29
An adaptive video An adaptive video multicast scheme for multicast scheme for varying workloads varying workloads Kien A.Hua, JungHwan Oh, Kien A.Hua, JungHwan Oh, Khanh Vu Khanh Vu Multimedia Systems, Springer-Verla Multimedia Systems, Springer-Verla g 2002 g 2002

An adaptive video multicast scheme for varying workloads Kien A.Hua, JungHwan Oh, Khanh Vu Multimedia Systems, Springer-Verlag 2002

  • View
    213

  • Download
    0

Embed Size (px)

Citation preview

An adaptive video multicast An adaptive video multicast scheme for varying workloadsscheme for varying workloads

Kien A.Hua, JungHwan Oh, KhanKien A.Hua, JungHwan Oh, Khanh Vuh Vu

Multimedia Systems, Springer-Verlag 2002Multimedia Systems, Springer-Verlag 2002

OutlineOutline

• Introduction

• Related Work

• Proposed Approach

• Performance Model

• Performance

• Conclusion

IntroductionIntroduction

• Maximize the efficiency of server resource with– Periodic broadcast – Scheduled Multicast (batching)– Hybrid Design

• Will show that existing scheduled multicast techniques are not suited for hybrid designs

Related WorkRelated WorkSkyscraper Broadcasting SchemeSkyscraper Broadcasting Scheme

• Fragmentation recursive function

– Series [1,2,2,5,5,12,12,25,25,52,52,…]

Related WorkRelated WorkSkyscraper Broadcasting SchemeSkyscraper Broadcasting Scheme

Apply aforementioned series function => segment size = 10.4 !!

22-mins video

1.5 Mbits/sec

5 min buffer

0.5 min latency

Related WorkRelated Work Scheduled Multicast Scheduled Multicast

• Differ primarily in the criterion used to select which batch will receive service– First come, first served (FCFS)– Maximum queue length first (MQL)– Maximum factored queue length first (MFQ)

Related WorkRelated Work Scheduled Multicast Scheduled Multicast

• FCFS

• MQL

timeVideo 1

timeVideo 2

time

timeVideo 2

Video 1

Fair , maybe bad throughput

Better throughput, maybe not fair

Related WorkRelated Work Maximum factored queue length first (MFQ)Maximum factored queue length first (MFQ)

• Applying a discriminatory weighting factor to the length of the queue

• : video i length, : the request frequency of video i

• Schedule video with the largest value of

iq if

tqtq

q

f

qi

i

i

i

i

/

Related WorkRelated Work Maximum factored queue length first (MFQ)Maximum factored queue length first (MFQ)

• d• d

Still not fair, because not average waiting time !!

Proposed ApproachProposed Approach

• Adaptive Hybrid Approach (AHA)– With a novel scheduled multicast --“Largest aggregated waiting time first scheme” (LAW)

– And SB (skyscraper broadcast)

LAWLAW

• Compare with MQL, it take account of the distribution of the request – With considering “aggregated waiting time”

m : the total number of pending requests for video i

ija : the arrival time of the jth request for video i

c : the current time

LAWLAW

S1=128*5-(107+111+115+121+126)=60

S2=128*4-(112+119+122+127)=32

S1=128*5-(107+111+115+121+126)=60

Compute the sum of video i service latency

Adaptive hybrid approachAdaptive hybrid approach

• With following procedures to decide which videos to broadcast

Adaptive hybrid approachAdaptive hybrid approach

Performance modelPerformance model

• Compare AHA with MFQ-SB-n

• Performance metrics– Defection rate– Unfairness– Average service latency– Throughput

• 100 videos, each 120 mins,

avg. playback rate 1.5 Mbits/sec.

Performance modelPerformance model

Performance - LAW vs. MFQPerformance - LAW vs. MFQ

Arrival rate : 8 req/min

Skew factor : 0.3

LAW perform slightly better than MFQ

in service latency,throughput, defection rate

PerformancePerformance

PerformancePerformance

• Compare MFQ-SB-n with altering one of– Server Capacity (channels)– Request Arrival Rate– Skew Factor

Alter Server Capacity Alter Server Capacity (channels)(channels)

Alter Request Arrival RateAlter Request Arrival Rate

Alter Skew FactorAlter Skew Factor

Alter request rate & skew factorAlter request rate & skew factor

ConclusionConclusion

• Prove that existing scheduled multicast schemes are not suited for hybrid design

• Proposed a new technique called Largest Aggregated Waiting time first (LAW)

• AHA is capable of coping with a changing workload

Periodic Broadcast (1996)Periodic Broadcast (1996)

video

time

• PB v.s. batch:– Short initial delay– Large client-side buffer

Client requests

Batching (1993)Batching (1993)

0 t1 t2 t3

Client requests

time

• Batch window:– The time interval to initiate a batch stream.

Adaptive hybrid approachAdaptive hybrid approach

Adaptive hybrid approachAdaptive hybrid approach