IRUS Total

Big data for autonomic intercontinental overlays

File Description SizeFormat 
RNN-based-overlay.pdfAccepted version960.32 kBAdobe PDFView/Open
Title: Big data for autonomic intercontinental overlays
Authors: Brun, O
Wang, L
Gelenbe, E
Item Type: Journal Article
Abstract: This paper uses big data and machine learning for the real-time management of Internet scale quality-of-service (QoS) route optimisation with an overlay network. Based on the collection of data sampled every 2 min over a large number of source-destinations pairs, we show that intercontinental Internet protocol (IP) paths are far from optimal with respect to QoS metrics such as end-to-end round-trip delay. We, therefore, develop a machine learning-based scheme that exploits large scale data collected from communicating node pairs in a multihop overlay network that uses IP between the overlay nodes, and selects paths that provide substantially better QoS than IP. Inspired from cognitive packet network protocol, it uses random neural networks with reinforcement learning based on the massive data that is collected, to select intermediate overlay hops. The routing scheme is illustrated on a 20-node intercontinental overlay network that collects some 2 × 106 measurements per week, and makes scalable distributed routing decisions. Experimental results show that this approach improves QoS significantly and efficiently.
Issue Date: 3-Feb-2016
Date of Acceptance: 10-Jan-2016
URI: http://hdl.handle.net/10044/1/44763
DOI: http://dx.doi.org/10.1109/JSAC.2016.2525518
ISSN: 1558-0008
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Start Page: 575
End Page: 583
Journal / Book Title: IEEE Journal on Selected Areas in Communications
Volume: 34
Issue: 3
Copyright Statement: © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Keywords: Science & Technology
Engineering, Electrical & Electronic
The Internet
big data
network quality of service (QoS)
smart overlays
random neural network
cognitive packet network
Networking & Telecommunications
0906 Electrical And Electronic Engineering
1005 Communications Technologies
0805 Distributed Computing
Publication Status: Published
Appears in Collections:Electrical and Electronic Engineering
Faculty of Engineering