Business Model With Alternative Scenarios (D4.1)

Jakob Luettgau, Julian Kunkel, Jens Jensen, Bryan Lawrence
2017 Zenodo  
This report summarizes the work on requirements and business models for the storage infrastructure within weather and climate data centres (although much of the work has wider applicability). The report concentrates on identifying and evaluating the interplay of important cost factors, along with an introduction to relevant (storage and data movement) hardware and software technology, terminology and performance metrics. The report begins with a description of how climate and weather
more » ... s make use of HPC systems, the arising challenges and data requirements, and some trends that are likely to impact future data centre designs. Related work follows that introduces some cost developments, cost modelling and technological developments. The body of the work is an integrated graph-based approach to modelling costs, resilience and performance for storage systems. Storage models are evaluated in several scenarios each introducing some architectural changes to currently deployed high-performance systems and discusses the cost and performance implications. These discussions are made on a high-level of abstraction as no model is able to predict the non-linear behaviour when scaling out big systems accurately. Conclusions identify the potential benefits that more refined models might offer and outline future work. About this document Work package in charge: WP4 Exploitability Actual delivery date for this deliverable: 24 February 2017 Dissemination level: PU (for public use) Lead author: Deutsches Klimarechenzentrum (DKRZ), Jakob Luettgau Other contributing authors: Deutsches Klimarechenzentrum (DKRZ), Julian Kunkel, Jakob Luettgau Science and Technology Facilities Council (STFC), Jens Jensen The University of Reading (UREAD), and Science and Technology Facilities Council (STFC), Bryan Lawrence
doi:10.5281/zenodo.1228749 fatcat:fdwtwtfcwjhhbkiusam6njs26a