UrbanFlood

UrbanFloodThe Common Information Space: A Framework for Early Warning Systems

Bartosz Baliś, Tomasz Bartyński, Marian Bubak,Grzegorz Dyk, Tomasz Gubała, Marek Kasztelnik

Motivation: Early Warning Systems against natural disasters

Complex distributed systemsMission and time-criticalInvolve resource-intensive computations

and data analysis Require compositions of resources into

complex scenarios◦ Sensors monitoring objects and natural

phenomena◦ Apps for data analysis & simulation◦ ICT infrastructure (hardware + software)

Example: Urban area flood simulation

GoalsDevelop a framework facilitating

development, deployment and execution of EWSs: the Common Information Space

EWS development◦ EWS reference model◦ EWS development framework

EWS deployment◦ EWS blueprints◦ EWS-factory-as-a-service

EWS execution◦ CIS runtime services for resource

allocation, self-monitoring, self-healing, mission-critical operation, and urgent computing

5Cracow Grid Workshop 2012 UrbanFlood

CIS Architecture and EWS reference model

6Cracow Grid Workshop 2012 UrbanFlood

CIS as a system factorySystem factory

ServiceService factory

Service factoryService

configurations

System instance

invoke

configurations

Virtual appliance store

customize

Systemblueprint

7Cracow Grid Workshop 2012 UrbanFlood

Case study: Flood Early Warning SystemProtection of urban areas against

floods due to dike failuresReal-time monitoring of embankments

using wireless sensorsA casade of models for:

◦ Anomaly detection◦ Risk assessment◦ Impact prediction

Dike anomaly detectionAnomaly detection using

neural cloud classification

Dike breach risk computationDistribution of probability of

dike breach is calculatedDepending on the current

water level

Flood simulation

Life Safety ModelLoss of life estimate

due to flood

Initial state of the world

Post-event summary (red color = deceased)

Virtual DikeComputer model of a dikeSimulation of dike

behaviourUseful for „what-if”

experiments Also for testing the real

EWS („emergency drill”)

Flood Early Warning System workflow

Alternate path AnySenseService

AI Anomaly Detection

Abnormal?Reliability Analysis

Flood Simulation

Life Safety Simulation

High impact?

Data flowControl

flow

action

High risk?

Virtual Dike

SensorCabinet

Dike

14Cracow Grid Workshop 2012 UrbanFlood

Flood EWS: implementation

15Cracow Grid Workshop 2012 UrbanFlood

Example: Flood Simulation Part

16Cracow Grid Workshop 2012 UrbanFlood

ConclusionCIS contributes conceptually and technologically in the following areas:CIS as a factory for Early Warning

Systems◦ Proven by the implementation of the Flood

EWSCIS as a geo-ICT technology for

spatial data processing services◦ CIS adopts guidelines of the INSPIRE

directive and leverages OGC standards for service interfaces

CIS as a runtime infrastructure for resource-intensive mission-critical systems

17Cracow Grid Workshop 2012 UrbanFlood

urbanflood.cyfronet.pl dice.cyfronet.pl/cis