Showing papers presented at "Testbeds and Research Infrastructures for the DEvelopment of NeTworks and COMmunities in 2012"

BonFIRE: A Multi-cloud Test Facility for Internet of Services Experimentation

Abstract: BonFIRE offers a Future Internet, multi-site, cloud testbed, targeted at the Internet of Services community, that supports large scale testing of applications, services and systems over multiple, geographically distributed, heterogeneous cloud testbeds. The aim of BonFIRE is to provide an infrastructure that gives experimenters the ability to control and monitor the execution of their experiments to a degree that is not found in traditional cloud facilities.

ExoGENI: A Multi-domain Infrastructure-as-a-Service Testbed

Abstract: NSF’s GENI program seeks to enable experiments that run within virtual network topologies built-to-order from testbed infrastructure offered by multiple providers (domains). GENI is often viewed as a network testbed integration effort, but behind it is an ambitious vision for multi-domain infrastructure-as-a-service (IaaS). This paper presents ExoGENI, a new GENI testbed that links GENI to two advances in virtual infrastructure services outside of GENI: open cloud computing (OpenStack) and dynamic circuit fabrics. ExoGENI orchestrates a federation of independent cloud sites and circuit providers through their native IaaS interfaces, and links them to other GENI tools and resources.

Federating Wired and Wireless Test Facilities through Emulab and OMF: The iLab.t Use Case

Abstract: The IBBT iLab.t technology centre provides computing hardware, software tools and measurement equipment to support researchers and developers in building their ICT solutions, and in measuring the performance of these solutions. Among other things, the iLab.t hosts several generic Emulab-based wired test environments called the Virtual Walls, and two wireless test environments which are grouped under the name w-iLab.t. Until very recently, these wired and wireless test facilities each had their own history: they were deployed and maintained by a different group of people, were operated using different tools, and each had their own community of experimenters. This paper provides insight on the origin and evolution of the Virtual Wall and w-iLab.t facilities. It explains how these facilities were federated, by using the best parts of both the OMF and Emulab frameworks. It discusses the benefits of our local federation as well as our future federation plans.

Designing a Federated Testbed as a Distributed System

Abstract: Traditionally, testbeds for networking and systems research have been stand-alone facilities: each is owned and operated by a single administrative entity, and is intended to be used independently of other testbeds. However, this isolated facility model is at odds with researchers’ ever-increasing needs for experiments at larger scale and with a broader diversity of network technologies. The research community will be much better served by a federated model. In this model, each federated testbed maintains its own autonomy and unique strengths, but all federates work together to make their resources available under a common framework.

A Demonstration of Fast Failure Recovery in Software Defined Networking

Abstract: Software defined networking (SDN) is a recent architectural framework for networking, which aims at decoupling the network control plane from the physical topology and at having the forwarding element controlled through a uniform vendor-agnostic interface A well-known implementation of SDN is OpenFlow The core idea of OpenFlow is to provide direct programming of a router or switch to monitor and modify the way in which the individual packets are handled by the device We describe our implemented fast failure recovery mechanisms (Restoration and Protection) in OpenFlow, capable of recovering from a link failure using an alternative path In the demonstration, a video clip is streamed from a server to a remote client, which is connected by a network with an emulated German Backbone Network topology We show switching of the video stream from the faulty path to the fault-free alternative path (restored or protected path) upon failure

How To Build a Better Testbed: Lessons From a Decade of Network Experiments on Emulab

Abstract: The Emulab network testbed provides an environment in which researchers and educators can evaluate networked systems. Available to the public since 2000, Emulab is used by thousands of experimenters at hundreds of institutions around the world, and the research conducted on it has lead to hundreds of publications. The original Emulab facility at the University of Utah has been replicated at dozens of other sites.

Implementation and End-to-end Throughput Evaluation of an IEEE 802.11 Compliant Version of the Enhanced-Backpressure Algorithm

Abstract: Extensive work has been done in wireless multihop routing with several ideas based on shortest path or load balancing routing algorithms, that aim at minimizing end-to-end delay or maximizing throughput respectively. Backpressure is a throughput-optimal scheme for multihop routing and scheduling, while Enhanced-Backpressure is an incremental work that reduces end-to-end delay without sacrificing throughput optimality. However, the implementation of both theoretical schemes is not straightforward in the presence of 802.11 MAC, mainly because of their requirement for centralized scheduling decisions that is not aligned with the aspects of CSMA/CA.

