Computer Science snBench: A Programming and Runtime Framework for Sensor Networks Michael Ocean with Azer Bestavros and Assaf Kfoury.

Slides:



Advertisements
Similar presentations
anywhere and everywhere. omnipresent A sensor network is an infrastructure comprised of sensing (measuring), computing, and communication elements.
Advertisements

Sensor Network Platforms and Tools
Overview: Chapter 7  Sensor node platforms must contend with many issues  Energy consumption  Sensing environment  Networking  Real-time constraints.
A system Performance Model Instructor: Dr. Yanqing Zhang Presented by: Rajapaksage Jayampthi S.
University of Houston So What’s Exascale Again?. University of Houston The Architects Did Their Best… Scale of parallelism Multiple kinds of parallelism.
Background Computer System Architectures Computer System Software.
Adding WiFi sensors to the infrastructure  Linksys Access Points run as “Kismet drones” passively monitoring all and report wireless frames over.
1 SAFIRE Project DHS Update – July 15, 2009 Introductions  Update since last teleconference Demo Video - Fire Incident Command Board (FICB) SAFIRE Streams.
Design and Implementation of a Middleware for Sentient Spaces Bijit Hore, Hojjat Jafarpour, Ramesh Jain, Shengyue Ji, Daniel Massaguer Sharad Mehrotra,
SCORE - Stream Computations Organized for Reconfigurable Execution Eylon Caspi, Michael Chu, Randy Huang, Joseph Yeh, Yury Markovskiy Andre DeHon, John.
Components for high performance grid programming in the GRID.it project 1 Workshop on Component Models and Systems for Grid Applications - St.Malo 26 june.
CS244-Introduction to Embedded Systems and Ubiquitous Computing Instructor: Eli Bozorgzadeh Computer Science Department UC Irvine Winter 2010.
Jan 31, 2007CS5111 Unbound STEP graph Bound STEP graph Resource management components solve graph embedding Deployment Sensor eXecution Environments Remember.
FI-WARE – Future Internet Core Platform FI-WARE Cloud Hosting July 2011 High-level description.
Program and deploy your SN in minutes  Program: Single System Image  “Write Once, Run… Wherever”  Each program runs on an SN “slice” i.e., a Virtual.
Pervasive Computing: What is it good for? Andrew C. Huang et all Stanford University Presented by Kalpana Banerjee.
If You Build It, They Will Come: The SN B ENCH Architecture Adam Bradley Azer Bestavros & Michael Long Computer Science.
Program and deploy your SN in minutes –Single System Image Program –“Write Once, Run… Wherever” –Each program runs on an SN “slice” i.e., a Virtual Sensor.
An Introduction to the Sensor Network WorkBench -- SN Bench Michael Ocean Azer Bestavros & Assaf Kfoury Computer Science.
Copyright © 2011 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Chapter 2 Overview of Database Languages and Architectures.
BRASS Analysis of QuasiStatic Scheduling Techniques in a Virtualized Reconfigurable Machine Yury Markovskiy, Eylon Caspi, Randy Huang, Joseph Yeh, Michael.
 Introduction Introduction  Definition of Operating System Definition of Operating System  Abstract View of OperatingSystem Abstract View of OperatingSystem.
Distributed Database The University of California Berkeley Extension Copyright © 2011 Patrick McDermott.
Computer System Architectures Computer System Software
MiLAN: Middleware to Support Sensor Network Applications Jonghak Kim, Da Huo, Hyungik Oh.
©Ian Sommerville 2006Software Engineering, 8th edition. Chapter 12 Slide 1 Distributed Systems Architectures.
Introduction to the Atlas Platform Mobile & Pervasive Computing Laboratory Department of Computer and Information Sciences and Engineering University of.
An approach to Intelligent Information Fusion in Sensor Saturated Urban Environments Charalampos Doulaverakis Centre for Research and Technology Hellas.
MSR Sense The Microsoft Research Networked Embedded Sensing Toolkit Stewart Tansley, PhD Adapted from: Feng Zhao.
Virtualization. Virtualization  In computing, virtualization is a broad term that refers to the abstraction of computer resources  It is "a technique.
International Conference on Software Engineering 2007
PhD Topic Template Based Composition PhD Course 5 th March – 9 th March 2012, Kaiserslautern.
An Integration Framework for Sensor Networks and Data Stream Management Systems.
