Showing papers presented at "Testbeds and Research Infrastructures for the DEvelopment of NeTworks and COMmunities in 2007"

Path Loss Measurements at 3.5 GHz: A Trial Test WiMAX Based in Rural Environment

Abstract: This paper addresses the dimensioning of the emerging wireless broadband networks operating in 3.5 GHz band by focusing on the key problem of propagation loss. The characteristics of the path loss in the 3.5 GHz band measured in a rural macro-cellular environment are presented. The existing empirical prediction models are compared with the measured data and a comparative analysis is carried out. The measurements are performed within the experimental activities developed on a WiMAX based platform located in an Italian rural area.

MagNets - experiences from deploying a joint research-operational next-generation wireless access network testbed

Abstract: In spite of the deployment of wireless access networks, such as meshes and WiFi backbones in cities, the potential and limitations of such networks is still unclear. Deployed networks have a limited ability to gather data or experimentally deploy new protocols, whereas lab testbeds are often limited in scale and lack real applications traffic. This paper presents MagNets, a next-generation wireless access network deployed in the city of Berlin. MagNets is a joint research-operational testbed that offers connectivity to students, but still allows for experimental deployment of new protocols. We describe the work breakdown and lessons learnt from the design and deployment process. In addition, initial measurement results highlight the potential to shed light on the suitability of wireless technology for next-generation access networks.

MeshTest: Laboratory-Based Wireless Testbed for Large Topologies

Abstract: Mobile, ad-hoc, wireless networks offer an interesting paradigm for ubiquitous connectivity. They have many proposed applications, and with every application comes new protocols. To test such protocols, one has two basic options: simulators and testbeds. We describe a novel wireless networks testbed called MeshTest, supporting mobile, ad-hoc, and mesh environments, with an emphasis on laboratory testing of large, outdoor environments. This paper details the testbed design, and derives mathematical relationships between attenuator settings and real-world topologies. We show how to accurately and efficiently map topologies to our testbed configuration in real time, while supporting both device mobility and multipath fading.

Efficient Packet Error Rate Estimation in Wireless Networks

Abstract: Wireless links exhibit diverse link quality (e.g., in terms of error rate, latency, and required transmit power), and inferring the link cost correctly is crucial to finding an efficient path in multihop wireless networks. In this paper, we consider the problem of estimating packet error rate (PER) in wireless networks. Most existing schemes use observed error rates of probe messages as representative packet error rates for wireless links. However, since typical data packets are larger than probe messages, the actual data packet error rate is often higher than the observed error rate of probe messages. Instead of directly using measurement statistics, our approach is to analyze them to determine the link characteristics and estimate the link quality (e.g., PER) based on the understanding. We describe a simple estimation scheme based on a well-known two-state Markov bit error model for wireless channels. We perform various experiments on two wireless testbeds and show the proposed scheme can successfully estimate PERs for packets of arbitrary size in diverse environments. When compared to other alternatives, the proposed estimation scheme is accurate and incurs small control overhead. We also integrate the scheme into an existing routing scheme. Our experiment results show that the combined scheme can reduce the transmission overhead by 60% when compared to a naive estimation strategy based on one type of probe messages.

Measuring the Quality of VoIP Traffic on a WiMAX Testbed

Abstract: The large coverage of the IEEE 802.16 standard, widely known as WiMAX, represents a key advantage compared to several first mile solutions proposed so far, while ensuring a rather inexpensive equipment at the subscriber side. The IEEE 802.16 standard, in practice, promises to be a flexible solution especially where cabling is not a viable choice, or as an alternative to customary leased lines. Nevertheless, modern requirements to wireless connectivity include mandatory QoS guarantees for a wide set of real-time applications, and this is the case of the ever growing trend of VoIP calls. To this aim, WiMAX supports natively real-time traffic. In this paper, we report the results of a set of measurements performed on the field on a WiMAX Alvarion testbed, located in Turin, Italy. We fed the system with synthetic VoIP traffic, real-time guaranteed, competing with concurrent best effort traffic. We obtained E-model figures, thus characterizing the operation intervals of the system, depending on the codec source and on the number of calls.