VF2x: Fast, Efficient Virtual Network Mapping for Real Testbed Workloads

Abstract: Distributed network testbeds like GENI aim to support a potentially large number of experiments simultaneously on a complex, widely distributed physical network by mapping each requested network onto a share or “slice” of physical hosts, switches and links. A significant challenge is network mapping: how to allocate virtual nodes, switches and links from the physical infrastructure so as to accurately emulate the requested network configurations.

FIBRE Project: Brazil and Europe Unite Forces and Testbeds for the Internet of the Future

Abstract: In October 2011 a new, ambitious project was launched, named FIBRE (Future Internet testbeds experimentation between Brazil and Europe). Its main goal is to create common space between Brazil and EU for Future Internet experimental research into network infrastructure and distributed applications, by building and operating a federated EU-Brazil Future Internet experimental facility. Apart from bridging partners from two continents, the project brings together different technologies, including OpenFlow, wireless and optical communications. To demonstrate the public utility of the facility, FIBRE will design and implement a set of pilot applications ranging from seamless wireless connectivity to high-definition content delivery. The poster to be presented describes FIBRE’s goals, its testbed facilities and a schema of the envisioned architecture embracing the functionalities of the individual testbeds, as well as their federation. This schema has resulted from the collaborative work of the partners in order to define the functional requirements related to such an architecture. Our ambition with this poster is to attract new users for the facility from the experimental research community, but also to stimulate interest for FIBRE’s activities among the conference’s attendees.

TaaSOR – Testbed-as-a-Service Ontology Repository

Abstract: This demonstration is introducing Testbed-as-a-Service (TaaS) infrastructure that illustrates use of community based approach to building experimental ontologies and generation of supporting testbed resources applied to OMF based testbed. While this TaaS demo is initially primarily targeting virtualization and community collaboration, the final objective is to support domain specific experimental description languages and resource management in federated testbeds.

Automated Deployment and Customization of Routing Overlays on Planetlab

Abstract: PlanetLab testbed is widely used to evaluate protocols and applications under realistic Internet conditions, but this realism comes at the cost of uncontrolled topology and traffic behavior. The use of overlay networks on PlanetLab can solve this problem by giving more control to the experimenter. However, manually creating such overlays is far from simple, and existing solutions are either not available for all PlanetLab nodes, or lack support for low level overlays. Deployment and customization of overlay architectures are also poorly supported. In this paper we present a flexible solution to support overlay networks on PlanetLab, providing deployment automation, tunneling, routing, and traffic shaping capabilities. By building our solution into NEPI, a general framework for network experimentation, which automates design, deployment, and management of experiments, we simplify the complexity of building overlays on PlanetLab, and foster reusability and extensibility though NEPI’s modular structure.

Experimentation in heterogeneous European testbeds through the Onelab facility: The case of PlanetLab federation with the wireless NITOS testbed

Abstract: The constantly increasing diversity of the infrastructure that is used to deliver Internet services to the end user, has created a demand for experimental network facilities featuring heterogeneous resources. Therefore, federation of existing network testbeds has been identified as a key goal in the experimental testbeds community, leading to a recent activity burst in this research field. In this paper, we present a federation scheme that was built during the Onelab 2 EU project. This scheme federates the NITOS wireless testbed with the wired PlanetLab Europe testbed, allowing researchers to access and use heterogeneous experimental facilities under an integrated environment. The usefulness of the resulting federated facility is demonstrated through the testing of an implemented end-to-end delay aware association scheme proposed for Wireless Mesh Networks. We present extensive experiments under both wired congestion and wireless channel contention conditions that demonstrate the effectiveness of the proposed approach in a realistic environment. Both the architectural building blocks that enable the federation of the testbeds and the execution of the experiment on combined resources, as well as the important insights obtained from the experimental results are described and analyzed, pointing out the importance of integrated experimental facilities for the design and development of the Future Internet.

A Framework for Resource Selection in Internet of Things Testbeds

Abstract: As the scale and heterogeneity of experimental environments increases, the selection of adequate testbed resources becomes a daunting task for the experimenter. Wrong choices or unexpected resource behavior can significantly decrease an experimenter’s productivity. These challenges are further amplified by the recent trend of moving testbeds from isolated labs to unpredictable real world environments to favor experimental evaluation under realistic conditions. This paper presents a framework for resource selection in large scale and heterogeneous Internet of Things testbeds, in order to support the experimenter with an increased understanding of available testbed resources, their expected behavior and topological relationships in the experimentation environment. Through an evaluation case study we demonstrate the effectiveness of our proposed framework.