Cluster Reliability Project ISIS Vanderbilt University.
Enterprise Java Beans Java for the Enterprise Server-based platform for Enterprise Applications Designed for “medium-to-large scale business, enterprise-wide.
Wireless Networks of Devices (WIND) Hari Balakrishnan and John Guttag MIT Lab for Computer Science NTT-MIT Meeting, January 2000.
Sogang University Advanced Computing System Chap 1. Computer Architecture Hyuk-Jun Lee, PhD Dept. of Computer Science and Engineering Sogang University.
한국기술교육대학교 컴퓨터 공학 김홍연 Habitat Monitoring with Sensor Networks DKE.
System Architecture Directions for Networked Sensors Jason Hill, Robert Szewczyk, Alec Woo, Seth Hollar, David Culler, Kris Pister Presented by Yang Zhao.
Architecture for Autonomous Assembly 1 Reid Simmons Robotics Institute Carnegie Mellon University.
1 SATWARE: A Semantic Middleware for Multi Sensor Applications Sharad Mehrotra.
© 2004 Mercury Computer Systems, Inc. FPGAs & Software Components Graham Bardouleau & Jim Kulp Mercury Computer Systems, Inc. High Performance Embedded.
snBENCH A Development and Run-Time Platform for Rapid Deployment of Sensor Network Applications Michael Ocean Azer Bestavros.
Investigating Survivability Strategies for Ultra-Large Scale (ULS) Systems Vanderbilt University Nashville, Tennessee Institute for Software Integrated.
CS244-Introduction to Embedded Systems and Ubiquitous Computing Instructor: Eli Bozorgzadeh Computer Science Department UC Irvine Winter 2010.
Application of Operating System Concepts to Coordination in Pervasive Sensing and Computing Systems Benjamin J. Ewy, Larry M. Sanders Ambient Computing,
Network Computing Laboratory A programming framework for Stream Synthesizing Service.
1 Run-Time Software Engineering An approach for Embedded and Ubiquitous Computing Environments Sooyong Park Sogang University South.
snBENCH A Development and Run-Time Platform for Rapid Deployment of Sensor Network Applications Michael Ocean Azer Bestavros.
Real-Time Support for Mobile Robotics K. Ramamritham (+ Li Huan, Prashant Shenoy, Rod Grupen)
Department of Computer Science MapReduce for the Cell B. E. Architecture Marc de Kruijf University of Wisconsin−Madison Advised by Professor Sankaralingam.
Virtualization and Databases Ashraf Aboulnaga University of Waterloo.
Programming Sensor Networks Andrew Chien CSE291 Spring 2003 May 6, 2003.
DESIGN OF SOFTWARE ARCHITECTURE
CS 351/ IT 351 Modeling and Simulation Technologies HPC Architectures Dr. Jim Holten.
Design and implementation of an intentional naming system William Adjie-WinotoElliot Schwartz Hari BalakrishnanJeremy Lilley MIT Laboratory for Computer.
DR. SIMING LIU SPRING 2016 COMPUTER SCIENCE AND ENGINEERING UNIVERSITY OF NEVADA, RENO Session 2 Computer Organization.
3/12/2013Computer Engg, IIT(BHU)1 INTRODUCTION-1.
Towards an IoT Ecosystem Flavia C. Delicato 1, Paulo F. Pires 1, Thais Batista 2, Everton Cavalcante 2, Bruno Costa 1, Thomaz Barros 1 1 Department of.
3/12/2013Computer Engg, IIT(BHU)1 CONCEPTS-1. Pipelining Pipelining is used to increase the speed of processing It uses temporal parallelism In pipelining,
Gaia An Infrastructure for Active Spaces Prof. Klara Nahrstedt Prof. David Kriegman Prof. Dennis Mickunas
University of Texas at Arlington Scheduling and Load Balancing on the NASA Information Power Grid Sajal K. Das, Shailendra Kumar, Manish Arora Department.
Ocean Observatories Initiative OOI Cyberinfrastructure Common Execution Infrastructure Michael Meisinger OOI Cyberinfrastructure Life Cycle Objectives.
Background Computer System Architectures Computer System Software.
May 7-8, 2007ICVCI 2007 RTP Autonomic Approach to IT Infrastructure Management in a Virtual Computing Lab Environment H. Abdel SalamK. Maly R. MukkamalaM.
Embedded Real-Time Systems Introduction to embedded software development Lecturer Department University.
Software Architecture of Sensors. Hardware - Sensor Nodes Sensing: sensor --a transducer that converts a physical, chemical, or biological parameter into.
Planning for Human-Robot Collaboration
What time is it?. What time is it? Major Concepts: a data structure model: basic representation of data, such as integers, logic values, and characters.
Client/Server Computing and Web Technologies
Presentation transcript:

