mobile computing at the edge - utah state university · 2015-10-15 · 8 mobile computing at the...
TRANSCRIPT
© 2015 Carnegie Mellon University
Mobile Computing at
the Edge
Grace A. LewisSoftware Engineering InstituteCarnegie Mellon [email protected]
Software Technology Conference (STC 2015)October 14, 2015
2
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Mobile Device Trends
Smartphones, tablets, and now phablets, have
become for many the preferred way of interacting
with the Internet, social media and the enterprise
• Mobile devices are increasingly becoming the first go-
to device for communications and content
consumption [1] [5] [8]
• Number of mobile devices will surpass desktops for
the first time this year [9]
• The time people spend using their smartphone is now
exceeding the time spent looking at TV screens [3]
• Not uncommon for there to be multiple mobile devices
per user and household [7]
• Wearable technology is showing a consistent increase
in popularity [2]
Organizations are pushing out more and more content and functionality to
mobile users
3
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Mobile Traffic Will Keep Increasing
Source: Cisco Visual Networking Index: Global Mobile Data Traffic Forecast Update
2014–2019 White Paper [15]
By the end of
2015, 4G LTE
data use will
rise by 59%
and mobile
video will
account for
60% of data
traffic [4]
Wearables market will grow five-fold in the next five years from 109
million devices in 2014 to 578 million devices by 2019. This will result in
an 18-fold increase in mobile data traffic [15]
4
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Permission for diagram use by Carnegie Mellon University consistent with its status as a non-profit University for any purpose the
institution sees fit by Matt Ceniceros, @mattceni, mattceni.com
Internet of Things (IoT): More Than Just “Things”
4.9 billion
connected
things will
be in use in
2015, up 30
percent from
2014, and
will reach 25
billion by
2020 [12]
99 percent
of physical
objects will
eventually
become part
of a
network[13]
5
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
The 3Vs of Data: Volume, Velocity and Variety
Permission for diagram use by Carnegie Mellon University consistent with its
status as a non-profit University for any purpose the institution sees fit by Amy
Allen, www.qmee.com
New Vs: Veracity, Validity, Volatility,
Visualization, Vulnerability and Value [14]
What to do with all the data?
How does it change business
processes and business
models?
6
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Integration Specialists
Digital Business Architects
Regulatory Analysts
Risk Professionals
Top Jobs in the Next 7 Years According to Gartner [25]
7
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Smartphone Penetration
Source: KPCB. 2015 Internet Trends. http://www.kpcb.com/internet-trends [6]
8
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Low-Cost Smartphones
By 2020, 75
percent of
smartphone
buyers will pay
less than $100
for a device [1]
Some low-cost
smartphones are
expected to reach
approximately $35
unsubsidized by
year-end 2014 [1]
As an example, ZTE manufactures
several low-end smartphones under
$50 and is quickly gaining market
share globally [16]
9
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Therefore …
Not unreasonable for users to expect the performance and capabilities of mobile devices to be equal to laptops and desktops
However …
• Mobile devices will always lag behind their PC counterparts due to size and battery limitations
• Large and variable end-to-end latency between mobile device and cloud, and the possibility of disruptions, have a negative effect on user experience
• Will only get worse with the amount of network traffic generated by IoT and growing market share of low-cost smartphones
10
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Edge Computing
Idea is to push applications, data and computing power to the logical extremes of a network — closer to where they are being used
• As an example, Akamai has servers around the world to distribute web site content from locations close to the user
Cyber-foraging moves the edge even closer to the user
11
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Cyber-Foraging
Leverage of external resource-rich surrogates to augment the capabilities of resource-limited devices
• Computation Offload
– Offload of expensive computation in order to extend battery life and increase computational capability
• Data Staging
– Improve data transfers between mobile computers and the cloud by temporarily staging data in transit on intermediate surrogates
Industry is starting to build on this concept to improve mobile user experience and decrease network traffic [10] [11]
Nokia Siemens NetworksLiquid Applications
Cisco SystemsFog Computing
12
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Cyber-Foraging to Proximate and Remote Resources
If we assume that
tsurrogate is less than tcloud,
proximate surrogates
are a better option from
an energy consumption
and latency perspective
13
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Cyber-Foraging: The Present
Forward-deployed surrogates located in single-hop proximity of mobile devices
• Communication with the central core in many cases is only needed for provisioning
Goal is to bring the
cloud closer to the
user
14
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Computation Offload (Short Operations)
Computation-intensive operations which if executed on a mobile device would take in the order of tens of seconds, but if offloaded could improve response time considerably
Typically request-response, synchronous operations
• Image, audio and video processing
• Face detection and recognition
• Speech recognition
• Speech translation
• Antivirus/Anti-malware
• Gaming (typically AI-based)
Systems can make runtime decisions on whether or not to offload computation
• Equivalent code on mobile device and surrogate
PowerSense: Image Processing for Dengue Detection [17]
PowerSense leverages
Microfluidic paper-based
analytical devices (μPADs) [17]
PowerSense
Features• User-Guided
Runtime Partitioning
• Resource-Adapted Input
15
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Computation Offload (Long Operations)
Computation-intensive operations which if executed on a mobile device would take minutes to hours, but if offloaded could improve response time considerably
Typically asynchronous operations to avoid blocking the application
• Service-based applications
• Workflow-based applications
• Search-based applications
Mobile device may lose contact with a surrogate before the operation finishes
• Caching data until the mobile device is reconnected
• Alternative communication mechanisms to reach the mobile device
3DMA Features [18]
• Offload requests are placed in a
space, processed on the
surrogate, and results placed in
the same space.
