skip to main content

DOE PAGESDOE PAGES

Title: Data-driven agent-based modeling, with application to rooftop solar adoption

Agent-based modeling is commonly used for studying complex system properties emergent from interactions among many agents. We present a novel data-driven agent-based modeling framework applied to forecasting individual and aggregate residential rooftop solar adoption in San Diego county. Our first step is to learn a model of individual agent behavior from combined data of individual adoption characteristics and property assessment. We then construct an agent-based simulation with the learned model embedded in artificial agents, and proceed to validate it using a holdout sequence of collective adoption decisions. We demonstrate that the resulting agent-based model successfully forecasts solar adoption trends and provides a meaningful quantification of uncertainty about its predictions. We utilize our model to optimize two classes of policies aimed at spurring solar adoption: one that subsidizes the cost of adoption, and another that gives away free systems to low-income house- holds. We find that the optimal policies derived for the latter class are significantly more efficacious, whereas the policies similar to the current California Solar Initiative incentive scheme appear to have a limited impact on overall adoption trends.
Authors:
 [1] ;  [1] ;  [2] ;  [2]
  1. Vanderbilt Univ., Nashville, TN (United States). Dept. of Electrical Engineering and Computer Science
  2. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Publication Date:
Report Number(s):
SAND-2015-2990C
Journal ID: ISSN 1387-2532; PII: 9326
Grant/Contract Number:
AC04-94AL85000
Type:
Accepted Manuscript
Journal Name:
Autonomous Agents and Multi-Agent Systems
Additional Journal Information:
Journal Volume: 30; Journal Issue: 6; Conference: International Conference on Autonomous Agents and Multiagent Systems, 2015, Istanbul (Turkey), 4-8 May, 2015; Journal ID: ISSN 1387-2532
Publisher:
Springer
Research Org:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sponsoring Org:
USDOE National Nuclear Security Administration (NNSA); USDOE Office of Energy Efficiency and Renewable Energy (EERE)
Country of Publication:
United States
Language:
English
Subject:
Machine learning; Agent-based modeling; Innovation diffusion; Rooftop solar; Policy optimization
OSTI Identifier:
1248850

Zhang, Haifeng, Vorobeychik, Yevgeniy, Letchford, Joshua, and Lakkaraju, Kiran. Data-driven agent-based modeling, with application to rooftop solar adoption. United States: N. p., Web. doi:10.1007/s10458-016-9326-8.
Zhang, Haifeng, Vorobeychik, Yevgeniy, Letchford, Joshua, & Lakkaraju, Kiran. Data-driven agent-based modeling, with application to rooftop solar adoption. United States. doi:10.1007/s10458-016-9326-8.
Zhang, Haifeng, Vorobeychik, Yevgeniy, Letchford, Joshua, and Lakkaraju, Kiran. 2016. "Data-driven agent-based modeling, with application to rooftop solar adoption". United States. doi:10.1007/s10458-016-9326-8. https://www.osti.gov/servlets/purl/1248850.
@article{osti_1248850,
title = {Data-driven agent-based modeling, with application to rooftop solar adoption},
author = {Zhang, Haifeng and Vorobeychik, Yevgeniy and Letchford, Joshua and Lakkaraju, Kiran},
abstractNote = {Agent-based modeling is commonly used for studying complex system properties emergent from interactions among many agents. We present a novel data-driven agent-based modeling framework applied to forecasting individual and aggregate residential rooftop solar adoption in San Diego county. Our first step is to learn a model of individual agent behavior from combined data of individual adoption characteristics and property assessment. We then construct an agent-based simulation with the learned model embedded in artificial agents, and proceed to validate it using a holdout sequence of collective adoption decisions. We demonstrate that the resulting agent-based model successfully forecasts solar adoption trends and provides a meaningful quantification of uncertainty about its predictions. We utilize our model to optimize two classes of policies aimed at spurring solar adoption: one that subsidizes the cost of adoption, and another that gives away free systems to low-income house- holds. We find that the optimal policies derived for the latter class are significantly more efficacious, whereas the policies similar to the current California Solar Initiative incentive scheme appear to have a limited impact on overall adoption trends.},
doi = {10.1007/s10458-016-9326-8},
journal = {Autonomous Agents and Multi-Agent Systems},
number = 6,
volume = 30,
place = {United States},
year = {2016},
month = {1}
}