The Design, Deployment, and Analysis of SignetLab: A Sensor Network Testbed and Interactive Management Tool

Abstract: The emergence of small, inexpensive, network-capable sensing devices led to a great deal of research on the design and implementation of sensor networks. A critical step in taking protocols from theory to actual deployment is comprehensive testing on physical sensor networks. Sensor network testbeds provide one way to facilitate such testing without requiring the deployment of a specialized sensor network for each protocol. However, for such testbeds to be useful, they must not overwhelm researchers with maintenance tasks and high learning curves. Previous work in testbed design has primarily focused on creating interfaces to maximize their usage by convenient scheduling of jobs and output access. In this work, we present two contributions to sensor network testbed design. The first is a unique management tool that allows users to program, interact with, and receive data from nodes in the network, filling a gap in current testbed management solutions. The second is the design, deployment, and analysis of the SignetLab testbed. The analysis of the testbed and its results provide quantitative measurements of the impact of physical deployment on signal propagation characteristics. Additionally, we present two case studies where researchers have used the testbed and discuss the user experiences and lessons learned.

DDoS Benchmarks and Experimenter's Workbench for the DETER Testbed

Abstract: While the DETER testbed provides a safe environment and basic tools for security experimentation, researchers face a significant challenge in assembling the testbed pieces and tools into realistic and complete experimental scenarios. In this paper, we describe our work on developing a set of sampled and comprehensive benchmark scenarios, and a workbench for experiments involving denial-of-service (DoS) attacks. The benchmark scenarios are developed by sampling features of attacks, legitimate traffic and topologies from the real Internet. We have also developed a measure of DoS impact on network services to evaluate the severity of an attack and the effectiveness of a proposed defense. The benchmarks are integrated with the testbed via the experimenter's workbench - a collection of traffic generation tools, topology and defense library, experiment control scripts and a graphical user interface. Benchmark scenarios provide inputs to the workbench, bypassing the user's selection of topology and traffic settings, and leaving her only with the task of selecting a defense, its configuration and deployment points. Jointly, the benchmarks and the experimenter's workbench provide an easy, point-and-click environment for DoS experimentation and defense testing.

Quail Ridge Wireless Mesh Network: Experiences, Challenges and Findings

Abstract: Wireless mesh networks are becoming a popular alternative to extending the wireless LANs we use today. Low-cost incremental deployment and the lack of a wired infrastructure lends mesh networks to "last-mile" solutions for ISPs or simply to aid in increased coverage area. In addition, we find that mesh networks are appropriate for our work in establishing a communication infrastructure at the quail ridge natural reserve. In deploying a mesh network at quail ridge, we seek to assist ecological research in the area and provide a testbed for wireless mesh networks research in the future. We are interested in looking at pursuing novel techniques for routing, QoS provisioning and wireless monitoring and maintenance tools. This paper will describe our work in the quail ridge mesh network. It will give the reader an overview of our current system, deployment status, and how this test-bed will benefit mesh networks research.

A Blueprint for a Manageable and Affordable Wireless Testbed: Design, Pitfalls and Lessons Learned

Abstract: In this paper, we describe the deployment efforts of our 802.11 indoor wireless testbed. We elucidate the challenges that we faced and the design decisions that we had to make, sometimes based on technical reasons, and other times due to practicalities. These design challenges involve: (a) accessibility to the software, in order to be able to modify and implement various functionalities, (b) physical extendability, in order to add hardware in the future and, (c) manageability, in order to configure and update the software easily and quickly, for all the nodes in the network. We justify the hardware and software design choices that we make in order to facilitate these requirements. For ease of maintenance and convenience, each node is diskless, and we utilize power-over-ethernet through an Ethernet connection with a central server. We ensure that the software can be easily modified; this provides for easier module implementation and parameter tuning. We explain the different ways of node deployment, decisions that we make on power settings and discuss how and why the receiver sensitivity affects deployment decisions. Finally, we present our observations based on a set of measurements to quantify the stability of the links in our testbed.

StarBED2: Large-scale, Realistic and Real-time Testbed for Ubiquitous Networks

Abstract: Nowadays many new technologies are being developed and introduced for Internet, home networks, and sensor networks. The new technologies must be evaluated in detail before deployment. However the above mentioned networks have a large number of nodes and a complicated topology. Therefore it is difficult to analyze such networks using typical network simulators. Accordingly testbeds for these networks must be able to perform accurately emulation of large-scale networks with a complex topology. In order to implement a testbed that satisfies these requirements, we developed a large-scale, realistic and real-time network testbed, StarBED, using hundreds of PCs, and switched networks. We are now implementing StarBED2, which expands StarBED so as to be suitable for emulating ubiquitous networks by introducing several new concepts. In this paper we describe first the present StarBED, its design concept, overall architecture, implemented functionalities, and some of the experiments we performed. Then we introduce StarBED2, its design policy, architecture, and additional components.

