data stashing: energy-efficient information delivery to mobile sinks through trajectory prediction...

26
Data Stashing: Energy- Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash Gnawali, and Leonidas Guibas Stanford University ACM/IEEE IPSN’10 April 15, 2010

Upload: dwayne-paske

Post on 31-Mar-2015

217 views

Category:

Documents


2 download

TRANSCRIPT

Page 1: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks

through Trajectory Prediction

HyungJune Lee,Martin Wicke, Branislav Kusy,

Omprakash Gnawali, and Leonidas GuibasStanford University

ACM/IEEE IPSN’10April 15, 2010

Page 2: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

Traditional Data Delivery to Mobile Sinks in Wireless Ad-Hoc/Sensor Networks

• Immediate delivery from data source to mobile sinks– Proactive scheme: DSDV, OLSR– Reactive scheme: DSR, AODV

Performance degradesrapidly with increasing mobility

• Data MULEs to collect data as it passes each of the sensor nodes– Wait until mobile sinks come

to collect

Often infeasible if we cannot control the movement

2

?

• What’s a compromise between two extremes?

• How to exploit the tolerated delay?• How to use regularity of mobility pattern? • How to select only a partial set of effective relays?

Page 3: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

3/34

Overview: Predictive Mobile Routing 1. Trajectory Prediction

• Anticipated trajectory nodes

2. Data request and trajectory announcement

3. Stashing node selection• To cover the likely paths and

minimize the routing cost

4. Data stashing 5. Data collection by mobile nodes

Page 4: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

4

Summary of Contributions

• Predictive Model of Users’ Trajectories– In the space of wireless connectivity– Capture

• Long-term behavior (in minutes) – a set of the future connected relays

• Predictive Data Delivery – Propose an energy-efficient data delivery scheme to mobile sinks– Turn even limited knowledge of future connectivity

into networking benefit

A

Page 5: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

5

Outline

[Off-line Learning Phase]• Mobile Trajectory Model

– In the space of wireless connectivity– For packet delivery purpose

[Routing]• Prediction of Future Relay Connectivity• Predictive Data Delivery to Mobile Users

[Evaluation]

Page 6: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

6

Capturing Mobile Trajectory Patterns

• Background– Trajectory: a sequence of node

associations on a given spatial path

– Trajectories from the same spatial trajectory are not necessarily identical• Due to imperfect links and radio

signal strength fluctuations

• Goal– To cluster similar mobile

trajectories – General trajectory pattern

models explored by a number of spatial trajectories

al

q

o

rt

zb

py

uix

s

T = a l o r t z b p y u T’ = a l q o r z s p i u z

T’’= a q r t z t s b y i x

Page 7: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

7

Constructing trajectory clusters

• Step I. Similarity measure

• Step II. Hierarchical clustering

• Step III. Compact representation

T1 a l o r t z t b o r t how similar?

T2 t o p r b o t a

Page 8: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

8

Step I: Similarity Measure

• Similarity measure (normalized)

– Not a distance metric

F(m,n)

min(m,n)

where F(m,n) is the length of

the longest common subsequence (LCS)

[ Example 1.]

T1 a l o r t z t b o r t how similar?

T2 t o p r b o t a

LCS o r b o t

[ Example 2.]

T1 a l o r t z t b o r t how similar?

T2 a z o t

LCS a z o t

sim(T1,T2) 5 /min(11,8) 5 /8

sim(T1,T2) 4 /min(11,4) 1

Page 9: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

9

Step II. Hierarchical Clustering

• Hierarchical clustering :

Every point is its own cluster

1. Find most similar pair of clusters

2. Merge it into a parent cluster

3. Calculate the average similarity between objects in two clusters

4. Repeat

sim(r,s) 1

nrnssim(xri,xsj )

j1

ns

i1

nr

, i (1,,nr ), j (1,,ns)

Page 10: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

10

Step III: Probabilistic Representation

1. Execute multiple sequence alignment(using ClustalW tool)- Computation complexity

2. Construct Profile: A probabilistic representation for efficient search in the usage phase

R T E A C E G I P D SR E C E I G I P S D SY E C I R E C E I C G I G N G N D SE D E C I G P D SR E C H C I G K D SR E C I G C R I E C G S G D L D K SK E C G I G T D W D SR E C N I G D G T D SR E P E C N I G I D G D K D S

O(N 2L2) where

N : # of sequences

L : the sequence length

Px, j : probability of column j that is character x

-RT-EACE-GIP----D--S-R--E-CEIGIPS---D--S--Y-E-C---I---------REC-EICG--IGNG-ND--S-ED-E-C---IGP---D--S-R--E-CH-CIGK---D--S-R--E-C---IGC--------RI-E-CG--SG-D-LDK-S--K-E-CG--IGTD-WD--S-R--E-CN--IG-DGTD--S-REPE-CN--IGID-GDKDS

Page 11: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

11

Summary: Mobility Trajectory Clustersin an off-line phase

Trajectory sequences

………………

……………………….

