Vol. 123 https://doi.org/10.1016/j.rser.2020.109749	journal	May 2020
Why significant variables aren’t automatically good predictors Lo, Adeline; Chernoff, Herman; Zheng, Tian Proceedings of the National Academy of Sciences, Vol. 112, Issue 45 https://doi.org/10.1073/pnas.1518285112	journal	October 2015
More alike than different: Profiles of high-income and low-income rooftop solar adopters in the United States Wolske, Kimberly S. Energy Research & Social Science, Vol. 63 https://doi.org/10.1016/j.erss.2019.101399	journal	May 2020
Exploring residential solar PV and battery energy storage adoption motivations and barriers in a mature PV market Alipour, M.; Irannezhad, Elnaz; Stewart, Rodney A. Renewable Energy, Vol. 190 https://doi.org/10.1016/j.renene.2022.03.040	journal	May 2022
Residential solar electricity adoption: What motivates, and what matters? A case study of early adopters Schelly, Chelsea Energy Research & Social Science, Vol. 2 https://doi.org/10.1016/j.erss.2014.01.001	journal	June 2014
Machine learning approach to understand regional disparity of residential solar adoption in Australia Lan, Haifeng; Gou, Zhonghua; Lu, Yi Renewable and Sustainable Energy Reviews, Vol. 136 https://doi.org/10.1016/j.rser.2020.110458	journal	February 2021
Assessing the feasibility of carbon dioxide mitigation options in terms of energy usage Babacan, Oytun; De Causmaecker, Sven; Gambhir, Ajay Nature Energy, Vol. 5, Issue 9 https://doi.org/10.1038/s41560-020-0646-1	journal	July 2020
Peer influence on household energy behaviours Wolske, Kimberly S.; Gillingham, Kenneth T.; Schultz, P. Wesley Nature Energy, Vol. 5, Issue 3 https://doi.org/10.1038/s41560-019-0541-9	journal	January 2020
Solar photovoltaic interventions have reduced rural poverty in China Zhang, Huiming; Wu, Kai; Qiu, Yueming Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-020-15826-4	journal	April 2020
Renewable energy: Back the renewables boom Trancik, Jessika E. Nature, Vol. 507, Issue 7492 https://doi.org/10.1038/507300a	journal	March 2014
Emerging role of machine learning in light-matter interaction Zhou, Jiajia; Huang, Bolong; Yan, Zheng Light: Science & Applications, Vol. 8, Issue 1 https://doi.org/10.1038/s41377-019-0192-4	journal	September 2019
The analysis of demographics, environmental and knowledge factors affecting prospective residential PV system adoption: A study in Tehran Bashiri, Ali; Alizadeh, Sasan H. Renewable and Sustainable Energy Reviews, Vol. 81 https://doi.org/10.1016/j.rser.2017.08.093	journal	January 2018
Factors Influencing Social Perception of Residential Solar Photovoltaic Systems in Saudi Arabia Alrashoud, Khalid; Tokimatsu, Koji Sustainability, Vol. 11, Issue 19 https://doi.org/10.3390/su11195259	journal	September 2019
Tracking the Sun: Pricing and Design Trends for Distributed Photovoltaic Systems in the United States - 2019 Edition Barbose, Galen; Darghouth, Naim; Elmallah, Salma https://doi.org/10.2172/1574343	report	October 2019
Automatic Boundary Extraction of Large-Scale Photovoltaic Plants Using a Fully Convolutional Network on Aerial Imagery Sizkouhi, Amir Mohammad Moradi; Aghaei, Mohammadreza; Esmailifar, Sayyed Majid IEEE Journal of Photovoltaics, Vol. 10, Issue 4 https://doi.org/10.1109/JPHOTOV.2020.2992339	journal	July 2020
Nudging for the increased adoption of solar energy? Evidence from a survey in Italy Colasante, Annarita; D'Adamo, Idiano; Morone, Piergiuseppe Energy Research & Social Science, Vol. 74 https://doi.org/10.1016/j.erss.2021.101978	journal	April 2021
What drives home solar PV uptake? Subsidies, peer effects and visibility in Sweden Mundaca, Luis; Samahita, Margaret Energy Research & Social Science, Vol. 60 https://doi.org/10.1016/j.erss.2019.101319	journal	February 2020
A study on the factors affecting household solar adoption in Kerala, India Parsad, Chandan; Mittal, Shashank; Krishnankutty, Raveesh International Journal of Productivity and Performance Management, Vol. 69, Issue 8 https://doi.org/10.1108/IJPPM-11-2019-0544	journal	July 2020
Nudging – A promising tool for sustainable consumption behaviour? Lehner, Matthias; Mont, Oksana; Heiskanen, Eva Journal of Cleaner Production, Vol. 134 https://doi.org/10.1016/j.jclepro.2015.11.086	journal	October 2016
Prediction of Rooftop Photovoltaic Solar Potential Using Machine Learning Mukilan, K.; Thaiyalnayaki, K.; Dwivedi, Yagya Dutta International Journal of Photoenergy, Vol. 2022 https://doi.org/10.1155/2022/1541938	journal	May 2022
A city-scale estimation of rooftop solar photovoltaic potential based on deep learning Zhong, Teng; Zhang, Zhixin; Chen, Min Applied Energy, Vol. 298 https://doi.org/10.1016/j.apenergy.2021.117132	journal	September 2021
Passive and active peer effects in the spatial diffusion of residential solar panels: A case study of the Las Vegas Valley Barnes, Jesse L.; Krishen, Anjala S.; Chan, Alexander Journal of Cleaner Production, Vol. 363 https://doi.org/10.1016/j.jclepro.2022.132634	journal	August 2022
