An Unsupervised Deep Learning Approach for Scenario Forecasts

In this paper, we propose a novel scenario forecasts approach which can be applied to a broad range of power system operations (e.g., wind, solar, load) over various forecasts horizons and prediction intervals. This approach is model-free and data-driven, producing a set of scenarios that represent possible future behaviors based only on historical observations and point forecasts. It first applies a newly-developed unsupervised deep learning framework, the generative adversarial networks, to learn the intrinsic patterns in historical renewable generation data. Then by solving an optimization problem, we are able to quickly generate large number of realistic future scenarios. The proposed method has been applied to a wind power generation and forecasting dataset from national renewable energy laboratory. Simulation results indicate our method is able to generate scenarios that capture spatial and temporal correlations. Our code and simulation datasets are freely available online.

[1]  David L. Woodruff,et al.  Toward scalable stochastic unit commitment. Part 1: load scenario generation , 2015 .

[2]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[3]  Xi-Yuan Ma,et al.  Scenario Generation of Wind Power Based on Statistical Uncertainty and Variability , 2013, IEEE Transactions on Sustainable Energy.

[4]  Zhang Yan,et al.  A review on the forecasting of wind speed and generated power , 2009 .

[5]  Baosen Zhang,et al.  Economic Dispatch Considering Spatial and Temporal Correlations of Multiple Renewable Power Plants , 2017, 1707.00237.

[6]  Stefanos Delikaraoglou,et al.  High-quality Wind Power Scenario Forecasts for Decision-making Under Uncertainty in Power Systems , 2014 .

[7]  Rüdiger,et al.  WILMAR Deliverable 6 . 2 ( d ) Documentation Methodology of the Scenario Tree Tool , 2006 .

[8]  Daniel Kirschen,et al.  Model-Free Renewable Scenario Generation Using Generative Adversarial Networks , 2017, IEEE Transactions on Power Systems.

[9]  Yingzhong Gu,et al.  Stochastic Look-Ahead Economic Dispatch With Variable Generation Resources , 2017, IEEE Transactions on Power Systems.

[10]  Robin Girard,et al.  Evaluating the quality of scenarios of short-term wind power generation , 2012 .

[11]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[12]  Bri-Mathias Hodge Final Report on the Creation of the Wind Integration National Dataset (WIND) Toolkit and API: October 1, 2013 - September 30, 2015 , 2016 .

[13]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[14]  C. Villani Optimal Transport: Old and New , 2008 .

[15]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[16]  G. J. Osórioa,et al.  A new scenario generation-based method to solve the unit commitment problem with high penetration of renewable energies , 2014 .

[17]  Kit Po Wong,et al.  Probabilistic Forecasting of Wind Power Generation Using Extreme Learning Machine , 2014, IEEE Transactions on Power Systems.

[18]  Yuzong Liu,et al.  Scenario Reduction With Submodular Optimization , 2017, IEEE Transactions on Power Systems.

[19]  Tao Wang,et al.  Toward a flexible scenario generation tool for stochastic renewable energy analysis , 2016, 2016 Power Systems Computation Conference (PSCC).

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

[21]  Geoffrey E. Hinton,et al.  On the importance of initialization and momentum in deep learning , 2013, ICML.

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