Distributed Multi-Hop Traffic Engineering via Stochastic Policy Gradient Reinforcement Learning

Pinyoanuntapong, Pinyarash; Lee, Minwoo; Wang, Pu

doi:10.1109/globecom38437.2019.9013134

Cited by 6 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [10], the authors presented a distributed multi-agent based TE solution to learn the optimal routing policy for the multi-path routing. The authors formulated the multi-path routing problem as a multi-agent Markov decision problem and proposed a multi-agent actor-critic technique where each router functions as a local actor and critic.…”

Section: Minimize E2e Delay and Efficiently Load Balancingmentioning

confidence: 99%

Toward Experience-Driven Traffic Management and Orchestration in Digital-Twin-Enabled 6G Networks

Tariq¹,

Naeem²,

Poor³

2022

Preprint

View full text Add to dashboard Cite

The envisioned 6G networks are expected to support extremely high data rates, low-latency, and radically new applications empowered by machine learning. The futuristic 6G networks require a novel framework that can be used to operate, manage, and optimize its underlying services such as ultra-reliable and low-latency communication, and Internet of everything. In recent years, artificial intelligence (AI) has demonstrated significant success in optimizing and designing networks. The AI-enabled traffic orchestration can dynamically organize different network architectures and slices to provide quality of experience considering the dynamic nature of the wireless communication network. In this paper, we propose a digital twin enabled network framework, empowered by AI to cater the variability and complexity of envisioned 6G networks, to provide smart resource management and intelligent service provisioning. Digital twin paves a way for achieving optimizing 6G services by creating a virtual representation of the 6G network along with its associated communication technologies (e.g., intelligent reflecting surfaces, terahertz and millimeter communication), computing systems (e.g., cloud computing and fog computing) with its associated algorithms (e.g., optimization and machine learning). We then discuss and review the existing AI-enabled traffic management and orchestration techniques and highlight future research directions and potential solutions in 6G networks.

show abstract

Section: Minimize E2e Delay and Efficiently Load Balancingmentioning

confidence: 99%

Toward Experience-Driven Traffic Management and Orchestration in Digital-Twin-Enabled 6G Networks

Tariq¹,

Naeem²,

Poor³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…QFLOW [25] , LEARNET [26] , multi-hop routing [27] , SDN RL [28] , TCP-DRINC [29] QFLOW [25] is a platform for RL-based edge network configuration that uses queuing, learning, and scheduling to meet the quatily of experience of video streaming applications.…”

Section: Network Traffic Controlmentioning

confidence: 99%

“…LEARNET [26] makes use of RL for flow control in timesensitive deterministic networks. In multi-hop routing [27] , a distributed model-free solution based on stochastic policy gradient RL was proposed, which aims to minimize the E2E delay by allowing each router to send a packet to the next-hop router according to the learned optimal probability.…”

Section: Network Traffic Controlmentioning

confidence: 99%

Model-based reinforcement learning for router port queue configurations

Kattepur¹,

David

Mohalik³

2021

Intell. and Converged Netw.

View full text Add to dashboard Cite

“…The generic framework is composed of a universal agentbased interaction environment, which is an expansive buildup system that pools together and supports the implementation of a diversity of various algorithms [163][164] [165]. The universal agent-based interaction environment is devised to support the use of various DL algorithmic techniques such as deep Q-learning and double Q-learning.…”

Section: Rt+1mentioning

confidence: 99%

AI-Assisted Framework for Green-Routing and Load Balancing in Hybrid Software-Defined Networking: Proposal, Challenges and Future Perspective

et al. 2020

View full text Add to dashboard Cite

The explosive growth of IP networks, the advent of cloud computing, and the rapid progress in wireless communications witnessed today reflect significant progress towards meeting the explosive data traffic demands. Consequently, communications service providers should deploy efficient and intelligent network solutions to accommodate the huge traffic demands and to ease the capacity pressure on their network infrastructure. Besides, vendors should develop novel energy-efficient networks to reduce network utility costs and carbon footprint. Software-defined networking (SDN) provides a suitable solution, however, complete SDN deployment is currently unachievable in the short-term. An alternative is the hybrid SDN/ open shortest path forwarding (OSPF) network, which allows the deployment of SDN in legacy networks. Nevertheless, hybrid SDN/OSPF also faces several technical, economic and organizational challenges. Although many energyefficiency routing solutions exist in hybrid SDN/OSPF networks, they are generic and reactive by design. Moreover, these solutions are characterized by manual control plane forwarding configurations, leading to sub-optimal performance. The recent promising combination of SDN and artificial intelligence (AI) techniques such as machine learning (ML) and deep learning (DL) in traffic management and control provides tremendous opportunities. In this paper, we first provide a review of the most recent optimization approaches for global energy-efficient routing and load balancing. Next, we investigate a scalable and intelligent integrated architectural framework that leverages deep reinforcement learning (DRL) techniques to realize predictive and rate adaptive energy-efficient routing with guaranteed quality of service (QoS), in transitional hybrid SDN/OSPF networks. Based on the need to minimize global network energy consumption and improve link performance, this paper provides key research insights into the current progress in hybrid SDN/OSPF, ML and AI in the hope of stimulating more research.

show abstract

Distributed Multi-Hop Traffic Engineering via Stochastic Policy Gradient Reinforcement Learning

Cited by 6 publications

References 11 publications

Toward Experience-Driven Traffic Management and Orchestration in Digital-Twin-Enabled 6G Networks

Toward Experience-Driven Traffic Management and Orchestration in Digital-Twin-Enabled 6G Networks

Model-based reinforcement learning for router port queue configurations

AI-Assisted Framework for Green-Routing and Load Balancing in Hybrid Software-Defined Networking: Proposal, Challenges and Future Perspective

Contact Info

Product

Resources

About