面向海量机器类通信(mMTC)的无线接入控制

Access control for massive machine-type communications(mMTC)

近年来,支持物联网(internet of things,IoT)应用的机器类通信(machine-type communications,MTC)成为未来移动通信网络的重要业务组成部分。随着MTC对广域连接需求的快速增长,通过蜂窝网承载IoT应用成为必然的趋势,蜂窝物联网也成为下一代移动通信系统(5G)的重点技术之一。特别地,海量机器通信(massive MTC,mMTC)被定义为5G网络三大通用场景之一。传统的无线接入技术很难适应mMTC的需求,因此,面向mMTC的无线接入控制研究具有重要的研究意义。在简单介绍传统随机接入过程之后,总结分析了现有mMTC接入新技术,并指出现有技术方案在面对越来越复杂的应用场景下的局限性,而近年来兴起的基于人工智能(artificial intelligence,AI)的接入机制成了解决此问题最具潜力的技术方案之一。分析了AI用于接入控制的可行性,并提出了一种基于Q学习的mMTC智能接入点选择机制,为将来基于AI的mMTC接入控制研究提供新的思路和技术手段。

Recently,as a key enabler of IoT,Machine Type Communication(MTC)becomes one of the important services in future wireless mobile networks.MTC deployments are expected to grow exponentially with an increasing demand on broad range interconnectivity.IoT is moving toward an architecture based on cellular network infrastructures with wide area coverage,and hence Cellular IoT is a very promising technology in the next generation mobile communication system(5G).Especially,massive Machine Type Communication(mMTC)has been identified as one of the three generic5G services.It is hard for traditional radio access technologies to provide adequate services for meeting mMTC requirements,and radio access for mMTC services is an important research problem.In this paper,we first briefly introduce the traditional random access procedure,and then survey the existing mMTC access technologies.Moreover,it is hard to address the mMTC access problem by using conventional technical tools in the progressively complicated and service centric network environments.Artificial Intelligence(AI)based access mechanism has been deemed as one of the most promising solutions.We analyze the feasibility of exploiting AI tools for solving mMTC access control,and propose a Q learning based smart access point selection scheme for mMTC,with the aim of providing useful insights into future AI based access control research.