Akademik Veri Yönetim Sistemi
Rocznik Ochrona Srodowiska, cilt.27, ss.341-353, 2025 (SCI-Expanded)
This review study provides a comprehensive analysis of the application of metaheuristic algorithms in energy efficiency, demand-side management, and cost estimation. By systematically evaluating over 50 scientific studies published between 2020 and 2024, the paper classifies and analyzes the most frequently used algorithms, their advantages, and key application areas. The findings reveal that metaheuristic algorithms are most commonly applied in energy efficiency optimization (40%), cost reduction (37%), and load planning (23%). From a systems perspective, these algorithms are predominantly implemented in microgrids (27%), smart grids (25%), and power systems (18%). Among them, Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Ant Colony Optimization (ACO) emerge as the most frequently used due to their high performance in balancing energy demand, minimizing operational costs, and reducing carbon emissions. The analysis also shows that PSO-based models can reduce energy costs by up to 33%, while hybrid algorithms can increase the share of renewable energy use to over 50%. In demand-side management applications, certain algorithms effectively reduce peak loads and improve grid flexibility by dynamically adjusting consumption patterns. These results demonstrate that metaheuristic algorithms offer powerful tools for solving complex energy-related problems. The study contributes to the field by providing a structured, up-to-date literature mapping and highlighting opportunities for future research focused on sustainable and intelligent energy management.