Humans in the Loop: Enabling and Facilitating Research on Cloud Computing
This workshop explores the important role of humans, in support roles, in making cloud computing useful in research settings. Cloud computing is clearly a type of cyberinfrastructure, which workshop organizer Craig Stewart defines as comprising “computing systems, data storage systems, advanced instruments and data repositories, visualization environments, and people, all linked together by software and high performance networks to improve research productivity and enable breakthroughs not otherwise possible" (2017). This workshop will focus on the "and people" part of cyberinfrastructure, and in particular on the role of people in supporting the use of commercial cloud resources in research.
The overall goal of this workshop is to share information about best practices, successes, and challenges in supporting research use of commercial clouds. To accomplish this, we will:
- Provide detailed, concrete examples of the effective use of cloud computing, comparing and contrasting use of cloud resources with traditional campus and national infrastructure alternatives.
- Provide a forum for a free exchange of ideas, challenges, and best-practices in supporting the use of commercial cloud computing in advancing research across many disciplines.
- Foster networking among attendees, broadening the impact of efforts to put greater emphasis on the human component of cyberinfrastructure, including Campus Champions, CaRCC (the Campus Research Computing Consortium), and a new effort led by IU called Humanware; working to build a larger and more effective community of experts.
The format of presentations for the day will be:
- Introductory talk by Craig Stewart and Brian Voss
- A mixture of talks by accepted participants and CSREs
- An ending panel to discuss lessons learned and share information
Papers/presentations may address any topic related to how the support of people (humanware) has advanced research/researcher use of cloud computing platforms. Such topics could include:
- Addressing and overcoming challenges with the offerings of various cloud computing platforms
- Compare and contrast the support required for using cloud computing resources versus on-premise cyberinfrastructure and resources available through regional/national compute centers
- Examples of specific research projects that make effective use of cloud computing
- Critiques of the service and support offerings of cloud computing platforms and providers – what are these providers doing well and in what areas must improvement/enhancement be made?
- Analyses of the costs of research use of cloud computing platforms and the impact on grant funding resources and policies
- Examination of strategies for support of research at institutions facing budgetary challenges with providing sufficient on-premise cyberinfrastructure
We are interested in papers about people facilitating the use of clouds in research: what people do, how they do it, and observations on how important it is for people to have help in order to make effective use of clouds. We want to have discussions about what the XSEDE community, campus champions, and research facilitators are all very good at.
We’re doing a couple of novel things for this workshop. First, we’re going to have a draft of the proceedings at the workshop and then let authors revise their paper and submit final, camera-ready versions a couple of weeks after the workshop is over. This way people can revise their papers after they have had a chance to learn from other presentations and from the feedback they get at the workshop. Second, we are going to allow people to create and present a poster and have a four-page paper in the proceedings. The proceedings will be peer reviewed and will be carried in the ACM online library.
We are happy to review working drafts so long as they are solid enough to be reviewable. We are also happy to review a four-page version of a paper with a comment that the submitters plan to flesh the paper out to a full eight pages, or if you want to do a poster and a four-page paper, rather than a talk, we’re happy to review four-page papers.
This is an area where we expect everyone to learn from each other, and we are trying to manage the workshop processes in ways that will enable that.
Papers may be of any length, but proposed presentations at the workshop must be delivered (including time for Q&A with workshop participants) in 20 minutes or less.
Selected participants may be asked to join the end-of-workshop panel by invitation of the workshop sponsors.