slide 1 of 16 internet service in developing regions through network coding mike p. wittie, kevin c....

23
Slide 1 of 16 Internet Service in Developing Regions Through Network Coding Mike P. Wittie, Kevin C. Almeroth, Elizabeth M. Belding, Department of Computer Science UC Santa Barbara Ivica Rimac, Volker Hilt Bell Labs Alcatel-Lucent

Upload: colleen-price

Post on 26-Dec-2015

218 views

Category:

Documents


0 download

TRANSCRIPT

Slide 1 of 16

Internet Service in Developing RegionsThrough Network Coding

Mike P. Wittie, Kevin C. Almeroth, Elizabeth M. Belding,

Department of Computer Science

UC Santa Barbara

Ivica Rimac, Volker Hilt

Bell Labs

Alcatel-Lucent

Slide 2 of 16

Networking and the Digital Divide

• The Digital Divide– Low penetration of Internet services– Higher price– Lack of adequate infrastructure

• Success of cellular deployments– No data services– High subscription price

• Rural mesh networks– Local communication patterns

• Goals: – Low cost data communications– Leverage cellular deployments– Cater to local communications

US Europe India Sub-saharan Africa

0

50

100

150

200

250

300

350

400

Broadband price (USD/month)

Slide 3 of 16

Multihop Cellular Networks (MCNs)

• Cellular network augmented by client-to-client Wi-Fi communications [Lin00] (A)

• Rural (sparse) MCNs– Large cell area– Large per-client spectrum usage

• Local traffic patterns (B):– Cannot use cell tower– Cannot form end-to-end paths

• Need: efficient opportunistic client-to-client forwarding in sparse MCNs

A. B.

Slide 4 of 16

Delay Tolerant Networks (DTNs)

• Epidemic Routing [Vahdat00]– Bundled data forwarded during

every contact for eventual delivery– Flood scoping by hop-count or TTL

• PRoPHET [Lindgren04]– Transitive destination contact

probability as routing metric– Data forwarded up a routing metric

gradient

• But, high cost of flooding creates network congestion

• Cloud Routing (CR) [Wittie09]– Network and traffic state disseminated

over a control channel– Forwards a small set of data copies– Lower forwarding cost and higher network

throughput

• But, replication wastes network resources

S

D

Slide 5 of 16

Intra-flow Network Coding (NC)

• Forwards randomly encoded data on each path

• With high probability, data arriving on multiple paths is innovative

• Codes are embedded in packets themselves [Chou03]

𝑛 bytes of data 𝐷𝑝×𝑛/𝑝 data matrix 𝐸𝑝×𝑝 encoding matrix, initially 𝐼 𝒗1×𝑝,𝒗𝑖 ∈𝒢ℱ(8) Coded piece: ሾ 𝒗𝐸 | 𝒗𝐷 ሿ1×(𝑝+𝑛/𝑝)

S

D

𝒗1𝐸1𝒗2𝐸2⋮𝒗3𝐸3||||𝒗1𝐷1𝒗1𝐷1⋮𝒗1𝐷1

൪𝐺𝑎𝑢𝑠𝑠𝑖𝑎𝑛 𝑒𝑙𝑖𝑚.ሱۛ ۛ ۛ ۛ ۛ ۛ ۛ ۛ ۛ ۛ ሮ ൦ 𝐼 |||| 𝐷 ൪

𝑝×(𝑝+𝑛/𝑝)

Slide 6 of 16

NC in DTNs

• Network Coding Probabilistic Routing (NCPR) [Widmer05]– Each node forwards floor(d)

coded pieces and additional coded piece with probability d-floor(d)

– Stops forwarding after ceil(d) coded pieces

– New innovative coded pieces reset forwarding cap

• But, tradeoff between high delivery rates and high load

• Need a more efficient mechanism for reliability

S

D

Slide 7 of 16

Semi-Innovative Set Routing (SISR)

S

D

Linearly independent?

Coded pieces required to decode bundle: 𝑏= 𝑝

Redundant coded pieces: 𝑟= 𝑏4

Maximum coded pieces at node (bundle fraction): 𝑓= 𝑟

b rb – f f

SISR (scissor) forwards: small forwarding footprint (CR) fraction of data on each path

through NC (NCPR)

Slide 8 of 16

Given a set of coded pieces 𝐶, ȁ'𝐶ȁ'= 𝑏+ 𝑟,𝑟≥ 1, we can construct a set of SISs over 𝐶, such that any subset of 𝐶 of size 𝑏 has full rank.

