© 2010 IBM Corporation
IBM Research and Development - Ireland
© 2011 IBM Corporation
Smarter Cities Research
Lisa Amini, PhD
Distinguished Engineer and Director IBM Research and Development – Ireland
IBM Research and Development - Ireland
© 2011 IBM Corporation
1997: Copper
Interconnect Wiring
1998: Silicon-on-Insulator
1998: Microdrive 2002:
Millipede
2004: Blue Gene The fastest
supercomputer in the world
2006: 5-stage Carbon Nanotube
Ring Oscillator
2008: World’s First Petaflop Supercomputer
1948: SSEC
1956: RAMAC
1944: Mark 1
1957: FORTRAN
1964: System/360
1971: Speech Recognition
1967: Fractals
1970: Relational Database
1966: One-Device Memory Cell
1973: Winchester Disk
1979: Thin Film Recording
Heads
1980: RISC
Nobel Prizes:
Scanning Tunneling Microscope
High Temperature Superconductivity
1990: Chemically
Amplified Photoresists
1994: SIGe
1993: RS/6000 SP 1996,97: Deep Blue
1987: 1986:
A legacy of World-Class Research
IBM Research and Development - Ireland
© 2011 IBM Corporation
IBM Research: 3 New Labs Established in 2010
IBM Research Labs 1998 - 2007
IBM Research – New Presence Since 2010
China
Watson Almaden
Austin
Tokyo Haifa
Zurich
India
Dublin
Melbourne
Brazil
! Natural Resources ! Smarter Devices ! Human Systems/Events ! Natural Resources
! Disaster management ! Healthcare/Life Sciences
! Smarter Cities ! Risk Analysis ! Exascale and Hybrid Computing
IBM Research and Development - Ireland
© 2011 IBM Corporation
Smarter Cities Technology Centre
! !"#"$%&'($)*(+","-./0")1(– !"#$%&'"()*+,-.-/+01-+2)")$23()2"/+014+567+58&9:8;"+*)<)&8=)2"++
– >$2?)#+.4-+%@+A!+,-.,+BC!5+D+567+58&9:8;"E+
! 23/"%4#"(– F$#$+G';';?/+G$3(';)+&)$2;';?/+H=:I'J$:8;/+K;#)&&'?);#+L8;#28&/+
7)8"=$:$&+M;$&@"'"+$;*+N'"9$&'J$:8;/+C)$&O:I)+"@"#)I"+$;*+$;$&@:3"/+
K;P82I$:8;+$;*+Q;8R&)*?)+G$;$?)I);#/+5)I$;:3+6)%/+C)$"8;';?+
– >2$;"=82#$:8;+53');3)/+6$#)2+G$;$?)I);#/+S8R)2+5@"#)I"+
https://researcher.ibm.com/researcher/view_researchers.php
IBM Research and Development - Ireland
© 2011 IBM Corporation
How can we help cities transform ?
1. Sensor data assimilation!– Data diversity, heterogeneity – Data accuracy, sparsity – Data volume!
!
2. Modelling human demand!– Understand how people use the city
infrastructure!
– Infer demand patterns!
3. Operations & Planning!– Factor in uncertainty!– Organise and open data and knowledge, to
engage citizens, empower universities and enable business!
IBM Research and Development - Ireland
© 2011 IBM Corporation
Sensor data assimilation • Continuous assimilation of real-time traffic data
Understanding/Modeling human demand • Characterizing urban dynamics from digital traces
Operations & Planning • Leveraging mathematical programming for planning
in an uncertain world
Operations & Planning • Organising data and information to better engage
citizens, empower universities and enable businesses to help drive overall growth
Outline
Tran
spor
tatio
n W
ater
M
ulti-
dom
ain
© 2010 IBM Corporation
IBM Research and Development - Ireland
© 2011 IBM Corporation
Continuous assimilation of real-time traffic data
Eric Bouillet, PhD
Research Staff Member, Analytics & Optimization Smarter Cities Technology Centre IBM Research and Development - Ireland
IBM Research and Development - Ireland
© 2011 IBM Corporation
• To become useful, GPS data has to be related to the underlying infrastructure (e.g., road or rail network) by means of map matching algorithms, which are often computationally expensive
• In addition, GPS data is sampled at irregular possibly large time intervals, which requires advanced analytics to reconstruct with high probability GPS trajectories
• Finally, GPS data is not accurate and often needs to be cleaned to remove erroneous observations.
