Abstract
Global energy transition to renewable sources is among the substantial challenges facing humanity. In this context, the precise estimation of the renewable potential of given areas is valuable to decision-makers. This is particularly difficult for the urban case. In Chile, valuable data for solving this problem is available, however, standard machine learning algorithms struggle with their variable-length input. We take advantage of the ability of 1-D Convolutional Neural Network to fuse feature extraction and learning over a heterogeneous representation of the data. In the present manuscript, we propose an architecture to estimate the PV potential of Chilean cities and extract the relevant features over heterogeneous representations of available data. To this end, we describe and examine the performance of said architecture over the available data. We also extract its intermediate convolutional features and use them as inputs of other machine learning algorithms to compare performances. The network outperforms all other tested machine learning algorithms, while the intermediate learned convolutional representations improve the results of all non-linear algorithms explored.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Assouline, D., Mohajeri, N., Scartezzini, J.-L.: Estimation of large-scale solar rooftop pv potential for smart grid integration: a methodological review. In: Amini, M.H., Boroojeni, K.G., Iyengar, S.S., Pardalos, P.M., Blaabjerg, F., Madni, A.M. (eds.) Sustainable Interdependent Networks. SSDC, vol. 145, pp. 173–219. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-74412-4_11
Assouline, D., Mohajeri, N., Scartezzini, J.-L.: Large-scale rooftop solar photovoltaic technical potential estimation using Random Forests. Appl. Energy 217, 189–211 (2018)
Campos, P., Troncoso, L., Lund, P.D., Cuevas, C., Fissore, A., Garcia, R.: Potential of distributed photovoltaics in urban Chile. Sol. Energy 135, 43–49 (2016)
Hawkins, D.M.: The problem of overfitting. J. Chem. Inf. Comput. Sci. 44(1), 1–12 (2004). https://doi.org/10.1021/ci0342472
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, December 2016, pp. 770–778 (2016)
Hecht-Nielsen, R.: Theory of the backpropagation neural network, based on “nonindent” by Robert Hecht-Nielsen, which appeared in Proceedings of the International Joint Conference on Neural Networks, June 1989, vol. 1, pp. 593–611. Academic Press, Inc. (1992)
Hubel, D.H., Wiesel, T.N.: Receptive fields and functional architecture of monkey striate cortex. J. Physiol. 195(1), 215–243 (1968)
International Energy Agency: Energy Technology Perspectives 2016: towards sustainable urban energy systems (2016)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: 32nd International Conference on Machine Learning, ICML 2015, vol. 1, pp. 448–456 (2015)
Izquierdo, S., Rodrigues, M., Fueyo, N.: A method for estimating the geographical distribution of the available roof surface area for large-scale photovoltaic energypotential evaluations. Sol. Energy 82(10), 929–939 (2008)
Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, pp. 1–15 (2015)
Kiranyaz, S., Avci, O., Abdeljaber, O., Ince, T., Gabbouj, M., Inman, D.J.: 1D convolutional neural networks and applications: a survey. Mech. Syst. Sig. Process. 151, 107398 (2021). https://doi.org/10.1016/j.ymssp.2020.107398
Krizhevsky, A.: Imagenet classification with deep convolutional neural networks alex. In: Handbook of Approximation Algorithms and Metaheuristics, pp. 1–1432 (2007)
Lecun, Y., Bottou, L., Bengio, Y., Ha, P.: LeNet. In: Proceedings of the IEEE, November, pp. 1–46 (1998)
Mainzer, K., Killinger, S., McKenna, R., Fichtner, W.: Assessment of rooftop photovoltaic potentials at the urban level using publicly available geodata and image recognition techniques. Sol. Energy 155, 561–573 (2017)
Molina, A., Falvey, M., Rondanelli, R.: A solar radiation database for Chile. Sci. Rep. 7(1), 1–11 (2017)
Servicio de Impuestos Internos: Avalúos y contribuciones de bienes raíces. https://www4.sii.cl/mapasui/internet/#/contenido/index.html. Accessed Jan 2021
Sharma, S.: Activation functions in neural networks - towards data science, vol. 6 (2017)
Simsek, Y., Lorca, Á., Urmee, T., Bahri, P.A., Escobar, R.: Review and assessment of energy policy developments in Chile. Energy Policy 127, 87–101 (2019). https://doi.org/10.1016/j.enpol.2018.11.058
US EIA: International Energy Outlook 2013 - DOE/EIA-0484 (2013). Outlook 2013, p. 312 (2013)
Wiginton, L.K., Nguyen, H.T., Pearce, J.M.: Quantifying rooftop solar photovoltaic potential for regional renewable energy policy. Comput. Environ. Urban Syst. 34(4), 345–357 (2010)
Zeiler, M.D.: Visualizing and understanding convolutional networks. Anal. Chem. Res. 12, 40–46 (2017). https://doi.org/10.1016/j.ancr.2017.02.001
Zhang, C., Recht, B., Bengio, S., Hardt, M., Vinyals, O.: Understanding deep learning requires rethinking generalization. In: 5th International Conference on Learning Representations, ICLR 2017 - Conference Track Proceedings (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Valderrama, A., Valle, C., Ibarra, M., Allende, H. (2021). A Heterogeneous 1D Convolutional Architecture for Urban Photovoltaic Estimation. In: Huang, DS., Jo, KH., Li, J., Gribova, V., Bevilacqua, V. (eds) Intelligent Computing Theories and Application. ICIC 2021. Lecture Notes in Computer Science(), vol 12836. Springer, Cham. https://doi.org/10.1007/978-3-030-84522-3_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-84522-3_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-84521-6
Online ISBN: 978-3-030-84522-3
eBook Packages: Computer ScienceComputer Science (R0)