Neural modeling of prices on the Day-Ahead Market at the Polish Power Exchange supported by an evolutionary algorithm and inspired by quantum computing

• Autorzy: Ruciński Dariusz

Identyfikatory

DOI

10.2478/candc-2022-0029

• Języki publikacji: EN

Abstrakty

EN

The purpose of the work, presented in this article, was to obtain a price model for the Day-Ahead Market of the Polish Power Exchange (PPE). The resulting proposed models are based on Artificial Neural Networks (ANN), and the involved suggested improvement concerns the proper selection of both the type of network and the factors used in model construction. The article also proposes a new approach to the ANN with the implemented quantum learning model. The purpose of the research was to analyze factors, which exert influence on the quality of the model, like weather or economic factors, or the type of neural network used. The model determines the relationship between the price and the volume of electricity for a given hour of the day. The mean square error and the coefficient of determination were used to measure the quality of the obtained models. The results from the experiments performed indicate the possibility of developing improved models of the Day-Ahead Market.

Słowa kluczowe

EN

Polish Power Exchange; Day Ahead Market; modeling of energy market; quantum inspired neural network

• Wydawca: Systems Research Institute, Polish Academy of Sciences
• Czasopismo: Control and Cybernetics
• Rocznik: 2022
• Tom: Vol. 51, No. 4
• Strony: 557--583
• Opis fizyczny: Bibliogr. 30 poz., rys., tab.

Twórcy

autor

Ruciński Dariusz

• University of Natural Sciences and Humanities, Computer Science Institute, 3 Maja 54, 08-110 Siedlce, Poland

Bibliografia

• Adamowski, J. (2019) Podstawy obliczeń kwantowych [Foundations of quantum calculations; in Polish]. Lectures at the Faculty of Physics and Applied Informatics, AGH University, Kraków, http://www.ftj.agh.edu.pl (access: 14.08.2019)
• Alaminos, D., Esteban, I. et al. (2020) Quantum Neural Networks for Forecasting Inflation Dynamics. Journal of Scientific & Industrial Research, 79, 2, doi: 10.56042/jsir.v79i2.68439 (access: 12.12.2022)
• Bai, J. and Ng, S. (2002) Determining the Number of Factors in Approximate Factor Models. Econometrica, 70, 1, 191–221.
• Bernhardt, C. (2020) Obliczenia kwantowe dla ka˙zdego [Quantum calculus for everyone; in Polish]. PWN, Warszawa.
• Bissing, D., Klein, M. T. et al. (2019) A Hybrid Regression Model for Day-Ahead Energy Price Forecasting. IEEE Access, 7, 36833-36842.
• Catalão, J., Mariano S. et al. (2022) An Artificial Neural Network Approach for Day-Ahead Electricity Prices Forecasting. Proceedings of the 6th WSEAS Int. Conf. on Neural Networks, Lisbon, Portugal, June 16-18, 2022; 80-83.
• Chudy, M. (2011)Wprowadzenie do informatyki kwantowej [Introduction into Quantum Informatics; in Polish]. OW EXIT, Warszawa.
• Ciechulski, T. and Osowski S. (2014) Badanie jakości predykcji obciążeń elektroenergetycznych za pomocą sieci neuronowych SVM, RBF i MLP [Analysing the quality of prediction of electric energy load with neural networks SVM, RBF and MLP; in Polish]. Przegląd Elektrotechniczny, 90, 8, 148-151.
• Conejo, A. J., Plazas M. A. et al. (2005) Day-ahead electricity price forecasting using the wavelet transform and ARIMA models. IEEE Transactions on Power Systems, 20, 2, 1035-1042.
• Feynman, R. P., Leughton, R. B. and Sands M. (2014) Feynmana wykłady z fizyki [Feynman’s lectures in physics; in Polish]. Volume 3. Mechanika kwantowa [Quantum mechanics]. PWN, Warszawa.
• Ge, L. and Wenping, M. (2022) A quantum artificial neural network for stock closing price prediction. Information Sciences, 598, 75-85, doi.org/10.1016/j.ins.2022.03.064 (access: 10.12.2022)
• Heller, M. (2016) Elementy mechaniki kwantowej dla filozofów [Elements of quantum mechanics for philosophers; in Polish]. Copernicus Center Press, Kraków.
• Hirvensalo, M. (2004) Algorytmy kwantowe [Quantum algorithms; in Polish]. WSiP, Warszawa.
• Lago, J., Marcjasz, G., De Schutter, B. and Weron R. (2021) Forecasting Day-ahead electricity prices: A review of state-of-the-art algorithms, best practices and an open-access benchmark. Applied Energy, 293.
• Mrozek, B. and Mrozek, Z. (2010) Matlab i Simulink: poradnik użytkownika [Matlab and Simulink: user’s guide; in Polish]. Helion, Gliwice.
• Mielczarski, W. (2000) Rynki energii elektrycznej. Wybrane aspekty techniczne i ekonomiczne [Electric energy markets. Selected technical and economic aspects; in Polish]. ARE S.A. i Energoprojekt-Consulting S.A., Warszawa.
• Nazarko, J. (2018) Prognozowanie w zarządzaniu przedsiębiorstwem. Część IV. Prognozowanie na podstawie modeli trendu [Forecasting in enterprise management. Part IV. Forecasting on the basis of trend models; in Polish]. Politechnika Białostocka, Białystok.
• Osowski, S. (2020) Sztuczne sieci neuronowe do przetwarzania informacji [Artificial neural networks for information processing; in Polish]. OW PW, Warszawa.
• Ruciński, D. (2018) Modelowanie neuronalne cen na Towarowej Giełdzie Energii Elektrycznej wspomagane algorytmem ewolucyjnym oraz inspirowane obliczeniami kwantowymi [Neural modeling of prices on Electric Power Exchange supported with evolutionary algorithm and inspired by quantum calculations; in Polish]. Doctoral dissertation elaborated under the guidance of Professor Jerzy Tchórzewski, UPH in Siedlce, IBS PAN,Warszawa.
• Ruciński, D. (2019) The Influence of the Artificial Neural Network Type on the Quality of Learning on the Day-Ahead Market Model at Polish Electricity Exchange Join-Stock Company. Studia Informatica. System and Information Technology, 1-2(23), 77-93.
• Ruciński, D. (2022) The impact of the size of the training set on the predictive abilities of neural models on the example of the Day-Ahead Market System of TGE S.A. Studia Informatica. Systems and Information Technology, 1(26)/2022, 5-24.
• Sawerwain, M. and Wiśniewska, J. (2015) Informatyka kwantowa. Wybrane obwody i algorytmy [Quantum informatics. Selected circuits and algorithms; in Polish]. PWN, Warszawa.
• Tchórzewski, J. (2013) Rozwój systemu elektroenergetycznego w ujęciu teorii sterowania i systemów [Development of the electric power system in the perspective of control and systems theory; in Polish]. OW PWr., Wrocław.
• Tchórzewski, J. (2021) Metody sztucznej inteligencji i informatyki kwantowej w ujęciu teorii sterowania i systemów [Methods of artificial intelligence and quantum mechanics in the light of control and systems theory; in Polish]. Wydawnictwo Naukowe UPH w Siedlcach.
• Tchórzewski, J. and Ruciński, D. (2016) Quantum inspired evolutionary algorithm to improve parameters of neural models on example of Polish electricity power exchange. Electric Power Networks (EPNet), 1-8, doi: 10.1109/EPNET.2016.7999349.
• Tchórzewski, J. and Ruciński, D. (2018) Quantum-inspired Artificial Neural Networks and Evolutionary Algorithms Methods Applied to Modeling of the Polish Electric Power Exchange Using the Day-ahead Market Data. Information Systems in Management, 7, 3, 201–212.
• Tchórzewski, J. and Ruciński, D. (2019) Evolutionarily-Supported and Quantum-Inspired Neural Modeling Applied to the Polish Electric Power Exchange. Progress in Applied Electrical Engineering (PAEE), 1-8, doi: 10.1109/PAEE.2019.8788987.
• Wiśniewska, J., Sawerwain, M. and Obuchowicz, A. (2020) Basic quantum circuits for classification and approximation tasks. International Journal of Applied Mathematics and Computer Science, 30(4), 733–744.
• Wright, J. and Jordanov, I. (2017), Quantum inspired evolutionary algorithms with improved rotation gates for real-coded synthetic and real world optimization problems. Integrated Computer-Aided Engineering, 24, 3, 203-223.
• Ziel, F. and Weron, R. (2018) Day-ahead electricity price forecasting with high-dimensional structures: Univariate vs. multivariate modeling frameworks. Energy Economics, Elsevier, 70(C), 396-420.