Time series decomposition model for accurate wind speed forecast
 V. Prema^{1}Email author and
 K. Uma Rao^{1}
https://doi.org/10.1186/s4080701500189
© Prema and Rao. 2015
Received: 15 June 2015
Accepted: 23 October 2015
Published: 12 November 2015
Abstract
Climate change can be considered to be the greatest environmental challenge our world is facing today. Along with the need to ensure longterm assurance of energy supply, it imposes an obligation on all of us to consider ways of reducing our carbon footprint and sourcing more of our energy from renewable sources. Wind energy is one such source and forecasting methods for the prediction of wind speed are becoming increasingly significant due to the penetration of wind power as an alternative to conventional energy sources. This paper proposes time series models for shortterm prediction of wind speed. The predictions are done for 1 day ahead using different time series models. For each model, these predicted values are compared with the actual values for the next day. Basic exponential smoothing for different duration of data was tested. A hybrid model with decomposition and exponential smoothing is proposed. A multiplicative decomposition is carried out for the measured data. Separate models were developed for seasonal and trend series and then combined to carry out the forecast. The models were tested for different durations of samples and different weather conditions. It is observed from the results that the prediction with decomposition model for 4 months data gave the least error.
Keywords
Wind speed Forecast Decomposition Time seriesBackground
Intermittency of wind is the biggest challenge in employing wind energy as a reliable autonomous source of electric power. Energy crisis, global warming, depletion of fossil fuels are the major threats looming the world today. Adequate utilization of renewable energy sources such as wind, solar and biomass proves to be the only alternative to overcome these problems. Because of the indeterminate nature and complementary behavior of wind and solar energy, many researchers are focusing their efforts towards hybrid energy systems. A hybrid energy system uses a combination of sources such as wind and solar along with a battery and Diesel Generator set. Optimal allocation of the available resources is one of the challenges faced in the design of hybrid energy systems. For a well planned system, it is essential to have accurate predictive models of the wind and solar sources. Wind energy is directly dependent on the wind speed available at that location and this speed is highly erratic. Hence, a model is needed for accurate prediction of wind speed.
Since the generation of power from wind energy is very erratic due to its heavy dependence on weather, seasonal changes, geographical location, time of the day, direction of wind speed, etc., the forecasting methods may not give uniformly efficient results for all regions. Hence, there is a need to critically examine the seasonality and the nature of the data to determine the models that can be used for prediction of wind speed. There are many methods available in literature for prediction such as time series models, regression models, models based on Artificial Neural Network and Fuzzy logic.
Zhao et al. (2011) and Wang et al. (2011) give thorough review on various methods of wind power forecasting. The authors also propose the development direction of forecast. It is mentioned that combining physical and statistical forecasting models can improve prediction. Erdem et al. (2014), a mixed ARMA model is proposed which incorporates wind direction also with the model. KMean clustering is used to examine the association between wind speed and wind direction. Lv and Yue (2011), the authors propose a forecast model based on wavelet ARIMAGARCH model. The input data are decomposed using wavelets to remove outliers and then modeled with ARIMAGARCH model. Liu et al. (2011), the time series mean and volatility of wind speed is predicted with ARMAGARCH model. Further, the wind power expected output equation is obtained using operational probability. Li et al. (2010) proposes a 2step forecast technique based on Bayesian algorithm and neural network. Results were obtained for 2 different sites and the MAPE is in the range of 14–18 %.
In Wang et al. (2012), a new multivariate Least Square Support Vector Machine (LSSVM) model is proposed. The proposed method is compared with the existing models such as ARIMA and neural network models. SVM is a regression model used to find out the mapping between the predicted values and actual values of wind speed. The data are collected from various wind farms for a duration of 1 year. MAPE is calculated and compared. The lowest MAPE is found to be 10.06 %. Sideratos and Hatziargyriou (2007), George Sideratos et al. combine Artificial Intelligence and fuzzy logic techniques and introduce a new forecasting technique. A preliminary forecast is done using NWP and quality is estimated using fuzzy rules. Three models are developed. The preliminary model predicts wind power for the next hour using neural network whose inputs are wind speed measurements from a wind farm, wind power prediction from NWP and hour of the day for which prediction is made. The