• When a device becomes
disconnected, it waits until a
connection is restored, and then
reads all available messages
(results) from the space
16
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Low Coverage Environments
Resource-challenged environments: Less-privileged regions characterized by limited Internet access, limited electricity and network access, and potentially low levels of literacy can leverage surrogates to obtain information to support their communities
Field operations: People that spend time away from their main offices or labs, such as researchers, medics, and sales personnel, can leverage portable surrogates to support their computation and data needs
AgroTempus: Agricultural Knowledge Exchange in Resource-
Challenged Environments [19]
AgroTempus Features [18]
• Surrogates in villages
download and cache data
from mobile hub
• Surrogates upload field-
collected data to the
mobile hub which
eventually syncs with the
cloud
17
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Hostile Environments
Characterized by very dynamic environments in which disconnected operations (or occasionally-connected operations) between surrogates and the cloud, and between mobile devices and surrogates, are highly likely
Tactical Cloudlet
Central Core (Enterprise Cloud)
High-bandwidth, stable connection
for pre-provisioning
Deployment in the field
Packaged Capabilities
(Service VMs)
Tactical Cloudlet
Data Sources
Low-bandwidth, intermittent connection for opportunistic data synchronization
Mobile Devices
Single-Hop Network
Tactical Cloudlets [19]
Tactical Cloudlet
Features [19]
• Pre-Provisioned Cloudlets with App Store
• Standard Packaging of Service VMs
• Optimal Cloudlet Selection
• Cloudlet Management Component
• Cloudlet Handoff/Migration
18
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Data-Intensive Mobile Apps 1
Rely on large sets of data to provide their functionality —data typically resides in data centers or in the enterprise cloud
• Mobile cloud applications
• Online gaming
• Apps in data-rich domains
Design goals
• Display of prioritized/relevant information
• Query efficiency
Mobile device specifies
interest in changes to specific
parts of web pages
Surrogate polls the web
servers involved, and if
relevant changes have
occurred, it aggregates the
updates as one batch that is
sent to the mobile device
Edge Proxy: Web Page
Monitoring [20]
Edge Proxy Features [20]
• In-Bound Pre-Processing: Mobile device is
only notified of changes
• Alternate Communications (SMS): if
connection to mobile device is lost, the
system uses SMS to notify changes —
based on the summary the user can
decide to visit or not the web page
19
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Data-Intensive Mobile Apps 2
Telemedik: Mobile healthcare system [21]
Telemedik Features [21]
• Context-sensitive priority-based
text fragmentation algorithm to
determine when and what
information to display to the user
• Dynamic generation of a
hierarchical view of relevant
information based on medical
domain knowledge
• Offload of image processing and
manipulation
• Pre-Fetching: stage data on
surrogate that is likely to be used
by applications based on usage
patterns or data alerts
20
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Sensing Applications
GigaSight: Scalable Crowd-Sourcing of Video from Mobile Devices [22]
GigaSight Features [22]
• Surrogate collects first-person
video from many contributors
• Surrogate provides video
denaturing capability for privacy
(user-specific lowering of fidelity)
and video indexing
• Only video metadata is stored in
a searchable global catalog in the
cloud
Perform context, environmental or urban sensing using on-board or connected sensors — send data to surrogates as these become available
• Context-aware applications
• Healthcare
• Intelligent transport systems
• Ambient intelligence
• Environmental monitoring
• Participatory sensing (Crowdsensing)
21
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
What is Common in the Examples of Cyber-Foraging in the Present?
