Selected Aspects of neural-evolutionary modeling of Prices on the Day Ahead Market of TGE S.A.

• Autorzy: Ruciński Dariusz

Identyfikatory

DOI

10.34739/si.2024.31.06

• Języki publikacji: EN

Abstrakty

EN

Modeling in the context of Artificial Intelligence (AI) is using mathematics to describe, analyze, and predict real-world systems. Building models that can simulate or predict various aspects of reality is a key issue that is the subject of many studies. The quality of models depends on many elements, starting from the architecture of the neural network itself, through the selection of teaching data in terms of the size of the sets, and the number of factors influencing the choice of the network itself. Modifications of the network training methods themselves also play an important role, e.g. through the use of Evolutionary Algorithms (AE). The paper focuses on several selected aspects related to the quality of modeling based on prices on the Day Ahead Market (DAM). The influence of network architecture factors, network type, number of training data, and Evolutionary Algorithms on the improvement of the model quality measured by the Mean Squared Error (MSE) and the coefficient of determination (R2) were considered.

Słowa kluczowe

EN

Day-Ahead Market; modeling; neural networks; evolutionary algorithms; model improvement; MATLAB environment

• Wydawca: Wydawnictwo Uniwersytetu Przyrodniczo-Humanistycznego w Siedlcach
• Czasopismo: Studia Informatica : systems and information technology
• Rocznik: 2024
• Tom: vol. 2 (31)
• Strony: 69--85
• Opis fizyczny: Bibliogr. 25 poz., rys., tab., wykr.

Twórcy

autor

Ruciński Dariusz

• University of Siedlce, Faculty of Exact and Natural Sciences, Institute of Computer Science, ul. 3 Maja 54, 08-110 Siedlce, Poland

• https://orcid.org/0000-0001-5458-9170

Bibliografia

• 1. Arabas, J. (2016), Wykłady z Algorytmów Ewolucyjnych (Lectures on Evolutionary Algorithms). WNT, Warszawa, p. 303.
• 2. Beale, M. H. [at al.] (1992-2019), Neural Network Toolbox TMUser’s Guide, The Math Works, Inc.p. 846.
• 3. Ejdys, J., Halicka, K., Godlewska, J., (2015), Prognozowanie cen energii elektrycznej na giełdzie energii (Forecasting electricity prices on the energy exchange), Wydawnictwo Politechniki Łódzkiej, Zeszyty Naukowe. Organizacja i Zarządzanie, zeszyt 77, pp. 53-61.
• 4. Bulatovic, L. B., Sukovic, G. R. (2018), On applying evolutionary algorithms for hybrid neural net-works’ architecture synthesis, 23rd International Scientific-Professional Conference on Information Technology, Zabljak, pp. 1-4.
• 5. Halicka, K., (2006), Skuteczność prognozowania w zarządzaniu transakcjami na giełdzie energiielektrycznej (The effectiveness of forecasting in managing transactions on the electricity exchange). Rozprawa doktorska pod kierunkiem prof. dr hab. inż. J. Nazarko, UW, Warszawa p. 207.
• 6. Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9, pp.1735-1780.
• 7. Holland, J. H. (1975). Adaptation in Natural and Artificial Systems. University of Michigan Press p.194.
• 8. Hopfield, J.J., (1982). Neural networks and physical systems with emergent collective computationalabilities. Proc. Natl Acad. Sci. USA. pp. 2554-2558. doi: 10.1073/pnas.79.8.2554
• 9. Koza, J. R. (1992). Genetic Programming: On the Programming of Computers by Means of Natural Selection p. 840.
• 10. McCarthy, J. (1960). Recursive Functions of Symbolic Expressions and Their Computation byMachine, Part I. Communications of the ACM, vol. 3, issue 4 pp. 184-195.
• 11. Moody, J., & Darken, C. (1989). Fast Learning in Networks of Locally-Tuned Processing Units. In D. S. Touretzky (Ed.), Advances in Neural Information Processing Systems 1, pp. 281-288.
• 12. Lago, J., Marcjasz, G. [et al.], (2021) Forecasting Day-ahead electricity prices: A review of state-of-the-art algorithms, best practices and an open-access benchmark. Aplayed Energy Vol. 293, p.21.
• 13. LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-Based Learning Applied toDocument Recognition. Proceedings of the IEEE, 86, pp. 2278-2324.
• 14. Marlęga, R. (2021) Comparative Study of the Identification Methods of the Management Systemof the Day-Ahead Market of Polish Energy Market S.A. Studia Informatica. System and InformationTechnology, Nr 1-2 pp. 67-86.
• 15. Michalewicz, Z. (2011) Genetic Algorithms + Data Structures = Evolution Programs, Springer-Verlag, p. 387.
• 16. Mielczarski, W. (2000) Rynki energii elektrycznej. Wybrane aspekty techniczne i ekonomiczne (Electricity markets. Selected technical and economic aspects), ARE, Warszawa, p. 308.
• 17. Popławski, T., Weżgowiec, M., (2017), Prognozowanie Cen Energii Na Rynku Spot Giełdy NordPool i TGE (Forecasting Energy Prices on the Spot Market of the Nord Pool and TGE StockExchanges), Rynek Energii 1/2017, p. 11.
• 18. Powell, M. J. D. (1987). Radial Basis Functions for Multivariable Interpolation: A Review. In J. C.Mason & M. G. Cox (Eds.), Algorithms for Approximation, pp. 143-167.
• 19. Rosenblatt, F. (1958) The perceptron: A probabilistic model for information storage and organizationin the brain. Psychological Review, 65, pp. 386-408.
• 20. Ruciński, D. (2016) Neural-evolutionary Modeling of Polish Electricity Power Exchange. ElectricalPower Networks, EPNet 2016, Katedra Energoelektryki PWr, Institute of Power Engineering and Control Systems of Lviv Polytechnic National University, Ukraine and O/Wrocławski SEP, XPlore Digital Library, Szklarska Poręba 2016 r., pp. 1-6.
• 21. Tchórzewski, J. (2021) Metody sztucznej inteligencji i informatyki kwantowej w ujęciu teoriisterowania i systemów (Methods of artificial intelligence and quantum computing in terms of controland systems theory), Wydawnictwo Naukowe Uniwersytetu Przyrodniczo-Humanistycznego, p. 343.
• 22. Voronin, S. (2013) Price Spike Forecasting in a competitive day-ahead energy market, Acta Universitatis, Lappeenrantaensis 530, 2013, p. 181.
• 23. Weron, R., Misiorek A.(2008) Forecasting spot electricity prices: A comparison of parametric andsemiparametric time series models, MPRA Paper, No.10428, Monachium, p. 23.
• 24. Zieliński, J. S. [et al.] (2000) Inteligentne systemy w zarządzaniu, Teoria i praktyka (Intelligentsystems in management, theory and practice). WN PWN, Warszawa, p. 349.
• 25. Zhang, H., Hu, W. [et al.] (2024) A Temporal Convolutional Network Based Hybrid Model for Short-term Electricity Price Forecasting, CSEE Journal Of Power And Energy Systems, Vol. 10, No.3, pp.1119-1130.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).