A deep generative model for probabilistic energy forecasting in power systems: normalizing flows

[en] Greater direct electrification of end-use sectors with a higher share of renewables is one of the pillars to power a carbon-neutral society by 2050. However, in contrast to conventional power plants, renewable energy is subject to uncertainty raising challenges for their interaction with power systems. Scenario-based probabilistic forecasting models have become an important tool to equip decision-makers. This paper proposes to present to the power systems forecasting practitioners a recent deep learning technique, the normalizing flows, to produce accurate scenario-based probabilistic forecasts that are crucial to face the new challenges in power systems applications. The strength of this technique is to directly learn the stochastic multivariate distribution of the underlying process by maximizing the likelihood. Through comprehensive empirical evaluations using the open data of the Global Energy Forecasting Competition 2014, we demonstrate that this methodology is competitive with other state-of-the-art deep learning generative models: generative adversarial networks and variational autoencoders. The models producing weather-based wind, solar power, and load scenarios are properly compared both in terms of forecast value, by considering the case study of an energy retailer, and quality using several complementary metrics. The numerical experiments are simple and easily reproducible. Thus, we hope it will encourage other forecasting practitioners to test and use normalizing flows in power system applications such as bidding on electricity markets, scheduling of power systems with high renewable energy sources penetration, energy management of virtual power plan or microgrids, and unit commitment.

Disciplines :

Engineering, computing & technology: Multidisciplinary, general & others
Energy
Computer science

Author, co-author :

Dumas, Jonathan ; Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart-Microgrids

Wehenkel, Antoine ; Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Big Data

Lanaspeze, damien; Mines ParisTech

Cornélusse, Bertrand ; Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart-Microgrids

Sutera, Antonio ; Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Méthodes stochastiques

Language :

English

Title :

A deep generative model for probabilistic energy forecasting in power systems: normalizing flows

Publication date :

01 January 2022

Journal title :

Applied Energy

ISSN :

0306-2619

eISSN :

1872-9118

Publisher :

Elsevier, London, United Kingdom

Volume :

305

Pages :

117-871

Peer reviewed :

Peer Reviewed verified by ORBi

Additional URL :

https://arxiv.org/pdf/2106.09370.pdf
https://authors.elsevier.com/a/1dpj015eif0fZ5

Available on ORBi :

since 31 July 2021

Statistics

Number of views

658 (26 by ULiège)

Number of downloads

280 (10 by ULiège)

More statistics

Scopus citations^®

Scopus citations^®
without self-citations

OpenCitations

OpenAlex citations

publications

supporting

mentioning

contrasting

Smart Citations

Citing PublicationsSupportingMentioningContrasting

View Citations

See how this article has been cited at scite.ai

scite shows how a scientific paper has been cited by providing the context of the citation, a classification describing whether it supports, mentions, or contrasts the cited claim, and a label indicating in which section the citation was made.

