Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Enhanced spatio-temporal electric load forecasts using less data with active deep learning

Abstract

An effective way to mitigate climate change is to electrify most of our energy demand and supply the necessary electricity from renewable wind and solar power plants. Spatio-temporal predictions of electric load become increasingly important for planning this transition, while deep learning prediction models provide increasingly accurate predictions for it. The data that are used for training deep learning models, however, are usually collected at random using a passive learning approach. This naturally results in a large demand for data and associated costs for sensors such as smart meters, posing a large barrier for electric utilities when decarbonizing their grids. Here we investigate whether electric utilities can use active learning to collect a more informative subset of data by leveraging additional computation for better distributing smart meters. We predict ground-truth electric load profiles for single buildings using only remotely sensed data from aerial imagery of these buildings and meteorological conditions in the area of these buildings at different times. We find that active learning can enable 26–81% more accurate predictions using 29–46% less data at the price of 4–11 times more computation compared with passive learning.

This is a preview of subscription content, access via your institution

Access options

Buy article

Get time limited or full article access on ReadCube.

$32.00

All prices are NET prices.

Fig. 1: The current state of global smart meter adoption.
Fig. 2: Overview of the spatio-temporal embedding network architecture.
Fig. 3: Overview of ADL variants.
Fig. 4: Exemplar results for spatio-temporal predictions and ADL variable \({\hat{{{{\mathbf{y}}}}}}_{t,s}\).
Fig. 5: Exemplar results for reducing computational time and testing query sequence.

Data availability

All of our data and results can be accessed on the Harvard Dataverse under a CC0 1.0 license (https://doi.org/10.7910/DVN/3VYYET). For privacy maintenance, we only provide load profiles that are sampled from the original data and histograms of pixel values of building images, which can be used to reproduce all the elements of our original experiments.

Code availability

All results, figures and tables can be reproduced using step-by-step instructions in Jupyter notebook sessions that we provide in a public Github repository (https://github.com/ArsamAryandoust/DataSelectionMaps). We further maintain a Python package (https://pypi.org/project/altility) and a Docker container (https://hub.docker.com/r/aryandoustarsam/altility) implementation of our algorithm. All code is available under an MIT license.

References

  1. Patt, A. Transforming Energy – Solving Climate Change with Technology Policy (Cambridge Univ. Press, 2015).

  2. IPCC Special Report on Global Warming of 1.5 °C (eds Masson-Delmotte, V. et al.) (WMO, 2018).

  3. IPCC Climate Change 2021: The Physical Science Basis (eds Masson-Delmotte, V. et al.) (Cambridge Univ. Press, 2021).

  4. Hahn, H., Meyer-Nieberg, S. & Pickl, S. Electric load forecasting methods: tools for decision making. Eur. J. Oper. Res. https://doi.org/10.1016/j.ejor.2009.01.062 (2009).

  5. Soliman, A.-h. S. & Al-Kandari, A. M. Electric Load Forecasting (Butterworth-Heinemann, 2010).

  6. Alfares, H. K. & Nazeeruddin, M. Electric load forecasting: literature survey and classification of methods. Int. J. Syst. Sci. 33, 23–24 (2002).

    Article  MATH  Google Scholar 

  7. Kofi Nti, I., Teimeh, M., Nyarko-Boateng, O. & Adekoya, A. F. Electricity load forecasting: a systematic review. J. Electr. Syst. Inform. Technol. 7, 13 (2020).

    Article  Google Scholar 

  8. Shi, J., Liu, Y. & Yu, N. Spatio-temporal modeling of electric loads. IEEE https://doi.org/10.1109/NAPS.2017.8107311 (2017).

  9. Tascikaraoglu, A. Evaluation of spatio-temporal forecasting methods in various smart city applications. Renew. Sustain. Energy Rev. 82, 424–435 (2018).

    Article  Google Scholar 

  10. Severiano, C. A., Cândido de Lima eSilva, P., Cohen, M. W. & Gadelha Guimarãesae, F. Evolving fuzzy time series for spatio-temporal forecasting in renewable energy systems. Renew. Energy 171, 764–783 (2021).

    Article  Google Scholar 

  11. Willis, H. L. Spatial Electric Load Forecasting (Marcel Dekker, 2002).

  12. Rolf, E. et al. A generalizable and accessible approach to machine learning with global satellite imagery. Nat. Commun. 12, 4392 (2021).

    Article  Google Scholar 

  13. Burke, M., Driscoll, A.Lobell, D. B. & Ermon, S. Using satellite imagery to understand and promote sustainable development. Science https://doi.org/10.1126/science.abe8628 (2021).

  14. Melo, J. D. & Carreno, E. M. Data Issues in Spatial Electric Load Forecasting (IEEE, 2014).

  15. Milam, M. & Venayagamoorthy, G. K. Smart meter deployment: US initiatives. IEEE https://doi.org/10.1109/ISGT.2014.6816507 (2014).

  16. Sovacool, B. K., Hook, A., Sareen, S. & Geels, F. W. Global sustainability, innovation and governance dynamics of national smart electricity meter transitions. Glob. Environ. Change https://doi.org/10.1016/j.gloenvcha.2021.102272 (2021).

