Distributed and Multi-Task Learning at the Edge for Energy Efficient Radio Access Networks

Abstract

The big data availability of Radio Access Network (RAN) statistics suggests using it for improving the network management through machine learning based Self Organized Network (SON) functionalities. However, this may increase the already high energy consumption of mobile networks. Multi-access Edge Computing can mitigate this problem; however, the machine learning solutions have to be properly designed for efficiently working in a distributed fashion. In this work, we propose distributed architectures for two RAN SON functionalities based on multi-task and gossip learning. We evaluate their accuracy and consumed energy in realistic scenarios. Results show that the proposed distributed implementations have the same performance but save energy with respect to their correspondent centralized versions and benchmark solutions. We conclude the paper discussing open research issues for this interesting emerging field.