Abstract. Usually, neural networks trained on historical feed-in time series
of wind turbines deterministically predict power output over the next hours
to days. Here, the training goal is to minimise a scalar cost function, often
the root mean square error (RMSE) between network output and target values.
Yet similar to the analog ensemble (AnEn) method, the training algorithm can
also be adapted to analyse the uncertainty of the power output from the
spread of possible targets found in the historical data for a certain
meteorological situation. In this study, the uncertainty estimate is achieved
by discretising the continuous time series of power targets into several bins
(classes). For each forecast horizon, a neural network then predicts the
probability of power output falling into each of the bins, resulting in an
empirical probability distribution. Similiar to the AnEn method, the proposed
method avoids the use of costly numerical weather prediction (NWP) ensemble
runs, although a selection of several deterministic NWP forecasts as input is
helpful. Using state-of-the-art deep learning technology, we applied our
method to a large region and a single wind farm. MAE scores of the
50-percentile were on par with or better than comparable deterministic
forecasts. The corresponding Continuous Ranked Probability Score (CRPS) was
even lower. Future work will investigate the overdispersiveness sometimes
observed, and extend the method to solar power forecasts.
[1]
Constantin Junk,et al.
Predictor-weighting strategies for probabilistic wind power forecasting with an analog ensemble
,
2015
.
[2]
Jürgen Schmidhuber,et al.
Deep learning in neural networks: An overview
,
2014,
Neural Networks.
[3]
H. Hersbach.
Decomposition of the Continuous Ranked Probability Score for Ensemble Prediction Systems
,
2000
.
[4]
Eugenia Kalnay,et al.
Ensemble Forecasting at NMC: The Generation of Perturbations
,
1993
.
[5]
H. M. van den Dool,et al.
A New Look at Weather Forecasting through Analogues
,
1989
.
[6]
Martin A. Riedmiller,et al.
A direct adaptive method for faster backpropagation learning: the RPROP algorithm
,
1993,
IEEE International Conference on Neural Networks.
[7]
R. Stull,et al.
Kalman Filter and Analog Schemes to Postprocess Numerical Weather Predictions
,
2011
.