Samuel Madden

TAG: a Tiny AGgregation service for Ad-Hoc sensor networks

We present the Tiny AGgregation (TAG) service for aggregation in low-power, distributed, wireless environments. TAG allows users to express simple, declarative queries and have them distributed and executed efficiently in networks of low-power, wireless sensors. We discuss various generic properties of aggregates, and show how those properties affect the performance of our in network approach. We include a performance study demonstrating the advantages of our approach over traditional centralized, out-of-network methods, and discuss a variety of optimizations for improving the performance and fault tolerance of the basic solution.

TinyDB: an acquisitional query processing system for sensor networks

We discuss the design of an acquisitional query processor for data collection in sensor networks. Acquisitional issues are those that pertain to where, when, and how often data is physically acquired (sampled) and delivered to query processing operators. By focusing on the locations and costs of acquiring data, we are able to significantly reduce power consumption over traditional passive systems that assume the a priori existence of data. We discuss simple extensions to SQL for controlling data acquisition, and show how acquisitional issues influence query optimization, dissemination, and execution. We evaluate these issues in the context of TinyDB, a distributed query processor for smart sensor devices, and show how acquisitional techniques can provide significant reductions in power consumption on our sensor devices.

TinyOS: An Operating System for Sensor Networks

We present TinyOS, a flexible, application-specific operating system for sensor networks, which form a core component of ambient intelligence systems. Sensor networks consist of (potentially) thousands of tiny, low-power nodes, each of which execute concurrent, reactive programs that must operate with severe memory and power constraints. The sensor network challenges of limited resources, event-centric concurrent applications, and low-power operation drive the design of TinyOS. Our solution combines flexible, fine-grain components with an execution model that supports complex yet safe concurrent operations. TinyOS meets these challenges well and has become the platform of choice for sensor network research; it is in use by over a hundred groups worldwide, and supports a broad range of applications and research topics. We provide a qualitative and quantitative evaluation of the system, showing that it supports complex, concurrent programs with very low memory requirements (many applications fit within 16KB of memory, and the core OS is 400 bytes) and efficient, low-power operation.We present our experiences with TinyOS as a platform for sensor network innovation and applications.

The design of an acquisitional query processor for sensor networks

We discuss the design of an acquisitional query processor for data collection in sensor networks. Acquisitional issues are those that pertain to where, when, and how often data is physically acquired (sampled) and delivered to query processing operators. By focusing on the locations and costs of acquiring data, we are able to significantly reduce power consumption over traditional passive systems that assume the a priori existence of data. We discuss simple extensions to SQL for controlling data acquisition, and show how acquisitional issues influence query optimization, dissemination, and execution. We evaluate these issues in the context of TinyDB, a distributed query processor for smart sensor devices, and show how acquisitional techniques can provide significant reductions in power consumption on our sensor devices.

A comparison of approaches to large-scale data analysis

There is currently considerable enthusiasm around the MapReduce (MR) paradigm for large-scale data analysis [17]. Although the basic control flow of this framework has existed in parallel SQL database management systems (DBMS) for over 20 years, some have called MR a dramatically new computing model [8, 17]. In this paper, we describe and compare both paradigms. Furthermore, we evaluate both kinds of systems in terms of performance and development complexity. To this end, we define a benchmark consisting of a collection of tasks that we have run on an open source version of MR as well as on two parallel DBMSs. For each task, we measure each systems performance for various degrees of parallelism on a cluster of 100 nodes. Our results reveal some interesting trade-offs. Although the process to load data into and tune the execution of parallel DBMSs took much longer than the MR system, the observed performance of these DBMSs was strikingly better. We speculate about the causes of the dramatic performance difference and consider implementation concepts that future systems should take from both kinds of architectures.

The pothole patrol: using a mobile sensor network for road surface monitoring

This paper investigates an application of mobile sensing: detecting and reporting the surface conditions of roads. We describe a system and associated algorithms to monitor this important civil infrastructure using a collection of sensor-equipped vehicles. This system, which we call the Pothole Patrol (P2), uses the inherent mobility of the participating vehicles, opportunistically gathering data from vibration and GPS sensors, and processing the data to assess road surface conditions. We have deployed P2 on 7 taxis running in the Boston area. Using a simple machine-learning approach, we show that we are able to identify potholes and other severe road surface anomalies from accelerometer data. Via careful selection of training data and signal features, we have been able to build a detector that misidentifies good road segments as having potholes less than 0.2% of the time. We evaluate our system on data from thousands of kilometers of taxi drives, and show that it can successfully detect a number of real potholes in and around the Boston area. After clustering to further reduce spurious detections, manual inspection of reported potholes shows that over 90% contain road anomalies in need of repair.

Query processing in sensor networks

Smart sensors are small wireless computing devices that sense information such as light and humidity at extremely high resolutions. A smart sensor query-processing architecture using database technology can facilitate deployment of sensor networks. Smart-sensor technology enables a broad range of ubiquitous computing applications. Their low cost, small size, and untethered nature lets them sense information at previously unobtainable resolutions. We discuss about query processing in sensor networks.

Continuously adaptive continuous queries over streams

We present a continuously adaptive, continuous query (CACQ) implementation based on the eddy query processing framework. We show that our design provides significant performance benefits over existing approaches to evaluating continuous queries, not only because of its adaptivity, but also because of the aggressive cross-query sharing of work and space that it enables. By breaking the abstraction of shared relational algebra expressions, our Telegraph CACQ implementation is able to share physical operators --- both selections and join state --- at a very fine grain. We augment these features with a grouped-filter index to simultaneously evaluate multiple selection predicates. We include measurements of the performance of our core system, along with a comparison to existing continuous query approaches.

TelegraphCQ: continuous dataflow processing

At Berkeley, we are developing TelegraphCQ [1, 2], a dataflow system for processing continuous queries over data streams. TelegraphCQ is based on a novel, highly-adaptive architecture supporting dynamic query workloads in volatile data streaming environments. In this demonstration we show our current version of TelegraphCQ, which we implemented by leveraging the code base of the open source PostgreSQL database system. Although TelegraphCQ differs significantly from a traditional database system, we found that a significant portion of the PostgreSQL code was easily reusable. We also found the extensibility features of PostgreSQL very useful, particularly its rich data types and the ability to load user-developed functions. Challenges: As discussed in [1], sharing and adaptivity are our main techniques for implementing a continuous query system. Doing this in the codebase of a conventional database posed a number of challenges:

Supporting aggregate queries over ad-hoc wireless sensor networks

We show how the database communitys notion of a generic query interface for data aggregation can be applied to ad-hoc networks of sensor devices. As has been noted in the sensor network literature, aggregation is important as a data reduction tool; networking approaches, however, have focused on application specific solutions, whereas our in-network aggregation approach is driven by a general purpose, SQL-style interface that can execute queries over any type of sensor data while providing opportunities for significant optimization. We present a variety of techniques to improve the reliability and performance of our solution. We also show how grouped aggregates can be efficiently computed and offer a comparison to related systems and database projects.