Semi-Innovative Sets (SISs)

S

D

SIS 𝑠 is a set of linearly independent coded pieces

𝐶

SIS1SIS2SIS3

every possible union of 𝑠𝑖,𝑠𝑗

𝑠1,𝑠2,⋯,𝑠 |𝐶|𝑏/2ඈ s1 s2 s3

b rb – f f

f

Slide 9 of 16

Semi-Innovative Sets (SISs)

S

D

SISs can be constructed to tolerate any number of losses 𝑙 = 𝑟/𝑓ہ ≥𝑓,ۂ 𝑟

𝑙 = 3 → 𝐶= 2𝑏,𝑓= 13 SIS1

every possible union of 𝑠𝑖,𝑠𝑗 SIS2SIS3SIS4SIS5SIS6

b rb rf ff b – f r-2f

Slide 10 of 16

SISR in an MCN

S

D

While the number of SISs grows

exponentially as ቆቒ𝑏+𝑟𝑏/2ቓ2 ቇ, each

node only needs to maintain

ቒ𝑏+𝑟𝑏/2ቓ− 1 SISs

n2 n3

When 𝑑 coded pieces are delivered, the global encoding adjusts accordingly

D

SIS1SIS2SIS3SIS4SIS5SIS6

ሺ𝑥,𝑦ሻ,𝒗𝐸

Embedded codes disseminated over the control channel to announce forwarding progress

b rb rSIS1SIS2SIS3SIS4SIS5SIS6

d

n1

Slide 11 of 16

SISR Cloud Progress Example

Slide 12 of 16

Evaluation Setup

• Want to compare SISR with CR and NCPR– NCPR – flooding and network coding– CR – small set of bundle copies– SISR – network coded bundle + redundancy

• Configuration details:– Area, node density and mobility models a rural community– Single flow between a node pair at different distances– Interested in evaluating:

• Bundle forwarding cost • End-to-end delay• Control channel load

Slide 13 of 16

Forwarding Cost

• Forwarding cost – the amount of data forwarded

in the network before delivery

• NCPR – high cost of flooding• CR – high cost of replication• SISR – lowest cost

– Fraction of data on each path– Improvements for multiple

simultaneous flows

Slide 14 of 16

Overhead of Control Traffic

• Control channel load– Position updates– Bundle progress notifications– Data encoding vectors (SISR

only)

• Cellular channel gain– Bundle size minus control traffic

• Prevalence of position updates• Higher gain for multiple flows• Gain higher for CR, but SISR

easier on client resources

Slide 15 of 16

A. B.

Conclusions and Future Work

• Introduced Semi-Innovative Set Routing (SISR)

• End-to-end management of NC and forwarding mechanisms

– Only innovative data forwarded– Tolerates any number of losses

• 2X reduction in forwarding cost– Lower cost of infrastructure and data

services– Make data services affordable for more

clients

• Future work:– Adaptation to different

network settings– Directional mesh

networks with smart antennas

– Different ratios of data and control traffic propagation speeds

S

D

b rSIS1SIS2SIS3SIS4SIS5SIS6

Slide 16 of 16

Thank You

Mike [email protected]

Slide 17 of 16

Q & A

Slide 18 of 16

Slide 19 of 16

Backup Slides

Slide 20 of 16

Evaluation Setup

• Want to compare SISR with CR and NCPR

• Configuration details:– Area, node density and

mobility models a rural community

– Single flow between random node pair

– NCPR – d configured for 100% delivery at 6km

– CR – lower forwarding cost at delay comparable to larger clouds

– SISR – lowest delay at 6km

Slide 21 of 16

Bundle Delay

• Delay– end-to-end forwarding delay of

entire bundle (all coded pieces)

• SISR - last copy delay• NCPR – nodes use up

forwarding allowance before delivery

• CR – first copy delay

Slide 22 of 16

Multihop Cellular Networks (MCNs)

• Cellular network augmented by client-to-client Wi-Fi communications [Lin00]

• MCNs can:– Reduce cellular channel load

(A)– Extend cell coverage (B, C)

• MCNs make cellular infrastructure go further

Slide 23 of 16

MCNs in Developing Regions

• Sparse MCNs– Fewer clients and larger cell area– Larger per-client spectrum usage

• Local data communications– Regional caches (B)– Opportunistic client-to-client

communications (C)

• Our focus: opportunistic client-to-client forwarding in sparse MCNs