A cluster-based solution for Service Function Chain allocation in large scale infrastructure

Changes in telecommunication services demand the development of a new infrastructure to attend new network applications' requirements. The traditional approach to network functions running over dedicated equipment can no longer handle all the dynamics of these new services. The network function virtualization (NFV) paradigm decouples a function from the underlying dedicated hardware thus making networks more flexible and agile. A set of virtual network functions (VNFs) can be deployed as virtual machines or containers across common servers, and orchestrated to compose a service function chain (SFC).Despite the many benefits of NFV, it raises several challenges. SFC placement is a complex task, since it requires taking into consideration the characteristics of VNFs, the SFC requirements, and the state of network infrastructure. This poses a challenge for large scale networks. Information regarding network resources are stored in a large database, and retrieving such data in order to perform SFC placement according to some strategy can be a problem. Limited memory capacity and the presence of a large number of disk operations can compromise the performance of SFC placement algorithms and make it unfeasible. In addition, the amount of memory available to run the allocation algorithm may not be sufficient to load the large amount of information that describe the network resources (occasionally in the hundreds of gigabytes). We address this problem by using a cluster based solution that stores and retrieves data for large scale infrastructures in order to perform SFC placement. The results demonstrate that the use of clusters in the preprocessing step can drastically reduce the size of the resulting database, as well as the execution time to select candidate nodes for a scalable SFC allocation.