Over the past several years, Cloud Data Services have been gaining increased popularity both in industry and in the research community. While several successful services are now commercially available, many questions remain open as to how we should be building such services. There are at least two major directions for such services. First, Database-as-a-Service (DaaS) functionality, which is being offered commercially, provides the ability to leverage data management functionality in the cloud. Second, there is also increasing interest in exploring various novel architectures for large-scale distributed data analytics platform (in addition to traditional SQL based infrastructures) in private as well as public clouds. Effective cloud data services must be able to support low manageability cost, fault tolerance, pay-as-you-go pricing, geo-replication, performance, scale, and other features that can be challenging to achieve at the same time.
The goal of this summer institute is to identify and discuss the technical challenges that the above systems need to address. We are bringing together researchers and practitioners from diverse but relevant areas such as database systems, distributed systems and machine learning to discuss the state-of-the-art and identify directions for future research and collaboration. Some examples of topics we will explore include:
Descriptions of past summer institutes may be viewed at: www.cs.washington.edu/mssi/.