Efficient load frequency controller for a power system comprising renewable resources based on deep reinforcement learning

Abstract This paper presents the development of an adaptive load frequency controller (LFC) to mitigate frequency deviations in power systems comprising renewable energy sources (RESs) during transient and steady-state conditions. Integrating RESs with power systems results in frequency problems due...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohamed A. El-Hameed, Mahfouz Saeed, Adnan Kabbani, Enas Abd El-Hay
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-03310-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849687989804859392
author Mohamed A. El-Hameed
Mahfouz Saeed
Adnan Kabbani
Enas Abd El-Hay
author_facet Mohamed A. El-Hameed
Mahfouz Saeed
Adnan Kabbani
Enas Abd El-Hay
author_sort Mohamed A. El-Hameed
collection DOAJ
description Abstract This paper presents the development of an adaptive load frequency controller (LFC) to mitigate frequency deviations in power systems comprising renewable energy sources (RESs) during transient and steady-state conditions. Integrating RESs with power systems results in frequency problems due to reduced system inertia and the intermittency of the RESs. The paper introduces a model-free controller that employs deep neural networks trained by the twin-delayed deep deterministic gradient reinforcement learning policy to generate the load reference signal (LRS) for the speed governor. The LRS is produced by the controller’s agent, which undergoes training by receiving observations and rewards from the power system. These observations capture frequency errors resulting from load disturbances and renewable power fluctuations, while the reward assesses the controller’s effectiveness in minimizing frequency errors. Compared to heuristic-based controllers, the proposed controller demonstrates considerable improvements in frequency stability for both steady-state error and transient response across various load disturbances when compared to heuristic-based controllers. Moreover, the proposed controller could limit the frequency deviations under varying weather conditions.
format Article
id doaj-art-04006d7e726b4801a9ca41f8596dd4a8
institution DOAJ
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-04006d7e726b4801a9ca41f8596dd4a82025-08-20T03:22:09ZengNature PortfolioScientific Reports2045-23222025-05-0115111210.1038/s41598-025-03310-2Efficient load frequency controller for a power system comprising renewable resources based on deep reinforcement learningMohamed A. El-Hameed0Mahfouz Saeed1Adnan Kabbani2Enas Abd El-Hay3Energy and Sustainable Engineering Department, College of Engineering, A’Sharqiyah UniversityEnergy and Sustainable Engineering Department, College of Engineering, A’Sharqiyah UniversityElectrical Engineering and Computer Science Department, College of Engineering, A’Sharqiyah UniversityElectrical Power and Machines Department, Faculty of Engineering, Zagazig UniversityAbstract This paper presents the development of an adaptive load frequency controller (LFC) to mitigate frequency deviations in power systems comprising renewable energy sources (RESs) during transient and steady-state conditions. Integrating RESs with power systems results in frequency problems due to reduced system inertia and the intermittency of the RESs. The paper introduces a model-free controller that employs deep neural networks trained by the twin-delayed deep deterministic gradient reinforcement learning policy to generate the load reference signal (LRS) for the speed governor. The LRS is produced by the controller’s agent, which undergoes training by receiving observations and rewards from the power system. These observations capture frequency errors resulting from load disturbances and renewable power fluctuations, while the reward assesses the controller’s effectiveness in minimizing frequency errors. Compared to heuristic-based controllers, the proposed controller demonstrates considerable improvements in frequency stability for both steady-state error and transient response across various load disturbances when compared to heuristic-based controllers. Moreover, the proposed controller could limit the frequency deviations under varying weather conditions.https://doi.org/10.1038/s41598-025-03310-2Deep neural networksReinforcement learningLoad frequency controlRenewable resources
spellingShingle Mohamed A. El-Hameed
Mahfouz Saeed
Adnan Kabbani
Enas Abd El-Hay
Efficient load frequency controller for a power system comprising renewable resources based on deep reinforcement learning
Scientific Reports
Deep neural networks
Reinforcement learning
Load frequency control
Renewable resources
title Efficient load frequency controller for a power system comprising renewable resources based on deep reinforcement learning
title_full Efficient load frequency controller for a power system comprising renewable resources based on deep reinforcement learning
title_fullStr Efficient load frequency controller for a power system comprising renewable resources based on deep reinforcement learning
title_full_unstemmed Efficient load frequency controller for a power system comprising renewable resources based on deep reinforcement learning
title_short Efficient load frequency controller for a power system comprising renewable resources based on deep reinforcement learning
title_sort efficient load frequency controller for a power system comprising renewable resources based on deep reinforcement learning
topic Deep neural networks
Reinforcement learning
Load frequency control
Renewable resources
url https://doi.org/10.1038/s41598-025-03310-2
work_keys_str_mv AT mohamedaelhameed efficientloadfrequencycontrollerforapowersystemcomprisingrenewableresourcesbasedondeepreinforcementlearning
AT mahfouzsaeed efficientloadfrequencycontrollerforapowersystemcomprisingrenewableresourcesbasedondeepreinforcementlearning
AT adnankabbani efficientloadfrequencycontrollerforapowersystemcomprisingrenewableresourcesbasedondeepreinforcementlearning
AT enasabdelhay efficientloadfrequencycontrollerforapowersystemcomprisingrenewableresourcesbasedondeepreinforcementlearning