Wind is a highly unstable renewable energy source. Accurate forecasting can mitigate the effects of wind inconsistency on the electric grid and help avoid investments in costly energy storage infrastructure. Basing the predictions on open-source forecast models and climate data also makes them entirely free of charge. The present work studies the feasibility of using two machine learning (ML) models and one deep learning (DL) model, random forest (RF) regression, support vector regression (SVR), and long short-term memory (LSTM) for short-term wind power forecasting based on the publicly accessible ERA5-Land dataset. For each forecast model, a selection of hyperparameters is first tuned, followed by determining the best performing input data structure using surrounding data grid points and increasing the time interval of data affecting a single prediction. Both the ML models and the DL model perform better than the baseline (BL) model when forecasting wind speed up to 24 hours ahead. However, a reduced forecast duration is needed to achieve satisfactory wind turbine (WT) power output forecast accuracy. Most notably, the RF is able to produce 3-hour forecasts with the combined WT power output prediction error amounting to less than 10 % of the WT's nominal power.

References

1. 1)
  - 13. Ali, M.E.K., Hassan, M.Z., Shawkat-Ali, A.B.M., et al: ‘Prediction of wind speed using real data: an analysis of statistical machine learning techniques’. 2017 4th Asia-Pacific World Congress on Computer Science and Engineering (APWC on CSE). (IEEE), Nadi, Fiji, 2017, pp. 259–264. Available from: https://ieeexplore.ieee.org/document/8487297/.
2. 2)
  - 29. Tawn, R., Browell, J., Dinwoodie, I.: ‘Missing data in wind farm time series: properties and effect on forecasts’, Electr. Power Syst. Res., 2020, 189, p. 106640. Available from: https://linkinghub.elsevier.com/retrieve/pii/S0378779620304430.
3. 3)
  - 18. Pandit, R.K., Infield, D., Kolios, A.: ‘Comparison of advanced non-parametric models for wind turbine power curves’, IET Renew. Power Gener., 2019, 13, (9), pp. 1503–1510. Available from: https://digital-library.theiet.org/content/journals/10.1049/iet-rpg.201 8.5728.
4. 4)
  - 24. ECMWF. ‘ERA5-Land documentation’, accessed Feb. 2020. https://confluence.ecmwf.int/display/CKB/ERA5-Land.
5. 5)
  - 32. Hoffmann, L., Günther, G., Li, D., et al: ‘From ERA-interim to ERA5: the considerable impact of ECMWF's next-generation reanalysis on lagrangian transport simulations’, Atmos. Chem. Phys., 2019, 19, (5), pp. 3097–3124. Available from: https://www.atmos-chem-phys.net/19/3097/2019/.
6. 6)
  - 23. Dong, D., Sheng, Z., Yang, T.: ‘Wind power prediction based on recurrent neural network with long short-term memory units’. 2018 Int. Conf. on Renewable Energy and Power Engineering (REPE). (IEEE), Toronto, ON, Canada, 2018, pp. 34–38. Available from: https://ieeexplore.ieee.org/document/8657666/.
7. 7)
  - 34. Ottens, E., Danesh, A., Adekanye, O., et al: ‘Short-term wind forecasting using spatial and temporal wind measurements’. 2015 IEEE Power & Energy Society General Meeting. (IEEE), Denver, CO, USA, 2015, pp. 1–4. Available from: http://ieeexplore.ieee.org/document/7286596/.
8. 8)
  - 11. Gilbert, C., Browell, J., McMillan, D.: ‘Probabilistic access forecasting for improved offshore operations’, Int. J. Forecast., 2021, 37, (1), pp. 134–150, Available from: https://linkinghub.elsevier.com/retrieve/pii/S016920702030056X.
9. 9)
  - 48. Silva, J., Ribeiro, C., Guedes, R., et al: ‘Roughness length classification of corine land cover classes’. Proc. of EWEC 2007, Milan, Italy, 2007.
10. 10)
  - 42. Hochreiter, S., Schmidhuber, J.: ‘Long short-term memory’, Neural Comput., 1997, 9, (8), pp. 1735–1780. Available from: https://doi.org/10.1162/neco.1997.9.8.1735.