Noisy GPS Data
IBM Research and Development - Ireland
© 2011 IBM Corporation
Real-Time Geomapping and Speed Estimation
Matching map artifact
Estimated path
GPS probe
Estimated speed & heading
IBM Research and Development - Ireland
© 2011 IBM Corporation
• Complex system & analytics challenges • Data diversity, heterogeneity • Data accuracy, sparsity • Data volume
• Active relationship with DCC • Deployed in Dublin’s DoT
Routes & maps
Bus AVL (GPS)
Parking
capacity
Accessibility
SCATS Induction
loop
Timetables
CCTV
Car
Bike
1,000 buses 3,000 GPS / min
200 CCTV cameras
700 intersections 4,000 loop detectors 20,000 tuples / min
Our Dublin Experience (2011)
IBM Research and Development - Ireland
© 2011 IBM Corporation
Actuating the city
• Real-time, proactive traffic control!
• Traffic control recommender!
• Recommend actions under uncertainty!
• Dynamic traffic light actuation strategy
• Traffic Management Towards a Low Carbon Society!
• Traffic (congestion) is a significant contributor to CO2 emissions !
• We are building a method, system and tools for adaptively influencing traffic in real-time to reduce carbon dioxide CO2- and black carbon (BC) emissions caused by road transport in urban and inter-urban areas.!
• Pilot cities include Glasgow, UK and Graz, Austria!
• FP7 EU-funded project starting September 2011!
• Interactive, dynamic personal journey advisor!
• Addresses complex, dynamic, multimodal transit network!
10:30
10:35
10:40
10:50
11:20
11:12
Best suggested route continuously updated based on changes in arrival departure times of buses and current position of subscriber
5
10
15
20
25−30
−20−10
010
2030
0
0.02
0.04
0.06
0.08
0.1
0.12
Delay in Minutes
Journey Pattern 046A0001; Bus Stop 2017; from 7h to 23h. weekdays
Hour of the Day
5
10
15
20
25−30
−20−10
010
2030
0
0.05
0.1
0.15
0.2
Delay in Minutes
Journey Pattern 046A0001; Bus Stop 6059; from 7h to 23h. weekdays
Hour of the Day
IBM Research and Development - Ireland
© 2011 IBM Corporation
Our Dublin Experience (2011)
• Complex system & analytics challenges • Data diversity, heterogeneity • Data accuracy, sparsity • Data volume
• Active relationship with DCC • Deployed in Dublin’s DoT
Routes & maps
Bus AVL (GPS)
Parking
capacity
Accessibility
SCATS Induction
loop
Timetables
CCTV
Car
Bike
1,000 buses 3,000 GPS / min
200 CCTV cameras
700 intersections 4,000 loop detectors 20,000 tuples / min
IBM Research and Development - Ireland
© 2011 IBM Corporation
Sensor data assimilation • Continuous assimilation of real-time traffic data
Understanding/Modeling human demand • Characterizing urban dynamics from digital traces
Operations & Planning • Leveraging mathematical programming for planning
in an uncertain world
Operations & Planning • Organising data and information to better engage
citizens, empower universities and enable businesses to help drive overall growth
Outline
Tran
spor
tatio
n W
ater
M
ulti-
dom
ain
© 2010 IBM Corporation
IBM Research and Development - Ireland
© 2011 IBM Corporation
Understanding urban dynamics from digital traces
Francesco Calabrese, PhD
Research Staff Member, Analytics & Optimization Smarter Cities Technology Centre IBM Research and Development - Ireland
IBM Research and Development - Ireland
© 2011 IBM Corporation
Pervasive Technologies Datasets as Digital Footprints
Understand how people use the city's infrastructure!
! Mobility (transportation mode) !
! Consumption (energy, water, waste)!
! Environmental impact (noise, pollution)!
!
Potentials!
! Improve city’s services!
! Optimize planning!
! Minimizing operational costs!
! Create feedback loops with citizens to reduce energy consumption and environmental impact!
