Abstract. Deploying and controlling experiments running on a distributed set of resources is a challenging task. Software developers often spend a significant amount of time dealing with the complexities associated with resource configuration and management in these environments. Experiment control systems are designed to automate the process, and to ultimately help developers cope with the common problems that arise during the design, implementation, and evaluation of distributed systems. However, many of the existing control systems were designed with specific computing environments in mind, and thus do not provide support for heterogeneous resources in different testbeds. In this paper, we explore the functionality of Gush, an experiment control system, and discuss how it supports execution on three of the four GENI control frameworks. 1

We investigate if WiFi access can be used to augment 3G capacity. To understand the feasibility of 3G augmentation, we conduct a detailed study of 3G and WiFi access from moving vehicles, in three different cities. We find that the average 3G and WiFi availability across the testbeds is 87 % and 11%, respectively. We also find that, unlike stationary environments, WiFi throughput is lower than 3G throughput in mobile environments, and WiFi loss rates are higher. We then design a system, called Wiffler, that uses two key ideas—leveraging delay tolerance and fast switching. For delay tolerant applications, Wiffler uses a simple model of the environment to predict WiFi connectivity, and delays applications to offload more data on WiFi. But Wiffler delays applications only if it results in 3G savings. For applications that are extremely sensitive to delay or loss (e.g., VoIP), Wiffler quickly switches to 3G if WiFi is unable to successfully transmit the packet within a small time window. We implement and deploy Wiffler in our vehicular testbed. Both our implementation and trace-driven experiments show that Wiffler significantly increases 3G savings. For example, for a realistic workload, Wiffler reduces 3G usage by 45 % for a delay tolerance of 60 seconds. 1.

We investigate if WiFi access can be used to augment 3G capacity in mobile environments. We first conduct a detailed study of 3G and WiFi access from moving vehicles, in three different cities. We find that the average 3G and WiFi availability across the cities is 87 % and 11%, respectively. WiFi throughput is lower than 3G throughput, and WiFi loss rates are higher. We then design a system, called Wiffler, to augments mobile 3G capacity. It uses two key ideas— leveraging delay tolerance and fast switching—to overcome the poor availability and performance of WiFi. For delay tolerant applications, Wiffler uses a simple model of the environment to predict WiFi connectivity. It uses these predictions to delays transfers to offload more data on WiFi, but only if delaying reduces 3G usage and the transfers can be completed within the application’s tolerance threshold. For applications that are extremely sensitive to delay or loss (e.g., VoIP), Wiffler quickly switches to 3G if WiFi is unable to successfully transmit the packet within a small time window. We implement and deploy Wiffler in our vehicular testbed. Our experiments show that Wiffler significantly reduces 3G usage. For a realistic workload, the reduction is 45 % for a delay tolerance of 60 seconds.

This document describes the test bed creation and methodology used in the N4C field tests. The methodology has developed in accordance with experience gained from the (hitherto) three N4C field tests. The document provides an introduction to methodological steps and practical guidelines to eventually achieve Living Labs type of field tests covering the N4C tests background, technical choices, practical issues, theoretical aspects and the methods to approach the stochastic and other challenges on the test field. Several concrete contexts of use are presented. The goal is to build at least one sustainable and long term test bed that can be operated also after the 36 months project N4C has ended. Due date of deliverable 2009-12-30: Actual submission date: 2010-02-10

The rise of new ways of communication along with the spread of mobile Internet will encourage the evolution of public transports to provide uninterrupted Internet service to its customers. It is obvious that using multiple technologies such as Wi-Fi, 3G and satellite each with their own characteristics will enhance the connectivity. Current proposals for mobility are mainly based on the use of proxies and need the modification of the infrastructure. The multi-homing feature included in SCTP allows roaming without losses and without interrupting the session. This study focuses on the use of geo-localization to improve SCTP handover, and shows how it can be implemented and what improvements can be done. KEYWORDS: geo-localization, handover, mobility, multi-homing, public transports, SCTP. 1.

Mobile devices are increasingly being relied on for tasks that go beyond simple connectivity and demand more complex processing. The primary approach in wide use today uses cloud computing resources to off-load the “heavy lifting ” to specially designated servers when they are well connected. In reality, a mobile device often encounters, albeit intermittently, many entities capable of lending computational resources. In this work-in-progress paper we first give an overview of this environment, which we call a Cirrus Cloud due to its intermittent connectivity feature, and explain how it provides a spectrum of computational contexts for remote computation in a mobile environment. An ultimately successful system will need to have the flexibility to handle intermittent connectivity and use a mix of options on that spectrum. We investigate two scenarios at the extremes of the spectrum: 1) a scenario where a mobile device experiences intermittent connectivity to a central cloud computing resource, and 2) a scenario where a mobile device off-loads computation to other mobile devices it might meet intermittently. We present preliminary designs, implementations, and evaluations of systems that enable a mobile application to use remote computational resources to speedup computing and conserve energy in these scenarios. The preliminary results show the effectiveness of our systems and demonstrate the potential of computing

Abstract not found