To path indicator Subpages of “Research“ To navigation To quick access To footer with other services
To content
Logo of TRR 391
Students in summer on north campus, red gears in background. © Roland Baege​/​TU Dortmund
C04

Targeting energy conservation

C04 considers the energy transition towards sustainability from the perspective of households and companies. The project leverages machine learning (ML) for domain and out-of-distribution (OOD) generalizations to identify characteristics of individuals that favor energy conservation. The aim is to determine relevant target groups that are susceptible for such interventions. In the long run, the project aims for scalable methods for OOD generalization which can be used for energy conservation campaigns at larger scales.

Project Leaders

Prof. Dr. Mark Andreas Andor
Department of Environment and Resources
RWI Leibniz Institute for Economic Research

Prof. Dr. Asja Fischer
Faculty of Computer Science - Chair of Machine Learning
Ruhr University Bochum

Prof. Dr. Andreas Löschel
Faculty of Management and Economics - Chair of Environmental/Resource Economics and Sustainability
Ruhr University Bochum

Summary

The transition towards sustainability requires effective policies that trigger changes in economic decisions by households and companies. This project addresses several key questions concerning policies targeting household energy use, energy use in firms, demand flexibility, and mobility behavior. It focuses on experimental methods and deep learning algorithms to demonstrate how machine learning (ML) on spatio-temporal data can be utilized to increase the effectiveness of policies through targeting. Targeting policies is typically understood as targeting those individuals who are expected to have the greatest behavioral response to the policy. We complement this view by targeting policies at the right time, such as peak hours on the power grid or rush hours on the road, and at the right place, such as in certain congested power distribution networks or on certain highways or city districts.

In particular, we conduct large-scale surveys and field experiments to investigate the effectiveness of promising innovative interventions aimed at changing individual behavior. Besides energy consumption, we also aim to study the effects on the well-being of the people affected. For these analyses, we leverage ML models such as deep neural networks to uncover the sensitivity of intervention effects with respect to personal characteristics as well as spatial and temporal circumstances. Further, we develop methods that tackle the problem of domain and out-of-distribution (OOD) generalization as well as test-time model adaptation for better generalization performance of deep learning models.

As a further step, we investigate how these findings can help to identify target groups in relevant populations outside the experimental setting, which leads to improved cost effectiveness of targeted interventions. ML methods trained on the basis of the field experiment are used to make predictions about the impact of such targeted interventions at the individual level based on readily available spatio-temporal data such as electricity load profiles, locations or traffic behavior. However, such predictions require generalizations of the patterns found in the training data. From an ML perspective, this poses a major challenge, as the populations to be generalized over may differ greatly from the training data. A particular focus of the project therefore lies on the development and the application of deep learning methods that allow for such OOD generalizations to succeed with as few additional data requirements as possible.

Allcott, H. (2011). Social norms and energy conservation. Journal of Public Economics 95, 1082–1095. doi: 10.1016/j.jpubeco.2011.03.003.

Allcott, H. and J. B. Kessler (2019). The Welfare Effects of Nudges: A Case Study of Energy Use Social Comparisons. American Economic Journal: Applied Economics 11, 236–276. doi: 10.1257/app.20170328.

Allcott, H. and S. Mullainathan (2010). Behavior and energy policy. Science 327, 1204–1205. doi: 10.1126/science.1180775.

Allcott, H. and T. Rogers (2014). The short-run and long-run effects of behavioral interventions: Experimental evidence from energy conservation. American Economic Review 104, 3003–3037. doi: 10.1257/aer.104.10.3003.

Anderson, M. L. (2014). Subways, strikes, and slowdowns: The impacts of public transit on traffic congestion. American Economic Review 104, 2763–2796. doi: 10.1257/aer.104.9.2763.

Andor, M. A. and K. M. Fels (2018). Behavioral economics and energy conservation — A systematic review of non-price interventions and their causal effects. Ecological Economics 148, 178–210. doi: 10.1016/j.ecolecon.2018.01.018.

Andor, M. A., A. Gerster, K. T. Gillingham, and M. Horvath (2020a). Running a car costs much more than people think — Stalling the uptake of green travel. Nature 580, 453–455. doi: 10.1038/d41586-020-01118-w.

Andor, M. A., A. Gerster, and J. Peters (2022). Information campaigns for residential energy conservation. European Economic Review 144, 104094. doi: 10.1016/j.euroecorev.2022.104094.

