PARALLEL AND DISTRIBUTED PLATFORM FOR PLUG-AND-PLAY AGENT-BASED SIMULATIONS. Wentong CAI

Size: px
Start display at page:

Download "PARALLEL AND DISTRIBUTED PLATFORM FOR PLUG-AND-PLAY AGENT-BASED SIMULATIONS. Wentong CAI"

Transcription

1 PARALLEL AND DISTRIBUTED PLATFORM FOR PLUG-AND-PLAY AGENT-BASED SIMULATIONS Wentong CAI Parallel & Distributed Computing Centre School of Computer Engineering Nanyang Technological University Singapore

2 Outline Agent-based Modelling and Simulation (ABMS) Computer Simulation Complex Adaptive System & Agent-based Modelling and Simulation Our Work on Crowd Simulation & Traffic Simulation Calibration of ABMS Motivation Evolution-based Approach Cloud-based Execution Speed-up and Scale-up ABMS Top-down vs. bottom-up decomposition Cluster-based partitioning (crowd simulation) Adaptive graph partitioning (traffic simulation) Federated simulation Challenges 2

3 Computer Simulation Simulation imitates the operations (behavior) of a real-world system or process over time, usually via computer programs, to evaluate and improve system performance. Simulation involves the generation of an artificial history of a system and the observation of that artificial history to draw inferences concerning the operating properties of the real system. analyze systems before they are built analyze operational systems create virtual environments for training, entertainment 3

4 Complex Adaptive Systems Complex Adaptive Systems are characterized by apparently complex behaviours that emerge as a result of often nonlinear spatial-temporal interactions among a large number of component systems at different levels of organization. decentralized decision making local-global interaction, selforganization, emergence heterogeneity 4

5 Agent-based Modelling & Simulation An Intelligent Agent is a computer system capable of flexible autonomous actions in some environment [Woodbridge]. reactive: deal with changes pro-active: goal directed behavior social: interact with other agents An Agent-based Model is an abstraction of a real or physical system described in terms of multiple intelligent agents. 5

6 Key Elements of ABM Autonomous decision-making How they can make decision vary Local interactions Behaviour Modelling No central authority exists Neighbourhoods (or environments) ABMS consist of a space, framework or environment in which interactions take place and a number of agents whose behaviour is defined in this space is defined by a basic set of rules and by characteristic parameters. [Reynolds] 6

7 ABMS Toolkits NetLogo Toolkits that support implementation and execution of agent-based models tools for environment modelling (e.g., spatial indexing) simulation engine (e.g., scheduler) supporting libraries (e.g., random number generator) MASON RePast 7

8 Crowd Modelling and Simulation Usefulness: planning, training, and operational decision making Importance: riot control, disaster management, emergency evacuation, and rescue operations 8

9 Navigation & Path Planning 9

10 Goal Oriented Agents 10

11 Large-scale Nanoscopic Traffic Simulation TUM CREATE Centre for Electromobility, Singapore 12

12 Outline Agent-based Modelling and Simulation (ABMS) Computer Simulation Complex Adaptive System & Agent-based Modelling and Simulation Our Work on Crowd Simulation & Traffic Simulation Calibration of ABMS Motivation Evolution-based Approach Cloud-based Execution Speed-up and Scale-up ABMS Top-down vs. bottom-up decomposition Cluster-based partitioning (crowd simulation) Adaptive graph partitioning (traffic simulation) Federated simulation Challenges 13

13 Motivation & Objective Parameter settings are very important for crowd simulation e.g., social force model Given a desired crowd scenario, finding the proper settings to reproduce the scenario is difficult and tedious Large search space Noise The objective of the study is to develop an evolutionary algorithm to automate the proper parameter configuration process Challenge similarity measure 14

14 Density-based Matching Scheme for Fitness Evaluation Z Axis * Z Axis Z Axis X Axis Y Axis X Axis Y Axis X Axis Y Axis weight matrix Reproduced behavior desired behavior T grid_ num 0 1 i i i i f w 15

15 Evolving Model Parameters initial simulation models simulation models Core Engine Module model execution Evolution Computing Module evaluate and generate new simulation models Evolve simulation model parameters to match desired crowd scenario multiple runs for each multiple simulation runs for model each simulation model 16

16 Cloud-based Execution initial simulation models Core Engine Module model execution multiple runs for each simulation model simulation models IaaS/PaaS multiple runs for each simulation model Evolution Computing Module evaluate and generate new simulation models multiple runs for each simulation model 18

17 Outline Agent-based Modelling and Simulation (ABMS) Computer Simulation Complex Adaptive System & Agent-based Modelling and Simulation Our Work on Crowd Simulation & Traffic Simulation Calibration of ABMS Motivation Evolution-based Approach Cloud-based Execution Speed-up and Scale-up ABMS Top-down vs. bottom-up decomposition Cluster-based partitioning (crowd simulation) Adaptive graph partitioning (traffic simulation) Federated simulation Challenges 19

18 Top-down vs. Bottom-up middleware to support federated simulation 20

19 Cluster Based Partitioning Partitioning is not a unique problem to crowds or agent simulation. Load balancing (distributing computational load among computers) is a long studied problem in many research fields. The work we do is obviously also applicable to Distributed Virtual Environments and MMORPGs. We replicate the virtual environment on each CPU and then divide the agents among them. Our approach is to use clustering techniques from data mining in order to identify groups of agents and then assign these groups to compute nodes. Use a k-means approach to group agents close together Grid-based clustering 21

20 Cluster Based Partitioning: K-Means K-means clusters objects into k clusters on some attributes which form a vector space. In our case, the agents positions are chosen as the attribute. Agents which are close to one another need to know about one another so should be in same cluster. Floyd s algorithm is used to minimize J J j 1 i 1 p i c j where: c j is the center of each cluster and p i is the position of an agent Each cluster is mapped to a compute node. Agents will be transferred between nodes if they move to another cluster. K-means executes at predefined interval periodically. k n 2 22

