context reasoning and prediction in smart environments: the home manager case
TRANSCRIPT
Context Reasoning and Prediction
in Smart Environments:
the Home Manager case
IIMSS 2017
Algarve - Portugal, 23 June 2017
Roberta Calegari, Enrico Denti
Outline
• Scope & Goals
• Smart Environments in the Butlers perspective
o The Butlers Vision
o The Home Manager Platform
o The Home Manager Architecture
• Smart Environment in HM
• The Smart Kitchen Case Study
o The Smart Kitchen: Scenario
o The Smart Kitchen: Prototype
• Conclusions & Future Work
Scope & Goals (1/2)
Smart Environments socio-technical nature calls for
from diverse fields multi-paradigm perspective
REQUIREMENTS
• availability of an effective coordination middleware
• effective support to situatedness
• guidelines and enabling techniques exploiting concepts,
methodologies, technologies from the most diverse fields,
in a multi-paradigm perspective
• skills
• concepts
• methodologies
• technologies
Framework for the design & development
of Smart Environments
• accounting for technological and human / organisational aspects
• combining different dimensions and behaviour from
pervasive, distributed, situated and intelligent computing
Scope & Goals (2/2)
Butlers for Smart Spaces
• technology-neutral
• reference framework
• focused on users’ situated-ness and interaction aspects
Home Manager
• platform for Smart Home & Smart Living contexts
• focused on reasoning aspects
• multi-paradigm, agent-based
The Butlers Vision
• Butlers for Smart Spaces specialises the Butlers framework
to the Smart Spaces context
• Home Manager leads to concretise it as a multi-agent system
on the TuCSoN infrastructure
Butlers for Smart Spaces…
Specialisation of the Butlers framework to the Smart
Spaces context
The Monitoring layer groups together the
Butlers information and control layers
The Services layer embeds
the coordination referring to
the pre-processing of raw
information into exploitable
knowledge
Goals & Policies side-by-
side take into account user-
awareness (user-related,
higher-level coordination)
The Reasoning & Situated
Reasoning layers split the
Butlers Intelligence layer
…on Home Manager as a MAS
Home Manager (apice.unibo.it/xwiki/bin/view/Products/HomeManager)
concretises it as a MAS on the TuCSoN infrastructure
The TuCSoN infrastructure conceptually
surrounds all layers, enabling and govern-
ing agent coordination & interaction
• All layers are re-shaped
based on TuCSoN concepts
& metaphors
• Agents & Policies sub-
layers appear side-by-side,
following the TuCSoN
approach
The Home Manager platform
• Open source platform for Smart Spaces, built on top of the
TuCSoN multi-agent infrastructure
o deployable also on a Raspberry PI 2
o Java-based
(~interoperable with Win10-IoT core)
• Smart House immersed in the surrounding environment
Smart Living context
o Devices (air conditioners, lights, etc.)
o Users of different categories + RBAC
• Focus on Context Reasoning & Context Prediction
o Satisfy users desires while respecting global constraints
suitable coordination laws to govern interaction
o Anticipate needs by exploiting the user’s situation in time and space
Intuitive architecture
Main features:
o Autonomous “situated” decisions by exploiting the user’s location
o Exploration of the environment around the user’s location
o Information about the surrounding environment (e.g. weather)
o Interaction with selected social networks (e.g. Twitter)
o Tracking of the human presence
Smart Environments in HM
• Designing a Smart Environment in Home Manager amounts to:
o identify relevant device and service categories
o define a tuple-based representation of the relevant knowledge
o define the agent interaction
o develop an agent for each device category & service to interact with
Clear separation between
• social / individual intelligence
• mechanisms / policies
Features
• independent testing and debug of agents and policies
• effective exploitation of the data-driven, multi-paradigm development approach
• Smart Fridge & Smart Pantry
o food monitoring
o collecting historical data on user’s habits
o generate the corresponding buy tuple if necessary (policies)
• Smart Oven
o support the user’s food cooking (e.g. dietary,…)
• Smart Mixer
o recipe instructions interacting with Smart Fridge & Smart Oven to
check food availability context adaptation
• Smart Shopper
o predict the user’s needs make contextualised suggestions
o shopping list based on the above data
o contact the “proper” vendor based on context- aware policies
The Smart Kitchen: scenario
The Smart Kitchen: prototype
Middleware coordination laws interoperability & integration
• Declarative approach
o bridge among different forms of heterogeneity
o support agent uncoupling
o support & promote separation between policies & mechanisms
o supports context reasoning
Future (current) work
Context prediction & adaptation: prediction agent
WEKA Classifier (Ilaria Bertoletti Master's thesis, 15 June 2017)
Tempera-
ture prefs
Device
usage
policies
Action plan on
air conditioners
Learning &
prediction of
user habits
Future (current) work
Context prediction & adaptation: prediction agent
WEKA Classifier (Ilaria Bertoletti Master's thesis, 15 June 2017)
CONTEXT PREDICTION
• Grab user habits info from multiple sources
• Select relevant data
• Anticipate user's routine & desires
CONTEXT
REASONING
• Compute heterogeneous context info
• Enable HM to make suggestions
• Increase HM decision autonomy
PROACTIVE ADAPTATION
• Autonomously appy action plan on house devices
• Enable HM to adapt to new needs
• Reduce user's interventions
Future (current) work
Context prediction & adaptation: prediction agent
WEKA Classifier (Ilaria Bertoletti Master's thesis, 15 June 2017)
• Get daily routine
• Weather + policies + routine
= decision
Future (current) work
Context prediction & adaptation: prediction agent
WEKA Classifier (Ilaria Bertoletti Master's thesis, 15 June 2017)
Home Manager lays the foundations to support
context reasoning and context prediction
• Yet, just a starting point..
• A lot of work remains to be done
Conclusions (1)
Butlers for Smart Spaces
• technology-neutral
• reference framework for pervasive IoT contexts
• focused on users’ situated-ness and interaction aspects
Home Manager
• concretise the BSS approach
• the infrastructure bridges among the agents’ ontologies, APIs, knowledge representations, interaction protocols
Conclusions (2)
Future work
• Deeper exploration of the context reasoning aspect
(machine learning,…)
• Cross-platform interoperability
• Java/Windows 10 on the Raspberry
• Emerging standards
• Developing more complex policies and implementing other
advanced situated services
Home Manager URLs
• Home page http://apice.unibo.it/xwiki/bin/view/Products/HomeManager
• Bitbucket repository https://bitbucket.org/tuprologteam/homemanager
Roberta Calegari [email protected]
Enrico Denti [email protected]
http://www.unibo.it
http://www.cse.unibo.it/en
http://apice.unibo.it/xwiki/bin/view/Main/?language=en