PRIME-Q: Privacy Aware End-to-End QoS Framework in Multi-Domain SDN

Joshi, Kalpana D and Kataoka, Kotaro (2019) PRIME-Q: Privacy Aware End-to-End QoS Framework in Multi-Domain SDN. In: IEEE Conference on Network Softwarization (NetSoft), 24-28 June 2019, Paris, France.

Full text not available from this repository. (Request a copy)

Abstract

This paper presents the privacy preserving End-to-End (E2E) Quality of Service (QoS) mechanism in multi-domain Software Defined Network (SDN). Guaranteed E2E QoS needs complete information about the network. But, in multi-domain SDN, information sharing among different operators mainly have privacy and security issues; thus, operators may not share such network information. Moreover, such information collection is not only computationally expensive but also it requires a lot of message exchange between the domain controllers. Hence, we propose PRIME-Q, a PRIvacy aware E2E QoS framework in Multi-domain SDN. In PRIME-Q, instead of collecting the required information about the network at a single location, the data is distributively processed, and only the binary decision is reported at a single point to take the final decision about E2E QoS. To quantify the gain of PRIME-Q, we define Privacy Index to measure the privacy of E2E QoS coordination in multidomain SDN. The results show that the learning approach of PRIME-Q can achieve the required E2E QoS with maximum privacy. Further, the numerical results for PRIME-Q show a significant reduction in the communication and computation overhead in the network.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Kataoka, KotaroUNSPECIFIED
Item Type: Conference or Workshop Item (Paper)
Subjects: Computer science
Divisions: Department of Computer Science & Engineering
Depositing User: Team Library
Date Deposited: 03 Sep 2019 04:03
Last Modified: 03 Sep 2019 04:03
URI: http://raiithold.iith.ac.in/id/eprint/6092
Publisher URL: http://doi.org/10.1109/NETSOFT.2019.8806645
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 6092 Statistics for this ePrint Item