21 Cluster Based Partitioning: K-Means Random_normal: agents randomly walk in the square Random_emergency: agents evacuate via the exit individually Group_normal: agents are formed into groups and walk randomly in the square Group_emergency: agents are formed into groups and evacuate via exit Static Fast Adaptive Load Balancing K-means 23

22 Cluster Based Partitioning: K-Means K-means works well for some cases To maintain the clusters one must migrate agents between machines. This involves sending the agent s state across the network So in some cases the time spent moving agents between machines will negate any gain achieved from reducing communication! Consider the crossing example Can maintain clustering and migrate agents. Perhaps a better option, just ignore ideal clustering while the two groups cross. Pay communication expense during crossing. In addition to location, use agents goals as another metric of similarity -> Grid-based Partitioning 24

23 Grid Based We define a uniform grid mesh over the environment space, each area of the grid is a cell. Each cell contains some number of agents. We can control execution time of algorithm with grid resolution. A set of statistics is collected for each cell For case study: Average Goal, Goal Variance The clustering algorithm then groups cells into clusters based on the difference of these statistics. Note that cells with high goal variance (many agents with different goals) are never clustered. These may be added to clusters later. Bounding box (shared among nodes along with statistics of clusters) is defined around cluster for determining when communication is necessary. Agents outside cluster are simulated as individuals on a specially dedicated compute node. 25

24 Grid Based We now have some collection of clusters each of which contains agents which are nearby each other and have similar statistics (goal). Next, we evenly assign clusters and individuals to partitions. The number of clusters C is determined by the algorithm. The number of partitions P is defined by number of machines we have. Clusters may need to be split if necessary. We actually have a parallel implementation of this algorithm. Clusters are formed (centrally) once at startup. Each partition then manages its own clusters and collaboratively performs the clustering algorithm with other partitions. Load-balancing is performed by splitting a large cluster into smaller ones transferring clusters between partitions. 26

25 Performance Sparse Groups Close Groups 27

26 Performance 28

27 Partitioning of Traffic Simulation P3 P2 P4 P1 29

28 Federated Simulation CO2 Emission Simulation Weather Simulation data logging & Control HLA/RTI Traffic Simulation Crowd Simulation Epidemic Simulation Simulation of Urban Dynamic 30

29 Service-oriented HLA/RTI Dynamic deployment of service components & decentralized services -> flexibility and scalability Client Federate Client Federate Shared services and communication overheads -> adaptive algorithms Client Federate 31

30 Vision Plug & Play Simulation RTI RTI RTI federate Model Factory federate Model Factory RTI RTI Discovery of Models Discovery of Resources Management of Simulation Execution 32

31 Outline Agent-based Modelling and Simulation (ABMS) Computer Simulation Complex Adaptive System & Agent-based Modelling and Simulation Our Work on Crowd Simulation & Traffic Simulation Calibration of ABMS Motivation Evolution-based Approach Cloud-based Execution Speed-up and Scale-up ABMS Top-down vs. bottom-up decomposition Cluster-based partitioning (crowd simulation) Adaptive graph partitioning (traffic simulation) Federated simulation Challenges 33

32 Challenges Verification & Validation Lack of data, predict past vs. predict the future Relying on SMEs (past experience)? Real-time Model Adaptation How to make sense from data to adapt agent behaviour? How to do this in real-time? Interoperability and composability Different types of simulations Different level of abstraction Scalability Ways to support execution of large models How to meet real-time requirement when the model is scaled up? 34

33 Questions? 35

Browsing the World in the Sensors Continuum. Franco Zambonelli. Motivations. all our everyday objects all our everyday environments

Browsing the World in the Sensors Continuum. Franco Zambonelli. Motivations. all our everyday objects all our everyday environments Browsing the World in the Sensors Continuum Agents and Franco Zambonelli Agents and Motivations Agents and n Computer-based systems and sensors will be soon embedded in everywhere all our everyday objects

More information

A comparative study of k-nearest neighbour techniques in crowd simulation

A comparative study of k-nearest neighbour techniques in crowd simulation A comparative study of k-nearest neighbour techniques in crowd simulation Jordi Vermeulen Arne Hillebrand Roland Geraerts Department of Information and Computing Sciences Utrecht University, The Netherlands

More information

A Capacity Planning Methodology for Distributed E-Commerce Applications

A Capacity Planning Methodology for Distributed E-Commerce Applications A Capacity Planning Methodology for Distributed E-Commerce Applications I. Introduction Most of today s e-commerce environments are based on distributed, multi-tiered, component-based architectures. The

More information

IOS: A Middleware for Decentralized Distributed Computing

IOS: A Middleware for Decentralized Distributed Computing IOS: A Middleware for Decentralized Distributed Computing Boleslaw Szymanski Kaoutar El Maghraoui, Carlos Varela Department of Computer Science Rensselaer Polytechnic Institute http://www.cs.rpi.edu/wwc

More information

Autonomic Computing. Pablo Chacin

Autonomic Computing. Pablo Chacin Autonomic Computing Pablo Chacin Acknowledgements Some Slides taken from Manish Parashar and Omer Rana presentations Agenda Fundamentals Definitions Objectives Alternative approaches Examples Research

More information

Opportunistic Application Flows in Sensor-based Pervasive Environments

Opportunistic Application Flows in Sensor-based Pervasive Environments Opportunistic Application Flows in Sensor-based Pervasive Environments Nanyan Jiang, Cristina Schmidt, Vincent Matossian, and Manish Parashar ICPS 2004 1 Outline Introduction to pervasive sensor-based

More information

ADAPTIVE AND DYNAMIC LOAD BALANCING METHODOLOGIES FOR DISTRIBUTED ENVIRONMENT

ADAPTIVE AND DYNAMIC LOAD BALANCING METHODOLOGIES FOR DISTRIBUTED ENVIRONMENT ADAPTIVE AND DYNAMIC LOAD BALANCING METHODOLOGIES FOR DISTRIBUTED ENVIRONMENT PhD Summary DOCTORATE OF PHILOSOPHY IN COMPUTER SCIENCE & ENGINEERING By Sandip Kumar Goyal (09-PhD-052) Under the Supervision

