A Survey of Methods and Architectures for Energy Management in Microgrids: A Hybrid Human Evolutionary Optimization Algorithm for Grid-Isolated Electric Vehicle Charging Systems

Abstract

The rapid expansion of renewable energy systems and electric vehicles (EVs) has increased the complexity of energy management in microgrids, particularly in grid-isolated environments. Microgrids integrate distributed energy resources, storage systems, and controllable loads to provide reliable and sustainable power. However, renewable energy intermittency and unpredictable EV charging demand create major challenges in maintaining system stability, efficiency, and cost-effectiveness. This survey reviews recent methods and architectures for microgrid energy management, focusing on hybrid human evolutionary optimization algorithms for grid-isolated EV charging systems. The study examines deterministic optimization methods, metaheuristic algorithms, artificial intelligence-based approaches, and distributed energy management frameworks. Traditional optimization techniques provide mathematical robustness but often struggle with uncertainty and dynamic operating conditions. In contrast, hybrid and bio-inspired optimization algorithms demonstrate better adaptability, robustness, and multi-objective optimization performance. Recent advancements also highlight the growing use of deep learning, reinforcement learning, multi-agent systems, and IoT-enabled frameworks for real-time energy management and decision-making. These intelligent approaches improve scalability, resilience, and charging efficiency in modern microgrids. Despite these developments, challenges such as computational complexity, real-time implementation, and large-scale deployment remain unresolved. Future research should focus on lightweight, scalable, and intelligent energy management architectures for next-generation microgrid systems.