Electricity Markets; Electricity Price; Long-short Term Memory; Price Forecasting
Abstract :
[en] With the increasing share of variable renewable energy sources in the power system, electricity prices are becoming more and more volatile and uncertain. This means that electricity market participants are experiencing issues related to trading activities as wrong electricity forecast can lead to wrong schedules and reduced profits. The state-of-the-art literature offers wide range of electricity price forecasting tools which build upon historical prices as well as various exogenous variables as inputs. The deep neural network algorithms are prevailing in literature and impose as the most advanced tools. In this paper we propose a long-short-term-memory network using only historic price, its timestamp and additional features engineered on top of that price. We will elaborate which features affect the forecasting and show how the algorithms trained on prices before significant change in trends behave when unexpected prices occur, such as those in the second half of 2021. The first research outcome is that proper feature selection can have significant impact on forecasting accuracy, for example day-of-week and statistical properties of last 24 or 168 hours increase the accuracy noticeably. The second one is that when drastic trend changes occur in the historical data it may show that using last few months as a test dataset is not a proper way to handle the issue. Better results are achieved if the test dataset is taken as certain months during the year.
Research center :
Interdisciplinary Centre for Security, Reliability and Trust (SnT) > FINATRAX - Digital Financial Services and Cross-organizational Digital Transformations
Disciplines :
Management information systems Electrical & electronics engineering Computer science Energy
Author, co-author :
Miletic, Marija; University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, Croatia
PAVIĆ, Ivan ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > FINATRAX
Pandzic, Hrvoje; University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, Croatia
Capuder, Tomislav; University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, Croatia
External co-authors :
yes
Language :
English
Title :
Day-ahead Electricity Price Forecasting Using LSTM Networks
Original title :
[en] Day-ahead Electricity Price Forecasting Using LSTM Networks
Publication date :
2022
Event name :
2022 7th International Conference on Smart and Sustainable Technologies (SpliTech)
Event place :
Split, Hrv
Event date :
05-07-2022 => 08-07-2022
By request :
Yes
Audience :
International
Main work title :
2022 7th International Conference on Smart and Sustainable Technologies, SpliTech 2022
Editor :
Solic, Petar
Publisher :
Institute of Electrical and Electronics Engineers Inc.
This work has been supported in part by the European Structural and Investment Funds under project KK.01.2.1.02.0063 SUPEER (System for optimization of energy consumption in households), and by the European Union’s Horizon 2020 research and innovation programme under grant agreement No 864274 (project FARCROSS).This work has been supported in part by the European Structural and Investment Funds under project KK.01.2.1.02.0063 SUPEER (System for optimization of energy consumption in households), and by the European Union's Horizon 2020 research and innovation programme under grant agreement No 864274 (project FARCROSS)
BP, "Statistical Review of World Energy, 2020-69th Edition, " tech. rep., BP, 2020.
H. Ritchie, "Energy mix-Our World in Data. " https://ourworldindata. org/energy-mix, visited on 2020-12-28.
M. Koivisto, P. Sorensen, P. Maule, and E. Nuño Martinez, Needs for Flexibility Caused by the Variability and Uncertainty in Wind and Solar Generation in 2020, 2030 and 2050 Scenarios. Denmark: DTU Wind Energy, 2017.
S. Impram, S. V. Nese, and B. Oral, "Challenges of renewable energy penetration on power system flexibility: A survey, " Energy Strategy Reviews, vol. 31, p. 100539, 9 2020.
A. A. Sánchez de la Nieta and J. Contreras, "Quantifying the effect of renewable generation on day-ahead electricity market prices: The Spanish case, " Energy Economics, vol. 90, p. 104841, aug 2020.
F. Paraschiv, D. Erni, and R. Pietsch, "The impact of renewable energies on EEX day-ahead electricity prices, " Energy Policy, vol. 73, pp. 196-210, oct 2014.
J. Seel, D. Millstein, A. Mills, M. Bolinger, and R. Wiser, "Plentiful electricity turns wholesale prices negative, " Advances in Applied Energy, vol. 4, p. 100073, nov 2021.
P. Atanasoae, R. D. Pentiuc, and E. Hopulele, "Considerations Regarding the Negative Prices on the Electricity Market, " Proceedings 2020, Vol. 63, Page 26, vol. 63, p. 26, dec 2020.
J. H. Keppler, S. Phan, and Y. L. Pen, "The Impacts of Variable Renewable Production and Market Coupling on the Convergence of French and German Electricity Prices, " The Energy Journal, vol. 37, no. 3, pp. 343-359, 2016.
P. K. Adom, M. Insaidoo, M. K. Minlah, and A. M. Abdallah, "Does renewable energy concentration increase the variance/uncertainty in electricity prices in Africa?, " Renewable Energy, vol. 107, pp. 81-100, jul 2017.
J. C. Ketterer, "The impact of wind power generation on the electricity price in Germany, " Energy Economics, vol. 44, pp. 270-280, jul 2014.
A. Ostrovnaya, I. Staffell, C. Donovan, and R. Gross, "The High Cost of Electricity Price Uncertainty, " SSRN Electronic Journal, feb 2020.
H. Peura and D. W. Bunn, "Renewable Power and Electricity Prices: The Impact of Forward Markets, " https://doi. org/10. 1287/mnsc. 2020. 3710, vol. 67, pp. 4772-4788, feb 2021.
R. Weron, "Electricity price forecasting: A review of the state-of-theart with a look into the future, " International Journal of Forecasting, vol. 30, pp. 1030-1081, oct 2014.
J. Lago, G. Marcjasz, B. De Schutter, and R. Weron, "Forecasting dayahead electricity prices: A review of state-of-the-art algorithms, best practices and an open-access benchmark, " Applied Energy, vol. 293, p. 116983, jul 2021.
B. Uniejewski, J. Nowotarski, and R. Weron, "Automated Variable Selection and Shrinkage for Day-Ahead Electricity Price Forecasting, " Energies 2016, Vol. 9, Page 621, vol. 9, p. 621, aug 2016.
J. Lago, F. De Ridder, and B. De Schutter, "Forecasting spot electricity prices: Deep learning approaches and empirical comparison of traditional algorithms, " Applied Energy, vol. 221, pp. 386-405, jul 2018.
Y. Chen, Y. Wang, J. Ma, and Q. Jin, "BRIM: An Accurate Electricity Spot Price Prediction Scheme-Based Bidirectional Recurrent Neural Network and Integrated Market, " Energies 2019, Vol. 12, Page 2241, vol. 12, p. 2241, jun 2019.
J. H. Meier, S. Schneider, I. Schmidt, P. Schüller, T. Schönfeldt, and B. Wanke, "ANN-Based Electricity Price Forecasting Under Special Consideration of Time Series Properties, " Communications in Computer and Information Science, vol. 1007, pp. 262-275, may 2018.
S. Mujeeb, N. Javaid, M. Ilahi, Z. Wadud, F. Ishmanov, and M. K. Afzal, "Deep Long Short-Term Memory: A New Price and Load Forecasting Scheme for Big Data in Smart Cities, " Sustainability 2019, Vol. 11, Page 987, vol. 11, p. 987, feb 2019.
S. Zhou, L. Zhou, M. Mao, H. M. Tai, and Y. Wan, "An Optimized Heterogeneous Structure LSTM Network for Electricity Price Forecasting, " IEEE Access, vol. 7, pp. 108161-108173, 2019.