Multi-objective energy management for standalone and grid-connected microgrid system with renewable energy sources using an IoT-enabled innovative framework

The integration of renewable energy sources (RES) such as wind, solar, and micro turbines into modern power systems presents significant challenges in energy resource scheduling. Efficient optimization is crucial for minimizing operational costs, improving system reliability, and ensuring effective incorporation of RES. This paper presents the Lotus Effect Optimization Algorithm (LEOA) combined with Feed-Forward Neural Networks (FFNN) for energy scheduling, referred to as LEF2NN. LEOA minimizes operational costs, while FFNN forecasts load demand. The method integrates multiple RES and optimizes energy storage usage, aiming to reduce operating power costs and improve energy management on both the generation and load sides, all while adhering to system constraints. The performance of the proposed LEF2NN strategy is compared with existing techniques, like Ant Lion Optimizer (ALO), Particle Swarm Optimization (PSO), and Salp Swarm Algorithm (SSA). In grid-connected mode, LEF2NN reduces operational costs to approximately $90 per hour, significantly outperforming SSA $120 per hour, ALO $300 per hour, and PSO $220 per hour. In standalone mode, LEF2NN achieves a cost of $0.72 per hour, lower than SSA $0.85 per hour, ALO $0.86 per hour, and PSO $0.88 per hour. These results demonstrate that optimized energy scheduling using LEOA and precise load forecasting by FFNN minimizes energy waste, reduces reliance on costly power sources, and improves system stability. Policymakers should consider such optimization frameworks to lower costs and enhance grid reliability.