Proactive and AoI-aware Failure Recovery for Stateful NFV-enabled Zero-Touch 6G Networks: Model-Free DRL Approach

TL;DR

This paper introduces ZT-PFR, a proactive failure recovery framework for NFV-enabled 6G networks using model-free deep reinforcement learning, balancing resource costs and failure risks with novel failure prediction and information freshness techniques.

Contribution

It presents a new DRL-based proactive failure recovery framework with a novel impending-failure model and age of information concept for NFV-enabled networks.

Findings

DRL agents effectively predict failures and optimize recovery actions.

Hybrid neural networks improve failure prediction accuracy.

Proposed framework reduces network downtime and resource usage.

Abstract

In this paper, we propose a Zero-Touch, deep reinforcement learning (DRL)-based Proactive Failure Recovery framework called ZT-PFR for stateful network function virtualization (NFV)-enabled networks. To this end, we formulate a resource-efficient optimization problem minimizing the network cost function including resource cost and wrong decision penalty. As a solution, we propose state-of-the-art DRL-based methods such as soft-actor-critic (SAC) and proximal-policy-optimization (PPO). In addition, to train and test our DRL agents, we propose a novel impending-failure model. Moreover, to keep network status information at an acceptable freshness level for appropriate decision-making, we apply the concept of age of information to strike a balance between the event and scheduling based monitoring. Several key systems and DRL algorithm design insights for ZT-PFR are drawn from our analysis and simulation results. For example, we use a hybrid neural network, consisting long short-term memory layers in the DRL agents structure, to capture impending-failures time dependency.