Download presentation
Presentation is loading. Please wait.
1
Elke A. Rundensteiner Database Systems Research Group Email: rundenst@cs.wpi.edurundenst@cs.wpi.edu Office: Fuller 238 Phone: Ext. – 5815 WebPages: http://www.cs.wpi.edu/~rundenst http://davis.wpi.edu/dsrg
2
CAPE : Engine for Querying and Monitoring Streaming Data Example of Stream Data Applications: Market Analysis –Streams of Stock Exchange Data - get rich Critical Care –Streams of Vital Sign Measurements – save lives Physical Plant Monitoring –Streams of Environmental Readings – protect env data Query data streams of data static data Standing queries one-time queries
3
Stream Query Monitoring Projects CAPE Query Engine Load Spiller Service (JAVA): Service for run-time spill/unspill services for a complete query plan Design query policies, operator data structures, algorithms Implement in CAPE engine, conduct experiments Event Pattern Monitoring Engine Support Sequence Queries and Extend to more Complex AND/OR Patterns Handle out-of-order event input arrivals by either logging and result-correction or by exploiting predicting meta-data messages Scale to support multiple event queries RFID Data Service Install actual RFID equipment in some campus environment Support simple data collection and tracking queries, of either goods or people Handling missing values or clean-up errors using domain knowledge Visual Stream Monitoring Tool Target a real stream application, such as flow simulation tool Develop algorithms for multi-resolution data aggregation in time and space Support visual query refinement of asking about a particular object or region CAPE Query Engine Load Spiller Service (JAVA): Service for run-time spill/unspill services for a complete query plan Design query policies, operator data structures, algorithms Implement in CAPE engine, conduct experiments Event Pattern Monitoring Engine Support Sequence Queries and Extend to more Complex AND/OR Patterns Handle out-of-order event input arrivals by either logging and result-correction or by exploiting predicting meta-data messages Scale to support multiple event queries RFID Data Service Install actual RFID equipment in some campus environment Support simple data collection and tracking queries, of either goods or people Handling missing values or clean-up errors using domain knowledge Visual Stream Monitoring Tool Target a real stream application, such as flow simulation tool Develop algorithms for multi-resolution data aggregation in time and space Support visual query refinement of asking about a particular object or region
4
Acquisition: Brand New Purchase of 20-Node High-Performance PC Cluster (Rundensteiner/Mani/Heineman – NSF ) Project 1: Implement and evaluate allocation/re- allocation algorithms for assigning stream query nodes to processor Project 2: Implement and compare two solutions for migrating at run-time query plans into new rewritten plans Project 3: Develop launch-pad for statistics monitoring for monitoring DCAPE experiments Acquisition: Brand New Purchase of 20-Node High-Performance PC Cluster (Rundensteiner/Mani/Heineman – NSF ) Project 1: Implement and evaluate allocation/re- allocation algorithms for assigning stream query nodes to processor Project 2: Implement and compare two solutions for migrating at run-time query plans into new rewritten plans Project 3: Develop launch-pad for statistics monitoring for monitoring DCAPE experiments PC-Cluster Java Applications
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.