Adaptive communication for collaborative interaction in ... · Adaptive communication for...

7/9/18

1

0 9 / 0 7 / 2 0 1 8 1

Adaptive communication for collaborative interaction in smart environments

Khalil Drira,Département Réseaux et Communications (RC)

Equipe Services et Architectures pour Réseaux Avancés(SARA)

LAAS-CNRS, Toulouse, FranceRT Days, June 21, 2018

0 9 / 0 7 / 2 0 1 8 20 9 / 0 7 / 2 0 1 8 2LAAS-CNRS

/ Laboratoire d’analyse et d’architecture des systèmes du CNRS2

Integration of heterogeneous

Systems & Semantic Reasoning

Datainteroperability

Communication Protocols

interoperability

Towards open & cognitive IoTBuy & track shipped

plants

Track Things in real time

Persons remotely monitor and control garden irrigation

facilities

Allow the remote control of Things

Cooperation between systems : irrigation, weather & botanic

to adapt watering

Let Things becomesmart & cooperative

Plants act on the irrigation system to water themselves

Let Things talk & understand

each others (M2M)

View images of plants & gardens

Provide on line content

7/9/18

2

0 9 / 0 7 / 2 0 1 8 30 9 / 0 7 / 2 0 1 8 3LAAS-CNRS


LAAS/SARA R&D directions for IoT challenges1

• Autonomic Management:• Semantic-

enabledDynamic deployment discovery & integration

IncreasingComplexity

• Common Services & Horizontal Architectures

• Semantic Interoperability:

• Protocol level • Data level

VerticalFragmentation

• Softwarized & Virtualized Networks: SDN, NFV, Overlays

NetworkMisalignment

• Detect anomalies & Prevent DoSattacks:• Unsupervised

Machine / Reinforcement / Deep Learning

Security

• Energy Saving: • Protocol-

level,• Middleware

levelLPWAN (LoRA, NB-IoT)

PowerManagement

1The internet of things: Key applications and protocols O.Hersent, D.Boswarthick, O.Elloumi John Wiley & Sons, 2012

0 9 / 0 7 / 2 0 1 8 40 9 / 0 7 / 2 0 1 8 4LAAS-CNRS


Enabling cross-domain interoperability

Building

Existing ICT infra

Dedicated devices

Security

Exis9ng ICT infra

Dedicated devices

Energy

Existing ICT infra

Dedicated devices

Invert the pipe

Building

M2M devices

Security

M2M devices

Energy

M2M devices

Converged ICT infra

Common service platform

VerticalFragmentation

> Horizontal Interoperability : International standards oneM2M, ETSI SmartM2M.

> Other initiatives & projects: Allseen, EU projects,etc.

7/9/18

3

0 9 / 0 7 / 2 0 1 8 50 9 / 0 7 / 2 0 1 8 5LAAS-CNRS


Semantic gap breaks IoT horizontality

Taxo

nom

y

Onto

logy

<measurement><device>TEMP-AZ1299B</device>

<value>17</value><unit>C</unit><time>20160116T192030</time>

</measurement>

Desc

riptio

n

<observation><ID>TEMP-AZ1299B</ID>

<data>17</data><unitOfmeasure>C</ unitOfmeasure><timestamp>126738</timestamp>

</observation>

Text

Keyw

ords

TEMP-AZ1299B , 17 , C , 20160116T192030

Hexa

/Bin

ary

rQrZflVb7Si/5kUxvqOdLNMXUU7

Knowledge

01010101101 0101 01010101

DataData

Ta g - le v e l1

o b s e r v a t io n

m e a s u r e m e n t

0 9 / 0 7 / 2 0 1 8 60 9 / 0 7 / 2 0 1 8 6LAAS-CNRS


Semantic IoT: The goals> Effective data interoperability between devices and

applications without any prior agreement.> Generic interworking and automated management of

devices.> Semantic discovery and data querying.> Semantic matching and binding of devices and apps.> Semantic reasoning to infer new knowledge from facts.> Better monitoring and understanding of the surrounding

environment. > Smart decisions to dynamically adapt to environment

changes.

