INFLUENCE OF THE CLIMATIC PHENOMENA OF EL NIÑO AND LA NIÑA ON THE FORECAST OF THE DAILY AVERAGE OF GLOBAL IRRADIATION IN THE CITY OF FORTALEZA
DOI:
https://doi.org/10.47820/acertte.v2i2.53Keywords:
work, predictions of the daily average of globalAbstract
In this work, predictions of the daily average of global solar irradiation were obtained by applying machine learning algorithms in two sets of data formed by exogenous variables (insolation, air temperature, precipitation, etc.), endogenous variables (temporal series of the daily average of global solar irradiation) and temporal variables (year, month and day of measurement). The difference between the data sets is related to the fact that in one considers the intensities of the climate phenomena of El Niño and La Niña as predictors for the learning models used, while in the other one one does not consider oneself. Thus, it was possible to evaluate whether the addition of the predictor related to El Niño/La Niña contributes to a better accuracy of prediction by the applied models: Minimal Learning Machine, Vector Support Regression, Random Forests, Closer K-Neighbors and a regression tree with the use of Bootstrap. The error metrics Absolute Mean Error, Mean Bias Error, Middle Quadratic Error Root, Relative Mean Quadratic Error Root, and Prediction Ability were used to analyze the performance of the algorithms. The arithmetic mean of the Root of the Mean Quadratic Error and the Predictability for the case in which El Niño/La Niña was considered as atibutos were 40.78 W/m² and 7.87% , respectively. For the case where these predictors are not considered, the values obtained were 40.86 W/m² and 7.69%. Indicating that the use of these predictors increases the accuracy of predicting the algorithms in question.
Downloads
References
NOTTON, Gilles et al. Intermittent and stochastic character of renewable energy sources: Consequences, cost of intermittence and benefit of forecasting. Renewable and Sustainable Energy Reviews, v. 87, p. 96-105, 2018. DOI: https://doi.org/10.1016/j.rser.2018.02.007
QING, Xiangyun; NIU, Yugang. Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM. Energy, v. 148, p. 461-468, 2018. DOI: https://doi.org/10.1016/j.energy.2018.01.177
MEJIA, John F.; GIORDANO, Marco; WILCOX, Eric. Conditional summertime day-ahead solar irradiance forecast. Solar Energy, v. 163, p. 610-622, 2018. DOI: https://doi.org/10.1016/j.solener.2018.01.094
NONNENMACHER, Lukas; KAUR, Amanpreet; COIMBRA, Carlos FM. Day-ahead resource forecasting for concentrated solar power integration. Renewable energy, v. 86, p. 866-876, 2016. DOI: https://doi.org/10.1016/j.renene.2015.08.068
TRAPERO, Juan R.; KOURENTZES, Nikolaos; MARTIN, Alberto. Short-term solar irradiation forecasting based on dynamic harmonic regression. Energy, v. 84, p. 289-295, 2015. DOI: https://doi.org/10.1016/j.energy.2015.02.100
DONG, Zibo et al. Short-term solar irradiance forecasting using exponential smoothing state space model. Energy, v. 55, p. 1104-1113, 2013. DOI: https://doi.org/10.1016/j.energy.2013.04.027
PEDRO, Hugo TC; COIMBRA, Carlos FM. Nearest-neighbor methodology for prediction of intra-hour global horizontal and direct normal irradiances. Renewable energy, v. 80, p. 770-782, 2015. DOI: https://doi.org/10.1016/j.renene.2015.02.061
PEDRO, Hugo TC et al. Assessment of machine learning techniques for deterministic and probabilistic intra-hour solar forecasts. Renewable Energy, v. 123, p. 191-203, 2018. DOI: https://doi.org/10.1016/j.renene.2018.02.006
PAWAR, Prathamesh et al. Detecting clear sky images. Solar Energy, v. 183, p. 50-56, 2019. DOI: https://doi.org/10.1016/j.solener.2019.02.069
KOO, Choongwan et al. A novel estimation approach for the solar radiation potential with its complex spatial pattern via machine-learning techniques. Renewable Energy, v. 133, p. 575-592, 2019. DOI: https://doi.org/10.1016/j.renene.2018.10.066
YAGLI, Gokhan Mert; YANG, Dazhi; SRINIVASAN, Dipti. Automatic hourly solar forecasting using machine learning models. Renewable and Sustainable Energy Reviews, v. 105, p. 487-498, 2019. DOI: https://doi.org/10.1016/j.rser.2019.02.006
BENALI, L. et al. Solar radiation forecasting using artificial neural network and random forest methods: Application to normal beam, horizontal diffuse and global components. Renewable energy, v. 132, p. 871-884, 2019. DOI: https://doi.org/10.1016/j.renene.2018.08.044
DE SOUZA JÚNIOR, Amauri Holanda et al. Minimal learning machine: a novel supervised distance-based approach for regression and classification. Neurocomputing, v. 164, p. 34-44, 2015. DOI: https://doi.org/10.1016/j.neucom.2014.11.073
CARRASCO, Miguel; LÓPEZ, Julio; MALDONADO, Sebastián. Epsilon-nonparallel support vector regression. Applied Intelligence, p. 1-14.
