A Combined Fuzzy GMDH Neural Network and Grey Wolf Optimization Application for Wind Turbine Power Production Forecasting Considering SCADA Data

A cost-effective and efficient wind energy production trend leads to larger wind turbine generators and drive for more advanced forecast models to increase their accuracy. This paper proposes a combined forecasting model that consists of empirical mode decomposition, fuzzy group method of data handling neural network, and grey wolf optimization algorithm. A combined K-means and identifying density-based local outliers is applied to detect and clean the outliers of the raw supervisory control and data acquisition data in the proposed forecasting model. Moreover, the empirical mode decomposition is employed to decompose signals and pre-processing data. The fuzzy GMDH neural network is a forecaster engine to estimate the future amount of wind turbines energy production, where the grey wolf optimization is used to optimize the fuzzy GMDH neural network parameters in order to achieve a lower forecasting error. Moreover, the model has been applied using actual data from a pilot onshore wind farm in Sweden. The obtained results indicate that the proposed model has a higher accuracy than others in the literature and provides single and combined forecasting models in different time-steps ahead and seasons.

[1]  S. S. Shen,et al.  Applications of Hilbert–Huang transform to non‐stationary financial time series analysis , 2003 .

[2]  Hoay Beng Gooi,et al.  Incorporating forecast uncertainties into EENS for wind turbine studies , 2011 .

[3]  Fabrizio Cumo,et al.  A GIS-based model to assess buildings energy consumption and usable solar energy potential in urban areas , 2018, Sustainable Cities and Society.

[4]  Azim Heydari,et al.  A new intelligent heuristic combined method for short-term electricity price forecasting in deregulated markets , 2016 .

[5]  Hans-Peter Kriegel,et al.  LOF: identifying density-based local outliers , 2000, SIGMOD 2000.

[6]  Farshid Keynia,et al.  Application of a new hybrid neuro-evolutionary system for day-ahead price forecasting of electricity markets , 2010, Appl. Soft Comput..

[7]  Benedetto Nastasi,et al.  Solar Energy Data Analytics: PV Deployment and Land Use , 2020, Energies.

[8]  Hang Li,et al.  Statistical distribution for wind power forecast error and its application to determine optimal size of energy storage system , 2014 .

[9]  H. Kusaka,et al.  Application of mesoscale ensemble forecast method for prediction of wind speed ramps , 2019, Wind Energy.

[10]  Peng Wang,et al.  Short-term wind power forecasting using the hybrid model of improved variational mode decomposition and Correntropy Long Short -term memory neural network , 2021, Energy.

[11]  João P. S. Catalão,et al.  A short-term spatio-temporal approach for Photovoltaic power forecasting , 2016, 2016 Power Systems Computation Conference (PSCC).

[12]  Andrew Lewis,et al.  Grey Wolf Optimizer , 2014, Adv. Eng. Softw..

[13]  Francesco Mancini,et al.  A GIS-based model to assess electric energy consumptions and usable renewable energy potential in Lazio region at municipality scale , 2019, Sustainable Cities and Society.

[14]  Zhengyang Wu,et al.  Wind power system reliability sensitivity analysis by considering forecast error based on non-standard third-order polynomial normal transformation method , 2019, Electric Power Systems Research.

[15]  Farshid Keynia,et al.  Short-term wind power forecasting using ridgelet neural network , 2011 .

[16]  Haiyan Lu,et al.  A novel combined model based on advanced optimization algorithm for short-term wind speed forecasting , 2018 .

[17]  Jian Su,et al.  A novel bidirectional mechanism based on time series model for wind power forecasting , 2016 .

[18]  Ceyhun Yildiz,et al.  An improved residual-based convolutional neural network for very short-term wind power forecasting , 2021 .

[19]  Jin Lin,et al.  A Versatile Probability Distribution Model for Wind Power Forecast Errors and Its Application in Economic Dispatch , 2013, IEEE Transactions on Power Systems.