Remote Control of Robots for Setting Up Mobility Scenarios during Wireless Experiments in the IBBT w-iLab.t

Abstract: The w-iLab.t is a large-scale generic wireless experimentation facility. Two locations are equipped with in total over 260 wireless nodes. In the w-iLab.t Zwijnaarde location mobile nodes are hosted. The mobile nodes are mounted on top of robots, of which the movement can be fully controlled by the experimenter. Due to a high accuracy positioning algorithm, the exact position of the robots is known at all time during the experiments. This enables us to provide repeatable and controlled mobile experiments to our users.

Demonstration of a Vehicle-to-Infrastructure (V2I) Communication Network Featuring Heterogeneous Sensors and Delay Tolerant Network Capabilities

Abstract: The development of applications based over vehicular networks, such as road safety, environmental information etc. require a complete testbed platform for research and evaluation. Such a platform will be provided by NITOS[1] testbed, that will include nodes mounted on cars and fixed nodes of the testbed operating as road side units (RSU). Besides the wireless infrastructure, there will be several sensors regarding the environmental conditions and the vehicle. These will gather measurements about air conditions and GPS data such as position and speed and will be collected in a central database, where the experimenter will be able to depict them in a Google map.

The IBBT w-iLab.t: A Large-Scale Generic Experimentation Facility for Heterogeneous Wireless Networks

Abstract: The w-iLab.t is a large-scale generic wireless experimentation facility. Over 260 wireless nodes are installed at two different locations. Every single wireless node is equipped with multiple wireless technologies, namely IEEE 802.15.4, Wi-Fi a/b/g(/n), and on some devices also Bluetooth. Additionally, w-iLab.t provides access to software defined radio platforms and also uses them to characterize the wireless environment during an experiment. The w-iLab.t flexibility and its tools enable experimenters to design and schedule a wide range of wireless experiments, and to collect and process results in a user-friendly way.

DNEmu: Design and Implementation of Distributed Network Emulation for Smooth Experimentation Control

Abstract: Conducting a realistic network experiment involving globally distributed physical nodes under heterogeneous environment introduces a requirement of experimentation control between the real world network and emulated/simulated networks. However, there is a gap between them to deploy network experiments. In this paper, we propose the Distributed Network Emulator (DNEmu) to fill the gap for the requirements of a planetary-scale network experiment. DNEmu addresses the issue of real-time execution with message synchronization through distributed processes, and enables us to evaluate protocols with actual background traffic using a fully controlled distributed environment. Through evaluation with micro-benchmarks, we find that our DNEmu prototype implementation is similar in terms of packet delivery delay and throughput to the existing non-virtualized environment. We also present a use-case of our proposed architecture for a large distributed virtual machine service in a simple control scenario involving actual background traffic on the global Internet. DNEmu will contribute to research in protocol evaluation and operation in a huge network experiment without interfering with the existing infrastructure.

GAIA Extended Research Infrastructure: Sensing, Connecting, and Processing the Real World

Abstract: The GAIA Extended Research Infrastructure is located at the southeast of Spain. It targets the research of Future Internet architectures and comprises several facilities from the University of Murcia and the Spanish government. It offers a vertical infrastructure, composed of a backend with high capacity of data storage, communication, and processing, together with a frontend with an extended set of multidisciplinary testbeds, deployments, and living labs for the ubiquitous monitoring, sensing, and processing. That said, it offers a highly flexible framework for experimentation with architectures and protocols for the Future Internet. In fact, it has been used in many research projects to evaluate their outputs from the communications and telematics point of view.

Environment-independent virtual wireless testbed

Abstract: Current digital packet-switching communications involves more cross-layer trade-offs than legacy wireless communications. Conventionally, each network layer is studied separately, and then the total system is evaluated in field tests. However, the results are always specific to the particular environmental conditions during the test and are not reproducible. Here we propose an architecture for an environment-independent virtual wireless testbed. We describe the implementation and validation results for a programmable wireless propagation emulator—the key component of the testbed. It was found that the system could emulate wireless propagation over at least 10 wireless nodes in real time using 10 field-programmable gate arrays with programmable parameters consisting of the channel model, path loss model, antenna model, and emulation scenario. Thus, the system is promising as a replacement for conventional field tests.

