20130503 icore at calipso workshop fia dublin

Post on 20-Jan-2015

172 Views

Category:

Technology

3 Downloads

Preview:

Click to see full reader

DESCRIPTION

iCore Presentation at CALIPSO FIA Workshop (Dublin May 2013). Positioning Cognitive IoT against Internet timeline

TRANSCRIPT

Supporting all-IP IoT

with Virtual Objectswith Virtual Objects

Raffaele Giaffreda (CREATE-NET)

EU FP7 iCore Project Coordinator

FIA Dublin – 7th May 2013

a bit of IoT infographics...

BOSCH

7 bln connected devices by 2015

SAP

24 bln connected devices by 2020

INTEL

31 bln connected devices by 2020

CISCO

37-50 bln connected devices by 2020

transistor density / space efficiency

Turing’s Pilot ACE: Automatic

Computing Engine

bandwidth / spectral efficiency

Space Efficiency + Spectral Efficiency =

MAZE OF TINY, CONNECTED THINGS

Trend: more and more widespread sensing and monitoring data available

...Tiny but Powerful devices

what’s beyond IP connectivity?

The Internet parallel...

HTTP/WWW

search engines

connect your info

TCP/IP

HTML

represent info / aggregate info

WWWpersonalised knowledge

collections, blogs...

The Semantic Web

find info

VALUE!

IoT, what’s beyond IP connectivity? early stages for the IoT...

HTTP/WWW

hundreds of bespoke

IoT applications

The Semantic Web

VALUE!

personalised knowledge

collections, blogs...

represent info / aggregate info

search engines

connect your info

TCP/IP

HTML

WWW

find infoobject

today

HUMANMACHINE

IoT innovation potential...

“Innovation”: one

can focus on apps!!!

OBD

On Board Diagnostics

MACHINEHUMAN

lesson #1

• connect your objects, unlock value

siloed and bespoke IoT applications

APPS

HO

US

E

APPS

FR

IDG

E

APPS

PA

TIE

NT

APPS

PA

TIE

NT

APPSAPPS

APPSAPPS

APPSAPPS

DATA / INFORMATION OVERLOAD, BUT...

CA

R

SENSORS

HO

US

E

SENSORSF

RID

GE

SENSORS

PA

TIE

NT

SENSORS

PA

TIE

NT

SENSORS

PA

TIE

NT

SENSORS

PA

TIE

NT

SENSORS

PA

TIE

NT

SENSORS

PA

TIE

NT

SENSORS

APPS

PA

TIE

NT

SENSORS

APPS

TR

UC

K

SENSORS

APPS

IF A WELL-DEFINED INTERFACE INTO CAR SENSORS BRINGS SUCH POTENTIAL...

APPS

HO

US

E

APPS

FR

IDG

E

APPS

PA

TIE

NT

APPS

PA

TIE

NT

APPSAPPS

APPSAPPS

APPSAPPS

CA

R

HO

US

E

FR

IDG

E

PA

TIE

NT

PA

TIE

NT

SENSORS

PA

TIE

NT

SENSORS

PA

TIE

NT

SENSORS

PA

TIE

NT

SENSORS

PA

TIE

NT

SENSORS

APPS

PA

TIE

NT

SENSORS

APPS

TR

UC

K

SENSORS

APPS

SENSORS SENSORS SENSORS SENSORS

iCore concepts

• Virtual Object

• Composite Virtual

Object

• Service / User Level

• Service / User Level

Virtual Object as OBD across silos

IoT services

Virtual Object SW Agent

IoT services

VO registry

To upper iCore levels and Internet

Semantic VO descriptions

Ab

stra

ctio

n

ICT objects

(heterogeneous world)

Sensors and actuators

Proprietary servicesIoT services

Associated physical objects

Ab

stra

ctio

n

17

what ingredients?

• common interfaces to interact with

objects (i.e. REST)

• + extra containers for metadata

• let the systems know what the object • let the systems know what the object

is good for, its location (“I am a Temp

sensor in Room A”), its accuracy, its

energy levels etc.

replicate what the HTML (HyperText Markup Language)

has done for simply connected info

“I am a webpage and I talk about Paris history”

WHAT ARE VOs GOOD FOR?

• OBJECTS PROXIMITY

– automated selection “by relevance” (see arguments

for cognitive technologies in a minute...)

• OBJECTS REUSE • OBJECTS REUSE

– reuse across different apps, increase availability,

hence, increase monitoring / sensing granularity

• OBJECTS MGMT

– i.e. energy management, contextualised sensing

(accuracy vs. sensing frequency) etc.

Providing IoT systems the ability to self-configure, based on various requirements, and ...

Ability to dynamically aggregate

ProxShape(QUADRILATERAL)

ProxColour(GREEN)

ProxColour(RED)

APP / SRV

APP / SRV

APP / SRV

Cognitive.prep

Cognitive.select

VO

...providing IoT systems the ability to adapt

CA

R

APPS

HO

US

E

APPS

FR

IDG

E

APPS

PA

TIE

NT

APPS

HO

US

E

FR

IDG

E

PA

TIE

NT

SENSORS SENSORS SENSORS SENSORS

PATIENT is near the FRIDGE

CAR is near the HOUSE

PATIENT is driving the CAR

objects reuse

across domains

KitchenPresDetect PatientStatusDetect

Easy for us...not for a “dumb” computer...

lesson #2

• connect your objects across domains, unlock

further value

Internet vs. IoT

• a page + a page + a page...connect info

• represent info – HTML

• aggregate info – hyperlink

• a (sensor) feed + a feed + a feed...