More information

Distributed Information Processing

Distributed Information Processing Distributed Information Processing 1 st Lecture Eom, Hyeonsang ( 엄현상 ) Department of Computer Science & Engineering Seoul National University Copyrights 2017 Eom, Hyeonsang All Rights Reserved Outline

More information

Outline of Presentation. Introduction to Overwatch Geospatial Software Feature Analyst and LIDAR Analyst Software

Outline of Presentation. Introduction to Overwatch Geospatial Software Feature Analyst and LIDAR Analyst Software Outline of Presentation Automated Feature Extraction from Terrestrial and Airborne LIDAR Presented By: Stuart Blundell Overwatch Geospatial - VLS Ops Co-Author: David W. Opitz Overwatch Geospatial - VLS

More information

Mobile robots and appliances to support the elderly people

Mobile robots and appliances to support the elderly people Microsoft Research Embedded Systems Invitation for Proposal Mobile robots and appliances to support the elderly people Luca Iocchi, Daniele Nardi Dipartimento di Informatica e Sistemistica Università di

More information

Evolutionary design for the behaviour of cellular automaton-based complex systems

Evolutionary design for the behaviour of cellular automaton-based complex systems Evolutionary design for the behaviour of cellular automaton-based complex systems School of Computer Science & IT University of Nottingham Adaptive Computing in Design and Manufacture Bristol Motivation

More information

White Paper: Next generation disaster data infrastructure CODATA LODGD Task Group 2017

White Paper: Next generation disaster data infrastructure CODATA LODGD Task Group 2017 White Paper: Next generation disaster data infrastructure CODATA LODGD Task Group 2017 Call for Authors This call for authors seeks contributions from academics and scientists who are in the fields of

More information

* Inter-Cloud Research: Vision

* Inter-Cloud Research: Vision * Inter-Cloud Research: Vision for 2020 Ana Juan Ferrer, ATOS & Cluster Chair Vendor lock-in for existing adopters Issues: Lack of interoperability, regulatory context, SLAs. Inter-Cloud: Hardly automated,

More information

Proceedings of the 2012 Winter Simulation Conference C. Laroque, J. Himmelspach, R. Pasupathy, O. Rose, and A. M. Uhrmacher, eds.

Proceedings of the 2012 Winter Simulation Conference C. Laroque, J. Himmelspach, R. Pasupathy, O. Rose, and A. M. Uhrmacher, eds. Proceedings of the 2012 Winter Simulation Conference C. Laroque, J. Himmelspach, R. Pasupathy, O. Rose, and A. M. Uhrmacher, eds. GRID-BASED PARTITIONING FOR LARGE-SCALE DISTRIBUTED AGENT-BASED CROWD SIMULATION

More information

Kyrre Glette INF3490 Evolvable Hardware Cartesian Genetic Programming

Kyrre Glette INF3490 Evolvable Hardware Cartesian Genetic Programming Kyrre Glette kyrrehg@ifi INF3490 Evolvable Hardware Cartesian Genetic Programming Overview Introduction to Evolvable Hardware (EHW) Cartesian Genetic Programming Applications of EHW 3 Evolvable Hardware

More information

Spatial Outlier Detection

Spatial Outlier Detection Spatial Outlier Detection Chang-Tien Lu Department of Computer Science Northern Virginia Center Virginia Tech Joint work with Dechang Chen, Yufeng Kou, Jiang Zhao 1 Spatial Outlier A spatial data point

More information

SCALING A DISTRIBUTED SPATIAL CACHE OVERLAY. Alexander Gessler Simon Hanna Ashley Marie Smith

SCALING A DISTRIBUTED SPATIAL CACHE OVERLAY. Alexander Gessler Simon Hanna Ashley Marie Smith SCALING A DISTRIBUTED SPATIAL CACHE OVERLAY Alexander Gessler Simon Hanna Ashley Marie Smith MOTIVATION Location-based services utilize time and geographic behavior of user geotagging photos recommendations

More information

Data Mining: Data. Lecture Notes for Chapter 2. Introduction to Data Mining

Data Mining: Data. Lecture Notes for Chapter 2. Introduction to Data Mining Data Mining: Data Lecture Notes for Chapter 2 Introduction to Data Mining by Tan, Steinbach, Kumar Data Preprocessing Aggregation Sampling Dimensionality Reduction Feature subset selection Feature creation

More information

Dynamic Adaptive Disaster Simulation: A Predictive Model of Emergency Behavior Using Cell Phone and GIS Data 1

Dynamic Adaptive Disaster Simulation: A Predictive Model of Emergency Behavior Using Cell Phone and GIS Data 1 Dynamic Adaptive Disaster Simulation: A Predictive Model of Emergency Behavior Using Cell Phone and GIS Data 1, Zhi Zhai, Greg Madey Dept. of Computer Science and Engineering University of Notre Dame Notre

More information

Simulation of Scale-Free Networks

Simulation of Scale-Free Networks Simulation of Scale-Free Networks Gabriele D Angelo http://www.cs.unibo.it/gdangelo/ it/ / joint work with: Stefano Ferretti Department of Computer Science University of Bologna SIMUTOOLS

More information

Sampling Urban Mobility through On-line Repositories of GPS Tracks

Sampling Urban Mobility through On-line Repositories of GPS Tracks Sampling Urban Mobility through On-line Repositories of GPS Tracks Michał PIóRKOWSKI School of Computer and Communication Sciences EPFL IC ISC LCA4 Motivation Mobility mining for: Mobility modeling Communication

More information

Mobile Wireless Sensor Network enables convergence of ubiquitous sensor services

Mobile Wireless Sensor Network enables convergence of ubiquitous sensor services 1 2005 Nokia V1-Filename.ppt / yyyy-mm-dd / Initials Mobile Wireless Sensor Network enables convergence of ubiquitous sensor services Dr. Jian Ma, Principal Scientist Nokia Research Center, Beijing 2 2005

More information

Energy efficient mapping of virtual machines

Energy efficient mapping of virtual machines GreenDays@Lille Energy efficient mapping of virtual machines Violaine Villebonnet Thursday 28th November 2013 Supervisor : Georges DA COSTA 2 Current approaches for energy savings in cloud Several actions

