Distributed Diagnostics on the Grid: DAME Progress Report

1
Distributed Diagnostics onthe Grid
DAMEProgress Report

• Professor Jim Austin/Tom Jackson
• University of York

2
Project Partners

• EPSRC Funded, 3.2 Million, 3 years, commenced
  Jan 2002.
• UK pilot project for e-Science
• 4 Universities
• University of York, Dept of Computer Science
• University of Sheffield, Dept of Automatic
  Control and Systems Engineering
• University of Oxford, Dept of Engineering Science
• University of Leeds, School of Computing and
  School of Mechanical Engineering
• Industrial Partners
• Rolls-Royce
• Data Systems and Solutions
• Cybula Ltd

3
Operational Scenario
Engine flight data
London Airport
Airline office
New York Airport
Grid
Diagnostics Centre
Maintenance Centre
American data center
European data center
4
DAME Grid Challenges

• Building a demonstration system as proof of
  concept for Grid technology in the aerospace
  diagnostic domain.
• Two primary Grid challenges
• Management of large, distributed and
  heterogeneous data repositories
• Rapid data mining and analysis of fault data
• Other key (commercial) issues
• Remote, secure access to flight data and other
  operational data and resources
• Management of distributed users and resources
• Quality of Service issues (and Service Level
  Agreements)

5
Progress March 2004

• Mid term demo completed Aug 2003.
• Main thrust since then has been to
• Develop services
• Develop data and services infrastructure
• Work on Dependability and Security
• System middleware SLA, workflow engine
• Publish papers!
• Gain acceptance of commercial users in technology

6
Demonstrator

• Fully operational system on the WRG
• Demonstrated the basic system architecture and
  main services

7
Services Data Management and Search

• Data management and searching is the main
  challenge within DAME
• Main aim is to manage gt1Tb per year of Aero
  Engine vibration and maintenance data.
• A data architecture has been defined based on
  Globus and SRB.
• Interlinks with search and reasoning services.

8
DAME Data Architecture
9
Service - Engine Data Explorer

• EDE Data visualisation and search control
• Need to allow users to view and search data
• Built on top of the York/Cybula AURA technology
• Directs search via the DAME data architecture

10
Services Engine Data Explorer
11
Services Engine model

• The engine simulation
• Aims to model correct engine operation.
• As Grid services
• GSI enabled secure engine performance simulation
• a number simulation instances generated by the
  factory service different engine simulation can
  be performed simultaneously
• Only lightweight computers or PDAs are needed to
  perform the engine simulation, while still
  benefit from high-performance/high-throughput
  computing power provided by the Grid

12
Services Engine model
13
Services Case Based Reasoning

• CBR Maintenance Advisor Service
• Integrates fault information and knowledge gained
  from fault diagnosis process
• Advises maintenance personnel on appropriate
  maintenance action
• Deployed as a Grid service on the Grid
• Accessible by user via a web browser across the
  Internet
• Secure access with X.509 user and host
  authentication, SSL encryption.

14
Services - CBR
15
Services Workflow advisor

• Workflow advisor
• Provides workflow advice and workflow scripts for
  diagnosing faults based on case history of DAME
  usage
• Captures domain expert knowledge and offers
  knowledge-based search across complex workflow
  information
• Integrated with CBR system
• Builds on the research work on provenance data

16
Services Workflow advisor
Maintenance Engineers Domain Experts
17
DAME Provenance Architecture
Workflow Definition (BPEL)
18
Services XTO advisor

• Grid based deployment of the vibration analysis
  algorithms
• Provides
• Opportunity for finer grain analysis
• More powerful algorithms
• Testing environment fordevelopment of
  newalgorithms
• Working on integration of more complex algorithms
  for engine modelling based on fusion of
  performance and vibration data.

19
Services XTO advisor
20
Middleware Work flow Manager

• Management of services
• Services are managed at the portalvia a Workflow
  Engine
• Workflow Engine providesmanagement of manual
  andautomated workflows.
• Also handles certificationand role management

21
Middleware Work flow Manager
Browser
Portal
Role
MyProxy
Database
Server
Workflow
Workflow
Event
Credential
Manager
Generator
Engine
Engine
SDM to
XTO
CBR
Aura-G
Data Store
Model
XTO
Broker
22
Middleware Brokerage SLA
Brokerage system is used for job allocation on
available Grid resource

• Due to commercial application domain, broker
  should also demonstrate capability to manage QoS
  issues, and specifically Service Level Agreements
  (SLAs)
• Integrates with GGF Grid Economic Architecture

23
Dependability and Security

• Contribute to the GRID community dependability
  and security studies, where possible.
• Provide dependability and security analysis to
  support the ultimate deployment of DAME as a
  working engine diagnosis environment.
• If possible, provide a basis (identify good
  practices) for dependability and security
  analysis for the deployment of DAME as a working
  diagnosis environment for other domains e.g.
  medical.
• Dependability analysis has meant need for
  business process analysis, asset identification,
  risk identification.

24
Commercial take-up

• Rolls-Royce evaluating DAME system in Engine Pass
  off testing.
• DSS and Cybula starting to develop markets for
  EDE system and data management system.

25
Final Demonstrator

• Final demonstrator will act as a more explicit
  vehicle for demonstration of core research
  activities
• Distributed Data Management and SRB
• Job brokerage
• Time-series pattern matching and data-mining
• QoS and SLAs
• Security management
• Workflow capture and provenance systems
• Will drive studies on business case for
  commercial deployment of the DAME system

26
Georges Honoré (L) Alison McKay (L) Sarfraz
Nadeem (L) Paul Hayton (O) Lionel Tarassenko
(O) Simukai Utete (O) Jeff Allan (S) Peter
Fleming (S) V. Kadirkamanathan (S) Max Ong
(S) Xiaoxu Ren (S) Vernon Bailey (O)
Haydn Thompson (S) Rob Davis (Y) Martyn Fletcher
(Y) Tom Jackson (Y) Mark Jessop (Y) Julian Young
(Y) Bojian Liang (Y) John McDermid (Y) Andy
Wellings (Y) Andy Pasley (Y) PhDs.
Paul Anuzis (RR) Peter Cowley (RR) Graham Hesketh
(RR) Jack Crawford (RR) Charlie Dibsdale
(DSS) Paul Irving (DSS) Peter Lobner
(DSS) Richard Bagshaw (L) Pete Dawson (L) Peter
Dew (L) Karim Djemame (L) Iain Gourlay (L)
Thanks!