New User Special Price Expires in

Let's log you in.

Sign in with Facebook


Don't have a StudySoup account? Create one here!


Create a StudySoup account

Be part of our community, it's free to join!

Sign up with Facebook


Create your account
By creating an account you agree to StudySoup's terms and conditions and privacy policy

Already have a StudySoup account? Login here

Distributed & Pervasive Compt

by: Abe Jones

Distributed & Pervasive Compt CS 556

Marketplace > West Virginia University > ComputerScienence > CS 556 > Distributed Pervasive Compt
Abe Jones
GPA 3.77


Almost Ready


These notes were just uploaded, and will be ready to view shortly.

Purchase these notes here, or revisit this page.

Either way, we'll remind you when they're ready :)

Preview These Notes for FREE

Get a free preview of these Notes, just enter your email below.

Unlock Preview
Unlock Preview

Preview these materials now for free

Why put in your email? Get access to more of this material and other relevant free materials for your school

View Preview

About this Document

Class Notes
25 ?




Popular in Course

Popular in ComputerScienence

This 57 page Class Notes was uploaded by Abe Jones on Saturday September 12, 2015. The Class Notes belongs to CS 556 at West Virginia University taught by Staff in Fall. Since its upload, it has received 5 views. For similar materials see /class/202771/cs-556-west-virginia-university in ComputerScienence at West Virginia University.

Similar to CS 556 at WVU

Popular in ComputerScienence


Reviews for Distributed & Pervasive Compt


Report this Material


What is Karma?


Karma is the currency of StudySoup.

You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!