maximum error obtained is 40–50 %. This output is fed to the second model which estimates quality of NWP. Wind power from NWP is compared with the theoretical wind power obtained from power curve of wind turbine. This decides the inputs of the fuzzy model. The output of the fuzzy model provides a quality index for the NWP. In the third model, each class of wind speed is forecasted separately. The error ranges between 5 and 14 %. Catalao et al. (2011), a hybrid approach is adopted for wind power prediction combining wavelet, Particle Swam Optimization (PSO) and adaptive Networkbased Fuzzy Inference System (ANFIS). The measured values of wind power are decomposed using wavelet transform. The prediction of this data is done using ANFIS. The performance is improved using PSO technique. It is used to train the parameters of membership function of ANFIS. This is to increase the accuracy of the model. The proposed model is compared with many existing models. The least MAPE obtained is 4.98 %.
In Yan et al. (2013), a new prediction model based on Gaussian Process is proposed. The computational complexity of the standard Gaussian process is reduced and is used to train the system and to predict the wind speed. This model is compared with the standard Gaussian model. It can be seen that the error has reduced tremendously. RMSE for each model is calculated and compared. 15 min ahead to 12 h ahead prediction has been carried out. Ghadi et al. (2012), a new neural network model named ICANN is proposed to predict wind speed. The inputs given are NWP data and data measured through SCADA. Initially, a neural network model is developed with temperature, humidity and wind speed. The weights are adjusted using Imperialist Competitive algorithm. The Mean Square Error is found to be less than 20 %. Wu et al. (2011), the wind power data obtained from a wind farm are preprocessed using Grubb’s test. This is used as input to ANN model. Grubb’s test eliminated the faulty data corresponding to outliers in the wind power or the errors in the measurement. The wind powers which are outside a predefined limit are eliminated. This is normalized and fed to RBF neural network. MAPE obtained is in the range of 7–23 % depending on the out samples of prediction.
In this paper, a novel decomposition model is proposed to separately predict seasonal and trend components of the wind speed so as to improve the forecast as compared to the existing time series models such as ARIMA, persistence, BPNN (Back Propagation Neural Network) and TES (Triple Exponential Smoothing). The paper is organized as follows. Section "Data used" explains the data used for the proposed work. Section "Time series models for prediction" gives a detailed explanation of the various time series models. Section "Error measures" gives the basic definitions of performance parameters which are used to validate the models used in this paper. Section "Model development" gives the insight of the models developed. In section "Results and discussions", the results of the developed models are shown. The predicted wind speed is compared with the actual data and the errors are calculated for the developed models.
Data used
 1.
1 Month data for the month of May was used to predict the wind speed for the first day of June.
 2.
2 Months data for the months of April and May was used to predict the wind speed for the first day of June.
 3.
4 Months data for the months of February through May was used to predict the wind speed for the first day of June.
Time series models for prediction
Time series analysis comprises of methods for analyzing time series data to extract meaningful statistics and other characteristics of the data.Sobu and Wu (2012), Kang et al. (2011), Mori and Takahashi (2012). The main types of time series models include—parametric and nonparametric time series models. The parametric approaches assume that the underlying stationary stochastic process has a certain structure which can be described using a small number of parameters Huang and Lu (2010). All the time series models used in this paper are parametric models, described as below Douglas and Kulahci (2008).
Single, double, centered and weighted moving average models were tested for the available data with different orders and intervals. It was observed from the analysis that the value of interval, when chosen to be small (that is, less than 11), the predicted values and the actual values in the test data were closely similar. Though the predicted values are good for higher values of wind speed, when predicting lower values, the moving average model of very small interval tends to saturate towards a constant value. Hence, exponential smoothing methods were developed. The models are developed using Rsoftware and Microsoft Excel Zhao (2012).
Single exponential smoothing (SES)
Exponential Smoothing is a class of methods that imply exponentially decreasing weights as the observations get older. They have a common property that recent values are given relatively more weight in forecasting than the older observations. The model assumes that the data fluctuate Lim (2011) around a reasonably smean (no trend or consistent pattern of growth).
Double exponential smoothening (DES)
Triple exponential smoothening (TES)