More information

SDN SEMINAR 2017 ARCHITECTING A CONTROL PLANE

SDN SEMINAR 2017 ARCHITECTING A CONTROL PLANE SDN SEMINAR 2017 ARCHITECTING A CONTROL PLANE NETWORKS ` 2 COMPUTER NETWORKS 3 COMPUTER NETWORKS EVOLUTION Applications evolve become heterogeneous increase in traffic volume change dynamically traffic

More information

Distributed simulation of situated multi-agent systems

Distributed simulation of situated multi-agent systems Distributed simulation of situated multi-agent systems Franco Cicirelli, Andrea Giordano, Libero Nigro Laboratorio di Ingegneria del Software http://www.lis.deis.unical.it Dipartimento di Elettronica Informatica

More information

Algorithm Engineering with PRAM Algorithms

Algorithm Engineering with PRAM Algorithms Algorithm Engineering with PRAM Algorithms Bernard M.E. Moret moret@cs.unm.edu Department of Computer Science University of New Mexico Albuquerque, NM 87131 Rome School on Alg. Eng. p.1/29 Measuring and

More information

Oracle Big Data. A NA LYT ICS A ND MA NAG E MENT.

Oracle Big Data. A NA LYT ICS A ND MA NAG E MENT. Oracle Big Data. A NALYTICS A ND MANAG E MENT. Oracle Big Data: Redundância. Compatível com ecossistema Hadoop, HIVE, HBASE, SPARK. Integração com Cloudera Manager. Possibilidade de Utilização da Linguagem

More information

Parallel Algorithm Design. Parallel Algorithm Design p. 1

Parallel Algorithm Design. Parallel Algorithm Design p. 1 Parallel Algorithm Design Parallel Algorithm Design p. 1 Overview Chapter 3 from Michael J. Quinn, Parallel Programming in C with MPI and OpenMP Another resource: http://www.mcs.anl.gov/ itf/dbpp/text/node14.html

More information

Self-formation, Development and Reproduction of the Artificial System

Self-formation, Development and Reproduction of the Artificial System Solid State Phenomena Vols. 97-98 (4) pp 77-84 (4) Trans Tech Publications, Switzerland Journal doi:.48/www.scientific.net/ssp.97-98.77 Citation (to be inserted by the publisher) Copyright by Trans Tech

More information

An Introduction to Complex Systems Science

An Introduction to Complex Systems Science DEIS, Campus of Cesena Alma Mater Studiorum Università di Bologna andrea.roli@unibo.it Disclaimer The field of Complex systems science is wide and it involves numerous themes and disciplines. This talk

More information

Networked CPS: Some Fundamental Challenges

Networked CPS: Some Fundamental Challenges Networked CPS: Some Fundamental Challenges John S. Baras Institute for Systems Research Department of Electrical and Computer Engineering Fischell Department of Bioengineering Department of Mechanical

More information

Collaborative Networks of Image Sensors

Collaborative Networks of Image Sensors Collaborative Networks of Image Sensors Abbas El Gamal, EE Leonidas Guibas, CS Balaji Prabhakar, EE&CS Ali Ozer Ercan. EE Jaewon Shin, EE Danny Yang, CS Wireless Sensor Networks small Distributed systems

More information

GPU ACCELERATED SELF-JOIN FOR THE DISTANCE SIMILARITY METRIC

GPU ACCELERATED SELF-JOIN FOR THE DISTANCE SIMILARITY METRIC GPU ACCELERATED SELF-JOIN FOR THE DISTANCE SIMILARITY METRIC MIKE GOWANLOCK NORTHERN ARIZONA UNIVERSITY SCHOOL OF INFORMATICS, COMPUTING & CYBER SYSTEMS BEN KARSIN UNIVERSITY OF HAWAII AT MANOA DEPARTMENT

More information

Distributed Geometric Data Structures. Philip Levis Stanford Platform Lab Review Feb 9, 2017

Distributed Geometric Data Structures. Philip Levis Stanford Platform Lab Review Feb 9, 2017 Distributed Geometric Data Structures Philip Levis Stanford Platform Lab Review Feb 9, 2017 Big Control The Physical World Big control applications collect data on, and take action in, the physical world

More information

Pro2SQL. OpenEdge Replication. for Data Reporting. for Disaster Recovery. March 2017 Greg White Sr. Progress Consultant Progress

Pro2SQL. OpenEdge Replication. for Data Reporting. for Disaster Recovery. March 2017 Greg White Sr. Progress Consultant Progress Pro2SQL for Data Reporting OpenEdge Replication for Disaster Recovery March 2017 Greg White Sr. Progress Consultant Progress 1 Introduction Greg White Sr. Progress Consultant (Database and Pro2) 2 Replication

More information

Javaentwicklung in der Oracle Cloud

Javaentwicklung in der Oracle Cloud Javaentwicklung in der Oracle Cloud Sören Halter Principal Sales Consultant 2016-11-17 Safe Harbor Statement The following is intended to outline our general product direction. It is intended for information

More information

Model-based Real-Time Estimation of Building Occupancy During Emergency Egress

Model-based Real-Time Estimation of Building Occupancy During Emergency Egress Model-based Real-Time Estimation of Building Occupancy During Emergency Egress Robert Tomastik 1, Satish Narayanan 2, Andrzej Banaszuk 3, and Sean Meyn 4 1 Pratt & Whitney 400 Main St., East Hartford,

More information

TrajStore: an Adaptive Storage System for Very Large Trajectory Data Sets

TrajStore: an Adaptive Storage System for Very Large Trajectory Data Sets TrajStore: an Adaptive Storage System for Very Large Trajectory Data Sets Philippe Cudré-Mauroux Eugene Wu Samuel Madden Computer Science and Artificial Intelligence Laboratory Massachusetts Institute

More information

Scaling the LTE Control-Plane for Future Mobile Access

Scaling the LTE Control-Plane for Future Mobile Access Scaling the LTE Control-Plane for Future Mobile Access Speaker: Rajesh Mahindra Mobile Communications & Networking NEC Labs America Other Authors: Arijit Banerjee, Utah University Karthik Sundaresan, NEC