The same individual/organization owns the mobile device and the surrogate
Advantage = Control
• Deployment
• Provisioning
• Privacy
• Security
• …
However … the future of cyber-foraging involves surrogates not necessarily owned by the mobile devices that use them
22
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Cyber-Foraging: The Future
Vision: Rich sensing and interaction capabilities of mobile devices seamlessly fused with compute-intensive and data-intensive processing on readily-available surrogates
Challenges
• Seamless mobility and execution
• Disconnected operations
• Multi-platform development and management
• Trusted nodes
• Software licensing and business models
• Privacy
23
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Seamless Mobility and Execution
Mobile applications that leverage cyber-foraging need capabilities to
• Discover surrogates
• Automatically offload computation and data
If a mobile device loses contact with a surrogate it will have to seamlessly fall back to local execution
• Requires very careful design of state transfer and management between mobile devices and surrogates or even between multiple surrogates
24
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Disconnected Operations
Mobile devices are not always going to be connected to a surrogate
Surrogate-ready mobile apps should make their best attempt to work completely disconnected from a surrogate and sync when one becomes available
• Caching
• Automatic data synchronization capabilities
• Pre-fetching
25
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Multi-Platform Development and Management
Surrogates have to be pre-provisioned with applications and content that adapt to multiple mobile devices
App and content developers have to consider
• Multiple devices with different processing power and screen sizes
• Different processing capabilities depending on input and output types and sizes
26
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Trusted Nodes
Mutual trust
• A mobile device needs to know if it can trust a surrogate
• A surrogate needs to know if it can trust a mobile device
Distributed trust is a very difficult problem
• Key and password management
• Revocation
27
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Software Licensing and Business Models
Requires creating incentives for
• Surrogate providers
• Content providers
• Network providers
• Mobile device manufacturers
• Mobile carriers
• End users
Which brings us to the next issue: Privacy
28
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Privacy
Business model would enable the surrogate provider control of, and access to, data sent by content providers to the device and data generated by connected applications
• Surrogate providers would have very valuable information about user interests and preferences
How far and how much to share?
• Example: User — home — neighborhood — … — cloud
Challenge will be the balance between user privacy preferences and requirements set by surrogate providers to host content The Joneses
(2009)
29
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
This Future Is Not Too Far Away
Source: Gartner, Hype Cycle for Emerging Technologies, 2015
Many of the 5-10 year out technologies on Gartner’s most recent Hype Cycle for Emerging Technologies require highly computation-intensive activities that people are going to want to have on their mobile devices
• Natural language question answering
• Smart advisors
• Connected home
• Affective computing
• People-literate technology
• Virtual personal assistants
30
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Summary
With increasing number of mobile devices and users, increased network traffic cause by IoT, and increasing complexity of user experience, cyber-foraging will become a standard feature of mobile applications
Requires mobile applications and infrastructures to be architected and designed to adapt to a changing environment in which resources with greater computing power are discovered and used opportunistically
While the benefits in terms of mobile user experience and new business opportunities are huge, it requires a different paradigm in mobile systems and software engineering
31
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Contact Information
Grace A. Lewis
Advanced Mobile Systems (AMS) Initiative
Software Engineering Institute4500 Fifth AvenuePittsburgh, PA 15213-2612USA
Phone: +1 412-268-5851Email: [email protected]: http://www.sei.cmu.edu/staff/glewis/
32
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
References[1] Gartner. Gartner Says By 2018, More Than 50 Percent of Users Will Use a Tablet or Smartphone First for All Online
Activities. http://www.gartner.com/newsroom/id/2939217 (2015)