Date Created: 09/12/15
Suhasini kallur u quot ALAN JONES Olivetti and OracleRe seamh laboratory ANDY HOPPER Univ of Cambridge computer laboratory Olivetti and Oracle Research laboratory Need for context aware computation gt Configuration of the computing and communications systems requires the attention of the user gt The complexity of the configuration of the electronic devices may increase in the future gt Hence computers are designed to be context aware gt A context aware computer or application must be able to determine the state of its surroundings LocationAvvare Computing gt Active Badges Small computing devices worn by a person gt Equipment TagsPlaced on the computer and printers reporting their position to the main system gt Parc Tab Is a PDA similar to the Active Badges They implement applications involving context triggered actions automatic reconfiguration and also a memory prosthesis Sensor Technologies gt Electromagnetic trackers 9 10 can determine object locations and orientations to a high accuracy but are expensive and require tethers to control units gt Optical trackers are very robust and can achieve levels of accuracy and resolution similar to those of electromagnetic tracking systems However they are most useful in wellconstrained environments and tend to be expensive and mechanically complex gt Radio positioning systems such as Global Positioning System GPS and LORAN 13 are very successful in the wide area but ineffective in buildings because of lesser proximity the radio signals reflect very often in indoor environments gt Accurate object locations can be determined using video images captured using relatively cheap hardware but large amounts of computer processing Location Technique gt The time of flights of sound pulses from an ultrasonic transmitter are measured gt The hardware consists of a small wireless transmitter and a matrix of receiver elements amplifier rectifier ADC and a FPGA gt The transmitterreceiver distance was detected is calculated using multilateration gt The transmitter and the receiver positions are then calculated gt Two techniques are used to determine and V eliminate in case of inaccurate distance measurements a Comparing the transmitter receiver distance and the two receivers distance b A second statistical test is based on the observation that the proportion of receivers which detect only reflected signals is small The orientation of objects is estimated from the positions of the devices placed at non collinear points Applications Information from ORL system to better the number of existing applications Some of them gt Active Badge data can be used to choose the nearest telephone or printer gt videophones can select appropriate cameras displays speakers and microphones in places where user are and what input and output devices they could interact with gt Location devices can also be used to signal gestures to do a particular task and to control certain devices Jeffrey Highmwer Gaetano Borriello gt Ubiquitous computing is in it s way addressing the problem of automatic location sensing gt It is striving to answer questions like What lab bench was I standing by when I prepared these tissue samples How should our searchandrescue team move to quickly locate all the avalanche victims Can I automatically display this stock devaluation chart on the large screen I am standing next to Location system gt Location system Techniques can be used to detect people objects or both Triangulation can be done via lateration which uses multiple distance measurements between known points or via angulation which measures angle or bearing relative to points with known separation Proximity measures nearness to a known set of points Scene analysis examines a view from a particular vantage point Properties of these systems gt Physical location and symbolic location GPS is an example that provides physical location information Symbol location gives information about where something is gt Absolute vs Relative An absolute system uses shared reference grid for all located objects In contrast each object has its own frame of reference in a relative system gt Localized location computation This property describes that a located object computes its position itself Personal badge location systems can be an example of this system gt Accuracy and precision The location system must provide the user data accurately and with a better precision gt Scale The scale of a system is calculated from the coverage area per unit of infrastructure number of objects the system can locate per unit of infrastructure per interval gt Recognition Automatic Identification system is used when recognized objects are to be classified to take the appropriate action A common technique is using the GUID globally unique lD s Cost Cost is also one factor that has to be considered in designing a system They can be of various types Capital Time Space gt Limitations All systems might not be compatible in all environments Some iocazfiom systems gt Active Badge A small infrared badge worn by personnel that radiates GUID every 10secs or on demand Active Bat This uses an ultra sound timeofflight lateration technique to provide the location to the receiver gt Cricket Contrast to active bat system the Cricket Location support uses ultra sound emitters to create the infrastructure and embeds receivers in object being located gt Radar It measures the signal strength sn ratio a device send at the base station to locate the 2D position of an object in a building gtMotionStar magnetic tracker These tracking systems generate axial DC magneticfield pulses from a transmitting antenna in a fixed location The system computes the position and orientation of the receiving antennas by measuring the response in three orthogonal axes to the transmitted field pulse combined with the constant effect of the earth s magnetic field gt Easy living This approach depicts a way in which the Digiclops realtime 3D cameras are used to provide an accurate vision capability in a home gt Smart floor This floor captures the footfalls and this data used to track a person s position Does not require use of any tag or badge to be used gt E911 Used to locate the places from where the emergency calls come THANK YOU Design of EnergyAdaptive Systems By Rajesh Vuppala Design of EnergyAdaptive Systems Constraints of Mobile Computinq 0 Mobile elements are resource poor relative to static elements 0 Mobility is inherently hazardous Mobile connectivity is highly variable in performance and reliability Mobile elements rely on a finite energy source Design of EnergyAdaptive Systems Resource Scarcitv or Finite Enerqv Source 0 The utility of a mobile computer such as a laptop is largely constrained by battery life 0 The display is a major consumer of battery energy 0 The next major consumers of battery are Hard Disk and Processor CPU Design of EnergyAdaptive Systems Design of EnergyAdaptive Systems 0 The processes running on the system and the display consume energy for their operation 0 So reducing the energy consumed by display and processor can overcome the constraint of mobile computing to some extent Design of EnergyAdaptive Systems Previous approaches to reduce enerqv W 39 Turning off entire display when not in use 0 Using lower quality or smaller sized displays to minimize power Design of EnergyAdaptive Systems User Study 0 Microsoft Windows environment 0 17 users 0 Wide range of tasks An application level logger program was run on the users machines to collect periodic information about 6 The current window of focus its size its location and its title 7 The size of total screen used Design of EnergyAdaptive Systems User Studv Results 0 On average only 59 of the entire screen area is used focused by the user 0 Additional 17 of the screen is used for background windows that are not minimized EnergyAdaptive Display System Designs Workloads can be classified into 2 Access related web browsing and e mail 3 Personal productivity and code development 4 System related and application control windows EnergyAdaptive Display System Designs Probosal based on the followind facts 0 Different workloads and users have varying display needs 0 Full screen is not used by the users all the time Only a part of the screen is usually focused by the user at any point of time 0 Processor is not busy all the time EnergyAdaptive System Designs Current approaches to reduce enerqv consumption 39 Use of Organic Light Emitting Diodes OLEDs 0 Use of Software optimizations called Dark Windows 0 Use of CPU Scheduling Algorithms EnergyAdaptive Display System Designs EnergyAdaptive Display System Designs HARDWARE LEVEL ADAPTATION 