\(\alpha\) is the level smoothing constant (lies between 0 and 1).

\(\beta\) is the trend smoothing constant (lies between 0 and 1).

\(\gamma\) is the seasonal smoothing constant (lies between 0 and 1).

\(L_{t}\) is the estimate of the level of the series at time t.

\(Y_{t}\) is the actual value of the series at time t.

\(b_{t}\) is the estimate of the slope of the series at time t.

\(S_{t}\) is the seasonal component.

s is the length of seasonality.

m is the number of periods ahead to be forecast.

\(F_{t+m}\) is the forecast for m periods ahead.
Decomposition model
 1.
Additive Decomposition: Here, the total data are taken as the sum of the decomposed patterns
Xt = seasonal (St) + trend (Tt) + random.
 2.
Multiplicative Decomposition: Here, the given time series data are treated as the product of the decomposed patterns
Xt = seasonal (St) \(\times\) trend (Tt) \(\times\) random.
 1.
Obtain the trend pattern by calculating the centered moving average for the entire data.
 2.
Find out the detrended pattern by dividing the total data by the trend series.
 3.
Seasonal component is calculated by averaging the detrended values for that particular time of all the days.
 4.
Calculate the deseasonalised data by dividing the seasonal data from the actual data.
 5.
Bring out a single exponential model for the deseasonalised data.
 6.
Forecast seasonal data by extending the data for the next day.
 7.
Forecast deseasonalised data by forecasting the exponential smoothing model.
 8.
Multiply both the forecasted data to get the forecast for the actual data.
Error measures
When there are more than one model developed, a comparative analysis can be made by calculating the accuracy of each model and comparing them. The accuracy of any predictive model can be determined only by choosing appropriate error measures. In this paper, different models are compared using two error measuring parameters, Mean Absolute Percentage Error (MAPE) and Symmetric Mean Absolute Percentage Error (SMAPE) which can be defined as shown below. MAPE is a relative measure which reflects error as the percentage of actual data. Hence, the accuracy of the model can be easily judged.
Mean absolute percentage error (MAPE)
Symmetric mean average percentage error (SMAPE)
Model development
Decomposition model and TES models were developed. The predicted values of wind speed obtained for the first day of June were compared with the actual values of wind speed and errors were calculated for each model. Amongst the developed models, decomposition model is found superior and further analysis was carried out with decomposition model. The model was tested on different durations of past data for a period of 1 year. The prediction was done for different climatic conditions such as monsoon, spring and winter.
Smoothing parameters of the TES models
Sl no  Model  \(\alpha\)  \(\beta\)  \(\gamma\) 

1  TES 1 month  0.59  0.09  0.17 
2  TES 2 months  0.71  0.11  0.21 
3  TES 4 months  0.68  0.099  0.2 
Comparison of errors
Data duration  Model  MAPE (%)  RMSE (m/s) 