Framework for making better predictions by directly estimating variables’ predictivity Lo, Adeline; Chernoff, Herman; Zheng, Tian Proceedings of the National Academy of Sciences, Vol. 113, Issue 50 https://doi.org/10.1073/pnas.1616647113	journal	November 2016
Disparities in rooftop photovoltaics deployment in the United States by race and ethnicity Sunter, Deborah A.; Castellanos, Sergio; Kammen, Daniel M. Nature Sustainability, Vol. 2, Issue 1 https://doi.org/10.1038/s41893-018-0204-z	journal	January 2019
U.S. Solar Photovoltaic System and Energy Storage Cost Benchmark (Q1 2020) Feldman, David; Ramasamy, Vignesh; Fu, Ran https://doi.org/10.2172/1764908	report	January 2021
Big data mining for the estimation of hourly rooftop photovoltaic potential and its uncertainty Walch, Alina; Castello, Roberto; Mohajeri, Nahid Applied Energy, Vol. 262 https://doi.org/10.1016/j.apenergy.2019.114404	journal	March 2020
Interrogating the Installation Gap and Potential of Solar Photovoltaic Systems Using GIS and Deep Learning Kalyan, Sumit; Sun, Qian (Chayn) Energies, Vol. 15, Issue 10 https://doi.org/10.3390/en15103740	journal	May 2022
Machine learning for characterizing risk of type 2 diabetes mellitus in a rural Chinese population: the Henan Rural Cohort Study Zhang, Liying; Wang, Yikang; Niu, Miaomiao Scientific Reports, Vol. 10, Issue 1 https://doi.org/10.1038/s41598-020-61123-x	journal	March 2020
The adoption of PV in the Netherlands: A statistical analysis of adoption factors Vasseur, Véronique; Kemp, René Renewable and Sustainable Energy Reviews, Vol. 41 https://doi.org/10.1016/j.rser.2014.08.020	journal	January 2015
Overcoming barriers and uncertainties in the adoption of residential solar PV Rai, Varun; Reeves, D. Cale; Margolis, Robert Renewable Energy, Vol. 89 https://doi.org/10.1016/j.renene.2015.11.080	journal	April 2016
Motivators for adoption of photovoltaic systems at grid parity: A case study from Southern Germany Karakaya, Emrah; Hidalgo, Antonio; Nuur, Cali Renewable and Sustainable Energy Reviews, Vol. 43 https://doi.org/10.1016/j.rser.2014.11.077	journal	March 2015
The impact of policies and business models on income equity in rooftop solar adoption O’Shaughnessy, Eric; Barbose, Galen; Wiser, Ryan Nature Energy, Vol. 6, Issue 1 https://doi.org/10.1038/s41560-020-00724-2	journal	November 2020
City-level analysis of subsidy-free solar photovoltaic electricity price, profits and grid parity in China Yan, Jinyue; Yang, Ying; Elia Campana, Pietro Nature Energy, Vol. 4, Issue 8 https://doi.org/10.1038/s41560-019-0441-z	journal	August 2019
Consumer Purchasing Behaviour towards Eco-Environment Residential Photovoltaic Solar Lighting Systems Kesari, Bikrant; Atulkar, Sunil; Pandey, Satyanarayan Global Business Review, Vol. 22, Issue 1 https://doi.org/10.1177/0972150918795550	journal	September 2018
A human-centered design approach to evaluating factors in residential solar PV adoption: A survey of homeowners in California and Massachusetts Bao, Qifang; Sinitskaya, Ekaterina; Gomez, Kelley J. Renewable Energy, Vol. 151 https://doi.org/10.1016/j.renene.2019.11.047	journal	May 2020
Money, not morale: The impact of desires and beliefs on private investment in photovoltaic citizen participation initiatives Fleiß, Eva; Hatzl, Stefanie; Seebauer, Sebastian Journal of Cleaner Production, Vol. 141 https://doi.org/10.1016/j.jclepro.2016.09.123	journal	January 2017
Solar photovoltaic power prediction using different machine learning methods Zazoum, Bouchaib Energy Reports, Vol. 8 https://doi.org/10.1016/j.egyr.2021.11.183	journal	April 2022
Perception towards rooftop solar PV in India: comparison between adopters and non-adopters Satapathy, Amitabh; Jain, Arvind Kumar; Barthwal, S. International Journal of Renewable Energy Technology, Vol. 12, Issue 1 https://doi.org/10.1504/IJRET.2021.114609	journal	January 2021
Which factors affect the willingness of consumers to adopt renewable energies? Sardianou, E.; Genoudi, P. Renewable Energy, Vol. 57 https://doi.org/10.1016/j.renene.2013.01.031	journal	September 2013

Similar Records

Impact of residential PV adoption on Retail Electricity Rates

Journal Article · 2013 · Energy Policy · OSTI ID:1211045

Cai, DWH; Adlakha, S; Low, SH; +2 more

The Effects of Market Concentration on Residential Solar PV Prices: Competition, Installer Scale, and Soft Costs

Program Document · 2018 · OSTI ID:1465935

The Effects of Market Concentration on Residential Solar PV Prices: Competition, Installer Scale, and Soft Costs

Technical Report · 2018 · OSTI ID:1452704

O'Shaughnessy, Eric J.

Related Subjects

97 MATHEMATICS AND COMPUTING
14 SOLAR ENERGY
machine learning
residential
rooftop solar photovoltaics
soft costs
technology adoption

Title: Machine learning reduces soft costs for residential solar photovoltaics

Citation Formats

References (58)

Similar Records

Related Subjects