z-TORCH: An Automated NFV Orchestration and Monitoring Solution

TL;DR

This paper introduces z-TORCH, an automated NFV orchestration system that uses machine learning to optimize resource placement and monitoring, improving decision quality while reducing monitoring load in large-scale NFV environments.

Contribution

The paper presents a novel machine learning-based framework for jointly optimizing NFV orchestration and monitoring to enhance decision quality and minimize monitoring costs.

Findings

Near-optimal VNF placement achieved

Reduced monitoring load without compromising QoD

Enhanced performance in large-scale NFV environments

Abstract

Autonomous management and orchestration (MANO) of virtualized resources and services, especially in large-scale Network Function Virtualization (NFV) environments, is a big challenge owing to the stringent delay and performance requirements expected of a variety of network services. The Quality-of-Decisions (QoD) of a Management and Orchestration (MANO) system depends on the quality and timeliness of the information received from the underlying monitoring system. The data generated by monitoring systems is a significant contributor to the network and processing load of MANO systems, impacting thus their performance. This raises a unique challenge: how to jointly optimize the QoD of MANO systems while at the same minimizing their monitoring loads at runtime? This is the main focus of this paper. In this context, we propose a novel automated NFV orchestration solution, namely z-TORCH (zero Touch Orchestration) that jointly optimizes the orchestration and monitoring processes by exploiting machine-learning-based techniques. The objective is to enhance the QoD of MANO systems achieving a near-optimal placement of Virtualized Network Functions (VNFs) at minimum monitoring costs.