Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

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

  • Published:
Autonomous Agents and Multi-Agent Systems Aims and scope Submit manuscript

Abstract

Agent-based modeling is commonly used for studying complex system properties emergent from interactions among agents. However, agent-based models are often not developed explicitly for prediction, and are generally not validated as such. We therefore present a novel data-driven agent-based modeling framework, in which individual behavior model is learned by machine learning techniques, deployed in multi-agent systems and validated using a holdout sequence of collective adoption decisions. We apply the framework to forecasting individual and aggregate residential rooftop solar adoption in San Diego county and demonstrate that the resulting agent-based model successfully forecasts solar adoption trends and provides a meaningful quantification of uncertainty about its predictions. Meanwhile, we construct a second agent-based model, with its parameters calibrated based on mean square error of its fitted aggregate adoption to the ground truth. Our result suggests that our data-driven agent-based approach based on maximum likelihood estimation substantially outperforms the calibrated agent-based model. Seeing advantage over the state-of-the-art modeling methodology, we utilize our agent-based model to aid search for potentially better incentive structures aimed at spurring more solar adoption. Although the impact of solar subsidies is rather limited in our case, our study still reveals that a simple heuristic search algorithm can lead to more effective incentive plans than the current solar subsidies in San Diego County and a previously explored structure. Finally, we examine an exclusive class of policies that gives away free systems to low-income households, which are shown significantly more efficacious than any incentive-based policies we have analyzed to date.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Notes

  1. Our choice of discount factor is in the typical range for residential photovoltaic systems [10]. We found that small variations in the discount rate do not significantly change the results.

  2. Prediction of simple linear regression model without log is unbounded, which could go below zero.

  3. \(l_1\) regularization is a common method of model selection in machine learning to prevent over-fitting by adding the \(l_1\) norm of weight vector to the loss function so as to penalize extreme parameter values [4]. In linear regression, it is also known as “lasso” regression [16].

  4. In fact, we have sampled the process multiple times, and can confirm that there is little variance in the model or final results.

  5. In the model developed by Palmer et al. [31], the weighs differ by agent’s socio-economic group, derived using proprietary means. Since this categorization is not available in our case, and also to reduce the number of parameters necessary to calibrate (and, consequently, to reduce the amount of over-fitting), we use identical weights for all agents.

  6. 9/12 is where the aggregate adoption becomes highly non-linear, so that the added value of the extra features used by our model sharply increases.

  7. It is important to note that the CSI program has many facets, and promoting solar adoption directly is only one of its many goals. For example, much of the program is focused on improving marketplace conditions for solar installers. Our analysis is therefore limited by the closed world assumption of our simulation model, and focused on only a single aspect of the program.

  8. In fact, we optimize over discrete choices of alpha (at 0.1 intervals), and the optimal alpha varies with budget.

References

  1. Arrow, K. J. (1962). The economic implications of learning by doing. Review of Economic Studies, 29(3), 155–173.

    Article  Google Scholar 

  2. Bass, F. M. (1969). A new product growth for model consumer durables. Management Science, 15(5), 215–227.

    Article  MATH  Google Scholar 

  3. Berger, T., & Schreinemachers, P. (2006). Creating agents and landscapes for multiagent systems from random samples. Ecology and Society, 11(2), 19.

    Google Scholar 

  4. Bishop, C. M. (2006). Pattern recognition and machine learning. Berlin: Springer.

    MATH  Google Scholar 

  5. Bollinger, B., & Gillingham, K. (2012). Peer effects in the diffusion of solar photovoltaic panels. Marketing Science, 31(6), 900–912.

    Article  Google Scholar 

  6. Bonabeau, E. (2002). Agent-based modeling: Methods and techniques for simulating human systems. Proceedings of the National Academy of Sciences, 99(Supp 3), 7280–7287.

    Article  Google Scholar 

  7. Borghesi, A., Milano, M., Gavanelli, M., & Woods, T. (2013). Simulation of incentive mechanisms for renewable energy policies. In European conference on modeling and simulation.

  8. Brown, D. G., & Robinson, D. T. (2006). Effects of heterogeneity in residential preferences on an agent-based model of urban sprawl. Ecology and Society, 11(1), 46.

