Less Information, Similar Performance: Comparing Machine Learning-Based Time Series of Wind Power Generation to Renewables.ninja

Driven by climatic processes, wind power generation is inherently variable. Long-term simulated wind power time series are therefore an essential component for understanding the temporal availability of wind power and its integration into future renewable energy systems. In the recent past, mainly power curve-based models such as Renewables.ninja (RN) have been used for deriving synthetic time series for wind power generation, despite their need for accurate location information and bias correction, as well as their insufficient replication of extreme events and short-term power ramps. In this paper, we assessed how time series generated by machine learning models (MLMs) compare to RN in terms of their ability to replicate the characteristics of observed nationally aggregated wind power generation for Germany. Hence, we applied neural networks to one wind speed input dataset derived from MERRA2 reanalysis with no location information and two with additional location information. The resulting time series and RN time series were compared with actual generation. All MLM time series feature an equal or even better time series quality than RN, depending on the characteristics considered. We conclude that MLM models show a similar performance to RN, even when information on turbine locations and turbine types is unavailable.

[1]  Aoife Foley,et al.  Current methods and advances in forecasting of wind power generation , 2012 .

[2]  Qingli Dong,et al.  A novel forecasting model based on a hybrid processing strategy and an optimized local linear fuzzy neural network to make wind power forecasting: A case study of wind farms in China , 2017 .

[3]  Ricardo Nicolau Nassar Koury,et al.  Prediction of wind speed and wind direction using artificial neural network, support vector regression and adaptive neuro-fuzzy inference system , 2018 .

[4]  Robert Vautard,et al.  Vulnerabilities and resilience of European power generation to 1.5 °C, 2 °C and 3 °C warming , 2018 .

[5]  José M. Matías,et al.  Performance assessment of five MCP models proposed for the estimation of long-term wind turbine power outputs at a target site using three machine learning techniques , 2018 .

[6]  Dirk Uwe Sauer,et al.  Comparison of long-term wind and photovoltaic power capacity factor datasets with open-license , 2018, Applied Energy.

[7]  Iain Staffell,et al.  How does wind farm performance decline with age , 2014 .

[8]  Rasool Kazemzadeh,et al.  A novel hybrid technique for prediction of electric power generation in wind farms based on WIPSO, neural network and wavelet transform , 2018 .

[9]  Max Kuhn,et al.  Building Predictive Models in R Using the caret Package , 2008 .

[10]  Dirk J. Cannon,et al.  Using reanalysis data to quantify extreme wind power generation statistics: A 33 year case study in Great Britain , 2015 .

[11]  Thomas Huld,et al.  Impact of different levels of geographical disaggregation of wind and PV electricity generation in large energy system models: A case study for Austria , 2017 .

[12]  Jürgen P. Kropp,et al.  Susceptibility of the European electricity sector to climate change , 2013 .

[13]  S. Pfenninger,et al.  Balancing Europe’s wind power output through spatial deployment informed by weather regimes , 2017, Nature climate change.

[14]  Dimitrios Tzovaras,et al.  A Decision Support System Tool to Manage the Flexibility in Renewable Energy-Based Power Systems , 2019 .

[15]  H. J. Lu,et al.  An improved neural network-based approach for short-term wind speed and power forecast , 2017 .

[16]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[17]  José Manuel Benítez,et al.  Neural Networks in R Using the Stuttgart Neural Network Simulator: RSNNS , 2012 .

[18]  Jon Olauson,et al.  Modelling the Swedish wind power production using MERRA reanalysis data , 2015 .

[19]  Peter Regner,et al.  Assessing the Global Wind Atlas and local measurements for bias correction of wind power generation simulated from MERRA-2 in Brazil , 2019 .

[20]  Afshin Ebrahimi,et al.  A novel hybrid approach for predicting wind farm power production based on wavelet transform, hybrid neural networks and imperialist competitive algorithm , 2016 .

[21]  Jouni Paavola,et al.  A systematic review of the impacts of climate variability and change on electricity systems in Europe , 2016 .

[22]  Jinkyoo Park,et al.  Physics-induced graph neural network: An application to wind-farm power estimation , 2019, Energy.

[23]  Jianzhong Wu,et al.  Short-term wind power forecasting using wavelet-based neural network , 2017 .

[24]  S. Pfenninger,et al.  Using bias-corrected reanalysis to simulate current and future wind power output , 2016 .

[25]  Bin Zhao,et al.  The Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2). , 2017, Journal of climate.

[26]  Martin Greiner,et al.  Validation of Danish wind time series from a new global renewable energy atlas for energy system analysis , 2014, 1409.3353.

[27]  Oliver Kramer,et al.  Machine learning ensembles for wind power prediction , 2016 .

[28]  S. Pfenninger,et al.  Impacts of Inter-annual Wind and Solar Variations on the European Power System , 2018, Joule.