More information

Mir Abolfazl Mostafavi Centre for research in geomatics, Laval University Québec, Canada

Mir Abolfazl Mostafavi Centre for research in geomatics, Laval University Québec, Canada Mir Abolfazl Mostafavi Centre for research in geomatics, Laval University Québec, Canada Mohamed Bakillah and Steve H.L. Liang Department of Geomatics Engineering University of Calgary, Alberta, Canada

More information

Announcements. me your survey: See the Announcements page. Today. Reading. Take a break around 10:15am. Ack: Some figures are from Coulouris

Announcements.  me your survey: See the Announcements page. Today. Reading. Take a break around 10:15am. Ack: Some figures are from Coulouris Announcements Email me your survey: See the Announcements page Today Conceptual overview of distributed systems System models Reading Today: Chapter 2 of Coulouris Next topic: client-side processing (HTML,

More information

An Introduction to Agent Based Modeling with Repast Michael North

An Introduction to Agent Based Modeling with Repast Michael North An Introduction to Agent Based Modeling with Repast Michael North north@anl.gov www.cas.anl.gov Repast is an Agent-Based Modeling and Simulation (ABMS) Toolkit with a Focus on Social Simulation Our goal

More information

Chapter Outline. Chapter 2 Distributed Information Systems Architecture. Distributed transactions (quick refresh) Layers of an information system

Chapter Outline. Chapter 2 Distributed Information Systems Architecture. Distributed transactions (quick refresh) Layers of an information system Prof. Dr.-Ing. Stefan Deßloch AG Heterogene Informationssysteme Geb. 36, Raum 329 Tel. 0631/205 3275 dessloch@informatik.uni-kl.de Chapter 2 Distributed Information Systems Architecture Chapter Outline

More information

Motivation and goal Design concepts and service model Architecture and implementation Performance, and so on...

Motivation and goal Design concepts and service model Architecture and implementation Performance, and so on... Motivation and goal Design concepts and service model Architecture and implementation Performance, and so on... Autonomous applications have a demand for grasping the state of hosts and networks for: sustaining

More information

Alma Mater Studiorum University of Bologna CdS Laurea Magistrale (MSc) in Computer Science Engineering

Alma Mater Studiorum University of Bologna CdS Laurea Magistrale (MSc) in Computer Science Engineering Mobile Systems M Alma Mater Studiorum University of Bologna CdS Laurea Magistrale (MSc) in Computer Science Engineering Mobile Systems M course (8 ECTS) II Term Academic Year 2016/2017 08 Application Domains

More information

Grid Computing Systems: A Survey and Taxonomy

Grid Computing Systems: A Survey and Taxonomy Grid Computing Systems: A Survey and Taxonomy Material for this lecture from: A Survey and Taxonomy of Resource Management Systems for Grid Computing Systems, K. Krauter, R. Buyya, M. Maheswaran, CS Technical

More information

Spatial Scattering for Load Balancing in Conservatively Synchronized Parallel Discrete-Event Simulations

Spatial Scattering for Load Balancing in Conservatively Synchronized Parallel Discrete-Event Simulations Spatial ing for Load Balancing in Conservatively Synchronized Parallel Discrete-Event Simulations Abstract We re-examine the problem of load balancing in conservatively synchronized parallel, discrete-event

More information

Agent based Cellular Automata Simulation

Agent based Cellular Automata Simulation Agent based Cellular Automata Simulation P. Fornacciari, G. Lombardo, M. Mordonini, A. Poggi and M. Tomaiuolo Dipartimento di Ingegneria e Architettura Università degli Studi di Parma Parma, Italy {paolo.fornacciari,gianfranco.lombardo,monica.mordonini,agostino.poggi,michele.tomaiuolo}@unipr.it

More information

A TIMING AND SCALABILITY ANALYSIS OF THE PARALLEL PERFORMANCE OF CMAQ v4.5 ON A BEOWULF LINUX CLUSTER

A TIMING AND SCALABILITY ANALYSIS OF THE PARALLEL PERFORMANCE OF CMAQ v4.5 ON A BEOWULF LINUX CLUSTER A TIMING AND SCALABILITY ANALYSIS OF THE PARALLEL PERFORMANCE OF CMAQ v4.5 ON A BEOWULF LINUX CLUSTER Shaheen R. Tonse* Lawrence Berkeley National Lab., Berkeley, CA, USA 1. INTRODUCTION The goal of this

More information

TrafficDB: HERE s High Performance Shared-Memory Data Store Ricardo Fernandes, Piotr Zaczkowski, Bernd Göttler, Conor Ettinoffe, and Anis Moussa

TrafficDB: HERE s High Performance Shared-Memory Data Store Ricardo Fernandes, Piotr Zaczkowski, Bernd Göttler, Conor Ettinoffe, and Anis Moussa TrafficDB: HERE s High Performance Shared-Memory Data Store Ricardo Fernandes, Piotr Zaczkowski, Bernd Göttler, Conor Ettinoffe, and Anis Moussa EPL646: Advanced Topics in Databases Christos Hadjistyllis

More information

Mobility Models. Larissa Marinho Eglem de Oliveira. May 26th CMPE 257 Wireless Networks. (UCSC) May / 50

Mobility Models. Larissa Marinho Eglem de Oliveira. May 26th CMPE 257 Wireless Networks. (UCSC) May / 50 Mobility Models Larissa Marinho Eglem de Oliveira CMPE 257 Wireless Networks May 26th 2015 (UCSC) May 2015 1 / 50 1 Motivation 2 Mobility Models 3 Extracting a Mobility Model from Real User Traces 4 Self-similar

More information

AN AGENT-BASED APPROACH TO THE SIMULATION OF PEDESTRIAN MOVEMENT AND FACTORS THAT CONTROL IT

AN AGENT-BASED APPROACH TO THE SIMULATION OF PEDESTRIAN MOVEMENT AND FACTORS THAT CONTROL IT AN AGENT-BASED APPROACH TO THE SIMULATION OF PEDESTRIAN MOVEMENT AND FACTORS THAT CONTROL IT 1. Why another model? Planned as part of a modular model able to simulate rent rate / land value / land use

