Abstract — In this paper, we present the design, implementation, and evaluation of the iPlane, a scalable service providing accurate predictions of Internet path performance for emerging overlay services. Unlike the more common black box latency prediction techniques in use today, the iPlane builds an explanatory model of the Internet. We predict end-to-end performance by composing measured performance of segments of known Internet paths. This method allows us to accurately and efficiently predict latency, bandwidth, capacity and loss rates between arbitrary Internet hosts. We demonstrate the feasibility and utility of the iPlane service by applying it to several representative overlay services in use today: content distribution, swarming peer-to-peer filesharing, and voice-over-IP. In each case, we observe that using iPlane’s predictions leads to a significant improvement in end user performance. 1

To use their pool of resources efficiently, distributed stream-processing systems push query operators to nodes within the network. Currently, these operators, ranging from simple filters to custom business logic, are placed manually at intermediate nodes along the transmission path to meet application-specific performance goals. Determining placement locations is challenging because network and node conditions change over time and because streams may interact with each other, opening venues for reuse and repositioning of operators. This paper describes a stream-based overlay network (SBON), a layer between a stream-processing system and the physical network that manages operator placement for stream-processing systems. Our design is based on a cost space, an abstract representation of the network and on-going streams, which permits decentralized, large-scale multi-query optimization decisions. We present an evaluation of the SBON approach through simulation, experiments on PlanetLab, and an integration with Borealis, an existing stream-processing engine. Our results show that an SBON consistently improves network utilization, provides low stream latency, and enables dynamic optimization at low engineering cost.

This paper presents the architecture of PIER , an Internetscale query engine we have been building over the last three years. PIER is the first general-purpose relational query processor targeted at a peer-to-peer (p2p) architecture of thousands or millions of participating nodes on the Internet. It supports massively distributed, database-style dataflows for snapshot and continuous queries. It is intended to serve as a building block for a diverse set of Internet-scale informationcentric applications, particularly those that tap into the standardized data readily available on networked machines, including packet headers, system logs, and file names

Vehicular sensor networks are emerging as a new network paradigm of primary relevance, especially for proactively gathering monitoring information in urban environments. Vehicles typically have no strict constraints on processing power and storage capabilities. They can sense events (e.g., imaging from streets), process sensed data (e.g., recognizing license plates), and route messages to other vehicles (e.g., diffusing relevant notification to drivers or police agents). In this novel and challenging mobile environment, sensors can generate a sheer amount of data, and traditional sensor network approaches for data reporting become unfeasible. This paper proposes MobEyes, an efficient lightweight support for proactive urban monitoring based on the primary idea of exploiting vehicle mobility to opportunistically diffuse summaries about sensed data. The reported experimental/analytic results show that MobEyes can

sensor networks

A key problem in current sensor network technology is the heterogeneity of the available software and hardware platforms which makes deployment and application development a tedious and time consuming task. To minimize the unnecessary and repetitive implementation of identical functionalities for different platforms, we present our Global Sensor Networks (GSN) middleware which supports the flexible integration and discovery of sensor networks and sensor data, enables fast deployment and addition of new platforms, provides distributed querying, filtering, and combination of sensor data, and supports the dynamic adaption of the system configuration during operation. GSN’s central concept is the virtual sensor abstraction which enables the user to declaratively specify XML-based deployment descriptors in combination with the possibility to integrate sensor network data through plain SQL queries over local and remote sensor data sources. In this demonstration, we specifically focus on the deployment aspects and allow users to dynamically reconfigure the running system, to add new sensor networks on the fly, and to monitor the effects of the changes via a graphical interface. The GSN implementation is available from

Abstract — This paper describes the architecture and programming model of a semantic-service-oriented sensor information system platform. We argue that the key to enabling scalable sensor information access is to define an ontology and associated sensor information hierarchy for interpretation of raw data streams. The ontological abstraction allows a sensing system to optimize its resource utilization in collecting, storing, and processing data. We describe the SONGS architecture that uses an automatic service planning to convert declarative user queries into a service composition graph, and performs compile-time and run-time optimizations for resource-aware execution of the service composite in a sensor network, building on the sensor information hierarchy. We motivate and demonstrate the SONGS platform using a parking garage example. I.

The development of a reliable large-scale wireless sensor networks (WSNs) is very difficult because of their stringent resource constraints, harsh energy budget, and demanding application requirements. We identify that three OS features – OS protection, virtual memory, and preemptive scheduling – will significantly improve the reliability of WSN systems and facilitate developing complex WSN software. However, due to the limitation of hardware, it is impossible to implement these features with traditional OS design techniques. To solve this problem, we design a new OS kernel, the tkernel, to perform extensive load-time code modification and enhance the system abstraction visible to programmers. After the modification, the application and OS work in a collaborative way supporting the aforementioned features. Having implemented the t-kernel on MICA2 motes with an 8-bit processor and 4KB RAM, we evaluate its performance by measuring the overhead and execution speed. We analyze the CPU utilization in sensor network applications, and verify that, though CPU-bound computation tasks may slow down 0.5–4 times, the performance of applications under typical workloads does not degrade. The t-kernel significantly enhances developers ’ ability to design sophisticated applications and protects WSNs from accidental programming errors. To the authors ’ best knowledge, the t-kernel is unique in the follow ways: it performs efficient binary translation on highly resource constrained sensor nodes with only 4KB RAM, it provides software based virtual memory without repeatedly writable swapping devices, and it protects OS from application error without memory protection or privileged execution hardware. 1

Sensor networks offer a powerful combination of distributed sensing, computing and communication. They lend themselves to countless applications and, at the same time, offer numerous challenges due to their peculiarities, primarily the stringent energy constraints to which sensing nodes are typically subjected. The distinguishing traits of sensor networks have a direct impact on the hardware design of the nodes at at least four levels: power source, processor, communication hardware, and sensors. Various hardware platforms have already been designed to test the many ideas spawned by the research community and to implement applications to virtually all fields of science and technology. We are convinced that CAS will be able to provide a substantial contribution to the development of this exciting field.

Our work is motivated by two observations about the state of networks today. Operators have little visibility into the end users' network experience while end users have little information or recourse when they encounter problems. We propose a system called NetProfiler, in which end hosts share network performance information with other hosts over a peer-to-peer network. The aggregated information from multiple hosts allows NetProfiler to profile the wide-area network, i.e., monitor end-to-end performance, and detect and diagnose problems from the perspective of end hosts. We define a set of attribute hierarchies associated with end hosts and their network connectivity. Information on the network performance and failures experienced by end hosts is then aggregated along these hierarchies, to identify patterns (e.g., shared attributes) that might be indicative of the source of the problem. In some cases, such sharing of information can also enable end hosts to resolve problems by themselves. The results from a 4-week-long Internet experiment indicate the promise of this approach.