On Deep Reinforcement Learning for Traffic Engineering in SD-WAN

Troia, Sebastian; Sapienza, Federico; Vare, Leonardo; Maier, Guido

doi:10.1109/jsac.2020.3041385

Cited by 58 publications

(24 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SDN is expected to work at full capacity in 6G. Two future versions of SDN are Software-Defined Wide Area Network (SD-WAN) and Software-Defined Local Area Network (SD-LAN) [163], [164]. Like SDN, SD-WAN attempts to enhance network control performance and intelligence by separating the packet forwarding process (data plane) from the routing process (control plane).…”

Section: E Sd-wan Security: 6g Network Management Controlmentioning

confidence: 99%

Security and privacy for 6G: A survey on prospective technologies and challenges

Nguyen,

Lin,

Cheng

et al. 2021

Preprint

View full text Add to dashboard Cite

Sixth-generation (6G) mobile networks will have to cope with diverse threats on a space-air-ground integrated network environment, novel technologies, and an accessible user information explosion. However, for now, security and privacy issues for 6G remain largely in concept. This survey provides a systematic overview of security and privacy issues based on prospective technologies for 6G in the physical, connection, and service layers, as well as through lessons learned from the failures of existing security architectures and state-of-the-art defenses.Two key lessons learned are as follows. First, other than inheriting vulnerabilities from the previous generations, 6G has new threat vectors from new radio technologies, such as the exposed location of radio stripes in ultra-massive MIMO systems at Terahertz bands and attacks against pervasive intelligence. Second, physical layer protection, deep network slicing, quantum-safe communications, artificial intelligence (AI) security, platform-agnostic security, real-time adaptive security, and novel data protection mechanisms such as distributed ledgers and differential privacy are the top promising techniques to mitigate the attack magnitude and personal data breaches substantially.

show abstract

Section: E Sd-wan Security: 6g Network Management Controlmentioning

confidence: 99%

Security and privacy for 6G: A survey on prospective technologies and challenges

Nguyen,

Lin,

Cheng

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…We presented an active monitoring application, comprised of multiple software modules running on the CPEs, with the aim of measuring WAN performance, such as packet delay and loss, to route the network traffic efficiently. In [5], we proposed different kinds of traffic engineering applications, running over the SD-WAN controller, based on traditional and Machine Learning algorithms. We proved that Machine Learning is able to anticipate the WAN failures by proactively switching critical traffic flows on a different path.…”

Section: Introductionmentioning

confidence: 99%

“…The goal of this work is to build an experimental SD-WAN solution capable of running and optimizing delay-sensitive services, such as video streaming. Unlike our previous works, in this paper we present a monitoring system able to collect not only classical network statistics acquired from the CPEs, as in [2] and [5], but also real-time transport network statistics acquired directly from the servers (or hosts) that generate the network traffic. To do this, we exploit the extended Berkeley Packet Filter (eBPF) [6]: a revolutionary technology that can run programs into the Linux kernel without changing kernel source code or loading kernel modules.…”

Section: Introductionmentioning

confidence: 99%

Performance Evaluation of Overlay Networking for delay-sensitive services in SD-WAN

Troia

Mazzara

Zorello

et al. 2021

2021 IEEE International Mediterranean Conference on Communications and Networking (MeditCom)

Self Cite

View full text Add to dashboard Cite

A reliable Wide Area Network (WAN) has become an imperative need for enterprises with Cloud-hosted applications and distributed branch offices. Software-Defined Wide Area Network (SD-WAN) has been regarded as the most promising technological solution for next generation enterprise networks capable of increasing network agility and reducing costs. In this paper, we present an experimental SD-WAN solution capable of running and optimizing delay-sensitive services, such as VoIP and video streaming, while minimizing downtime caused by network failures. We validate our solution thanks to two SD-WAN testbeds: the first one is deployed in a municipal network of an Italian city, while the other is emulated in our laboratory. The goal is to show the capability of SD-WAN of guaranteeing fast recovery and resilience in case of network failures, exploiting an innovative eBPF-based monitoring technique.

show abstract

“…We presented an active monitoring application, comprised of multiple software modules running on the CPEs, with the aim of measuring WAN performance, such as packet delay and loss, to route the network traffic efficiently. In [4], we proposed different kinds of traffic engineering applications, running over the SD-WAN controller, based on traditional and Machine Learning algorithms. We proved that Machine Learning is able to anticipate the WAN failures by proactively switching critical traffic flows on a different path.…”

Section: Introductionmentioning

confidence: 99%

“…We proved that Machine Learning is able to anticipate the WAN failures by proactively switching critical traffic flows on a different path. Unlike our previous works, in this demo we present a monitoring system no longer based on network statistics acquired from the CPEs, as in [1] and [4], but on transport network statistics acquired directly from the servers (or hosts) that generate the network traffic. To do this, we exploit the extended Berkeley Packet Filter (eBPF) [5]: a revolutionary technology that can run programs into the Linux kernel without changing kernel source code or loading kernel modules.…”

Section: Introductionmentioning

confidence: 99%

Resiliency in SD-WAN with eBPF Monitoring: Municipal Network and Video Streaming Use Cases

Troia

Mazzara

Zorello

et al. 2021

2021 17th International Conference on the Design of Reliable Communication Networks (DRCN)

Self Cite

View full text Add to dashboard Cite

A reliable Wide Area Network (WAN) has become an imperative business for enterprises with Cloud-hosted applications and distributed branch offices. Software-Defined Wide Area Networking (SD-WAN) has been regarded as the promising technological solution for next generation enterprise networks capable of increasing network agility and reducing costs. In this demonstration, we present two SD-WAN testbeds: the first one is deployed in a municipal network of an Italian city, while the other is emulated in our laboratory. The goal is to show the capability of SD-WAN to guarantee service availability and resiliency in case of network failures, exploiting an innovative eBPF-based monitoring technique.

show abstract

On Deep Reinforcement Learning for Traffic Engineering in SD-WAN

Cited by 58 publications

References 27 publications

Security and privacy for 6G: A survey on prospective technologies and challenges

Security and privacy for 6G: A survey on prospective technologies and challenges

Performance Evaluation of Overlay Networking for delay-sensitive services in SD-WAN

Resiliency in SD-WAN with eBPF Monitoring: Municipal Network and Video Streaming Use Cases

Contact Info

Product

Resources

About