1 Month  Persistence  31.63  1.43 
ARIMA  25.21  1.07  
BPNN  37.6  1.98  
TES  23.94  1.47  
Decomposition  20.15  0.965  
2 Months  Persistence  31.63  1.43 
ARIMA  22.15  0.979  
BPNN  40.94  1.89  
TES  26.03  1.772  
Decomposition  22.03  1.105  
4 Months  Persistence  31.63  1.43 
ARIMA  23.26  1.022  
BPNN  44.37  1.91  
TES  28.63  1.35  
Decomposition  18.24  1.05 
Results and discussions
Table 2 shows the comparison of the errors calculated for the prediction. As per Government of India, a deviation of 30percent in the forecast is acceptable CERC (2012).
It can be observed from Table 2 that the proposed decomposition models outperform all other benchmark models such as Persistence, TES, ARIMA and BPNN. The benchmark models have a MAPE in the range of 40–23 % and RMSE of around 1 m/s. But decomposition models give an error as less as 18 %. Thus, decomposition models are considered for further analysis. The decomposition model proposed above is tested with various time durations of data and wind speed is predicted for different climatic conditions. For these studies, a data set of wind speed for duration of 1 year from January 2013 to December 2013 is considered. The results are presented as various case studies explained below.
Case study 1: to determine ideal time period for model building
Forecast of 31 Dec 2013 using different time periods for model building
Sl no  Time period  MAPE  SMAPE  Mean MAPE  RMSE 

1  1 year  34.89  14.61  26.84  0.90 
2  6 months  28.30  26.21  24.53  0.96 
3  4 months  22.55  21.49  18.72  0.68 
4  2 months  25.89  26.02  23.64  0.87 
5  1 month  31.12  26.09  25.63  0.97 
Case study 2: prediction during different climatic conditions
To understand the performance of model, it is tested for different climatic conditions. Wind speeds for 5 days each in monsoon, spring and winter seasons are predicted.
Monsoon
Prediction of wind speed during monsoon
Sl no  Time period  MAPE  SMAPE  Mean MAPE  RMSE 

1  01 June 2013  21.16  20.22  19.29  1.05 
2  31 May 2013  26.92  16.10  14.05  0.92 
3  30 May 2013  16.82  15.81  15.23  1.195 
4  29 May 2013  19.13  19.37  16.36  0.96 
5  28 May 2013  20.19  18.35  16.53  0.98 
Spring
Prediction of wind speed during spring
Sl no  Time period  MAPE  SMAPE  Mean MAPE  RMSE 

1  5 Sept 2013  8.3  8.26  8.14  0.66 
2  4 Sept 2013  6.72  6.67  6.92  0.66 
3  3 Sept 2013  8.14  8.16  8.51  0.79 
4  2 Sept 2013  9.2  9.04  9.49  0.81 
5  1 Sept 2013  7.44  7.41  7.31  0.69 
Winter
Prediction of wind speed during winter
Sl no  Time period  MAPE  SMAPE  Mean MAPE  RMSE 

1  31 Dec 2013  22.54  21.46  18.70  0.68 
2  30 Dec 2013  11.64  11.49  10.63  0.68 
3  29 Dec 2013  9.50  9.31  8.68  0.51 
4  28 Dec 2013  7.83  7.74  7.16  0.52 
5  27 Dec 2013  10.85  10.77  9.48  0.52 
Case study 3: extension of models to predict out sample
Comparison of errors for different out samples of prediction
Sl no  Forecast horizon  MAPE  SMAPE  Mean MAPE  RMSE 

