Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
158 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

PVNet: A LRCN Architecture for Spatio-Temporal Photovoltaic PowerForecasting from Numerical Weather Prediction (1902.01453v4)

Published 4 Feb 2019 in cs.LG and cs.AI

Abstract: Photovoltaic (PV) power generation has emerged as one of the lead renewable energy sources. Yet, its production is characterized by high uncertainty, being dependent on weather conditions like solar irradiance and temperature. Predicting PV production, even in the 24-hour forecast, remains a challenge and leads energy providers to left idling - often carbon emitting - plants. In this paper, we introduce a Long-Term Recurrent Convolutional Network using Numerical Weather Predictions (NWP) to predict, in turn, PV production in the 24-hour and 48-hour forecast horizons. This network architecture fully leverages both temporal and spatial weather data, sampled over the whole geographical area of interest. We train our model on an NWP dataset from the National Oceanic and Atmospheric Administration (NOAA) to predict spatially aggregated PV production in Germany. We compare its performance to the persistence model and state-of-the-art methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (32)
  1. TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. Technical report. URL www.tensorflow.org.
  2. Accurate photovoltaic power forecasting models using deep LSTM-RNN. Neural Computing and Applications, pp.  1–14, 2017. ISSN 09410643. doi: 10.1007/s00521-017-3225-z.
  3. Probabilistic Model for Spatio-Temporal Photovoltaic Power Forecasting. IEEE Transactions on Sustainable Energy, 2018. ISSN 19493029. doi: 10.1109/TSTE.2018.2847558.
  4. Bidirectional recurrent neural network language models for automatic speech recognition. In 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.  5421–5425. IEEE, 4 2015. ISBN 978-1-4673-6997-8. doi: 10.1109/ICASSP.2015.7179007. URL http://ieeexplore.ieee.org/document/7179007/.
  5. Master optimization process based on neural networks ensemble for 24-h solar irradiance forecast. Solar Energy, 111:297–312, 2015. ISSN 0038092X. doi: 10.1016/j.solener.2014.10.036. URL http://dx.doi.org/10.1016/j.solener.2014.10.036.
  6. Solar and wind forecasting by NARX neural networks. Renewable Energy and Environmental Sustainability, 1:39, 2016. ISSN 2493-9439. doi: 10.1051/rees/2016047. URL http://www.rees-journal.org/10.1051/rees/2016047.
  7. An ANN-based Approach for Forecasting the Power Output of Photovoltaic System. 2011. doi: 10.1016/j.proenv.2011.12.196. URL www.elsevier.com/locate/procedia.
  8. A physical hybrid artificial neural network for short term forecasting of PV plant power output. Energies, 8(2):1138–1153, 2015. ISSN 19961073. doi: 10.3390/en8021138.
  9. Long-term recurrent convolutional networks for visual recognition and description. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2015. ISBN 9781467369640. doi: 10.1109/CVPR.2015.7298878.
  10. The Effect of Temperature on Photovoltaic Cell Efficiency. Technical report, 2011. URL http://research.iaun.ac.ir/pd/jjfesharakiold/pdfs/PaperC_4124.pdf.
  11. Deep Learning for solar power forecasting - An approach using AutoEncoder and LSTM Neural Networks. 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings, pp.  2858–2865, 2017. ISSN 1879-0852. doi: 10.1109/SMC.2016.7844673.
  12. Forecasting short-term solar irradiance based on artificial neural networks and data from neighboring meteorological stations. Solar Energy, 134:119–131, 2016. ISSN 0038092X. doi: 10.1016/j.solener.2016.04.020. URL http://dx.doi.org/10.1016/j.solener.2016.04.020.
  13. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. Technical report. URL https://arxiv.org/pdf/1502.01852.pdf.