11. 11)
  - 4. Child, M., Kemfert, C., Bogdanov, D., et al: ‘Flexible electricity generation, grid exchange and storage for the transition to a 100% renewable energy system in europe’, Renew. Energy, 2019, 139, pp. 80–101. Available from: https://linkinghub.elsevier.com/retrieve/pii/S0960148119302319.
12. 12)
  - 27. Olauson, J.: ‘ERA5: the new champion of wind power modelling?’, Renew. Energy, 2018, 126, pp. 322–331. Available from: https://linkinghub.elsevier.com/retrieve/pii/S0960148118303677.
13. 13)
  - 6. Liu, F., Giulietti, M., Chen, B.: ‘Joint optimisation of generation and storage in the presence of wind’, IET Renew. Power Gener., 2016, 10, (10), pp. 1477–1487. Available from: https://digital-library.theiet.org/content/journals/10.1049/iet-rpg.201 5.0547.
14. 14)
  - 33. Ascencio-Vásquez, J., Kaaya, I., Brecl, K., et al: ‘Global climate data processing and mapping of degradation mechanisms and degradation rates of PV modules’, Energies, 2019, 12, (24), p. 4749. Available from: https://www.mdpi.com/1996-1073/12/24/4749.
15. 15)
  - 28. Bechtle, P., Schelbergen, M., Schmehl, R., et al: ‘Airborne wind energy resource analysis’, Renew. Energy, 2019, 141, pp. 1103–1116. Available from: https://linkinghub.elsevier.com/retrieve/pii/S0960148119304306.
16. 16)
  - 51. Bajt, G., Marinšek, A.: ‘Onshore wind forecasting repository’, accessed Feb. 2020. https://github.com/AlexanderMarinsek/onshore-wind-forecasting.
17. 17)
  - 26. Troen, I., Lundtang-Petersen, E.: ‘European wind Atlas’ (Risø National Laboratory, Roskilde, 1989).
18. 18)
  - 10. Messner, J.W., Pinson, P., Browell, J., et al: ‘Evaluation of wind power forecasts–an up-to-date view’, Wind Energy, 2020, 23, (6), pp. 1461–1481. Available from: https://onlinelibrary.wiley.com/doi/abs/10.1002/we.2497.
19. 19)
  - 3. Lombardi, P., Sokolnikova, T., Suslov, K., et al: ‘Isolated power system in russia: a chance for renewable energies?’, Renew. Energy, 2016, 90, pp. 532–541. Available from: https://linkinghub.elsevier.com/retrieve/pii/S0960148116300167.
20. 20)
  - 2. Reichenberg, L., Hedenus, F., Odenberger, M., et al: ‘The marginal system LCOE of variable renewables – evaluating high penetration levels of wind and solar in europe’, Energy, 2018, 152, pp. 914–924. Available from: https://linkinghub.elsevier.com/retrieve/pii/S0360544218302895.
21. 21)
  - 41. Pandit, R., Infield, D.: ‘Comparative analysis of binning and support vector regression for wind turbine rotor speed based power curve use in condition monitoring’. 2018 53rd Int. Universities Power Engineering Conf. (UPEC), Glasgow, IEEE, 2018, pp. 1–6. Available from: https://ieeexplore.ieee.org/document/8542057/.
22. 22)
  - 20. Ak, R., Fink, O., Zio, E.: ‘Two machine learning approaches for short-term wind speed time-series prediction’, IEEE Trans. Neural Netw. Learning Syst., 2016, 27, (8), pp. 1734–1747. Available from: http://ieeexplore.ieee.org/document/7091914/.
23. 23)
  - 7. Tam, K.S.: ‘Energy storage technologies for future electric power systems’. 10th Int. Conf. on Advances in Power System Control Operation & Management (APSCOM 2015). (Institution of Engineering and Technology, Hong Kong, China, 2015, Available from: https://digital-library.theiet.org/content/conferences/10.1049/ic.2015. 0238.
24. 24)
  - 46. Bauelos-Ruedas, F., Angeles-Camacho, C., Sebastin, : ‘Methodologies used in the extrapolation of wind speed data at different heights and its impact in the wind energy resource assessment in a region’, in Suvire, G.O. (Ed.): ‘Wind farm - technical regulations, potential estimation and siting assessment’ (InTech, Rijeka, Croatia, 2011). Available from: http://www.intechopen.com/books/wind-farm-technical-regulations-potenti al-estimation-and-siting-assessment/methodologies-used-in-the-extrapolation-of -wind-speed-data-at-different-heights-and-its-impact-in-th.
