Latency Aware VNF Deployment at Edge Devices for IoT Services: An Artificial Neural Network Based Approach

Abstract

Virtual Network Functions (VNFs) placed at the edge devices in the vicinity of users improve response time, avoid redundant utilization of core network, and reduce user-to-VNF end to end latency to a great extent, while leveraging the Internet of Things (IoT) services in Network functions virtualization (NFV) context. Different approaches for VNF placement have been proposed, however, the main concern has been to minimize resource utilization as much as possible by reducing the required number of servers to run a chain of VNFs to provide a specific service, without considering network conditions, for example, latency. In this paper, we implement the optimal edge VNF placement problem as an Integer Linear Programming model that guarantees the minimum end to end latency, while ensuring Quality of Service by not overstepping beyond an acceptable limit of latency violation. Latency beyond such limits can be the cause of disruption and degradation of performance for time-sensitive IoT services. The time complexity of the existing optimal edge VNF placement algorithm being NP-hard, we further propose a VNF placement strategy using Artificial Neural Network (ANN) trained by the assignment solutions generated from the Integer Linear Programming (ILP) model of the optimal edge VNF placement method for smaller instances of VNFs. This approach solves the VNF assignment problem at edge devices for a larger number of VNFs, while reducing the time complexity to be linear and providing similar results as the ILP model in terms of latency. This research work can be considered as a pioneering mark for IoT virtual service orchestration systems by embedding intelligence that can scale down the massive fabrication costs of IoT endpoints (e.g., sensors, actuators) required to be equipped with high processing power to enable ultra-low response time for users.