A Survey of Methods and Architectures for Optimal Scheduling of Distributed Energy Resources with an IoT-Enabled Smart Energy Management Device

Abstract

The increasing integration of distributed energy resources (DERs), including solar photovoltaic systems, wind turbines, battery energy storage, electric vehicles, and flexible loads, has transformed conventional power grids into intelligent and decentralized energy systems. However, the intermittent nature of renewable energy and dynamic load variations create significant challenges in optimal scheduling, energy balancing, and real-time decision-making. Conventional optimization techniques often struggle with scalability and computational complexity in large-scale smart grid environments. This survey comprehensively reviews recent methods and architectures for optimal scheduling of DERs within IoT-enabled smart energy management systems. It examines optimization techniques including particle swarm optimization, genetic algorithms, ant colony optimization, simulated annealing, and hybrid frameworks alongside artificial intelligence approaches such as convolutional neural networks, recurrent neural networks, long short-term memory networks, reinforcement learning, and deep reinforcement learning for forecasting and adaptive energy scheduling. The role of IoT-enabled smart energy management devices is analyzed in enabling real-time monitoring, decentralized control, edge computing, cloud-based optimization, and secure energy transactions. Applications across residential buildings, industrial facilities, microgrids, and smart cities are compared using metrics such as energy cost, computational efficiency, renewable utilization, reliability, and emission reduction. Finally, the survey identifies key challenges including uncertainty management, interoperability, cybersecurity, privacy, and scalability, while highlighting future directions involving digital twins, edge intelligence, blockchain integration, and AI-driven adaptive energy management frameworks for sustainable smart grids.