25. 25)
  - 1. REN21: ‘Renewables 2019 Global Status Report’, (REN21 Secretariat Paris), 2019, p. 41.
26. 26)
  - 16. Demolli, H., Dokuz, A.S., Ecemis, A., et al: ‘Wind power forecasting based on daily wind speed data using machine learning algorithms’, Energy Convers. Manage., 2019, 198. Available fromhttps://www.sciencedirect.com/science/article/pii/S0196890419308052.
27. 27)
  - 36. Kumar, S.P.: ‘Improved prediction of wind speed using machine learning’, EAI Endorsed Trans. Energy Web, 2019, 6, (23). Available from: https://eudl.eu/doi/10.4108/eai.13-7-2018.157033.
28. 28)
  - 30. Albergel, C., Dutra, E., Munier, S., et al: ‘ERA-5 and ERA-interim driven ISBA land surface model simulations: which one performs better?’, Hydrology Earth Syst. Sci., 2018, 22, (6), pp. 3515–3532. Available from: https://www.hydrol-earth-syst-sci.net/22/3515/2018/.
29. 29)
  - 15. Wang, X.: ‘Forecasting short-term wind speed using support vector machine with particle swarm optimization’. 2017 Int. Conf. on Sensing Diagnostics Prognostics and Control (SDPC). (IEEE, Shanghai, China, 2017, pp. 241–245. Available from: http://ieeexplore.ieee.org/document/8186509/.
30. 30)
  - 31. Uppala, S., Dee, D., Kobayashi, S., et al: ‘Evolution of reanalysis at ECMWF’, 2008. https://www.researchgate.net/publication/242086230_Evolution_of_reanaly sis_at_ECMWF.
31. 31)
  - 49. Technical University of Denmark (DTU). ‘Global Wind Atlas’, accessed Feb. 2020. https://globalwindatlas.info/.
32. 32)
  - 47. Gualtieri, G.: ‘A comprehensive review on wind resource extrapolation models applied in wind energy’, Renew. Sustain. Energy Rev., 2019, 102, pp. 215–233. Available from: https://linkinghub.elsevier.com/retrieve/pii/S1364032118308104.
33. 33)
  - 25. Majidi-Nezhad, M., Groppi, D., Marzialetti, P., et al: ‘Wind energy potential analysis using sentinel-1 satellite: a review and a case study on mediterranean islands’, Renew. Sustain. Energy Rev., 2019, 109, pp. 499–513. Available from: https://linkinghub.elsevier.com/retrieve/pii/S1364032119302801.
34. 34)
  - 8. Miettinen, J., Holttinen, H.: ‘Impacts of wind power forecast errors on the real-time balancing need: a nordic case study’, IET Renew. Power Gener., 2019, 13, (2), pp. 227–233. Available from: https://digital-library.theiet.org/content/journals/10.1049/iet-rpg.201 8.5234.
35. 35)
  - 44. Panchal, F.S., Panchal, M.: ‘Review on methods of selecting number of hidden nodes in artificial neural network’, Int. J. Comput. Sci. Mobile Comput., 2014, 3, pp. 455–464.
36. 36)
  - 37. Copernicus. ‘Era5-Land API’, accessed Feb. 2020. https://cds.climate.copernicus.eu/cdsapp#!/dataset/reanalysis-era5-land.
37. 37)
  - 43. Pandit, R.K., Kolios, A., Infield, D.: ‘Data-driven weather forecasting models performance comparison for improving offshore wind turbine availability and maintenance’, IET Renew. Power Gener., 2020, 14, (13), pp. 2386–2394. Available from: https://digital-library.theiet.org/content/journals/10.1049/iet-rpg.201 9.0941.
38. 38)
  - 22. Wu, Y.X., Wu, Q.B., Zhu, J.Q.: ‘Data-driven wind speed forecasting using deep feature extraction and LSTM’, IET Renew. Power Gener., 2019, 13, (12), pp. 2062–2069. Available from: https://digital-library.theiet.org/content/journals/10.1049/iet-rpg.201 8.5917.