An experimental framework for channel sensing through USRP/GNU radios

Abstract: In the last decade testbeds have been set-up to evaluate network protocols and algorithms under realistic settings. In order to draw solid conclusions about the corresponding experimental results, it is important for the experimenter to have a detailed view of the existing channel conditions. Moreover, especially in the context of non-RF-isolated wireless testbeds, where external interference severely impacts the resulting performance, the requirement of experimenters for accurate channel monitoring becomes a prerequisite. Toward, this direction, various channel sensing platforms have been introduced, where each one offers different operational characteristics. In this demo, we propose the NITOS Channel Sensing framework, which is based on software-defined radio (SDR) devices that feature highly flexible wireless transceivers and are able to provide highly accurate channel sensing measurements. Through this framework, online measurement gathering is automated and further simplified using specifically developed scripts, so that it becomes a transparent process for the experimenter. The proposed framework is also accompanied by a web user interface that allows the user to get a graphical representation of the gathered measurements.

A Passive Measurement System for Network Testbeds

Abstract: The ability to capture and process packet-level data is of intrinsic importance in network testbeds that offer broad experimental capabilities to researchers. In this paper we describe the design and implementation of a passive measurement system for network testbeds called GIMS. The system enables users to specify and centrally manage packet capture on a set of dedicated measurement nodes deployed on links in a distributed testbed. The first component of GIMS is a scalable experiment management system that coordinates multi-tenant access to measurement nodes through a web-based user interface. The second component of GIMS is a node management system that enables (i) local processing on packets (e.g., flow aggregation and sampling), (ii) meta-data to be added to captured packets (e.g., timestamps), (iii) packet anonymization per local security policy, and (iv) flexible data storage including transfer to remote archives. We demonstrate the capabilities of GIMS through a set of micro-benchmarks that specifically highlight the performance of the node management system deployed on a commodity workstation. Our implementations are openly available to the community and our development efforts are on-going.

Integrating FlowVisor Access Control in a Publicly Available OpenFlow Testbed with Slicing Support

Abstract: OpenFlow technology has recently attracted a lot of attention in the networking research community, as the ability to control the forwarding plane of a switch through software opens new exciting capabilities for protocol designers. Several network testbeds have added OpenFlow-capable switches to their equipment, while at the same time new OpenFlow-centric testbeds have been created. This demo describes a proposed approach to provide testbed slicing in a publicly available testbed featuring OpenFlow switching equipment. The approach leverages the slicing features of the FlowVisor software component and combines them with the NITOS Scheduler resource reservation framework. The resulting configuration was implemented and successfully integrated into the software framework of the publicly available testbed NITOS.

Enabling Sensing and Mobility on Wireless Testbeds

Abstract: The inherent inability of simulation models to adequately express factors such as wireless signal propagation etc., can lead to incomplete evaluation of wireless protocols and applications. Thus, testing of proposed schemes under real-life settings has become the de facto validation process. More specifically, in the context of testing scenarios that include mobility, evaluation in real environments becomes a prerequisite. Networking testbeds have recently extended their capabilities by providing the researchers with the ability to include mobile nodes in their experiments as well. Towards this direction, we have developed a prototype mobile node in NITOS, which features a mounted camera and wireless interfaces that enable remote access and control. The proposed mobility framework is also accompanied by a graphical user interface that allows the experimenter to observe the node’s behavior remotely.

A Demonstration of a Relaying Selection Scheme for Maximizing A Diamond Network's Throughput ?

Abstract: We demonstrate a queue-aware algorithm studied in a diamond network topology. This algorithm’s decisions are obtained from an analytical optimization framework relying on our technical work [4] and we devise an implementation part by modifying the features of ath9k driver [3] and click modular router [5]. Performance evaluation is conducted through experimentation on the NITOS Wireless Testbed and it reveals a significant rise in total throughput considering a particular networking scenario while also it maintains stability of backlog queues when schedules indicated by Lyapunov-based technique as throughput optimal are selected.