1  1 day (Dec 27)  10.85  10.77  9.48  0.52 
2  2 days (Dec 27, 28)  15.42  16.78  14.36  0.88 
3  3 days (Dec 27–29)  16.02  16.84  15.39  0.92 
4  4 days (Dec 27–30)  20.51  21.87  19.63  1.18 
5  5 days (Dec 27–31)  16.40  17.49  15.70  1.05 
Comparison with existing models
The classic models for prediction such as persistence, BPNN, ARIMA and TES are developed with the same set of data. MAPE and RMSE of these models are compared with the proposed model in Table 2. MAPE is above 30 % for persistence and BPNN and above 20 % for ARIMA and TES. RMSE is also on the higher side. This proves that these models cannot predict erratic data like wind speed efficiently. The lowest MAPE obtained for the proposed model is 6.72 %, which is very less compared to the classic models.
The total run time of the simulations is also a matter of concern in prediction. As model building is done offline, the time taken for model building does not significantly affect the system performance. Once the model is built, running the model to gather a dayahead prediction takes only less than 2 s in the proposed model, whereas BPNN model took around 11 s to get the predicted wind speed.
A comparison of the proposed model with the models available in the literature becomes very difficult as the performance of a model is heavily dependent on the data and it is influenced by various parameters such as geographical locations and forecast out samples. The error measures considered in various models are also different. Still an effort is done to compare the proposed model with some of the existing models which use time series predictive models. Li et al. (2010), a 2step forecasting technique based on Bayesian algorithm and neural network is developed. The results were obtained for two different sites and the MAPE is in the range of 14–18 %. Lv and Yue (2011)propose a forecast model based on wavelet, ARIMA and ARCH. The input is wavelet decomposed to remove outliers and the MAPE obtained is in the range of 17.85–8.72 %. Wen et al. (2012), Support Vector Machine (SVM) model and Lifting Wavelet Transform SVM (LWTSVM) are compared and least MAPE obtained is 14.96 %. The decomposition model proposed in this paper gives a minimum MAPE of 6.7 %, which is less than the models discussed above. Johnson et al. (2007), wind forecast model is developed using adaptive neurofuzzy inference systems. The proposed model is compared with persistence model and percentage improvement obtained is found to be 8 %. In this paper, the percentage improvement of the proposed model compared to persistence model is 23 %.
Conclusion
In this paper, a new method for forecast of wind speed has been proposed using decomposition of raw time series data. The forecast result has been compared with classical methods such as Persistence, ARIMA, BPNN and TES models. It is observed from the results and calculated errors that decomposition model gives better results compared to conventional forecasting methods. Models were tested with different durations of historical data and it was found that decomposition models worked well with data duration of 4 months. The model was tested for different weather conditions throughout a year. The prediction error was highest during onset of monsoon when wind speed is erratic and as less as 6.7 % during spring when wind speed is reasonably consistent. The models developed have better applications at State Load Regional Dispatch Center (SLRDC) for scheduling generation a day ahead thereby increasing penetration of wind power in the grid. If the data are viewed as a signal, the sudden variations can be treated as highfrequency components. The performance of the model can be further improved if these high frequency components are captured. Work is being carried out using wavelets to capture the highfrequency components, which can be incorporated in the decomposition model to improve the prediction.
Declarations
Authors’ contributions
Both the authors have equal contribution on the entire work done for this paper. Both authors read and approved the final manuscript.
Competing interests
The authors declare that there are no financial or nonfinancial competing interests with any other person or organization.
Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
Authors’ Affiliations
References
 Catalao, J. P. S., Pousinho, H. M. I., & Mendes, V. M. F. (2011). Hybrid waveletpsoanfis approach for shortterm wind power forecasting in portugal. IEEE Transactions on Sustainable Energy, 2 Google Scholar