Recursive Routing in the Cognitive Packet Network

Abstract: Applications such as streaming multimedia, Voice over IP (VoIP) and video teleconferencing require quality of service (QoS), and developing algorithms that find routes from a source to a destination which meet the users' QoS requirements under rapidly changing network conditions remains a technical challenge. Recently, the cognitive packet network (CPN) has been proposed so as to offer adaptive QoS driven routing based on on-line sensing and monitoring. In this paper, we propose a recursive routing algorithm for CPN which breaks large scale route discovery problems into smaller ones. The solutions to those smaller routing problems arc cached in the intermediate nodes of the network, which can be utilized by Smart Packets to solve larger scale routing problems. The experiments conducted on a 46-node network test-bed indicate that when recursive routing is deployed, the network connection establishment time can be drastically reduced without sacrificing the QoS of the routes discovered, and that the QoS that the users experience is also improved.

Dynamic Optimal Fragmentation for Goodput Enhancement in WLANs

Abstract: To meet the demand for broadband wireless communication, wireless systems should work well in typical wireless environments, characterized by the path loss of the signals, multipath fading, interference to adjacent channels, and random errors. IEEE 802.11 VVLANs use the unlicensed 2.4 GHz industrial, scientific and medical (ISM) band, which is vulnerable to noise generated by TVs, microwaves, and cordless phones. This paper proposes an algorithm to enhance system goodput through the dynamic optimal fragmentation. The number of contending stations, packet collisions, packet error probabilities, and fragmentation overheads are modeled in the analysis. Using an adaptive SNR estimator, the sender estimates the SNR of the receiver, and chooses a fragmentation threshold to shape arbitrary sized packets into optimal length packets. Through the rigorous analysis and extensive experiments with implemented test-bed, we show that the dynamic optimal fragmentation enhances the goodput approximately 18% in a typical WLAN environment. The experiment results reinforce that the algorithm is a comprehensive analytical model applicable to any CSMA/CA based MAC protocol for next generation wireless networks, and a realistic approach that can be deployed without changing the IEEE802.11 MAC protocol.

JANUS: A Framework for Distributed Management of Wireless Mesh Networks

Abstract: Wireless mesh networks (WMNs) are emerging as a potentially attractive access architecture for metropolitan-scale networks. While research on WMNs has been up to a large extent confined to the study of efficient routing protocols, there is a clear need to envision new network management tools, able to sufficiently exploit the peculiarities of WMNs. In particular, a new generation of middleware tools for network monitoring and profiling must be introduced in order to speed up development and testing of novel protocol architectures. Currently, management functionalities are developed using conventional centralized approaches. The distributed and self-organizing nature of WMNs suggest a transition from network monitoring to network sensing. In this work, we propose JANUS, a novel framework for distributed monitoring of WMNs. We describe the JANUS architecture, present a possible implementation based on open-source software and report some experimental measurements carried out on a small-scale testbed.

Dynamic Resource Allocation Mechanisms for Grid Computing Environment

Abstract: Grid computing is an emerging paradigm to enable scalable computational environment through efficient resource utilization. In this context, resource allocation is one of the major challenges in grid environment. Currently, several approaches were proposed to solve this problem. However, most of the approaches rely on administrators' intervention for proper allocation. In this paper, we propose dynamic resource allocation mechanisms of computations using a combination of best fit algorithm and process migration.

Integrating multiuser dynamic OFDMA into IEEE 802.11a and prototyping it on a real-time software-defined radio testbed

Abstract: Multiuser dynamic orthogonal frequency division multiple access (OFDMA) can achieve high downlink capacities in future wireless networks by optimizing the subcarrier allocation for each user. When it comes to the integration into current wireless local area network (WLAN) standards, dynamic OFDMA raises several implementation issues which are neglected in theoretical papers. Putting this emerging approach into practice requires to treat these issues accordingly and to demonstrate the feasibility of the system design. In this paper, we propose a dynamic OFDMA integration for the physical layer of the widespread IEEE 802.11a standard. To test our implementation and demonstrate its practical relevance we use a pragmatic approach: We prototype multiuser dynamic OFDMA on a real-time software-defined radio testbed for WLANs. We discuss details of our implementation and provide measurements showing that it does not introduce significant overhead into the IEEE 802.11a system at high subcarrier allocation quality. We particularly focus on the problems of our integration as well as the concepts and limitations of the used testbed.