7/9/18

4

0 9 / 0 7 / 2 0 1 8 70 9 / 0 7 / 2 0 1 8 7LAAS-CNRS


LAAS’s OM2M: IoT sw service pla3orm

> The reference standard-com pliant open

source p latform : O M 2M .org

> O ngoing extensions (+10K lines) by O range & D eutsche Telekom

> Experim ental deploym ent at LA A S: A D R EA M /Sm art A ppart/R obots (w ith D O /R IS )

> D eployed to protect the gatew ay of the A D R EA M

build ing from dam age caused tw ice by oversized trucks

0 9 / 0 7 / 2 0 1 8 80 9 / 0 7 / 2 0 1 8 8LAAS-CNRS


IoT-O: LAAS’ ontology for IoT> Validated and disseminated in “Communication Standards” SI,

IEEE Comm. Mag. Dec 2015> Enhanced, implemented, experimented since 2016 (W iley ITL 2018)

> Reused for contribution to the international standard oneM2M Base Ontology (LAAS-CNRS/Alcatel-NOKIA) :

OneM2M base ontology proposalMAS-2015-0564R01, June 2015

7/9/18

5

0 9 / 0 7 / 2 0 1 8 90 9 / 0 7 / 2 0 1 8 9LAAS-CNRS


Highlights, Deployments, Experiments, Hackathons

ADREAM @ LAAS

Eclipse OM2M V1, V2

Startup hosted by IoT Valley Toulouse

0 9 / 0 7 / 2 0 1 8 1 00 9 / 0 7 / 2 0 1 8 1 0LAAS-CNRS

/ Laboratoire d’analyse et d’architecture des systèmes du CNRS1 0

Semantic models: Recent Publications

Contribution to OneM2M Standard, Mar. 2015 “OneM2M base ontology proposal”.

“A model-driven methodology for the design of autonomic and cognitive IoT-based systems: application to healthcare“. IEEE Transactions on Emerging Topics in Computational Intelligence, Vol.1, N°3, Jun. 2017.

“Towards semantic data interoperability in oneM2M standard”. Communication Standards SI. IEEE Communications Magazine, Dec. 2015

“An Autonomic Cognitive Pattern for Smart IoT-based System Manageability: Application to Comorbidity Management ”, ACM TOIT to appear in 2018.

“Cache freshness in named data networking for the internet of things”. The Computer Journal, Janv. 2018,

7/9/18

6

0 9 / 0 7 / 2 0 1 8 1 10 9 / 0 7 / 2 0 1 8 1 1LAAS-CNRS


Machine Learning: Recent Publications

“Cache freshness in named data networking

for the internet of things”. The Computer Journal, Janv. 2018,

Scalable , Se lf-healing and Self-optim izing Routing O verlays, IF IP

N etw orking 2016.

“B ig D ata for A utonom icIntercontinental O verlays“. IEEE JSAC, 34(3), 2016.

“U nsupervised N etw ork Intrusion D etection System s: D etecting the U nknow n w ithout Know ledge”,

IEEE N etw ork, 26 (1), 2012.

“IoT Attack D etection w ithD eep Learning ’’, ISC IS

Security W orkshop 2018.

0 9 / 0 7 / 2 0 1 8 1 20 9 / 0 7 / 2 0 1 8 1 2LAAS-CNRS


Implementation scenario

7/9/18

7

0 9 / 0 7 / 2 0 1 8 1 30 9 / 0 7 / 2 0 1 8 1 3LAAS-CNRS


Thanks

0 9 / 0 7 / 2 0 1 8 1 40 9 / 0 7 / 2 0 1 8 1 4LAAS-CNRS


E-health (with LIST/LU)

Fleet Management (with ATOS)

Smart Metering (with VTT/FI)

Robotics (with RO/RIS)

Dynamic Manufacturing

Networks (with Airbus group)

Rescue Systems (with RO/RIS,

IRIT, ONERA)

Related activities of SARA: executive summary

N etw ork V irtualisation

Scalability M anagem ent

Softw are-D efined N etw orks

O pen Interoperable IoT

A rchitectures

Traffic M anagem ent

& O ptim ization

Theories &Techniques

Reinforcement Learning

Unsupervised learning

FM, Graphs & G. Grammars

SemanLc & Ontologies

Game Theory

Transversal Axis

SYNERGYAI

Platform s

OM2M V0.8 OM2M V1.0

Tools & FW

F A C U S

G M T E

FrameSelf

Recent Projects AATAC ROSACEA2NETS IMAGINE

EndeavorLAAS/OPA

CNES DGAe-Horizon

OrangeP a n a c e a

TOUIX S2C2

IDEX/ChairRTRA/ CYPHYS

7/9/18

8

0 9 / 0 7 / 2 0 1 8 1 50 9 / 0 7 / 2 0 1 8 1 5LAAS-CNRS


Semantic IoT vs Semantic Web

> Semantic IoT has more requirements and constraints than Semantic Web.