39. 39)
  - 45. Sheela, K.G., Deepa, S.N.: ‘Review on methods to fix number of hidden neurons in neural networks’, Math. Probl. Eng., 2013, 2013, pp. 1–11. Available from: http://www.hindawi.com/journals/mpe/2013/425740/.
40. 40)
  - 35. Liu, Y., Zhang, H.: ‘An empirical study on machine learning models for wind power predictions’. 2016 15th IEEE Int. Conf. on Machine Learning and Applications (ICMLA). (IEEE), Anaheim, CA, USA, 2016, pp. 758–763. Available from: http://ieeexplore.ieee.org/document/7838239/.
41. 41)
  - 17. Huang, C.M., Kuo, C.J., Huang, Y.C.: ‘Short-term wind power forecasting and uncertainty analysis using a hybrid intelligent method’, IET Renew. Power Gener., 2017, 11, (5), pp. 678–687. Available from: https://digital-library.theiet.org/content/journals/10.1049/iet-rpg.201 6.0672.
42. 42)
  - 40. Dragomir, G., Şerban, A., Năstase, G., et al: ‘Wind energy in romania: a review from 2009 to 2016’, Renew. Sustain. Energy Rev., 2016, 64, pp. 129–143. Available from: http://linkinghub.elsevier.com/retrieve/pii/S1364032116301927.
43. 43)
  - 21. Gendeel, M., Yuxian, Z., Aoqi, H.: ‘Performance comparison of ANNs model with VMD for short-term wind speed forecasting’, IET Renew. Power Gener., 2018, 12, (12), pp. 1424–1430. Available from: https://digital-library.theiet.org/content/journals/10.1049/iet-rpg.201 8.5203.
44. 44)
  - 39. Onea, F., Rusu, L.: ‘A study on the wind energy potential in the romanian coastal environment’, J. Marine Sci. Eng., 2019, 7, (5), p. 142. Available from: https://www.mdpi.com/2077-1312/7/5/142.
45. 45)
  - 9. El-Moursi, M.S., Al-Hinai, A., Ssekulima, E.B., et al: ‘Wind speed and solar irradiance forecasting techniques for enhanced renewable energy integration with the grid: a review’, IET Renew. Power Gener., 2016, 10, (7), pp. 885–989. Available from: https://digital-library.theiet.org/content/journals/10.1049/iet-rpg.201 5.0477.
46. 46)
  - 12. Gilbert, C., Browell, J., McMillan, D.: ‘Leveraging turbine-Level data for improved probabilistic wind power forecasting’, IEEE Trans. Sustain. Energy, 2020, 11, (3), pp. 1152–1160. Available from: https://ieeexplore.ieee.org/document/8732463/.
47. 47)
  - 38. Marinšek, A.: ‘ERA5-Land downloader online repository’, accessed Feb. 2020. https://github.com/AlexanderMarinsek/ERA5-Land-Downloader.
48. 48)
  - 5. Hansen, K., Breyer, C., Lund, H.: ‘Status and perspectives on 100% renewable energy systems’, Energy, 2019, 175, pp. 471–480. Available from: https://linkinghub.elsevier.com/retrieve/pii/S0360544219304967.
49. 49)
  - 14. Du, P.: ‘Ensemble machine learning-based wind forecasting to combine NWP output with data from weather station’, IEEE Trans. Sustain. Energy, 2019, 10, (4), pp. 2133–2141. Available from: https://ieeexplore.ieee.org/document/8531732/.
50. 50)
  - 19. Netsanet, S., Zhang, J., Zheng, D., et al: ‘An aggregative machine learning approach for output power prediction of wind turbines’. 2018 IEEE Texas Power and Energy Conf. (TPEC), College Station, TX, IEEE, 2018, pp. 1–6. Available from: http://ieeexplore.ieee.org/document/8312085/.
51. 51)
  - 50. Jung, P.: ‘System-wide evaluation of inertia support potentials from wind farms’ (Chalmers University of Technology, Department of Energy & Environment, Chalmers University: Gothenburg, Sweden, 2017), pp. 37–56.

Demystifying the use of ERA5-land and machine learning for wind power forecasting

References

Related content