Large-scale Reconfigurable Virtual Testbed for Information Security Experiments

Abstract: The vulnerability of a modem computer network to information attacks stems from its high complexity, global interconnectivity and multiple entry points. While experimental security-related studies cannot be performed on "real" operating computer networks, and data collected during real information attacks is incomplete and sporadic, extensive network facilities have become a necessary component of security research. In order to assure the scalability of results, it is important that the experimental network properly emulates the "real" network. The development of such an experimental facility for network security research is presented. It will allow for a high level of software visualization enabling the users to achieve a high level of network scalability and rapid deployment, ensuring proper analysis and development of new tools and techniques for threat detection and mitigation.

An Efficient Task Scheduling Method for Improved Network Delay in Distributed Sensor Networks

Abstract: One of the challenge in developing smart sensor networks is the minimization of network delay or at the very least be able to have upper and lower boundaries of network delay when sensor nodes respond to higher level applications. In this paper, we present a highly efficient task scheduling method based on linear programming that integrates both sensing and networking communication delay. The objective is to minimize the total response time and global power consumption of the network with respect to the total number of sensor nodes in the network. Simulation results based on closed-form solutions for the task scheduling problem are presented for two scenarios with homogeneous and six scenarios with heterogeneous sensor nodes using single level tree-network topology. Specifically, for the heterogeneous scenarios, responding sequence that results in global optimum total respond time has also been found.

A splitting infrastructure for load balancing and security in an MPLS network

Abstract: Several multi-path routing algorithms have been recently proposed to achieve load balancing and increase security. However, the functionalities required to split traffic flows over multiple paths have not been standardized yet. Multi-protocol label switching (MPLS) offers a suitable environment to implement multi-path routing algorithms, as multiple parallel label switched paths (LSPs) may be established to carry each a portion of a traffic flow. This paper focuses on a traffic splitting mechanism designed for MPLS networks. We propose a set of new operations to be performed by the edge routers and illustrate them with reference to a popular open source implementation of the MPLS stack. We implemented the new operations and give a demonstration of their functionality using an experimental testbed.

The TATPA Testbed; A Testbed for Advanced Transport Protocols and Architecture performance evaluation on wireless channels

Abstract: The paper describes the Testbed for Advanced Transport Protocols and Architecture (TATPA) developed by the University of Bologna, inside the SatNEx (Satellite Network of Excellence) framework. The aim is to provide partners, and in general the scientific community, with a powerful and flexible emulation tool to evaluate new proposal at transport layer (both protocols and architectures). In accordance with our research interests, the testbed is focused on performance evaluation on heterogeneous networks that include satellite links. The testbed architecture is based on a cluster of Linux PCs and, in addition to some widely adopted networking tools (NistNet, Ipcrf), it also exploits software packages specifically developed by the authors (Multi TCP, PEPsal, released under GNU license). The testbed is controlled by remote through a web interface, which provides both users and administrators with a ubiquitous easy access to the testbed features. A dedicated PC, acting as testbed controller, hosts the web server and the control engine, developed in PHP and bash and based on a MySQL database. In the paper, a particular attention is devoted to the description of the innovative design and the many advanced features of this controller. An example of use, seen from the final user point of view, completes the description of the TATPA testbed.

Integration of Open Source and Enterprise IP PBXs

Abstract: Over the last few years, voice over Internet protocol (VoIP) evolved from enabling voice communications between computer terminals to providing much wider functionality of the public switched telephony network (PSTN). The idea of deploying VoIP in private branch exchanges (PBXs) is gaining credence among service providers, and this paper addresses some of the design issues related to an IP PBX implementation. Specifically, the paper explores the interoperability between Cisco call manager (CCM) and Linux-based asterisk PBXs corresponding to the enterprise-class and open source IP PBXs, respectively. The architecture of the networking testbed is documented for running various VoIP protocols between multi-vendor devices and IP PBXs. The results presented can be broadly defined into three areas of investigation: (i) the use of session initiation protocol (SIP) and inter asterisk exchange (IAX) trunks to integrate CCM to Asterisk PBXs and Asterisk to Asterisk PBXs, respectively; (ii) examining interoperability between the CCM and Asterisk PBX with advanced features like call display, voicemail, call detail records (CDR) and voicemail to e-mail transfer; and (iii) testing the resilience of voice quality against packet loss and delay in the open source PBX trunks with National Institute of Standards and Technology (NIST) network simulator.

