Informed Mobile Prefetching T.J. Giuli † Christopher Peplin † David Watson †‡ Brett Higgins Jason Flinn Brian Noble †‡

Slides:



Advertisements
Similar presentations
Experiences with a vehicular cloud computing platform Jason Flinn, T.J. Giuli, and Brian Noble University of Michigan and Ford Motor Co.
Advertisements

Eduardo Cuervo - Duke Aruna Balasubramanian - U Mass Amherst Dae-ki Cho - UCLA Alec Wolman, Stefan Saroiu, Ranveer Chandra, Paramvir Bahl – Microsoft Research.
BreadCrumbs: Forecasting Mobile Connectivity Anthony Nicholson and Brian Noble University of Michigan Presented by: Scott Winkleman.
Intentional Networking: Opportunistic Exploitation of Mobile Network Diversity T.J. Giuli David Watson Brett Higgins Azarias Reda Timur Alperovich Jason.
The Use of Cases: Use Case Scenarios College of Alameda Copyright © 2007 Patrick McDermott Sometimes a Word is worth a thousand.
High Performing Cache Hierarchies for Server Workloads
1 Adapted from UCB CS252 S01, Revised by Zhao Zhang in IASTATE CPRE 585, 2004 Lecture 14: Hardware Approaches for Cache Optimizations Cache performance.
1 Storage-Aware Caching: Revisiting Caching for Heterogeneous Systems Brian Forney Andrea Arpaci-Dusseau Remzi Arpaci-Dusseau Wisconsin Network Disks University.
3G v.s WIFI Radio Energy with YouTube downloads. Energy in Mobile Phone Data Transfers In 3G, there are three states –Idle –DCH (Dedicated Channel), do.
GREENBAG: ENERGY-EFFICIENT BANDWIDTH AGGREGATION FOR REAL-TIME STREAMING IN HETEROGENEOUS MOBILE WIRELESS NETWORKS STUDENT: BUI, HOANG DUC ADVISOR: PROFESSOR.
FindAll: A Local Search Engine for Mobile Phones Aruna Balasubramanian University of Washington.
Green Computing Energy in Location-Based Mobile Value-Added Services Maziar Goudarzi.
Informed Mobile Prefetching T.J. Giuli Christopher Peplin David Watson Brett Higgins Jason Flinn Brian Noble.
LBVC: Towards Low-bandwidth Video Chats on Smartphones Xin Qi, Qing Yang, David T. Nguyen, Gang Zhou, Ge Peng College of William and Mary 1.
Energy-Efficient Rate-Adaptive GPS-based Positioning for Smartphones Jeongyeup Paek, Joongheon Kim, Ramesh Govindan CENS Talk April 30, 2010.
Brett Higgins Balancing Interactive Performance and Budgeted Resources in Mobile Applications.
Fjording the Stream: An Architecture for Queries over Streaming Sensor Data Samuel Madden, Michael J. Franklin University of California, Berkeley Proceedings.
Improving Energy Efficiency of Location Sensing on Smartphones Kyu-Han Kim and Jatinder Pal Singh Deutsche Telekom Inc. R&D Lab USA Zhenyun Zhuang Georgia.
Reducing the Energy Usage of Office Applications Jason Flinn M. Satyanarayanan Carnegie Mellon University Eyal de Lara Dan S. Wallach Willy Zwaenepoel.
Intentional Networking Brett Higgins, Azarias Reda, Timur Alperovich, Jason Flinn, T.J. Giuli (Ford), Brian Noble, David Watson (Ford)
10th Workshop on Information Technologies and Systems 1 A Comparative Evaluation of Internet Pricing Schemes: Smart Market and Dynamic Capacity Contracting.
Augmenting Mobile 3G Using WiFi Aruna Balasubramanian Ratul Mahajan Arun Venkataramani University of Massachusetts Microsoft Research.
Lexmark Print Management
Aiding intelligent next-gen systems with mobile applications Dr. Jeyakesavan Veerasamy University of Texas at Dallas Note: Almost all.
Timecard: Controlling User-Perceived Delays in Server-Based Mobile Applications Lenin Ravindranath, Jitu Padhye, Ratul Mahajan, Hari Balakrishnan.
Advanced Metering Infrastructure
ThinkAir: Dynamic Resource Allocation and Parallel Execution in Cloud for Mobile Code Offloading Sokol Kosta, Pan Hui Deutsche Telekom Labs, Berlin, Germany.
Energy Audit- a small introduction A presentation by Pune Power Development Pvt. Ltd.
Augmenting Mobile 3G Using WiFi Aruna Balasubramanian Ratul Mahajan Arun Venkataramani University of Massachusetts Microsoft Research.
Niranjan Balasubramanian Aruna Balasubramanian Arun Venkataramani University of Massachusetts Amherst Energy Consumption in Mobile Phones: A Measurement.