More information

Data Mining: Classifier Evaluation. CSCI-B490 Seminar in Computer Science (Data Mining)

Data Mining: Classifier Evaluation. CSCI-B490 Seminar in Computer Science (Data Mining) Data Mining: Classifier Evaluation CSCI-B490 Seminar in Computer Science (Data Mining) Predictor Evaluation 1. Question: how good is our algorithm? how will we estimate its performance? 2. Question: what

More information

Behavioral Data Mining. Lecture 9 Modeling People

Behavioral Data Mining. Lecture 9 Modeling People Behavioral Data Mining Lecture 9 Modeling People Outline Power Laws Big-5 Personality Factors Social Network Structure Power Laws Y-axis = frequency of word, X-axis = rank in decreasing order Power Laws

More information

Evolving IoT with Smart Objects

Evolving IoT with Smart Objects Evolving IoT with Smart Objects John Soldatos (jsol@ait.gr) Associate Professor Athens Information Technology isprint Workshop, Brussels, September 19th, 2017 Monolithic IoT applications (2005-2010) IoT

More information

Ad Hoc Distributed Simulation of Surface Transportation Systems

Ad Hoc Distributed Simulation of Surface Transportation Systems Ad Hoc Distributed Simulation of Surface Transportation Systems Richard Fujimoto Jason Sirichoke Michael Hunter, Randall Guensler Hoe Kyoung Kim, Wonho Suh Karsten Schwan Bala Seshasayee Computational

More information

SDN Technologies Primer: Revolution or Evolution in Architecture?

SDN Technologies Primer: Revolution or Evolution in Architecture? There is no single, clear definition of softwaredefined networking (SDN), but there are two sets of beliefs centralized control and management of packet forwarding vs. a distributed architecture. This

More information

SceneNet: 3D Reconstruction of Videos Taken by the Crowd on GPU. Chen Sagiv SagivTech Ltd. GTC 2015 San Jose

SceneNet: 3D Reconstruction of Videos Taken by the Crowd on GPU. Chen Sagiv SagivTech Ltd. GTC 2015 San Jose SceneNet: 3D Reconstruction of Videos Taken by the Crowd on GPU Chen Sagiv SagivTech Ltd. GTC 2015 San Jose Established in 2009 and headquartered in Israel Core domain expertise: GPU Computing and Computer

More information

Table of Contents 1 Introduction A Declarative Approach to Entity Resolution... 17

Table of Contents 1 Introduction A Declarative Approach to Entity Resolution... 17 Table of Contents 1 Introduction...1 1.1 Common Problem...1 1.2 Data Integration and Data Management...3 1.2.1 Information Quality Overview...3 1.2.2 Customer Data Integration...4 1.2.3 Data Management...8

More information

Application Layer Switching: A Deployable Technique for Providing Quality of Service

Application Layer Switching: A Deployable Technique for Providing Quality of Service Application Layer Switching: A Deployable Technique for Providing Quality of Service Raheem Beyah Communications Systems Center School of Electrical and Computer Engineering Georgia Institute of Technology

More information

Virginia Tech Research Center Arlington, Virginia, USA

Virginia Tech Research Center Arlington, Virginia, USA SMART BUILDINGS AS BUILDING BLOCKS OF A SMART CITY Professor Saifur Rahman Virginia Tech Advanced Research Institute Electrical & Computer Engg Department University of Sarajevo Bosnia, 06 October, 2016

More information

Chapter Outline. Chapter 2 Distributed Information Systems Architecture. Layers of an information system. Design strategies.

Chapter Outline. Chapter 2 Distributed Information Systems Architecture. Layers of an information system. Design strategies. Prof. Dr.-Ing. Stefan Deßloch AG Heterogene Informationssysteme Geb. 36, Raum 329 Tel. 0631/205 3275 dessloch@informatik.uni-kl.de Chapter 2 Distributed Information Systems Architecture Chapter Outline

More information

Automatic visual recognition for metro surveillance

Automatic visual recognition for metro surveillance Automatic visual recognition for metro surveillance F. Cupillard, M. Thonnat, F. Brémond Orion Research Group, INRIA, Sophia Antipolis, France Abstract We propose in this paper an approach for recognizing

More information

Object-Based Classification & ecognition. Zutao Ouyang 11/17/2015

Object-Based Classification & ecognition. Zutao Ouyang 11/17/2015 Object-Based Classification & ecognition Zutao Ouyang 11/17/2015 What is Object-Based Classification The object based image analysis approach delineates segments of homogeneous image areas (i.e., objects)

More information

Application of SDN: Load Balancing & Traffic Engineering

Application of SDN: Load Balancing & Traffic Engineering Application of SDN: Load Balancing & Traffic Engineering Outline 1 OpenFlow-Based Server Load Balancing Gone Wild Introduction OpenFlow Solution Partitioning the Client Traffic Transitioning With Connection

More information

Latent Space Model for Road Networks to Predict Time-Varying Traffic. Presented by: Rob Fitzgerald Spring 2017

Latent Space Model for Road Networks to Predict Time-Varying Traffic. Presented by: Rob Fitzgerald Spring 2017 Latent Space Model for Road Networks to Predict Time-Varying Traffic Presented by: Rob Fitzgerald Spring 2017 Definition of Latent https://en.oxforddictionaries.com/definition/latent Latent Space Model?

