A Novel Method for Forecasting Surface Wind Speed using Wind-direction based on Hierarchical Markov Model

Document Type : Original Article


Department of Electrical Engineering, Shahid Beheshti University, Tehran, Iran


This article presents a new method for detecting heterogeneities in wind data set to predict wind speed based on the well-known Hidden Markov Model (HMM). In the proposed method, the HMM categorizes the wind time series into some groups in which each group represents a wind regime. Each regime uses an internal first-order Markov Chain (MC) for forecasting, and the combination of all regimes outputs generates the final wind speed forecast. The model proposed in this study is called “Hierarchical Markov Model ”. The first layer detects and separates wind regimes as heterogenic groups of wind data by the use of wind direction data, based on  HMM, and the second layer forecasts the wind speed using MC. The proposed model is implemented and tested using real data. Its effectiveness in terms of temporal stationary index is compared with that of a first-order MC-based method. The results showed that more than 70% improvement can be achieved in wind speed prediction by the proposed method. Moreover, it gives a probability distribution function of wind speed prediction, which is sharper than the one obtained with the first-order MC; means that more precise prediction


1.     Zhanxin, Y., Fang, Z., Lixiong, X., Hongjun, L., Dapeng, X., Junnan, L., Yu, D. and Yalei, L., "Investigation on equivalent trans-utilization mode and benefit of wind energy", International Journal of Engineering, Transactions A: Basics,  Vol. 31, No. 10, (2018), 1708-1714. doi:10.5829/ije.2018.31.10a.13.
2.     Keyhani, A., Ghasemi-Varnamkhasti, M., Khanali, M. and Abbaszadeh, R., "An assessment of wind energy potential as a power generation source in the capital of iran, tehran", Energy,  Vol. 35, No. 1, (2010), 188-201. doi: 10.1016/j.energy.2009.09.009.
3.     Lei, M., Shiyan, L., Chuanwen, J., Hongling, L. and Yan, Z., "A review on the forecasting of wind speed and generated power", Renewable and Sustainable Energy Reviews,  Vol. 13, No. 4, (2009), 915-920. doi: 10.1016/j.rser.2008.02.002.
4.     Han, K., Choi, J. and Kim, C., "Comparison of statistical post-processing methods for probabilistic wind speed forecasting", Asia-Pacific Journal of Atmospheric Sciences,  Vol. 54, No. 1, (2018), 91-101. doi: 10.1007/s13143-017-0062-z.
5.     Wang, X., Guo, P. and Huang, X., "A review of wind power forecasting models", Energy procedia,  Vol. 12, (2011), 770-778. doi: 10.1016/j.egypro.2011.10.103.
6.     Tagliaferri, F., Hayes, B., Viola, I. and Djokić, S., "Wind modelling with nested markov chains", Journal of Wind Engineering and Industrial Aerodynamics,  Vol. 157, (2016), 118-124. doi: 10.1016/j.jweia.2016.08.009.
7.     Liu, L. and Hu, F., "Long-term correlations and extreme wind speed estimations", Advances in Atmospheric Sciences,  Vol. 36, No. 10, (2019), 1121-1128. doi: 10.1007/s00376-019-9031-z.
8.     Liu, C., Fu, L., Yang, D., Miller, D.R. and Wang, J., "Non-gaussian lagrangian stochastic model for wind field simulation in the surface layer", Advances in Atmospheric Sciences,  Vol. 37, No. 1, (2020), 90-104. doi: 10.1007/s00376-019-9052-7.
9.     Shamshad, A., Bawadi, M., Hussin, W.W., Majid, T. and Sanusi, S., "First and second order markov chain models for synthetic generation of wind speed time series", Energy,  Vol. 30, No. 5, (2005), 693-708. doi: 10.1016/j.energy.2004.05.026.
