Stochastic Forecasts Achieve High Throughput and Low · PDF fileVerizon LTE uplink throughput 0 500 1000 1500 ... Verizon 3G/LTE, AT&T LTE, T-Mobile 3G uplink and ... Stochastic Forecasts

Stochastic Forecasts Achieve High Throughputand Low Delay over Cellular Networks

Keith Winstein

MIT Computer Science and Artificial Intelligence Laboratory

http://alfalfa.mit.edu

March 6, 2014

Joint work with Anirudh Sivaraman and Hari Balakrishnan.

Sprout: a transport protocol designed for variability

Observation:Videoconferences perform poorly over cellular networks.

Keith Winstein (with Anirudh Sivaraman and Hari Balakrishnan)

Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks

Verizon LTE uplink throughput

0

500

1000

1500

2000

0:00 0:30 1:00 1:30

thro

ugh

pu

t(k

bp

s)



Verizon LTE ping delay during one TCP download

0.2

0.3

2

3

0.1

1

10

0 50 100 150 200 250

Ro

un

d-t

rip

tim

e(s

)

Time (s)



Interactive apps work poorly

I We measured cellular networks while driving:

I Verizon LTEI Verizon 3G (1xEV-DO)I AT&T LTEI T-Mobile 3G (UMTS)

I Then ran apps across replayed network trace:

I Skype (Windows 7)I Google Hangouts (Chrome on Windows 7)I Apple Facetime (OS X)



Skype’s performance



Performance summary

0

1000

2000

3000

4000

5000

6000

7000

8000

100200300500100020005000

Th

rou

gh

pu

t(k

bp

s)

Self-inflicted delay (ms)

Verizon LTE Downlink

SkypeFacetime

Google Hangout

Bette

r



What’s wrong?

I Existing schemes react to congestion signals.

I Packet loss.I Increase in round-trip time.

I Feedback comes too late.

I The killer: self-inflicted queueing delay.



Sprout’s mission

I Most throughput

I Bounded risk of delay > 100 ms



Bounded risk of delay

I Model variation in link speed

I Infer current link speed

I Predict future link speed

I Don’t wait for congestion

I Control: Send as much as possible, but require:

I 95% chance all packets arrive within 100 ms



Model: packet deliveries looks like flicker noise

0.0001

0.001

0.01

0.1

1

10

100

(< 0.5)

39041 10 100 1000

Per

cen

tin

tera

rriv

als

interarrival time (ms)

t−3.27

(Verizon LTE, phone stationary.)



Model: average rate looks like random walk

0

500

1000

1500

2000

0:00 0:30 1:00 1:30

thro

ugh

pu

t(k

bp

s)



Sprout’s model

Sender Queue Receiver

Poisson process

Rate λ controls

λ

σ

Brownian motion

λz

If in an outage,

drains queue

Poisson process

of σ√t varies λ λz is escape rate.



Sprout’s model parameters

Volatility σ: fixed @ 200 pkts/s√s

Expected outage time 1/λz : 1 sTick length (τ): 20 msForecast length: 160 msDelay target: 100 msRisk tolerance: 5%

All source code was frozen before data collection began.



Infer: current link speed

I Observe packets received every τ

I Update P(λ)



Predict: future link speed

I Evolve model forward

I Forecast 5th percentile cumulative packets



Control: fill up 100 ms forecast window

0

10

20

30

40

50

60

70

0 20 40 60 80 100 120 140 160

Cum

ulat

ive

pack

ets

sent

time (ms)

Cautious fo

recast




0

10

20

30

40

50

60

70

0 20 40 60 80 100 120 140 160

Cum

ulat

ive

pack

ets

sent

time (ms)

100 ms

Cautious fo

recast




0

10

20

30

40

50

60

70

0 20 40 60 80 100 120 140 160

Cum

ulat

ive

pack

ets

sent

time (ms)

Sen

d 50

pkt

s

100 ms

Cautious fo

recast




0

10

20

30

40

50

60

70

0 20 40 60 80 100 120 140 160

Cum

ulat

ive

pack

ets

sent

time (ms)

Sen

d 50

pkt

s

100 ms

100 ms

Cautious fo

recast




0

10

20

30

40

50

60

70

0 20 40 60 80 100 120 140 160

Cum

ulat

ive

pack

ets

sent

time (ms)

Sen

d 50

pkt

s

Sen

d 5

100 ms

100 ms

Cautious fo

recast




0

10

20

30

40

50

60

70

0 20 40 60 80 100 120 140 160

Cum

ulat

ive

pack

ets

sent

time (ms)

Sen

d 50

pkt

s

Sen

d 5

100 ms

100 ms100 ms

Cautious fo

recast




0

10

20

30

40

50

60

70

0 20 40 60 80 100 120 140 160

Cum

ulat

ive

pack

ets

sent

time (ms)

Sen

d 50

pkt

s

Sen

d 5

Sen

d 3 100 ms

100 ms100 ms

Cautious fo

recast



Sprout’s results



0

1000

2000

3000

4000

5000

6000

7000

8000

100200300500100020005000

Th

rou

gh

pu

t(k

bp

s)



SkypeFacetime

Google Hangout

Bette

r



0

1000

2000

3000

4000

5000

6000

7000

8000

100200300500100020005000

Th

rou

gh

pu

t(k

bp

s)



Compound TCP

LEDBAT

SkypeFacetime

Google Hangout

Vegas

Bette

r



0

1000

2000

3000

4000

5000

6000

7000

8000

100200300500100020005000

Th

rou

gh

pu

t(k

bp

s)



Compound TCP

LEDBAT

Cubic

SkypeFacetime

Google Hangout

Vegas

Bette

r



0

1000

2000

3000

4000

5000

6000

7000

8000

100200300500100020005000

Th

rou

gh

pu

t(k

bp

s)