Bibliography

Allen, M., Antwi-Agyei, P., Aragon-Durand, F., Babiker, M., Bertoldi, P., Bind, M., et al. Technical summary: Global warming of 1.5 °C. An IPCC special report on the impacts of global warming of 1.5 °C above pre-industrial levels and related global greenhouse gas emission pathways, in the context of strengthening the global response to the threat of climate change, sustainable development, and efforts to eradicate poverty: Technical report., 2019, Intergovernmental Panel on Climate Change.
Gneiting, T., Katzfuss, M., Probabilistic forecasting. Annu Rev Stat Appl 1 (2014), 125–151.
Hong, T., Fan, S., Probabilistic electric load forecasting: A tutorial review. Int J Forecast 32:3 (2016), 914–938.
Morales, J.M., Conejo, A.J., Madsen, H., Pinson, P., Zugno, M., Integrating renewables in electricity markets: operational problems, vol. 205. 2013, Springer Science & Business Media.
Hong, T., Pinson, P., Wang, Y., Weron, R., Yang, D., Zareipour, H., et al. Energy forecasting: A review and outlook: Technical report., 2020, Department of Operations Research and Business Intelligence, Wroclaw.
Khoshrou, A., Pauwels, E.J., Short-term scenario-based probabilistic load forecasting: A data-driven approach. Appl Energy 238 (2019), 1258–1268.
Mashlakov, A., Kuronen, T., Lensu, L., Kaarna, A., Honkapuro, S., Assessing the performance of deep learning models for multivariate probabilistic energy forecasting. Appl Energy, 285, 2021, 116405.
Wang, P., Liu, B., Hong, T., Electric load forecasting with recency effect: A big data approach. Int J Forecast 32:3 (2016), 585–597.
De Gooijer, J.G., Hyndman, R.J., 25 years of time series forecasting. Int J Forecast 22:3 (2006), 443–473.
Morales, J.M., Minguez, R., Conejo, A.J., A methodology to generate statistically dependent wind speed scenarios. Appl Energy 87:3 (2010), 843–855.
Karaki, S.H., Salim, B.A., Chedid, R.B., Probabilistic model of a two-site wind energy conversion system. IEEE Trans Energy Convers 17:4 (2002), 530–536.
Karaki, S., Chedid, R., Ramadan, R., Probabilistic performance assessment of autonomous solar-wind energy conversion systems. IEEE Trans Energy Convers 14:3 (1999), 766–772.
Pinson, P., Madsen, H., Nielsen, H.A., Papaefthymiou, G., Klöckl, B., From probabilistic forecasts to statistical scenarios of short-term wind power production. Wind Energy 12:1 (2009), 51–62.
Zhang, H., Lu, Z., Hu, W., Wang, Y., Dong, L., Zhang, J., Coordinated optimal operation of hydro–wind–solar integrated systems. Appl Energy 242 (2019), 883–896.
Camal, S., Teng, F., Michiorri, A., Kariniotakis, G., Badesa, L., Scenario generation of aggregated Wind, Photovoltaics and small Hydro production for power systems applications. Appl Energy 242 (2019), 1396–1406.
Shi, H., Xu, M., Li, R., Deep learning for household load forecasting—A novel pooling deep RNN. IEEE Trans Smart Grid 9:5 (2017), 5271–5280.
Dumas, J., Cointe, C., Fettweis, X., Cornélusse, B., Deep learning-based multi-output quantile forecasting of pv generation. 2021 IEEE Madrid PowerTech, 2021, 1–6, 10.1109/PowerTech46648.2021.9494976.
Hewamalage, H., Bergmeir, C., Bandara, K., Recurrent neural networks for time series forecasting: Current status and future directions. Int J Forecast 37:1 (2020), 388–427.
Toubeau, J.-F., Bottieau, J., Vallée, F., De Grève, Z., Deep learning-based multivariate probabilistic forecasting for short-term scheduling in power markets. IEEE Trans Power Syst 34:2 (2018), 1203–1215.
Salinas, D., Flunkert, V., Gasthaus, J., Januschowski, T., DeepAR: Probabilistic forecasting with autoregressive recurrent networks. Int J Forecast 36:3 (2020), 1181–1191.
Bond-Taylor, S., Leach, A., Long, Y., Willcocks, C.G., Deep generative modelling: A comparative review of VAEs, GANs, normalizing flows, energy-based and autoregressive models. 2021 arXiv preprint arXiv:2103.04922.
Ruthotto, L., Haber, E., An introduction to deep generative modeling. GAMM-Mitt, 2021, e202100008.
Kingma, D.P., Welling, M., Auto-encoding variational bayes. 2013 arXiv preprint arXiv:1312.6114.
Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., et al. Generative adversarial networks. 2014 arXiv preprint arXiv:1406.2661.
Ordiano, J.A.G., Gröll, L., Mikut, R., Hagenmeyer, V., Probabilistic energy forecasting using the nearest neighbors quantile filter and quantile regression. Int J Forecast 36:2 (2020), 310–323.
Sun, M., Feng, C., Zhang, J., Probabilistic solar power forecasting based on weather scenario generation. Appl Energy, 266, 2020, 114823.