Computer Science snBench: A Programming and Runtime Framework for Sensor Networks Michael Ocean with Azer Bestavros and Assaf Kfoury

Computer Science Motivation (sensing change)  Traditional Sensor Networks :  Homogeneous nodes  Highly constrained (e.g., computation, communication, power, etc.)  Nodes programmed for a single common goal  “Embedded” Sensor Networks (Sensoria) :  Heterogeneous nodes/Hybrid networks  Varied constraints on devices/networks  Program the network to achieve multiple (potentially conflicting) goals running simultaneously

Computer Science Motivation (sensing change) What sensors can I use and what functionality do I get from them?  Embedded SNs (“Sensoria”) :  Heterogeneous nodes  Varied constraints  Program the network  diff't goals running simultaneously

Computer Science snBench: Programming Cycle  Program  SNAFU language high-level “glue”  Compile  A SNAFU program is compiled into a Sensorium Task Execution Plan (STEP)  Map and Link  STEPs are decomposed in smaller dispatch-able (baby) STEPs which are linked to resources  Load and Execute  Linked STEPs are dispatched to sensor runtime/execution environments (SXEs)

Computer Science SNet Apps as FUnctions  SNAFU: functional specification language  computation, sensing, communication, storage, values, etc.  e.g., identify the face seen through camera 1  Use “annotative” functions for constraints  e.g., what streams can be “exposed”  e.g., minimum acceptable resolution identify(facefind(grabframe(cam1))) public(facecount(grabframe(private(cam1))))) facecount(resn(800x600x24b,grabframe(cam1)) )

Computer Science Sensorium Task Execution Plan  SNAFU is compiled into STEP  our “Instruction Set Architecture” cam2 snapshot motion clock4am 2am << && trigger trigger( (motion(snapshot(cam2)) && (2am<NOW<4am)), snapshot(cam2))) snafu program Sensorium Task Execution Plan

Computer Science Sensorium Task Execution Plan  serialized as XML

Computer Science Infrastructure support  Scheduling/linking as graph partitioning SXE ? cam2 snapshot motion clock4am 2am << && trigger

Computer Science Infrastructure support  Sensorium Resource Manager (SRM)  Manage “local”-area Sensorium resources  Sensorium Service Dispatcher (SSD)  STEP scheduling, deployment and monitoring: SD, SXE SXE

Computer Science Sensor eXecution Environment  Shares local (virtual) resources with the Sensorium  Abstraction of local resources through STEP program abstraction  Advertises computational and sensing capabilities to SSD  Accepts STEPs from SSD  STEP interpreter  can be dynamically tasked with new functionalities via the network