IBM Research and Development - Ireland
© 2011 IBM Corporation
Understanding Urban Dynamics
• Research goals • Understanding human behavior in terms of mobility demand • Analyzing and predicting transportation needs in short & long terms
• Outcome • Design adaptive urban transportation systems • Support urban planning and design
• Examples of projects • How geography influences the way people interact • How travel demand changes over space and time • How social events impact mobility in the city
IBM Research and Development - Ireland
© 2011 IBM Corporation
Angle of Arrival (AOA)
Timing Advance (TA)
Received Signal Strength (RSS)
The image cannot be displayed. Your computer may not have enough memory to open the image, or the image may
Example of extracted trajectory over 1 week
!F. Calabrese, M. Colonna, P. Lovisolo, D. Parata, C. Ratti, Real-Time Urban Monitoring Using Cell Phones: a Case Study in Rome, IEEE Transactions on Intelligent Transportation Systems, 2011.!
!
Mobile phones to detect human mobility and interactions
IBM Research and Development - Ireland
© 2011 IBM Corporation
Findings • Spatial cohesiveness of regions ! State boundaries emerge in most of
the cases ! Metropolitan areas (e.g. NYC, LA)
define new regions ! Some states merge as level of
interaction is higher than expected
Applications ! Help regional and city provides to
better plan or adjust their operations ! Adjust service catchment areas
(e.g. hospital serviced neighbors) ! Plan new transit systems to help
connecting areas with low interaction
The Connected States of America. Can data help us think beyond state lines?, Time Magazine, 11 April 2011!
Regional partitioning based on level of interaction
IBM Research and Development - Ireland
© 2011 IBM Corporation
!F. Calabrese, G. Di Lorenzo, L. Liu, C. Ratti, “Estimating Origin-Destination flows using opportunistically collected mobile phone location data from one million users in Boston Metropolitan Area”, IEEE Pervasive Computing, 2011.!
!
!
Origin Destination matrices are used for transport planning!!!Estimated from census data or travel surveys!
• Very costly, so rarely done in developing countries, and quickly outdated !• Only commuting!!
!Developed a new method making use of mobile phone location data to estimate ODs!• All travels (not only commuting)!• Real time monitoring!
How travel demand changes over space and time
IBM Research and Development - Ireland
© 2011 IBM Corporation
Modeling and predicting non-routine additive origin-destination flows in the city !
!
!F. Calabrese, F. Pereira, G. Di Lorenzo, L. Liu, C. Ratti, “The geography of taste: analyzing cell-phone mobility and social events”, In International Conference on Pervasive Computing, 2010.!
!
Event duration! User stop!
Time!
Overlap time > 70%!
Estimated home location!
Attendance Inference!
How social events impact mobility in the city
IBM Research and Development - Ireland
© 2011 IBM Corporation
Detecting and predicting travel demand
Applications!
• Improving event planning & management!
• Predicting the effect of an event on the urban transportation!
• Adapting public transit (schedules and routes) to accommodate additional demand!
• Location based services!
• Recommending social events!
• Cold start problem!!
IBM Research and Development - Ireland
© 2011 IBM Corporation
Summary
• In order to make city’s services more efficient we need to understand how people use the city infrastructure!
• Pervasive technologies datasets allow to infer micro and macro behaviors of a population!
• Inferred demand patterns can be used to make services more adaptive and efficient!
IBM Research and Development - Ireland
© 2011 IBM Corporation
Sensor data assimilation • Continuous assimilation of real-time traffic data
Understanding/Modeling human demand • Characterizing urban dynamics from digital traces
Operations & Planning • Leveraging mathematical programming for planning
in an uncertain world
Operations & Planning • Organising data and information to better engage
citizens, empower universities and enable businesses to help drive overall growth
Outline
Tran
spor
tatio
n W
ater
M
ulti-
dom
ain
© 2010 IBM Corporation
IBM Research and Development - Ireland
© 2011 IBM Corporation
Leveraging mathematical programming for planning in an uncertain world Susara van den Heever, PhD
Research Staff Member, Analytics & Optimization Smarter Cities Technology Centre IBM Research and Development - Ireland
IBM Research and Development - Ireland
© 2011 IBM Corporation
• Design and planning of urban infrastructures!– Transportation – Water distribution and treatment – Energy
• “Standard” optimization approaches minimize costs while meeting demand!
• Additional environmental objectives!– Minimize carbon footprint!– Meet pollution reduction targets!
