Deep Learning and GTO-Based Energy Management for IoT-Enabled Smart Buildings and Electric Vehicle Scheduling

Abstract

The rapid deployment of Internet of Things (IoT) technologies in large-scale buildings has transformed energy management by enabling real-time monitoring and intelligent control of complex systems. These buildings account for a significant share of global energy consumption, and the integration of distributed energy resources, electric vehicles, and demand response strategies introduces challenges in managing nonlinear, stochastic, and multi-objective energy systems efficiently. This paper presents a comprehensive review of IoT-enabled energy management systems, emphasizing the integration of deep learning techniques with the Giant Trevally Optimizer (GTO). Deep learning models such as CNNs, LSTMs, and reinforcement learning frameworks provide accurate forecasting and adaptive control, while GTO effectively handles multi-objective optimization problems involving cost minimization, peak load reduction, and renewable energy utilization. The synergy between predictive intelligence and metaheuristic optimization enhances decision-making for electric vehicle scheduling, distributed energy resource coordination, and demand response planning. Applications include vehicle-to-grid integration, load forecasting, and intelligent energy dispatch in smart buildings. Comparative studies show that combined deep learning and GTO frameworks outperform traditional methods in accuracy, efficiency, and convergence speed. However, challenges such as scalability, interoperability, and cybersecurity remain significant. This review highlights the potential of integrating IoT, deep learning, and advanced optimization techniques to develop sustainable and intelligent energy management solutions for large buildings.