DRUCKER, Harris et al. Support vector regression machines. In: Advances in neural information processing systems. 1997. p. 155-161.
SHARMA, Navin et al. Predicting solar generation from weather forecasts using machine learning. In: 2011 IEEE international conference on smart grid communications (SmartGridComm). IEEE, 2011. p. 528-533. DOI: https://doi.org/10.1109/SmartGridComm.2011.6102379
WALCH, Alina et al. Spatio-temporal modelling and uncertainty estimation of hourly global solar irradiance using Extreme Learning Machines. Energy Procedia, v. 158, p. 6378-6383, 2019. DOI: https://doi.org/10.1016/j.egypro.2019.01.219
<http://enos.cptec.inpe.br/>. Acesso em 17. jun. 2019.
<https://www.noaa.gov/>. Acesso em 17. jun. 2019.
MOHAMMADI, Kasra; GOUDARZI, Navid. Study of inter-correlations of solar radiation, wind speed and precipitation under the influence of El Niño Southern Oscillation (ENSO) in California. Renewable energy, v. 120, p. 190-200, 2018. DOI: https://doi.org/10.1016/j.renene.2017.12.069
LI, Mao-Fen et al. General models for estimating daily global solar radiation for different solar radiation zones in mainland China. Energy conversion and management, v. 70, p. 139-148, 2013. DOI: https://doi.org/10.1016/j.enconman.2013.03.004
JAMES, Gareth et al. An introduction to statistical learning. New York: springer, 2013. DOI: https://doi.org/10.1007/978-1-4614-7138-7
HYNDMAN, Rob J.; ATHANASOPOULOS, George. Forecasting: principles and practice. OTexts, 2018.
MEHROTRA, Sanjay. On the implementation of a primal-dual interior point method. SIAM Journal on optimization, v. 2, n. 4, p. 575-601, 1992. DOI: https://doi.org/10.1137/0802028
KUHN, Max; JOHNSON, Kjell. Applied predictive modeling. New York: Springer, 2013. DOI: https://doi.org/10.1007/978-1-4614-6849-3
BEN-ISRAEL, Adi; GREVILLE, Thomas NE. Generalized inverses: theory and applications. Springer Science & Business Media, 2003.
PENROSE, Roger. A generalized inverse for matrices. In: Mathematical proceedings of the Cambridge philosophical society. Cambridge University Press, 1955. p. 406-413. DOI: https://doi.org/10.1017/S0305004100030401
NIEWIADOMSKA-SZYNKIEWICZ, Ewa; MARKS, Michał. Optimization schemes for wireless sensor network localization. International Journal of Applied Mathematics and Computer Science, v. 19, n. 2, p. 291-302, 2009. DOI: https://doi.org/10.2478/v10006-009-0025-3
MARQUARDT, Donald W. An algorithm for least-squares estimation of nonlinear parameters. Journal of the society for Industrial and Applied Mathematics, v. 11, n. 2, p. 431-441, 1963. DOI: https://doi.org/10.1137/0111030
MORÉ, Jorge J. The Levenberg-Marquardt algorithm: implementation and theory. In: Numerical analysis. Springer, Berlin, Heidelberg, 1978. p. 105-116. DOI: https://doi.org/10.1007/BFb0067700
BELLMAN, Robert. Curse of dimensionality. Adaptive control processes: a guided tour. Princeton, NJ, 1961. DOI: https://doi.org/10.1515/9781400874668
WOLD, Svante; ESBENSEN, Kim; GELADI, Paul. Principal component analysis. Chemometrics and intelligent laboratory systems, v. 2, n. 1-3, p. 37-52, 1987. DOI: https://doi.org/10.1016/0169-7439(87)80084-9
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2022 ACERTTE SCIENTIFIC JOURNAL
This work is licensed under a Creative Commons Attribution 4.0 International License.
Os direitos autorais dos artigos/resenhas/TCCs publicados pertecem à revista ACERTTE, e seguem o padrão Creative Commons (CC BY 4.0), permitindo a cópia ou reprodução, desde que cite a fonte e respeite os direitos dos autores e contenham menção aos mesmos nos créditos. Toda e qualquer obra publicada na revista, seu conteúdo é de responsabilidade dos autores, cabendo a ACERTTE apenas ser o veículo de divulgação, seguindo os padrões nacionais e internacionais de publicação.
