Virtual machine placement for backhaul traffic minimization in fog radio access networks

With the advance of wireless technologies, the rapid mobile data traffic growth will lead to severe network resource consumption and exceptionally long latency to access services, especially for cloud-based applications. To tackle these issues, Fog Radio Access Network (F-RAN) is recently emerged for next generation cellular networks. F-RAN is considered as an extension of the cloud computing paradigm to the edge of the network and a highly virtualized platform that provides computing, storage, and network services for mobile devices. However, how to appropriately place virtual machines (VMs) into fog nodes in F-RAN systems is very challenging, and will significantly affect the bandwidth consumption of backhaul links. Thus this paper studies the replication-based VM placement problem, and aims at minimizing the total backhaul traffic generated by VM migrations and data transmissions. We observe that the VM placement operation should not be frequently executed and practically considers the problem in a long term aspect. Then we propose a heuristic algorithm to solve the problem. The simulation results agree our observation and show that compared with a greedy approach and an optimal algorithm, the proposed algorithm demonstrates with favorable results for the overall backhaul network usage.