Combined Nonparametric Prediction Intervals for Wind Power Generation

Prediction intervals (PIs) are a promising tool for quantification of uncertainties associated with point forecasts of wind power. However, construction of PIs using parametric methods is questionable, as forecast errors do not follow a standard distribution. This paper proposes a nonparametric method for construction of reliable PIs for neural network (NN) forecasts. A lower upper bound estimation (LUBE) method is adapted for construction of PIs for wind power generation. A new framework is proposed for synthesizing PIs generated using an ensemble of NN models in the LUBE method. This is done to guard against NN performance instability in generating reliable and informative PIs. A validation set is applied for short listing NNs based on the quality of PIs. Then, PIs constructed using filtered NNs are aggregated to obtain combined PIs. Performance of the proposed method is examined using data sets taken from two wind farms in Australia. Simulation results indicate that the quality of combined PIs is significantly superior to the quality of PIs constructed using NN models ranked and filtered by the validation set.

[1]  Spyros Makridakis,et al.  The M3-Competition: results, conclusions and implications , 2000 .

[2]  S. Nahavandi,et al.  Prediction Intervals for Short-Term Wind Farm Power Generation Forecasts , 2013, IEEE Transactions on Sustainable Energy.

[3]  S. Nahavandi,et al.  Wind farm power uncertainty quantification using a mean-variance estimation method , 2012, 2012 IEEE International Conference on Power System Technology (POWERCON).

[4]  Amir F. Atiya,et al.  Comprehensive Review of Neural Network-Based Prediction Intervals and New Advances , 2011, IEEE Transactions on Neural Networks.

[5]  A. V. Savkin,et al.  A Method for Short-Term Wind Power Prediction With Multiple Observation Points , 2012, IEEE Transactions on Power Systems.

[6]  P Pinson,et al.  Conditional Prediction Intervals of Wind Power Generation , 2010, IEEE Transactions on Power Systems.

[7]  Wei-Jen Lee,et al.  An Integration of ANN Wind Power Estimation Into Unit Commitment Considering the Forecasting Uncertainty , 2007, IEEE Transactions on Industry Applications.

[8]  Henrik Madsen,et al.  Adaptive modelling and forecasting of offshore wind power fluctuations with Markov‐switching autoregressive models , 2012 .

[9]  J. Stock,et al.  Combination forecasts of output growth in a seven-country data set , 2004 .

[10]  Bruce W. Schmeiser,et al.  Improving model accuracy using optimal linear combinations of trained neural networks , 1995, IEEE Trans. Neural Networks.

[11]  Ruddy Blonbou,et al.  Very short-term wind power forecasting with neural networks and adaptive Bayesian learning , 2011 .

[12]  John Bjørnar Bremnes,et al.  Probabilistic wind power forecasts using local quantile regression , 2004 .

[13]  W. Rivera,et al.  Short term wind speed forecasting in La Venta, Oaxaca, México, using artificial neural networks , 2009 .

[14]  Amir F. Atiya,et al.  Lower Upper Bound Estimation Method for Construction of Neural Network-Based Prediction Intervals , 2011, IEEE Transactions on Neural Networks.

[15]  A. Llombart,et al.  Statistical Analysis of Wind Power Forecast Error , 2008, IEEE Transactions on Power Systems.

[16]  Amir F. Atiya,et al.  Forecast combinations of computational intelligence and linear models for the NN5 time series forecasting competition , 2011 .

[17]  Saeid Nahavandi,et al.  Construction of Optimal Prediction Intervals for Load Forecasting Problems , 2010, IEEE Transactions on Power Systems.

[18]  M. Lange.  On the Uncertainty of Wind Power Predictions—Analysis of the Forecast Accuracy and Statistical Distribution of Errors , 2005 .

[19]  A. Weigend,et al.  Estimating the mean and variance of the target probability distribution , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

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

[21]  P. Pinson,et al.  Very‐short‐term probabilistic forecasting of wind power with generalized logit–normal distributions , 2012 .

[22]  Jing Shi,et al.  Bayesian adaptive combination of short-term wind speed forecasts from neural network models , 2011 .

[23]  David J. C. MacKay,et al.  The Evidence Framework Applied to Classification Networks , 1992, Neural Computation.

[24]  G. Nemhauser,et al.  Wiley‐Interscience Series in Discrete Mathematics and Optimization , 2014 .

[25]  Saeid Nahavandi,et al.  Optimizing the quality of bootstrap-based prediction intervals , 2011, The 2011 International Joint Conference on Neural Networks.

[26]  Henrik Madsen,et al.  Using quantile regression to extend an existing wind power forecasting system with probabilistic forecasts , 2006 .

[27]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[28]  J. T. Hwang,et al.  Prediction Intervals for Artificial Neural Networks , 1997 .

[29]  Tom Heskes,et al.  Practical Confidence and Prediction Intervals , 1996, NIPS.

[30]  Jing Shi,et al.  Evaluation of hybrid forecasting approaches for wind speed and power generation time series , 2012 .

[31]  José M. Matías,et al.  Influence of the input layer signals of ANNs on wind power estimation for a target site: A case study , 2011 .

[32]  Tomonobu Senjyu,et al.  A new strategy for predicting short-term wind speed using soft computing models , 2012 .

[33]  Pierre Pinson,et al.  Non‐parametric probabilistic forecasts of wind power: required properties and evaluation , 2007 .

[34]  Saeid Nahavandi,et al.  Prediction Interval Construction and Optimization for Adaptive Neurofuzzy Inference Systems , 2011, IEEE Transactions on Fuzzy Systems.

[35]  J. B. Bremnes.  A comparison of a few statistical models for making quantile wind power forecasts , 2006 .

[36]  Ioannis B. Theocharis,et al.  A locally recurrent fuzzy neural network with application to the wind speed prediction using spatial correlation , 2007, Neurocomputing.