Faculty Members to Present Four Papers at SIGMOD/PODS 2013

ISTC for Big Data faculty members will present four papers at the 2013 ACM SIGMOD/PODS Conference, June 22-27, 2013, in New York City.   SIGMOD/PODS is a leading international conference about the theoretical aspects of databases, and annually showcases papers of interest chosen through a broad submission and rigorous selection process.

“Toward Practical Query Pricing with QueryMarket.”  Paraschos Koutris, Prasang Upadhyaya, Magdalena Balazinska, Bill Howe, and Dan Suciu, University of Washington

The authors develop a pricing system, “QueryMarket,” for flexible query pricing in a data market (on the theoretical framework of Koutris et al., PODS 2012). They show how to use an Integer Linear Programming formulation of the pricing problem for a large class of queries, even when pricing is computationally hard. QueryMarket can prevent double charging and can fairly share revenue among multiple sellers. The authors build a prototype and evaluate its performance.

“Performance and Resource Modeling in Highly-Concurrent OLTP Workloads.”   Barzan Mozafari of MIT CSAIL; Carlo Curino of Microsoft; Alekh Jindal of MIT CSAIL; and Samuel Madden of MIT CSAIL.

DBAs of OLTP systems constantly face difficult questions such as, “What is the maximum throughput I can sustain with my current hardware?” Resource prediction and performance analysis are difficult due to high degrees of concurrency, competition for resources, and complex interactions between transactions. The authors introduce a framework, “DBSeer,” that employs statistical models for answering such questions in highly concurrent OLTP workloads, with accuracy within a few percent.

“A Vision for Personalized Service Level Agreements in the Cloud.”  Jennifer Ortiz, Computer Science and Engineering Department, University of Washington; Victor Teixeira de Almeida, PETROBRAS S.A., Rio de Janeiro, RJ, Brazil; and Magdalena Balazinska, Computer Science and Engineering Department, University of Washington.

For public clouds, the authors propose a “Personalized Service Level Agreement” defining what users can do in terms of query capabilities, guaranteed query performance, and fixed hourly prices – thereby making it easier for users to select a service, pick a configuration, and predict the actual analysis cost. In contrast, current pricing models and SLAs specify levels of compute resources and vary from one service to the next.

“The Power of Data Use Management in Action.”  Prasang Upadhyaya, Nick Anderson, Magdalena Balazinska, and Bill Howe of the University of Washington; Raghav Kaushik and Ravi Ramamurthy of Microsoft; and Dan Suciu of the University of Washington.

The authors demonstrate a database management system extended with a new type of component that they call a “Data Use Manager” (DUM), which enables DBAs to attach policies to data loaded into the DBMS. The DUM monitors how users query the data, flags potential policy violations, recommends possible fixes, and supports offline analysis of user activities related to data policies.

In addition, ISTC for Big Data co-director Mike Stonebraker of MIT CSAIL will be moderating a panel of database community leaders presenting the provocatively titled paper “We are Drowning in a Sea of Least Publishable Units (LPUs).”  The authors’ assertion:  “In order to improve the quality of the papers being published, we must reduce the number being submitted” [to database conferences]. Dr. Stonebraker’s co-authors (and panelists) are Microsoft Technical Fellow David DeWitt; Jeff Naughton, professor at the University of Wisconsin-Madison; and Ihab Ilyas, a principal scientist at the Qatar Computing Research Institute and an associate professor of computer science at the University of Waterloo.

June 28, 2013 Update:  ISTC for Big Data co-director Sam Madden (now of MIT CSAIL) and his co-authors/-developers at the University of California, Berkeley and Intel Research were honored this week when their 2003 SIGMOD paper, “The Design of An Acquisitional Query Processor for Sensor Networks,” received the 2013 SIGMOD Test of Time Award. The paper described a novel technique for acquisitional query processing (ACQP) in wireless sensor networks (WSNs), and its design and implementation in the TinyDB system.

About SIGMOD 

The ACM Special Interest Group on Management of Data (SIGMOD) is concerned with the principles, techniques and applications of database management systems and data management technology. Its members include software developers, academic and industrial researchers, practitioners, users, and students.

 

 

This entry was posted in Big Data Architecture, Data Management, DBMS, ISTC for Big Data Blog, Tools for Big Data and tagged , , , . Bookmark the permalink.

Leave A Reply

Your email address will not be published. Required fields are marked *


8 + = fifteen