A Methodology for Clock Benchmarking

Abstract: Accurate timestamping is a basic need in traffic monitoring as well as distributed computing in the broad sense, and is destined to become increasingly important as network latency becomes a hard barrier to improved performance across networks. Software clocks need to be improved to meet this challenge, however evaluating their performance is non trivial, as they are imbedded inside computing systems. We present a methodology for clock validation which allows many of the difficult problems to be resolved. Our method involves a combination of external and internal validation strategies, and makes use of GPS synchronized DAG cards and system clocks. We illustrate in detail how it may be applied using real data collected from 3 clocks implemented in UNIX PCs.

An Open Wireless Mesh Testbed Architecture with Data Collection and Software Distribution Platform

Abstract: A Wireless Mesh Network (WMN) is a fast growing network, which is now a popular technology for providing wireless Internet connection to industry as well as community. A WMN is a collection of nodes (usually a computer with one or mint: wireless Network Interface Cards (NICs)) that are connected to one another with single or multiple hop ad hoc links forming a mesh backbone network. Ad hoc links are popular in mesh connectivity as they are self-configuring and self-healing. In this paper, we discuss WMN design and deployment issues with reference to our WiSEMesh testbed. WiSEMesh has 56 nodes deployed in the campus area providing internet connection for over 1000 users. Each node consists of a small form factor computer with three wireless NICs. We developed the WiSEMesh node software stack that contains Unix based operating system, wireless NIC drivers, tools such as DHCP server, NAT etc. WiSEMesh has properties like scalability, open source operating software, heterogeneous hardware support, high performance, globally reachable, and easy to configure network. Hence, it can spread faster as a community wireless network and also provide a flexible platform for testing communication network layers. We also address design issues of a Network Management System (NMS) that can be implemented in any wireless network. Our NMS named WiVi provides platform for software distribution and network configuration with an elaborate data collection and storage facilities. For a large and scalable network like WiSEMesh, a massive database needs to be designed. One of the WiVi design objectives is to provide a robust, flexible and scalable database. WiVi achieves database design goals by implementing a concept "network in database" where network is logically divided into hierarchy of hardware components and each component is treated as an object in the database. The "network in database" implementation guarantees data collection and storage flexibility. By implementing the NMS software distribution platform and the hardware independent WiSEMesh node software stack, our testbed is confirmed to achieve scalability.

High Mobility in a Realistic Wireless Environment: a Mobile IP Handoff Model for NS-2

Abstract: Wireless technology has the great merit to allow users' mobility. However, this may affect the functioning of all the applications and traditional protocols, worsening the already known problems with wireless connections and requiring the design and evaluation of novel solutions. Scenarios involving high mobility can be very complex; think, for instance, to a realistic case involving several nodes, representing people and cars moving under the coverage of several base stations. Since the geographical width and the number of involved nodes in such a scenario, simulations represent a fundamental tool to analyze the state of the art and newly proposed solutions. Unfortunately, modeling mobility with the most popular network simulator in the scientific community (i.e., NS-2) is not an easy task as its handoff mechanism appears faulty when coupled with a realistic model for wireless transmissions. In this paper, we discuss this problem and propose a new simulation module for mobile IP able to guarantee smooth handoffs even with realistic simulation set-ups.

Chowkidar: A Health Monitor for Wireless Sensor Network Testbeds

Abstract: Wireless sensor network (WSN) testbeds are useful because they provide a way to test applications in an environment that makes it easy to deploy experiments, configure them statically or dynamically, and gather performance information. Sensor data collected in the field can be replayed on nodes, and new ways to process the data can be tested easily. Testbeds are rapidly growing in size, with hundreds or thousands of devices, and testbed services are also becoming richer and more complex. Due to their size and complexity, faults can (and do) occur in these testbeds, affecting the outcomes of experiments. Awareness of testbed health status is important to both testbed administrators charged with maintaining functional services, and users who prefer to use healthy devices and like to know if there are any failures during their experiments. Based on our experience with Kansei, a large WSN testbed at Ohio State, we identify use cases that motivate the design of Chowkidar, a health monitoring facility. Key among these are: monitoring as a service that operates independently of users to provide up-to-date testbed status information; monitoring of heterogeneous testbed devices and networks; distinguishing between node and interface failures; and diagnosing common-mode failures such as power supply or Ethernet hub failure. We present in this paper, a centralized and a distributed Chowkidar protocol that reliably monitor the health of large, heterogenous WSN testbeds. We present experimentally measured Chowkidar performance as well as real experiences and lessons learnt from the integration of Chowkidar with Kansei, including feedback from both testbed users and administrators who have found Chowkidar to be a useful tool for improving the accuracy and efficiency of testbed experimentation and maintenance.