………………….

………………………….

……………

Page 12: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

12

Outline

[Off-line Learning Phase]• Mobile Trajectory Model

[Routing]• Prediction of Future Relay Connectivity• Predictive Data Delivery to Mobile Users

[Evaluation]

Page 13: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

Prediction of Future Relay Connectivity

• Given a partial test sequence,

• 1) First find the closest cluster – A variant of Smith-Waterman

algorithm for local matching– With the largest F(*,*) among

all profiles

• 2) Find the highly overlapped region

Test sequence:

Profile:

R C E C N C

13

Mobility Profile Database

J

. . .?

Page 14: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

14

Prediction of Future Relay Connectivity

• 3) Obtain the most probable subsequences starting from J+1 through J+W

J W

Page 15: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

15

Optimal Route Selection Using Predictive Knowledge

• Data stashing:Given a set of future trajectories of multiple mobile users,

– Find the optimal stashing nodes for each data source

– Considering • Cover all possible future trajectories• Minimize routing cost to the selected relay

nodes

M1

M2

A

T3T1

T2T4

T5T6

N

Page 16: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

16

Optimal Route Selection Using Predictive Knowledge

• Optimization problem – For sensor node A, – Minimize total routing cost

• From sensor node itself • To the selected stashing nodes

– Subject to• Stashing nodes cover all possible

future paths of multiple mobile users

• Solved by LP/IP solvers such as CPLEX, Gurobi, GLPK, …

M1

M2

A

T3T1

T2T4

T5T6

N

Page 17: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

17

Outline

[Off-line Phase]• Mobile Trajectory Model

[Routing]• Prediction of Future Relay Connectivity• Predictive Data Delivery to Mobile Users

[Evaluation]• Dynamic mobility model

– Prediction Accuracy• Routing performance

– Scalability– Tolerated Delay – Load Balance– Computation for Selecting Stashing Nodes

Page 18: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

18

Validated trajectory clustering using UMass DieselNet real-world dataset : 34 buses, 4198 APs, 789 bus trips around UMass campus

• Prediction method results in excellent stashing node selections for real-world data

Prediction Accuracy of Mobile Trajectory Model

Page 19: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

19

Simulation Setup for Routing

TOSSIM under ‘meyer-light’ interference 830x790 m2

716 nodes 20 mobile trajectories

Vehicle moves at a random speed N(30, 52) km/h Vehicle sends a beacon every 1 sec Each sensor node has data to deliver to mobile

sinks

Page 20: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

20

Scalability depending on # of mobile sinks

• Data stashing consumes less energy than immediate point-to-point routing– Scalable with # of mobile sinks!

• Data stashing keeps high packet delivery even for network congestion

• Data stashing performs closely to the upper bound by perfect prediction – Even limited knowledge of future

trajectories can significantly improve routing performance!

(lower is better)

(higher is better)

Page 21: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

21

• W: # of future trajectory hops

• Large W means more chance to exploit data stashing scheme

• As W 1, data stashing should break

• Implication

Trade-off:

Tolerated delay vs. Network performance

Tolerated Delay W

(lower is better)

(higher is better)

Page 22: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

22

• Data stashing has a good load balancing performance compared to a point-to-point routing immediately to mobile sinks

Load Balance

better

Immediate Routing Data Stashing

Page 23: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

23

• PC: Dell Precision 390 (2.4 GHz Core 2 Duo)Small Embedded: fit-PC2 (Intel Atom Z530 1.6GHz)

• Measured running time for solving the optimization problem - binary integer program

• Feasible even in a small embedded platform, taking less than 500ms

(lower is better)

Running time for a source to compute stashing nodes

Page 24: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

24

Conclusion

• Dynamic mobile trajectory model in the space of wireless connectivity, capturing wireless volatility

• Mobile data delivery can be improved through mobility pattern learning and prediction

• Even limited knowledge of the future trajectory can improve networking performance

• Take-home lesson:

“If you know where someone is going (even uncertainly), you can deliver data to him more efficiently and reliably.”

Page 25: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

Two problemsCurrent delivery scheme is “best-effort”Current clustering method cannot share common pieces of trajectories

More robust packet delivery:When the system detects delivery

would fail, restashing can significantly improve robustness

Trajectory prediction and data stashing can be more intertwined

Multi-tier clustering:Long trajectories can be partitioned into

short pieces for efficient clusteringOn-line clusteringA multi-tier clustering approach can deal

with extremely large complex networks

25

Limitations & Future Works

Page 26: Data Stashing: Energy-Efficient Information Delivery to Mobile Sinks through Trajectory Prediction HyungJune Lee, Martin Wicke, Branislav Kusy, Omprakash

26

Questions?

HyungJune [email protected]