0 At the hardware level energy consumption can be reduced by use of OLED displays 0 OLEDs consume energy proportional to the overall light output of the display EnergyAdaptive Display System Designs OLEDs are made up of organic molecules which emit light when stimulated by an electric field a uLEDschemnllc 1 2mm H1 Emssweuyena Emssmn Madman Cmmm rve men 5 Anna M EnergyAdaptive Display System Designs 0 The energy consumed by a pixel is dependent on the color being displayed as well as its brightness 0 Different regions of the screen have different energy consumptions EnergyAdaptive Display System Designs SOFTWARE LEVEL ADAPTATION 0 At the software level energy consumption can be reduced by Dark Windows optimization Dark Windows enable the windowing environment to change the brightness and color of areas of interest on the screen 0 Scheduling Algorithms spread the task in to available time periods so that the task can be comoleted before its deadline EnergyAdaptive Display System Designs Software level optimization can be implemented at several layers 3 The application level 4 The window system level 5 The operating system level EnergyAdaptive Display System Designs Dark Windows Algorithms 0 HalfDimmed Dimmed by 50 0 FullyDimmed Dimmed fully turned off 0 GrayScale Changed to gray by setting red green and blue values to the average of three GreenSoale Changed to green and its value is set to the average of the three colors and and the red and blue values are zeroed EnergyAdaptive Display System Designs Prototyping the interface 1 l H WWW wcsew y Tmc ungep n m 3 row a mun m i mm mm mm IIInewt Wquot hmwe numehuwir Figure Methodology used In pmmrype the user interface EnergyAdaptive Display System Designs Prototyping the interface Prototype is implemented on the X Windows System under Linux 0 Opensource VNC Virtual Network Computing server 3 VNC provides a virtual representation of the display hardware Le a virtual frame buffer 4 Easy to manipulate the pixel values 5 Access to the window server data structures such as the window of focus EnergyAdaptive Display System Designs Background half dim Background fully dim Dark Windows Brightness Control Background grayscale Background greenscale Dark Windows Color Control Figure 8 Screen shots of the user interfaces with dark Windows optimizations EnergyAdaptive Display System Designs 75 LCD OLED Half Fully GrayScaIe Green Dimmed Dimmed Scale Figure Power bene ts from energyadaptive display designs Power consumption Watts N 01 U1 0 EnergyAdaptive Display System Designs Other energy adaptive displays 2 Field Emission Displays 3 Conventional CRT displays 4 Hybrid technologies like LCD displays with OLED backlights 5 sticky lamps at software level adaptation Scheduling for Reduced CPU Energy Scheduling for Reduced CPU Energy Background 0 Every task to be precise instruction requires some fixed number of clock cycles for execu on 0 Most of the processors run at maximum speed and execute tasks much before the deadline is reached and enter idle state Scheduling for Reduced CPU Energy 0 Most of the processors are based on CMOS logic which dissipate an energy per clock cycle proportional to the square of the operating voltage 0 Since the processors running at maximum speed require maximum voltage more energy will be dissipated Scheduling for Reduced CPU Energy Approach Make use of the idle state clock cycles and spread the task to idle state but before the deadHne 0 Processor need not run at maximum hequency 0 There by the operating voltage and hence the energy dissipation can be reduced Approach Scheduling for Reduced CPU Energy As a result the operating frequency decreases tasks take longer time for execution but before the deadline is reached and the energy dissipation decreases Example A task has a deadline in 100ms but takes only 50 ms of CPU time when running at full speed to complete on a normal system If run at half the speed and half the voltage then the task can be completed at 14th the energy consumed by a normal system Scheduling for Reduced CPU Energy 0 A new metric of interest MIPJ Millions of Instructions Per Joule is defined which indicates how many instructions are executed for a given amount of energy MIPJ MIPS WATTS 0 Reducing clock speed causes a linear reduction in energy consumption but a similar reduction in MIPS The two effects canceL Scheduling for Reduced CPU Energy Schedulino Aloorithms 0 Unbounded delay perfect future OPT 0 Bounded delay limited future FUTURE 0 Bounded delay limited past PAST The above algorithms are simulated for trace data taken from UNIX workstations over many hours of use by a variety of users Scheduling for Reduced CPU Energy Unboundeddelav perfect future OPT 0 Takes the entire trace and stretches all the run times to fill all the idle times 0 Impractical Difficult to predict perfect future 0 Undesirable Real time events might not be completed before the deadline Scheduling for Reduced CPU Energy Bounded delav limited future FUTURE 0 Similar to OPT but peers into the future only a small window 0 Impractical Depends on future 0 Desirable No real time responses are delayed longer than the window Scheduling for Reduced CPU Energy Bounded delav limitedpast PAST 0 Looks a fixed window into the past and assumes the next window will be like the previous one 0 Practical Doesn t depend on future 0 Desirable No real time responses are delayed longer than the window Scheduling for Reduced CPU Energy Adjust Intewal secs Enmaurisinn nf all alnnrilhms Scheduling for Reduced CPU Energy Dvnamic Voltaqe Scalind Aldorithms DVS 0 These algorithms ensure that the real time events are executed well before their deadHnes These are to be integrated into the popular real time OS Schedulers like 0 Rate Monotonic RM EarliestDeadline First EDF 0 Inseok Choi Ho39un Shim and Naehyuck Chang Low Power Color TFT LCD Display for Hand Held Embedde Systems In Proceedings of the International Symposium on Low Power Electronics and Devices pages 112 117 August 2002 0 Jason Flinn and M Satyanarayanan EnergyAware Adaptation for Mobile Applications In Proceedings of the 17th ACM Symposium on Operating Systems Principles December 1999 0 Stanford Resources Inc editor Organic LightEmitting Diode Displays Annual Display Industry Report Second edition 2001 0 N Kamijoh T Inoue C M Olsen M T Raghunath and C Narayanaswami Energy Tradeoffs in the IBM Wristwatch Computer In Proceedings of the Fifth International Symposium on Wearable Computers ISWCO1 pages 133 140 October 2001 0 Trevor Pering Tom Burd and Robert Broderson The Simulation and Evaluation of Dynamic Voltage ScaIIn Algorithms In Proceedings of the International Symposium on Low Power Electronics an Design August 1998 0 T Richardson Q StaffordFraser K R Wood and A HoEper Virtual Network Computing In IEEE Internet Computing Vol2 No1 pages 33 38 Jan eb 1998 0 Sanjay Udani and Jonathan Smith The Power Broker Intelligent Power Management for Mobile Computers Technical Report MSCIS96 12 Distributed Systems Laboratory Department of Computer Information Science University of Pennslyvania 1996 0 S Xiong W Xie Y Zhao J Wang E Liu and C Wu A Simple and Flexible Driver for OLED In Proceedings of the Asian Symposium on Information Display ASID99 pages 147150 1999 0 William C Athas Jeffrey G Koller and Lars Svensson An EnergyEfficient CMOS Line Driver JIsin Agigfatic Switching 1994 IEEE Fourth Great Lakes Symposium on VLSI pp 196199 arc References httpenwikipediaorgwikiOled William C Athas Jeffrey G Koller and Lars J Svensson An EnergyEfficient CMOS Line Driver Using Adiabatic Switching 1994 IEEE Fourth Great Lakes Symposium on VLSI pp 196199 March 1994 0 A P Chandrakasan and S Sheng and R W Brodersen LowPower CMOS Digital Design JSSC V27 N4 April 1992 pp 473484 0 Michael Culbert Low Power Hardware for a High Performance PDA to appear Proc of the 1994 Computer Conference San Francisco 0 Fred Douglis P Krishnan Brian Marsh Thwarting the PowerHungry Disk Proc of Winter 1994 USENIX Conference January 1994 pp 293306 0 Mark A Horowitz SelfClocked Structures for Low Power Systems ARPA semi annual report December 1993 Computer Systems Laboratory Stanford University Kester Li Roger Kumpf Paul Horton Thomas Anderson A Quantitative Analysis of Disk Drive Power Management in Portable Computers Proc of Winter 1994 USENIX Conference January 1994 pp 279292 S Younis and T Knight Practical Implementation of Charge Recovering Asymptotically Zero Power CMOS 1993 Symposium on Integrated Systems C Ebeling and 0 Borriello eds Univ of Washington 1993 0 Wilkes JoIm Idleness is not Sloth to appeai proc of the 1995 Winter USENIX Conf Design of EnergyAdaptive Systems Thank You


