Towards In-Band Telemetry for Self Driving Wireless Networks

Jayagopal, Prabhu; Pinyoanuntapong, Pinyarash; Wang, Pu; Lee, Minwoo

doi:10.1109/infocomwkshps50562.2020.9162923

Cited by 5 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the release of initial speci cation, many applications of INT for network operations and management have been proposed, including for failure detection [252,253], congestion control [96] and tracking the data plane rules matched by the ows [95, 254], among others. Although INT was initially proposed for IP networks, several extensions of INT have been proposed such as for wireless networks [255] and multi-layer IP-over-Optical networks [256,257,258]. It is worth mentioning that INT is one of several concurrent e orts towards performing in-band network telemetry using live network tra c (cf.…”

Section: Softwarized Network Monitoringmentioning

confidence: 99%

Resource Management in Softwarized Networks

Chowdhury¹

2022

NOMS 2022-2022 IEEE/IFIP Network Operations and Management Symposium

View full text Add to dashboard Cite

This thesis consists of material all of which I authored or co-authored: see Statement of Contributions included in the thesis. This is a true copy of the thesis, including any required nal revisions, as accepted by my examiners.I understand that my thesis may be made electronically available to the public.iii Statement of ContributionsThis dissertation includes rst authored peer-reviewed materials that have appeared in journals and conference proceedings published by the Institute of Electrical and Electronics Engineers (IEEE). The IEEE's policy on reuse of published materials in a dissertation is as follows: "The IEEE does not require individuals working on a thesis to obtain a formal reuse license".The following list serves as a declaration of the Versions of Record for works included in this dissertation:

show abstract

Section: Softwarized Network Monitoringmentioning

confidence: 99%

Resource Management in Softwarized Networks

Chowdhury¹

2022

NOMS 2022-2022 IEEE/IFIP Network Operations and Management Symposium

View full text Add to dashboard Cite

show abstract

“…In addition, we need to realize distributed and programmable network control so that the MA-RL policies can be learned, deployed, and executed in a real-time fashion. To satisfy the above two requirements, we developed a federated networking subsystem by enhancing and customizing WiNOS, a distributed wireless network operating system proposed in our previous work [37]. The federated networking subsystem is composed of three layers (1) Dataplane, (2) Network Core services, and (3) RL Applications.…”

Section: Federated Networkingmentioning

confidence: 99%

“…The primary objective of our telemetry solution is to collect real-time experience of packets, such as per-hop delay over each traversing link or end-to-end link, in a cost-efficient manner. Towards this end, we have developed and implemented a distributed in-band telemetry system [37], where each router runs its own telemetry module built on the top of OpenFlow processing pipeline. Our inband telemetry system consists of a new telemetry packet header, two new packet matching actions (i.e., PUSHINTL and POPINTL) and the telemetry processor.…”

Section: Federated Networkingmentioning

confidence: 99%

EdgeML: Towards Network-Accelerated Federated Learning over Wireless Edge

Pinyoanuntapong¹,

Jayagopal²,

Balakrishnan³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Federated learning (FL) is a distributed machine learning technology for next-generation AI systems that allows a number of workers, i.e., edge devices, collaboratively learn a shared global model while keeping their data locally to prevent privacy leakage. Enabling FL over wireless multi-hop networks can democratize AI and make it accessible in a costeffective manner. However, the noisy bandwidth-limited multihop wireless connections can lead to delayed and nomadic model updates, which significantly slows down the FL convergence speed. To address such challenges, this paper aims to accelerate FL convergence over wireless edge by optimizing the multi-hop federated networking performance. In particular, the FL convergence optimization problem is formulated as a Markov decision process (MDP). To solve such MDP, multiagent reinforcement learning (MA-RL) algorithms along with domain-specific action space refining schemes are developed, which online learn the delay-minimum forwarding paths to minimize the model exchange latency between the edge devices (i.e., workers) and the remote server. To validate the proposed solutions, FedEdge is developed and implemented, which is the first experimental framework in the literature for FL over multihop wireless edge computing networks. FedEdge allows us to fast prototype, deploy, and evaluate novel FL algorithms along with RL-based system optimization methods in real wireless devices. Moreover, a physical experimental testbed is implemented by customizing the widely adopted Linux wireless routers and ML computing nodes. Such testbed can provide valuable insights into the practical performance of FL in the field. Finally, our experimentation results on the testbed show that the proposed networkaccelerated FL system can practically and significantly improve FL convergence speed, compared to the FL system empowered by the production-grade commercially-available wireless networking protocol, BATMAN-Adv. I. INTRODUCTION:Distributed machine learning, specifically federated learning (FL), has been envisioned as a key technology for enabling next-generation AI at scale. FL significantly reduces privacy risks and communication costs, which are critical in modern AI systems. FL allows workers (i.e., edge devices) to collaboratively learn a global model and maintains the locality

show abstract

AI-Driven Packet Forwarding With Programmable Data Plane: A Survey

Quan

Liu

et al. 2023

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

Towards In-Band Telemetry for Self Driving Wireless Networks

Cited by 5 publications

References 14 publications

Resource Management in Softwarized Networks

Resource Management in Softwarized Networks

EdgeML: Towards Network-Accelerated Federated Learning over Wireless Edge

AI-Driven Packet Forwarding With Programmable Data Plane: A Survey

Contact Info

Product

Resources

About