    Google Scholar 

  9. Chen, W., Wang, Y., & Yang, S. (2009). Efficient influence maximization in social networks. In Proceedings of the 15th ACM SIGKDD international conference on knowledge discovery and data mining (pp. 199–208).

  10. Coughlin, J., & Cory, K. (2009). Solar photovoltaic financing: Residential sector deployment. National Renewable Energy Laboratory. Technical report.

  11. CPUC: California solar initiative program handbook (2013).

  12. Dancik, G. M., Jones, D. E., & Dorman, K. S. (2011). Parameter estimation and sensitivity analysis in an agent-based model of leishmania major infection. Journal of Theoretical Biology, 262(3), 398–412.

    Article  Google Scholar 

  13. Denholm, P., Drury, E., & Margolis, R. (2009). The solar deployment system (SolarDS) model: Documentation and sample results. National Renewable Energy Laboratory. Technical report.

  14. Draper, N., & Smith, H. (1981). Applied Regression Analysis (2nd ed.). New York: Wiley.

    MATH  Google Scholar 

  15. Duong, Q., Wellman, M. P., Singh, S., & Vorobeychik, Y. (2010). History-dependent graphical multiagent models. In Proceedings of the 9th international conference on autonomous agents and multiagent aystems (Vol. 1, pp. 1215–1222). International Foundation for Autonomous Agents and Multiagent Systems.

  16. Friedman, J., Hastie, T., & Tibshirani, R. (2001). The elements of statistical learning., Springer series in statistics Stanford: Springer.

    MATH  Google Scholar 

  17. Geroski, P. A. (2000). Models of technology diffusion. Research Policy, 29(4), 603–625.

    Article  Google Scholar 

  18. Golovin, D., & Krause, A. (2011). Adaptive submodularity: Theory and applications in active learning and stochastic optimization. Journal of Artificial Intelligence Research, 42, 427–486.

    MathSciNet  MATH  Google Scholar 

  19. Happe, K., Kellermann, K., & Balmann, A. (2006). Agent-based analysis of agricultural policies: An illustration of the agricultural policy simulator agripolis, its adaptation and behavior. Ecology and Society, 11(1), 49.

    Google Scholar 

  20. Harmon, C. (2000). Experience curves of photovoltaic technology. International Institute for Applied Systems Analysis. Technical report.

  21. Huigen, M. G., Overmars, K. P., & de Groot, W. T. (2006). Multiactor modeling of settling decisions and behavior in the san mariano watershed, the Philippines: A first application with the mameluke framework. Ecology and Society, 11(2), 33.

    Google Scholar 

  22. Janssen, M. A., & Ahn, T. K. (2006). Learning, signaling, and social preferences in public-good games. Ecology and Society, 11(2), 21.

    Google Scholar 

  23. Janssen, M. A., & Ostrom, E. (2006). Empirically based, agent-based models. Ecology and Society, 11(2), 37.

    Google Scholar 

  24. Judd, S., Kearns, M., & Vorobeychik, Y. (2010). Behavioral dynamics and influence in networked coloring and consensus. Proceedings of the National Academy of Sciences, 107(34), 14978–14982.

    Article  Google Scholar 

  25. Kearns, M., & Wortman, J. (2008). Learning from collective behavior. In Conference on learning theory.

  26. Kempe, D., Kleinberg, J., & Tardos, E. (2003). Maximizing the spread of influence through a social network. In Proceedings of the ninth ACM SIGKDD international conference on knowledge discovery and data mining (pp. 137–146).

  27. Lobel, R., & Perakis, G. (2011). Consumer choice model for forecasting demand and designing incentives for solar technology. Working paper.

  28. McDonald, A., & Schrattenholzer, L. (2001). Learning rates for energy technologies. Energy Policy, 29(4), 255–261.

    Article  Google Scholar 

  29. Miller, J. H., & Page, S. E. (2007). Complex adaptive systems: An introduction to computational models of social life. Princeton: Princeton University Press.

    MATH  Google Scholar 

  30. North, M., Collier, N., Ozik, J., Tatara, E., Altaweel, M., Macal, C., et al. (2013). Complex adaptive systems modeling., Complex adaptive systems modeling with repast simphony New York: Springer.

    Google Scholar 

  31. Palmer, J., Sorda, G., & Madlener, R. (2013). Modeling the diffusion of residential photovoltaic systems in Italy: An agent-based simulation. Working paper.