• Additional challenge – capturing uncertainty, such as:!– Population growth and urban dynamics!– Rainfall !– Renewable energy sources!– Energy costs!
Overview
IBM Research and Development - Ireland
© 2011 IBM Corporation
Design & long-term planning
Tactical planning
Operations planning
Time horizon
Real-time Hours Days Weeks Months Years
Dec
isio
n ag
greg
atio
n
Operations scheduling
Real-time control
Planning Levels
IBM Research and Development - Ireland
© 2011 IBM Corporation
Time horizon
Real-time Hours Days Weeks Months Years
Dec
isio
n ag
greg
atio
n
Design & longterm planning
Tactical planning
Operations planning
Operations scheduling
Real-time control
Plant & network design (e.g. valve placement), capacity expansion
Reservoir targets Production,
maintenance plans (e.g. leak detection)
Pump scheduling
Equipment set points
Examples of Decisions
IBM Research and Development - Ireland
© 2011 IBM Corporation
Time horizon
Real-time Hours Days Weeks Months Years
Dec
isio
n ag
greg
atio
n
Design & longterm planning
Tactical planning
Operations planning
Operations scheduling
Real-time control
Reservoir targets
Pump scheduling
Equipment set points
Population growth
Long-term demand patterns
Energy costs, demand
Rainfall, renewable energy sources
Production, maintenance plans (e.g. leak detection)
Plant & network design (e.g. valve placement), capacity expansion
Impact of Uncertainty
IBM Research and Development - Ireland
© 2011 IBM Corporation
Reservoir!
*Based on Inniscarra network!
Example: Water treatment infrastructure*!
Water source!
Pumphouse!
Treatment plant!
Reservoir!Reservoir!
Pumphouse!
Reservoir!
Reservoir!
Network of pumps, treatment plant, pipelines, and reservoirs!
IBM Research and Development - Ireland
© 2011 IBM Corporation
Inniscarra reservoir!
*Based on Inniscarra network!
Example: Water treatment infrastructure*!
Inniscarra dam!
Inniscarra pumphouse!
Inniscarra plant!
Curraleigh reservoir!
Chetwynd reservoir!
Carrshill pumphouse!
Carrshill reservoir!
Strawhall reservoir!
Network of pumps, treatment plant, pipelines, and reservoirs!
Long-term:!“What are the best investment
choices over the next two decades to optimize the network design?”!
!Mid-term:!
“What should the reservoir level targets be to best hedge against
uncertain demand?”!!
Short-term:!“How can we optimize our low-tariff
pumping?”!Current focus
IBM Research and Development - Ireland
© 2011 IBM Corporation
Summary
• Design and planning of urban infrastructures under uncertainty !
• Ignoring uncertainty could lead to costly decisions!
• Traditional approaches to dealing with uncertainty!• Often require an expert to implement!• Scenario creation and analysis not obvious!
• Research towards generalized approach to aid!• Scenario creation!• Uncertainty and sensitivity analysis!
IBM Research and Development - Ireland
© 2011 IBM Corporation
Sensor data assimilation • Continuous assimilation of real-time traffic data
Understanding/Modeling human demand • Characterizing urban dynamics from digital traces
Operations & Planning • Leveraging mathematical programming for planning
in an uncertain world
Operations & Planning • Organising data and information to better engage
citizens, empower universities and enable businesses to help drive overall growth
Outline
Tran
spor
tatio
n W
ater
© 2010 IBM Corporation
IBM Research and Development - Ireland
© 2011 IBM Corporation
Dublinked and Open City Data
Pol Mac Aonghusa
Smarter Cities Technology Centre IBM Research and Development - Ireland
IBM Research and Development - Ireland
© 2011 IBM Corporation
Opening the Data locked in our Cities is no longer an option Open access to data and services coupled with ad hoc social innovation are only the beginning
2009, Data.gov.uk
Data.gov (US)
1993, SEC Online
2004, USG announces e-
Gov 2.0
Content Factual &
Static
>350 ‘Open City Data
Catalogs’ (data.gov)
2011+, Gov 3.0 City as an Enterprise ....
