FORECAST-CONTROLLED ENERGY STORAGE SYSTEM FOR CONSUMERS WITH HOURLY TARIFFS
Bulletin of the South Ural State University series "Power Engineering" · 2026 · 26 (1) · 15-23
DOI: 10.14529/power260102 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bulletin of the South Ural State University series "Power Engineering", 2026. Verfasst von D.V. Bortnik und 2 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This article addresses the optimization of electricity costs for consumers in pricing categories III and IV of the Russian retail electricity market. Electricity costs for such consumers include a charge based on hourly tariffs and a power charge that depends on the average power during the hours of maximum total consumption in the region. However, information about hourly tariffs and the hours of maximum total consumption becomes available only after the billing period has ended, making it impossible for consumers to accurately predict their electricity costs. To reduce electricity expenses, the paper proposes to supplement the conventional power supply system with an energy storage system. The operation mode of this system is managed by a controller installed at the consumer's site, which ensures storage charging during periods of low electricity prices and discharging during peak load and high-priced hours. This reduces grid consumption and, consequently, the enterprise's costs. A LSTM-based recurrent neural network was used to forecast hourly electricity prices, demonstrating high accuracy in predicting price trends and peak values. However, efforts to predict the hours of maximum total consumption were unsuccessful due to the lack of stable periodicity. Therefore, we propose using the statistically most probable value for the hour of maximum consumption. We developed an algorithm for managing the energy storage system, taking into account price forecasts and a fixed value for the maximum consumption hour. The algorithm employs a strategy of storage charging during low-priced periods and discharging during peak hours. We used a shopping and entertainment center as an example to demonstrate the effectiveness of the proposed approach. The application of the algorithm almost halved the average power during peak hours (from 290kW to 140kW) and decreased overall electricity costs by 15.3 %. The obtained results demonstrate the potential of integrating energy storage systems with intelligent forecasting methods for energy conservation and load mana¬gement tasks.
Zitieren
APA
Bortnik, D., Orlov, A., & Karpov, I. (2026). FORECAST-CONTROLLED ENERGY STORAGE SYSTEM FOR CONSUMERS WITH HOURLY TARIFFS. Bulletin of the South Ural State University series "Power Engineering", 26(1), 15-23. https://doi.org/10.14529/power260102
Vancouver
Bortnik D, Orlov A, Karpov I. FORECAST-CONTROLLED ENERGY STORAGE SYSTEM FOR CONSUMERS WITH HOURLY TARIFFS. Bulletin of the South Ural State University series "Power Engineering". 2026;26(1):15-23. doi:10.14529/power260102
BibTeX
@article{Bortnik2026,
author = {Bortnik, D.V. and Orlov, A.I. and Karpov, I.A.},
title = {FORECAST-CONTROLLED ENERGY STORAGE SYSTEM FOR CONSUMERS WITH HOURLY TARIFFS},
journal = {Bulletin of the South Ural State University series "Power Engineering"},
year = {2026},
volume = {26},
number = {1},
pages = {15--23},
doi = {10.14529/power260102}
}
EUVIMED