Temporal Convolutional Neural Networks for Solar Power Forecasting
Authors:
- 1 July 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
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.Keywords
This publication has 20 references indexed in Scilit:
- The value of day-ahead solar power forecasting improvementSolar Energy, 2016
- 2D-interval forecasts for solar power productionSolar Energy, 2015
- Forecasting solar power generated by grid connected PV systems using ensembles of neural networks2015
- Short-term reforecasting of power output from a 48 MWe solar PV plantSolar Energy, 2015
- Analysis of daily solar power prediction with data-driven approachesApplied Energy, 2014
- On the Properties of Neural Machine Translation: Encoder–Decoder Approaches2014
- Assessment of forecasting techniques for solar power production with no exogenous inputsSolar Energy, 2012
- Forecasting Power Output of Photovoltaic Systems Based on Weather Classification and Support Vector MachinesIEEE Transactions on Industry Applications, 2012
- Long Short-Term MemoryNeural Computation, 1997
- Phoneme recognition using time-delay neural networksIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989