An End-to-End Programmable Platform for Dynamic Service Creation in 5G Networks

Latency-Aware Resource Orchestration in SDN-Based Packet Over Optical Flexi-Grid Transport Networks

“…Every experimental point is realized with 1000 requests following a Poisson process VNF-FG Req whose mean inter-arrival time is set to 25s and the duration (holding time, HT) is exponentially modelled varying its mean to 100, 150, 200, 250, 300 and 350 s. This provides different offered traffic loads (expressed in Er): 4, 6, 8, 10, 12 and 14. The requirements of each VNF-FG Req are generated as follows: the number of VMs per DC is uniformly distributed between [1,5]; the IT resources (i.e., CPU, RAM and Disk) are randomly chosen in the ranges of [1,4] cores, [1,6] GB and [4,10,20,40] GB, respectively; the demanded bandwidth (bw) is randomly selected among [10, 40, 100] Gb/s, and the latency (l) is in the range of [8,15] ms. The 5 DCs have different sizes and cloud resource characteristics.…”

“…The possibility of dynamically provisioning network slices is attracting a lot of interest from network and service operators and standardization organizations [6] eager to leverage its high flexibility, rapidity and cost-effectiveness when deploying network services [7] [8]. However, the above softwarization capabilities are at the expenses of imposing a burden on the DCs and on the (metro and core) network interconnecting the DCs.…”