A File System Abstraction and Shell Interface for a Wireless Sensor Network Testbed

Abstract: Despite tremendous research interest and increased adoption, deeply embedded sensor networks are difficult to design, debug, and deploy; ultra-dependability remains an elusive goal. To address these difficulties, we have previously presented an Interactive, server-centric testbed for wireless sensor networks that targets systems constructed using nesC and TinyOS - the emerging standard in sensor system development. The testbed infrastructure exposes an API suite that enables users to rapidly configure, instrument, compile, install, and profile their systems on one or more remote network deployments. The prototype deployment consists of 80 Tmote Sky devices arranged in a regular grid. The architecture is extensible in both the hardware and software dimensions to foster adoption and specialization. In this paper, we demonstrate the extensibility of the testbed software design, and present a novel file system abstraction and shell interface developed using the original API suite. The design of the new interface is informed by user feedback from client institutions where the standard graphical interface is being used to support research and teaching activities. The new shell interface complements the traditional graphical interface, reducing interaction latency, and enabling programmatic experimentation through an interpreted scripting facility. We present the design and implementation of the new testbed interface, and present a small, but representative case-study that illustrates its utility.

SWARMS: A Sensornet Wide Area Remote Management System

Abstract: Our experiences deploying a wide area wireless sensor network (WSN) in the wildfires of Idaho motivate the need for a software middleware system capable of remotely managing many sensor nodes deployed in widely disparate geographic regions. This requirement is unlike the localized focus of many traditional WSN middleware systems, which manage a group of sensor nodes deployed in a single small region, e.g. a warehouse or lab. We describe in this paper SWARMS, a wide area sensor network management system. The SWARMS architecture is designed for scalability and flexibility, while providing an infrastructure to manage in situ sensor nodes, e.g. upload code images, retrieve diagnostics, etc. To demonstrate its flexibility, we present two deployments of SWARMS, the first in a wide area weather sensor network, and the second in a local area testbed that was used by a class of graduate students. To demonstrate its scalability, we analyze the performance of SWARMS when the middleware is subject to sensor data loads of thousands of packets per second.

SPHERE - A Simulation Platform for Heterogeneous Wireless Systems

Abstract: This paper presents SPHERE, a Simulation Platform for HEterogeneous wiREIess systems, and describes its motivation, methodology and implementation approach. This advanced system level simulation platform emulates simultaneously the transmission of GPRS, EDGE Multi-slot, HSDPA and WLAN at the packet level, which allows conducting novel investigations on common radio resource management for beyond 3G systems or on the optimization of radio resource management techniques. This paper presents the simulation platform, validates it and introduces its research potential.

A General Architecture in Support of Personalized, Interactive Multimedia Services in the Mobile Broadcast Convergent Environment

Abstract: The widespread use of 2G cellular systems and the availability of 3G cellular systems and mobile digital broadcast systems are facilitating the development of new personalized, interactive applications on mobile devices with limitations on computational resources and battery. However, as of today, most of these applications are unidirectional or target vehicle device as the terminal. This article describes a modular and general architecture that supports the development of interactive, multimedia, personalized applications, providing an extra level of service to the users. The performance evaluation of the architecture demonstrates that our prototype is friendly and easy to use, and saves power consumption.

The TeraPaths Testbed: Exploring End-to-End Network QoS

Abstract: The TeraPaths project at Brookhaven National Laboratory (BNL) investigates the combination of DiffServ-based LAN QoS with WAN MPLS tunnels in creating end-to-end (host-to-host) virtual paths with bandwidth guarantees. These virtual paths prioritize, protect, and throttle network flows in accordance with site agreements and user requests, and prevent the disruptive effects that conventional network flows can cause in one another. This paper focuses on the TeraPaths testbed, a collection of end-site subnets connected through high-performance WANs, serving the research and software development needs of the TeraPaths project. The testbed is rapidly evolving towards a multiple end-site infrastructure, dedicated to QoS networking research, and it offers unique opportunities for experimentation with minimal or no impact on regular, production networking operations.

Application Aware Optical Burst Switching Test-bed with SIP Based Session Control

Abstract: In this paper we propose a novel architecture for the control plane of an application aware optical burst switching (OBS) network, able to support grid computing applications. We suggest the use of the session initiation protocol (SIP) to implement a protocol layer between the grid specific control messages and the network control plane. The proposed architecture was implemented in an existing OBS network test-bed and was successfully tested as described in the paper.