Advanced long short-term memory-based forecasting of electricity imbalances in the Ukrainian power system: Enhancing accuracy and stability with comparative model analysis

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F25%3A10258282" target="_blank" >RIV/61989100:27240/25:10258282 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/61989100:27730/25:10258282

Výsledek na webu

<a href="https://journals.sagepub.com/doi/10.1177/01445987251360272" target="_blank" >https://journals.sagepub.com/doi/10.1177/01445987251360272</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1177/01445987251360272" target="_blank" >10.1177/01445987251360272</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Advanced long short-term memory-based forecasting of electricity imbalances in the Ukrainian power system: Enhancing accuracy and stability with comparative model analysis

Popis výsledku v původním jazyce

Accurate forecasting of electricity imbalances is critical for maintaining power system stability and improving market efficiency, particularly in systems with high renewable energy penetration. This study proposes an advanced short-term forecasting methodology for the Ukrainian integrated power system using optimized long short-term memory (LSTM) neural networks. The novelty of the approach lies in the integration of automatic hyperparameter tuning and ensemble learning within LSTM architectures, specifically tailored to handle the high non-stationarity and extreme variability in real-world Ukrainian imbalance data. This hybrid structure enables robust performance under volatile market conditions. A comprehensive statistical analysis confirms significant skewness and volatility in hourly imbalance data from March 2022 to September 2024, obtained from NPC &quot;Ukrenergo,&quot; with variation coefficients of 100.14% and 77.37% for positive and negative imbalances, respectively. The proposed LSTM model with a 24-h input window achieved the best standalone accuracy, reducing mean absolute percentage error (MAPE) to 47.49% for positive and 35.96% for negative imbalances. Ensemble configurations (e.g. 4 + 24, 12 + 24) further improved stability, with correlation coefficients R(f, p) reaching 91.9% for positive and 77.83% for negative forecasts. In contrast, benchmark auto-regressive integrated moving average and seasonal auto-regressive integrated moving average models yielded significantly higher errors, with MAPE exceeding 92% and root mean square error values up to 522.15 MW&lt;middle dot&gt;h. Statistical tests, including the Diebold-Mariano and Durbin-Watson tests, validated the superior accuracy and residual independence of the LSTM ensembles. The proposed framework demonstrates substantial improvements in both accuracy and forecast stability, making it a scalable solution for real-time imbalance management in power systems undergoing structural transitions and renewable energy integration. This approach offers practical value for transmission system operators and balancing market participants seeking to enhance predictive performance and reduce imbalance-related penalties.

Název v anglickém jazyce

Advanced long short-term memory-based forecasting of electricity imbalances in the Ukrainian power system: Enhancing accuracy and stability with comparative model analysis

Popis výsledku anglicky

Accurate forecasting of electricity imbalances is critical for maintaining power system stability and improving market efficiency, particularly in systems with high renewable energy penetration. This study proposes an advanced short-term forecasting methodology for the Ukrainian integrated power system using optimized long short-term memory (LSTM) neural networks. The novelty of the approach lies in the integration of automatic hyperparameter tuning and ensemble learning within LSTM architectures, specifically tailored to handle the high non-stationarity and extreme variability in real-world Ukrainian imbalance data. This hybrid structure enables robust performance under volatile market conditions. A comprehensive statistical analysis confirms significant skewness and volatility in hourly imbalance data from March 2022 to September 2024, obtained from NPC &quot;Ukrenergo,&quot; with variation coefficients of 100.14% and 77.37% for positive and negative imbalances, respectively. The proposed LSTM model with a 24-h input window achieved the best standalone accuracy, reducing mean absolute percentage error (MAPE) to 47.49% for positive and 35.96% for negative imbalances. Ensemble configurations (e.g. 4 + 24, 12 + 24) further improved stability, with correlation coefficients R(f, p) reaching 91.9% for positive and 77.83% for negative forecasts. In contrast, benchmark auto-regressive integrated moving average and seasonal auto-regressive integrated moving average models yielded significantly higher errors, with MAPE exceeding 92% and root mean square error values up to 522.15 MW&lt;middle dot&gt;h. Statistical tests, including the Diebold-Mariano and Durbin-Watson tests, validated the superior accuracy and residual independence of the LSTM ensembles. The proposed framework demonstrates substantial improvements in both accuracy and forecast stability, making it a scalable solution for real-time imbalance management in power systems undergoing structural transitions and renewable energy integration. This approach offers practical value for transmission system operators and balancing market participants seeking to enhance predictive performance and reduce imbalance-related penalties.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20700 - Environmental engineering

Projekt

<a href="/cs/project/TN02000025" target="_blank" >TN02000025: Národní centrum pro energetiku II</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Energy Exploration and Exploitation

ISSN

0144-5987

e-ISSN

2048-4054

Svazek periodika

Neuveden

Číslo periodika v rámci svazku

July

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

25

Strana od-do

1-25

Kód UT WoS článku

001534477000001

EID výsledku v databázi Scopus

—