Autors: Georgieva, A. N., Georgiev, M. G., Ivanov D.
Title: Photovoltaic Energy Production Modeling Using Linear Regression Models in MS Excel
Keywords: Demand response, Electricity market, Energy management, Machine learning, Photovoltaic energy

Abstract: Photovoltaic Energy Production is a basic element of current energy systems. The transition to decentralized energy production which characterizes fast dynamics in the change of electricity consumption and production leads to new developments in control systems for grid management and its maintenance. On the other hand, the energy system is closely related to the energy market and the trading rules. This raises additional constraints for utilizing production and consumption capacities related to existing business models. Therefore, it is necessary to develop analytical models and software tools for modeling the behavior of renewable energy sources, electricity consumption, and storage. This knowledge is a milestone for successful participation in the electricity market, demand response, and smart energy management. The current research represents a software tool based on MS Excel for photovoltaic energy production modeling and forecasting. Linear regression models with different numbers of variables and their applications are used in the research process including cases of gaps in the raw data.

References

  1. European Environment Agency, ““Share of energy consumption from renewable sources in Europe,” (eea.europa.eu, Copenhagen, 2024)
  2. I. Jebli, F. Z. Belouadha, M. I. Kabbaj, A. Tilioua, “Prediction of solar energy guided by pearson correlation using machine learning,” Energy, vol. 224, no. 11, 2021.
  3. J. Curwin, R. Slater, D. Eadson, Quantitative Methods For Business Decisions, Learning EMEA, 2013.
  4. R. J. Freund; W. J. Wilson; D. L. Mohr, “Linear Regression,” Statistical Methods (Third Edition), pp. 321-374, 2010.
  5. G. Box, G. Jenkins, G. Reinsel, Tme series analysis: Forcasting and control, Prentice Hall, 1994.
  6. E. Garipov, Identification of systems, Part II, Sofia: Technical University, 2007.
  7. A. El Hammoumi, S. Chtita, S. Motahhir, A. El Ghzizal, “Solar PV energy: From material to use, and the most commonly usedtechniques to maximize the power output of PV systems: A focus onsolar trackers and floating solar panels,” Energy Reports, vol. 8, p. 11992–12010, 2022
  8. K. Doherty, R. Adams, N. Davey, “"Non-Euclidean Norms and Data Normalisation,",” European Symposium on Artificial Neural Networks Bruges,, pp. 181-186, 2004
  9. D. Maurya, A. K. Tangirala, S. Narasimhan, “ARX Model Identification using Generalized Spectral Decomposition,” IFAC Papers On Line, vol. 54, no. 9, pp. 690-695, 2021
  10. Masuda, J. C. Baltazar, D. Claridge, J. Ji, “Development of Data Quality Control Limits for Data Screening through the "Energy Balance" Method,” in Proceedings of the Sixteenth Symposium on Improving Building Systems in Hot and Humid Climates, Plano,2008

Issue

2024 16th Electrical Engineering Faculty Conference, BulEF 2024, 2024, Albania, https://doi.org/10.1109/BULEF63204.2024.10794869

Цитирания (Citation/s):
1. Jafari F., Moerschell J., Riesen K., Comparison of PV Power Prediction Techniques: From Regression to LSTM Models, 2025, 2025 International Conference on Control Automation and Diagnosis Iccad 2025, issue 0, DOI 10.1109/ICCAD64771.2025.11099459 - 2025 - в издания, индексирани в Scopus

Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus