Prediction capabilities of the LSTM and Perceptron models based on the Day-Ahead Market on the Polish Power Exchange S.A.

• Autorzy: Ruciński Dariusz

Identyfikatory

DOI

10.34739/si.2023.28.04

• Języki publikacji: EN

Abstrakty

EN

The main purpose of the research was to examine the properties of models for two kinds of neural networks, a deep learning models in which the Long Short-Term Memory was chosen and shallow neural model in which the Perceptron Neural Network was chosen. The subject of the examination was the Day-Ahead Market system of PPE S.A. The article presents the learning results of both networks and the results of the predictive abilities of the models. The research was conducted based on data published on the Polish Stock Exchange for the 2018 year. The MATLAB environment was chosen as a tool for providing the examinations. The determination index (R2) and the mean square error (MSE) was adopted as the network evaluation criterion for the learning ability and for the prediction ability of both networks.

Słowa kluczowe

EN

shallow networks; deep networks; Day-Ahead Market; MATLAB; Simulink environment; neural modeling; prediction time; electricity prices

• Wydawca: Wydawnictwo Uniwersytetu Przyrodniczo-Humanistycznego w Siedlcach
• Czasopismo: Studia Informatica : systems and information technology
• Rocznik: 2023
• Tom: Vol. 1(28)
• Strony: 69--82
• Opis fizyczny: Bibliogr. 12 poz., rys., tab., wykr.

Twórcy

autor

Ruciński Dariusz

• PhD Student at Institute of Computer Science, Siedlce University of Natural Sciences and Humanities, 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. Bedi J., Toshniwal D., Deep learning framework to forecast electricity demand, Applied Energy, Vol. 238, pp 1312-1326, 2019.
• 2. McCulloch W. S., W. Pitts W.,(1943), A logical calculus of the ideas immanent in nervous activity, Bull. Math. Bioph. No 5, pp. 115-133, 1943.
• 3. Fukushima K, Neocognitron. A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position, Biological Cybernetics. No 36, pp. 193-202, 1980.
• 4. Hochreiter S. and Schmidhuber J., Long Short-term Memory. Neural computation. No. 9, 1997.
• 5. Jiang L., Hu G., Day-Ahead Price Forecasting for Electricity Market using Long-Short Term Memory Recurrent Neural Network, 15th International Conference on Control, Automation, Robotics and Vision (ICARCV), Singapore, pp. 949-954, 2018.
• 6. Kingma, D. P. and Ba J., Adam: A Method for Stochastic Optimization. ArXiv. /abs/1412.6980, 2014.
• 7. Marszałek, A., Burczynski T., Forecasting Day-ahead spot electricity prices using deep neural networks with attention mechanism. J. Smart. Environ. Green. Comput. 1, pp. 21-31, 2021, http://dx.doi.org/10.20517/jsegc.2021.02 (accessed: 20.09.2023].
• 8. Matlab, Help for MATLAB and Simulink. https://www.mathworks.com/help/deeplearning/ug/list-of-deep-learning-layers.html. 2023, [accessed: 10-15 Aug. 2023].
• 9. Ruciński D., Modeling of the Day-Ahead Market on the Polish Power Exchange on the example of selected artificial neural networks, [chapter in monograph no 1:] Theory and Application in Artrificial Intelligence Methods, Wydawnictwo Naukowe UPH, pp. 85-117, 2021.
• 10. Ruciński D., 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, Vol. 1(26), pp. 5-24, 2021.
• 11. Tchórzewski J., Metody sztucznej inteligencji i informatyki kwantowej w ujęciu teorii sterowania i systemów (in Polish) [ eng. Methods of artificial intelligence and quantum computing in terms of control theory and systems]. Wydawnictwo Naukowe. UPH. Siedlce, pages 343, 2021.
• 12. Zhang R., Li G., and Ma Z, A Deep Learning Based Hybrid Framework for Day-Ahead Electricity Price Forecasting," in IEEE Access, Vol. 8, pp. 143423-143436, 2020.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024)