AI-Powered Dynamic Optimization of Mobile IoT Networks for Smart Cities and Industrial Applications

AI-Powered Optimization of Mobile IoT Networks for Smart Cities & Industries

Abstract

The development of the Internet of Things (IoT) technology enhanced communication through mobile gadgets to a great extent. Mobile IoT networks were however faced with the challenges of limited bandwidth, energy, and increasing demands of real-time processing. The problems in this area were solved by this study by providing improved networks using an AI-based solution in addition to packet aggregation and multiplexing. The dynamic framework proposed was made to be responsive to the mobile IoT systems where the devices were constantly moving between different zones and access points were changing resulting in handovers and fluctuating network conditions. The AI-based techniques monitored the activity of the network and dynamically adjusted the aggregation sizes and multiplexing procedures on the fly. The evaluation of the mobile IoT scenarios was throughput, latency, and energy consumption analysis. The experiments revealed that bandwidth overhead reduction, multiplexing, and real-time decision-making were facilitated by the use of AI systems because of packet aggregation. Typically, the solution has improved the efficiency of transmission, reduced energy usage and supported the performance enhancement of mobile IoT solutions. The project contributed to developing self-learning IoT applications, which will support the management of smart cities in the future, healthcare monitoring, and automation in industries.