A Survey of Methods and Architectures for Energy Management in Smart Grids Using IoT and Price-Based Demand Response with a Hybrid FHO-RERNN Approach

Abstract

The rapid evolution of smart grid technologies has transformed conventional power systems into intelligent, data-driven infrastructures capable of meeting growing energy demands. The integration of distributed energy resources, renewable systems, and Internet of Things (IoT) technologies enables real-time monitoring, communication, and control. However, challenges such as uncertain renewable generation, fluctuating demand, and system complexity require advanced energy management solutions.  This paper presents a comprehensive review of AI-driven and hybrid optimization approaches for smart grid energy management, with a focus on IoT-enabled systems and price-based demand response strategies. In particular, it highlights the hybrid Forest Herd Optimization–Recurrent Echo State Neural Network (FHO-RERNN) framework, which combines global optimization capability with efficient temporal modeling for improved forecasting and decision-making. The study examines architectures such as edge, fog, and cloud computing, along with pricing mechanisms including time-of-use and real-time pricing. Applications across residential, commercial, and industrial domains are analyzed using benchmark datasets. Key challenges such as data privacy, cybersecurity, and scalability are discussed, along with emerging trends like blockchain integration, federated learning, and digital twins, providing insights for developing intelligent and sustainable energy systems.