More information

NoSQL systems: introduction and data models. Riccardo Torlone Università Roma Tre

NoSQL systems: introduction and data models. Riccardo Torlone Università Roma Tre NoSQL systems: introduction and data models Riccardo Torlone Università Roma Tre Leveraging the NoSQL boom 2 Why NoSQL? In the last fourty years relational databases have been the default choice for serious

More information

Improving the Performance of Partitioning Methods for Crowd Simulations

Improving the Performance of Partitioning Methods for Crowd Simulations Eighth International Conference on Hybrid Intelligent Systems Improving the Performance of Partitioning Methods for Crowd Simulations G. Vigueras, M. Lozano, J. M. Orduña and F. Grimaldo Departamento de

More information

USE CASES BROADBAND AND MEDIA EVERYWHERE SMART VEHICLES, TRANSPORT CRITICAL SERVICES AND INFRASTRUCTURE CONTROL CRITICAL CONTROL OF REMOTE DEVICES

USE CASES BROADBAND AND MEDIA EVERYWHERE SMART VEHICLES, TRANSPORT CRITICAL SERVICES AND INFRASTRUCTURE CONTROL CRITICAL CONTROL OF REMOTE DEVICES 5g Use Cases BROADBAND AND MEDIA EVERYWHERE 5g USE CASES SMART VEHICLES, TRANSPORT CRITICAL SERVICES AND INFRASTRUCTURE CONTROL CRITICAL CONTROL OF REMOTE DEVICES HUMAN MACHINE INTERACTION SENSOR NETWORKS

More information

The Repast Simulation/Modelling System for Geospatial Simulation. Andrew Crooks. CASA University College London 1-19 Torrington Place London

The Repast Simulation/Modelling System for Geospatial Simulation. Andrew Crooks. CASA University College London 1-19 Torrington Place London The Repast Simulation/Modelling System for Geospatial Simulation Andrew Crooks CASA University College London 1-19 Torrington Place London http://www.casa.ucl.ac.uk http://www.gisagents.blogspot.com Introduction

More information

Mobile Offloading. Matti Kemppainen

Mobile Offloading. Matti Kemppainen Mobile Offloading Matti Kemppainen kemppi@cs.hut.fi 1. Promises and Theory Learning points What is mobile offloading? What does offloading promise? How does offloading differ from earlier practices? What

More information

CPSC / Sonny Chan - University of Calgary. Collision Detection II

CPSC / Sonny Chan - University of Calgary. Collision Detection II CPSC 599.86 / 601.86 Sonny Chan - University of Calgary Collision Detection II Outline Broad phase collision detection: - Problem definition and motivation - Bounding volume hierarchies - Spatial partitioning

More information

R07. FirstRanker. 7. a) What is text mining? Describe about basic measures for text retrieval. b) Briefly describe document cluster analysis.

R07. FirstRanker. 7. a) What is text mining? Describe about basic measures for text retrieval. b) Briefly describe document cluster analysis. www..com www..com Set No.1 1. a) What is data mining? Briefly explain the Knowledge discovery process. b) Explain the three-tier data warehouse architecture. 2. a) With an example, describe any two schema

More information

Robot Motion Planning

Robot Motion Planning Robot Motion Planning James Bruce Computer Science Department Carnegie Mellon University April 7, 2004 Agent Planning An agent is a situated entity which can choose and execute actions within in an environment.

More information

Interactive Analysis of Large Distributed Systems with Scalable Topology-based Visualization

Interactive Analysis of Large Distributed Systems with Scalable Topology-based Visualization Interactive Analysis of Large Distributed Systems with Scalable Topology-based Visualization Lucas M. Schnorr, Arnaud Legrand, and Jean-Marc Vincent e-mail : Firstname.Lastname@imag.fr Laboratoire d Informatique

More information

A distributed architecture to support infomobility services. University of Modena and Reggio Emilia

A distributed architecture to support infomobility services. University of Modena and Reggio Emilia A distributed architecture to support infomobility services Claudia Canali Riccardo Lancellotti University of Modena and Reggio Emilia Motivation Web 1.0 Static Web pages Information repository Limited

More information

BSC Smart Cities Initiative

BSC Smart Cities Initiative www.bsc.es BSC Smart Cities Initiative José Mª Cela CASE Director josem.cela@bsc.es CITY DATA ACCESS 2 City Data Access 1. Standardize data access (City Semantics) Define a software layer to keep independent

More information

A P2P REcommender system based on Gossip Overlays (PREGO)

A P2P REcommender system based on Gossip Overlays (PREGO) 10 th IEEE INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATION TECHNOLOGY Bradford,UK, 29 June - 1 July, 2010 Ranieri Baraglia, Patrizio Dazzi, Matteo Mordacchini ISTI,CNR, Pisa,Italy Laura Ricci University

More information

Locally Weighted Learning for Control. Alexander Skoglund Machine Learning Course AASS, June 2005

Locally Weighted Learning for Control. Alexander Skoglund Machine Learning Course AASS, June 2005 Locally Weighted Learning for Control Alexander Skoglund Machine Learning Course AASS, June 2005 Outline Locally Weighted Learning, Christopher G. Atkeson et. al. in Artificial Intelligence Review, 11:11-73,1997

More information

Automatic Scaling Iterative Computations. Aug. 7 th, 2012

Automatic Scaling Iterative Computations. Aug. 7 th, 2012 Automatic Scaling Iterative Computations Guozhang Wang Cornell University Aug. 7 th, 2012 1 What are Non-Iterative Computations? Non-iterative computation flow Directed Acyclic Examples Batch style analytics

More information

Load Balancing and Data Migration in a Hybrid Computational Fluid Dynamics Application

Load Balancing and Data Migration in a Hybrid Computational Fluid Dynamics Application Load Balancing and Data Migration in a Hybrid Computational Fluid Dynamics Application Esteban Meneses Patrick Pisciuneri Center for Simulation and Modeling (SaM) University of Pittsburgh University of

More information

Introduction to Objective Analysis

Introduction to Objective Analysis Chapter 4 Introduction to Objective Analysis Atmospheric data are routinely collected around the world but observation sites are located rather randomly from a spatial perspective. On the other hand, most

More information

Applications. Oversampled 3D scan data. ~150k triangles ~80k triangles

Applications. Oversampled 3D scan data. ~150k triangles ~80k triangles Mesh Simplification Applications Oversampled 3D scan data ~150k triangles ~80k triangles 2 Applications Overtessellation: E.g. iso-surface extraction 3 Applications Multi-resolution hierarchies for efficient

More information

Mobility Data Management & Exploration

Mobility Data Management & Exploration Mobility Data Management & Exploration Ch. 07. Mobility Data Mining and Knowledge Discovery Nikos Pelekis & Yannis Theodoridis InfoLab University of Piraeus Greece infolab.cs.unipi.gr v.2014.05 Chapter

