A Proposal for End-to-End QoS Provisioning in Software-Defined Networks

Abstract

This paper describes a framework application for the control plane of a network infrastructure; the objective is to feature end-user applications with the capability of requesting at any time a customised end-to-end Quality-of-Service profile in the context of dynamic Service-Level-Agreements. Our solution targets current and future real-time applications that require tight QoS parameters, such as a guaranteed end-to-end delay bound. These applications include, but are not limited to, health-care, mobility, education, manufacturing, smart grids, gaming and much more. We discuss the issues related to the previous Integrated Service and the reason why the RSVP protocol for guaranteed QoS did not take off. Then we present a new signaling and resource reservation framework based on the cutting-edge network controller ONOS. Moreover, the presented system foresees the need of considering the edges of the network, where terminal applications are connected to, to be piloted by distinct logically centralised controllers. We discuss a possible inter-domain communication mechanism to achieve the end-to-end QoS guarantee.Copyright c 201x Institute of Advanced Engineering and Science.All rights reserved.Corresponding Author: Name: Francesco Lucrezia Affiliation: Polytechnic of Turin, Italy Address. Corso Duca degli Abruzzi, 24, 10129 Torino, Italy Email: francesco.lucrezia@polito.it INTRODUCTIONInternet service providers (ISPs) are striving to innovate their network infrastructures at the pace content providers do with their services. Digital contents are consumed by smart phones and sophisticated terminal stations that continuously evolve together with the applications they host. Interestingly enough, the evolution of the OverThe-Top (OTT) services is mainly happening without the aid of network service providers, within the best-effort data traffic channel in the access networks. Recently, a new plethora of applications requiring a RTT delay of around 1ms have been grouped under the hat of tactile-internet applications: a tactile sensor reads information and a connected system reacts with actuators seen by a human within 1 ms [1]. Although we are still far from achieving end-to-end RTT of around 1ms with wireless communications, ISPs need to be ready to re-architect their software control-plane in order to fully exploit the enormous potentials offered by their infrastructures. The goal of this paper is to present the design and a prototype implementation of a control-plane network application for provisioning dynamic end-to-end QoS profiles to end-user applications. The current adoption of distributed control algorithms forces the use of the same signaling protocol (e.g. RSVP, BGP-LS) in all the data-path nodes, not taking into account the resistances inevitably present between device vendors and between administrative domains. For this reason the Service-Level-Agreements (SLAs) between a service provider and its customers or between providers are still mainly static. Moreover, the experience has shown that the scal...

An Effective Hierarchical Control Plane for Software-Defined Networks Leveraging TOPSIS for End-to-End QoS Class-Mapping

“…The study in [26] provided a resource reservation framework for E2E QoS fulfillment for delay bound applications. Moreover, the significance of E2E QoS in various applications (such as smart grids, healthcare, education, mobility, gaming, and manufacturing) is discussed.…”

Two-level scheduling scheme for integrated 4G-WLAN network

“…Scenario 2 was the implementation of our proposed scheduling scheme, that included implementation in the converged 4G-WLAN network. In this scenario, we set the same priority level of Diffserv and QCI as in Scenerio 1 [20]. However, the proposed scheduling scheme was implemented based on allocated bandwidth ratios.…”

Integrated hybrid optical networking for 5G access networks

“…A number of researches have done in optical packet switched networks [9][10][11][12][13][14][15]. The papers focused on optimizing PLR by using different QoS differentiation policies and scheme of transport networks.…”