Cost optimization in microgrids: artificial intelligence-powered solutions for advanced battery management and longevity

• Proposes an innovative microgrid optimization framework integrating advanced lithium-ion Battery Energy Storage Systems (BESS). • Applies AI-driven genetic algorithms (GA) to enhance battery performance, energy efficiency, and lifetime. • Simulation results in Python show up to 5% improvement in energy efficiency and 10% extension of battery lifetime. • Utilizes IoT and AI for real-time monitoring and dynamic energy management, improving system reliability and durability. • Achieves significant operational benefits, including 20% reduction in battery cycles and up to 10% energy cost savings through optimized SOC, temperature, and charge/discharge control. This paper proposes an Artificial Intelligence (AI)- and Internet of Things (IoT)-enabled Battery Management System (BMS) for cost optimization and performance enhancement in microgrids. The framework integrates genetic algorithms to optimize charge–discharge cycles while leveraging real-time IoT sensor data for predictive monitoring and control. Simulation results demonstrate a 5% improvement in energy efficiency, up to 10% extension in battery life, and a 20% reduction in charge–discharge cycles. In addition, the proposed approach achieved cost savings of up to 10% by optimizing State of Charge (SoC), temperature, and operational frequency. These findings highlight the potential of AI- and IoT-driven BMS solutions to enhance the sustainability, reliability, and economic viability of microgrid energy storage systems.