CaltechAUTHORS
  A Caltech Library Service

Fine-grained, multi-domain network resource abstraction as a fundamental primitive to enable high-performance, collaborative data sciences

Xiang, Qiao and Zhang, J. Jensen and Wang, X. Tony and Liu, Y. Jace and Guok, Chin and Le, Franck and MacAuley, John and Newman, Harvey and Yang, Y. Richard (2018) Fine-grained, multi-domain network resource abstraction as a fundamental primitive to enable high-performance, collaborative data sciences. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis. IEEE , Piscataway, NJ, Art. No. 5. ISBN 978-1-5386-8384-2. http://resolver.caltech.edu/CaltechAUTHORS:20181120-141045120

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20181120-141045120

Abstract

Multi-domain network resource reservation systems are being deployed, driven by the demand and substantial benefits of providing predictable network resources. However, a major lack of existing systems is their coarse granularity, due to the participating networks' concern of revealing sensitive information, which can result in substantial inefficiencies. This paper presents Mercator, a novel multi-domain network resource discovery system to provide fine-grained, global network resource information, for collaborative sciences. The foundation of Mercator is a resource abstraction through algebraic-expression enumeration (i.e., linear inequalities/equations), as a compact representation of the available bandwidth in multi-domain networks. In addition, we develop an obfuscating protocol, to address the privacy concerns by ensuring that no participant can associate the algebraic expressions with the corresponding member networks. We also introduce a super-set projection technique to increase Mercator's scalability. Finally, we implement Mercator and demonstrate both its efficiency and efficacy through extensive experiments using real topologies and traces.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://dl.acm.org/citation.cfm?id=3291663PublisherArticle
ORCID:
AuthorORCID
Newman, Harvey0000-0003-0964-1480
Additional Information:© 2018 IEEE. The authors thank Kai Gao, Geng Li, Linghe Kong, Ennan Zhai, Alan Liu, Yeon-sup Lim and Haizhou Du for their help during the preparation of this paper. The authors also thank the anonymous reviewers for their valuable comments. This research is supported in part by NSFC grants #61702373, #61672385 and #61701347; China Postdoctoral Science Foundation #2017-M611618; NSF awards #1440745, #1246133, #1341024, #1120138, and #1659403; DOE award #DE-AC02-07CH11359; DOE/ASCR project #000219898; Google Research Award, and the U.S. Army Research Laboratory and the U.K. Ministry of Defence under Agreement Number W911NF-16-3-0001.
Funders:
Funding AgencyGrant Number
National Natural Science Foundation of China61702373
National Natural Science Foundation of China61672385
National Natural Science Foundation of China61701347
China Postdoctoral Science Foundation2017-M611618
NSFOAC-1440745
NSFOAC-1246133
NSFOAC-1341024
NSFPHY-1120138
NSFOAC-1659403
Department of Energy (DOE)DE-AC02-07CH11359
Department of Energy (DOE)000219898
GoogleUNSPECIFIED
Army Research Laboratory (ARL)W911NF-16-3-0001
Ministry of Defence (UK)UNSPECIFIED
Subject Keywords:Multi-domain networks, resource discovery, privacy preserving
Record Number:CaltechAUTHORS:20181120-141045120
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20181120-141045120
Official Citation:Qiao Xiang, J. Jensen Zhang, X. Tony Wang, Y. Jace Liu, Chin Guok, Franck Le, John MacAuley, Harvey Newman, and Y. Richard Yang. 2018. Fine-grained, multi-domain network resource abstraction as a fundamental primitive to enable high-performance, collaborative data sciences. In Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC '18). IEEE Press, Piscataway, NJ, USA, Article 5, 13 pages.
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:91092
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:20 Nov 2018 22:26
Last Modified:05 Apr 2019 22:11

Repository Staff Only: item control page