250 likes | 386 Vues
This presentation by Emma Buneci discusses the LEAD project and highlights critical advancements in self-managing systems relevant to weather and IT. It covers dynamic adaptations in weather forecasting, ensemble forecasting, and the architecture of adaptive cyber-infrastructure. The discussion emphasizes the challenges faced in managing these systems, particularly in large-scale networks and supercomputing environments, while sharing lessons learned that can inform similar infrastructures in various domains. The future impact of LEAD on weather systems and technology is explored as well.
E N D
LEAD Project Discussion Presented by: Emma Buneci for CPS 296.2: Self-Managing Systems Source for many slides: Kelvin Droegemeier, Year 2 site visit presentation.
The Case for Dynamic Adaptation • Adaptation in Time • Adaptation in Space • Ensemble Forecasting • Adaptive Observing Systems • Adaptive Cyber-infrastructure • Managing Forecast and Simulation Process
Managing the Forecast & Simulation Process • Current State: 50,000 lines of Perl code. • In Progress: LEAD Workflow Environment
LEAD Service Oriented Architecture Desktop Applications • IDV • WRF Configuration GUI User Interface LEAD Portal Crosscutting Services Why A Service-Oriented Architecture? • Flexible and malleable • Platform independence (emphasis on protocols, not platforms) • Loose integration via modularity • Evolvable and re-usable (e.g. Java) • Interoperable by use of standards robustness Control Education Browse Workflow Visualization Portlets MyLEAD Monitor Control Query Ontology Client Interface Workflow Monitor Application Resource Broker (Scheduler) Stream Service Control Service Authorization Workflow Services Workflow Engine/Factories Ontology Service Query Service Application & Configuration Services Configuration and Execution Services Data Services Execution Description Host Environment Authentication Decoder/Resolver Service Transcoder Service/ ESML VO Catalog Application Description Application Host Catalog Services WRF, ADaM, IDV, ADAS THREDDS GPIR Geo-Reference GUI Monitoring Resource Access Services OPenDAP Scheduler Grid FTP Generic Ingest Service OGSA-DAI RLS LDM SSH GRAM Notification Observations • Streams • Static • Archived Data Bases Distributed Resources Steerable Instruments Specialized Applications Computation Storage Source: LEAD Team
Some Discussion Points • Complexity of the infrastructure to support LEAD • Lesson learned: viable solution where small number of services are persistent; remaining are on-demand • Challenges for the system administrators • Large scale networks, supercomputers; different for sys. Admins in industry setting? • What lessons from this experiment will apply to building similar infrastructures in other domains • Future impact of LEAD