Buy Material

Are you sure you want to buy this material for

25 Karma

Buy Material

BOOM! Enjoy Your Free Notes!

We've added these Notes to your profile, click here to view them now.


You're already Subscribed!

Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'

Why people love StudySoup

Steve Martinelli UC Los Angeles

"There's no way I would have passed my Organic Chemistry class this semester without the notes and study guides I got from StudySoup."

Amaris Trozzo George Washington University

"I made $350 in just two days after posting my first study guide."

Bentley McCaw University of Florida

"I was shooting for a perfect 4.0 GPA this semester. Having StudySoup as a study aid was critical to helping me achieve my goal...and I nailed it!"

Parker Thompson 500 Startups

"It's a great way for students to improve their educational experience and it seemed like a product that everybody wants, so all the people participating are winning."

Become an Elite Notetaker and start selling your notes online!

Refund Policy


All subscriptions to StudySoup are paid in full at the time of subscribing. To change your credit card information or to cancel your subscription, go to "Edit Settings". All credit card information will be available there. If you should decide to cancel your subscription, it will continue to be valid until the next payment period, as all payments for the current period were made in advance. For special circumstances, please email


StudySoup has more than 1 million course-specific study resources to help students study smarter. If you’re having trouble finding what you’re looking for, our customer support team can help you find what you need! Feel free to contact them here:

Recurring Subscriptions: If you have canceled your recurring subscription on the day of renewal and have not downloaded any documents, you may request a refund by submitting an email to

Satisfaction Guarantee: If you’re not satisfied with your subscription, you can contact us for further help. Contact must be made within 3 business days of your subscription purchase and your refund request will be subject for review.

Please Note: Refunds can never be provided more than 30 days after the initial purchase date regardless of your activity on the site.