Abstract
Wind power unlike power generated from conventional sources is not constant. There are many factors that influence the power generated from wind energy, like wind speed, location, climate change etc. Owing to this, there is always uncertainty in wind power output. Thus, for proper load scheduling and better integration of wind power with the grid, it becomes essential to develop a robust wind power forecasting system. For developing a reliable forecasting system, it is essential to factor in all the possible factors that affect the wind power output and analyze a huge amount of data set for a higher accuracy rate. This paper proposes the use of two machine learning techniques, namely LASSO and XGBoost classifier, and a comparison is made between the two to find which technique is better for our task. For training and validation of this model, wind power data of the Kolkata region is taken. The result shows that XGBoost is better than LASSO for forecasting wind power accurately with a MAPE value of 1.121 for XGBoost and 62.1476 for LASSO.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bhaskar M, Jain A, Venkata Srinath N (2010) Wind speed forecasting: present status. Power system technology (POWERCON), 2010 international conference, pp 1–6, 24–28 October 2010
Sharp J, Hodge B, Florita A, Margulis M, Mcreavy D (2010) The value of improved short-term wind power forecasting. In: 9th International proceedings on proceedings, pp 1–2. http://www.nrel.gov/publications.
Orwig K, Ahlstrom M, Banunarayanan V, Sharp J, Wilczak J, Freedman J, Haupt S, Cline J, Bartholomy O, Hamann H, Hodge B-M, Finley C, Nakafuji D, Peterson J, Maggio D, Marquis M (2015) Recent trends in variable generation forecasting and its value to the power system. IEEE Trans Sustain Energy 6:924–933
Manwell JF, McGowan JG, Rogers AL (2010) wind energy explained: theory, design and application . John Wiley & Sons, Hoboken, NJ, USA
Gasch R, Twele J (2011) Wind power plants: fundamentals, design, construction and operation. Springer, Berlin, Germany
Foley AM, Leahy PG, Marvuglia A, McKeogh SJ (2012) Current methods and advances in forecasting of wind power generation. Renew Energy 37:1–8
Wang X, Guo P, Huang X (2011) A review of wind power forecasting models. Energy Proc 12:770–778
Zhao X, Wang S, Li T (2011) Review of evaluation criteria and main methods of wind power forecasting. Energy Proc 12:761–769
Dongmei Z, Yuchen Z, Xu Z (2011) Research on wind power forecasting in wind farms. In: Proceedings of the 2011 IEEE power engineering and automation conference (PEAM), Wuhan, China, 8–9 September 2011
Buhan S, Cadirci I (2015) Multistage wind-electric power forecast by using a combination of advanced statistical methods. IEEE Trans Ind Inf 11(5):1231–1242
Lu HJ, Chang GW (2018) Wind power forecast by using improved radial basis function neural network. In: 2018 IEEE power & energy society general meeting (PESGM), Portland, OR pp 1–5
Palomares-Salas JE, de I a Rosa JJG, Ramiro JG, Melgar J et al (2009) ARlMA vs. neural networks for wind speed forecasting. In: Proceedings of IEEE international conference on computational intelligence for measurement systems and applications, pp 129–133
Tesfaye A, Zhang JH, Zheng DH, Shiferaw D (2016) Short-term wind power forecasting using artificial neural networks for resource scheduling in microgrids. Int J Sci Eng Appl (iJSEA) 5(3)
Song YY, Lu Y (2015) Decision tree methods: applications for classification and prediction. Shanghai Arch Psychiatry 27(2):130–135. https://doi.org/10.11919/j.issn.1002-0829.215044
Sammut C, Webb GI (eds) (2011) Random forests. In: Encyclopedia of machine learning. Springer, Boston, MA
Friedman JH. IMS 1999 greedy function approximation: a gradient boosting machine Reitz lecture
Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. arXiv:1603.02754
Gauraha N (2018) Introduction to the LASSO. Reson 23:439–464. https://doi.org/10.1007/s12045-018-0635-x
Foley AM, Leahy PG, Marvuglia A, McKeogh EJ (2012) Current methods and advances in forecasting of wind power generation. Renew Energy 37(1):1–8
Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. In: Proceedings of the ACM SIGKDD international conference on knowledge discovery & data mining, San Francisco, CA, USA, 13–17 August 2016
Martinez-De-Pison FJ, Fraile-Garcia E, Ferreiro-Cabello J, Gonzalez R, Pernia A (2016) Searching parsimonious solutions with GA-PARSIMONY and XGBoost in high-dimensional databases. In: Grana M, LopezGuede JM, Etxaniz O, Herrero A, Quintian H, Corchado E (eds) International joint conference Soco’16-CISIS’16-ICEUTE’16, San Sebastián, Spain, 19–21 October 2016, vol 527, pp 201–210. Springer, Cham, Switzerland
Song RW, Chen SD, Deng BL, Li L (2016) XGBoost boosting for identifying individual users across different digital devices. In: Cui B, Zhang N, Xu J, Lian X, Liu D (eds) Proceedings of the web-age information management: 17th International conference, WAIM 2016, Nanchang, China, 3–5 June 2016, vol 9658, pp 43–54. Springer, Cham, Switzerland
Sheridan RP, Wang WM, Liaw A, Ma JS, Gifford EM (2016) XGBoost boosting as a method for quantitative structure-activity relationships. J Chem Inf Model 56:2353–2360
Ye J, Chow J-H, Chen J, Zheng Z. Stochastic gradient boosted distributed decision trees. In: Proceedings of the 18th ACM conference on information and knowledge management, CIKM ’09
Rodríguez O (2013) A generalization of ridge, lasso and elastic net regression to interval data. https://doi.org/10.13140/2.1.3753.0883
Arribas-Gil A, Bertin K, Meza C, Rivoirard V. Lasso-type estimators for semiparametric nonlinear mixed-effects models estimation. Stat Comput 24(3):443–460
Zou H, Hastie T (2005) Regularization and variable selection via the elastic net. Stanford University, USA
Boulesteix A-L, De Bin R, Jiang X, Fuchs M (2017) IPF-LASSO: integrative-penalized regression with penalty factors for prediction based on multi-omics data, vol 2017, Computational and mathematical methods in medicine, Hindawi, pp 1748–670X. https://doi.org/10.1155/2017/7691937
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kumar, A., Kumar, N., Singh, B., Chaudhary, A., Dikshit, K., Sharma, A. (2021). Comparative Investigation of Machine Learning Algorithms for Wind Power Forecasting. In: Singh, J., Kumar, S., Choudhury, U. (eds) Innovations in Cyber Physical Systems. Lecture Notes in Electrical Engineering, vol 788. Springer, Singapore. https://doi.org/10.1007/978-981-16-4149-7_46
Download citation
DOI: https://doi.org/10.1007/978-981-16-4149-7_46
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-4148-0
Online ISBN: 978-981-16-4149-7
eBook Packages: Computer ScienceComputer Science (R0)