Sequence to sequence deep learning models for solar irradiation forecasting

The energy output a photo voltaic(PV) panel is a function of solar irradiation and weather parameters like temperature and wind speed etc. A general measure for solar irradiation called Global Horizontal Irradiance (GHI), customarily reported in Watt/meter2, is a generic indicator for this intermittent energy resource. An accurate prediction of GHI is necessary for reliable grid integration of the renewable as well as for power market trading. While some machine learning techniques are well introduced along with the traditional time-series forecasting techniques, deep-learning techniques remains less explored for the task at hand. In this paper we give deep learning models suitable for sequence to sequence prediction of GHI. The deep learning models are reported for short-term forecasting $\{1-24\}$ hour along with the state-of-the art techniques like Gradient Boosted Regression Trees(GBRT) and Feed Forward Neural Networks(FFNN). We have checked that spatio-temporal features like wind direction, wind speed and GHI of neighboring location improves the prediction accuracy of the deep learning models significantly. Among the various sequence-to-sequence encoder-decoder models LSTM performed superior, handling short-comings of the state-of-the-art techniques.

[1]  G. Nagy,et al.  GEFCom2014: Probabilistic solar and wind power forecasting using a generalized additive tree ensemble approach , 2016 .

[2]  Emil Isaksson,et al.  Solar Power Forecasting with Machine Learning Techniques , 2018 .

[3]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.

[4]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[5]  Vladimiro Miranda,et al.  Probabilistic solar power forecasting in smart grids using distributed information , 2015 .

[6]  Henrik Madsen,et al.  Multivariate conditional parametric models for a spatio-temporal analysis of short-term wind power forecast errors , 2010 .

[7]  M. Raza,et al.  On recent advances in PV output power forecast , 2016 .

[8]  R. Urraca,et al.  Review of photovoltaic power forecasting , 2016 .

[9]  Ki-Hyun Kim,et al.  Solar energy: Potential and future prospects , 2018 .

[10]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[11]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[12]  Rob J Hyndman,et al.  Probabilistic energy forecasting: Global Energy Forecasting Competition 2014 and beyond , 2016 .

[13]  Judith Gurney.  BP Statistical Review of World Energy , 1985 .

[14]  Aron Habte,et al.  Evaluation of the National Solar Radiation Database (NSRDB): 1998-2015 , 2017 .

[15]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[16]  Sepp Hochreiter,et al.  Self-Normalizing Neural Networks , 2017, NIPS.

[17]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[18]  Sonia Leva,et al.  Physical and hybrid methods comparison for the day ahead PV output power forecast , 2017 .

[19]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[20]  R. Shanmugam.  Introduction to Time Series and Forecasting , 1997 .

[21]  Peter L. Bartlett,et al.  Boosting Algorithms as Gradient Descent , 1999, NIPS.

[22]  Chaker El Amrani,et al.  Sequence to Sequence Weather Forecasting with Long Short-Term Memory Recurrent Neural Networks , 2016 .

[23]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[24]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[25]  Richard A. Davis,et al.  Introduction to time series and forecasting , 1998 .