On -Demand Placement and Scheduling of Virtual Network Functions with Software Requirements
Giovanne Marcelo dos Santos, Daniel Macêdo Batista · 2020
Virtual Network Functions (VNFs) can be combined together to meet several network services with reduced capital and operational expenditures. Given that the VNFs are virtualized, a network operator needs to solve two problems to efficiently deploy them: VNF placement and VNF scheduling. In this paper, we propose an algorithm to solve the two problems at the same time, placing and scheduling the VNFs on demand, and taking the software requirements into consideration, in a way that traditional distributed computing schedulers can be used. The proposed algorithm was evaluated via simulation against three other schedulers. Results showed that the algorithm is able to increase, by 19.7%, the number of completed VNFs in a scenario with 16540 VNFs being instantiated.