Research of software solutions for forecasting electricity generation and consumption in Ukraine that are based on machine learning methods

I.P. Sinitsyn, V.L. Shevchenko, А.Yu. Doroshenko, O.A. Yatsenko


The problem of security in energy sector is an important aspect for Ukraine. The purpose of monitoring in this area is to optimize the flow of electricity between market participants, between European partners and Ukraine. It is critically important to maintain a balance between producers and consumers of energy. Both over and undersupply of energy represent risks to infrastructure. The previously available wholesale electricity market model with single buyer has been replaced by a model based on bilateral, day-ahead and intraday markets, as well as balancing and ancillary services markets. Now the participants can freely trade electricity and energy companies can provide services that provide stability of the energy system and supply electricity to the final consumer. The demand forecasting in electricity markets is one of the components that must be implemented for successful business operations and optimization of business processes. Based on the model of the Institute of problems of modeling electricity engineering of NANU, the paper sets out the task of developing a software system for forecasting threats in the energy sector of Ukraine using machine learning methods. Experiments were conducted on the application of regression methods to restore a column with data from bilateral contracts for the task of forecasting electricity generation and consumption. The results of the application of machine learning algorithms on peacetime data demonstrated that it is possible to predict market volumes and tariff plans one hour in advance with a good accuracy which allows to go beyond one-day planning in the future.

Prombles in programming 2023; 3: 99-108


electricity; algorithm; machine learning; forecasting; regression; bilateral contracts market; day-ahead market; intraday market; balancing market


Illina, O.P., Sinitsyn, I.P. & Slabospitska, O.O. (2022) Principles and models of expert-analytical methodology for adaptive organizational decisions forming under deep uncertainty. Problems in programming. (3-4). p. 364-375. (in Ukrainian) CrossRef

Petrivskyi, V.Ya., Petrivskyi, Ya.B., Shevchenko, V.L. & Sinitsyn, I.P. (2022) Optimization of the trajectory of sensors motion taking into account the importance of the areas of the monitoring area segments and the probability of detection of objects. Problems of control and informatics. 67 (2). p. 6-21. (in Ukrainian) CrossRef

Rodin, Y.S. & Sinitsyn, I.P. (2021) Security basic model for applied tasks of the distributed information system. Problems in rogramming. (2). p. 16-23. CrossRef

Sinitsyn, I.P., Ignatenko, P.P. & Slabospitska, O.O. (2020) Architectural solutions for automated support of expert-analytical monitoring of the effectiveness of the weapons management system of the Armed Forces of Ukraine. Proc. 20th Scientific and Technical Conference "Creation and modernization of weapons and military equipment in modern conditions". Chernihiv: Brahinets. p. 95-96. (in Ukrainian)

Law of Ukraine. On Electricity Market. Available from: [Accessed 29/08/2023].

Careri, F., Genesi, C., Marannino, P., Montagna, M., Rossi, S. & Siviero, I. (2010) Bidding strategies in day-ahead energy markets: system marginal price vs. pay as bid. 7th International Conference on the European Energy Market. p. 1-7. [Online]. CrossRef

Wang, F., Ge, X., Li, K. & Mi, Z. (2019) Day-ahead market optimal bidding strategy and quantitative compensation mechanism design for load aggregator engaging demand response. 2019 IEEE/IAS 55th Industrial and Commercial Power Systems Technical Conference CrossRef

Evdokimov, V.A. & Polukhin, A.V. (2022) Income optimization of market participants in the day ahead market by modeling of processes of price determination for day ahead market. Electronic modeling. 44 (4). p. 121-129. [Online]. CrossRef

Singh, A.K., Ibraheem, S.K. & Muazzam, M. (2013) An overview of electricity demand forecasting techniques. Network and Complex Systems. 3. p. 38-48. [Online]. Available from: [Accessed 29/08/2023].

Solyali, D. (2020) A comparative analysis of machine learning approaches for short-/longterm electricity load forecasting in Cyprus. CrossRef

Krutsyak, M.O. (2018) Forecasting demand on the domestic electricity market on the basis of the results of social and economic indicators dynamics analysis. Ekonomichnyy analiz.28. p. 37-46. [Online]. CrossRef

Polukhin, A. & Evdokimov, V. Conceptual principles of forecasting demand on the dayahead market using changes in hourly bidded demand between previous similar days (in print)

Shah, I. & Lisi, F. (2015) Day-ahead electricity demand forecasting with nonparametric functional models. 12th International Conference on the European Energy Market (EEM). p. 1-5. [Online]. CrossRef

Vilar, J.M., Cao, R. & Aneiros G. (2012) Forecasting next-day electricity demand and price using nonparametric functional methods. International Journal of Electrical Power & Energy Systems. 39 (1). p. 48-55. [Online]. CrossRef

Ferraty, W.F. & Vieu, P. (2008) Nonparametric functional data analysis: theory and practice. Computational Statistics. 23. p. 341-342.[Online]. CrossRef

What Is ETL (Extract Transform Load)? [Online]. Available from: [Accessed 29/08/2023].

PostgreSQL: The world's most advanced open source database [Online]. Available from: [Accessed 29/08/2023].

Pautasso, C., Wilde, E. & Alarcon, R. (2014) REST: advanced research topics and practical applications. New York: Springer.

Scikit-learn. Machine learning in Python. [Online]. Available from: [Accessed 29/08/2023].



  • There are currently no refbacks.