systems wireless embedded distributed system design from a sensor net perspective david culler

19
S y s t e m s Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

Post on 15-Jan-2016

215 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

Sys

temsW

irel

ess

EmBedded

Distributed System Design from a Sensor

Net Perspective

David Culler

Page 2: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

1/28/2004 Sensor Net Day 2

Sys

temsW

irel

ess

EmBedded

Moore’s Law – 2x stuff per 1-2 yr

Page 3: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

1/28/2004 Sensor Net Day 3

Sys

temsW

irel

ess

EmBedded

Bell’s Law – new computer class per 10 years

year

log

(p

eo

ple

pe

r c

om

pu

ter)

streaming informationto/from physical world

Number CrunchingData Storage

productivityinteractive

• Enabled by technological opportunities

• Smaller, more numerous and more intimately connected

• Ushers in a new kind of application

• Ultimately used in many ways not previously imagined

Page 4: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

1/28/2004 Sensor Net Day 4

Sys

temsW

irel

ess

EmBedded

Making it happen

• Move the research from ‘simulations of imagined problems’ to ‘experience with real ones’

open, widely used HW/SW “close enough” platform

• Pilot applications that show how it might change the way we do science and engineering

Focus the technology advance Set the bar on capability

• Tackle the new computer systems challenges due resource constraints, scale, & embedment

Fundamentally simpler, more robust software structures

Page 5: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

1/28/2004 Sensor Net Day 5

Sys

temsW

irel

ess

EmBedded

Open Experimental Platform to Catalyze a Community

Small microcontroller

- 8 kb code,

- 512 B data

Simple, low-power radio

- 10 kb

EEPROM (32 KB)

Simple sensors

WeC 99“Smart Rock”

Mica 1/02

NEST open exp. platform

128 KB code, 4 KB data

50 KB radio

512 KB Flash

comm accelerators

- DARPA NEST

Dot 9/01

Demonstrate scale

- Intel

Rene 11/00

Designed for experimentation

-sensor boards

-power boards

DARPA SENSIT, Expeditions

TinyOS www.tinyos.net

Networking

Services

Crossbow

Page 6: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

1/28/2004 Sensor Net Day 6

Sys

temsW

irel

ess

EmBedded

Example uses

• Env. Monitoring, Conservation biology, ...– Precision agriculture, land conservation, ...

– built environment comfort & efficiency ...

– alarms, security, surveillance, treaty verification ...

• Civil Engineering: structures response– condition-based maintenance

– disaster management

– urban terrain mapping & monitoring

• Interactive Environments– context aware computing, non-verbal

communication

– handicap assistance

» home/elder care

» asset tracking

• Integrated robotics

CENS.ucla.eduLifetime and Scale

Sample Rate & Precision

Mobility & Disconnection

Page 7: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

1/28/2004 Sensor Net Day 7

Sys

temsW

irel

ess

EmBedded

Resolving The Systems Challenge

applications

service

network

system

architecture

data mgmt

Monitoring & Managing Spaces and Things

technology

MEMSsensing Power

Comm. uRobotsactuate

Miniature, low-power connections to the physical world

Proc

Store

Page 8: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

1/28/2004 Sensor Net Day 8

Sys

temsW

irel

ess

EmBedded

Traditional Systems

• Well established layers of abstractions

• Strict boundaries

• Ample resources

• Independent Applications at endpoints communicate pt-pt through routers

• Well attended

User

System

Physical Layer

Data Link

Network

Transport

Network Stack

Threads

Address Space

Drivers

Files

Application

Application

Routers

Page 9: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

1/28/2004 Sensor Net Day 9

Sys

temsW

irel

ess

EmBedded

by comparison ...

• Highly Constrained resources– processing, storage, bandwidth, power

• Applications spread over many small nodes– self-organizing Collectives – highly integrated with changing environment and network– communication is fundamental

• Concurrency intensive in bursts– streams of sensor data and

network traffic

• Robust– inaccessible, critical operation

• Unclear where the boundaries belong

– even HW/SW will move

=> Provide a framework for:

• Resource-constrained concurrency

• Defining boundaries

• Appl’n-specific processing and power management

allow abstractions to emerge

Page 10: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

1/28/2004 Sensor Net Day 10

Sys

temsW

irel

ess

EmBedded

Example 1: Rethinking Across Layers

• Appln Specific VM• Routing

– Bcast– Aggregate operation– Epidemic

Dissemination

• Sleep• Neighborhood

– Link estimation– Table mgmt– Reflected tuples

• MAC– Backoff– Collision– Recovery– TimeStamp

• Phy– Energy– Sampling

Watchdog

analog

Digital

???

Clocks

Timers

Flash

StorePower Mgmt

Phy

Link

Network

Transport

nbr

mac

Broadcast Collect

Aggregate

Scheduler

Data proc.

Neighborhoods

AS Virtual Machine

Timesynch

Localize

Page 11: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

1/28/2004 Sensor Net Day 11

Sys

temsW

irel

ess

EmBedded

Example 2: Multihop Routing

• Necessity for low-power operation at scale

• Discover connectivity graph

• Determine routing subgraph relative to traffic pattern

• Route data hop-by-hop

Page 12: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

1/28/2004 Sensor Net Day 12

Sys

temsW

irel

ess

EmBedded

Example Radio Cells

Page 13: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

1/28/2004 Sensor Net Day 13

Sys

temsW

irel

ess

EmBedded

Discovery & Routes formation

0

112

2

2

22

Page 14: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

1/28/2004 Sensor Net Day 14

Sys

temsW

irel

ess

EmBedded

Behavior over Time

70-100%

Est. Link Quality

40-70%

0- 40%

Tree Depth

1

2

3

Page 15: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

1/28/2004 Sensor Net Day 15

Sys

temsW

irel

ess

EmBedded

What is connectivity?

• CS: Ability to correctly receive a large fraction of transmitted packets

• EE: Signal-to-noise ratio exceeds some threshold

Page 16: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

1/28/2004 Sensor Net Day 16

Sys

temsW

irel

ess

EmBedded

The Amoeboed “cell”

Signal

Noise

Distance

Page 17: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

1/28/2004 Sensor Net Day 17

Sys

temsW

irel

ess

EmBedded

Which node do you route through?

Page 18: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

1/28/2004 Sensor Net Day 18

Sys

temsW

irel

ess

EmBedded

What does this mean?

• Always routing through nodes “at the hairy edge”

– Wherever you set the threshold, the most useful node will be close to it

• The underlying connectivity graph changes when you use it

– More connectivity when less communication

– Discovery must be performed under load

Page 19: Systems Wireless EmBedded Distributed System Design from a Sensor Net Perspective David Culler

1/28/2004 Sensor Net Day 19

Sys

temsW

irel

ess

EmBedded

Deeper questions

• Localized algorithms: Distributed computation where each node performs local operations and communicates within some neighborhood to accomplish a desired global behavior

– D. Estrin, “21st Century Challenges…”

• It takes energy to maintain ‘structure’ from local interactions.

• How much?– To maintain a routing tree?

– To aggregate?

– To disseminate info?

• Compression / reliability, ….