Modelling of electrical consumption and generation in an energy community
DOI:
https://doi.org/10.17979/ja-cea.2025.46.12268Keywords:
Renewable energy system modeling and integration, Forecasting, Time series modelling, Machine Learning, Optimization, ModelingAbstract
An energy community is a form if collective organization between citizens, companies, and local administrations that enables to produce, manage and consume energy jointly, with the aim of achieving environmental, social and economic benefits. This project develops models to optimize and forecast photovoltaic generation within the framework of an energy community. The study uses hourly data collected between January 2023 and December 2024 from two photovoltaic installations located in Vilassar de Mar (Maresme, Barcelona), along with meteorological data from the same municipality. The work is structured around two main lines: (1) identifying the statistical distribution that best fits the photovoltaic production, and (2) developing predictive models based on machine learning techniques to estimate future generation from weather forecasts.
References
Abad-Alcaraz, V., et al., 2023. Desarrollo de modelos de predicción de radiación solar mediante técnicas de machine learning. XLIV Jornadas de Automática, 382-387. DOI: https://doi.org/10.17979/spudc.9788497498609.382
CAEN, s.f. [Website]. Catalan Institute of Energy. Available at: https://icaen.gencat.cat
Frank J. Massey Jr., 2012. The Kolmogorov-Smirnov Test for Goodness of Fit. Journal of the American Statistical Association, 68-18. DOI: https://doi.org/10.2307/2280095
Ge, Z., Sun, Z., 2007. Neural Network Theory and MATLAB R2007 Application; 108–122.
J. A. R. Huamani et al., 2023. Prediction of hourly solar radiation using an Artificial Neural Network model in a district of Peru. 18th Iberian Conference on Information Systems and Technologies (CISTI), 1-4. DOI: 10.23919/CISTI58278.2023.10211948
Kolmogorov, A.N., 1957. On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition. Dokl. Akad. Nauk. Russ. Acad. Sci. 1957, 114, 953–956.
Myung, I.J., 2003. Tutorial on maximum likelihood estimation. Journal of Mathematical Psychology 47, 90–100. DOI: https://doi.org/10.1016/S0022-2496(02)00028-7
Pasari, S. et al, 2020. Statistical Modeling of Solar Energy. In; K. S. Sangwan and C. Herrmann (Eds.), Sustainable Production, Life Cycle Engineering and Management, India, pp. 157-165.
Razavi, S. et al., 2012. Review of surrogate modeling in water resources. Water Resources Research, 48 (7). DOI: 10.1029/2011WR011527
Pedregosa, F. et al., 2011. Scikit-learn: Machine Learning in Python. The Journal of Machine Learning Research, Volume 12, pp 2825 – 2830.
Tieleman, T. and Hinton, G., 2012. Lecture 6.5 - RMSProp: Divide the gradient by a running average of its recent magnitude. Coursera: Neural Networks for Machine Learning.
Nair, V. and Hinton, G.E., 2010. Rectified linear units improve restricted Boltzmann machines. Proceedings of the 27th International Conference on Machine Learning (ICML), 807-814
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Berta Mitjavila, Miquel Oliver
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
