High-quality Wind Power Scenario Forecasts for Decision-making Under Uncertainty in Power Systems

The large scale integration of wind generation in existing power systems requires novel operational strategies and market clearing mechanisms to account for the variable nature of this energy source. An efficient method to cope with this uncertainty is stochastic optimization which however requires high-quality forecasts in the form of scenarios. The main goal of this work is to release a public dataset of wind power forecasts to be used as a reference for future research. To that extent, we provide a complete framework to describe wind power uncertainty in terms of single-valued and probabilistic predictions as well as scenarios representing the spatio-temporal dependence structure of forecast errors. The applicability of the proposed framework is demonstrated with a small-scale stochastic unit commitment model.

[1]  A. Conejo,et al.  Economic Valuation of Reserves in Power Systems With High Penetration of Wind Power , 2009 .

[2]  Stefanos Delikaraoglou,et al.  Operational strategies for predictive dispatch of control reserves in view of stochastic generation , 2014, 2014 Power Systems Computation Conference.

[3]  G. Papaefthymiou,et al.  Modeling of Spatial Dependence in Wind Power Forecast Uncertainty , 2008, Proceedings of the 10th International Conference on Probablistic Methods Applied to Power Systems.

[4]  A. Atiya,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2005, IEEE Transactions on Neural Networks.

[5]  Oliver Kramer,et al.  Short-Term Wind Energy Forecasting Using Support Vector Regression , 2011, SOCO.

[6]  H. Madsen,et al.  From probabilistic forecasts to statistical scenarios of short-term wind power production , 2009 .

[7]  R. Brereton,et al.  Support vector machines for classification and regression. , 2010, The Analyst.

[8]  M. O'Malley,et al.  Unit Commitment for Systems With Significant Wind Penetration , 2009, IEEE Transactions on Power Systems.

[9]  H. Madsen,et al.  Predictive Densities for Day-Ahead Electricity Prices Using Time-Adaptive Quantile Regression , 2014 .

[10]  Pierre Pinson,et al.  Wind Energy: Forecasting Challenges for Its Operational Management , 2013, 1312.6471.

[11]  Jianxue Wang,et al.  Review on probabilistic forecasting of wind power generation , 2014 .

[12]  Gregor Giebel,et al.  The State-Of-The-Art in Short-Term Prediction of Wind Power. A Literature Overview , 2003 .

[13]  A. Papavasiliou,et al.  Reserve Requirements for Wind Power Integration: A Scenario-Based Stochastic Programming Framework , 2011, IEEE Transactions on Power Systems.

[14]  Jin Zhong,et al.  Pricing Electricity in Pools With Wind Producers , 2012, IEEE Transactions on Power Systems.

[15]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[16]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[17]  Geoffrey Pritchard,et al.  A Single-Settlement, Energy-Only Electric Power Market for Unpredictable and Intermittent Participants , 2010, Oper. Res..