Node-Resource- and User-Demand-Aware Resource Allocation in NFV-enabled Elastic Optical Networks

Abstract

To solve the resource allocation problem for the scenario where node resources and users’ demands are heterogeneous in network function virtualization (NFV) more effectively and practically, we formulate this problem as an integer linear programming (ILP) model with weighted node importance and on-demand requests. Then we propose a node-resource- and user-demand-aware mapping (NUAM) algorithm with a specially designed virtual network functions (VNFs) reusing and deploying mechanism so as to reuse VNFs instances and reduce bandwidth consumption jointly. Simulation results show that the proposed NUAM algorithm can reduce bandwidth usage and adapt to users’ demands effectively compared with existing methods.