Innovative hybrid models for forecasting time series applied in wind generation based on the combination of time series models with artificial neural networks

Abstract This work shows two innovative hybrid methodologies capable of performing short and long term wind speed predictions from the mathematical junction of two classical time series models the Autoregressive Integrated Moving Average with Explanatory Variable (ARIMAX) and the Holt-Winters (HW), both combined with Artificial Neural Networks (ANN). The first hybrid model (ARIMAX and ANN) is made from the physical relations between pressure, temperature and precipitation with the wind speed, that is, this model is considered as multivariate. The second hybrid model (HW and ANN) is considered as univariate, i.e. allowing only wind speed inputs. By means of statistical analysis of error it is verified that the proposed hybrid models offer perfect adjustments to the observed data at the regions of study, and thus, better comparisons with traditional ones from the literature. It is possible to find in this analysis percentage error of 5.0% and efficiency coefficient (Nash-Sutcliffe) of approximately 0.96. The confirmation of accuracy by the hybrid models reveals that they provide time series that are able to follow the observed time series profiles with similarities of maximum and minimum values between both series. Therefore, it became an important indicative in the representation of characteristics of seasonality by the models.

[1]  W. Rivera,et al.  Wind speed forecasting in the South Coast of Oaxaca, México , 2007 .

[2]  Jing Shi,et al.  On comparing three artificial neural networks for wind speed forecasting , 2010 .

[3]  I. F. Cavalcanti,et al.  Atmospheric centres of action associated with the Atlantic ITCZ position , 2009 .

[4]  S. Jain,et al.  Fitting of Hydrologic Models: A Close Look at the Nash–Sutcliffe Index , 2008 .

[5]  R. Kavasseri,et al.  Day-ahead wind speed forecasting using f-ARIMA models , 2009 .

[6]  D. Fadare.  The application of artificial neural networks to mapping of wind speed profile for energy application in Nigeria , 2010 .

[7]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1971 .

[8]  Renjin Sun,et al.  Do natural gas and renewable energy consumption lead to less CO2 emission? Empirical evidence from a panel of BRICS countries , 2017 .

[9]  Richard A. Davis,et al.  Introduction to time series and forecasting , 1998 .

[10]  V. Misra.  A sensitivity study of the coupled simulation of the Northeast Brazil rainfall variability , 2007 .

[11]  Yan Su,et al.  An ARMAX model for forecasting the power output of a grid connected photovoltaic system , 2014 .

[12]  Jay Squalli,et al.  Renewable energy, coal as a baseload power source, and greenhouse gas emissions: Evidence from U.S. state-level data , 2017 .

[13]  Hui Liu,et al.  Comparison of two new ARIMA-ANN and ARIMA-Kalman hybrid methods for wind speed prediction , 2012 .

[14]  Paulo Alexandre Costa Rocha,et al.  An efficiency comparison of numerical methods for determining Weibull parameters for wind energy applications: A new approach applied to the northeast region of Brazil , 2014 .

[15]  Jianzhou Wang,et al.  A hybrid forecasting approach applied to wind speed time series , 2013 .

[16]  Çagdas Hakan Aladag,et al.  Forecasting nonlinear time series with a hybrid methodology , 2009, Appl. Math. Lett..

[17]  Boqiang Lin,et al.  Brazilian energy efficiency and energy substitution: A road to cleaner national energy system , 2017 .

[18]  J. Servain,et al.  Tropical Atlantic Contributions to Strong Rainfall Variability Along the Northeast Brazilian Coast , 2015 .

[19]  J.C. Palomares-Salas,et al.  ARIMA vs. Neural networks for wind speed forecasting , 2009, 2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications.

[20]  L. E. Brandão,et al.  Elephant grass biorefineries: towards a cleaner Brazilian energy matrix? , 2015 .

[21]  C. Ahrens,et al.  Meteorology Today: An Introduction to Weather, Climate, and the Environment , 1982 .

[22]  Carla Freitas de Andrade,et al.  Comparison of seven numerical methods for determining Weibull parameters for wind energy generation in the northeast region of Brazil , 2012 .

[23]  J. Minx,et al.  Climate Change 2014 : Synthesis Report , 2014 .

[24]  R. Wilcox.  Fundamentals of Modern Statistical Methods: Substantially Improving Power and Accuracy , 2001 .

[25]  Lars Dannecker.  Energy Time Series Forecasting - Efficient and Accurate Forecasting of Evolving Time Series from the Energy Domain , 2015 .

[26]  Fernando Ramos Martins,et al.  Enhancing information for solar and wind energy technology deployment in Brazil , 2011 .

[27]  Raúl Rojas,et al.  Neural Networks - A Systematic Introduction , 1996 .

[28]  Erasmo Cadenas,et al.  Wind speed forecasting in three different regions of Mexico, using a hybrid ARIMA–ANN model , 2010 .

[29]  Mario Orestes Aguirre González,et al.  Sustainable development: Case study in the implementation of renewable energy in Brazil , 2017 .

[30]  Rob J Hyndman,et al.  Automatic Time Series Forecasting: The forecast Package for R , 2008 .

[31]  Steven C. Wheelwright,et al.  Forecasting methods and applications. , 1979 .

[32]  Mehdi Khashei,et al.  An artificial neural network (p, d, q) model for timeseries forecasting , 2010, Expert Syst. Appl..

[33]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.