A Satellite Network Emulation Platform for Implementation and Testing of TCP/IP Applications

Abstract: In order to assess the performance of TCP/IP based applications and protocols for communication over heterogeneous networks, simulation and emulation activities are of great importance. In particular, real time emulation provides the opportunity to reproduce realistic environment thanks to the implementation in laboratory of real architectures and protocols, avoiding utilizing real networks and in a controlled environment. We developed a broadband satellite real-time emulation platform called SNEP, designed to match the DVB-RCS European standards. The SNEP reproduces with great details the architecture and behavior of a real satellite broadband network, where it is possible to attach end-user PCs and use real protocols and applications. In this way, real network applications can be benchmarked in laboratory as in the real scenario of broadband satellite communications, at the same time proposing alternative solutions and optimizations. Furthermore with the SNEP the integration of satellite platforms with further terrestrial networks is also possible, both real and simulated/emulated, in order to extend the scope for testing.

A Framework for Multidimensional Measurements on an Experimental WiMAX Testbed

Abstract: A major difficulty in the design, study, and implementation of wireless protocols and applications is the multitude of nondeterministic factors (e.g. interference, weather conditions, competing traffic) that can affect their performance. For this reason, testbeds that enable researchers to quantify these influences have become increasingly essential in the wireless research community. The growing sophistication of wireless testbeds and the wide array of services they can provide to researchers have advanced the field tremendously.

A Real-Time Testbed for Routing Network

Abstract: Existing network testbeds can enable developers to evaluate the performance of different routing protocols in a network and help students to enhance their hands-on experiences and understand complex and abstract concepts of routing protocols by allowing them to carry out real-world experiments, but they are either limited in features or expensive to establish and manage To address the problem, this paper presents ARTNet - A Real-Time Testbed for Routing Network – which supports almost all the popular routing protocols for typical applications in a cost-effective manner ARTNet has been implemented on a multiprocessor server for users to create and manage their routing networks Performance and functionality evaluations on the ARTNet platform show that it is a promising approach

Experimental Demonstration of Network Virtualization and Resource Flexibility in the COMCON Project

Abstract: In the recent past, Network Virtualization (NV) received much attention. Nevertheless, Virtual Networks (VNs) are still not available on the market. The consortium of the COntrol and Management of COexisting Networks (COMCON) project examines the potential interactions in vertically and horizontally divided markets and evaluates the applicability of existing technologies, like Generalized Multi-Protocol Label Switching (GMPLS), for automated virtualization-enabled network management. To promote the manifold research, a selected scenario was demonstrated at the EuroView 2011 comprising a Video on Demand (VoD) service using a Scalable Video Codec (SVC). All necessary components have been implemented and the selected scenario was performed on a real network based on Linux PCs. In this paper, we describe the components, the scenario, and the gained insights in detail.

An Instrumentation and Measurement Architecture Supporting Multiple Control Monitoring Frameworks

Abstract: Virtual and/or experimental networks capable of supporting an entire new set of applications and services (Future Internet, Grids, Cloud Computing, other) use, typically, different Control and Monitoring Frameworks (CMFs). This poster addresses the multiple federated CMFs instrumentation and measurement problems. A monitoring architecture (FIBRE-BR IM the collected data control access; and, finally, the multiple CMFs I&M data integration. This poster presents the FIBRE-BR I&M Architecture that integrates diverse I&M services, tools and facilities from multiple CMFs, allowing FIBRE-BR users, possibly transparently to each specific CMF, to benefit from the corresponding infrastructure and experiment specific measurement data.

An Integrated Chassis Manager Card Platform Featuring Multiple Sensor Modules

Abstract: The gradually growing demand for experimentation of protocols designed for wireless networks in real environments has resulted in the development of experimental network facilities (testbeds). Most currently deployed testbeds have been designed so as to offer services to experimenters that lie within the testbed’s premises, thus limiting the accessibility to external users. The requirement for multi-user access of network resources has led several large-scale testbeds to provide remote access services to certified experimenters. However, management and maintenance of large-scale remotely accessible testbeds is a rather challenging task that requires proper hardware, as well as software custom-built tools. In order to provide for remote switching of testbed nodes, NITOS has developed a new chassis manager (CM) card and also a custom framework that allows for monitoring and controlling of the nodes’ operational mode. In addition, NITOS CM card provides for gathering of various types of sensor measurements, through the attached temperature, humidity and light intensity sensor modules. Another innovative characteristic of the proposed card is that it provides the experimenters with the ability to monitor the energy consumption of each testbed node, which is rather important for experimentation with power optimization schemes. In this demo, we will present the various functionalities of the NITOS CM card and the developed control framework that accompanies it.