  14. Long Short-Term Memory. Neural Computation, 1997. ISSN 08997667. doi: 10.1162/neco.1997.9.8.1735.
  15. pvlib python: a python package for modeling solar energy systems. 2018. doi: 10.21105/joss.00884. URL https://doi.org/10.21105/joss.00884.
  16. Application of extreme learning machine for short term output power forecasting of three grid-connected PV systems. Journal of Cleaner Production, 167:395–405, 2018. ISSN 09596526. doi: 10.1016/j.jclepro.2017.08.081. URL http://dx.doi.org/10.1016/j.jclepro.2017.08.081.
  17. Solar forecasting methods for renewable energy integration. 2013. doi: 10.1016/j.pecs.2013.06.002. URL http://dx.doi.org/10.1016/j.pecs.2013.06.002.
  18. Application of time series and artificial neural network models in short-term forecasting of PV power generation. Proceedings of the Universities Power Engineering Conference, pp.  1–6, 2013. ISSN 1944-9925. doi: 10.1109/UPEC.2013.6714975.
  19. Adam: A Method for Stochastic Optimization. 12 2014. URL http://arxiv.org/abs/1412.6980.
  20. An ARMAX model for forecasting the power output of a grid connected photovoltaic system. 2014. doi: 10.1016/j.renene.2013.11.067. URL http://dx.doi.org/10.1016/j.renene.2013.11.067.
  21. Forecasting the daily power output of a grid-connected photovoltaic system based on multivariate adaptive regression splines. Applied Energy, 180:392–401, 2016a. ISSN 03062619. doi: 10.1016/j.apenergy.2016.07.052. URL http://dx.doi.org/10.1016/j.apenergy.2016.07.052.
  22. A hierarchical approach using machine learning methods in solar photovoltaic energy production forecasting. Energies, 9(1), 2016b. ISSN 19961073. doi: 10.3390/en9010055.
  23. Local and regional photovoltaic power prediction for large scale grid integration: Assessment of a new algorithm for snow detection. International Journal of ChemTech Research, 9(11):261–270, 2011. ISSN 09744290. doi: 10.1002/pip.
  24. Photovoltaic power forecasting using statistical methods: impact of weather data. IET Science, Measurement & Technology, 8(3):90–97, 2013. ISSN 1751-8822. doi: 10.1049/iet-smt.2013.0135. URL http://digital-library.theiet.org/content/journals/10.1049/iet-smt.2013.0135.
  25. Muzathik, A. M. Photovoltaic Modules Operating Temperature Estimation Using a Simple Correlation. International Journal of Energy engineering, 4:151–158, 2014. ISSN 1470-2045.
  26. Data-driven photovoltaic power production nowcasting and forecasting for polygeneration microgrids. IEEE Systems Journal, 12(3):2842–2853, 2018. ISSN 19379234. doi: 10.1109/JSYST.2017.2688359.
  27. SANDIA REPORT Global Horizontal Irradiance Clear Sky Models: Implementation and Analysis. Technical report. URL http://www.ntis.gov/help/ordermethods.asp?loc=7-4-0#online.
  28. Bidirectional Recurrent Neural Networks. Technical Report 11, 1997. URL https://pdfs.semanticscholar.org/4b80/89bc9b49f84de43acc2eb8900035f7d492b2.pdf.
  29. Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. pp.  1–12, 2015. ISSN 10495258. doi: 10.1074/jbc.M200827200. URL http://arxiv.org/abs/1506.04214.
  30. Solar photovoltaic generation forecasting methods: A review. Energy Conversion and Management, 156(May 2017):459–497, 2018. ISSN 01968904. doi: 10.1016/j.enconman.2017.11.019. URL https://doi.org/10.1016/j.enconman.2017.11.019.
  31. Visualizing and Understanding Convolutional Networks. 11 2013. URL http://arxiv.org/abs/1311.2901.
  32. LSTM network: a deep learning approach for short-term traffic forecast. IET Intelligent Transport Systems, 11(2):68–75, 2017. ISSN 1751-956X. doi: 10.1049/iet-its.2016.0208. URL http://digital-library.theiet.org/content/journals/10.1049/iet-its.2016.0208.
Citations (24)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Youtube Logo Streamline Icon: https://streamlinehq.com

YouTube