Andor, M. A., A. Gerster, J. Peters, and C. M. Schmidt (2020b). Social Norms and Energy Conservation Beyond the US. Journal of Environmental Economics and Management 103, 102351. doi: 10.1016/j.jeem.2020.102351.

Arpit, D., S. Jastrzebski, N. Ballas, D. Krueger, et al. (n.d.). A Closer Look at Memorization in Deep Networks.

Athey, S. and G. Imbens (2016). Recursive partitioning for heterogeneous causal effects. Proceedings of the National Academy of Sciences 113, 7353–7360. doi: 10.1073/pnas.1510489113.

Athey, S., J. Tibshirani, and S. Wager (2019). Generalized Random Forests. The Annals of Statistics 47, 1148–1178. doi: 10.1214/18-AOS1709.

Berger, S., F. Ebeling, C. Feldhaus, A. Löschel, et al. (2022). What motivates smart meter adoption? Evidence from an experimental advertising campaign in Germany. Energy Research & Social Science 85, 102357. doi: 10.1016/j.erss.2021.102357.

Brandon, A., J. A. List, R. D. Metcalfe, M. K. Price, et al. (2019). Testing for crowd out in social nudges: Evidence from a natural field experiment in the market for electricity. Proceedings of the National Academy of Sciences 116, 5293–5298. doi: 10.1073/pnas.1802874115.

Breiman, L., J. Friedman, R. Olshen, and C. Stone (1984). Classification and regression trees. Routledge. doi: 10.1201/9781315139470.

Breiman, L. (2001). Random forests. Machine learning 45, 5–32. doi: 10.1023/A:1010933404324.

Byrne, D. P., A. L. Nauze, and L. A. Martin (2018). Tell me something I don’t already know: Informedness and the impact of information programs. Review of Economics and Statistics 100, 510–527. doi: 10.1162/rest_a_00695.

Chernozhukov, V., M. Demirer, E. Duflo, and I. Fernandez-Val (2018). Generic machine learning inference on heterogeneous treatment effects in randomized experiments, with an application to immunization in India. doi: 10.3386/w24678.

Christensen, P., P. Francisco, E. Myers, H. Shao, et al. (2022). Energy Efficiency Can Deliver for Climate Policy: Evidence from Machine Learning-Based Targeting. doi: 10.3386/w30467.

Christensen, P., P. Francisco, E. Myers, and M. Souza (2021). Decomposing the wedge between projected and realized returns in energy efficiency programs. Review of Economics and Statistics 105, 798–817. doi: 10.1162/rest_a_01087.

Cramton, P., R. R. Geddes, and A. Ockenfels (2018). Set road charges in real time to ease traffic. Nature 560, 23–25. doi: 10.1038/d41586-018-05836-0.

Credit, K. and M. Lehnert (2023). A structured comparison of causal machine learning methods to assess heterogeneous treatment effects in spatial data. Journal of Geographical Systems. doi: 10.1007/s10109-023-00413-0.

Farrell, M. H., T. Liang, and S. Misra (2021). Deep neural networks for estimation and inference. Econometrica 89, 181–213. doi: 10.3982/ECTA16901.

Ferraro, P. J. and J. J. Miranda (2013). Heterogeneous treatment effects and mechanisms in information-based environmental policies: Evidence from a large-scale field experiment. Resource and Energy Economics 35, 356–379. doi: 10.1016/j.reseneeco.2013.04.001.

Friedberg, R., J. Tibshirani, S. Athey, and S. Wager (2020). Local linear forests. Journal of Computational and Graphical Statistics 30, 503–517. doi: 10.1080/10618600.2020.1831930.

Hahn, P. R., J. S. Murray, and C. M. Carvalho (2020). Bayesian regression tree models for causal inference: Regularization, confounding, and heterogeneous effects (with discussion). Bayesian Analysis 15, 965–1056. doi: 10.1214/19-BA1195.

Hill, J. L. (2011). Bayesian nonparametric modeling for causal inference. Journal of Computational and Graphical Statistics 20, 217–240. doi: 10.1198/jcgs.2010.08162.

Ida, T., T. Ishihara, K. Ito, D. Kido, et al. (2021). Paternalism, Autonomy, or Both? Experimental Evidence from Energy Saving Programs. url: http://arxiv.org/abs/2112.09850.

Imai, K. and M. Ratkovic (2013). Estimating treatment effect heterogeneity in randomized program evaluation. The Annals of Applied Statistics 7, 443–470. doi: 10.1214/12-AOAS593.