Presented by Tao HUANG Lingzhi XU. Context Mobile devices need exploit variety of connectivity options as they travel. Operating systems manage wireless.
BreadCrumbs: Forecasting Mobile Connectivity Presented by Hao He Slides adapted from Dhruv Kshatriya Anthony J. Nicholson and Brian D. Noble.
Characterizing and Modeling the Impact of Wireless Signal Strength on Smartphone Battery Drain Ning Ding Xiaomeng Chen Abhinav Pathak Y. Charlie Hu 1 Daniel.
Integrating Fine-Grained Application Adaptation with Global Adaptation for Saving Energy Vibhore Vardhan, Daniel G. Sachs, Wanghong Yuan, Albert F. Harris,
Turducken: Hierarchical Power Management for Mobile Devices Jacob Sorber, Nilanjan Banerjee, Mark Corner, Sami Rollins University of Massachusetts, Amherst.
Android Genetic Programming Framework Alban Cotillon Philip Valencia Raja Jurdak CSIRO ICT Centre, Brisbane, Australia.
Energy Consumption in Mobile Phones: A Measurement Study and Implications for Network Applications REF:Balasubramanian, Niranjan, Aruna Balasubramanian,
Procrastinator: Pacing Mobile Apps’ Usage of the Network mobisys 2014.
1 Tuning Garbage Collection in an Embedded Java Environment G. Chen, R. Shetty, M. Kandemir, N. Vijaykrishnan, M. J. Irwin Microsystems Design Lab The.
Timecard: Controlling User-Perceived Delays in Server-Based Mobile Applications Lenin Ravindranath, Jitu Padhye, Ratul Mahajan, Hari Balakrishnan.
Hybrid Cellular-Ad hoc Data Network Shuai Zhang, Ziwen Zhang, Jikai Yin.
Quality Software Project Management Software Size and Reuse Estimating.
Brett D. Higgins ^, Kyungmin Lee *, Jason Flinn *, T.J. Giuli +, Brian Noble *, and Christopher Peplin + Arbor Networks ^ University of Michigan * Ford.
Cell Zooming for Cost-Efficient Green Cellular Networks
Design Process … and some design inspiration. Course ReCap To make you notice interfaces, good and bad – You’ll never look at doors the same way again.
Guidelines Revisions Defining What RTF Means by “Savings” December 17,
Eduardo Cuervo – Duke University Aruna Balasubramanian - University of Massachusetts Amherst Dae-ki Cho - UCLA Alec Wolman, Stefan Saroiu, Ranveer Chandra,
Evaluating Wireless Network Performance David P. Daugherty ITEC 650 Radford University March 23, 2006.
Adaptive Sleep Scheduling for Energy-efficient Movement-predicted Wireless Communication David K. Y. Yau Purdue University Department of Computer Science.
Chapter 14 : Modeling Mobility Andreas Berl. 2 Motivation  Wireless network simulations often involve movements of entities  Examples  Users are roaming.
2011 ULTRA Program: Green Radio Prof. Jinho Choi College of Engineering Swansea University, UK.
M2M Study Item 3GPP2 Orlett W. Pearson May | 3GPP2 M2M Study Item | May GPP2 M2M This study will include the following study targets: 
Power Guru: Implementing Smart Power Management on the Android Platform Written by Raef Mchaymech.
KAIS T System Support for Mobile, Adaptive Applications Brian Noble, University of Michigan Presented by Hyeeun Choi.
100K ACTIVE CLIENTS SOLUTION Version: 18 May 2015.
Data-Centric Systems Lab. A Virtual Cloud Computing Provider for Mobile Devices Gonzalo Huerta-Canepa presenter 김영진.
Accurate WiFi Packet Delivery Rate Estimation and Applications Owais Khan and Lili Qiu. The University of Texas at Austin 1 Infocom 2016, San Francisco.
Center for Networked Computing. Motivation Model and problem formulation Theoretical analysis The idea of the proposed algorithm Performance evaluations.
Seminar On Energy Audit Submitted To: Submitted By:
Jacob R. Lorch Microsoft Research
Protocols for Low Power
Sentio: Distributed Sensor Virtualization for Mobile Apps
ECF: an MPTCP Scheduler to Manage Heterogeneous Paths
Di Zhang, Yuezhi Zhou, Xiang Lan, Yaoxue Zhang, Xiaoming Fu
Efficient and Transparent Dynamic Content Updates for Mobile Clients
Cross-Layer Optimization for State Update in Mobile Gaming
PredictRemainingTime
Update : about 8~16% are writes
3PL Logistic Software. What is a 3PL? You take the orders. Your third-party logistics provider (3PL) fulfils them. It’s that simple and if it’s seamless,
Presentation transcript:

