Upload
flower
View
22
Download
0
Embed Size (px)
DESCRIPTION
Mobility Aware Server Selection for Mobile Streaming Multimedia CDN. Muhammad Mukarram Bin Tariq , Ravi Jain, Toshiro Kawahara {tariq , jain, kawahara}@docomolabs-usa.com DoCoMo USA Labs. September 29, 2003. Summary. - PowerPoint PPT Presentation
Citation preview
1
Mobility Aware Server Selection for Mobile Streaming Multimedia CDN
Muhammad Mukarram Bin Tariq, Ravi Jain, Toshiro Kawahara{tariq, jain, kawahara}@docomolabs-usa.com
DoCoMo USA Labs.September 29, 2003
2
Summary• We present a mobility-aware server selection scheme for content
distribution networks. • Our target is CDN with high density of servers, each server having a small
coverage area. Mobile users can move out of such service areas in the duration of streaming media sessions, resulting potentially degraded QoS.
• Server Handoff can be performed to revive QoS, but it is expensive.
• We use user’s mobility along with traditional criteria such as proximity, server load etc., and assigns a server such that the probability of user moving out of coverage area of the assigned server is reduced, while meeting QoS criteria.
• Simulation results show up to 18 % reduction in number of server handoffs.
3
Outline• Summary• Introduction
– Overview– Problem Statement
• Mobility Aware Server Selection– Assumed CDN topology– Gathering user mobility information and estimating residence time
with servers.– Server Selection.
• Simulation– Mobility, Server Selection, Content Distribution.
• Results• Conclusions
4
Introduction
• Multimedia has increasing share in overall traffic
• Fixed broadband has not harnessed Multimedia, how will mobile broadband?– Mobile phones are there all the time.
– Usage scenarios: movies, songs, news, playing video games etc, while traveling
• CDN must meet the challenge of mobility, wireless and streaming media trio.– Our focus is the (Mobility + Streaming).
Expected Future mobile communication market [Yumiba01]
2005 2010Year
Mar
ket S
ize
(tra
ffic
)
Voice20-30%
Multimedia70-80%
5
Streaming Media In Mobile Networks
• In previous work [Tariq02] we showed that server handoff is helpful for streaming content to mobile users.
• Localizes traffic, reduces delay, jitter, and load on the network.
R
R
Subnets in a Mobile Network
R R R
RR
R
Logically Non Adjacent Subnets,
(hot spots)
R
Server Server
R
Server Handoff
Server Handoff
Server
6
Naïve server handoff scheme has problems
• If the users move too fast, there would be too many server handoffs, which are expensive for the network. – Signaling, Content Placement
• Our mobility-aware server selection assigns right users to right servers, reducing the need for handoffs.– Reduce Number of Handoffs while meeting QoS
criteria.
7
CDN Topology
• Allows:– Maximization of traffic localization– Obtain desired QoS ↔ Number of Handoffs
tradeoff by choosing appropriate server tier.
Access Network Subnets
Tier 1 Server Coverage Areaaka. server-zoneEach has a RR
Tier 2 Server Coverage Area
Tier 3 Server Coverage Area Servers
More Coverage
Area
Better QoS
8
Server Selection Process
Server Tiers
RR
Server Capacity Information
Move to higher tier if
1) Server Capacity Available
2) User is Moving Fast
3) QoS Diff is maintained
Move to lower tier if
1) Server Capacity Available
2) Won’t increase handoffs
3) QoS Diff is maintained
Mobility Information
We introduce a Lazy Mode where we do not move users to lower tiers unless higher tiers are saturated!!!
9
Mobility Informationiririr
( )n n ki
t tr
k
Residence Time
Trajectory of the clientA subnet
1nt nt1( )n nt t Client i
Client maintains its average subnet residence time over k
recent moves
1
n
ii
r
nr
Mean residence time of all
n clients in RR’s server-zone
tR
, ( )ii t t
rE R
r
Mean Server Residence-time
for each tier tRR uses the information to estimate a future residence time of client i with tier t
We can make a high granularity estimate using subnet specific information, at cost of higher overhead. , ,( )i
i t t ss
rE R
r
10
Simulation
• Simulate realistic user movement in a large geographical area, collect movement events – we wrote a custom simulator for this.
• Simulate different server selection algorithms– Baseline, clients always assigned to default tier
– Eager mode with both Low and High Granularity Mobility Information
– Lazy Mode with both Low and High Granularity Mobility Information.
• See how we did in terms of delay and jitter experience by the users.
Mobility Simulation
Server Selection Simulation
Content Distribution Simulation
11
Mobility Simulation
• Custom simulator to simulate realistic urban area user movement. – Cars, Trains, Streets,
Freeways, Public Transport, Congestion, etc.
– San Francisco Bay area, 3575 sq. miles.
– Over laid with 189 base-stations, 59 subnets
12
Simulation Parameters• CDN topology
– 34 servers arranged in 3 tiers, 21, 8 and 4 in tiers 1, 2, and 3 respectively.– The 3 tiers at 80ms, 160ms and 240ms respectively, from the edge.– Server Capacity, variable {50, 75, 100, 200, 300} simultaneous sessions
• Users– 2500 users with three QoS class, {1, 2, 3}, users distributed across the
three QoS classes proportionately to the number of servers at corresponding tier.
– Session Durations, variable {50, 100, 200, 1000, 1500} seconds– Data rate per user: 64kbps, 20pps
• Selection Criteria– Desired QoS Separation between adjacent classes: 20 ms.– Server Overload threshold for Lazy mode. 10% of the maximum reported
load allowance.
13
Reduction in number of handoffs
-4-202468
101214161820
50 100 200 500 1000 1500
Session Duration (seconds)
Per
cent
Red
ucti
on in
N
umbe
r of
Han
doff
sSimulation Results (1/2)
Eager Mode
Lazy Mode
Low Granularity
High Granularity
Results for server capacity = 300
Results for server capacity = 100
More results in the paper…
14
Simulation Results (2/2)
• Desired Separation is maintained in all scenarios
• Eager mode is achievesbetter convergence and at lower overall value.
• Higher server capacityallows us to do more.
• Accuracy of estimationhas little impact.
Impact on QoS
0.08
0.1
0.12
0.14
0.16
0.18
0.2
0.22
0.24
0.26
100 200 300
Server Capacity (number of sessions)
E2E
Del
ay (
seco
nd
s)
Eager Mode
QoS Class 1 QoS Class 2 QoS Class 3Lazy Mode
15
Conclusions• We have presented a mobility aware server selection scheme.
– Up to 18% reduction in number of server handoffs. – Simple, Largely stateless– Relies on simple and manageable information – much of which is
already available in the network.• If you are eager, you better be sure – with eager mode, higher
accuracy is crucial.• Has applications beyond streaming media.
– Anywhere that you want to make tradeoff with mobility by switching to wider-area systems.
• Open issues: – Improving while maintaining simplicity.– Manageability.– Bundling with other technologies.
16
Algorithm Details
Task: Assign server to a client i of QoS class q and current/default server tier tselectedTier := t
Find load allowance of next higher tier Lt+1
If the client is in fastest Lt+1
– true if is less than Lt+1 here Uj number of sessions of a client j
If the delay separation will be maintained – true if . similarly for q,q-1
Assign Server Tier t+1.End-If
Else-If Eager Mode or (Lazy Mode with Lt+1 too low) – checking to see if we can move it to lower tier instead
Make sure client won’t increase the number of handoffs i.e., Assign Server Tier t-1.
End-If
: j i
C
jj r r
U
1 , 1q q q qD D
, 1i t tE R