10.   D'Amico, G., Petroni, F. and Prattico, F., "Wind speed modeled as an indexed semi-markov process", Environmetrics,  Vol. 24, No. 6, (2013), 367-376. doi: 10.1002/env.2215.
11.   Suomalainen, K., Silva, C., Ferrão, P. and Connors, S., "Synthetic wind speed scenarios including diurnal effects: Implications for wind power dimensioning", Energy,  Vol. 37, No. 1, (2012), 41-50. doi: 10.1016/j.energy.2011.08.001.
12.   Scholz, T., Lopes, V.V. and Estanqueiro, A., "A cyclic time-dependent markov process to model daily patterns in wind turbine power production", Energy,  Vol. 67, (2014), 557-568. doi: 10.1016/j.energy.2013.12.071
13.   Karatepe, S. and Corscadden, K.W., "Wind speed estimation: Incorporating seasonal data using markov chain models", International Scholarly Research Notices, Vol. 2013, (2013). doi: 10.1155/2013/657437.
14.   Xie, K., Liao, Q., Tai, H.-M. and Hu, B., "Non-homogeneous markov wind speed time series model considering daily and seasonal variation characteristics", IEEE Transactions on Sustainable Energy,  Vol. 8, No. 3, (2017), 1281-1290. doi: 10.1109/TSTE.2017.2675445.
15.   Ailliot, P. and Monbet, V., "Markov-switching autoregressive models for wind time series", Environmental Modelling & Software,  Vol. 30, (2012), 92-101. doi: 10.1016/j.envsoft.2011.10.011.
16.   Ailliot, P., Bessac, J., Monbet, V. and Pene, F., "Non-homogeneous hidden markov-switching models for wind time series", Journal of Statistical Planning and Inference,  Vol. 160, (2015), 75-88. doi: 10.1016/j.jspi.2014.12.005.
17.   Seyedarabi, H. and Feizi, A., "Application of combined local object based features and cluster fusion for the behaviors recognition and detection of abnormal behaviors", International Journal of Engineering, Transactions B: Applications,  Vol. 28, No. 11, (2015), 1597-1604. doi: 10.5829/idosi.ije.2015.28.11b.07.
18.   Zucchini, W., MacDonald, I.L. and Langrock, R., "Hidden markov models for time series: An introduction using r, CRC press, (2017). doi: 10.1201/9781420010893.
19.   Jiang, Y., Song, Z. and Kusiak, A., "Very short-term wind speed forecasting with bayesian structural break model", Renewable energy,  Vol. 50, (2013), 637-647. doi: 10.1016/j.renene.2012.07.041.
20.   Schlipf, D., Schlipf, D.J. and Kühn, M., "Nonlinear model predictive control of wind turbines using lidar", Wind energy,  Vol. 16, No. 7, (2013), 1107-1129. doi: 10.1002/we.1533.
21.   Khosravi, S., Zamanifar, M. and Derakhshan-Barjoei, P., "Analysis of bifurcations in a wind turbine system based on dfig", Emerging Science Journal,  Vol. 2, No. 1, (2018), 39-52. doi: 10.28991/esj-2018-01126.
22.   Chiniforosh, N. and Latif Shabgahi, G., "Wind measuring devices: Challenges, methods and technology trend", Journal of Climate Research,  Vol. 1397, No. 33, (2018), 43-62. http://clima.irimo.ir/article_77185_f6f291e750d365d4005ec5a3010d214c.pdf
23.   Abdulrazzaq, Z.T., Hasan, R.H. and Aziz, N.A., "Integrated trmm data and standardized precipitation index to monitor the meteorological drought", Civil Engineering Journal,  Vol. 5, No. 7, (2019), 1590-1598. doi: 10.28991/cej-2019-03091355
24.   Thanh, N.T., "Evaluation of multi-precipitation products for multi-time scales and spatial distribution during 2007-2015", Civil Engineering Journal,  Vol. 5, No. 1, (2019), 255-267. doi: 10.28991/cej-2019-03091242.