> It requires continuous:• monitoring, • pre-processing, • filtering, • aggregation, • annotation, and • integration.

0 9 / 0 7 / 2 0 1 8 1 60 9 / 0 7 / 2 0 1 8 1 6LAAS-CNRS


Mastering complexity by semantic reasoning

Challenges for Autonomic Mgt in IoT:• Generic solutions for autonomic management

of IoT systems. • Ontology for semantic reasoning: self-

configuration of devices

Monitor

Plan

Execute

Analyze

Knowledge

A utonom ic M anager [Kephart’03]

Managed Element

IncreasingComplexity

7/9/18

9

0 9 / 0 7 / 2 0 1 8 1 70 9 / 0 7 / 2 0 1 8 1 7LAAS-CNRS


STATE_SERVICE

Sensor

TEMPERATURE_SENSORService

TEMPERATURE

QuantityKind

CONTROL_SERVICE

ActuatorHEATER_ACTUATOR

Service

GATEWAY1_NODENode

GATEWAY2_NODE

Node

SERVER_NODE

Node

LAN

Gateway 1

Server

Gateway 2

WAN

LAN

Temperature sensor

HeaterActuator

M K

A P

E

1. M onitoring

• Runtime discovery of devices andupdate of the IoT-O ontology instance.

Self-configuring IoT devices (1/4)

0 9 / 0 7 / 2 0 1 8 1 80 9 / 0 7 / 2 0 1 8 1 8LAAS-CNRS


STATE_SERVICE

Sensor

TEMPERATURE_SENSOR

Service

TEMPERATURE

QuantityKind

CONTROL_SERVICE

Actuator

HEATER_ACTUATOR

Service

GATEWAY1_NODE

Node

GATEWAY2_NODE

Node

SERVER_NODE

Node

LAN

Gateway 1

Server

Gateway 2

WAN

LAN

M K

A P

E

2. A nalyzing

• Apply seman5c rules to find relevant matching between

devices and actuators.


Temperature

sensorHeater

Actuator

7/9/18

10

0 9 / 0 7 / 2 0 1 8 1 90 9 / 0 7 / 2 0 1 8 1 9LAAS-CNRS


STATE_SERVICE

SensorTEMPERATURE_SENSOR

Service

TEMPERATURE

QuantityKind

CONTROL_SERVICE

ActuatorHEATER_ACTUATOR

Service

GATEWAY1_NODENode

GATEWAY2_NODENode

SERVER_NODE

Node

LAN

Gateway 1

Server

Gateway 2WAN

LAN

M K

A P

E

3. P lanning

• Query the ontology instance to find service operaNons of matched devices to create acNons.


Temperature sensor Heater

Actuator

0 9 / 0 7 / 2 0 1 8 2 00 9 / 0 7 / 2 0 1 8 2 0LAAS-CNRS


STATE_SERVICE

Sensor

TEMPERATURE_SENSOR

Service

TEMPERATURE

Quan:tyKind

CONTROL_SERVICE

Actuator

HEATER_ACTUATOR

Service

GATEWAY1_NODE

Node

GATEWAY2_NODE

Node

SERVER_NODE

Node

LAN

Gateway 1

Server

Gateway 2

WAN

LAN

M K

A P

E

4. Executing

• Convert actions to HTTP requests

and create required device subscriptions on the platform.


Temperature

sensor

Heater

Actuator

7/9/18

11

0 9 / 0 7 / 2 0 1 8 2 10 9 / 0 7 / 2 0 1 8 2 1LAAS-CNRS


Ambient Intelligence: the scope of challenges

Adaptive communication for collaborative interaction in ... · Adaptive communication for...

Documents

Transcript of Adaptive communication for collaborative interaction in ... · Adaptive communication for...