Improving Development of a Control Scheme for a Hybrid Renewable Energy System Using Ann Based Supercapacitor
Authors: Ogbuokebe, Stanislaus Kaosoluchukwu, Ngang Bassey Ngang, Ogharandukun, M., Nwagu, C. C.
Journal: International Journal of Electrical, Electronics and Communication Engineering (IJEECE), ISSN 3023-3569
Citation: IJEECE 6(2): 1-12, 2025-07-16.
DOI: 10.5281/zenodo.15953884
PDF: Download full-text PDF
Type: Original Research
Abstract
This study addresses the challenges associated with the intermittent nature of renewable energy sources (RES) in hybrid renewable energy systems (HRES) by developing an improved control scheme utilizing an Artificial Neural Network (ANN)-based supercapacitor (SC). The research focuses on mitigating power fluctuations and enhancing system stability through the intelligent management of SC charge and discharge. The ANN control scheme is designed to learn and adapt to the dynamic behavior of the HRES, optimizing power flow under varying environmental conditions. By leveraging the high-power density and fast response of SCs, coupled with the adaptive learning capabilities of ANNs, this approach aims to improve the reliability and efficiency of HRES operation. Simulation and analysis are conducted to evaluate the performance of the proposed control scheme, demonstrating its effectiveness in smoothing power fluctuations and enhancing system stability. The results highlight the potential of ANN-based SC control for advancing the integration of RES into power grids, contributing to a more sustainable and reliable energy future. The conventional Battery Storage Limitations causes of power failure in development of a control scheme for a hybrid renewable energy system was 15%. Meanwhile, when an ANN BASED SUPERCAPACITOR was imbibed in the system, it decisively reduced it to13%. Thereby boosting constant power supply in the renewable energy. Finally, percentage improvement in development of a control scheme for a hybrid renewable energy system when an ANN BASED SUPERCAPACITOR was imbibed in the system was 2%.
Keywords
Control Scheme, Hybrid Renewable Energy System, Ann Based Supercapacitor
Full Text
This study addresses the challenges associated with the intermittent nature of renewable energy sources (RES) in hybrid renewable energy systems (HRES) by developing an improved control scheme utilizing an Artificial Neural Network (ANN)-based supercapacitor (SC). The research focuses on mitigating power fluctuations and enhancing system stability through the intelligent management of SC charge and discharge. The ANN control scheme is designed to learn and adapt to the dynamic behavior of the HRES, optimizing power flow under varying environmental conditions. By leveraging the high-power density and fast response of SCs, coupled with the adaptive learning capabilities of ANNs, this approach aims to improve the reliability and efficiency of HRES operation. Simulation and analysis are conducted to evaluate the performance of the proposed control scheme, demonstrating its effectiveness in smoothing power fluctuations and enhancing system stability. The results highlight the potential of ANN-based SC control for advancing the integration of RES into power grids, contributing to a more sustainable and reliable energy future. The conventional Battery Storage Limitations causes of power failure in development of a control scheme for a hybrid renewable energy system was 15%. Meanwhile, when an ANN BASED SUPERCAPACITOR was imbibed in the system, it decisively reduced it to13%. Thereby boosting constant power supply in the renewable energy. Finally, percentage improvement in development of a control scheme for a hybrid renewable energy system when an ANN BASED SUPERCAPACITOR was imbibed in the system was 2%.