DRL-QOR: Deep Reinforcement Learning-Based QoS/QoE-Aware Adaptive Online Orchestration in NFV-Enabled Networks

Chen, Jing; Chen, Jia; Zhang, Hongke

doi:10.1109/tnsm.2021.3055494

Cited by 45 publications

(14 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The number of VNFs per SFC is set to a random number within [2,4], and the required bandwidth is set to be randomly distributed between [1,4] Gbps. For the convenience of the experiment, the BRC of each type of VNF is set to 2 units of computing resources.…”

Section: Sfc Request Settingmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid reconfiguration strategy for optimize service cost in NFV environment

Xu¹,

Shi²,

Huang³

2023

International Conference on Signal Processing and Communication Technology (SPCT 2022)

View full text Add to dashboard Cite

When using Network Function Virtualization (NFV) technology, the deployment of Virtual Network Function (VNF) is dynamic and fast. The time-varying nature of service requests from users requires the resource allocation of the underlying infrastructure to be flexible in response to changes. If only horizontal scaling is used to dynamically add or delete virtual machine (VM) copies, it will lead to over-provisioning of some unnecessary resources and high reconfiguration costs, so how to effectively use the reconfiguration method to reduce resource consumption and reducing the corresponding reconfiguration cost is challenging. Therefore, this paper adopts a Hybrid Reconfiguration Strategy (HRS) that jointly considers horizontal scaling and vertical scaling to reduce the resource consumption and reconfiguration cost of VNF deployment, and establishes a corresponding integer linear programming model. Experimental results show that compared with existing methods, the total cost can be reduced, while ensuring a higher acceptance rate of service requests.

show abstract

Section: Sfc Request Settingmentioning

confidence: 99%

“…How to determine the placement of VNFs to meet business requirements and quality of service (QoS) has been proven to be an NP-hard problem [4]. Cohend et al [5] aimed to find a solution that minimizes VNF connection and deployment costs.…”

Section: Introductionmentioning

confidence: 99%

Hybrid reconfiguration strategy for optimize service cost in NFV environment

Xu¹,

Shi²,

Huang³

2023

International Conference on Signal Processing and Communication Technology (SPCT 2022)

View full text Add to dashboard Cite

show abstract

“…An efficient approach to capturing the dynamic network state transitions and orchestrating SFCs with various requirements is the implementation of reinforcement learning. For instance, Chen et al 26 proposed a QoS/QoE (Quality of Experience)‐aware adaptive online orchestration approach that uses deep reinforcement learning to adapt to the real‐time variations in network state. Troia et al 27 developed a reinforcement learning system for optimizing resource allocation of SFCs in a multilayer network, where for the given network state and historical traffic traces, a reinforcement learning agent decides whether and when to reconfigure the SFCs.…”

Section: Related Workmentioning

confidence: 99%

SARM: Service function chain active reconfiguration mechanism based on load and demand prediction

Cai

Qian

Luo

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Network function virtualization is a promising technology for providing personalized services via agile service function chains (SFCs). Flexible SFC orchestration and rational resource allocation are pivotal for improving the SFC's quality of service (QoS). However, the requirements for computational load and resources have frequently been changing. Consequently, static resource allocation can result in resource insufficiency when SFCs turn busy and resource waste due to resource overplus when SFCs are idle. Since a dynamic resource allocation is necessary, the existing dynamic resource allocation methods' responses have often been delayed. This paper proposes an SFC active reconfiguration mechanism (SARM) based on computational load and resource demand. The SARM predicts nodes' computation loads and SFCs' resource demands and uses these predictions to estimate future QoS and develop the SFC reconfiguration strategy. The SARM considers multiple factors and applies a heuristic algorithm to achieve the tradeoff between migration cost and QoS preservation. The experiments demonstrate that the SARM can effectively predict the nodes' load and the resource demand of SFCs. In addition, the SARM can successfully identify the SFCs to reconfigure and reduce the QoS maintenance costs. The simulation results indicate that the average delays of the SFCs can be reduced by at least 26%.

show abstract

“…In [31], a novel resource allocation model was proposed to allocate resources and reduce latency. In [32], a reinforcement learning-based quality-of-service cognitive adaptive online orchestration method was proposed to adjust the real change of network. In [33], a novel reinforcement learning optimal framework was proposed to ensure good experience of playing.…”

Section: Related Workmentioning

confidence: 99%

Quality Evaluation of Online Mental Health Education Based on Reinforcement Learning in the Pandemic

Zhang

2021

Discrete Dynamics in Nature and Society

View full text Add to dashboard Cite

The COVID-19 pandemic has become one of the biggest major health crises reported due its massive impact on many countries. From mental health experts, we know that we cannot lose sight of an equally alarming issue which is the long-term mental health impact the pandemic is going to leave on the society. The rapid spread of the pandemic gives little chance to prepare for or even process all that has happened in terms of job losses and the complete uprooting of everyday life and relationships. It is understandable that students may feel irritable, frustrated, or sad sometimes. Loneliness, confusion, and anxiety are also common, but the issue is how we can know if students’ emotions are a normal reaction to an abnormal situation. Therefore, online mental health education has become pretty important for students during the pandemic. Furthermore, it is important to evaluate the quality of online mental health education through microlessons. In this paper, based on Q-learning algorithm, the real-time adaptive bitrate (ABR) configuration parameters mechanism is proposed to detect the changes of network state constantly and select the optimal precalculated configuration according to the current network state. The simulation results show that the proposed algorithm based on Q-learning outperforms other baselines in average latency, average bitrate, and Mean Opinion Score (MOS) on Chrome DevTools and Clumsy. Meanwhile, the experimental results also reveal that the average number of identified mental health problems of the proposed mechanism has always been the best with the bandwidth from 10 Mbit/s to 500 Mbit/s.

show abstract

DRL-QOR: Deep Reinforcement Learning-Based QoS/QoE-Aware Adaptive Online Orchestration in NFV-Enabled Networks

Cited by 45 publications

References 35 publications

Hybrid reconfiguration strategy for optimize service cost in NFV environment

Hybrid reconfiguration strategy for optimize service cost in NFV environment

SARM: Service function chain active reconfiguration mechanism based on load and demand prediction

Quality Evaluation of Online Mental Health Education Based on Reinforcement Learning in the Pandemic

Contact Info

Product

Resources

About