Economic Dispatch in Microgrids with Renewable Energy Resources Using Artificial Intelligence Techniques

Authors: Gwaivangmin, B.I., Bakare, G.A., Haruna, Y.S. And Amoo, A.L.

DOI Info: http://doi.org/10.5281/zenodo.14566237

ABSTRACT

This study addresses the global challenge of scarce and expensive electricity by investigating artificial intelligence techniques for optimizing economic load dispatch in microgrids with renewable energy sources. The study explores methods to minimize power generation costs within these systems. The analysis showed that a Hybrid Genetic Algorithm - Firefly Algorithm (HGA-FFA) approach emerges as the most cost-effective solution. HGA-FFA achieves the lowest total cost, significantly lower than competing methods. A Hybrid Genetic Algorithm - Particle Swarm Optimization (HGA-PSO) method proved to be a strong alternative, striking a balance between optimization complexity and cost. The traditional Genetic Algorithm (GA), while effective, exhibits the highest total cost, making it the least economical option among the three. Therefore, for minimizing economic load dispatch costs in similar microgrid scenarios, HGA-FFA is the optimal choice, followed by HGA-PSO. While GA remains a viable approach, its economic efficiency falls short of the hybrid methods.

Download Full Text