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

• URL: http://arxiv.org/abs/2103.03817v1
• Date: Tue, 2 Feb 2021 21:40:35 GMT
• Title: Proactive and AoI-aware Failure Recovery for Stateful NFV-enabled Zero-Touch 6G Networks: Model-Free DRL Approach
• Authors: Amirhossein Shaghaghi, Abolfazl Zakeri (Student Member, IEEE), Nader Mokari (Senior Member, IEEE), Mohammad Reza Javan (Senior Member, IEEE), Mohammad Behdadfar and Eduard A Jorswieck (Fellow, IEEE)
• Abstract summary: We propose a model-free deep reinforcement learning (DRL)-based proactive failure recovery framework called zero-touch PFR (ZT-PFR) ZT-PFR is for the embedded stateful virtual network functions (VNFs) in network function virtualization (NFV) enabled networks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we propose a model-free deep reinforcement learning (DRL)- based proactive failure recovery (PFR) framework called zero-touch PFR (ZT-PFR) for the embedded stateful virtual network functions (VNFs) in network function virtualization (NFV) enabled networks. To realize the ZT-PFR concept, sequential decision-making based on network status is necessary. To this end, we formulate an optimization problem for efficient resource usage by minimizing the defined network cost function including resource cost and wrong decision penalty. Inspired by ETSI and ITU, we propose a novel impending failure model where each VNF state transition follows a Markov process. As a solution, we propose state-of-the-art DRL-based methods such as soft actor-critic and proximal policy optimization. Moreover, to keep network state monitoring information at an acceptable level of freshness in order to make appropriate decisions, we apply the concept of the age of information (AoI) to strike a balance between the event and scheduling-based monitoring. Several simulation scenarios are considered to show the effectiveness of our algorithm and provide a fair comparison with baselines. Several key systems and DRL algorithm design insights for PFR are drawn from our analysis and simulation results. For example we use a hybrid neural network, consisting of long short time memory (LSTM) layers in the DRL agent structure, to capture impending failure time dependency.

Related papers

• Event-Triggered Reinforcement Learning Based Joint Resource Allocation for Ultra-Reliable Low-Latency V2X Communications [10.914558012458425]
  6G-enabled vehicular networks face the challenge ensuring low-latency communication (URLLC) for delivering safety-critical information in a timely manner. Traditional resource allocation schemes for vehicle-to-everything (V2X) communication systems rely on traditional decoding-based algorithms.
  arXiv  Detail & Related papers  (2024-07-18T23:55:07Z)
• Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning [69.00997996453842]
  We propose a deep Reinforcement Learning approach to learn a joint Admission Control and Resource Allocation policy for virtual network embedding. We show that HRL-ACRA outperforms state-of-the-art baselines in terms of both the acceptance ratio and long-term average revenue.
  arXiv  Detail & Related papers  (2024-06-25T07:42:30Z)
• DNN Partitioning, Task Offloading, and Resource Allocation in Dynamic Vehicular Networks: A Lyapunov-Guided Diffusion-Based Reinforcement Learning Approach [49.56404236394601]
  We formulate the problem of joint DNN partitioning, task offloading, and resource allocation in Vehicular Edge Computing. Our objective is to minimize the DNN-based task completion time while guaranteeing the system stability over time. We propose a Multi-Agent Diffusion-based Deep Reinforcement Learning (MAD2RL) algorithm, incorporating the innovative use of diffusion models.
  arXiv  Detail & Related papers  (2024-06-11T06:31:03Z)
• Intelligent Hybrid Resource Allocation in MEC-assisted RAN Slicing Network [72.2456220035229]
  We aim to maximize the SSR for heterogeneous service demands in the cooperative MEC-assisted RAN slicing system. We propose a recurrent graph reinforcement learning (RGRL) algorithm to intelligently learn the optimal hybrid RA policy.
  arXiv  Detail & Related papers  (2024-05-02T01:36:13Z)
• A Neuromorphic Architecture for Reinforcement Learning from Real-Valued Observations [0.34410212782758043]
  Reinforcement Learning (RL) provides a powerful framework for decision-making in complex environments. This paper presents a novel Spiking Neural Network (SNN) architecture for solving RL problems with real-valued observations.
  arXiv  Detail & Related papers  (2023-07-06T12:33:34Z)
• Performance Optimization for Variable Bitwidth Federated Learning in Wireless Networks [103.22651843174471]
  This paper considers improving wireless communication and computation efficiency in federated learning (FL) via model quantization. In the proposed bitwidth FL scheme, edge devices train and transmit quantized versions of their local FL model parameters to a coordinating server, which aggregates them into a quantized global model and synchronizes the devices. We show that the FL training process can be described as a Markov decision process and propose a model-based reinforcement learning (RL) method to optimize action selection over iterations.
  arXiv  Detail & Related papers  (2022-09-21T08:52:51Z)
• Depth-Optimized Delay-Aware Tree (DO-DAT) for Virtual Network Function Placement [3.5584529568201377]
  Network Function (NFV) has been identified as a solution, but several challenges must be addressed to ensure its feasibility. We present a machine learning-based solution to the Virtual Network (VNF) placement problem.
  arXiv  Detail & Related papers  (2020-06-02T17:18:20Z)
• Iterative Network for Image Super-Resolution [69.07361550998318]
  Single image super-resolution (SISR) has been greatly revitalized by the recent development of convolutional neural networks (CNN) This paper provides a new insight on conventional SISR algorithm, and proposes a substantially different approach relying on the iterative optimization. A novel iterative super-resolution network (ISRN) is proposed on top of the iterative optimization.
  arXiv  Detail & Related papers  (2020-05-20T11:11:47Z)
• Deep Adaptive Inference Networks for Single Image Super-Resolution [72.7304455761067]
  Single image super-resolution (SISR) has witnessed tremendous progress in recent years owing to the deployment of deep convolutional neural networks (CNNs) In this paper, we take a step forward to address this issue by leveraging the adaptive inference networks for deep SISR (AdaDSR) Our AdaDSR involves an SISR model as backbone and a lightweight adapter module which takes image features and resource constraint as input and predicts a map of local network depth.
  arXiv  Detail & Related papers  (2020-04-08T10:08:20Z)
• Machine Learning for Performance-Aware Virtual Network Function Placement [3.5558885788605323]
  We develop a machine learning decision tree model that learns from the effective placement of the various Virtual Network Function instances forming a Service Function Chain (SFC) The model takes several performance-related features from the network as an input and selects the placement of the various VNF instances on network servers with the objective of minimizing the delay between dependent VNF instances.
  arXiv  Detail & Related papers  (2020-01-13T14:08:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.