Zhanga, H., Hua, W., Yub, R., Tangb, M., Dingc, L., Optimized operation of cascade reservoirs Considering Complementary Characteristics between wind and photovoltaic based on variational auto-encoder. MATEC web of conferences, vol. 246, 2018, EDP Sciences, 01077.
Dairi, A., Harrou, F., Sun, Y., Khadraoui, S., Short-term forecasting of photovoltaic solar power production using variational auto-encoder driven deep learning approach. Appl Sci, 10(23), 2020, 8400.
Chen, Y., Wang, Y., Kirschen, D., Zhang, B., Model-free renewable scenario generation using generative adversarial networks. IEEE Trans Power Syst 33:3 (2018), 3265–3275.
Chen, Y., Li, P., Zhang, B., Bayesian renewables scenario generation via deep generative networks. 2018 52nd annual conference on information sciences and systems, 2018, IEEE, 1–6.
Yuan, R., Wang, B., Mao, Z., Watada, J., Multi-objective wind power scenario forecasting based on PG-GAN. Energy, 2021, 120379.
Chen, Z., Jiang, C., Building occupancy modeling using generative adversarial network. Energy Build 174 (2018), 372–379.
Lan, J., Guo, Q., Sun, H., Demand side data generating based on conditional generative adversarial networks. Energy Procedia 152 (2018), 1188–1193.
Zhang, Y., Ai, Q., Xiao, F., Hao, R., Lu, T., Typical wind power scenario generation for multiple wind farms using conditional improved wasserstein generative adversarial network. Int J Electr Power Energy Syst, 114, 2020, 105388.
Wang, Y., Hug, G., Liu, Z., Zhang, N., Modeling load forecast uncertainty using generative adversarial networks. Electr Power Syst Res, 189, 2020, 106732.
Jiang, C., Mao, Y., Chai, Y., Yu, M., Day-ahead renewable scenario forecasts based on generative adversarial networks. Int J Energy Res 45:5 (2021), 7572–7587.
Qi, Y., Hu, W., Dong, Y., Fan, Y., Dong, L., Xiao, M., Optimal configuration of concentrating solar power in multienergy power systems with an improved variational autoencoder. Appl Energy, 274, 2020, 115124.
Ge, L., Liao, W., Wang, S., Bak-Jensen, B., Pillai, J.R., Modeling daily load profiles of distribution network for scenario generation using flow-based generative network. IEEE Access 8 (2020), 77587–77597.
Rezende, D., Mohamed, S., Variational inference with normalizing flows. International conference on machine learning, 2015, PMLR, 1530–1538.
Oord, A., Li, Y., Babuschkin, I., Simonyan, K., Vinyals, O., Kavukcuoglu, K., et al. Parallel wavenet: Fast high-fidelity speech synthesis. International conference on machine learning, 2018, PMLR, 3918–3926.
Green, S.R., Gair, J., Complete parameter inference for GW150914 using deep learning. Mach Learn: Sci Technol, 2(3), 2021, 03LT01.
Albergo, M.S., Boyda, D., Hackett, D.C., Kanwar, G., Cranmer, K., Racanière, S., et al. Introduction to normalizing flows for lattice field theory. 2021 arXiv preprint arXiv:2101.08176.
Dumas, J., Cointe, C., Wehenkel, A., Sutera, A., Fettweis, X., Cornélusse, B., A probabilistic forecast-driven strategy for a risk-aware participation in the capacity firming market. IEEE Trans Sustain Energy, 2021 Manuscript [submitted for publication].
Huang, C.-W., Krueger, D., Lacoste, A., Courville, A., Neural autoregressive flows. International conference on machine learning, 2018, PMLR, 2078–2087.
Hong, T., Pinson, P., Fan, S., Zareipour, H., Troccoli, A., Hyndman, R.J., Probabilistic energy forecasting: Global energy forecasting competition 2014 and beyond. 2016, Elsevier.
Silva, J.A.A., López, J.C., Arias, N.B., Rider, M.J., da Silva, L.C., An optimal stochastic energy management system for resilient microgrids. Appl Energy, 300, 2021, 117435.
Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y., Deep learning, vol. 1, no. 2. 2016, MIT Press Cambridge.
Zhang, A., Lipton, Z.C., Li, M., Smola, A.J., Dive Into Deep Learning, 2020 https://d2l.ai.
Kingma, D.P., Salimans, T., Jozefowicz, R., Chen, X., Sutskever, I., Welling, M., Improving variational inference with inverse autoregressive flow. 2016 arXiv preprint arXiv:1606.04934.
Wehenkel, A., Louppe, G., Unconstrained monotonic neural networks. Advances in neural information processing systems, 2019, 1545–1555.
Papamakarios, G., Pavlakou, T., Murray, I., Masked autoregressive flow for density estimation. Advances in neural information processing systems, 2017, 2338–2347.
Pérez-Cruz, F., Kullback–Leibler divergence estimation of continuous distributions. 2008 IEEE international symposium on information theory, 2008, IEEE, 1666–1670.
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A., Improved training of wasserstein gans. 2017 arXiv preprint arXiv:1704.00028.
Wehenkel, A., Louppe, G., Graphical normalizing flows. 2020 arXiv preprint arXiv:2006.02548.