Informed Mobile Prefetching T.J. Giuli † Christopher Peplin † David Watson †‡ Brett Higgins Jason Flinn Brian Noble †‡

Prefetching + Mobile Networks Brett Higgins 2 Time, distance $#&*! ! Phone activity Read article Phone activity Slow fetch Prefetch Article loads instantly Sleeping

A Tale of Two Apps Brett Higgins 3 The Data HogThe Data Miser

A Tale of Two Apps Brett Higgins 4 Four hours later: Battery died hours ago Fetch time: INF Four hours later: Battery: 10% Fetch time: many seconds Scenario: 50% battery 4 hours until recharge We must conserve energy! (…no big surprise there.) ✖

A Tale of Two Apps Brett Higgins 5 One hour later: Battery: 5% (charging) Fetch time: << 1 second One hour later: Battery: 40% (charging) Fetch time: many seconds Scenario: 50% battery 1 hour until recharge It’s okay to spend resources… …if it will benefit the user. (And if we can spare the resources.) ✖

One more scenario: Reality The only scenario that matters Network conditions change rapidly User/app behavior changes too No one strategy is always best Even for two scenarios Mobile prefetching is complex. Must consider: Network availability/quality Network energy cost model Overall resource spending Time until resource replenishment Observed usefulness of prefetching… But the benefits could be great! Brett Higgins 6

So, who should deal with it? Users? Monitor resources, networks Adjust behavior Fiddle with app settings Brett Higgins 7 Developers? Monitor resources, networks Observe user behavior Adjust prefetch strategy

Informed Mobile Prefetching System support for prefetching on mobile networks Applications specify hints What & how to prefetch System decides when to prefetch Monitors network availability and quality Tracks resource spending over time Adjusts the importance of energy/data conservation Tracks how often the user consumes hinted data Brett Higgins 8

Roadmap Motivation IMP Design & Implementation Interface Prefetch decision algorithm Applications & Evaluation Summary Brett Higgins 9

IMP Interface App passes a Fetcher Callback to fetch data Size of data item Optional prefetch class IMP returns a Future Handle for future access get() invokes app fetch Intentional Networking Simple use of multiple networks Prioritize FG traffic over prefetches Application IMP Intentional Networking 10 Brett Higgins prefetch() get() fetch()

How to decide when to prefetch? Core: cost/benefit analysis Inspired by TIP (SOSP ‘95) Benefit: time savings Cost: energy, cellular data Prefetch when: Benefit > cost How to calculate? How to compare? Brett Higgins 11 HintsIMP Benefit Cost

How to decide when to prefetch? Network measurements Bandwidth, RTT, availability Benefit = future fetch time Cost = energy + data PowerTutor power model (CODES+ISSS ‘10) (Current cost) – (future cost) Future depends on user How often is data used? Brett Higgins 12 HintsIMP Benefit Cost Observations: Bandwidth RTT Power state

How to decide when to prefetch? API lets us track accuracy Fraction of hinted data used “Used” = get() “Not used” = cancel() Use accuracy in calculations e.g. benefit = time × accuracy Per-class accuracy estimate If app specifies classes Brett Higgins 13 HintsIMP Benefit Cost Observations: Bandwidth RTT Power state Accuracy of prefetch hints

How to decide when to prefetch? Budgeted resources Fixed, replenishable capacity Time period to spend Approach: Price is Right™ Spend close to budget But not over budget! Goal-directed adaptation Odyssey (TOCS ‘04) Measure resource spending Adjust resource importance Brett Higgins 14 HintsIMP Benefit Cost User Time Energy, Data Observations: Bandwidth RTT Power state Accuracy of prefetch hints

How to decide when to prefetch? Re-evaluation Outcome may change later Network conditions change Resource spending slows Periodically re-run analysis Batching Can amortize tail energy cost Evaluate all batch sizes Prefetch when benefit > cost For any batch size Brett Higgins 15 HintsIMP Benefit Cost User Time Energy, Data Observations: Bandwidth RTT Power state Accuracy of prefetch hints New batch, or wait a bit

Roadmap Motivation IMP Design & Implementation Interface Prefetch decision algorithm Applications & Evaluation Summary Brett Higgins 16

Applications K9 client Popular Android client Supported transparently via IMP-aware IMAP proxy Default: prefetch s over 32KB OpenIntents News Reader Open-source Android Atom/RSS feed reader Added IMP support code Default: no article text/media prefetching (summary only) Brett Higgins 17

Evaluation: Methodology Gathered network trace in a moving vehicle Sprint 3G & open WiFi BW up/down, RTT Replayed in lab (trace map here) 18 Brett Higgins

Evaluation: Comparison Strategies Never prefetch Prefetch items under a size threshold App-specific threshold value Prefetch only over WiFi Always prefetch Common heuristics; simple to implement 19 Brett Higgins

Evaluation Results: 20 Brett Higgins

Evaluation Results: All resource goals met Much smaller fetch time Within 300ms of “always” 2-8x less than others Walking trace on campus Similar results 21 Brett Higgins

Evaluation Results: News 22 Brett Higgins

Evaluation Results: News 23 Brett Higgins All resource goals met Smaller fetch time Whenever other strategies meet the goals Walking trace on campus Similar results* * …with one exception.

Evaluation Results: News 24 Brett Higgins

Evaluation Results: News 25 Brett Higgins Effect of prefetch classes Lower average fetch time Meet goals more reliably Small developer effort Significant improvement

Summary Informed Mobile Prefetching App supplies prefetch hints System decides when to prefetch Manages budgeted resources “Price is Right” approach Tracks prefetch accuracy Avoids wasteful prefetching Meets all resource goals Improves average fetch time in most cases Compared to simple strategies that meet same goals Brett Higgins 26