Jastrzebski, S., Z. Kenton, N. Ballas, A. Fischer, et al. (2019). On the relation between the sharpest directions of DNN loss and the SGD step length. International Conference on Learning Representations. url: https://openreview.net/forum?id=SkgEaj05t7.

Jastrzębski, S., Z. Kenton, D. Arpit, N. Ballas, et al. (2018). Width of Minima Reached by Stochastic Gradient Descent is Influenced by Learning Rate to Batch Size Ratio. Artificial Neural Networks and Machine Learning – ICANN 2018. Ed. by V. Kůrková, Y. Manolopoulos, B. Hammer, L. Iliadis, et al. Vol. 11141. Cham: Springer International Publishing, 392–402. doi: 10.1007/978-3-030-01424-7_39.

Jessoe, K. and D. Rapson (2014). Knowledge is (less) power: Experimental evidence from residential energy use. American Economic Review 104, 1417–1438. doi: 10.1257/aer.104.4.1417.

Jin, X., Y. Park, D. Maddix, H. Wang, et al. (2022). Domain adaptation for time series forecasting via attention sharing. Proceedings of the 39th International Conference on Machine Learning. Ed. by K. Chaudhuri, S. Jegelka, L. Song, C. Szepesvari, et al. Vol. 162. Proceedings of Machine Learning Research, 10280–10297. url: https://proceedings.mlr.press/v162/jin22d.html.

Kennedy, E. H. (2020). Towards optimal doubly robust estimation of heterogeneous causal effects.

Khanna, T. M., A. Löschel, G. Baiocchi, M. Callaghan, et al. (2021). A multi-country meta-analysis on the role of behavioural change in reducing energy consumption and CO2 emissions in residential buildings. Nature Energy 6, 925–932. doi: 10.1038/s41560-021-00866-x.

Knaus, M. C., M. Lechner, and A. Strittmatter (2021). Machine learning estimation of heterogeneous causal effects: Empirical Monte Carlo evidence. The Econometrics Journal 24, 134–161. doi: 10.1093/ectj/utaa014.

Knittel, C. R. and S. Stolper (2021). Machine Learning about Treatment Effect Heterogeneity: The Case of Household Energy Use. AEA Papers and Proceedings 111, 440–444. doi: 10.1257/pandp.20211090.

Künzel, S., J. Sekhon, P. J. Bickel, and B. Yu (2019). Metalearners for estimating heterogeneous treatment effects using machine learning. Proceedings of the National Academy of Sciences 116, 4156–4165. doi: 10.1073/pnas.1804597116.

Lal, A., W. Zheng, and S. Ejdemyr (2023). A framework for generalization and transportation of causal estimates under covariate shift.

Lechner, M. (2018). Modified causal forests for estimating heterogeneous causal effects.

Liang, J., R. He, and T. Tan (2023). A comprehensive survey on test-time adaptation under distribution shifts.

Löschel, A., M. Rodemeier, and M. Werthschulte (2024). Can self-set goals encourage resource conservation? Field experimental evidence from a smartphone app. European Economic Review (accepted). doi: 10.2139/ssrn.3676090.

Löschel, A., M. Rodemeier, and M. Werthschulte (n.d.). When Nudges Fail to Scale: Field Experimental Evidence from Goal Setting on Mobile Phones (). doi: 10.2139/ssrn.3693673.

Nie, X. and S. Wager (2021). Quasi-oracle estimation of heterogeneous treatment effects. Biometrika 108, 299–319. doi: 10.1093/biomet/asaa076.

Ozyurt, Y., S. Feuerriegel, and C. Zhang (2023). Contrastive learning for unsupervised domain adaptation of time series. The Eleventh International Conference on Learning Representations. url: https://openreview.net/forum?id=xPkJYRsQGM.

Parry, I. W. H. and K. A. Small (2009). Should urban transit subsidies be reduced? American Economic Review 99, 700–724. doi: 10.1257/aer.99.3.700.

Powers, S., J. Qian, K. Jung, A. Schuler, et al. (2018). Some methods for heterogeneous treatment effect estimation in high dimensions. Statistics in Medicine 37, 1767–1787. doi: 10.1002/sim.7623.

Ratnayake, R., F. Finger, A. S. Azman, D. Lantagne, et al. (2021). Highly targeted spatiotemporal interventions against cholera epidemics, 2000–19: A scoping review. The Lancet Infectious Diseases 21, 37–48. doi: 10.1016/S1473-3099(20)30479-5.

