View in EDS

Adaptive control strategy for islanded microgrid with cryptocurrency mining load.

Saved in:
Bibliographic Details
Title: Adaptive control strategy for islanded microgrid with cryptocurrency mining load.
Authors: Ahmad, Ghali1 (AUTHOR) g202214940@kfupm.edu.sa, Shafiullah, Md1,2 (AUTHOR), Abido, Mohammad A.2,3 (AUTHOR), Aljehani, Faris4 (AUTHOR)
Source: Neural Computing & Applications. Mar2026, Vol. 38 Issue 5, p1-17. 17p.
Abstract: The rapidly increasing cryptocurrency mining sector requires sustainable solutions that improve power system flexibility because they lead to rising energy consumption demands. The proposed framework develops an adaptive Artificial Neural Network-based Proportional Integral Derivative control scheme for Load Frequency Control in islanded Microgrids due to their high penetration of Renewable Energy Sources and cryptocurrency mining loads that use Application-Specific Integrated Circuits as dynamic loads. The load frequency control methods based on conventional techniques fail to adjust control parameters for unpredictable variations of renewable energy sources and load variation, which causes frequency instability. The study compares artificial neural network controllers optimized using various metaheuristic optimization techniques, such as Genetic Algorithm, Particle Swarm Optimization, Grey Wolf Optimization, Simulated Annealing-based Whale Swarm Optimization, Flower Pollination Algorithm, and Modified Jellyfish Search algorithm. Under different operating conditions, performance indices such as Integral of Squared Error, Integral of Absolute Error, and Integral of Time-weighted Absolute Error were used to evaluate the controllers. It is shown that a genetic algorithm-based artificial neural network consistently outperforms other controllers by providing the lowest error values and superior disturbance rejection capabilities. The particle swarm optimization-based artificial neural network and grey wolf optimization-based artificial neural network also offer strong performance in reducing oscillations and faster system stabilization. The remaining ones demonstrate moderate enhancements compared to the standard artificial neural network due to their ability to manage high errors with slower time responses. The work shows the application of intelligent optimization techniques in frequency regulation using an artificial neural network. [ABSTRACT FROM AUTHOR]
Copyright of Neural Computing & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:The rapidly increasing cryptocurrency mining sector requires sustainable solutions that improve power system flexibility because they lead to rising energy consumption demands. The proposed framework develops an adaptive Artificial Neural Network-based Proportional Integral Derivative control scheme for Load Frequency Control in islanded Microgrids due to their high penetration of Renewable Energy Sources and cryptocurrency mining loads that use Application-Specific Integrated Circuits as dynamic loads. The load frequency control methods based on conventional techniques fail to adjust control parameters for unpredictable variations of renewable energy sources and load variation, which causes frequency instability. The study compares artificial neural network controllers optimized using various metaheuristic optimization techniques, such as Genetic Algorithm, Particle Swarm Optimization, Grey Wolf Optimization, Simulated Annealing-based Whale Swarm Optimization, Flower Pollination Algorithm, and Modified Jellyfish Search algorithm. Under different operating conditions, performance indices such as Integral of Squared Error, Integral of Absolute Error, and Integral of Time-weighted Absolute Error were used to evaluate the controllers. It is shown that a genetic algorithm-based artificial neural network consistently outperforms other controllers by providing the lowest error values and superior disturbance rejection capabilities. The particle swarm optimization-based artificial neural network and grey wolf optimization-based artificial neural network also offer strong performance in reducing oscillations and faster system stabilization. The remaining ones demonstrate moderate enhancements compared to the standard artificial neural network due to their ability to manage high errors with slower time responses. The work shows the application of intelligent optimization techniques in frequency regulation using an artificial neural network. [ABSTRACT FROM AUTHOR]
ISSN:09410643
DOI:10.1007/s00521-025-11823-0