[20]  Ricardo J. Bessa,et al.  Wind power probabilistic forecast in the Reproducing Kernel Hilbert Space , 2016, 2016 Power Systems Computation Conference (PSCC).

[21]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[22]  İnci Okumuş,et al.  Current status of wind energy forecasting and a hybrid method for hourly predictions , 2016 .

[23]  Daniel S. Kirschen,et al.  Estimating the Spinning Reserve Requirements in Systems With Significant Wind Power Generation Penetration , 2009, IEEE Transactions on Power Systems.

[24]  Abbas Mardani,et al.  An extended new approach for forecasting short-term wind power using modified fuzzy wavelet neural network: A case study in wind power plant , 2021 .

[25]  Mohammad Najafzadeh.  Neurofuzzy-Based GMDH-PSO to Predict Maximum Scour Depth at Equilibrium at Culvert Outlets , 2016 .

[26]  Farshid Keynia.  A new feature selection algorithm and composite neural network for electricity price forecasting , 2012, Eng. Appl. Artif. Intell..

[27]  Farshid Keynia,et al.  Day ahead price forecasting of electricity markets by a mixed data model and hybrid forecast method , 2008 .

[28]  Gianluigi Lo Basso,et al.  RES (Renewable Energy Sources) Availability Assessments for Eco-fuels Production at Local Scale: Carbon Avoidance Costs Associated to a Hybrid Biomass/H2NG-based Energy Scenario , 2015 .

[29]  R. Billinton,et al.  A simplified wind power generation model for reliability evaluation , 2006, IEEE Transactions on Energy Conversion.

[30]  Qing Wang,et al.  An improved random forest model of short-term wind-power forecasting to enhance accuracy, efficiency, and robustness , 2018, Wind Energy.

[31]  Farshid Keynia,et al.  A new short-term load forecast method based on neuro-evolutionary algorithm and chaotic feature selection , 2014 .

[32]  Hüseyin Akçay,et al.  Short-term wind speed forecasting by spectral analysis from long-term observations with missing values , 2017 .

[33]  Hidetomo Ichihashi,et al.  Orthogonal and Successive Projection Methods for Learning of Neurofuzzy GMDH , 1998, Inf. Sci..

[34]  Fulei Chu,et al.  Non-parametric hybrid models for wind speed forecasting , 2017 .

[35]  Kenneth Bruninx,et al.  A Statistical Description of the Error on Wind Power Forecasts for Probabilistic Reserve Sizing , 2014, IEEE Transactions on Sustainable Energy.

[36]  Elham B. Makram,et al.  Energy management system for enhanced resiliency of microgrids during islanded operation , 2016 .

[37]  João P. S. Catalão,et al.  Hybrid evolutionary-adaptive approach to predict electricity prices and wind power in the short-term , 2014, 2014 Power Systems Computation Conference.

[38]  Bin Zhou,et al.  Optimal sizing of energy storage system and its cost-benefit analysis for power grid planning with intermittent wind generation , 2018, Renewable Energy.

[39]  Jonas C. Pelajo,et al.  Wind farm generation forecast and optimal maintenance schedule model , 2019 .

[40]  Azim Heydari,et al.  A novel composite neural network based method for wind and solar power forecasting in microgrids , 2019, Applied Energy.

[41]  Xiaobo Zhang,et al.  Short-term electric load forecasting based on singular spectrum analysis and support vector machine optimized by Cuckoo search algorithm , 2017 .

[42]  Julio Usaola,et al.  Probabilistic load flow with correlated wind power injections , 2010 .

[43]  Yue Cui,et al.  Wind Turbine Health Assessment Framework Based on Power Analysis Using Machine Learning Method , 2019, 2019 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe).

[44]  Jing Ma,et al.  Research and application of a hybrid wavelet neural network model with the improved cuckoo search algorithm for electrical power system forecasting , 2017 .