Rolnick, D., P. L. Donti, L. H. Kaack, K. Kochanski, et al. (2023). Tackling Climate Change with Machine Learning. ACM Computing Surveys 55, 1–96. doi: 10.1145/3485128.

Schultz, P. W., J. M. Nolan, R. B. Cialdini, N. J. Goldstein, et al. (2007). The constructive, destructive, and reconstructive power of social norms. Psychological Science 18, 429–434. doi: 10.1111/j.1467-9280.2007.01917.x.

Shen, Z., J. Liu, Y. He, X. Zhang, et al. (2021). Towards out-of-distribution generalization: A survey.

Shi, C., D. M. Blei, and V. Veitch (2019). Adapting neural networks for the estimation of treatment effects. Proceedings of the 33rd International Conference on Neural Information Processing Systems. Red Hook, NY, USA: Curran Associates Inc. doi: 10.48550/arXiv.1906.02120.

Shi, X., Z. Chen, H. Wang, D.-Y. Yeung, et al. (2015). Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Proceedings of the 28th International Conference on Neural Information Processing Systems — Volume 1. NIPS’15. Cambridge, MA, USA: MIT Press, 802–810. doi: 10.48550/arXiv.1506.04214.

Song, J., C. Zhao, S. Zhong, T. A. S. Nielsen, et al. (2019). Mapping spatio-temporal patterns and detecting the factors of traffic congestion with multi-source data fusion and mining techniques. Computers, Environment and Urban Systems 77, 101364. doi: 10.1016/j.compenvurbsys.2019.101364.

Song, X., S. Zhao, J. Yang, H. Yue, et al. (2021). Spatio-temporal contrastive domain adaptation for action recognition. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9787–9795. doi: 10.1109/CVPR46437.2021.00966.

Sun, T. Q. and R. Medaglia (2019). Mapping the challenges of Artificial Intelligence in the public sector: Evidence from public healthcare. Government Information Quarterly 36, 368–383. doi: 10.1016/j.giq.2018.09.008.

Sun, Z., Q. Ke, H. Rahmani, M. Bennamoun, et al. (2022). Human Action Recognition From Various Data Modalities: A Review. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1–20. doi: 10.1109/TPAMI.2022.3183112.

Tiefenbeck, V., L. Goette, K. Degen, V. Tasic, et al. (2018). Overcoming Salience Bias: How Real-Time Feedback Fosters Resource Conservation. Management Science 64, 1458–1476. doi: 10.1287/mnsc.2016.2646.

Tiefenbeck, V., T. Staake, K. Roth, and O. Sachs (2013). For better or for worse? Empirical evidence of moral licensing in a behavioral energy conservation campaign. Energy Policy 57, 160–171. doi: 10.1016/j.enpol.2013.01.021.

Vapnik, V. (1995). The nature of statistical learning theory. Springer. doi: 10.1007/978-1-4757-3264-1.

Wager, S. and S. Athey (2018). Estimation and inference of heterogeneous treatment effects using random forests. Journal of the American Statistical Association 113, 1228–1242. doi: 10.1080/01621459.2017.1319839.

Wang, D., E. Shelhamer, S. Liu, B. Olshausen, et al. (2021). TENT: FULLY TEST-TIME ADAPTATION BY ENTROPY MINIMIZATION.

Werthschulte, M. and A. Löschel (2021). On the role of present bias and biased price beliefs in household energy consumption. Journal of Environmental Economics and Management 109, 102500. doi: 10.1016/j.jeem.2021.102500.

Wu, J., Z. Niu, X. Li, L. Huang, et al. (2023). Understanding multi-scale spatiotemporal energy consumption data: A visual analysis approach. Energy 263, 125939. doi: 10.1016/j.energy.2022.125939.

Ye, H., C. Xie, T. Cai, R. Li, et al. (2021). Towards a theoretical framework of out-of-distribution generalization. Advances in Neural Information Processing Systems. Ed. by A. Beygelzimer, Y. Dauphin, P. Liang, and J. W. Vaughan. url: https://openreview.net/forum?id=0WASBV4xkhy.

Yu, B., H. Yin, and Z. Zhu (2018). Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. doi: 10.24963/ijcai.2018/505.

Zhou, A. and S. Levine (n.d.). Training on Test Data with Bayesian Adaptation for Covariate Shift.

To top of page