Modeling and Optimization of Microgrid Networks Using Renewable Energy Sources
Main Article Content
Abstract
This research focuses on the modeling and optimization of microgrid networks incorporating renewable energy sources (RES), specifically solar and wind power. Microgrids are increasingly recognized for their ability to enhance energy efficiency and reliability, particularly in decentralized energy systems. However, the variability of RES poses significant challenges to their stability and cost-effectiveness. To address this, advanced optimization techniques such as Genetic Algorithms (GA), Particle Swarm Optimization (PSO), and Artificial Neural Networks (ANN) were applied to optimize energy flow, minimize energy losses, and reduce operational costs in the microgrid. The results demonstrated that ANN-based optimization achieved the highest energy efficiency (88%), cost savings (13%), and reliability (99%). PSO and GA also showed notable improvements over the base model, though ANN was the most effective in handling the fluctuations inherent in RES generation. The findings suggest that integrating machine learning and optimization techniques into microgrid management systems can significantly enhance performance, supporting the transition to sustainable and resilient energy systems. Future research could explore hybrid optimization models, electric vehicle integration, and smart grid technologies to further improve microgrid scalability and efficiency.