FIPAM: Fuzzy Inference Based Placement and Migration Approach for NFV-Based IoTs

The advancement and spread of the Internet-of-Things (IoT) have massively been increased over a decade. With the widespread of IoT networks, it is becoming difficult to acquire and execute real-time data. Network function virtualization (NFV) provides a flexible and efficient solution for IoT-based applications and service management. NFV creates a virtualized environment that can run a large number of micro-services for different IoT applications by using the virtual network functions (VNFs) through placement and chaining. In this paper, we propose a novel fuzzy inference-based placement and migration (FIPAM) approach for placement and migration/chaining of VNFs to ensure that resource allocation is carefully carried out during VNF orchestration and embedding. Firstly, we formulate the VNF chaining and placement problem. Secondly, we propose a lightweight VNF placement solution that considers the underlying network conditions while making the placement decisions. A novel usage of fuzzy inference is proposed to optimize the chaining mechanism along with the dynamic instantiation of VNFs to meet specific service needs. Simulation results are shown to validate the superiority of the proposed algorithm over existing schemes.