Compound TCP

LEDBAT

Cubic

SkypeFacetime

Google Hangout

Vegas

Sprout

Bette

r



0

1000

2000

3000

4000

5000

6000

7000

8000

100200300500100020005000

Th

rou

gh

pu

t(k

bp

s)



Sprout-EWMA

Compound TCP

LEDBAT

Cubic

SkypeFacetime

Google Hangout

Vegas

Sprout

Bette

r



0

1000

2000

3000

4000

5000

300500100020003000500010000

Th

rou

gh

pu

t(k

bp

s)


Verizon LTE Uplink

Sprout-EWMA

Compound TCP

LEDBAT

Cubic

Skype Facetime

Google Hangout

Vegas

Sprout



Overall results on 8 links

Verizon 3G/LTE, AT&T LTE, T-Mobile 3G uplink and downlink:

Sprout vs. Avg. speedup Delay reduction

Skype 2.2× 7.9×Hangout 4.4× 7.2×Facetime 1.9× 8.7×Compound 1.3× 4.8×TCP Vegas 1.1× 2.1×LEDBAT Same 2.8×Cubic 0.91× 79×



Sprout is end-to-end, but comparable to in-net control

0

20

40

60

80

100

2003005001000300050001000030000

Uti

lizat

ion

(per

cen

t)


Sprout

Sprout-EWMA

Cubic

Cubic-over-CoDel



M.I.T. 6.829 contest (March–April 2013)

I Turnkey network emulator, evaluation

I Sender, receiver run in Linux containers

I Mission: maximize throughput/delay

I 4th prize: $20

I 3rd prize: $30

I 2nd prize: $40

I (If beat Sprout) 1st prize:

Co-authorship on future paper

Anirudh Sivaraman, KW, Pauline Varley, Somak Das, Joshua Ma, Ameesh Goyal, JoaoBatalha, and Hari Balakrishnan, Protocol Design Contests, in submission







I 4th prize: $20

I 3rd prize: $30

I 2nd prize: $40

I (If beat Sprout) 1st prize: Co-authorship on future paper








I 4th prize: $20

I 3rd prize: $30

I 2nd prize: $40

I (If beat Sprout) 1st prize: Co-authorship on future paper




Baseline



Land of 3,000 student protocols



Sprout was on the frontier



Limitations

I Sprout wants to control all of the traffic on a queue.

I Cells generally have per-user queues. . .I . . . but Wi-Fi and wired networks usually don’t.

I What if cell link isn’t the bottleneck?

I Assumption: application always has data to send



Our approach

I Pick a model, any model.

I All models are wrong, but they help anyway!

I See if it lands on the frontier.*

* (On a large set of real network paths or newly-collectedtraces.)

I Kaizen for congestion



Thank you

I Lakshminarayanan Subramanian

I Shuo Deng

I Jonathan Perry

I Katrina LaCurts

I Andrew McGregor

I Tim Shepard

I Dave Taht

I Michael Welzl

I Hannes Tschofenig

I Wireless@MIT members (http://wireless.csail.mit.edu)

I NSF & Shannon family (fellowship)



Sprout for controlled delay over cellular networks

I Model varying link speed

I Infer current link speed

I Predict future link speed

I Control risk of large delay with cautious forecast

I Yields 2–4× throughput of Skype, Facetime, Hangout

I Achieves 7–9× reduction in self-inflicted delay

I Matches some active queue management purely end-to-end

I Code and directions at http://alfalfa.mit.edu

I [email protected]



150

200

250

300

350

400

450

500

550

200030005000100002000050000100000

Th

rou

gh

pu

t(k

bp

s)


Verizon 3G (1xEV-DO) Downlink

Sprout-EWMACompound TCP

LEDBAT

Cubic

Skype

FacetimeGoogle Hangout

Vegas

Sprout



200

300

400

500

600

200300500100020003000500010000

Th

rou

gh

pu

t(k

bp

s)


Verizon 3G (1xEV-DO) Uplink

Sprout-EWMA

Compound TCP

LEDBAT

Cubic

Skype

Facetime

Google Hangout

Vegas

Sprout



500

1000

1500

2000

2500

3000

3500

4000

3050100200300500100020005000

Th

rou

gh

pu

t(k

bp

s)


AT&T LTE Downlink

Sprout-EWMA

Compound TCPLEDBATCubic

Skype

Facetime

Google Hangout

Vegas

Sprout



200

300

400

500

600

700

800

900

2003005001000200050001000020000

Th

rou

gh

pu

t(k

bp

s)


AT&T LTE Uplink

Sprout-EWMA

Compound TCP

LEDBATCubic

SkypeFacetime

Google Hangout

Vegas

Sprout



200

400

600

800

1000

1200

1400

1600

3005001000200030005000

Th

rou

gh

pu

t(k

bp

s)


T-Mobile 3G (UMTS) Downlink

Sprout-EWMA

Compound TCPLEDBAT

Cubic

SkypeFacetime

Google Hangout

Vegas

Sprout



200

300

400

500

600

700

800

900

1000

2003005001000200050001000030000

Th

rou

gh

pu

t(k

bp

s)


T-Mobile 3G (UMTS) Uplink

Sprout-EWMA

Compound TCP

LEDBAT

Cubic

Skype

Facetime

Google Hangout

Vegas

Sprout



Documents

Stochastic Forecasts Achieve High Throughput and Low · PDF fileVerizon LTE uplink throughput 0 500 1000 1500 ... Verizon 3G/LTE, AT&T LTE, T-Mobile 3G uplink and ... Stochastic Forecasts