Lyrebird Optimization Algorithm for Power Control in IoT-Integrated Smart Grid Systems

Le résumé fourni par la source

Smart Grid (SG) power control with Internet of Things (IoT) devices facilitates the seamless integration of Wind Turbines (WT), Photovoltaic (PV) systems and the grid, ensuring optimal power distribution and system stability. The use of IoT-enabled monitoring enhances the coordination of WT, PV and grid operations, allowing precise control of power flow for improved power quality. SG operation faces difficulties in achieving low Total Harmonic Distortion (THD) rates alongside high energy efficiency since RES has variable characteristics which demand accurate IoT-based management methods. In order to address these issues; this paper proposes an approach of Lyrebird Optimization Algorithm (LOA) for SG power control with IoT devices. The main goal is to minimize the THD and enhance efficiency in power utilization through IoT-based SG power management. LOA is utilized to optimize energy distribution by efficiently managing power flow, enhancing voltage regulation, and improving power stability. The proposed method undergoes implementation and evaluation using MATLAB against various existing approaches, such as Multi-Layered Deep Recurrent Neural Network (MLDRNN), Deer Hunting Optimization and Crow Search Algorithm and Deep Adaptive Recurrent Neural Network (DHOCSA-DARNN), Artificial Neural Network (ANN), Modified Elephant Herd Optimization Algorithm-Two-Stage Deep Dilated Multi-Kernel Convolutional Network (MEHOA- DDMKC) and Grey Wolf Optimizer-tuned Artificial Neural Network (GWO-ANN). The proposed LOA method reaches a THD of 1.8% while maintaining an efficiency of 99.2% which demonstrates its ability to improve power quality along with energy conversion.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.