 Central Electricity Regulatory Commission (CERC). (2012). New Delhi, Statement of Objects and Reasons(Terms and Conditions for Tariff Determination from Renewable Energy Sources). URL:http://www.cercind.gov.in/2012/regulation/RETariffRegulations2012SOR%20622012.pdfGoogle Scholar
 Erdem, E., Peng, Y., & Shi, J. (2014). Shortterm forecasting of wind speed and power—a clustering approach. In Proceedings of the 2014 Industrial and Systems Engineering Research Conference Google Scholar
 Ghadi, M. J., Sharifiyan, A., Gilani, S. H., & Afrakhteh, H. (2012). A new method for shortterm wind power forecasting. International Journal of Electrical Power and Energy Systems, 34, 1–176Google Scholar
 Holland, R. E. W. P. W. (1977). Communications in statistics: theory and methods, 6th edn. New York: Wiley Student EditionGoogle Scholar
 Huang, Y., & Lu, J. (2010). Comparative study of power forecasting methods for pv stations. In International Conference on Power System Technology (POWERCON) (pp. 1–6)Google Scholar
 Johnson, P., Muttaqi, K. M., & Negnevitsky, M. (2007). Short term wind power forecasting using adaptive neurofuzzy inference systems. In Power Engineering Conference (AUPEC) (pp. 1–6)Google Scholar
 Kang, M. C., Sohn, J. M., Park, J. Y., Lee, S. K., & Yoon, Y. T. (2011). Development of algorithm for day ahead pv generation forecasting using data mining method. In IEEE 54th International Midwest Symposium on Circuits and Systems (MWSCAS) (pp. 1–4)Google Scholar
 Li, G., Zhou, J., & Shi, J. (2010). Bayesian adaptive combination of shortterm wind speed forecasts from neural network models, 36th edn. Renewable Energy ElsevierGoogle Scholar
 Lim, Y. P. (2011). Power management strategies for offgrid hybrid power systems. PhD thesis, Curtin University, School of Electrical and Computer EngineeringGoogle Scholar
 Liu, H., Erdem, E., & Shi, J. (2011). An integrated wind power forecasting methodology: interval estimation of wind speed, operation probability of wind turbine, and conditional expected wind power output of a wind farm, 12th edn. ElsevierGoogle Scholar
 Lv, P., & Yue, L. (2011). Shortterm wind speed forecasting based on nonstationary time series analysis and arch model, 12th edn. IEEEGoogle Scholar
 Montgomery, D. C., Jennings, C. L., & Kulahci, M. (2008). Introduction to time series analysis and forecasting. New York: Wiley publicationsGoogle Scholar
 Mori, H., & Takahashi, A. (2012). A data mining method for selecting input variables for forecasting model of global solar radiation. In IEEE PES Transmission and Distribution Conference and Exposition Google Scholar
 Sideratos, G., & Hatziargyriou, N. D. (2007). An advanced statistical method for wind power forecasting. IEEE Transactions On Power Systems, 22, 258–265.View ArticleGoogle Scholar
 Sobu, A., & Wu, G. (2012). Dynamic optimal schedule management method for microgrid system considering forecast errors of renewable power generations. In IEEE International Conference on Power System Technology (POWERCON) (pp. 1–6)Google Scholar
 Wang, X., Huang, X., & Guo, P. (2011). A review of wind power forecasting models, 12th edn. ElsevierGoogle Scholar
 Wang, Q., Lai, K. K., Niu, D., & Zhang, Q. (2012). A multivariate wind power forecasting model based on lssvm. In: Fifth International Joint Conference on Computational Sciences and Optimization Google Scholar
 Wen, J., Wang, X., Zheng, Y., Li, L., Zhou, L., Yao, G., & Chen, H. (2012). Shortterm wind power forecasting based on lifting wavelet transform and svm. In IEEE Power Engineering and Automation Conference (PEAM) (pp. 1–4)Google Scholar
 Wu, X., Wen, F., Hong, B., Peng, X., & Huang, J. (2011). Radial basis function neural network based shortterm wind power forecasting with grubbs test. In 4th International Conference on Electric Utility Deregulation and Restructuring and Power Technologies (DRPT) Google Scholar
 Yan, J., Li, K., & Bai, E. W. (2013). Prediction error adjusted gaussian process for shortterm wind power forecasting. In IEEE International Workshop on Intelligent Energy Systems (IWIES) (pp. 173–178)Google Scholar
 Zhao, X., Li, T., & Wang, S. (2011). Review of evaluation criteria and main methods of wind power forecasting, 12th edn. ElsevierGoogle Scholar
 Zhao, Y. (2012). R and Data Mining: Examples and Case Studies. New York: ElsevierGoogle Scholar