More information

Systematic Cooperation in P2P Grids

Systematic Cooperation in P2P Grids 29th October 2008 Cyril Briquet Doctoral Dissertation in Computing Science Department of EE & CS (Montefiore Institute) University of Liège, Belgium Application class: Bags of Tasks Bag of Task = set of

More information

Extracting Rankings for Spatial Keyword Queries from GPS Data

Extracting Rankings for Spatial Keyword Queries from GPS Data Extracting Rankings for Spatial Keyword Queries from GPS Data Ilkcan Keles Christian S. Jensen Simonas Saltenis Aalborg University Outline Introduction Motivation Problem Definition Proposed Method Overview

More information

Junichi Suzuki, Member, IEEE, and Tatsuya Suda, Fellow, IEEE. 1 The Bio-Networking Architecture was first proposed in [2], later adopted by

Junichi Suzuki, Member, IEEE, and Tatsuya Suda, Fellow, IEEE. 1 The Bio-Networking Architecture was first proposed in [2], later adopted by IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, VOL. 23, NO. 2, FEBRUARY 2005 249 A Middleware Platform for a Biologically Inspired Network Architecture Supporting Autonomous and Adaptive Applications

More information

Data Center Services and Optimization. Sobir Bazarbayev Chris Cai CS538 October

Data Center Services and Optimization. Sobir Bazarbayev Chris Cai CS538 October Data Center Services and Optimization Sobir Bazarbayev Chris Cai CS538 October 18 2011 Outline Background Volley: Automated Data Placement for Geo-Distributed Cloud Services, by Sharad Agarwal, John Dunagan,

More information

Peer-to-Peer Systems. Chapter General Characteristics

Peer-to-Peer Systems. Chapter General Characteristics Chapter 2 Peer-to-Peer Systems Abstract In this chapter, a basic overview is given of P2P systems, architectures, and search strategies in P2P systems. More specific concepts that are outlined include

More information

Lecture 6: Input Compaction and Further Studies

Lecture 6: Input Compaction and Further Studies PASI Summer School Advanced Algorithmic Techniques for GPUs Lecture 6: Input Compaction and Further Studies 1 Objective To learn the key techniques for compacting input data for reduced consumption of

More information

RSM Split-Plot Designs & Diagnostics Solve Real-World Problems

RSM Split-Plot Designs & Diagnostics Solve Real-World Problems RSM Split-Plot Designs & Diagnostics Solve Real-World Problems Shari Kraber Pat Whitcomb Martin Bezener Stat-Ease, Inc. Stat-Ease, Inc. Stat-Ease, Inc. 221 E. Hennepin Ave. 221 E. Hennepin Ave. 221 E.

More information

The 7 deadly sins of cloud computing [2] Cloud-scale resource management [1]

The 7 deadly sins of cloud computing [2] Cloud-scale resource management [1] The 7 deadly sins of [2] Cloud-scale resource management [1] University of California, Santa Cruz May 20, 2013 1 / 14 Deadly sins of of sin (n.) - common simplification or shortcut employed by ers; may

More information

GPU-based Distributed Behavior Models with CUDA

GPU-based Distributed Behavior Models with CUDA GPU-based Distributed Behavior Models with CUDA Courtesy: YouTube, ISIS Lab, Universita degli Studi di Salerno Bradly Alicea Introduction Flocking: Reynolds boids algorithm. * models simple local behaviors

More information

ELECTRICITY SUPPLY SYSTEMS OF THE FUTURE

ELECTRICITY SUPPLY SYSTEMS OF THE FUTURE ELECTRICITY SUPPLY SYSTEMS OF THE FUTURE Rob Stephen President Cigre AFSEC conference March 2017 CIGRE Founded in 1921, CIGRE, the Council on Large Electric Systems, Our Mission:To be the world s foremost

More information

IT Level Power Provisioning Business Continuity and Efficiency at NTT

IT Level Power Provisioning Business Continuity and Efficiency at NTT IT Level Power Provisioning Business Continuity and Efficiency at NTT Henry M.L. Wong Intel Eco-Technology Program Office Environment Global CO 2 Emissions ICT 2% 98% Source: The Climate Group Economic

More information

Tensor Based Approaches for LVA Field Inference

Tensor Based Approaches for LVA Field Inference Tensor Based Approaches for LVA Field Inference Maksuda Lillah and Jeff Boisvert The importance of locally varying anisotropy (LVA) in model construction can be significant; however, it is often ignored

More information

Open mustard seed. Patrick Deegan, Ph.D. ID3

Open mustard seed. Patrick Deegan, Ph.D. ID3 Open mustard seed Patrick Deegan, Ph.D. ID3 OpenSocial FSN (draft) August 8, 2013 Open Mustard Seed (OMS) Introduction The OMS Trustworthy Compute Framework (TCF) extends the core functionality of Personal

More information

Demystifying the Cloud With a Look at Hybrid Hosting and OpenStack

Demystifying the Cloud With a Look at Hybrid Hosting and OpenStack Demystifying the Cloud With a Look at Hybrid Hosting and OpenStack Robert Collazo Systems Engineer Rackspace Hosting The Rackspace Vision Agenda Truly a New Era of Computing 70 s 80 s Mainframe Era 90

More information

Diffusing Your Mobile Apps: Extending In-Network Function Virtualisation to Mobile Function Offloading

Diffusing Your Mobile Apps: Extending In-Network Function Virtualisation to Mobile Function Offloading Diffusing Your Mobile Apps: Extending In-Network Function Virtualisation to Mobile Function Offloading Mario Almeida, Liang Wang*, Jeremy Blackburn, Konstantina Papagiannaki, Jon Crowcroft* Telefonica

More information

Computer Experiments: Space Filling Design and Gaussian Process Modeling

Computer Experiments: Space Filling Design and Gaussian Process Modeling Computer Experiments: Space Filling Design and Gaussian Process Modeling Best Practice Authored by: Cory Natoli Sarah Burke, Ph.D. 30 March 2018 The goal of the STAT COE is to assist in developing rigorous,

More information