Zhao, S., Song, J., Ermon, S., Towards deeper understanding of variational autoencoding models. 2017 arXiv preprint arXiv:1702.08658.
Arjovsky, M., Bottou, L., Towards principled methods for training generative adversarial networks. 2017 arXiv preprint arXiv:1701.04862.
Theis, L., Oord, A.v.d., Bethge, M., A note on the evaluation of generative models. 2015 arXiv preprint arXiv:1511.01844.
Borji, A., Pros and cons of gan evaluation measures. Comput Vis Image Underst 179 (2019), 41–65.
Xu, Q., Huang, G., Yuan, Y., Guo, C., Sun, Y., Wu, F., et al. An empirical study on evaluation metrics of generative adversarial networks. 2018 arXiv preprint arXiv:1806.07755.
Gneiting, T., Raftery, A.E., Strictly proper scoring rules, prediction, and estimation. J Amer Statist Assoc 102:477 (2007), 359–378.
Lauret, P., David, M., Pinson, P., Verification of solar irradiance probabilistic forecasts. Sol Energy 194 (2019), 254–271.
Golestaneh, F., Gooi, H.B., Pinson, P., Generation and evaluation of space–time trajectories of photovoltaic power. Appl Energy 176 (2016), 80–91.
Scheuerer, M., Hamill, T.M., Variogram-based proper scoring rules for probabilistic forecasts of multivariate quantities. Mon Weather Rev 143:4 (2015), 1321–1334.
Geurts, P., Ernst, D., Wehenkel, L., Extremely randomized trees. Mach Learn 63:1 (2006), 3–42.
Fawcett, T., ROC graphs: Notes and practical considerations for researchers. Mach Learn 31:1 (2004), 1–38.
Diebold, F.X., Mariano, R.S., Comparing predictive accuracy. J Bus Econom Statist 20:1 (2002), 134–144.
Ziel, F., Weron, R., Day-ahead electricity price forecasting with high-dimensional structures: Univariate vs. multivariate modeling frameworks. Energy Econ 70 (2018), 396–420.
Landry, M., Erlinger, T.P., Patschke, D., Varrichio, C., Probabilistic gradient boosting machines for GEFCom2014 wind forecasting. Int J Forecast 32:3 (2016), 1061–1066.
Buitinck L, Louppe G, Blondel M, Pedregosa F, Mueller A, Grisel O et al. API design for machine learning software: experiences from the scikit-learn project. In: ECML PKDD workshop: languages for data mining and machine learning. 2013. p. 108–22.
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., et al. PyTorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, vol. 32, 2019, Curran Associates, Inc., 8024–8035.
Biewald, L., Experiment tracking with weights and biases. 2020 URL: https://www.wandb.com/. Software available from wandb.com.
Papamakarios, G., Nalisnick, E., Rezende, D.J., Mohamed, S., Lakshminarayanan, B., Normalizing flows for probabilistic modeling and inference. 2019 arXiv preprint arXiv:1912.02762.
Kobyzev, I., Prince, S., Brubaker, M., Normalizing flows: An introduction and review of current methods. IEEE Trans Pattern Anal Mach Intell, 2020.
Arjovsky, M., Chintala, S., Bottou, L., Wasserstein generative adversarial networks. International conference on machine learning, 2017, PMLR, 214–223.
Villani, C., Optimal transport: old and new, vol. 338. 2008, Springer Science & Business Media.
Kingma, D.P., Ba, J., Adam: A method for stochastic optimization. 2014 arXiv preprint arXiv:1412.6980.
Zamo, M., Naveau, P., Estimation of the continuous ranked probability score with limited information and applications to ensemble weather forecasts. Math Geosci 50:2 (2018), 209–234.
Gneiting, T., Stanberry, L.I., Grimit, E.P., Held, L., Johnson, N.A., Assessing probabilistic forecasts of multivariate quantities, with an application to ensemble predictions of surface winds. Test 17:2 (2008), 211–235.
Lehmann, E.L., Romano, J.P., Testing statistical hypotheses. 2006, Springer Science & Business Media.

Similar publications

Sorry the service is unavailable at the moment. Please try again later.

Name	Provider / Domaine	Expiration	Description
JSESSIONID	Oracle Corporation www.uliege.be	Session	General purpose platform session cookie, used by sites written in JSP. Usually used to maintain an anonymous user session by the server.
CookieScriptConsent	CookieScript .uliege.be	1 year	This cookie is used by Cookie-Script.com service to remember visitor cookie consent preferences. It is necessary for Cookie-Script.com cookie banner to work properly.

Name	Provider / Domaine	Expiration	Description
_pk_id	InnoCraft Ltd .uliege.be	1 year	Used to store a few details about the user such as the unique visitor ID
_pk_ses	InnoCraft Ltd .uliege.be	30 minutes	Short lived cookies used to temporarily store data for the visit
_pk_ref	InnoCraft Ltd .uliege.be	6 months	Used to store the attribution information, the referrer initially used to visit the website