Publication Type : Journal Article
Thematic Areas : Wireless Network and Application
Publisher : EAI Endorsed Transactions on Cloud Systems, EAI.
Source : EAI Endorsed Transactions on Cloud Systems, EAI, volume (5), number (14), 2019
Url : https://eudl.eu/doi/10.4108/eai.15-3-2019.162140
Keywords : 5G networks, machine learning, radio link manager, scheduler, mission critical services
Campus : Amritapuri
School : School of Engineering
Center : Amrita Center for Wireless Networks and Applications (AmritaWNA)
Department : Electronics and Communication, Wireless Networks and Applications (AWNA)
Year : 2019
Abstract : Next generation networks or 5G will be “network of networks” that can support ultra-reliable and low latency communication, high data rate, huge connectivity and high security. Network transformation stirring towards virtualized Radio Access Network (v-RAN) and intelligent resource management are foreseen as key solutions to realise such varied 5G requirements. Effective Radio Resource Management (RRM) is crucial for Mission Critical (MC) services to underpin communication between smartphone, massive machines and tiny sensor devices. The paper explores pioneering research related to architecture and intelligent RRM that helps Service Providers (SPs) to design reference framework of an advanced Radio Link Manager (RLM) enabled by Machine Learning (ML). One example optimization for commercial network/Long Term Evolution (LTE) and some preliminary results are analysed to understand the reference framework. The paper addresses the general reference architecture framework of advanced Radio Link Manager to support Mission Critical services in 5G. The paper also discusses about the ongoing standardisation activities and open source initiatives in 5G RAN.