Artificial Intelligence Techniques for Energy Management in Smart Grids Using IoT and Price-Based Demand Response with a Hybrid FHO-RERNN Approach: Trends and Challenges

Abstract

The evolution of conventional power systems into intelligent and decentralized smart grids has driven the adoption of advanced computational techniques for efficient energy management, grid stability, and cost optimization. The integration of Artificial Intelligence (AI), Internet of Things (IoT), and price-based demand response (DR) has emerged as a key solution to address the increasing complexity of modern energy systems. IoT-enabled devices facilitate real-time monitoring and control; however, uncertainties in renewable energy generation and fluctuating demand present significant challenges, AI-driven approaches, particularly deep learning and hybrid optimization methods, have shown strong potential in overcoming these challenges. This paper reviews the integration of the Fire Hawk Optimization (FHO) algorithm with Enhanced Recurrent Neural Networks (RERNN), forming a hybrid FHO-RERNN framework for efficient energy scheduling and demand-side management. The approach enhances forecasting accuracy, supports optimal load scheduling, and enables adaptive decision-making in dynamic environments. The study also examines IoT architectures, pricing mechanisms such as time-of-use and real-time pricing, and the application of various AI techniques in smart grids. Key challenges, including data privacy, scalability, and computational complexity, are discussed along with future directions such as explainable AI, blockchain integration, and edge intelligence for sustainable energy systems.