|
Original research CONGESTION CONTROL FOR MMTC IN 5G CELLULAR IOT NETWORKS - A REVIEW OF REINFORCEMENT LEARNING AND NETWORK SLICING APPROACHESPages 133-138 Abstract
Massive Machine Type Communications (mMTC) is one of 3 foundations of the Next Generation Networks (NGN). This inherent support that enables the Internet of Things (IoT) paradigm presents a significant challenge for cellular networks due to the sheer number of connected devices. MTC traffic is sporadic, and a simultaneous network access by these devices at time t0 can lead to a crippling congestion situation. The resultant service degradation cannot be tolerated in 5G network, which aims to provide ultra-reliable and low latency communications (URLLCs) and high Quality of Experience (QoE).
This paper reviews recent research efforts on addressing congestion management for mMTC in 5G Ultra- Dense Networks (UDN). Various approaches in literature are explored such as adaptive congestion control mechanisms, Reinforcement Learning, Resource Allocation Algorithms and data aggregation for mMTC traffic. The primary focus will be on Machine Learning Based solutions alongside network slicing.
This paper aims to provide a comprehensive overview of the diverse approaches to managing congestion in mMTC, synthesizing the literature and organizing them under key headings, identifying trends, open issues and future research directions.
Keywords: 5G, mMTC, Reinforcement Learning, Congestion..
|
Nathaniel Nyakotey 
PDF 