Scalable explicit path control in software-defined networks. (1st September 2019)

• Record Type: Journal Article
• Authors: Luo, Long; Yu, Hongfang; Luo, Shouxi; Ye, Zilong; Du, Xiaojiang; Guizani, Mohsen
• Is Part Of: Journal of network and computer applications. Volume 141(2019)
• Page Start: 86
• Page End: 103
• Publication Date: 2019-09-01
• Subjects: Software-defined networks -- Scalability -- Explicit path control -- Segment routing; Microcomputers -- Periodicals; Computer networks -- Periodicals; Application software -- Periodicals; Micro-ordinateurs -- Périodiques; Réseaux d'ordinateurs -- Périodiques; Logiciels d'application -- Périodiques; Application software; Computer networks; Microcomputers; Periodicals; 004.05; 004
• DOI: 10.1016/j.jnca.2019.05.014
• Languages: English
• ISSNs: 1084-8045

Abstract

Abstract: In this paper, we present a scalable PAth COntrol (PACO) approach to meet the increasing demands of fine-grained and explicit paths in Software-Defined Networks. PACO builds upon Segment Routing and adopts the pathlet segment as the building blocks for constructing network paths. By proactively generating and pre-installing a small collection of segments in networks, PACO can explicitly and quickly set up a massive number of reactive paths by simply concatenating these segments. We theoretically investigate the proactive segment generation as well as the optimal concatenation for reactive paths and propose efficient algorithms based on the optimal solutions for each of them. Extensive simulations show that PACO outperforms the state-of-the-art SR-based approach by supporting more than 40 % explicit paths and achieves a substantial reduction in switch memory (up to 94 % ) compared with the OpenFlow-based approach.