Adaptive Replication and Partitioning in Data Systems

Organizers: Brad Glasbergen, Michael Abebe and Khuzaima Daudjee (Waterloo University).

Driven by enterprise and individual needs, big data applications are placing ever increasing demands on data systems. There are two primary means of scaling systems that manage data: replication and partitioning. Replication creates replicas of data or services and spreads them across a pool of machines. Conversely, partitioning splits data or services across multiple machines, enabling requests to be processed in parallel. In this tutorial, we will focus on intelligent and adaptive data replication and partitioning strategies; that is, methods of spreading data across a pool of machines to increase scalability and performance.

The target audience of this tutorial is systems researchers and practitioners that have a basic knowledge of distributed data management. Some knowledge of data replication and partitioning is helpful, but is not necessary. For newcomers to the area, this tutorial will introduce replication and partitioning, and motivate adaptive replication and partitioning of data. For researchers that are experienced with replication and partitioning, this tutorial will provide a broader view of the common approaches to providing adaptivity in these systems and offer suggestions on how current techniques can be improved.

Blockchain Landscape and AI Renaissance: The Bright Path Forward

Organizers: Hans-Arno Jacobsen, Mohamad Sadoghi, Mohammad H. Tabatabaei, Roman Vitenberg and Kaiwen Zhang