Abstract
High connectivity and robustness are essential in distributed networks, ensuring resilience, efficient communication, and adaptability. Optimizing energy consumption is also crucial for sustaining energy-constrained networks and extending their operational lifespan. In this study, we introduce an Artificial Intelligence (AI)-enhanced self-organizing network model, where each adaptive node autonomously adjusts its transmission range to optimize network connectivity while lowering energy consumption. Building on our previous Hamiltonian-based methodology, which is designed to achieve globally optimized states of complete connectivity with minimal energy usage, this research integrates a Multi-Layer Perceptron (MLP)-based decision-making model at each node. By leveraging a dataset from the Hamiltonian approach, nodes independently learn and adapt transmission range based on local conditions, leading to emergent global behaviors characterized by high connectivity and resilience to structural disruptions. This distributed, AI-driven adaptability allows nodes to make context-aware range adjustments autonomously, enabling the network to maintain its optimized state over time. Simulation results show that AI-driven adaptive nodes achieve stable connectivity, robustness, and energy efficiency across different conditions, including static and mobile scenarios. This work contributes to the growing field of self-organizing networks by demonstrating AI's potential to enhance complex network design, fostering scalable, resilient, and energy-efficient distributed systems.