Application of Machine Learning to Next-Generation Communication Protocols for IoT and 5G Network

Authors- Abayomi I. O. Yussuff, Oluwafemi S. Adeleke, Kehinde G. Adekusibe

Abstract-The rapid expansion of the Internet of Things (IoT) and the deployment of 5G network call for advanced communication protocols capable of meeting the stringent demands of diverse applications. 5G network slicing— categorized into enhanced Mobile Broadband (eMBB), Ultra-Reliable Low- Latency Communication (URLLC), and massive Machine-Type Communication (mMTC) enables customized network services for different uses. However, existing protocols struggle to address the complex requirements of these slices, suchas low latency, high throughput, reliability, and scalability. This research proposed next- generation communication protocols for IoT and 5G network slicing, leveraging Machine Learning (ML) to enhance adaptability and performance. ML techniques are applied for predictive traffic management, resource allocation, dynamic protocol optimization, and slice orchestration in real-time. By anticipating network behavior and adjusting protocol parameters proactively, the proposed approach ensures optimal Quality of Service (QoS) for eMBB, URLLC, and mMTC slices. The study evaluates the ML- augmented protocols through simulations, demonstrating improvements in latency, reliability, and network efficiency across heterogeneous IoT environments. This work laid a foundation for intelligent, adaptive communication frameworks that address the evolving needs of future IoT and 5G ecosystems.

DOI: /10.61463/ijset.vol.13.issue1.119