Activity
Time 2010,
Amazon, Google & MSoft
Content
Structure
Innovation
Aggregation & Efforts to
create linkage based on
Semantic Web
>25 Billion Triples on Linked Data Cloud
Innovation based on
Collaboration & Social
Innovation
35 Cities in Open Data Hackday, 12/2010
Ecosystem increasingly focused on long-term
sustainability
Publicdata.eu – LOD2 for Citizen study due 2014
IBM Research and Development - Ireland
© 2011 IBM Corporation
Open Innovation Portal (OIP) ! publish, organise, discover & consume the information resources of a City
IBM Connections Content Sharing & Collaboration Services
IBM Intelligent Operations Center (IOC) Integrated data visualization, real-time collaboration, deep analytics.
Dublin City
Enterprise Applications
IBM Enterprise Cloud Scalable compute, storage & network infrastructure
City 2 ..N
Enterprise Citizen
Open REST Web Services API
Contents & Catalog
Privacy & Security Knowledge Representation & Reasoning
Administration Monitor & Events
Semantic Query & Analytics
Open Innovation Portal
IBM Products & Services
Robust models to organize and represent resources and their context
Scalable privacy and security of resources Automated assimilation and sharing of resources
Composable resources for development, mash-up & visualization
Research Challenges include ..
IBM Research
Partners & People
Key
Efficient knowledge representation for continuous machine reasoning and diagnosis
IBM Research and Development - Ireland
© 2011 IBM Corporation
Dublinked
http://www-958.ibm.com/software/data/cognos/manyeyes/visualizations/word-tree-of-dublinked-launch-open
Creating meaningful and accurate meta-data is still a tedious and error prone task. Enhanced support a priority for version 2. Have provided a review of site usability & function by student as input. Will also provide analysis of data sets from researchers.
Excellent download statistics The highest demand data sets are for water telemetry reading (Water, Traffic, Planning)
IBM Research and Development - Ireland
© 2011 IBM Corporation
How can we help cities achieve their aspirations?
" Sensor data assimilation! From noisy data! ! to uncertain information!
!
!" Modeling human demand!
! !Capturing uncertainty!
!!" Operations & Planning!
! !Factoring in uncertainty!
IBM Research and Development - Ireland
© 2011 IBM Corporation
Working harder is not sustainable
Cities require innovative approaches
IBM Research and Development - Ireland
© 2011 IBM Corporation
Publications • The Connected States of America. Can data help us think beyond state lines?, Time Magazine, 11 April 2011!
• F Calabrese, D Dahlem, A Gerber, D Paul, X Chen, J Rowland, C Rath, C Ratti, The Connected States of America: Quantifying Social Radii of Influence, International Conference on Social Computing, 2011.!
• F. Calabrese, G. Di Lorenzo, L. Liu, C. Ratti, “Estimating Origin-Destination flows using opportunistically collected mobile phone location data from one million users in Boston Metropolitan Area”, IEEE Pervasive Computing, 2011.!
• G. Di Lorenzo, F. Calabrese, "Identifying Human Spatio-Temporal Activity Patterns from Mobile-Phone Traces”, IEEE ITSC, 2011!
• F. Calabrese, Z. Smoreda, V. Blondel, C. Ratti, “The Interplay Between Telecommunications and Face-to-Face Interactions-An Initial Study Using Mobile Phone Data”, PLoS ONE, 2011.!
• D. Quercia, G. Di Lorenzo, F. Calabrese, C. Ratti, “Mobile Phones and Outdoor Advertising: Measurable Advertising”, IEEE Pervasive Computing, 2011.!
• F. Calabrese, M. Colonna, P. Lovisolo, D. Parata, C. Ratti, “Real-Time Urban Monitoring Using Cell Phones: a Case Study in Rome”, IEEE Transactions on Intelligent Transportation Systems, 2011.!
• L. Gasparini, E. Bouillet, F. Calabrese, O. Verscheure, Brendan O’Brien, Maggie O’Donnell, "System and Analytics for Continuously Assessing Transport Systems from Sparse and Noisy Observations: Case Study in Dublin”, IEEE ITSC, 2011!
• A. Baptista, E. Bouillet, F. Calabrese, O. Verscheure, "Towards Building an Uncertainty-aware Multi-Modal Journey Planner”, IEEE ITSC, 2011!
• T. Tchrakian, O. Verscheure, "A Lagrangian State-Space Representation of a Macroscopic Traffic Flow Model”, IEEE ITSC, 2011!