• represent feeds – VO

• aggregate feeds – CVO

VALUE?

the need for cognitive technologies

• iCore Composite Virtual Object (CVO)

– aggregation of simple sensing capability

– self-maintenance (service maintained in case of

failure) increased sensing granularity needed!failure) increased sensing granularity needed!

– System Knowledge

• what is available to meet reqs?

“smart but not so much...”

ability to select alternatives based on

what metadata we put in the extra VO

containers

CT 1

the need for cognitive technologies

• iCore Service Level and overall Cognitive

Management Framework

CT 2,3

use of cognitive technologies in the IoT

• Build models for Real World

Knowledge representation

• Help predict based on observation

of past (training)

• Assist rather than replace human • Assist rather than replace human

decisions

• Personalise the behaviour of IoT

systems to tailor user changing

needs and situations

Putting it all together, iCore Cognitive Mgmt Framework

Service Level

Service

Execution

Request

Service

Request

select, notification

Service

Request

Alert / Predict

ACK

Application

CVO Level

VO Level

CVO/VO

Execution

Request

RWO

interactions

select,

deploy

(bind), runset of

running

processes

satisfying

Service

Request

notification

according

to service

templateACK

RWOs

dynamic

binding

Internet vs. IoT

• find info

• personalised knowledge collections, blogs as

“ready info meals”...

• find VOs / CVOs

• personalised IoT services, applications that

learn how to assist users

the need for cognitive technologies

• factoring “smart logic algorithms” out of developers

concerns

– IF “crash” THEN “alertRSA”

– “crash” (IF VO_x = TRUE THEN crash := TRUE)

– (IF VO_x = TRUE AND VO_y = TRUE THEN crash := TRUE)

TAG:

crash

detect

VO_x

TAG:

crash

detect

VO_yIF (VO_x = TRUE) AND (VO_y = TRUE)

THEN crash := TRUE

IF VO_x = TRUE

THEN crash := TRUE

IF (VO_x > TH_x) AND (VO_y > TH_y)

THEN crash := TRUE

factor out cognitive technologies

CT 2

• iCore community: foster “ready meals” for IoT apps

the need for cognitive technologies

• rather than for the selection of appropriate templates,

here focus is on refinement of selected one according

to observed system-reality matching

• Real-World-Knowledge “growing”

• Learning and adaptation to the users preferences• Learning and adaptation to the users preferences

TAG:

crash

detect

VO_x

TAG:

crash

detect

VO_yIF (VO_x > TH_x) AND (VO_y > TH_y)

THEN crash := TRUE

CT 3

assess

QUALITY of

PREDICTION

REFINE

TH_x, and TH_y

iCore Architecture, RWK grow and SK grow

Service Level

Service

Execution

Request

Service

Request

select,

Delta (RWK-RW)

ACK

Application

RWK

Model

tweak

parameters /

algorithms

CVO Level

VO Level

CVO/VO

Execution

Request

RWO

interactions

select,

deploy

(bind), runset of

running

processes

satisfying

Service

Request

ACK

RWOs

RWK

SK

Delta (SK-S)

SK

Model

Personalised RWK and SK...

in one slide

srv templates

(RWK models)srv templates

(RWK models)srv templates

(RWK models)

CVO templates

(SK models)

instantiation of same cognitive algorithms linking sensors

gets tailored with usage to produce outputs and alerts that

match user preferences, situation, infrastructure context

CVO templates

(SK models)CVO templates

(SK models)

iCore and Cognitive Technologies

• CVO Level “system knowledge” – SLA-driven VO selection / maintainance

– semantic enrichment � semantic-based reasoning

– selection by relevance to the needs of the application

• deal with data / information overload– template select

Summary

CT 1

– template select

– given VO / CVO “types” find best algorithms that combine these for desired output

• deal with data / information overload– learn and predict

– given an algorithm, tweak parameters to better align iCoresystem behaviour to the observed real situation

– Real World Knowledge (RWK) “growing”, adaptation to user preferences

CT 2

CT 3

The Internet of Things evolution timeline

The Dumb IoT The Craft IoT The Cognitive IoT

YESTERDAY TODAY TOMORROW

The Dumb Internet The Craft Internet The Technicolor Internet

The Dumb IoT The Craft IoT The Cognitive IoT

Bear with us, we are building it!

references

• iCore application in smart-cities and IoT-based

monitoring[REF1] P. Vlacheas, R. Giaffreda et al. "Enabling Smart Cities Through

a Cognitive Management Framework for the Internet of Things“,

to appear in IEEE Communications Magazine - Special Issue onto appear in IEEE Communications Magazine - Special Issue on

Smart Cities (June 2013)

[REF2] IERC Newsletter April 2013 – foreword by R. Giaffreda

thank you!

iCore Website

www.iot-icore.eu

Contacts:

Raffaele Giaffreda

raffaele.giaffreda@create-net.org

3 yrs EU FP7 Integrated Project

(started 1st Oct 2011)

20 Partners with strong industrial

representation

8.7mEur EU Funding

EU + China and Japan

ID Card

Japan

raffaele.giaffreda@create-net.org

Abdur Rahim

abdur.rahim@create-net.org

EU + China and Japan

top related