Temporal Convolutional Neural Networks for Solar Power Forecasting

We investigate the application of Temporal Convolutional Neural Networks (TCNNs) for solar power forecasting. TCNN is a novel convolutional architecture designed for sequential modelling, which combines causal and dilated convolutions and residual connections. We compare the performance of TCNN with multi-layer feedforward neural networks, and also with recurrent networks, including the state-of-the-art LSTM and GRU recurrent networks. The evaluation is conducted on two Australian datasets containing historical solar and weather data, and weather forecast data for future days. Our results show that TCNN outperformed the other models in terms of accuracy and was able to maintain a longer effective history compared to the recurrent networks. This highlights the potential of convolutional architectures for solar power forecasting tasks.

[1]  Irena Koprinska,et al.  Convolutional Neural Networks for Energy Time Series Forecasting , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[2]  Zheng Wang,et al.  Solar power prediction using weather type pair patterns , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[3]  H. Pedro,et al.  Assessment of forecasting techniques for solar power production with no exogenous inputs , 2012 .

[4]  Mashud Rana,et al.  Multiple steps ahead solar photovoltaic power forecasting based on univariate machine learning models and data re-sampling , 2020 .

[5]  Peng Wang,et al.  Forecasting Power Output of Photovoltaic Systems Based on Weather Classification and Support Vector Machines , 2011, IEEE Transactions on Industry Applications.

[6]  Zheng Wang,et al.  Solar power prediction with data source weighted nearest neighbors , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[7]  Gautier Marti,et al.  Autoregressive Convolutional Neural Networks for Asynchronous Time Series , 2017, ICML.

[8]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[9]  Irena Koprinska,et al.  Dynamic Ensemble Using Previous and Predicted Future Performance for Multi-step-ahead Solar Power Forecasting , 2019, ICANN.

[10]  Irena Koprinska,et al.  Big data solar power forecasting based on deep learning and multiple data sources , 2019, Expert Syst. J. Knowl. Eng..

[11]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[12]  B. Hodge,et al.  The value of day-ahead solar power forecasting improvement , 2016 .

[13]  Carlos F.M. Coimbra,et al.  Short-term reforecasting of power output from a 48 MWe solar PV plant , 2015 .

[14]  Irena Koprinska,et al.  Forecasting solar power generated by grid connected PV systems using ensembles of neural networks , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[15]  Xiang Zhang,et al.  Character-level Convolutional Networks for Text Classification , 2015, NIPS.

[16]  Zheng Wang,et al.  Solar Power Forecasting Using Dynamic Meta-Learning Ensemble of Neural Networks , 2018, ICANN.

[17]  Irena Koprinska,et al.  Pattern Sequence Neural Network for Solar Power Forecasting , 2019, ICONIP.

[18]  Thomas Reindl,et al.  A novel hybrid approach based on self-organizing maps, support vector regression and particle swarm optimization to forecast solar irradiance , 2015 .

[19]  Irena Koprinska,et al.  2D-interval forecasts for solar power production , 2015 .

[20]  Yoshua Bengio,et al.  On the Properties of Neural Machine Translation: Encoder–Decoder Approaches , 2014, SSST@EMNLP.

[21]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[22]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[24]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[25]  Yan Su,et al.  Analysis of daily solar power prediction with data-driven approaches , 2014 .

[26]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

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

[28]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[29]  Razvan Pascanu,et al.  On the difficulty of training recurrent neural networks , 2012, ICML.

[30]  Sander Bohte,et al.  Conditional Time Series Forecasting with Convolutional Neural Networks , 2017, 1703.04691.

[31]  Vladlen Koltun,et al.  An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling , 2018, ArXiv.