  32. Rai, V., & Robinson, S. (2014). Agent-based modeling of energy technology adoption: Empirical integration of social, behavioral, economic, and environmental factors. Working paper.

  33. Rai, V., & Sigrin, B. (2013). Diffusion of environmentally-friendly energy technologies: Buy versus lease differences in residential PV markets. Environmental Research Letters, 8(1), 014022.

    Article  Google Scholar 

  34. Rand, W., & Rust, R. (2011). Agent-based modeling in marketing: Guidelines for rigor. International Journal of Research in Marketing, 28(3), 181–193.

    Article  Google Scholar 

  35. Rao, K., & Kishore, V. (2010). A review of technology diffusion models with special reference to renewable energy technologies. Renewable and Sustainable Energy Reviews, 14(3), 1070–1078.

    Article  MathSciNet  Google Scholar 

  36. Robinson, S., & Rai, V. (2014). Determinants of spatio-temporal patterns of energy technology adoption: An agent-based modeling approach. Working paper.

  37. Robinson, S., Stringer, M., Rai, V., & Tondon, A. (2013). GIS-integrated agent-based model of residential solar PV diffusion. Working paper.

  38. Rogers, E. M. (2003). Diffusion of innovations (5th ed.). New York: Free Press.

    Google Scholar 

  39. Thiele, J. C., Kurth, W., & Grimm, V. (2014). Facilitating parameter estimation and sensitivity analysis of agent-based models: A cookbook using NetLogo and R. Journal of Artificial Societies and Social Simulation, 17(3), 11.

    Article  Google Scholar 

  40. Torrens, P., Li, X., & Griffin, W. A. (2011). Building agent-based walking models by machine-learning on diverse databases of space-time trajectory samples. Transactions in GIS, 15(s1), 67–94.

    Article  Google Scholar 

  41. van Benthem, A., Gillingham, K., & Sweeney, J. (2008). Learning-by-doing and the optimal solar policy in california. Energy Journal, 29(3), 131–151.

    Google Scholar 

  42. Wunder, M., Suri, S., & Watts, D. J. (2013). Empirical agent based models of cooperation in public goods games. In Proceedings of the fourteenth ACM conference on electronic commerce (pp. 891–908). ACM.

  43. Zhai, P., & Williams, E. (2012). Analyzing consumer acceptance of photovoltaics (PV) using fuzzy logic model. Renewable Energy, 41, 350–357.

    Article  Google Scholar 

  44. Zhang, H., Vorobeychik, Y., Letchford, J., & Lakkaraju, K. (2015). Data-driven agent-based modeling, with application to rooftop solar adoption. In International conference on autonomous agents and multiagent systems, (pp. 513–521).

  45. Zhao, J., Mazhari, E., Celik, N., & Son, Y. J. (2011). Hybrid agent-based simulation for policy evaluation of solar power generation systems. Simulation Modelling Practice and Theory, 19, 2189–2205.

    Article  Google Scholar 

Download references

Acknowledgments

This work was partially supported by the U.S. Department of Energy (DOE) office of Energy Efficiency and Renewable Energy, under the Solar Energy Evolution and Diffusion Studies (SEEDS) program.

Author information

Authors and Affiliations

  1. Electrical Engineering and Computer Science, Vanderbilt University, Nashville, TN, USA

    Haifeng Zhang & Yevgeniy Vorobeychik

  2. Sandia National Laboratories, Albuquerque, NM, USA

    Joshua Letchford & Kiran Lakkaraju

Authors
  1. Haifeng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yevgeniy Vorobeychik
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Joshua Letchford
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Kiran Lakkaraju
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Haifeng Zhang.

Additional information

This paper is a significant extension of the following article: Haifeng Zhang, Yevgeniy Vorobeychik, Joshua Letchford, and Kiran Lakkaraju. Data-driven agent-based modeling, with applications to rooftop solar adoption. International Conference on Autonomous Agents and Multiagent Systems, 2015.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, H., Vorobeychik, Y., Letchford, J. et al. Data-driven agent-based modeling, with application to rooftop solar adoption. Auton Agent Multi-Agent Syst 30, 1023–1049 (2016). https://doi.org/10.1007/s10458-016-9326-8

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10458-016-9326-8

Keywords

Search

Navigation