IoT-Driven Smart Grid Control Using Holographic Convolutional Neural Networks for Renewable Energy and Electric Vehicles

Abstract

The rapid transformation of conventional power systems into smart grids has been driven by the integration of Internet of Things (IoT) technologies, renewable energy sources, and electric vehicles (EVs). These advancements require intelligent monitoring, control, and optimization techniques to ensure grid stability, reliability, and efficiency. This paper presents a systematic review of recent advances in IoT-driven control and monitoring of substations and smart grids, with a particular focus on the integration of renewable energy and EVs using Holographic Convolutional Neural Networks (HCNNs). Artificial intelligence (AI)-based approaches, including deep learning, reinforcement learning, and hybrid optimization models, are analysed for their effectiveness in real-time grid management, fault detection, and energy optimization. IoT-enabled systems facilitate real-time data acquisition and communication across grid components, improving operational efficiency and resilience. However, challenges such as data heterogeneity, energy variability, cybersecurity threats, and computational complexity persist. Comparative analysis indicates that hybrid AI models, particularly CNN-based architectures combined with optimization techniques, provide improved performance in handling dynamic grid conditions. The study also highlights emerging trends such as edge computing, digital twins, and AI-driven energy management systems. Finally, future research directions are identified to enhance scalability, security, and energy efficiency in next-generation smart grid systems.