  17. Kezunovic, M., Xie, L. & Grijalva, S. The role of big data in improving power system operation and protection. IEEE https://doi.org/10.1109/IREP.2013.6629368 (2013).

  18. Yu, N. et al. The role of big data in improving power system operation and protection. IEEE https://doi.org/10.1109/ISGT.2015.7131868 (2015).

  19. Stein, A. L. Artificial intelligence and climate change. Yale J. Regul. 37, 890–934 (2020).

    Google Scholar 

  20. Rolnick, D. et al. Tackling climate change with machine learning. ACM Comput. Surv. https://doi.org/10.1145/3485128 (2022).

  21. Kuo, P., Liang, D., Gao, L. & Lou, J. Probabilistic electricity price forecasting with variational heteroscedastic Gaussian process and active learning. Energy Convers. Manage. 89, 298–308 (2015).

    Article  Google Scholar 

  22. Wang, Z., Zhao, B., Guo, H., Tang, L. & Peng, Y. Deep ensemble learning model for short-term load forecasting within active learning framework. Energies https://doi.org/10.3390/en12203809 (2019).

  23. Zhang, L. & Wen, J. Active learning strategy for high fidelity short-term data-driven building energy forecasting. Energy Build. https://doi.org/10.1016/j.enbuild.2021.111026 (2021).

  24. Kuster, C., Rezgui, Y. & Mourshed, M. Electrical load forecasting models: a critical systematic review. Sustain. Cities Soc. 35, 257–270 (2017).

    Article  Google Scholar 

  25. Panamtash, H., Mahdavi, S., Dimitrovski, A. & Zhou, Q. Comparison of Probabilistic Forecasts for Predictive Voltage Control (North American Power Symposium, 2021).

  26. Chen, T. et al. Big self-supervised models are strong semi-supervised learners. In Proc. of the 34th Conference on Advances in Neural Information Processing Systems 33 (eds Larochelle, H. et al.) 22243–22255 (NeurIPS, 2020).

  27. Yue, X. et al. Prototypical cross-domain self-supervised learning for few-shot unsupervised domain adaptation. In Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 13834–13844 (CVF, 2021).

  28. Yang, W. et al. Class distribution alignment for adversarial domain adaptation. Preprint at https://arxiv.org/abs/2004.09403 (2020).

  29. Saito, K., Saenko, K. & Liu, M.-Y. COCO-FUNIT: few-shot unsupervised image translation with a content conditioned style encoder. In Proc. of 16th European Conference on Computer Vision (eds Vedaldi, A. et al.) 382–398 (Springer, 2020).

  30. Jain, A., Zamir, A. R., Savarese, S. & Saxena, A. Structural-RNN: deep learning on spatio-temporal graphs. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016).

  31. Mikolov, T., Chen, K., Corrado, G. & Dean, J. Efficient estimation of word representations in vector space. Preprint at https://arxiv.org/abs/1301.3781 (2013).

  32. Frome, A. et al. DeViSE: a deep visual-semantic embedding model. In Proc. of the 26th Advances in Neural Information Processing Systems 26 (eds Burges, C.J. et al.) 2121–2129 (NIPS, 2013).

  33. Pennington, J., Socher, R. & Manning, C. D. GloVe: Global vectors for word representation. In Proc. of the 2014 Conference on Empirical Methods in Natural Language Processing (eds Moschitti, A. et al.) 1532–1543 (ACL, 2014).

  34. Perozzi, B., Al-Rfou, R. & Skiena, S. DeepWalk: online learning of social represenations. Preprint at https://arxiv.org/abs/1403.6652 (2014).

  35. Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. BERT: pre-training of deep bidirectional transformers for language understanding. Preprint at https://arxiv.org/abs/1810.04805 (2019).

  36. GeoVITE – user-friendly geodata service. Swiss Federal Office of Topography https://geovite.ethz.ch/ (2020).

  37. Pfenninger, S. & Staffel, I. Long-term patterns of European PV output using 30 years of validated hourly reanalysis and satellite data. Energy 114, 1251–1265 (2016).

    Article  Google Scholar 

  38. Staffel, I. & Pfenninger, S. Using bias-corected reanalysis to simulate current and future wind power output. Energy 114, 1224–1239 (2016).

    Article  Google Scholar 

  39. Ash, J. T., Zhang, C., Krishnamurthy, A., Langford, J. & Agarwal, A. Deep batch active learning by diverse, uncertain gradient lower bounds. In Proc. of International Conference on Learning Representations https://openreview.net/forum?id=ryghZJBKPS (2020).

Download references

Acknowledgements

We acknowledge funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement no. 837089 (A.A., A.P. and S.P.), for the SENTINEL project.

Author information

Authors and Affiliations

Authors

Contributions

A.A. conceptualized the research, designed and implemented all the methods, conducted all the analyses and drafted the manuscript. S.P. edited and revised the manuscript and reviewed the code. A.P. helped in interpreting the data and supervised the creation of the manuscript.

Corresponding author

Correspondence to Arsam Aryandoust.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Machine Intelligence thanks Valentin Robu and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Aryandoust, A., Patt, A. & Pfenninger, S. Enhanced spatio-temporal electric load forecasts using less data with active deep learning. Nat Mach Intell 4, 977–991 (2022). https://doi.org/10.1038/s42256-022-00552-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s42256-022-00552-x

Search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing