Since it was originally proposed by Ahlswede et al. (2000), network coding (NC) has been the focus of many research efforts and proposals. In particular, NC has been put forward as a means to increase the capacity of wireless mesh networks, by exploiting the broadcast nature of wireless links. However, in spite of the fairly large number of papers on the subject of network coding, the impact of NC on TCP performance in wireless mesh networks is still not fully understood. By means of a thorough simulation study, this paper aims thus at providing insights about the interaction between TCP's congestion control mechanisms and the underlying NC done by wireless relays. In particular, we focus on the influence of the main parameters related to the coding buffer used by such relays to encode packets. Our results suggest the feasibility of devising engineering rules for setting such parameters. Another main conclusion, in line with previous preliminary findings by the authors (Hassayoun et al., 2010) is that TCP performance can indeed be improved by the use of NC, but only as long as the wireless channel quality is above a certain level.

Impact of network coding on TCP performance in wireless mesh networks

Modern mobile devices comprise multiple interfaces for heterogeneous network technologies. However, currently implemented mechanisms to decide which one(s) to use and distribute application flows accordingly (i.e., solving the multihomed flow management problem, MFM) are rather coarse and do not leverage the opportunities. A user-centric quality-aware (QA) MFM has been proposed which optimises network use based on user-perceivable metrics such as application quality as well as energy and monetary costs. This paper refines this approach by providing a single method for both real-time and elastic (i.e., TCP-based) traffic, and uses realistic available capacity estimation. We evaluate this method in OPNET-simulated LTE and WLAN mobile networks. We study the impact of methods used to trigger the decision algorithm, and investigate the influence of an increasing number of users employing the QA-MFM technique on both the user-perceivable metrics and the global network performance. We find that on-demand triggering performs better than a static periodic method. We also demonstrate that the proposed approach out-performs classical network selection techniques in terms of application quality. We also show that the QA-MFM is not too greedy as to not scale with a number of users, and has a positive effect on the network loads, by preemptively adapting applications parameters to match network conditions.

Evaluating user-centric multihomed flow management in multi-user scenarios

We implemented approaches to solve the multihomed flow management problem using the OPNET simulator. We formulate a quality-aware decision method as a binary integer problem and use it (with the CPLEX solver) to drive the network selection and flow distribution in the simulated scenarios. We compare the behaviour of application flows with our approach and the most commonly implemented nowadays. This allows us to more accurately evaluate these approaches’ potential when applied to real network scenarios, where adaptation loops in protocols and algorithms in the network stack may alter the expected performance. We show that, even uncalibrated, the quality-aware multihomed flow management allows to make better trade-offs between different user criteria and identify improvement directions.

Evaluating User-Centric Multihomed Flow Management for Mobile Devices in Simulated Heterogeneous Networks

Cloud environments play an important role for network and service providers. Cloud network providers require ubiquitous, broadband and minimum-delay connectivity from network providers. There are different realizations of cloud connectivity based on the Software Defined Networking (SDN) and the Network Function Virtualization (NFV) paradigm. In this paper we introduce a new concept based on the OConS architecture developed within the SAIL FP7 project. Our advanced connectivity concept focuses on interdomain connectivity.

Enabling Cloud Connectivity Using SDN and NFV Technologies

We describe an advanced concept and its experimental realisation for open connectivity services to cope with the complexity of multi-technology networks, especially with regard to control, management and algorithmic flexibility across layer-3 routing, layer-2 switching and in future even optical switching. We introduce a unifying control element in each supported network domain called the Domain Control Unit (DCU) that separates the control functions from the data forwarding functions by concentrating most of the control plane mechanisms and intelligence in a single entity. The DCU incorporates PCE-like components for path computation and OpenFlow-like dynamic flow control to enforce the forwarding adjacencies in the switching or routing network. Additionally, the DCU provides intra-domain communication to the packet-forwarding network elements (e.g. routers, switches) in order to collect topological information and to react properly in case of failure. The persistency of the topology and resource information of the network is ensured by a traffic engineering database. The DCU also supports the inter-domain communication between several domain controllers. For experimentation purposes we followed an OpenFlow-like approach to realize a flexible and extensible test installation of the DCU networking concept. This enabled us to demonstrate intra- and inter-domain path computation and flow establishment in a mixed environment of cooperating (layer2) switches and (layer3) routers in virtual and physical networks, as it is common in the context of interconnectivity of large distributed data centers and cloud centers.

On converged multidomain management of connectivity in heterogeneous networks

The recent advances on networking technologies (both at the access and the core realms) together with the ever-increasing requirements of the end-users and their applications/services call for an open approach, yet with a clear migration strategy, so as to avoid the well-known shortcomings and limitations of clean-slate approaches. These requirements have streamlined the design of a novel (yet not revolutionary) architecture framework based on the identification of functional entities and their interfaces. The most distinguishing feature is its flexibility, allowing its adaptation to already existing protocols/technologies/algorithms as well as to novel solutions.

OConS: Towards Open Connectivity Services in the Future Internet

In this paper we present an Open Connectivity Services architecture, which has been conceived such as to cope with the challenges posed by the Future Internet By relying on currently working solutions and establishing a trustworthy migration strategy, the proposed architecture provides a flexible framework that supports both legacy and enhanced connectivity mechanisms It is able to dynamically adapt the operation of the involved mechanisms according to the particular requirements of the services and applications This open architecture is based on three main modules (information gathering, decision taking and decision enforcement) which mimic the basic functionalities of any connectivity mechanism By having a common way of representing current and future mechanisms, the OConS operation eases the instantiation, launch and interconnection of mechanisms by the specified orchestration procedures A challenging flash crowd scenario is presented for validation of the architecture, where enhanced connectivity mechanisms support both cloud networking and network of information use cases

Open connectivity services for the future internet

/pdf/ocons-towards-open-connectivity-services-in-the-future-2axm9xrcs6.pdf

The Open Connectivity Services (OConS) framework is currently being defined within the framework of the SAIL project. Its main objective is to offer adaptive connectivity services to seamlessly address user and service requirements while complying with operator policies and dealing with the heterogeneous and changing network conditions of the future Internet. This paper describes a realization of this framework. It supports flexible integration of both legacy and novel mechanisms and protocols by mapping them to three abstract functional entities: information, decision and execution elements. Organization of these entities is done through an orchestration process to combine and integrate the various mechanisms into a full service for the user. We introduce the OConS protocol used for communication between the presented entities as well as the role played by the orchestration process. We then present the concrete example of a testbed based on this implementation, which shows the feasibility and effectiveness of the proposed approach.

Lucian Suciu

Papers

OConS: Towards Open Connectivity Services in the Future Internet

Open connectivity services for the future internet

OConS: Towards Open Connectivity Services in the Future Internet

Design and Implementation of the Open Connectivity Services Framework