[2] mobiForge. Mobile Hardware Statistics 2015. https://mobiforge.com/research-analysis/mobile-hardware-statistics-2015 (2015)
[3] mobiForge. Mobile User Behavior Statistics 2015. https://mobiforge.com/research-analysis/mobile-user-behaviour-statistics-2015 (2015)
[4] mobiForge. Mobile Network Statistics 2015. https://mobiforge.com/research-analysis/mobile-networks-statistics-2015-0 (2015)
[5] comScore. Number of Mobile-Only Internet Users Now Exceeds Desktop-Only in the U.S. http://www.comscore.com/Insights/Blog/Number-of-Mobile-Only-Internet-Users-Now-Exceeds-Desktop-Only-in-the-U.S (2015)
[6] KPCB. Internet Trends 2015. (2015)
[7] GfK. Tech Trends 2015. http://www.gfk.com/Documents/GfK-TechTrends-2015.pdf (2015)
[8] CTIA. Wireless Quick Facts. http://www.ctia.org/your-wireless-life/how-wireless-works/wireless-quick-facts (2015)
[9] Baseline. Nine Mobility Trends You Must Watch in 2015. http://www.baselinemag.com/mobility/slideshows/nine-mobility-trends-you-must-watch-in-2015.html (2015)
[10] Nokia. Liquid Applications. http://networks.nokia.com/fr/portfolio/liquid-net/intelligent-broadband-management/liquid-applications (2015)
[11] Cisco. Fog Computing. https://techradar.cisco.com/trends/Fog-Computing (2015)
[12] Gartner. Gartner Says 4.9 Billion Connected "Things" Will Be in Use in 2015. http://www.gartner.com/newsroom/id/2905717 (2015)
[13] Baseline. Six Top Tech Trends to Watch in 2014. http://www.baselinemag.com/innovation/six-top-tech-trends-to-watch-in-2014-2.html/#sthash.dFWvTRaw.dpuf (2015)
[14] Farroha, B.S.; Farroha, D.L., "A Framework for Managing Mission Needs, Compliance, and Trust in the DevOps Environment," in Military Communications Conference (MILCOM), 2014 IEEE , vol., no., pp.288-293, 6-8 Oct. 2014
33
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
References
[15] Cisco. Cisco Visual Networking Index: Global Mobile Data Traffic Forecast Update 2014–2019 White Paper. http://www.cisco.com/c/en/us/solutions/collateral/service-provider/visual-networking-index-vni/white_paper_c11-520862.html (2015)
[16] Bloomberg. The Cheap Phones Quietly Winning the U.S. http://www.bloomberg.com/news/articles/2015-09-03/zte-s-cheap-phones-quietly-winning-the-u-s- (2015)
[17] Matthews, Jerrid, et al. "PowerSense: power aware dengue diagnosis on mobile phones." Proceedings of the First ACM Workshop on Mobile Systems, Applications, and Services for Healthcare. ACM, 2011.
[18] Fjellheim, Tore, Stephen Milliner, and Marlon Dumas. "Middleware support for mobile applications." International Journal of Pervasive Computing and Communications 1.2 (2005): 75-88.
[19] Brion, Reuel. Demonstrator for a Cyber-Foraging System to Support Agricultural Knowledge Exchange in Resource-challenged Environments. Masters Thesis. VU University Amsterdam. 2015.
[20] Armstrong, Trevor, et al. "Efficient and transparent dynamic content updates for mobile clients." Proceedings of the 4th international conference on Mobile systems, applications and services. ACM, 2006.
[21] Kundu, Suman, et al. "Algorithms and heuristics for efficient medical information display in PDA." Computers in Biology and Medicine 37.9 (2007): 1272-1282.
[22] Simoens, Pieter, et al. "Scalable crowd-sourcing of video from mobile devices." Proceeding of the 11th annual international conference on Mobile systems, applications, and services. ACM, 2013.
[23] Gartner. Gartner Says Digital Business Economy is Resulting in Every Business Unit Becoming a Technology Startup. http://www.gartner.com/newsroom/id/2865519 (2015)
34
Mobile Computing at the Edge
STC 2015
© 2015 Carnegie Mellon University
Copyright 2015 Carnegie Mellon University and IEEE
This material is based upon work funded and supported by the Department of Defense under Contract No. FA8721-05-C-0003 with Carnegie Mellon University for the operation of the Software Engineering Institute, a federally funded research and development center.
NO WARRANTY. THIS CARNEGIE MELLON UNIVERSITY AND SOFTWARE ENGINEERING INSTITUTE MATERIAL IS FURNISHED ON AN “AS-IS” BASIS. CARNEGIE MELLON UNIVERSITY MAKES NO WARRANTIES OF ANY KIND, EITHER EXPRESSED OR IMPLIED, AS TO ANY MATTER INCLUDING, BUT NOT LIMITED TO, WARRANTY OF FITNESS FOR PURPOSE OR MERCHANTABILITY, EXCLUSIVITY, OR RESULTS OBTAINED FROM USE OF THE MATERIAL. CARNEGIE MELLON UNIVERSITY DOES NOT MAKE ANY WARRANTY OF ANY KIND WITH RESPECT TO FREEDOM FROM PATENT, TRADEMARK, OR COPYRIGHT INFRINGEMENT.
This material has been approved for public release and unlimited distribution.
This material may be reproduced in its entirety, without modification, and freely distributed in written or electronic form without requesting formal permission. Permission is required for any other use. Requests for permission should be directed to the Software Engineering Institute at [email protected].
DM-0002864